{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.9518738215277047, "eval_steps": 50.0, "global_step": 30150, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 6.474010892523326e-05, "grad_norm": 1.419605016708374, "learning_rate": 9.99999997414816e-06, "loss": 1.1176714897155762, "step": 1, "token_acc": 0.7241750491815448 }, { "epoch": 0.00032370054462616633, "grad_norm": 0.6177670955657959, "learning_rate": 9.999999353704e-06, "loss": 0.9963289499282837, "step": 5, "token_acc": 0.7254535994780612 }, { "epoch": 0.0006474010892523327, "grad_norm": 0.6848709583282471, "learning_rate": 9.999997414816162e-06, "loss": 0.9509101867675781, "step": 10, "token_acc": 0.726653069987119 }, { "epoch": 0.000971101633878499, "grad_norm": 0.4581913352012634, "learning_rate": 9.999994183336991e-06, "loss": 0.9750848770141601, "step": 15, "token_acc": 0.7190706334429346 }, { "epoch": 0.0012948021785046653, "grad_norm": 0.4680929481983185, "learning_rate": 9.999989659267321e-06, "loss": 0.9625024795532227, "step": 20, "token_acc": 0.7215026754058899 }, { "epoch": 0.0016185027231308317, "grad_norm": 0.5254758596420288, "learning_rate": 9.999983842608321e-06, "loss": 0.9510323524475097, "step": 25, "token_acc": 0.7249505687800119 }, { "epoch": 0.001942203267756998, "grad_norm": 0.5879510641098022, "learning_rate": 9.999976733361495e-06, "loss": 0.9607544898986816, "step": 30, "token_acc": 0.723084855723731 }, { "epoch": 0.0022659038123831643, "grad_norm": 0.45034876465797424, "learning_rate": 9.99996833152868e-06, "loss": 0.9397544860839844, "step": 35, "token_acc": 0.7268458315272359 }, { "epoch": 0.0025896043570093306, "grad_norm": 0.44632700085639954, "learning_rate": 9.999958637112051e-06, "loss": 0.9361320495605469, "step": 40, "token_acc": 0.7275815622280762 }, { "epoch": 0.002913304901635497, "grad_norm": 0.4751383066177368, "learning_rate": 9.999947650114112e-06, "loss": 0.9362952232360839, "step": 45, "token_acc": 0.7281440057240769 }, { "epoch": 0.0032370054462616633, "grad_norm": 0.5343373417854309, "learning_rate": 9.999935370537703e-06, "loss": 0.9301636695861817, "step": 50, "token_acc": 0.729929679221655 }, { "epoch": 0.0035607059908878296, "grad_norm": 0.4330422580242157, "learning_rate": 9.999921798386002e-06, "loss": 0.9310144424438477, "step": 55, "token_acc": 0.7295162748336493 }, { "epoch": 0.003884406535513996, "grad_norm": 0.3396628797054291, "learning_rate": 9.99990693366251e-06, "loss": 0.9389154434204101, "step": 60, "token_acc": 0.7281562965791646 }, { "epoch": 0.004208107080140163, "grad_norm": 0.620532751083374, "learning_rate": 9.999890776371079e-06, "loss": 0.9442959785461426, "step": 65, "token_acc": 0.7254207263064659 }, { "epoch": 0.004531807624766329, "grad_norm": 0.5384201407432556, "learning_rate": 9.999873326515878e-06, "loss": 0.9206907272338867, "step": 70, "token_acc": 0.7314527244326013 }, { "epoch": 0.004855508169392495, "grad_norm": 0.39212316274642944, "learning_rate": 9.999854584101425e-06, "loss": 0.9187379837036133, "step": 75, "token_acc": 0.732506452083373 }, { "epoch": 0.005179208714018661, "grad_norm": 0.4231693744659424, "learning_rate": 9.99983454913256e-06, "loss": 0.8998111724853516, "step": 80, "token_acc": 0.7370742404194388 }, { "epoch": 0.005502909258644828, "grad_norm": 0.383301317691803, "learning_rate": 9.999813221614466e-06, "loss": 0.9062105178833008, "step": 85, "token_acc": 0.7353797807925193 }, { "epoch": 0.005826609803270994, "grad_norm": 0.4488587975502014, "learning_rate": 9.999790601552653e-06, "loss": 0.9143259048461914, "step": 90, "token_acc": 0.7321178583692121 }, { "epoch": 0.006150310347897161, "grad_norm": 0.5287695527076721, "learning_rate": 9.99976668895297e-06, "loss": 0.8999946594238282, "step": 95, "token_acc": 0.7352756191647565 }, { "epoch": 0.006474010892523327, "grad_norm": 0.39071130752563477, "learning_rate": 9.999741483821602e-06, "loss": 0.9071149826049805, "step": 100, "token_acc": 0.7334309987461296 }, { "epoch": 0.006797711437149493, "grad_norm": 0.4476543664932251, "learning_rate": 9.99971498616506e-06, "loss": 0.938323974609375, "step": 105, "token_acc": 0.727615425894886 }, { "epoch": 0.007121411981775659, "grad_norm": 0.48294010758399963, "learning_rate": 9.999687195990198e-06, "loss": 0.8915648460388184, "step": 110, "token_acc": 0.7378530685176277 }, { "epoch": 0.007445112526401826, "grad_norm": 0.3868415057659149, "learning_rate": 9.999658113304198e-06, "loss": 0.9050452232360839, "step": 115, "token_acc": 0.7335766899159116 }, { "epoch": 0.007768813071027992, "grad_norm": 0.3346639573574066, "learning_rate": 9.999627738114579e-06, "loss": 0.9243963241577149, "step": 120, "token_acc": 0.7290086607623428 }, { "epoch": 0.008092513615654159, "grad_norm": 0.5152879357337952, "learning_rate": 9.999596070429194e-06, "loss": 0.9094121932983399, "step": 125, "token_acc": 0.7322061803444783 }, { "epoch": 0.008416214160280325, "grad_norm": 2.1928350925445557, "learning_rate": 9.999563110256231e-06, "loss": 0.9117186546325684, "step": 130, "token_acc": 0.7330029296584838 }, { "epoch": 0.00873991470490649, "grad_norm": 0.48166051506996155, "learning_rate": 9.999528857604208e-06, "loss": 0.8967769622802735, "step": 135, "token_acc": 0.7362026570646625 }, { "epoch": 0.009063615249532657, "grad_norm": 0.42778295278549194, "learning_rate": 9.999493312481983e-06, "loss": 0.8941813468933105, "step": 140, "token_acc": 0.7372688068998563 }, { "epoch": 0.009387315794158824, "grad_norm": 0.4457942843437195, "learning_rate": 9.999456474898742e-06, "loss": 0.8982257843017578, "step": 145, "token_acc": 0.7369362117653269 }, { "epoch": 0.00971101633878499, "grad_norm": 0.4489797353744507, "learning_rate": 9.999418344864008e-06, "loss": 0.8879405975341796, "step": 150, "token_acc": 0.739641477717468 }, { "epoch": 0.010034716883411156, "grad_norm": 0.4277820885181427, "learning_rate": 9.999378922387642e-06, "loss": 0.8834354400634765, "step": 155, "token_acc": 0.7386905433407948 }, { "epoch": 0.010358417428037323, "grad_norm": 0.47622355818748474, "learning_rate": 9.999338207479831e-06, "loss": 0.9011181831359864, "step": 160, "token_acc": 0.7370494551550713 }, { "epoch": 0.01068211797266349, "grad_norm": 0.43810367584228516, "learning_rate": 9.999296200151105e-06, "loss": 0.9136867523193359, "step": 165, "token_acc": 0.7322615305026066 }, { "epoch": 0.011005818517289656, "grad_norm": 0.3954918682575226, "learning_rate": 9.999252900412321e-06, "loss": 0.8854312896728516, "step": 170, "token_acc": 0.7398164473981644 }, { "epoch": 0.011329519061915821, "grad_norm": 0.4095935523509979, "learning_rate": 9.999208308274672e-06, "loss": 0.9092643737792969, "step": 175, "token_acc": 0.7353880149283453 }, { "epoch": 0.011653219606541988, "grad_norm": 0.4761139154434204, "learning_rate": 9.999162423749689e-06, "loss": 0.8895297050476074, "step": 180, "token_acc": 0.7379413560982813 }, { "epoch": 0.011976920151168155, "grad_norm": 0.4381120800971985, "learning_rate": 9.999115246849231e-06, "loss": 0.8863605499267578, "step": 185, "token_acc": 0.7390856077123119 }, { "epoch": 0.012300620695794321, "grad_norm": 0.43919098377227783, "learning_rate": 9.999066777585496e-06, "loss": 0.8737846374511719, "step": 190, "token_acc": 0.74064775124175 }, { "epoch": 0.012624321240420486, "grad_norm": 0.6226565837860107, "learning_rate": 9.999017015971013e-06, "loss": 0.8781806945800781, "step": 195, "token_acc": 0.7433386315565512 }, { "epoch": 0.012948021785046653, "grad_norm": 0.4476548731327057, "learning_rate": 9.998965962018645e-06, "loss": 0.8934864044189453, "step": 200, "token_acc": 0.7377522305490721 }, { "epoch": 0.01327172232967282, "grad_norm": 0.41267263889312744, "learning_rate": 9.998913615741594e-06, "loss": 0.8676982879638672, "step": 205, "token_acc": 0.7424472664225514 }, { "epoch": 0.013595422874298987, "grad_norm": 0.4544789493083954, "learning_rate": 9.99885997715339e-06, "loss": 0.8828779220581054, "step": 210, "token_acc": 0.7405412399215515 }, { "epoch": 0.013919123418925152, "grad_norm": 0.4396820366382599, "learning_rate": 9.998805046267901e-06, "loss": 0.8871561050415039, "step": 215, "token_acc": 0.740457679975403 }, { "epoch": 0.014242823963551319, "grad_norm": 0.456473708152771, "learning_rate": 9.998748823099328e-06, "loss": 0.9114726066589356, "step": 220, "token_acc": 0.7343903330703662 }, { "epoch": 0.014566524508177485, "grad_norm": 0.5236892700195312, "learning_rate": 9.9986913076622e-06, "loss": 0.8873723030090332, "step": 225, "token_acc": 0.7401675333976894 }, { "epoch": 0.014890225052803652, "grad_norm": 0.4560414254665375, "learning_rate": 9.998632499971394e-06, "loss": 0.9067856788635253, "step": 230, "token_acc": 0.7328753418261855 }, { "epoch": 0.015213925597429817, "grad_norm": 0.4759744703769684, "learning_rate": 9.998572400042109e-06, "loss": 0.8780265808105469, "step": 235, "token_acc": 0.7420124474692491 }, { "epoch": 0.015537626142055984, "grad_norm": 0.49464520812034607, "learning_rate": 9.99851100788988e-06, "loss": 0.8846060752868652, "step": 240, "token_acc": 0.7384213663694795 }, { "epoch": 0.01586132668668215, "grad_norm": 0.46222376823425293, "learning_rate": 9.998448323530582e-06, "loss": 0.8701190948486328, "step": 245, "token_acc": 0.7427714973182961 }, { "epoch": 0.016185027231308317, "grad_norm": 0.44141677021980286, "learning_rate": 9.998384346980418e-06, "loss": 0.9181423187255859, "step": 250, "token_acc": 0.7324641495246791 }, { "epoch": 0.016508727775934484, "grad_norm": 0.33784645795822144, "learning_rate": 9.998319078255926e-06, "loss": 0.9056981086730957, "step": 255, "token_acc": 0.7351813555777587 }, { "epoch": 0.01683242832056065, "grad_norm": 0.3956162631511688, "learning_rate": 9.998252517373981e-06, "loss": 0.8926022529602051, "step": 260, "token_acc": 0.737427887608428 }, { "epoch": 0.017156128865186814, "grad_norm": 0.4765373766422272, "learning_rate": 9.998184664351791e-06, "loss": 0.9022045135498047, "step": 265, "token_acc": 0.7352742088332184 }, { "epoch": 0.01747982940981298, "grad_norm": 0.44379451870918274, "learning_rate": 9.998115519206895e-06, "loss": 0.8823341369628906, "step": 270, "token_acc": 0.7402975665111587 }, { "epoch": 0.017803529954439148, "grad_norm": 0.41809940338134766, "learning_rate": 9.998045081957168e-06, "loss": 0.9008275032043457, "step": 275, "token_acc": 0.7348032956631665 }, { "epoch": 0.018127230499065315, "grad_norm": 0.5065150260925293, "learning_rate": 9.997973352620822e-06, "loss": 0.8757299423217774, "step": 280, "token_acc": 0.7407185355585822 }, { "epoch": 0.01845093104369148, "grad_norm": 0.4396342635154724, "learning_rate": 9.9979003312164e-06, "loss": 0.9067764282226562, "step": 285, "token_acc": 0.7333737312528404 }, { "epoch": 0.018774631588317648, "grad_norm": 0.43488243222236633, "learning_rate": 9.997826017762774e-06, "loss": 0.8744321823120117, "step": 290, "token_acc": 0.7414612570995304 }, { "epoch": 0.019098332132943815, "grad_norm": 0.45008257031440735, "learning_rate": 9.997750412279163e-06, "loss": 0.8781099319458008, "step": 295, "token_acc": 0.7404804598913559 }, { "epoch": 0.01942203267756998, "grad_norm": 0.33521798253059387, "learning_rate": 9.997673514785111e-06, "loss": 0.8590770721435547, "step": 300, "token_acc": 0.7454268091344948 }, { "epoch": 0.019745733222196145, "grad_norm": 0.3800932466983795, "learning_rate": 9.997595325300491e-06, "loss": 0.8821535110473633, "step": 305, "token_acc": 0.7410614708390737 }, { "epoch": 0.02006943376682231, "grad_norm": 0.35737451910972595, "learning_rate": 9.997515843845525e-06, "loss": 0.8644197463989258, "step": 310, "token_acc": 0.7428164664835275 }, { "epoch": 0.02039313431144848, "grad_norm": 0.347900390625, "learning_rate": 9.997435070440753e-06, "loss": 0.8697114944458008, "step": 315, "token_acc": 0.7418372327617064 }, { "epoch": 0.020716834856074645, "grad_norm": 0.49462440609931946, "learning_rate": 9.997353005107061e-06, "loss": 0.8620218276977539, "step": 320, "token_acc": 0.7444521427946805 }, { "epoch": 0.021040535400700812, "grad_norm": 0.37602922320365906, "learning_rate": 9.997269647865664e-06, "loss": 0.8848018646240234, "step": 325, "token_acc": 0.7399849640210504 }, { "epoch": 0.02136423594532698, "grad_norm": 0.29893648624420166, "learning_rate": 9.99718499873811e-06, "loss": 0.8745439529418946, "step": 330, "token_acc": 0.7403799167424397 }, { "epoch": 0.021687936489953145, "grad_norm": 0.3824983835220337, "learning_rate": 9.997099057746282e-06, "loss": 0.8677508354187011, "step": 335, "token_acc": 0.744122003770536 }, { "epoch": 0.022011637034579312, "grad_norm": 0.40624433755874634, "learning_rate": 9.9970118249124e-06, "loss": 0.8768255233764648, "step": 340, "token_acc": 0.7418545126309152 }, { "epoch": 0.022335337579205475, "grad_norm": 0.3721212148666382, "learning_rate": 9.996923300259011e-06, "loss": 0.8972923278808593, "step": 345, "token_acc": 0.7369658930234162 }, { "epoch": 0.022659038123831642, "grad_norm": 0.34050673246383667, "learning_rate": 9.996833483809005e-06, "loss": 0.8957050323486329, "step": 350, "token_acc": 0.7356304533789564 }, { "epoch": 0.02298273866845781, "grad_norm": 0.4068893790245056, "learning_rate": 9.996742375585597e-06, "loss": 0.8718267440795898, "step": 355, "token_acc": 0.7425319219880877 }, { "epoch": 0.023306439213083976, "grad_norm": 0.48321112990379333, "learning_rate": 9.996649975612343e-06, "loss": 0.8793611526489258, "step": 360, "token_acc": 0.7406522122333862 }, { "epoch": 0.023630139757710143, "grad_norm": 0.332204133272171, "learning_rate": 9.99655628391313e-06, "loss": 0.8980621337890625, "step": 365, "token_acc": 0.735040719119969 }, { "epoch": 0.02395384030233631, "grad_norm": 0.5123544335365295, "learning_rate": 9.996461300512177e-06, "loss": 0.8812270164489746, "step": 370, "token_acc": 0.7392018186410709 }, { "epoch": 0.024277540846962476, "grad_norm": 0.456012487411499, "learning_rate": 9.99636502543404e-06, "loss": 0.8782167434692383, "step": 375, "token_acc": 0.7403954630921332 }, { "epoch": 0.024601241391588643, "grad_norm": 0.33305755257606506, "learning_rate": 9.99626745870361e-06, "loss": 0.8684906005859375, "step": 380, "token_acc": 0.741442711971636 }, { "epoch": 0.024924941936214806, "grad_norm": 0.39011913537979126, "learning_rate": 9.996168600346106e-06, "loss": 0.8590014457702637, "step": 385, "token_acc": 0.7442417096955191 }, { "epoch": 0.025248642480840973, "grad_norm": 0.4387055039405823, "learning_rate": 9.996068450387088e-06, "loss": 0.8644292831420899, "step": 390, "token_acc": 0.7437728329458652 }, { "epoch": 0.02557234302546714, "grad_norm": 0.4508276879787445, "learning_rate": 9.995967008852445e-06, "loss": 0.8947925567626953, "step": 395, "token_acc": 0.7374358071028848 }, { "epoch": 0.025896043570093306, "grad_norm": 0.32120782136917114, "learning_rate": 9.9958642757684e-06, "loss": 0.8633054733276367, "step": 400, "token_acc": 0.7439770242485558 }, { "epoch": 0.026219744114719473, "grad_norm": 0.37675023078918457, "learning_rate": 9.995760251161516e-06, "loss": 0.8643070220947265, "step": 405, "token_acc": 0.7435353027086069 }, { "epoch": 0.02654344465934564, "grad_norm": 0.47113099694252014, "learning_rate": 9.995654935058679e-06, "loss": 0.871909236907959, "step": 410, "token_acc": 0.7418441257887368 }, { "epoch": 0.026867145203971807, "grad_norm": 0.34517166018486023, "learning_rate": 9.99554832748712e-06, "loss": 0.8692180633544921, "step": 415, "token_acc": 0.7426218519582496 }, { "epoch": 0.027190845748597973, "grad_norm": 0.31174635887145996, "learning_rate": 9.995440428474397e-06, "loss": 0.847544002532959, "step": 420, "token_acc": 0.7470227659381047 }, { "epoch": 0.027514546293224137, "grad_norm": 0.3463517129421234, "learning_rate": 9.995331238048405e-06, "loss": 0.8719354629516601, "step": 425, "token_acc": 0.7414496805375146 }, { "epoch": 0.027838246837850304, "grad_norm": 0.45001697540283203, "learning_rate": 9.995220756237372e-06, "loss": 0.8604646682739258, "step": 430, "token_acc": 0.7439254273739578 }, { "epoch": 0.02816194738247647, "grad_norm": 0.328935444355011, "learning_rate": 9.995108983069856e-06, "loss": 0.8790054321289062, "step": 435, "token_acc": 0.7386447675577649 }, { "epoch": 0.028485647927102637, "grad_norm": 0.347543329000473, "learning_rate": 9.994995918574757e-06, "loss": 0.8681373596191406, "step": 440, "token_acc": 0.7430981792033694 }, { "epoch": 0.028809348471728804, "grad_norm": 0.3348560333251953, "learning_rate": 9.994881562781304e-06, "loss": 0.8563289642333984, "step": 445, "token_acc": 0.7450069326760129 }, { "epoch": 0.02913304901635497, "grad_norm": 0.3712228536605835, "learning_rate": 9.994765915719056e-06, "loss": 0.8788246154785156, "step": 450, "token_acc": 0.7404556929251084 }, { "epoch": 0.029456749560981137, "grad_norm": 0.47007790207862854, "learning_rate": 9.994648977417913e-06, "loss": 0.8790873527526856, "step": 455, "token_acc": 0.7409593344950838 }, { "epoch": 0.029780450105607304, "grad_norm": 0.32646119594573975, "learning_rate": 9.994530747908104e-06, "loss": 0.8864717483520508, "step": 460, "token_acc": 0.7396067497313468 }, { "epoch": 0.030104150650233467, "grad_norm": 0.4372415542602539, "learning_rate": 9.994411227220197e-06, "loss": 0.8603729248046875, "step": 465, "token_acc": 0.7455870805794449 }, { "epoch": 0.030427851194859634, "grad_norm": 0.3528849482536316, "learning_rate": 9.994290415385086e-06, "loss": 0.863395881652832, "step": 470, "token_acc": 0.7430947221300656 }, { "epoch": 0.0307515517394858, "grad_norm": 0.39837881922721863, "learning_rate": 9.994168312434005e-06, "loss": 0.8434829711914062, "step": 475, "token_acc": 0.7488212707471756 }, { "epoch": 0.031075252284111968, "grad_norm": 0.5514006614685059, "learning_rate": 9.99404491839852e-06, "loss": 0.8558374404907226, "step": 480, "token_acc": 0.7446788111217642 }, { "epoch": 0.031398952828738134, "grad_norm": 0.3533843457698822, "learning_rate": 9.993920233310532e-06, "loss": 0.8706111907958984, "step": 485, "token_acc": 0.7414565120471418 }, { "epoch": 0.0317226533733643, "grad_norm": 0.35331991314888, "learning_rate": 9.993794257202272e-06, "loss": 0.8767377853393554, "step": 490, "token_acc": 0.7411663560234164 }, { "epoch": 0.03204635391799047, "grad_norm": 0.4786873757839203, "learning_rate": 9.993666990106308e-06, "loss": 0.856317138671875, "step": 495, "token_acc": 0.7455905506580127 }, { "epoch": 0.032370054462616635, "grad_norm": 0.3675483465194702, "learning_rate": 9.993538432055539e-06, "loss": 0.8693881034851074, "step": 500, "token_acc": 0.7428355142208284 }, { "epoch": 0.0326937550072428, "grad_norm": 0.4883832633495331, "learning_rate": 9.993408583083203e-06, "loss": 0.8729747772216797, "step": 505, "token_acc": 0.7427574911644376 }, { "epoch": 0.03301745555186897, "grad_norm": 0.44024819135665894, "learning_rate": 9.993277443222866e-06, "loss": 0.8659051895141602, "step": 510, "token_acc": 0.7422729103865976 }, { "epoch": 0.033341156096495135, "grad_norm": 0.2568567991256714, "learning_rate": 9.993145012508431e-06, "loss": 0.8917436599731445, "step": 515, "token_acc": 0.7376323238126014 }, { "epoch": 0.0336648566411213, "grad_norm": 0.4289894700050354, "learning_rate": 9.993011290974134e-06, "loss": 0.8777000427246093, "step": 520, "token_acc": 0.7396424546319604 }, { "epoch": 0.03398855718574746, "grad_norm": 0.552097499370575, "learning_rate": 9.992876278654546e-06, "loss": 0.8467668533325196, "step": 525, "token_acc": 0.7460483001305409 }, { "epoch": 0.03431225773037363, "grad_norm": 0.3342556357383728, "learning_rate": 9.992739975584566e-06, "loss": 0.8849756240844726, "step": 530, "token_acc": 0.7392617730045183 }, { "epoch": 0.034635958274999795, "grad_norm": 0.405696302652359, "learning_rate": 9.992602381799434e-06, "loss": 0.862635612487793, "step": 535, "token_acc": 0.7435003454540802 }, { "epoch": 0.03495965881962596, "grad_norm": 0.4352284371852875, "learning_rate": 9.992463497334719e-06, "loss": 0.8403263092041016, "step": 540, "token_acc": 0.7517495513970777 }, { "epoch": 0.03528335936425213, "grad_norm": 0.31643733382225037, "learning_rate": 9.992323322226328e-06, "loss": 0.850887393951416, "step": 545, "token_acc": 0.7480465014617087 }, { "epoch": 0.035607059908878295, "grad_norm": 0.38386309146881104, "learning_rate": 9.992181856510494e-06, "loss": 0.8686901092529297, "step": 550, "token_acc": 0.7423723335488042 }, { "epoch": 0.03593076045350446, "grad_norm": 0.3316640853881836, "learning_rate": 9.992039100223791e-06, "loss": 0.8667654037475586, "step": 555, "token_acc": 0.7432694105795274 }, { "epoch": 0.03625446099813063, "grad_norm": 0.3988274335861206, "learning_rate": 9.991895053403126e-06, "loss": 0.8675498962402344, "step": 560, "token_acc": 0.7437749416699604 }, { "epoch": 0.036578161542756796, "grad_norm": 0.3323687016963959, "learning_rate": 9.991749716085737e-06, "loss": 0.8330869674682617, "step": 565, "token_acc": 0.7521257207344519 }, { "epoch": 0.03690186208738296, "grad_norm": 0.5594270825386047, "learning_rate": 9.991603088309195e-06, "loss": 0.8752755165100098, "step": 570, "token_acc": 0.7412277322050284 }, { "epoch": 0.03722556263200913, "grad_norm": 0.3675437867641449, "learning_rate": 9.991455170111403e-06, "loss": 0.8789483070373535, "step": 575, "token_acc": 0.7406275771627888 }, { "epoch": 0.037549263176635296, "grad_norm": 0.43670547008514404, "learning_rate": 9.991305961530608e-06, "loss": 0.8815210342407227, "step": 580, "token_acc": 0.7390612464112136 }, { "epoch": 0.03787296372126146, "grad_norm": 0.4208093285560608, "learning_rate": 9.991155462605378e-06, "loss": 0.8520967483520507, "step": 585, "token_acc": 0.7462375739272682 }, { "epoch": 0.03819666426588763, "grad_norm": 0.3035094738006592, "learning_rate": 9.99100367337462e-06, "loss": 0.8461785316467285, "step": 590, "token_acc": 0.7468487459139095 }, { "epoch": 0.038520364810513796, "grad_norm": 0.42488372325897217, "learning_rate": 9.990850593877575e-06, "loss": 0.8649591445922852, "step": 595, "token_acc": 0.7431925600206928 }, { "epoch": 0.03884406535513996, "grad_norm": 0.4242069721221924, "learning_rate": 9.990696224153818e-06, "loss": 0.8506732940673828, "step": 600, "token_acc": 0.745276580940402 }, { "epoch": 0.03916776589976612, "grad_norm": 0.30094972252845764, "learning_rate": 9.990540564243256e-06, "loss": 0.8472579956054688, "step": 605, "token_acc": 0.7489212717638153 }, { "epoch": 0.03949146644439229, "grad_norm": 0.3987672030925751, "learning_rate": 9.99038361418613e-06, "loss": 0.8449127197265625, "step": 610, "token_acc": 0.7476395813962196 }, { "epoch": 0.039815166989018456, "grad_norm": 0.32243767380714417, "learning_rate": 9.990225374023012e-06, "loss": 0.8514744758605957, "step": 615, "token_acc": 0.7456620611581519 }, { "epoch": 0.04013886753364462, "grad_norm": 0.40580907464027405, "learning_rate": 9.990065843794814e-06, "loss": 0.8459139823913574, "step": 620, "token_acc": 0.74815345860656 }, { "epoch": 0.04046256807827079, "grad_norm": 0.3889685869216919, "learning_rate": 9.989905023542774e-06, "loss": 0.8431923866271973, "step": 625, "token_acc": 0.7479246260441624 }, { "epoch": 0.04078626862289696, "grad_norm": 0.46483319997787476, "learning_rate": 9.989742913308468e-06, "loss": 0.8409564971923829, "step": 630, "token_acc": 0.7479616205293428 }, { "epoch": 0.041109969167523124, "grad_norm": 0.35899844765663147, "learning_rate": 9.989579513133806e-06, "loss": 0.8535250663757324, "step": 635, "token_acc": 0.7465836711059641 }, { "epoch": 0.04143366971214929, "grad_norm": 0.41857948899269104, "learning_rate": 9.989414823061028e-06, "loss": 0.8625528335571289, "step": 640, "token_acc": 0.7446176688938382 }, { "epoch": 0.04175737025677546, "grad_norm": 0.37190157175064087, "learning_rate": 9.98924884313271e-06, "loss": 0.8466529846191406, "step": 645, "token_acc": 0.7481205662376015 }, { "epoch": 0.042081070801401624, "grad_norm": 0.4641806185245514, "learning_rate": 9.989081573391763e-06, "loss": 0.8478928565979004, "step": 650, "token_acc": 0.7492733761031772 }, { "epoch": 0.04240477134602779, "grad_norm": 0.30975034832954407, "learning_rate": 9.988913013881426e-06, "loss": 0.8635974884033203, "step": 655, "token_acc": 0.7449402568246519 }, { "epoch": 0.04272847189065396, "grad_norm": 0.5708988308906555, "learning_rate": 9.988743164645276e-06, "loss": 0.8428747177124023, "step": 660, "token_acc": 0.7487946344104963 }, { "epoch": 0.043052172435280124, "grad_norm": 0.3784821927547455, "learning_rate": 9.988572025727223e-06, "loss": 0.8497096061706543, "step": 665, "token_acc": 0.746406617989543 }, { "epoch": 0.04337587297990629, "grad_norm": 0.3801673948764801, "learning_rate": 9.988399597171507e-06, "loss": 0.8509566307067871, "step": 670, "token_acc": 0.7475834769000118 }, { "epoch": 0.04369957352453246, "grad_norm": 0.4408676028251648, "learning_rate": 9.988225879022709e-06, "loss": 0.8545393943786621, "step": 675, "token_acc": 0.7458759475018419 }, { "epoch": 0.044023274069158624, "grad_norm": 0.2651773989200592, "learning_rate": 9.988050871325734e-06, "loss": 0.8409065246582031, "step": 680, "token_acc": 0.7490239937757895 }, { "epoch": 0.044346974613784784, "grad_norm": 0.4902036488056183, "learning_rate": 9.987874574125825e-06, "loss": 0.8415003776550293, "step": 685, "token_acc": 0.7469100461388206 }, { "epoch": 0.04467067515841095, "grad_norm": 0.3801291584968567, "learning_rate": 9.98769698746856e-06, "loss": 0.8407993316650391, "step": 690, "token_acc": 0.7482587536127902 }, { "epoch": 0.04499437570303712, "grad_norm": 0.4620113670825958, "learning_rate": 9.987518111399847e-06, "loss": 0.826237678527832, "step": 695, "token_acc": 0.7526994399325937 }, { "epoch": 0.045318076247663285, "grad_norm": 0.46179404854774475, "learning_rate": 9.98733794596593e-06, "loss": 0.8280405044555664, "step": 700, "token_acc": 0.7525693819046768 }, { "epoch": 0.04564177679228945, "grad_norm": 0.5189854502677917, "learning_rate": 9.98715649121338e-06, "loss": 0.8704814910888672, "step": 705, "token_acc": 0.7411428102069871 }, { "epoch": 0.04596547733691562, "grad_norm": 0.43426212668418884, "learning_rate": 9.986973747189115e-06, "loss": 0.859717845916748, "step": 710, "token_acc": 0.7441797667527842 }, { "epoch": 0.046289177881541785, "grad_norm": 0.42333903908729553, "learning_rate": 9.986789713940372e-06, "loss": 0.8680317878723145, "step": 715, "token_acc": 0.7423424006210175 }, { "epoch": 0.04661287842616795, "grad_norm": 0.3414107859134674, "learning_rate": 9.98660439151473e-06, "loss": 0.8309438705444336, "step": 720, "token_acc": 0.7510768237306532 }, { "epoch": 0.04693657897079412, "grad_norm": 0.421144962310791, "learning_rate": 9.986417779960094e-06, "loss": 0.8695832252502441, "step": 725, "token_acc": 0.7433916716958359 }, { "epoch": 0.047260279515420285, "grad_norm": 0.33431702852249146, "learning_rate": 9.98622987932471e-06, "loss": 0.8534290313720703, "step": 730, "token_acc": 0.7481297502552376 }, { "epoch": 0.04758398006004645, "grad_norm": 0.46437472105026245, "learning_rate": 9.986040689657153e-06, "loss": 0.8546113967895508, "step": 735, "token_acc": 0.7455213716430652 }, { "epoch": 0.04790768060467262, "grad_norm": 0.38697564601898193, "learning_rate": 9.985850211006331e-06, "loss": 0.8532279014587403, "step": 740, "token_acc": 0.7459880512243476 }, { "epoch": 0.048231381149298785, "grad_norm": 0.37626636028289795, "learning_rate": 9.985658443421489e-06, "loss": 0.8383029937744141, "step": 745, "token_acc": 0.7481843259018404 }, { "epoch": 0.04855508169392495, "grad_norm": 0.43161553144454956, "learning_rate": 9.9854653869522e-06, "loss": 0.8462516784667968, "step": 750, "token_acc": 0.7482538040027281 }, { "epoch": 0.04887878223855112, "grad_norm": 0.4193752706050873, "learning_rate": 9.985271041648371e-06, "loss": 0.8691276550292969, "step": 755, "token_acc": 0.743379293152051 }, { "epoch": 0.049202482783177286, "grad_norm": 0.43977534770965576, "learning_rate": 9.985075407560247e-06, "loss": 0.8372348785400391, "step": 760, "token_acc": 0.7488013250806381 }, { "epoch": 0.04952618332780345, "grad_norm": 0.39897048473358154, "learning_rate": 9.984878484738402e-06, "loss": 0.8541616439819336, "step": 765, "token_acc": 0.7452108532200066 }, { "epoch": 0.04984988387242961, "grad_norm": 0.4492208957672119, "learning_rate": 9.984680273233745e-06, "loss": 0.8556131362915039, "step": 770, "token_acc": 0.7462023068930596 }, { "epoch": 0.05017358441705578, "grad_norm": 0.434584379196167, "learning_rate": 9.984480773097518e-06, "loss": 0.8435573577880859, "step": 775, "token_acc": 0.7487085590602212 }, { "epoch": 0.050497284961681946, "grad_norm": 0.29261907935142517, "learning_rate": 9.98427998438129e-06, "loss": 0.8354069709777832, "step": 780, "token_acc": 0.7517011765642202 }, { "epoch": 0.05082098550630811, "grad_norm": 0.26844683289527893, "learning_rate": 9.984077907136976e-06, "loss": 0.8496073722839356, "step": 785, "token_acc": 0.7479465590711654 }, { "epoch": 0.05114468605093428, "grad_norm": 0.4194391369819641, "learning_rate": 9.98387454141681e-06, "loss": 0.8253273010253906, "step": 790, "token_acc": 0.752777638756819 }, { "epoch": 0.051468386595560446, "grad_norm": 0.3669556975364685, "learning_rate": 9.983669887273373e-06, "loss": 0.8465200424194336, "step": 795, "token_acc": 0.7479244752024357 }, { "epoch": 0.05179208714018661, "grad_norm": 0.4555341303348541, "learning_rate": 9.983463944759566e-06, "loss": 0.8519526481628418, "step": 800, "token_acc": 0.7458492226459372 }, { "epoch": 0.05211578768481278, "grad_norm": 0.4790143668651581, "learning_rate": 9.98325671392863e-06, "loss": 0.8568413734436036, "step": 805, "token_acc": 0.7467548522685128 }, { "epoch": 0.052439488229438946, "grad_norm": 0.4296301305294037, "learning_rate": 9.98304819483414e-06, "loss": 0.8284554481506348, "step": 810, "token_acc": 0.7518344631296735 }, { "epoch": 0.05276318877406511, "grad_norm": 0.5178402066230774, "learning_rate": 9.98283838753e-06, "loss": 0.8117453575134277, "step": 815, "token_acc": 0.7552318896128785 }, { "epoch": 0.05308688931869128, "grad_norm": 0.42189329862594604, "learning_rate": 9.98262729207045e-06, "loss": 0.8524287223815918, "step": 820, "token_acc": 0.7468737909915345 }, { "epoch": 0.05341058986331745, "grad_norm": 0.41368284821510315, "learning_rate": 9.982414908510063e-06, "loss": 0.8523839950561524, "step": 825, "token_acc": 0.7449302582153459 }, { "epoch": 0.05373429040794361, "grad_norm": 0.33992910385131836, "learning_rate": 9.982201236903742e-06, "loss": 0.83810396194458, "step": 830, "token_acc": 0.7498381290305871 }, { "epoch": 0.05405799095256978, "grad_norm": 0.3260256350040436, "learning_rate": 9.981986277306725e-06, "loss": 0.8392291069030762, "step": 835, "token_acc": 0.7489433803012074 }, { "epoch": 0.05438169149719595, "grad_norm": 0.44844335317611694, "learning_rate": 9.981770029774585e-06, "loss": 0.8373539924621582, "step": 840, "token_acc": 0.750277726912043 }, { "epoch": 0.054705392041822114, "grad_norm": 0.4370143711566925, "learning_rate": 9.981552494363226e-06, "loss": 0.8406907081604004, "step": 845, "token_acc": 0.7480915008169716 }, { "epoch": 0.055029092586448274, "grad_norm": 0.5567945837974548, "learning_rate": 9.981333671128884e-06, "loss": 0.859100341796875, "step": 850, "token_acc": 0.7452003338898163 }, { "epoch": 0.05535279313107444, "grad_norm": 0.3701243996620178, "learning_rate": 9.981113560128127e-06, "loss": 0.8180648803710937, "step": 855, "token_acc": 0.753455461277846 }, { "epoch": 0.05567649367570061, "grad_norm": 0.40432071685791016, "learning_rate": 9.980892161417859e-06, "loss": 0.837767505645752, "step": 860, "token_acc": 0.7506684621183323 }, { "epoch": 0.056000194220326774, "grad_norm": 0.30236193537712097, "learning_rate": 9.980669475055318e-06, "loss": 0.842387580871582, "step": 865, "token_acc": 0.7491906316935286 }, { "epoch": 0.05632389476495294, "grad_norm": 0.2780148386955261, "learning_rate": 9.980445501098071e-06, "loss": 0.817818546295166, "step": 870, "token_acc": 0.7538956726102284 }, { "epoch": 0.05664759530957911, "grad_norm": 0.435394287109375, "learning_rate": 9.980220239604018e-06, "loss": 0.852633285522461, "step": 875, "token_acc": 0.7467311921460393 }, { "epoch": 0.056971295854205274, "grad_norm": 0.42657145857810974, "learning_rate": 9.979993690631394e-06, "loss": 0.8497573852539062, "step": 880, "token_acc": 0.7469188371633544 }, { "epoch": 0.05729499639883144, "grad_norm": 0.41185009479522705, "learning_rate": 9.979765854238765e-06, "loss": 0.8375543594360352, "step": 885, "token_acc": 0.7506740383178603 }, { "epoch": 0.05761869694345761, "grad_norm": 0.37973061203956604, "learning_rate": 9.979536730485036e-06, "loss": 0.8456315994262695, "step": 890, "token_acc": 0.7476165185626571 }, { "epoch": 0.057942397488083774, "grad_norm": 0.3738889992237091, "learning_rate": 9.979306319429432e-06, "loss": 0.8661626815795899, "step": 895, "token_acc": 0.744105351438211 }, { "epoch": 0.05826609803270994, "grad_norm": 0.37237390875816345, "learning_rate": 9.979074621131526e-06, "loss": 0.8459030151367187, "step": 900, "token_acc": 0.7475840978593272 }, { "epoch": 0.05858979857733611, "grad_norm": 0.3581589460372925, "learning_rate": 9.97884163565121e-06, "loss": 0.831664752960205, "step": 905, "token_acc": 0.7511512260716234 }, { "epoch": 0.058913499121962275, "grad_norm": 0.2871849834918976, "learning_rate": 9.97860736304872e-06, "loss": 0.8487959861755371, "step": 910, "token_acc": 0.7462301641307603 }, { "epoch": 0.05923719966658844, "grad_norm": 0.45226943492889404, "learning_rate": 9.978371803384616e-06, "loss": 0.8417272567749023, "step": 915, "token_acc": 0.7494518497894407 }, { "epoch": 0.05956090021121461, "grad_norm": 0.4182718098163605, "learning_rate": 9.978134956719795e-06, "loss": 0.8587264060974121, "step": 920, "token_acc": 0.7443008274559894 }, { "epoch": 0.059884600755840775, "grad_norm": 0.4626004993915558, "learning_rate": 9.977896823115489e-06, "loss": 0.8211191177368165, "step": 925, "token_acc": 0.7534526040622126 }, { "epoch": 0.060208301300466935, "grad_norm": 0.31187593936920166, "learning_rate": 9.97765740263326e-06, "loss": 0.8490426063537597, "step": 930, "token_acc": 0.7471458208708269 }, { "epoch": 0.0605320018450931, "grad_norm": 0.3573067784309387, "learning_rate": 9.977416695334997e-06, "loss": 0.8080699920654297, "step": 935, "token_acc": 0.7559429175877423 }, { "epoch": 0.06085570238971927, "grad_norm": 0.3948529362678528, "learning_rate": 9.977174701282933e-06, "loss": 0.8302188873291015, "step": 940, "token_acc": 0.7495536651963873 }, { "epoch": 0.061179402934345435, "grad_norm": 0.45548227429389954, "learning_rate": 9.976931420539626e-06, "loss": 0.8283008575439453, "step": 945, "token_acc": 0.7517305239165204 }, { "epoch": 0.0615031034789716, "grad_norm": 0.4732871949672699, "learning_rate": 9.976686853167967e-06, "loss": 0.8526391983032227, "step": 950, "token_acc": 0.7461732638702401 }, { "epoch": 0.06182680402359777, "grad_norm": 0.36254310607910156, "learning_rate": 9.976440999231186e-06, "loss": 0.8304115295410156, "step": 955, "token_acc": 0.7506567456654786 }, { "epoch": 0.062150504568223935, "grad_norm": 0.2739548683166504, "learning_rate": 9.976193858792835e-06, "loss": 0.8154356002807617, "step": 960, "token_acc": 0.7546265336255471 }, { "epoch": 0.0624742051128501, "grad_norm": 0.33888575434684753, "learning_rate": 9.975945431916806e-06, "loss": 0.8214314460754395, "step": 965, "token_acc": 0.7521550111237354 }, { "epoch": 0.06279790565747627, "grad_norm": 0.4098851978778839, "learning_rate": 9.975695718667325e-06, "loss": 0.8471939086914062, "step": 970, "token_acc": 0.7476107986063802 }, { "epoch": 0.06312160620210243, "grad_norm": 0.34324970841407776, "learning_rate": 9.975444719108944e-06, "loss": 0.823505973815918, "step": 975, "token_acc": 0.7532748452440785 }, { "epoch": 0.0634453067467286, "grad_norm": 0.46451514959335327, "learning_rate": 9.975192433306552e-06, "loss": 0.8495012283325195, "step": 980, "token_acc": 0.7481056186674854 }, { "epoch": 0.06376900729135476, "grad_norm": 0.40157556533813477, "learning_rate": 9.97493886132537e-06, "loss": 0.8641617774963379, "step": 985, "token_acc": 0.7435505690575385 }, { "epoch": 0.06409270783598094, "grad_norm": 0.3853186070919037, "learning_rate": 9.97468400323095e-06, "loss": 0.845036792755127, "step": 990, "token_acc": 0.7469988468774655 }, { "epoch": 0.0644164083806071, "grad_norm": 0.34764206409454346, "learning_rate": 9.97442785908918e-06, "loss": 0.8330976486206054, "step": 995, "token_acc": 0.7490758675027084 }, { "epoch": 0.06474010892523327, "grad_norm": 0.31506723165512085, "learning_rate": 9.974170428966275e-06, "loss": 0.8283443450927734, "step": 1000, "token_acc": 0.751051160387109 }, { "epoch": 0.06506380946985943, "grad_norm": 0.2967841625213623, "learning_rate": 9.973911712928788e-06, "loss": 0.8187541961669922, "step": 1005, "token_acc": 0.7537403793128252 }, { "epoch": 0.0653875100144856, "grad_norm": 0.39454829692840576, "learning_rate": 9.973651711043598e-06, "loss": 0.8380043029785156, "step": 1010, "token_acc": 0.750283540398836 }, { "epoch": 0.06571121055911176, "grad_norm": 0.3047250509262085, "learning_rate": 9.973390423377924e-06, "loss": 0.8382277488708496, "step": 1015, "token_acc": 0.7497977170445959 }, { "epoch": 0.06603491110373794, "grad_norm": 0.4503442645072937, "learning_rate": 9.973127849999314e-06, "loss": 0.826992416381836, "step": 1020, "token_acc": 0.752088574388226 }, { "epoch": 0.0663586116483641, "grad_norm": 0.28738656640052795, "learning_rate": 9.972863990975644e-06, "loss": 0.8347396850585938, "step": 1025, "token_acc": 0.7500524370100417 }, { "epoch": 0.06668231219299027, "grad_norm": 0.37331703305244446, "learning_rate": 9.97259884637513e-06, "loss": 0.8439510345458985, "step": 1030, "token_acc": 0.7482383868175552 }, { "epoch": 0.06700601273761643, "grad_norm": 0.37928661704063416, "learning_rate": 9.972332416266316e-06, "loss": 0.8318387985229492, "step": 1035, "token_acc": 0.7508695284717752 }, { "epoch": 0.0673297132822426, "grad_norm": 0.3839714229106903, "learning_rate": 9.972064700718079e-06, "loss": 0.8273399353027344, "step": 1040, "token_acc": 0.7525713994027717 }, { "epoch": 0.06765341382686876, "grad_norm": 0.44493699073791504, "learning_rate": 9.971795699799627e-06, "loss": 0.8212203979492188, "step": 1045, "token_acc": 0.7536179472248613 }, { "epoch": 0.06797711437149492, "grad_norm": 0.2760777175426483, "learning_rate": 9.971525413580502e-06, "loss": 0.8352254867553711, "step": 1050, "token_acc": 0.7482090706338708 }, { "epoch": 0.0683008149161211, "grad_norm": 0.4302615523338318, "learning_rate": 9.971253842130582e-06, "loss": 0.8311487197875976, "step": 1055, "token_acc": 0.7491002214839424 }, { "epoch": 0.06862451546074726, "grad_norm": 0.5115905404090881, "learning_rate": 9.970980985520068e-06, "loss": 0.8223262786865234, "step": 1060, "token_acc": 0.7540657825363994 }, { "epoch": 0.06894821600537343, "grad_norm": 0.5176857113838196, "learning_rate": 9.9707068438195e-06, "loss": 0.8269092559814453, "step": 1065, "token_acc": 0.7512535750102143 }, { "epoch": 0.06927191654999959, "grad_norm": 0.5241871476173401, "learning_rate": 9.97043141709975e-06, "loss": 0.8237984657287598, "step": 1070, "token_acc": 0.7534184705412605 }, { "epoch": 0.06959561709462576, "grad_norm": 0.41725751757621765, "learning_rate": 9.970154705432021e-06, "loss": 0.8271929740905761, "step": 1075, "token_acc": 0.7519510871833396 }, { "epoch": 0.06991931763925192, "grad_norm": 0.33261430263519287, "learning_rate": 9.969876708887845e-06, "loss": 0.8370507240295411, "step": 1080, "token_acc": 0.748943443968882 }, { "epoch": 0.0702430181838781, "grad_norm": 0.3709154725074768, "learning_rate": 9.969597427539093e-06, "loss": 0.8221452713012696, "step": 1085, "token_acc": 0.7534447914752893 }, { "epoch": 0.07056671872850426, "grad_norm": 0.3518909513950348, "learning_rate": 9.96931686145796e-06, "loss": 0.8245235443115234, "step": 1090, "token_acc": 0.7540494154982028 }, { "epoch": 0.07089041927313043, "grad_norm": 0.48535478115081787, "learning_rate": 9.969035010716982e-06, "loss": 0.8441253662109375, "step": 1095, "token_acc": 0.7484240212342402 }, { "epoch": 0.07121411981775659, "grad_norm": 0.4184863269329071, "learning_rate": 9.968751875389023e-06, "loss": 0.8196090698242188, "step": 1100, "token_acc": 0.7542052729947907 }, { "epoch": 0.07153782036238276, "grad_norm": 0.40680333971977234, "learning_rate": 9.968467455547273e-06, "loss": 0.8299535751342774, "step": 1105, "token_acc": 0.7513151924656947 }, { "epoch": 0.07186152090700892, "grad_norm": 0.4117944836616516, "learning_rate": 9.968181751265265e-06, "loss": 0.8294032096862793, "step": 1110, "token_acc": 0.751205668128684 }, { "epoch": 0.0721852214516351, "grad_norm": 0.3121304214000702, "learning_rate": 9.967894762616856e-06, "loss": 0.8066354751586914, "step": 1115, "token_acc": 0.7579650664587749 }, { "epoch": 0.07250892199626126, "grad_norm": 0.28385818004608154, "learning_rate": 9.967606489676239e-06, "loss": 0.8365500450134278, "step": 1120, "token_acc": 0.7496921889635753 }, { "epoch": 0.07283262254088743, "grad_norm": 0.38698074221611023, "learning_rate": 9.967316932517939e-06, "loss": 0.8247472763061523, "step": 1125, "token_acc": 0.7527137858469666 }, { "epoch": 0.07315632308551359, "grad_norm": 0.3490273952484131, "learning_rate": 9.96702609121681e-06, "loss": 0.8426301956176758, "step": 1130, "token_acc": 0.7488177020274654 }, { "epoch": 0.07348002363013975, "grad_norm": 0.39180025458335876, "learning_rate": 9.966733965848038e-06, "loss": 0.8122749328613281, "step": 1135, "token_acc": 0.7554935686713135 }, { "epoch": 0.07380372417476593, "grad_norm": 0.3861452639102936, "learning_rate": 9.966440556487149e-06, "loss": 0.8271347999572753, "step": 1140, "token_acc": 0.7513701333574899 }, { "epoch": 0.07412742471939208, "grad_norm": 0.4037511646747589, "learning_rate": 9.966145863209988e-06, "loss": 0.8223764419555664, "step": 1145, "token_acc": 0.7531209090786402 }, { "epoch": 0.07445112526401826, "grad_norm": 0.29931265115737915, "learning_rate": 9.965849886092743e-06, "loss": 0.8458913803100586, "step": 1150, "token_acc": 0.7470527469087495 }, { "epoch": 0.07477482580864442, "grad_norm": 0.4146230220794678, "learning_rate": 9.965552625211929e-06, "loss": 0.838533592224121, "step": 1155, "token_acc": 0.7506490763860421 }, { "epoch": 0.07509852635327059, "grad_norm": 0.3771176040172577, "learning_rate": 9.965254080644391e-06, "loss": 0.8467449188232422, "step": 1160, "token_acc": 0.7464503882657463 }, { "epoch": 0.07542222689789675, "grad_norm": 0.2941979169845581, "learning_rate": 9.964954252467309e-06, "loss": 0.8388958930969238, "step": 1165, "token_acc": 0.7480664481595888 }, { "epoch": 0.07574592744252293, "grad_norm": 0.4028726816177368, "learning_rate": 9.964653140758196e-06, "loss": 0.8034677505493164, "step": 1170, "token_acc": 0.7568650818541053 }, { "epoch": 0.07606962798714909, "grad_norm": 0.482595831155777, "learning_rate": 9.964350745594894e-06, "loss": 0.8295696258544922, "step": 1175, "token_acc": 0.7522698032329072 }, { "epoch": 0.07639332853177526, "grad_norm": 0.23872578144073486, "learning_rate": 9.964047067055578e-06, "loss": 0.8218801498413086, "step": 1180, "token_acc": 0.7533661949435523 }, { "epoch": 0.07671702907640142, "grad_norm": 0.39604368805885315, "learning_rate": 9.963742105218752e-06, "loss": 0.8206081390380859, "step": 1185, "token_acc": 0.7533795980584861 }, { "epoch": 0.07704072962102759, "grad_norm": 0.3759368062019348, "learning_rate": 9.963435860163258e-06, "loss": 0.8157907485961914, "step": 1190, "token_acc": 0.7549900537234259 }, { "epoch": 0.07736443016565375, "grad_norm": 0.3664221465587616, "learning_rate": 9.963128331968264e-06, "loss": 0.8134490966796875, "step": 1195, "token_acc": 0.7564195249953142 }, { "epoch": 0.07768813071027993, "grad_norm": 0.4156801998615265, "learning_rate": 9.962819520713271e-06, "loss": 0.8452971458435059, "step": 1200, "token_acc": 0.7476802332711096 }, { "epoch": 0.07801183125490609, "grad_norm": 0.4046424925327301, "learning_rate": 9.962509426478114e-06, "loss": 0.845283031463623, "step": 1205, "token_acc": 0.7501433343304417 }, { "epoch": 0.07833553179953225, "grad_norm": 0.387143611907959, "learning_rate": 9.962198049342958e-06, "loss": 0.8433997154235839, "step": 1210, "token_acc": 0.7485941260252443 }, { "epoch": 0.07865923234415842, "grad_norm": 0.3061625361442566, "learning_rate": 9.961885389388297e-06, "loss": 0.8256988525390625, "step": 1215, "token_acc": 0.7522440962514155 }, { "epoch": 0.07898293288878458, "grad_norm": 0.4471091330051422, "learning_rate": 9.961571446694961e-06, "loss": 0.8365732192993164, "step": 1220, "token_acc": 0.7491712321596817 }, { "epoch": 0.07930663343341075, "grad_norm": 0.35513952374458313, "learning_rate": 9.961256221344114e-06, "loss": 0.8171173095703125, "step": 1225, "token_acc": 0.7541171604752595 }, { "epoch": 0.07963033397803691, "grad_norm": 0.3916638493537903, "learning_rate": 9.960939713417242e-06, "loss": 0.809746265411377, "step": 1230, "token_acc": 0.7544343713046906 }, { "epoch": 0.07995403452266309, "grad_norm": 0.38526245951652527, "learning_rate": 9.96062192299617e-06, "loss": 0.8348697662353516, "step": 1235, "token_acc": 0.7504578908173603 }, { "epoch": 0.08027773506728925, "grad_norm": 0.36683419346809387, "learning_rate": 9.960302850163053e-06, "loss": 0.8151309967041016, "step": 1240, "token_acc": 0.7549775208734746 }, { "epoch": 0.08060143561191542, "grad_norm": 0.43303632736206055, "learning_rate": 9.959982495000376e-06, "loss": 0.8334847450256347, "step": 1245, "token_acc": 0.7505233518596548 }, { "epoch": 0.08092513615654158, "grad_norm": 0.4581274390220642, "learning_rate": 9.959660857590958e-06, "loss": 0.819674015045166, "step": 1250, "token_acc": 0.7537339231415046 }, { "epoch": 0.08124883670116775, "grad_norm": 0.3025493919849396, "learning_rate": 9.95933793801795e-06, "loss": 0.8045278549194336, "step": 1255, "token_acc": 0.7555210457712002 }, { "epoch": 0.08157253724579391, "grad_norm": 0.29485049843788147, "learning_rate": 9.959013736364828e-06, "loss": 0.8282971382141113, "step": 1260, "token_acc": 0.7515371552380394 }, { "epoch": 0.08189623779042009, "grad_norm": 0.3592197597026825, "learning_rate": 9.958688252715408e-06, "loss": 0.8533744812011719, "step": 1265, "token_acc": 0.7457571780254798 }, { "epoch": 0.08221993833504625, "grad_norm": 0.4529035687446594, "learning_rate": 9.95836148715383e-06, "loss": 0.7977831840515137, "step": 1270, "token_acc": 0.7578859168546568 }, { "epoch": 0.08254363887967242, "grad_norm": 0.3495670557022095, "learning_rate": 9.958033439764574e-06, "loss": 0.7991341590881348, "step": 1275, "token_acc": 0.7588739828458324 }, { "epoch": 0.08286733942429858, "grad_norm": 0.32097184658050537, "learning_rate": 9.95770411063244e-06, "loss": 0.8220799446105957, "step": 1280, "token_acc": 0.75155500970643 }, { "epoch": 0.08319103996892475, "grad_norm": 0.45630165934562683, "learning_rate": 9.95737349984257e-06, "loss": 0.8429093360900879, "step": 1285, "token_acc": 0.7477213122530716 }, { "epoch": 0.08351474051355091, "grad_norm": 0.49449244141578674, "learning_rate": 9.957041607480434e-06, "loss": 0.8045038223266602, "step": 1290, "token_acc": 0.7576282043385605 }, { "epoch": 0.08383844105817707, "grad_norm": 0.3417322635650635, "learning_rate": 9.956708433631828e-06, "loss": 0.8348349571228028, "step": 1295, "token_acc": 0.7501807906578102 }, { "epoch": 0.08416214160280325, "grad_norm": 0.3610595166683197, "learning_rate": 9.956373978382886e-06, "loss": 0.8291410446166992, "step": 1300, "token_acc": 0.7498621576916008 }, { "epoch": 0.08448584214742941, "grad_norm": 0.3314981460571289, "learning_rate": 9.956038241820071e-06, "loss": 0.8184576034545898, "step": 1305, "token_acc": 0.7528265980073884 }, { "epoch": 0.08480954269205558, "grad_norm": 0.2848573327064514, "learning_rate": 9.955701224030177e-06, "loss": 0.8175847053527832, "step": 1310, "token_acc": 0.7546665045297015 }, { "epoch": 0.08513324323668174, "grad_norm": 0.3704996705055237, "learning_rate": 9.955362925100329e-06, "loss": 0.8106403350830078, "step": 1315, "token_acc": 0.7557008420009906 }, { "epoch": 0.08545694378130791, "grad_norm": 0.38236308097839355, "learning_rate": 9.955023345117982e-06, "loss": 0.8168708801269531, "step": 1320, "token_acc": 0.7551257815908099 }, { "epoch": 0.08578064432593407, "grad_norm": 0.3814598023891449, "learning_rate": 9.954682484170926e-06, "loss": 0.8283339500427246, "step": 1325, "token_acc": 0.7518782347376036 }, { "epoch": 0.08610434487056025, "grad_norm": 0.39399048686027527, "learning_rate": 9.95434034234728e-06, "loss": 0.8259765625, "step": 1330, "token_acc": 0.7523408299018055 }, { "epoch": 0.08642804541518641, "grad_norm": 0.339703768491745, "learning_rate": 9.953996919735492e-06, "loss": 0.8248964309692383, "step": 1335, "token_acc": 0.7532640081032906 }, { "epoch": 0.08675174595981258, "grad_norm": 0.4779535233974457, "learning_rate": 9.953652216424344e-06, "loss": 0.8183027267456054, "step": 1340, "token_acc": 0.7553601967407743 }, { "epoch": 0.08707544650443874, "grad_norm": 0.3550388216972351, "learning_rate": 9.953306232502948e-06, "loss": 0.8300731658935547, "step": 1345, "token_acc": 0.7504188060961824 }, { "epoch": 0.08739914704906492, "grad_norm": 0.27982622385025024, "learning_rate": 9.952958968060748e-06, "loss": 0.8285084724426269, "step": 1350, "token_acc": 0.7506129314571941 }, { "epoch": 0.08772284759369108, "grad_norm": 0.2636326849460602, "learning_rate": 9.952610423187516e-06, "loss": 0.8386549949645996, "step": 1355, "token_acc": 0.7508162716552068 }, { "epoch": 0.08804654813831725, "grad_norm": 0.4213744103908539, "learning_rate": 9.952260597973362e-06, "loss": 0.8397204399108886, "step": 1360, "token_acc": 0.7480089514908181 }, { "epoch": 0.08837024868294341, "grad_norm": 0.3875499367713928, "learning_rate": 9.951909492508715e-06, "loss": 0.7796120643615723, "step": 1365, "token_acc": 0.7650329738224114 }, { "epoch": 0.08869394922756957, "grad_norm": 0.2554747462272644, "learning_rate": 9.95155710688435e-06, "loss": 0.8093796730041504, "step": 1370, "token_acc": 0.7566841437921935 }, { "epoch": 0.08901764977219574, "grad_norm": 0.38105618953704834, "learning_rate": 9.95120344119136e-06, "loss": 0.8314165115356446, "step": 1375, "token_acc": 0.750195098551617 }, { "epoch": 0.0893413503168219, "grad_norm": 0.3186558485031128, "learning_rate": 9.950848495521175e-06, "loss": 0.8185358047485352, "step": 1380, "token_acc": 0.75370798748129 }, { "epoch": 0.08966505086144808, "grad_norm": 0.503135621547699, "learning_rate": 9.950492269965557e-06, "loss": 0.8326706886291504, "step": 1385, "token_acc": 0.7527409947683297 }, { "epoch": 0.08998875140607424, "grad_norm": 0.4720476269721985, "learning_rate": 9.950134764616595e-06, "loss": 0.8158396720886231, "step": 1390, "token_acc": 0.7540396310492883 }, { "epoch": 0.09031245195070041, "grad_norm": 0.33322903513908386, "learning_rate": 9.94977597956671e-06, "loss": 0.8135051727294922, "step": 1395, "token_acc": 0.7544233961835386 }, { "epoch": 0.09063615249532657, "grad_norm": 0.3454587757587433, "learning_rate": 9.949415914908656e-06, "loss": 0.8412824630737304, "step": 1400, "token_acc": 0.7515318944377172 }, { "epoch": 0.09095985303995274, "grad_norm": 0.34025445580482483, "learning_rate": 9.949054570735516e-06, "loss": 0.8223638534545898, "step": 1405, "token_acc": 0.7531854880925254 }, { "epoch": 0.0912835535845789, "grad_norm": 0.3533569276332855, "learning_rate": 9.948691947140706e-06, "loss": 0.8023181915283203, "step": 1410, "token_acc": 0.7584036362384216 }, { "epoch": 0.09160725412920508, "grad_norm": 0.40662574768066406, "learning_rate": 9.948328044217967e-06, "loss": 0.8549972534179687, "step": 1415, "token_acc": 0.7470087299139597 }, { "epoch": 0.09193095467383124, "grad_norm": 0.3114791810512543, "learning_rate": 9.947962862061378e-06, "loss": 0.8317176818847656, "step": 1420, "token_acc": 0.7501793388263531 }, { "epoch": 0.09225465521845741, "grad_norm": 0.3416985869407654, "learning_rate": 9.947596400765343e-06, "loss": 0.8255702972412109, "step": 1425, "token_acc": 0.751184170233837 }, { "epoch": 0.09257835576308357, "grad_norm": 0.3436278700828552, "learning_rate": 9.9472286604246e-06, "loss": 0.8027515411376953, "step": 1430, "token_acc": 0.7577578491717046 }, { "epoch": 0.09290205630770974, "grad_norm": 0.46781232953071594, "learning_rate": 9.946859641134217e-06, "loss": 0.8091534614562989, "step": 1435, "token_acc": 0.7565264947353162 }, { "epoch": 0.0932257568523359, "grad_norm": 0.374834805727005, "learning_rate": 9.94648934298959e-06, "loss": 0.8026360511779785, "step": 1440, "token_acc": 0.7581572098562244 }, { "epoch": 0.09354945739696208, "grad_norm": 0.39197078347206116, "learning_rate": 9.946117766086451e-06, "loss": 0.8028425216674805, "step": 1445, "token_acc": 0.7585168062450264 }, { "epoch": 0.09387315794158824, "grad_norm": 0.3487560749053955, "learning_rate": 9.945744910520857e-06, "loss": 0.8028284072875976, "step": 1450, "token_acc": 0.7569911708305382 }, { "epoch": 0.0941968584862144, "grad_norm": 0.40305736660957336, "learning_rate": 9.945370776389203e-06, "loss": 0.8201408386230469, "step": 1455, "token_acc": 0.7534568103589575 }, { "epoch": 0.09452055903084057, "grad_norm": 0.30857619643211365, "learning_rate": 9.944995363788203e-06, "loss": 0.816007423400879, "step": 1460, "token_acc": 0.7543063441799519 }, { "epoch": 0.09484425957546673, "grad_norm": 0.416228324174881, "learning_rate": 9.944618672814911e-06, "loss": 0.8003097534179687, "step": 1465, "token_acc": 0.7585468782810733 }, { "epoch": 0.0951679601200929, "grad_norm": 0.39137470722198486, "learning_rate": 9.94424070356671e-06, "loss": 0.8270932197570801, "step": 1470, "token_acc": 0.7526637485183002 }, { "epoch": 0.09549166066471906, "grad_norm": 0.38609907031059265, "learning_rate": 9.943861456141308e-06, "loss": 0.7915128231048584, "step": 1475, "token_acc": 0.761497653824197 }, { "epoch": 0.09581536120934524, "grad_norm": 0.3931332230567932, "learning_rate": 9.94348093063675e-06, "loss": 0.8080845832824707, "step": 1480, "token_acc": 0.7567216934298839 }, { "epoch": 0.0961390617539714, "grad_norm": 0.3775719702243805, "learning_rate": 9.94309912715141e-06, "loss": 0.7926640510559082, "step": 1485, "token_acc": 0.7607235041571008 }, { "epoch": 0.09646276229859757, "grad_norm": 0.33790385723114014, "learning_rate": 9.942716045783988e-06, "loss": 0.8493965148925782, "step": 1490, "token_acc": 0.7471104857724753 }, { "epoch": 0.09678646284322373, "grad_norm": 0.4099980592727661, "learning_rate": 9.942331686633521e-06, "loss": 0.7843810558319092, "step": 1495, "token_acc": 0.7621827746734675 }, { "epoch": 0.0971101633878499, "grad_norm": 0.5117467045783997, "learning_rate": 9.941946049799372e-06, "loss": 0.8233473777770997, "step": 1500, "token_acc": 0.7528770812928501 }, { "epoch": 0.09743386393247606, "grad_norm": 0.3538203239440918, "learning_rate": 9.941559135381233e-06, "loss": 0.8117660522460938, "step": 1505, "token_acc": 0.7548127105767325 }, { "epoch": 0.09775756447710224, "grad_norm": 0.3619396984577179, "learning_rate": 9.941170943479131e-06, "loss": 0.8286912918090821, "step": 1510, "token_acc": 0.7528947742601557 }, { "epoch": 0.0980812650217284, "grad_norm": 0.39819517731666565, "learning_rate": 9.940781474193421e-06, "loss": 0.795016098022461, "step": 1515, "token_acc": 0.7599387968754194 }, { "epoch": 0.09840496556635457, "grad_norm": 0.4854394197463989, "learning_rate": 9.940390727624785e-06, "loss": 0.8050803184509278, "step": 1520, "token_acc": 0.7573598619535662 }, { "epoch": 0.09872866611098073, "grad_norm": 0.3732016980648041, "learning_rate": 9.939998703874241e-06, "loss": 0.8357625961303711, "step": 1525, "token_acc": 0.7493017301574987 }, { "epoch": 0.0990523666556069, "grad_norm": 0.3567621409893036, "learning_rate": 9.939605403043133e-06, "loss": 0.7986313343048096, "step": 1530, "token_acc": 0.7583465165492161 }, { "epoch": 0.09937606720023306, "grad_norm": 0.27592092752456665, "learning_rate": 9.939210825233137e-06, "loss": 0.8070465087890625, "step": 1535, "token_acc": 0.7566992002349894 }, { "epoch": 0.09969976774485922, "grad_norm": 0.38391321897506714, "learning_rate": 9.938814970546257e-06, "loss": 0.8320230484008789, "step": 1540, "token_acc": 0.7503169072507052 }, { "epoch": 0.1000234682894854, "grad_norm": 0.3723084032535553, "learning_rate": 9.938417839084833e-06, "loss": 0.8266716957092285, "step": 1545, "token_acc": 0.7534492739640117 }, { "epoch": 0.10034716883411156, "grad_norm": 0.3520377576351166, "learning_rate": 9.938019430951526e-06, "loss": 0.8294548034667969, "step": 1550, "token_acc": 0.7521480997317429 }, { "epoch": 0.10067086937873773, "grad_norm": 0.35556313395500183, "learning_rate": 9.937619746249333e-06, "loss": 0.8181920051574707, "step": 1555, "token_acc": 0.7548768422921793 }, { "epoch": 0.10099456992336389, "grad_norm": 0.3761628270149231, "learning_rate": 9.937218785081584e-06, "loss": 0.8133426666259765, "step": 1560, "token_acc": 0.7564381834076155 }, { "epoch": 0.10131827046799007, "grad_norm": 0.3608764708042145, "learning_rate": 9.936816547551928e-06, "loss": 0.8028289794921875, "step": 1565, "token_acc": 0.7580036503551697 }, { "epoch": 0.10164197101261623, "grad_norm": 0.48098722100257874, "learning_rate": 9.936413033764355e-06, "loss": 0.8149139404296875, "step": 1570, "token_acc": 0.7551047850846819 }, { "epoch": 0.1019656715572424, "grad_norm": 0.40561845898628235, "learning_rate": 9.936008243823184e-06, "loss": 0.7809530735015869, "step": 1575, "token_acc": 0.7615172240697747 }, { "epoch": 0.10228937210186856, "grad_norm": 0.3769603669643402, "learning_rate": 9.935602177833052e-06, "loss": 0.807318115234375, "step": 1580, "token_acc": 0.7569699730999919 }, { "epoch": 0.10261307264649473, "grad_norm": 0.2720699608325958, "learning_rate": 9.935194835898941e-06, "loss": 0.7992434501647949, "step": 1585, "token_acc": 0.7585371550602289 }, { "epoch": 0.10293677319112089, "grad_norm": 0.5171566605567932, "learning_rate": 9.934786218126154e-06, "loss": 0.8088821411132813, "step": 1590, "token_acc": 0.7539421031760337 }, { "epoch": 0.10326047373574707, "grad_norm": 0.40040063858032227, "learning_rate": 9.934376324620327e-06, "loss": 0.8035178184509277, "step": 1595, "token_acc": 0.7585466111748825 }, { "epoch": 0.10358417428037323, "grad_norm": 0.33128225803375244, "learning_rate": 9.933965155487427e-06, "loss": 0.8066617965698242, "step": 1600, "token_acc": 0.7566671926779233 }, { "epoch": 0.1039078748249994, "grad_norm": 0.40732792019844055, "learning_rate": 9.933552710833745e-06, "loss": 0.8089414596557617, "step": 1605, "token_acc": 0.7556742060052014 }, { "epoch": 0.10423157536962556, "grad_norm": 0.3686521351337433, "learning_rate": 9.933138990765906e-06, "loss": 0.8095306396484375, "step": 1610, "token_acc": 0.7570073141142067 }, { "epoch": 0.10455527591425172, "grad_norm": 0.26073089241981506, "learning_rate": 9.932723995390866e-06, "loss": 0.8156635284423828, "step": 1615, "token_acc": 0.7548855673129699 }, { "epoch": 0.10487897645887789, "grad_norm": 0.44252339005470276, "learning_rate": 9.932307724815909e-06, "loss": 0.8186473846435547, "step": 1620, "token_acc": 0.754936874855365 }, { "epoch": 0.10520267700350405, "grad_norm": 0.33286410570144653, "learning_rate": 9.931890179148649e-06, "loss": 0.7976008415222168, "step": 1625, "token_acc": 0.7574486301369863 }, { "epoch": 0.10552637754813023, "grad_norm": 0.32357296347618103, "learning_rate": 9.931471358497027e-06, "loss": 0.7932855606079101, "step": 1630, "token_acc": 0.7595069381036279 }, { "epoch": 0.10585007809275639, "grad_norm": 0.37899741530418396, "learning_rate": 9.931051262969315e-06, "loss": 0.8027450561523437, "step": 1635, "token_acc": 0.7595510542282118 }, { "epoch": 0.10617377863738256, "grad_norm": 0.33620673418045044, "learning_rate": 9.93062989267412e-06, "loss": 0.8190309524536132, "step": 1640, "token_acc": 0.7533290391309195 }, { "epoch": 0.10649747918200872, "grad_norm": 0.40369850397109985, "learning_rate": 9.930207247720372e-06, "loss": 0.8120275497436523, "step": 1645, "token_acc": 0.7548441191231012 }, { "epoch": 0.1068211797266349, "grad_norm": 0.4382023811340332, "learning_rate": 9.92978332821733e-06, "loss": 0.8356988906860352, "step": 1650, "token_acc": 0.7501784615384616 }, { "epoch": 0.10714488027126105, "grad_norm": 0.47011998295783997, "learning_rate": 9.929358134274589e-06, "loss": 0.8160425186157226, "step": 1655, "token_acc": 0.7553509300352835 }, { "epoch": 0.10746858081588723, "grad_norm": 0.2733902633190155, "learning_rate": 9.928931666002066e-06, "loss": 0.8112756729125976, "step": 1660, "token_acc": 0.7556161388497122 }, { "epoch": 0.10779228136051339, "grad_norm": 0.38214224576950073, "learning_rate": 9.928503923510012e-06, "loss": 0.8148434638977051, "step": 1665, "token_acc": 0.7527079351075823 }, { "epoch": 0.10811598190513956, "grad_norm": 0.2747705578804016, "learning_rate": 9.928074906909006e-06, "loss": 0.816562271118164, "step": 1670, "token_acc": 0.7545947508309823 }, { "epoch": 0.10843968244976572, "grad_norm": 0.30863821506500244, "learning_rate": 9.92764461630996e-06, "loss": 0.7731424808502197, "step": 1675, "token_acc": 0.7639098029787288 }, { "epoch": 0.1087633829943919, "grad_norm": 0.5135633945465088, "learning_rate": 9.927213051824108e-06, "loss": 0.8120750427246094, "step": 1680, "token_acc": 0.754845131447977 }, { "epoch": 0.10908708353901805, "grad_norm": 0.33060863614082336, "learning_rate": 9.926780213563018e-06, "loss": 0.803803825378418, "step": 1685, "token_acc": 0.75786507269545 }, { "epoch": 0.10941078408364423, "grad_norm": 0.29626965522766113, "learning_rate": 9.926346101638588e-06, "loss": 0.8149587631225585, "step": 1690, "token_acc": 0.7550958433783473 }, { "epoch": 0.10973448462827039, "grad_norm": 0.36867237091064453, "learning_rate": 9.925910716163043e-06, "loss": 0.794578742980957, "step": 1695, "token_acc": 0.7580276212136194 }, { "epoch": 0.11005818517289655, "grad_norm": 0.40186992287635803, "learning_rate": 9.925474057248938e-06, "loss": 0.7921136379241943, "step": 1700, "token_acc": 0.7593942831370994 }, { "epoch": 0.11038188571752272, "grad_norm": 0.3756592273712158, "learning_rate": 9.925036125009157e-06, "loss": 0.8010628700256348, "step": 1705, "token_acc": 0.7571059903346359 }, { "epoch": 0.11070558626214888, "grad_norm": 0.3192559778690338, "learning_rate": 9.924596919556917e-06, "loss": 0.8130430221557617, "step": 1710, "token_acc": 0.7549420586230402 }, { "epoch": 0.11102928680677505, "grad_norm": 0.3456304967403412, "learning_rate": 9.924156441005756e-06, "loss": 0.8027805328369141, "step": 1715, "token_acc": 0.7585145737368241 }, { "epoch": 0.11135298735140121, "grad_norm": 0.32546669244766235, "learning_rate": 9.923714689469548e-06, "loss": 0.7994984149932861, "step": 1720, "token_acc": 0.7579972696749437 }, { "epoch": 0.11167668789602739, "grad_norm": 0.35042431950569153, "learning_rate": 9.923271665062495e-06, "loss": 0.820315933227539, "step": 1725, "token_acc": 0.7541205794265238 }, { "epoch": 0.11200038844065355, "grad_norm": 0.33014485239982605, "learning_rate": 9.922827367899125e-06, "loss": 0.803193473815918, "step": 1730, "token_acc": 0.7605264166123903 }, { "epoch": 0.11232408898527972, "grad_norm": 0.4758773148059845, "learning_rate": 9.922381798094295e-06, "loss": 0.7970531940460205, "step": 1735, "token_acc": 0.7590055226211158 }, { "epoch": 0.11264778952990588, "grad_norm": 0.40979859232902527, "learning_rate": 9.9219349557632e-06, "loss": 0.821840476989746, "step": 1740, "token_acc": 0.7523398410673992 }, { "epoch": 0.11297149007453205, "grad_norm": 0.2812923789024353, "learning_rate": 9.921486841021351e-06, "loss": 0.7976829051971436, "step": 1745, "token_acc": 0.7585343857269695 }, { "epoch": 0.11329519061915821, "grad_norm": 0.34597551822662354, "learning_rate": 9.921037453984594e-06, "loss": 0.7970170021057129, "step": 1750, "token_acc": 0.7590407449376755 }, { "epoch": 0.11361889116378439, "grad_norm": 0.40089061856269836, "learning_rate": 9.920586794769106e-06, "loss": 0.8127138137817382, "step": 1755, "token_acc": 0.7569442425440611 }, { "epoch": 0.11394259170841055, "grad_norm": 0.3393767476081848, "learning_rate": 9.920134863491392e-06, "loss": 0.7945090293884277, "step": 1760, "token_acc": 0.7606683495612453 }, { "epoch": 0.11426629225303672, "grad_norm": 0.4965689480304718, "learning_rate": 9.919681660268282e-06, "loss": 0.7964975833892822, "step": 1765, "token_acc": 0.7588099578252067 }, { "epoch": 0.11458999279766288, "grad_norm": 0.4919307827949524, "learning_rate": 9.919227185216936e-06, "loss": 0.817933464050293, "step": 1770, "token_acc": 0.7541659189376266 }, { "epoch": 0.11491369334228904, "grad_norm": 0.3712409436702728, "learning_rate": 9.918771438454848e-06, "loss": 0.8282442092895508, "step": 1775, "token_acc": 0.7513946029997732 }, { "epoch": 0.11523739388691522, "grad_norm": 0.342835932970047, "learning_rate": 9.918314420099835e-06, "loss": 0.7863557815551758, "step": 1780, "token_acc": 0.7603969967454001 }, { "epoch": 0.11556109443154138, "grad_norm": 0.349636435508728, "learning_rate": 9.917856130270042e-06, "loss": 0.7885005950927735, "step": 1785, "token_acc": 0.7611608552340781 }, { "epoch": 0.11588479497616755, "grad_norm": 0.4746887981891632, "learning_rate": 9.917396569083953e-06, "loss": 0.7945443153381347, "step": 1790, "token_acc": 0.7598573001654958 }, { "epoch": 0.11620849552079371, "grad_norm": 0.4364038109779358, "learning_rate": 9.916935736660365e-06, "loss": 0.790207815170288, "step": 1795, "token_acc": 0.7618466224243976 }, { "epoch": 0.11653219606541988, "grad_norm": 0.3374902307987213, "learning_rate": 9.916473633118414e-06, "loss": 0.8060110092163086, "step": 1800, "token_acc": 0.7573141451809471 }, { "epoch": 0.11685589661004604, "grad_norm": 0.3760474920272827, "learning_rate": 9.916010258577565e-06, "loss": 0.7860349655151367, "step": 1805, "token_acc": 0.7620488027961977 }, { "epoch": 0.11717959715467222, "grad_norm": 0.479196161031723, "learning_rate": 9.915545613157604e-06, "loss": 0.8160076141357422, "step": 1810, "token_acc": 0.7539424969931531 }, { "epoch": 0.11750329769929838, "grad_norm": 0.4425339996814728, "learning_rate": 9.915079696978657e-06, "loss": 0.8311895370483399, "step": 1815, "token_acc": 0.7510435810858942 }, { "epoch": 0.11782699824392455, "grad_norm": 0.38159993290901184, "learning_rate": 9.914612510161166e-06, "loss": 0.7995384693145752, "step": 1820, "token_acc": 0.7583006204887932 }, { "epoch": 0.11815069878855071, "grad_norm": 0.20836448669433594, "learning_rate": 9.914144052825909e-06, "loss": 0.8120525360107422, "step": 1825, "token_acc": 0.7547441837539433 }, { "epoch": 0.11847439933317688, "grad_norm": 0.37427636981010437, "learning_rate": 9.913674325093993e-06, "loss": 0.7973691463470459, "step": 1830, "token_acc": 0.7587870609652082 }, { "epoch": 0.11879809987780304, "grad_norm": 0.42289912700653076, "learning_rate": 9.913203327086848e-06, "loss": 0.8331962585449219, "step": 1835, "token_acc": 0.7500814967046985 }, { "epoch": 0.11912180042242922, "grad_norm": 0.2651755213737488, "learning_rate": 9.91273105892624e-06, "loss": 0.8212228775024414, "step": 1840, "token_acc": 0.7527467774028895 }, { "epoch": 0.11944550096705538, "grad_norm": 0.36039358377456665, "learning_rate": 9.912257520734254e-06, "loss": 0.806733226776123, "step": 1845, "token_acc": 0.7566651011161454 }, { "epoch": 0.11976920151168155, "grad_norm": 0.4553592801094055, "learning_rate": 9.911782712633311e-06, "loss": 0.8119277954101562, "step": 1850, "token_acc": 0.7564884422233504 }, { "epoch": 0.12009290205630771, "grad_norm": 0.44605401158332825, "learning_rate": 9.911306634746158e-06, "loss": 0.8347728729248047, "step": 1855, "token_acc": 0.7496703512972742 }, { "epoch": 0.12041660260093387, "grad_norm": 0.3287297487258911, "learning_rate": 9.91082928719587e-06, "loss": 0.8093500137329102, "step": 1860, "token_acc": 0.7575369776652208 }, { "epoch": 0.12074030314556004, "grad_norm": 0.30942466855049133, "learning_rate": 9.910350670105848e-06, "loss": 0.8129170417785645, "step": 1865, "token_acc": 0.7568617741924392 }, { "epoch": 0.1210640036901862, "grad_norm": 0.3202270269393921, "learning_rate": 9.909870783599825e-06, "loss": 0.7883732795715332, "step": 1870, "token_acc": 0.7613010195082373 }, { "epoch": 0.12138770423481238, "grad_norm": 0.38599419593811035, "learning_rate": 9.909389627801859e-06, "loss": 0.8048713684082032, "step": 1875, "token_acc": 0.7581891265840033 }, { "epoch": 0.12171140477943854, "grad_norm": 0.3357534110546112, "learning_rate": 9.90890720283634e-06, "loss": 0.8046482086181641, "step": 1880, "token_acc": 0.7567245465924525 }, { "epoch": 0.12203510532406471, "grad_norm": 0.2897888720035553, "learning_rate": 9.908423508827981e-06, "loss": 0.7885725021362304, "step": 1885, "token_acc": 0.7609687356623189 }, { "epoch": 0.12235880586869087, "grad_norm": 0.354964941740036, "learning_rate": 9.90793854590183e-06, "loss": 0.825558090209961, "step": 1890, "token_acc": 0.753131571139234 }, { "epoch": 0.12268250641331704, "grad_norm": 0.34741419553756714, "learning_rate": 9.907452314183253e-06, "loss": 0.7971377849578858, "step": 1895, "token_acc": 0.7593848001601388 }, { "epoch": 0.1230062069579432, "grad_norm": 0.29874104261398315, "learning_rate": 9.906964813797955e-06, "loss": 0.7947663784027099, "step": 1900, "token_acc": 0.7597816075075756 }, { "epoch": 0.12332990750256938, "grad_norm": 0.3150380849838257, "learning_rate": 9.906476044871962e-06, "loss": 0.8050804138183594, "step": 1905, "token_acc": 0.7571348699295779 }, { "epoch": 0.12365360804719554, "grad_norm": 0.4308234751224518, "learning_rate": 9.905986007531627e-06, "loss": 0.7869509696960449, "step": 1910, "token_acc": 0.7615274337026351 }, { "epoch": 0.12397730859182171, "grad_norm": 0.437505304813385, "learning_rate": 9.905494701903639e-06, "loss": 0.790229606628418, "step": 1915, "token_acc": 0.7628057664289548 }, { "epoch": 0.12430100913644787, "grad_norm": 0.3529367446899414, "learning_rate": 9.905002128115005e-06, "loss": 0.8124950408935547, "step": 1920, "token_acc": 0.7559340712995319 }, { "epoch": 0.12462470968107404, "grad_norm": 0.44262439012527466, "learning_rate": 9.904508286293067e-06, "loss": 0.7997640609741211, "step": 1925, "token_acc": 0.7580620023716754 }, { "epoch": 0.1249484102257002, "grad_norm": 0.3023328483104706, "learning_rate": 9.904013176565493e-06, "loss": 0.8044060707092285, "step": 1930, "token_acc": 0.7571042412766367 }, { "epoch": 0.12527211077032638, "grad_norm": 0.3754063546657562, "learning_rate": 9.903516799060274e-06, "loss": 0.8113571166992187, "step": 1935, "token_acc": 0.7547668943392322 }, { "epoch": 0.12559581131495254, "grad_norm": 0.3682366609573364, "learning_rate": 9.903019153905736e-06, "loss": 0.8007579803466797, "step": 1940, "token_acc": 0.758545557791302 }, { "epoch": 0.1259195118595787, "grad_norm": 0.3675124943256378, "learning_rate": 9.902520241230526e-06, "loss": 0.7979817390441895, "step": 1945, "token_acc": 0.7588765576574376 }, { "epoch": 0.12624321240420486, "grad_norm": 0.26925966143608093, "learning_rate": 9.902020061163628e-06, "loss": 0.8102991104125976, "step": 1950, "token_acc": 0.7559841037990341 }, { "epoch": 0.12656691294883105, "grad_norm": 0.46576064825057983, "learning_rate": 9.901518613834342e-06, "loss": 0.7947103977203369, "step": 1955, "token_acc": 0.7617056443655023 }, { "epoch": 0.1268906134934572, "grad_norm": 0.2864416539669037, "learning_rate": 9.901015899372306e-06, "loss": 0.7665206909179687, "step": 1960, "token_acc": 0.765379447723581 }, { "epoch": 0.12721431403808336, "grad_norm": 0.3116483688354492, "learning_rate": 9.900511917907477e-06, "loss": 0.7939901351928711, "step": 1965, "token_acc": 0.7607900090849765 }, { "epoch": 0.12753801458270952, "grad_norm": 0.39957693219184875, "learning_rate": 9.900006669570146e-06, "loss": 0.8042171478271485, "step": 1970, "token_acc": 0.757797975624871 }, { "epoch": 0.1278617151273357, "grad_norm": 0.4044257700443268, "learning_rate": 9.899500154490926e-06, "loss": 0.8048600196838379, "step": 1975, "token_acc": 0.7574681650055058 }, { "epoch": 0.12818541567196187, "grad_norm": 0.34437084197998047, "learning_rate": 9.898992372800765e-06, "loss": 0.7883660793304443, "step": 1980, "token_acc": 0.761359084764432 }, { "epoch": 0.12850911621658803, "grad_norm": 0.3970194160938263, "learning_rate": 9.89848332463093e-06, "loss": 0.7984449386596679, "step": 1985, "token_acc": 0.7579246956270667 }, { "epoch": 0.1288328167612142, "grad_norm": 0.30004093050956726, "learning_rate": 9.897973010113023e-06, "loss": 0.7902321815490723, "step": 1990, "token_acc": 0.7608574690093904 }, { "epoch": 0.12915651730584038, "grad_norm": 0.3238575756549835, "learning_rate": 9.897461429378965e-06, "loss": 0.7920487880706787, "step": 1995, "token_acc": 0.7613509369233568 }, { "epoch": 0.12948021785046654, "grad_norm": 0.3849390745162964, "learning_rate": 9.896948582561012e-06, "loss": 0.7865208148956299, "step": 2000, "token_acc": 0.7626054142739951 }, { "epoch": 0.1298039183950927, "grad_norm": 0.38503870368003845, "learning_rate": 9.896434469791744e-06, "loss": 0.8411520004272461, "step": 2005, "token_acc": 0.7492874406764743 }, { "epoch": 0.13012761893971886, "grad_norm": 0.399854451417923, "learning_rate": 9.89591909120407e-06, "loss": 0.8112757682800293, "step": 2010, "token_acc": 0.7563620752286913 }, { "epoch": 0.13045131948434502, "grad_norm": 0.2996760308742523, "learning_rate": 9.895402446931221e-06, "loss": 0.7766604900360108, "step": 2015, "token_acc": 0.7647095812713405 }, { "epoch": 0.1307750200289712, "grad_norm": 0.3887699842453003, "learning_rate": 9.894884537106763e-06, "loss": 0.807637882232666, "step": 2020, "token_acc": 0.7555888047878895 }, { "epoch": 0.13109872057359737, "grad_norm": 0.38718870282173157, "learning_rate": 9.894365361864583e-06, "loss": 0.7853747367858886, "step": 2025, "token_acc": 0.7630093958636444 }, { "epoch": 0.13142242111822353, "grad_norm": 0.5241858959197998, "learning_rate": 9.893844921338898e-06, "loss": 0.7983800888061523, "step": 2030, "token_acc": 0.7597332313615182 }, { "epoch": 0.13174612166284969, "grad_norm": 0.2670592963695526, "learning_rate": 9.893323215664252e-06, "loss": 0.7782926559448242, "step": 2035, "token_acc": 0.7625667168684189 }, { "epoch": 0.13206982220747587, "grad_norm": 0.27565762400627136, "learning_rate": 9.892800244975513e-06, "loss": 0.8009489059448243, "step": 2040, "token_acc": 0.7595994149872338 }, { "epoch": 0.13239352275210203, "grad_norm": 0.3264261484146118, "learning_rate": 9.892276009407883e-06, "loss": 0.8009617805480957, "step": 2045, "token_acc": 0.7567140494539708 }, { "epoch": 0.1327172232967282, "grad_norm": 0.3297363221645355, "learning_rate": 9.891750509096882e-06, "loss": 0.7939507007598877, "step": 2050, "token_acc": 0.7585339474291826 }, { "epoch": 0.13304092384135435, "grad_norm": 0.3661598861217499, "learning_rate": 9.891223744178364e-06, "loss": 0.7800419807434082, "step": 2055, "token_acc": 0.7630345182895415 }, { "epoch": 0.13336462438598054, "grad_norm": 0.4170563519001007, "learning_rate": 9.890695714788507e-06, "loss": 0.7720829963684082, "step": 2060, "token_acc": 0.765093111565259 }, { "epoch": 0.1336883249306067, "grad_norm": 0.3434704840183258, "learning_rate": 9.890166421063818e-06, "loss": 0.8107850074768066, "step": 2065, "token_acc": 0.756242475003926 }, { "epoch": 0.13401202547523286, "grad_norm": 0.3380182683467865, "learning_rate": 9.889635863141125e-06, "loss": 0.8077285766601563, "step": 2070, "token_acc": 0.7569981977776914 }, { "epoch": 0.13433572601985902, "grad_norm": 0.42324894666671753, "learning_rate": 9.889104041157591e-06, "loss": 0.8035425186157227, "step": 2075, "token_acc": 0.7583204672081627 }, { "epoch": 0.1346594265644852, "grad_norm": 0.4266190826892853, "learning_rate": 9.8885709552507e-06, "loss": 0.7799316883087158, "step": 2080, "token_acc": 0.7618784599741404 }, { "epoch": 0.13498312710911137, "grad_norm": 0.3729105591773987, "learning_rate": 9.888036605558263e-06, "loss": 0.8062995910644531, "step": 2085, "token_acc": 0.7584248238765229 }, { "epoch": 0.13530682765373753, "grad_norm": 0.36872467398643494, "learning_rate": 9.887500992218421e-06, "loss": 0.8012554168701171, "step": 2090, "token_acc": 0.7590693746123494 }, { "epoch": 0.1356305281983637, "grad_norm": 0.3490530848503113, "learning_rate": 9.886964115369642e-06, "loss": 0.8104093551635743, "step": 2095, "token_acc": 0.7541340241188084 }, { "epoch": 0.13595422874298985, "grad_norm": 0.5046199560165405, "learning_rate": 9.886425975150715e-06, "loss": 0.7846456527709961, "step": 2100, "token_acc": 0.7624921943697511 }, { "epoch": 0.13627792928761603, "grad_norm": 0.35594046115875244, "learning_rate": 9.88588657170076e-06, "loss": 0.8071084976196289, "step": 2105, "token_acc": 0.757021792569721 }, { "epoch": 0.1366016298322422, "grad_norm": 0.28654584288597107, "learning_rate": 9.885345905159224e-06, "loss": 0.8212639808654785, "step": 2110, "token_acc": 0.7541596031895523 }, { "epoch": 0.13692533037686835, "grad_norm": 0.3708454370498657, "learning_rate": 9.88480397566588e-06, "loss": 0.8221547126770019, "step": 2115, "token_acc": 0.7548754276027003 }, { "epoch": 0.1372490309214945, "grad_norm": 0.3319258689880371, "learning_rate": 9.884260783360823e-06, "loss": 0.7828885555267334, "step": 2120, "token_acc": 0.7621660688473687 }, { "epoch": 0.1375727314661207, "grad_norm": 0.35026755928993225, "learning_rate": 9.88371632838448e-06, "loss": 0.7899295806884765, "step": 2125, "token_acc": 0.7594405594405594 }, { "epoch": 0.13789643201074686, "grad_norm": 0.2870061993598938, "learning_rate": 9.883170610877605e-06, "loss": 0.7742057800292969, "step": 2130, "token_acc": 0.7662716358404996 }, { "epoch": 0.13822013255537302, "grad_norm": 0.34815409779548645, "learning_rate": 9.882623630981274e-06, "loss": 0.8105604171752929, "step": 2135, "token_acc": 0.7565524193548387 }, { "epoch": 0.13854383309999918, "grad_norm": 0.4651942253112793, "learning_rate": 9.88207538883689e-06, "loss": 0.817144775390625, "step": 2140, "token_acc": 0.7548188182378759 }, { "epoch": 0.13886753364462537, "grad_norm": 0.368376761674881, "learning_rate": 9.881525884586185e-06, "loss": 0.7805706024169922, "step": 2145, "token_acc": 0.7627636665195351 }, { "epoch": 0.13919123418925153, "grad_norm": 0.37820670008659363, "learning_rate": 9.880975118371217e-06, "loss": 0.7768424987792969, "step": 2150, "token_acc": 0.7646564062213841 }, { "epoch": 0.1395149347338777, "grad_norm": 0.34830841422080994, "learning_rate": 9.880423090334369e-06, "loss": 0.7720579147338867, "step": 2155, "token_acc": 0.7654570959716267 }, { "epoch": 0.13983863527850385, "grad_norm": 0.30386555194854736, "learning_rate": 9.879869800618349e-06, "loss": 0.8050990104675293, "step": 2160, "token_acc": 0.7589521734084667 }, { "epoch": 0.14016233582313004, "grad_norm": 0.30525851249694824, "learning_rate": 9.879315249366193e-06, "loss": 0.7762526512145996, "step": 2165, "token_acc": 0.7639546079779918 }, { "epoch": 0.1404860363677562, "grad_norm": 0.35275694727897644, "learning_rate": 9.878759436721264e-06, "loss": 0.7971002101898194, "step": 2170, "token_acc": 0.7579885094571042 }, { "epoch": 0.14080973691238236, "grad_norm": 0.30901145935058594, "learning_rate": 9.878202362827248e-06, "loss": 0.8067163467407227, "step": 2175, "token_acc": 0.7566399093149855 }, { "epoch": 0.14113343745700851, "grad_norm": 0.3778212368488312, "learning_rate": 9.877644027828157e-06, "loss": 0.780291748046875, "step": 2180, "token_acc": 0.7652288256093418 }, { "epoch": 0.14145713800163467, "grad_norm": 0.31788817048072815, "learning_rate": 9.877084431868337e-06, "loss": 0.7849106788635254, "step": 2185, "token_acc": 0.7616381046422492 }, { "epoch": 0.14178083854626086, "grad_norm": 0.36724594235420227, "learning_rate": 9.87652357509245e-06, "loss": 0.7933049201965332, "step": 2190, "token_acc": 0.7598482136464524 }, { "epoch": 0.14210453909088702, "grad_norm": 0.25927862524986267, "learning_rate": 9.875961457645486e-06, "loss": 0.7951359748840332, "step": 2195, "token_acc": 0.7595253747041809 }, { "epoch": 0.14242823963551318, "grad_norm": 0.47269338369369507, "learning_rate": 9.875398079672766e-06, "loss": 0.8180553436279296, "step": 2200, "token_acc": 0.7529515480640384 }, { "epoch": 0.14275194018013934, "grad_norm": 0.42048999667167664, "learning_rate": 9.874833441319933e-06, "loss": 0.8260639190673829, "step": 2205, "token_acc": 0.753173698213607 }, { "epoch": 0.14307564072476553, "grad_norm": 0.23487035930156708, "learning_rate": 9.874267542732955e-06, "loss": 0.7921098709106446, "step": 2210, "token_acc": 0.758734450704772 }, { "epoch": 0.1433993412693917, "grad_norm": 0.32928428053855896, "learning_rate": 9.87370038405813e-06, "loss": 0.8128484725952149, "step": 2215, "token_acc": 0.7560306646259701 }, { "epoch": 0.14372304181401785, "grad_norm": 0.33449527621269226, "learning_rate": 9.873131965442073e-06, "loss": 0.7964910984039306, "step": 2220, "token_acc": 0.7596511167583996 }, { "epoch": 0.144046742358644, "grad_norm": 0.40894728899002075, "learning_rate": 9.872562287031738e-06, "loss": 0.7932240009307862, "step": 2225, "token_acc": 0.761189026476021 }, { "epoch": 0.1443704429032702, "grad_norm": 0.28404590487480164, "learning_rate": 9.871991348974393e-06, "loss": 0.784614086151123, "step": 2230, "token_acc": 0.762766084272714 }, { "epoch": 0.14469414344789636, "grad_norm": 0.3368241488933563, "learning_rate": 9.871419151417636e-06, "loss": 0.784084701538086, "step": 2235, "token_acc": 0.762937286610085 }, { "epoch": 0.14501784399252252, "grad_norm": 0.3983159065246582, "learning_rate": 9.870845694509393e-06, "loss": 0.8018725395202637, "step": 2240, "token_acc": 0.7577257705537196 }, { "epoch": 0.14534154453714868, "grad_norm": 0.4090729355812073, "learning_rate": 9.87027097839791e-06, "loss": 0.8057136535644531, "step": 2245, "token_acc": 0.7585264487814609 }, { "epoch": 0.14566524508177486, "grad_norm": 0.3076653480529785, "learning_rate": 9.869695003231765e-06, "loss": 0.7911934375762939, "step": 2250, "token_acc": 0.7602373196835738 }, { "epoch": 0.14598894562640102, "grad_norm": 0.38469579815864563, "learning_rate": 9.869117769159857e-06, "loss": 0.8029971122741699, "step": 2255, "token_acc": 0.7589153844088187 }, { "epoch": 0.14631264617102718, "grad_norm": 0.46578797698020935, "learning_rate": 9.86853927633141e-06, "loss": 0.79376220703125, "step": 2260, "token_acc": 0.7589450144698764 }, { "epoch": 0.14663634671565334, "grad_norm": 0.3728380799293518, "learning_rate": 9.867959524895977e-06, "loss": 0.8022598266601563, "step": 2265, "token_acc": 0.7606927701222123 }, { "epoch": 0.1469600472602795, "grad_norm": 0.4314401149749756, "learning_rate": 9.867378515003435e-06, "loss": 0.7832779884338379, "step": 2270, "token_acc": 0.7628743142209943 }, { "epoch": 0.1472837478049057, "grad_norm": 0.4426799416542053, "learning_rate": 9.866796246803982e-06, "loss": 0.7909422397613526, "step": 2275, "token_acc": 0.7599928747288262 }, { "epoch": 0.14760744834953185, "grad_norm": 0.4069959223270416, "learning_rate": 9.866212720448149e-06, "loss": 0.7687554359436035, "step": 2280, "token_acc": 0.7670318706922249 }, { "epoch": 0.147931148894158, "grad_norm": 0.31530988216400146, "learning_rate": 9.865627936086786e-06, "loss": 0.7913294315338135, "step": 2285, "token_acc": 0.7604953992770292 }, { "epoch": 0.14825484943878417, "grad_norm": 0.3169374167919159, "learning_rate": 9.86504189387107e-06, "loss": 0.7965718746185303, "step": 2290, "token_acc": 0.7593025977065294 }, { "epoch": 0.14857854998341036, "grad_norm": 0.4109789729118347, "learning_rate": 9.864454593952507e-06, "loss": 0.7766550064086915, "step": 2295, "token_acc": 0.7653599099397391 }, { "epoch": 0.14890225052803652, "grad_norm": 0.33008208870887756, "learning_rate": 9.863866036482923e-06, "loss": 0.8037012100219727, "step": 2300, "token_acc": 0.7578966988636742 }, { "epoch": 0.14922595107266268, "grad_norm": 0.43283799290657043, "learning_rate": 9.86327622161447e-06, "loss": 0.8145326614379883, "step": 2305, "token_acc": 0.7563106860289112 }, { "epoch": 0.14954965161728884, "grad_norm": 0.4650854170322418, "learning_rate": 9.862685149499626e-06, "loss": 0.8113916397094727, "step": 2310, "token_acc": 0.7558115851505852 }, { "epoch": 0.14987335216191502, "grad_norm": 0.38058730959892273, "learning_rate": 9.862092820291195e-06, "loss": 0.7982804775238037, "step": 2315, "token_acc": 0.7587137213852231 }, { "epoch": 0.15019705270654118, "grad_norm": 0.2805602252483368, "learning_rate": 9.861499234142307e-06, "loss": 0.7950688362121582, "step": 2320, "token_acc": 0.7603465691644496 }, { "epoch": 0.15052075325116734, "grad_norm": 0.3466147780418396, "learning_rate": 9.86090439120641e-06, "loss": 0.8105476379394532, "step": 2325, "token_acc": 0.7557832940473845 }, { "epoch": 0.1508444537957935, "grad_norm": 0.36765536665916443, "learning_rate": 9.860308291637286e-06, "loss": 0.8070659637451172, "step": 2330, "token_acc": 0.7558819573001608 }, { "epoch": 0.1511681543404197, "grad_norm": 0.39134305715560913, "learning_rate": 9.859710935589035e-06, "loss": 0.788728141784668, "step": 2335, "token_acc": 0.7599941602874154 }, { "epoch": 0.15149185488504585, "grad_norm": 0.4112735390663147, "learning_rate": 9.859112323216087e-06, "loss": 0.7887354850769043, "step": 2340, "token_acc": 0.7612030096475768 }, { "epoch": 0.151815555429672, "grad_norm": 0.3153291940689087, "learning_rate": 9.858512454673193e-06, "loss": 0.7801234722137451, "step": 2345, "token_acc": 0.7626579804560261 }, { "epoch": 0.15213925597429817, "grad_norm": 0.3870939016342163, "learning_rate": 9.85791133011543e-06, "loss": 0.8119009017944336, "step": 2350, "token_acc": 0.7548115992359785 }, { "epoch": 0.15246295651892433, "grad_norm": 0.28564098477363586, "learning_rate": 9.8573089496982e-06, "loss": 0.7872633457183837, "step": 2355, "token_acc": 0.7609941668780117 }, { "epoch": 0.15278665706355052, "grad_norm": 0.2606883645057678, "learning_rate": 9.85670531357723e-06, "loss": 0.785515546798706, "step": 2360, "token_acc": 0.7609237574146042 }, { "epoch": 0.15311035760817668, "grad_norm": 0.39620479941368103, "learning_rate": 9.85610042190857e-06, "loss": 0.7871094226837159, "step": 2365, "token_acc": 0.7597360392625017 }, { "epoch": 0.15343405815280284, "grad_norm": 0.34266600012779236, "learning_rate": 9.855494274848594e-06, "loss": 0.7790332794189453, "step": 2370, "token_acc": 0.7619843961330126 }, { "epoch": 0.153757758697429, "grad_norm": 0.2923348546028137, "learning_rate": 9.854886872554007e-06, "loss": 0.7722497463226319, "step": 2375, "token_acc": 0.765341474073558 }, { "epoch": 0.15408145924205519, "grad_norm": 0.37447589635849, "learning_rate": 9.85427821518183e-06, "loss": 0.784908676147461, "step": 2380, "token_acc": 0.7617634375871953 }, { "epoch": 0.15440515978668135, "grad_norm": 0.31713008880615234, "learning_rate": 9.853668302889411e-06, "loss": 0.7990044116973877, "step": 2385, "token_acc": 0.7588970782633367 }, { "epoch": 0.1547288603313075, "grad_norm": 0.30233678221702576, "learning_rate": 9.853057135834428e-06, "loss": 0.7831322193145752, "step": 2390, "token_acc": 0.7630176709865361 }, { "epoch": 0.15505256087593366, "grad_norm": 0.3875415325164795, "learning_rate": 9.852444714174875e-06, "loss": 0.7916570663452148, "step": 2395, "token_acc": 0.7615779120415905 }, { "epoch": 0.15537626142055985, "grad_norm": 0.25592756271362305, "learning_rate": 9.851831038069077e-06, "loss": 0.7800069332122803, "step": 2400, "token_acc": 0.7633666802652329 }, { "epoch": 0.155699961965186, "grad_norm": 0.4244098663330078, "learning_rate": 9.851216107675679e-06, "loss": 0.7848933219909668, "step": 2405, "token_acc": 0.7619785743776212 }, { "epoch": 0.15602366250981217, "grad_norm": 0.24110783636569977, "learning_rate": 9.850599923153653e-06, "loss": 0.8059353828430176, "step": 2410, "token_acc": 0.7564152627468481 }, { "epoch": 0.15634736305443833, "grad_norm": 0.32907646894454956, "learning_rate": 9.849982484662291e-06, "loss": 0.7928881645202637, "step": 2415, "token_acc": 0.760323349745355 }, { "epoch": 0.1566710635990645, "grad_norm": 0.3356437385082245, "learning_rate": 9.849363792361216e-06, "loss": 0.7865829467773438, "step": 2420, "token_acc": 0.7628330563448239 }, { "epoch": 0.15699476414369068, "grad_norm": 0.36240553855895996, "learning_rate": 9.848743846410368e-06, "loss": 0.7868570327758789, "step": 2425, "token_acc": 0.7610527299675528 }, { "epoch": 0.15731846468831684, "grad_norm": 0.34313514828681946, "learning_rate": 9.848122646970018e-06, "loss": 0.8041836738586425, "step": 2430, "token_acc": 0.7580738576986515 }, { "epoch": 0.157642165232943, "grad_norm": 0.45247983932495117, "learning_rate": 9.847500194200757e-06, "loss": 0.7849461555480957, "step": 2435, "token_acc": 0.762658622978399 }, { "epoch": 0.15796586577756916, "grad_norm": 0.4256982207298279, "learning_rate": 9.846876488263496e-06, "loss": 0.8016901016235352, "step": 2440, "token_acc": 0.7577352176717393 }, { "epoch": 0.15828956632219535, "grad_norm": 0.334710031747818, "learning_rate": 9.84625152931948e-06, "loss": 0.8021125793457031, "step": 2445, "token_acc": 0.7589153476631422 }, { "epoch": 0.1586132668668215, "grad_norm": 0.2628311812877655, "learning_rate": 9.845625317530268e-06, "loss": 0.7998260974884033, "step": 2450, "token_acc": 0.7585666278577476 }, { "epoch": 0.15893696741144767, "grad_norm": 0.4217314124107361, "learning_rate": 9.84499785305775e-06, "loss": 0.8006004333496094, "step": 2455, "token_acc": 0.757997248105399 }, { "epoch": 0.15926066795607383, "grad_norm": 0.3626715838909149, "learning_rate": 9.844369136064136e-06, "loss": 0.7874389171600342, "step": 2460, "token_acc": 0.7613213680139937 }, { "epoch": 0.1595843685007, "grad_norm": 0.32673531770706177, "learning_rate": 9.843739166711961e-06, "loss": 0.8037915229797363, "step": 2465, "token_acc": 0.75639141933588 }, { "epoch": 0.15990806904532617, "grad_norm": 0.26492682099342346, "learning_rate": 9.843107945164086e-06, "loss": 0.775997257232666, "step": 2470, "token_acc": 0.7651775810942345 }, { "epoch": 0.16023176958995233, "grad_norm": 0.32735562324523926, "learning_rate": 9.842475471583689e-06, "loss": 0.8078242301940918, "step": 2475, "token_acc": 0.7578765702090099 }, { "epoch": 0.1605554701345785, "grad_norm": 0.34904050827026367, "learning_rate": 9.84184174613428e-06, "loss": 0.777880859375, "step": 2480, "token_acc": 0.763916954046801 }, { "epoch": 0.16087917067920468, "grad_norm": 0.42478621006011963, "learning_rate": 9.841206768979686e-06, "loss": 0.7934082984924317, "step": 2485, "token_acc": 0.7599475038196848 }, { "epoch": 0.16120287122383084, "grad_norm": 0.30720892548561096, "learning_rate": 9.840570540284062e-06, "loss": 0.8137962341308593, "step": 2490, "token_acc": 0.7571276581417585 }, { "epoch": 0.161526571768457, "grad_norm": 0.3222382366657257, "learning_rate": 9.839933060211883e-06, "loss": 0.7953144073486328, "step": 2495, "token_acc": 0.7587216023168373 }, { "epoch": 0.16185027231308316, "grad_norm": 0.26697003841400146, "learning_rate": 9.839294328927951e-06, "loss": 0.7994664192199707, "step": 2500, "token_acc": 0.7586529343588663 }, { "epoch": 0.16217397285770932, "grad_norm": 0.3451988399028778, "learning_rate": 9.83865434659739e-06, "loss": 0.7989131927490234, "step": 2505, "token_acc": 0.7577888146285964 }, { "epoch": 0.1624976734023355, "grad_norm": 0.4736741781234741, "learning_rate": 9.838013113385647e-06, "loss": 0.8199655532836914, "step": 2510, "token_acc": 0.752641894762812 }, { "epoch": 0.16282137394696167, "grad_norm": 0.41418614983558655, "learning_rate": 9.83737062945849e-06, "loss": 0.8000605583190918, "step": 2515, "token_acc": 0.7594349665983552 }, { "epoch": 0.16314507449158783, "grad_norm": 0.3707706034183502, "learning_rate": 9.836726894982017e-06, "loss": 0.7931794166564942, "step": 2520, "token_acc": 0.7610284946752375 }, { "epoch": 0.163468775036214, "grad_norm": 0.3948606550693512, "learning_rate": 9.836081910122643e-06, "loss": 0.7983452796936035, "step": 2525, "token_acc": 0.7567124320588143 }, { "epoch": 0.16379247558084017, "grad_norm": 0.3736239969730377, "learning_rate": 9.835435675047107e-06, "loss": 0.7814363956451416, "step": 2530, "token_acc": 0.7634639159326224 }, { "epoch": 0.16411617612546633, "grad_norm": 0.3588305115699768, "learning_rate": 9.834788189922476e-06, "loss": 0.7785300254821778, "step": 2535, "token_acc": 0.7638739160208557 }, { "epoch": 0.1644398766700925, "grad_norm": 0.270817369222641, "learning_rate": 9.834139454916135e-06, "loss": 0.7773758888244628, "step": 2540, "token_acc": 0.765642280019256 }, { "epoch": 0.16476357721471865, "grad_norm": 0.3514851927757263, "learning_rate": 9.833489470195793e-06, "loss": 0.8176965713500977, "step": 2545, "token_acc": 0.7529835299582613 }, { "epoch": 0.16508727775934484, "grad_norm": 0.26827913522720337, "learning_rate": 9.832838235929485e-06, "loss": 0.8122584342956543, "step": 2550, "token_acc": 0.7558925242813695 }, { "epoch": 0.165410978303971, "grad_norm": 0.39021360874176025, "learning_rate": 9.832185752285567e-06, "loss": 0.7815345764160156, "step": 2555, "token_acc": 0.7639256952369899 }, { "epoch": 0.16573467884859716, "grad_norm": 0.33471110463142395, "learning_rate": 9.831532019432716e-06, "loss": 0.8150336265563964, "step": 2560, "token_acc": 0.7555645706558486 }, { "epoch": 0.16605837939322332, "grad_norm": 0.27822425961494446, "learning_rate": 9.830877037539936e-06, "loss": 0.7975808620452881, "step": 2565, "token_acc": 0.7588768898488121 }, { "epoch": 0.1663820799378495, "grad_norm": 0.3968735933303833, "learning_rate": 9.830220806776549e-06, "loss": 0.8042243957519531, "step": 2570, "token_acc": 0.7575911822862624 }, { "epoch": 0.16670578048247567, "grad_norm": 0.4340336322784424, "learning_rate": 9.829563327312207e-06, "loss": 0.8003009796142578, "step": 2575, "token_acc": 0.7574101450923467 }, { "epoch": 0.16702948102710183, "grad_norm": 0.3137311041355133, "learning_rate": 9.828904599316877e-06, "loss": 0.786655044555664, "step": 2580, "token_acc": 0.7617068829378622 }, { "epoch": 0.167353181571728, "grad_norm": 0.3675454556941986, "learning_rate": 9.828244622960854e-06, "loss": 0.7909666061401367, "step": 2585, "token_acc": 0.7604854978999239 }, { "epoch": 0.16767688211635415, "grad_norm": 0.3564167022705078, "learning_rate": 9.827583398414753e-06, "loss": 0.7829960346221924, "step": 2590, "token_acc": 0.7626473791054408 }, { "epoch": 0.16800058266098034, "grad_norm": 0.46220365166664124, "learning_rate": 9.826920925849514e-06, "loss": 0.7965115070343017, "step": 2595, "token_acc": 0.7597671547478395 }, { "epoch": 0.1683242832056065, "grad_norm": 0.27171412110328674, "learning_rate": 9.826257205436398e-06, "loss": 0.7827787876129151, "step": 2600, "token_acc": 0.7616674690016784 }, { "epoch": 0.16864798375023266, "grad_norm": 0.4418017566204071, "learning_rate": 9.825592237346988e-06, "loss": 0.8208152770996093, "step": 2605, "token_acc": 0.7561204930363469 }, { "epoch": 0.16897168429485881, "grad_norm": 0.3713787794113159, "learning_rate": 9.824926021753191e-06, "loss": 0.758054542541504, "step": 2610, "token_acc": 0.7683199196500549 }, { "epoch": 0.169295384839485, "grad_norm": 0.3865847587585449, "learning_rate": 9.824258558827236e-06, "loss": 0.7987438201904297, "step": 2615, "token_acc": 0.7590055470159728 }, { "epoch": 0.16961908538411116, "grad_norm": 0.37222209572792053, "learning_rate": 9.823589848741675e-06, "loss": 0.8094339370727539, "step": 2620, "token_acc": 0.7558015247514552 }, { "epoch": 0.16994278592873732, "grad_norm": 0.3364333212375641, "learning_rate": 9.822919891669382e-06, "loss": 0.7930501937866211, "step": 2625, "token_acc": 0.7587510949996795 }, { "epoch": 0.17026648647336348, "grad_norm": 0.36668169498443604, "learning_rate": 9.82224868778355e-06, "loss": 0.7871602058410645, "step": 2630, "token_acc": 0.7610173840528578 }, { "epoch": 0.17059018701798967, "grad_norm": 0.42403140664100647, "learning_rate": 9.821576237257703e-06, "loss": 0.772428321838379, "step": 2635, "token_acc": 0.7644520462987746 }, { "epoch": 0.17091388756261583, "grad_norm": 0.35713526606559753, "learning_rate": 9.82090254026568e-06, "loss": 0.7908596992492676, "step": 2640, "token_acc": 0.7598818636610211 }, { "epoch": 0.171237588107242, "grad_norm": 0.3545772433280945, "learning_rate": 9.82022759698164e-06, "loss": 0.7704067230224609, "step": 2645, "token_acc": 0.7680318238704569 }, { "epoch": 0.17156128865186815, "grad_norm": 0.3827153444290161, "learning_rate": 9.819551407580073e-06, "loss": 0.7763235092163085, "step": 2650, "token_acc": 0.7623814851893292 }, { "epoch": 0.17188498919649434, "grad_norm": 0.3791406750679016, "learning_rate": 9.818873972235784e-06, "loss": 0.7910462856292725, "step": 2655, "token_acc": 0.7605045907972375 }, { "epoch": 0.1722086897411205, "grad_norm": 0.4481504559516907, "learning_rate": 9.818195291123903e-06, "loss": 0.7896520137786865, "step": 2660, "token_acc": 0.7604191428259375 }, { "epoch": 0.17253239028574666, "grad_norm": 0.35920706391334534, "learning_rate": 9.817515364419883e-06, "loss": 0.801445484161377, "step": 2665, "token_acc": 0.7577618671557333 }, { "epoch": 0.17285609083037282, "grad_norm": 0.4011499285697937, "learning_rate": 9.816834192299497e-06, "loss": 0.8209673881530761, "step": 2670, "token_acc": 0.7514854649456362 }, { "epoch": 0.17317979137499898, "grad_norm": 0.3102526068687439, "learning_rate": 9.816151774938838e-06, "loss": 0.8010541915893554, "step": 2675, "token_acc": 0.7580771912034984 }, { "epoch": 0.17350349191962516, "grad_norm": 0.28616008162498474, "learning_rate": 9.815468112514324e-06, "loss": 0.7812345504760743, "step": 2680, "token_acc": 0.7620946031784441 }, { "epoch": 0.17382719246425132, "grad_norm": 0.3552723824977875, "learning_rate": 9.814783205202698e-06, "loss": 0.7952231407165528, "step": 2685, "token_acc": 0.7608656758380085 }, { "epoch": 0.17415089300887748, "grad_norm": 0.3600381016731262, "learning_rate": 9.81409705318102e-06, "loss": 0.7786556720733643, "step": 2690, "token_acc": 0.7636311661840192 }, { "epoch": 0.17447459355350364, "grad_norm": 0.2851613461971283, "learning_rate": 9.813409656626669e-06, "loss": 0.780790138244629, "step": 2695, "token_acc": 0.764166406493912 }, { "epoch": 0.17479829409812983, "grad_norm": 0.3489321768283844, "learning_rate": 9.812721015717353e-06, "loss": 0.7875720977783203, "step": 2700, "token_acc": 0.7626354094431466 }, { "epoch": 0.175121994642756, "grad_norm": 0.4326906204223633, "learning_rate": 9.812031130631098e-06, "loss": 0.7948905944824218, "step": 2705, "token_acc": 0.7594667190775681 }, { "epoch": 0.17544569518738215, "grad_norm": 0.39281198382377625, "learning_rate": 9.811340001546252e-06, "loss": 0.7649192810058594, "step": 2710, "token_acc": 0.7682531564267405 }, { "epoch": 0.1757693957320083, "grad_norm": 0.24043503403663635, "learning_rate": 9.810647628641486e-06, "loss": 0.7715402603149414, "step": 2715, "token_acc": 0.7656623289018804 }, { "epoch": 0.1760930962766345, "grad_norm": 0.38591936230659485, "learning_rate": 9.809954012095786e-06, "loss": 0.7864626884460449, "step": 2720, "token_acc": 0.7605227149226468 }, { "epoch": 0.17641679682126066, "grad_norm": 0.2916549742221832, "learning_rate": 9.809259152088471e-06, "loss": 0.7735540390014648, "step": 2725, "token_acc": 0.7633771396880589 }, { "epoch": 0.17674049736588682, "grad_norm": 0.28285834193229675, "learning_rate": 9.80856304879917e-06, "loss": 0.7878674030303955, "step": 2730, "token_acc": 0.7618391307988073 }, { "epoch": 0.17706419791051298, "grad_norm": 0.2997364103794098, "learning_rate": 9.807865702407842e-06, "loss": 0.7827334403991699, "step": 2735, "token_acc": 0.7618605231594784 }, { "epoch": 0.17738789845513914, "grad_norm": 0.4366566240787506, "learning_rate": 9.807167113094761e-06, "loss": 0.7964831352233886, "step": 2740, "token_acc": 0.7591119273275834 }, { "epoch": 0.17771159899976532, "grad_norm": 0.35436686873435974, "learning_rate": 9.80646728104053e-06, "loss": 0.7854168891906739, "step": 2745, "token_acc": 0.761737406506263 }, { "epoch": 0.17803529954439148, "grad_norm": 0.3139379024505615, "learning_rate": 9.805766206426063e-06, "loss": 0.7978481769561767, "step": 2750, "token_acc": 0.758441825892771 }, { "epoch": 0.17835900008901764, "grad_norm": 0.30729976296424866, "learning_rate": 9.805063889432602e-06, "loss": 0.7808998107910157, "step": 2755, "token_acc": 0.7634107310003322 }, { "epoch": 0.1786827006336438, "grad_norm": 0.40953531861305237, "learning_rate": 9.804360330241711e-06, "loss": 0.7844409942626953, "step": 2760, "token_acc": 0.7637406917894329 }, { "epoch": 0.17900640117827, "grad_norm": 0.4064871370792389, "learning_rate": 9.803655529035272e-06, "loss": 0.7600902557373047, "step": 2765, "token_acc": 0.767753836389001 }, { "epoch": 0.17933010172289615, "grad_norm": 0.28195688128471375, "learning_rate": 9.802949485995489e-06, "loss": 0.8012962341308594, "step": 2770, "token_acc": 0.7591423848749368 }, { "epoch": 0.1796538022675223, "grad_norm": 0.3173101246356964, "learning_rate": 9.802242201304885e-06, "loss": 0.7934397697448731, "step": 2775, "token_acc": 0.7602407850677128 }, { "epoch": 0.17997750281214847, "grad_norm": 0.31188446283340454, "learning_rate": 9.801533675146311e-06, "loss": 0.7856735229492188, "step": 2780, "token_acc": 0.7621467593516889 }, { "epoch": 0.18030120335677466, "grad_norm": 0.3776959478855133, "learning_rate": 9.80082390770293e-06, "loss": 0.7623728275299072, "step": 2785, "token_acc": 0.7665958345343513 }, { "epoch": 0.18062490390140082, "grad_norm": 0.4840259850025177, "learning_rate": 9.800112899158229e-06, "loss": 0.797330665588379, "step": 2790, "token_acc": 0.7584839194549102 }, { "epoch": 0.18094860444602698, "grad_norm": 0.3365883529186249, "learning_rate": 9.799400649696022e-06, "loss": 0.8024835586547852, "step": 2795, "token_acc": 0.7600253380562091 }, { "epoch": 0.18127230499065314, "grad_norm": 0.3654714822769165, "learning_rate": 9.798687159500433e-06, "loss": 0.8113205909729004, "step": 2800, "token_acc": 0.7577014783023367 }, { "epoch": 0.18159600553527933, "grad_norm": 0.43927016854286194, "learning_rate": 9.797972428755916e-06, "loss": 0.7853537559509277, "step": 2805, "token_acc": 0.7596768209736593 }, { "epoch": 0.18191970607990549, "grad_norm": 0.3950940668582916, "learning_rate": 9.797256457647243e-06, "loss": 0.7688463687896728, "step": 2810, "token_acc": 0.7675335221533404 }, { "epoch": 0.18224340662453165, "grad_norm": 0.4081851541996002, "learning_rate": 9.7965392463595e-06, "loss": 0.7635940551757813, "step": 2815, "token_acc": 0.7675275491509667 }, { "epoch": 0.1825671071691578, "grad_norm": 0.3920752704143524, "learning_rate": 9.795820795078105e-06, "loss": 0.7510787010192871, "step": 2820, "token_acc": 0.7710562634399974 }, { "epoch": 0.18289080771378396, "grad_norm": 0.3842032849788666, "learning_rate": 9.795101103988786e-06, "loss": 0.7825761318206788, "step": 2825, "token_acc": 0.7632612664670843 }, { "epoch": 0.18321450825841015, "grad_norm": 0.3732960820198059, "learning_rate": 9.7943801732776e-06, "loss": 0.7847836971282959, "step": 2830, "token_acc": 0.7621949245284241 }, { "epoch": 0.1835382088030363, "grad_norm": 0.47637876868247986, "learning_rate": 9.793658003130921e-06, "loss": 0.7906402587890625, "step": 2835, "token_acc": 0.7608593306470597 }, { "epoch": 0.18386190934766247, "grad_norm": 0.3518696427345276, "learning_rate": 9.792934593735444e-06, "loss": 0.776333236694336, "step": 2840, "token_acc": 0.7635380096831188 }, { "epoch": 0.18418560989228863, "grad_norm": 0.3132615387439728, "learning_rate": 9.79220994527818e-06, "loss": 0.783528995513916, "step": 2845, "token_acc": 0.7608346923153726 }, { "epoch": 0.18450931043691482, "grad_norm": 0.32278716564178467, "learning_rate": 9.791484057946465e-06, "loss": 0.795533275604248, "step": 2850, "token_acc": 0.7604812653082496 }, { "epoch": 0.18483301098154098, "grad_norm": 0.4089743494987488, "learning_rate": 9.790756931927957e-06, "loss": 0.7841410160064697, "step": 2855, "token_acc": 0.7617257781371328 }, { "epoch": 0.18515671152616714, "grad_norm": 0.4279327392578125, "learning_rate": 9.790028567410628e-06, "loss": 0.7897992610931397, "step": 2860, "token_acc": 0.7590362216818124 }, { "epoch": 0.1854804120707933, "grad_norm": 0.3661292493343353, "learning_rate": 9.789298964582774e-06, "loss": 0.7846569061279297, "step": 2865, "token_acc": 0.7631140182121329 }, { "epoch": 0.1858041126154195, "grad_norm": 0.35765358805656433, "learning_rate": 9.788568123633016e-06, "loss": 0.776146411895752, "step": 2870, "token_acc": 0.7653532838750541 }, { "epoch": 0.18612781316004565, "grad_norm": 0.267931193113327, "learning_rate": 9.787836044750284e-06, "loss": 0.7905539035797119, "step": 2875, "token_acc": 0.7612815437902029 }, { "epoch": 0.1864515137046718, "grad_norm": 0.3143913149833679, "learning_rate": 9.787102728123833e-06, "loss": 0.7771368503570557, "step": 2880, "token_acc": 0.7626593373569407 }, { "epoch": 0.18677521424929797, "grad_norm": 0.3742850422859192, "learning_rate": 9.786368173943243e-06, "loss": 0.7785853385925293, "step": 2885, "token_acc": 0.7629364230387545 }, { "epoch": 0.18709891479392415, "grad_norm": 0.30817466974258423, "learning_rate": 9.785632382398409e-06, "loss": 0.7848929405212403, "step": 2890, "token_acc": 0.7621650661473374 }, { "epoch": 0.1874226153385503, "grad_norm": 0.35639894008636475, "learning_rate": 9.784895353679547e-06, "loss": 0.7900637149810791, "step": 2895, "token_acc": 0.7613314088011083 }, { "epoch": 0.18774631588317647, "grad_norm": 0.33386826515197754, "learning_rate": 9.784157087977188e-06, "loss": 0.7815920829772949, "step": 2900, "token_acc": 0.7627170504092404 }, { "epoch": 0.18807001642780263, "grad_norm": 0.35801962018013, "learning_rate": 9.783417585482194e-06, "loss": 0.7917407035827637, "step": 2905, "token_acc": 0.7595738643373553 }, { "epoch": 0.1883937169724288, "grad_norm": 0.35449206829071045, "learning_rate": 9.782676846385734e-06, "loss": 0.7901681900024414, "step": 2910, "token_acc": 0.760759493670886 }, { "epoch": 0.18871741751705498, "grad_norm": 0.28919172286987305, "learning_rate": 9.781934870879308e-06, "loss": 0.7820283889770507, "step": 2915, "token_acc": 0.7625511653161807 }, { "epoch": 0.18904111806168114, "grad_norm": 0.35905036330223083, "learning_rate": 9.781191659154725e-06, "loss": 0.7792873382568359, "step": 2920, "token_acc": 0.7616896936352501 }, { "epoch": 0.1893648186063073, "grad_norm": 0.3802794814109802, "learning_rate": 9.780447211404123e-06, "loss": 0.7730549812316895, "step": 2925, "token_acc": 0.7647596244723079 }, { "epoch": 0.18968851915093346, "grad_norm": 0.50030517578125, "learning_rate": 9.779701527819953e-06, "loss": 0.8086664199829101, "step": 2930, "token_acc": 0.7578473404140724 }, { "epoch": 0.19001221969555965, "grad_norm": 0.29848799109458923, "learning_rate": 9.77895460859499e-06, "loss": 0.7658865928649903, "step": 2935, "token_acc": 0.7664147567784324 }, { "epoch": 0.1903359202401858, "grad_norm": 0.3727698028087616, "learning_rate": 9.778206453922326e-06, "loss": 0.7752533435821534, "step": 2940, "token_acc": 0.763464327834185 }, { "epoch": 0.19065962078481197, "grad_norm": 0.36743399500846863, "learning_rate": 9.777457063995372e-06, "loss": 0.7889808177947998, "step": 2945, "token_acc": 0.7616285928952418 }, { "epoch": 0.19098332132943813, "grad_norm": 0.3197905123233795, "learning_rate": 9.776706439007856e-06, "loss": 0.7737939834594727, "step": 2950, "token_acc": 0.7642130262302477 }, { "epoch": 0.19130702187406431, "grad_norm": 0.22239695489406586, "learning_rate": 9.775954579153834e-06, "loss": 0.774415111541748, "step": 2955, "token_acc": 0.7629169458148081 }, { "epoch": 0.19163072241869047, "grad_norm": 0.3556951582431793, "learning_rate": 9.775201484627675e-06, "loss": 0.7613700866699219, "step": 2960, "token_acc": 0.7661423758547137 }, { "epoch": 0.19195442296331663, "grad_norm": 0.38413384556770325, "learning_rate": 9.774447155624063e-06, "loss": 0.7910480976104737, "step": 2965, "token_acc": 0.760765923634661 }, { "epoch": 0.1922781235079428, "grad_norm": 0.33247891068458557, "learning_rate": 9.773691592338009e-06, "loss": 0.7787972927093506, "step": 2970, "token_acc": 0.7635468624361799 }, { "epoch": 0.19260182405256898, "grad_norm": 0.39336660504341125, "learning_rate": 9.77293479496484e-06, "loss": 0.7857119560241699, "step": 2975, "token_acc": 0.7618718209562564 }, { "epoch": 0.19292552459719514, "grad_norm": 0.4187951683998108, "learning_rate": 9.772176763700203e-06, "loss": 0.7538229942321777, "step": 2980, "token_acc": 0.7691645787462354 }, { "epoch": 0.1932492251418213, "grad_norm": 0.3513242304325104, "learning_rate": 9.771417498740061e-06, "loss": 0.7874238967895508, "step": 2985, "token_acc": 0.7629351004622206 }, { "epoch": 0.19357292568644746, "grad_norm": 0.3476497530937195, "learning_rate": 9.770657000280698e-06, "loss": 0.7986389636993408, "step": 2990, "token_acc": 0.7589162824881406 }, { "epoch": 0.19389662623107362, "grad_norm": 0.33293795585632324, "learning_rate": 9.769895268518718e-06, "loss": 0.7658947944641114, "step": 2995, "token_acc": 0.7668177794789598 }, { "epoch": 0.1942203267756998, "grad_norm": 0.3030817210674286, "learning_rate": 9.769132303651044e-06, "loss": 0.7947961807250976, "step": 3000, "token_acc": 0.7591615533929991 }, { "epoch": 0.19454402732032597, "grad_norm": 0.3354075849056244, "learning_rate": 9.768368105874914e-06, "loss": 0.759487247467041, "step": 3005, "token_acc": 0.7665011925231572 }, { "epoch": 0.19486772786495213, "grad_norm": 0.2738666236400604, "learning_rate": 9.767602675387889e-06, "loss": 0.7818994522094727, "step": 3010, "token_acc": 0.7633383871200635 }, { "epoch": 0.1951914284095783, "grad_norm": 0.2757876217365265, "learning_rate": 9.766836012387843e-06, "loss": 0.7482170104980469, "step": 3015, "token_acc": 0.7719972240122936 }, { "epoch": 0.19551512895420448, "grad_norm": 0.21835948526859283, "learning_rate": 9.76606811707298e-06, "loss": 0.7894564151763916, "step": 3020, "token_acc": 0.7605825591683256 }, { "epoch": 0.19583882949883064, "grad_norm": 0.36654651165008545, "learning_rate": 9.765298989641807e-06, "loss": 0.7839884757995605, "step": 3025, "token_acc": 0.7620185994518481 }, { "epoch": 0.1961625300434568, "grad_norm": 0.358254998922348, "learning_rate": 9.764528630293162e-06, "loss": 0.7726278305053711, "step": 3030, "token_acc": 0.7645600749473027 }, { "epoch": 0.19648623058808296, "grad_norm": 0.3223457634449005, "learning_rate": 9.763757039226196e-06, "loss": 0.7750576972961426, "step": 3035, "token_acc": 0.7632640039099623 }, { "epoch": 0.19680993113270914, "grad_norm": 0.391098290681839, "learning_rate": 9.762984216640378e-06, "loss": 0.791838550567627, "step": 3040, "token_acc": 0.7599411578447411 }, { "epoch": 0.1971336316773353, "grad_norm": 0.33461418747901917, "learning_rate": 9.762210162735502e-06, "loss": 0.7901575088500976, "step": 3045, "token_acc": 0.7614181264964727 }, { "epoch": 0.19745733222196146, "grad_norm": 0.36951547861099243, "learning_rate": 9.761434877711668e-06, "loss": 0.7764082908630371, "step": 3050, "token_acc": 0.7645168974819565 }, { "epoch": 0.19778103276658762, "grad_norm": 0.4313047528266907, "learning_rate": 9.760658361769308e-06, "loss": 0.7770369052886963, "step": 3055, "token_acc": 0.7641559846255866 }, { "epoch": 0.1981047333112138, "grad_norm": 0.21310923993587494, "learning_rate": 9.759880615109161e-06, "loss": 0.8021001815795898, "step": 3060, "token_acc": 0.758735430991738 }, { "epoch": 0.19842843385583997, "grad_norm": 0.4073273837566376, "learning_rate": 9.75910163793229e-06, "loss": 0.7717059135437012, "step": 3065, "token_acc": 0.765028307429365 }, { "epoch": 0.19875213440046613, "grad_norm": 0.3277987539768219, "learning_rate": 9.758321430440079e-06, "loss": 0.8101734161376953, "step": 3070, "token_acc": 0.7553044234177003 }, { "epoch": 0.1990758349450923, "grad_norm": 0.3988119959831238, "learning_rate": 9.75753999283422e-06, "loss": 0.7754087448120117, "step": 3075, "token_acc": 0.7643974573108432 }, { "epoch": 0.19939953548971845, "grad_norm": 0.35684940218925476, "learning_rate": 9.75675732531673e-06, "loss": 0.7860881805419921, "step": 3080, "token_acc": 0.7616962609376408 }, { "epoch": 0.19972323603434464, "grad_norm": 0.44016802310943604, "learning_rate": 9.755973428089947e-06, "loss": 0.7660076141357421, "step": 3085, "token_acc": 0.766163653364456 }, { "epoch": 0.2000469365789708, "grad_norm": 0.31183603405952454, "learning_rate": 9.75518830135652e-06, "loss": 0.7801190376281738, "step": 3090, "token_acc": 0.7626532016835641 }, { "epoch": 0.20037063712359696, "grad_norm": 0.38972941040992737, "learning_rate": 9.754401945319419e-06, "loss": 0.7870226383209229, "step": 3095, "token_acc": 0.7609558732303111 }, { "epoch": 0.20069433766822312, "grad_norm": 0.2667846381664276, "learning_rate": 9.75361436018193e-06, "loss": 0.7516722679138184, "step": 3100, "token_acc": 0.7687112038261932 }, { "epoch": 0.2010180382128493, "grad_norm": 0.3752143383026123, "learning_rate": 9.75282554614766e-06, "loss": 0.740943431854248, "step": 3105, "token_acc": 0.7714810987801769 }, { "epoch": 0.20134173875747546, "grad_norm": 0.3118124306201935, "learning_rate": 9.752035503420534e-06, "loss": 0.793263578414917, "step": 3110, "token_acc": 0.7616053475720059 }, { "epoch": 0.20166543930210162, "grad_norm": 0.3989730775356293, "learning_rate": 9.751244232204788e-06, "loss": 0.7920110702514649, "step": 3115, "token_acc": 0.7601420356346039 }, { "epoch": 0.20198913984672778, "grad_norm": 0.2957896888256073, "learning_rate": 9.750451732704984e-06, "loss": 0.7706083297729492, "step": 3120, "token_acc": 0.7666266683649186 }, { "epoch": 0.20231284039135397, "grad_norm": 0.34205162525177, "learning_rate": 9.749658005125995e-06, "loss": 0.7680117607116699, "step": 3125, "token_acc": 0.766030136296616 }, { "epoch": 0.20263654093598013, "grad_norm": 0.3488030433654785, "learning_rate": 9.748863049673017e-06, "loss": 0.8015929222106933, "step": 3130, "token_acc": 0.7591513729544868 }, { "epoch": 0.2029602414806063, "grad_norm": 0.34260743856430054, "learning_rate": 9.748066866551557e-06, "loss": 0.7576711654663086, "step": 3135, "token_acc": 0.7684101834692998 }, { "epoch": 0.20328394202523245, "grad_norm": 0.330812007188797, "learning_rate": 9.747269455967445e-06, "loss": 0.7733806133270263, "step": 3140, "token_acc": 0.7634475344587072 }, { "epoch": 0.2036076425698586, "grad_norm": 0.33860599994659424, "learning_rate": 9.746470818126827e-06, "loss": 0.7857972621917725, "step": 3145, "token_acc": 0.7614361166827454 }, { "epoch": 0.2039313431144848, "grad_norm": 0.36154353618621826, "learning_rate": 9.745670953236166e-06, "loss": 0.7765348434448243, "step": 3150, "token_acc": 0.7644283453062218 }, { "epoch": 0.20425504365911096, "grad_norm": 0.2889145016670227, "learning_rate": 9.74486986150224e-06, "loss": 0.7645468711853027, "step": 3155, "token_acc": 0.7668141592920354 }, { "epoch": 0.20457874420373712, "grad_norm": 0.2388637810945511, "learning_rate": 9.744067543132146e-06, "loss": 0.7599886894226074, "step": 3160, "token_acc": 0.7680962430399065 }, { "epoch": 0.20490244474836328, "grad_norm": 0.3099842369556427, "learning_rate": 9.743263998333297e-06, "loss": 0.7530904769897461, "step": 3165, "token_acc": 0.7695424093035015 }, { "epoch": 0.20522614529298946, "grad_norm": 0.26868966221809387, "learning_rate": 9.742459227313428e-06, "loss": 0.7610658645629883, "step": 3170, "token_acc": 0.7692365371506475 }, { "epoch": 0.20554984583761562, "grad_norm": 0.2959752678871155, "learning_rate": 9.741653230280586e-06, "loss": 0.7597875595092773, "step": 3175, "token_acc": 0.7690722098432998 }, { "epoch": 0.20587354638224178, "grad_norm": 0.32802119851112366, "learning_rate": 9.740846007443132e-06, "loss": 0.7599448204040528, "step": 3180, "token_acc": 0.7678074153953504 }, { "epoch": 0.20619724692686794, "grad_norm": 0.33426615595817566, "learning_rate": 9.740037559009752e-06, "loss": 0.7872793197631835, "step": 3185, "token_acc": 0.7631015156444712 }, { "epoch": 0.20652094747149413, "grad_norm": 0.4109802544116974, "learning_rate": 9.739227885189444e-06, "loss": 0.789936637878418, "step": 3190, "token_acc": 0.7616222745058567 }, { "epoch": 0.2068446480161203, "grad_norm": 0.4431893527507782, "learning_rate": 9.738416986191523e-06, "loss": 0.7697278976440429, "step": 3195, "token_acc": 0.7646264714513973 }, { "epoch": 0.20716834856074645, "grad_norm": 0.3178509771823883, "learning_rate": 9.737604862225622e-06, "loss": 0.7637476921081543, "step": 3200, "token_acc": 0.765523146980338 }, { "epoch": 0.2074920491053726, "grad_norm": 0.39136868715286255, "learning_rate": 9.73679151350169e-06, "loss": 0.7777809143066406, "step": 3205, "token_acc": 0.7630905403391456 }, { "epoch": 0.2078157496499988, "grad_norm": 0.3291126787662506, "learning_rate": 9.735976940229993e-06, "loss": 0.7641996383666992, "step": 3210, "token_acc": 0.766032130868013 }, { "epoch": 0.20813945019462496, "grad_norm": 0.3770281970500946, "learning_rate": 9.73516114262111e-06, "loss": 0.770118236541748, "step": 3215, "token_acc": 0.76622171145686 }, { "epoch": 0.20846315073925112, "grad_norm": 0.26318544149398804, "learning_rate": 9.734344120885943e-06, "loss": 0.7674957275390625, "step": 3220, "token_acc": 0.7663601305250668 }, { "epoch": 0.20878685128387728, "grad_norm": 0.34906405210494995, "learning_rate": 9.733525875235706e-06, "loss": 0.7818118572235108, "step": 3225, "token_acc": 0.7637115847299941 }, { "epoch": 0.20911055182850344, "grad_norm": 0.33873096108436584, "learning_rate": 9.732706405881931e-06, "loss": 0.7710757732391358, "step": 3230, "token_acc": 0.7665213152840773 }, { "epoch": 0.20943425237312963, "grad_norm": 0.3763071298599243, "learning_rate": 9.731885713036467e-06, "loss": 0.7643842697143555, "step": 3235, "token_acc": 0.7671685093171913 }, { "epoch": 0.20975795291775579, "grad_norm": 0.33912917971611023, "learning_rate": 9.731063796911475e-06, "loss": 0.7693071365356445, "step": 3240, "token_acc": 0.766375082670926 }, { "epoch": 0.21008165346238195, "grad_norm": 0.3639385402202606, "learning_rate": 9.730240657719437e-06, "loss": 0.7899769306182861, "step": 3245, "token_acc": 0.7603962268611552 }, { "epoch": 0.2104053540070081, "grad_norm": 0.33833739161491394, "learning_rate": 9.729416295673151e-06, "loss": 0.7521747589111328, "step": 3250, "token_acc": 0.7695303215898496 }, { "epoch": 0.2107290545516343, "grad_norm": 0.3480476140975952, "learning_rate": 9.728590710985729e-06, "loss": 0.7817681312561036, "step": 3255, "token_acc": 0.7629872416155072 }, { "epoch": 0.21105275509626045, "grad_norm": 0.368113249540329, "learning_rate": 9.7277639038706e-06, "loss": 0.7611424446105957, "step": 3260, "token_acc": 0.768047537053918 }, { "epoch": 0.2113764556408866, "grad_norm": 0.2995114028453827, "learning_rate": 9.726935874541508e-06, "loss": 0.7949772834777832, "step": 3265, "token_acc": 0.760978670012547 }, { "epoch": 0.21170015618551277, "grad_norm": 0.3944428861141205, "learning_rate": 9.726106623212512e-06, "loss": 0.7621077060699463, "step": 3270, "token_acc": 0.7684456459593572 }, { "epoch": 0.21202385673013896, "grad_norm": 0.3337678909301758, "learning_rate": 9.725276150097993e-06, "loss": 0.7710770606994629, "step": 3275, "token_acc": 0.7659892367499965 }, { "epoch": 0.21234755727476512, "grad_norm": 0.32433149218559265, "learning_rate": 9.724444455412643e-06, "loss": 0.7790711879730224, "step": 3280, "token_acc": 0.7648184745505051 }, { "epoch": 0.21267125781939128, "grad_norm": 0.32357579469680786, "learning_rate": 9.723611539371466e-06, "loss": 0.77362060546875, "step": 3285, "token_acc": 0.7656126507204866 }, { "epoch": 0.21299495836401744, "grad_norm": 0.3631189167499542, "learning_rate": 9.722777402189792e-06, "loss": 0.7752429962158203, "step": 3290, "token_acc": 0.7648962591375683 }, { "epoch": 0.21331865890864363, "grad_norm": 0.40521150827407837, "learning_rate": 9.721942044083255e-06, "loss": 0.7638182163238525, "step": 3295, "token_acc": 0.767229429303761 }, { "epoch": 0.2136423594532698, "grad_norm": 0.44079896807670593, "learning_rate": 9.721105465267815e-06, "loss": 0.7817677974700927, "step": 3300, "token_acc": 0.7631888926836409 }, { "epoch": 0.21396605999789595, "grad_norm": 0.4045206308364868, "learning_rate": 9.72026766595974e-06, "loss": 0.7884150505065918, "step": 3305, "token_acc": 0.761530925739572 }, { "epoch": 0.2142897605425221, "grad_norm": 0.4345124661922455, "learning_rate": 9.719428646375618e-06, "loss": 0.7686977863311768, "step": 3310, "token_acc": 0.7661295427530472 }, { "epoch": 0.21461346108714827, "grad_norm": 0.32954588532447815, "learning_rate": 9.718588406732352e-06, "loss": 0.7729491233825684, "step": 3315, "token_acc": 0.7651685393258427 }, { "epoch": 0.21493716163177445, "grad_norm": 0.34197497367858887, "learning_rate": 9.717746947247158e-06, "loss": 0.7819440841674805, "step": 3320, "token_acc": 0.7620074680182791 }, { "epoch": 0.2152608621764006, "grad_norm": 0.37403446435928345, "learning_rate": 9.716904268137567e-06, "loss": 0.7771095275878906, "step": 3325, "token_acc": 0.7641967531530113 }, { "epoch": 0.21558456272102677, "grad_norm": 0.4042831361293793, "learning_rate": 9.716060369621431e-06, "loss": 0.7702694892883301, "step": 3330, "token_acc": 0.7653315472203617 }, { "epoch": 0.21590826326565293, "grad_norm": 0.3149575889110565, "learning_rate": 9.715215251916912e-06, "loss": 0.7699717521667481, "step": 3335, "token_acc": 0.765391848713794 }, { "epoch": 0.21623196381027912, "grad_norm": 0.3230549097061157, "learning_rate": 9.714368915242487e-06, "loss": 0.7706016063690185, "step": 3340, "token_acc": 0.7654986001264402 }, { "epoch": 0.21655566435490528, "grad_norm": 0.3052970767021179, "learning_rate": 9.713521359816948e-06, "loss": 0.7742881774902344, "step": 3345, "token_acc": 0.7636411687337897 }, { "epoch": 0.21687936489953144, "grad_norm": 0.3947570025920868, "learning_rate": 9.71267258585941e-06, "loss": 0.7822360992431641, "step": 3350, "token_acc": 0.7624238753743144 }, { "epoch": 0.2172030654441576, "grad_norm": 0.4085257649421692, "learning_rate": 9.711822593589291e-06, "loss": 0.7808273315429688, "step": 3355, "token_acc": 0.763347657268116 }, { "epoch": 0.2175267659887838, "grad_norm": 0.2736096680164337, "learning_rate": 9.710971383226331e-06, "loss": 0.7495641231536865, "step": 3360, "token_acc": 0.771434501496893 }, { "epoch": 0.21785046653340995, "grad_norm": 0.3342858850955963, "learning_rate": 9.710118954990584e-06, "loss": 0.7715148448944091, "step": 3365, "token_acc": 0.7637833150842727 }, { "epoch": 0.2181741670780361, "grad_norm": 0.4780276119709015, "learning_rate": 9.70926530910242e-06, "loss": 0.78654465675354, "step": 3370, "token_acc": 0.7630651517000309 }, { "epoch": 0.21849786762266227, "grad_norm": 0.35714954137802124, "learning_rate": 9.70841044578252e-06, "loss": 0.7749226570129395, "step": 3375, "token_acc": 0.7642414619719187 }, { "epoch": 0.21882156816728845, "grad_norm": 0.24126482009887695, "learning_rate": 9.707554365251882e-06, "loss": 0.7930656433105469, "step": 3380, "token_acc": 0.7591521046797004 }, { "epoch": 0.21914526871191461, "grad_norm": 0.3813343644142151, "learning_rate": 9.706697067731819e-06, "loss": 0.7620888710021972, "step": 3385, "token_acc": 0.7658129021696699 }, { "epoch": 0.21946896925654077, "grad_norm": 0.3863377571105957, "learning_rate": 9.705838553443959e-06, "loss": 0.7826441287994385, "step": 3390, "token_acc": 0.7633149861731546 }, { "epoch": 0.21979266980116693, "grad_norm": 0.3884413540363312, "learning_rate": 9.70497882261024e-06, "loss": 0.772504186630249, "step": 3395, "token_acc": 0.7640113077220541 }, { "epoch": 0.2201163703457931, "grad_norm": 0.20735950767993927, "learning_rate": 9.704117875452923e-06, "loss": 0.7732357025146485, "step": 3400, "token_acc": 0.7648349975259144 }, { "epoch": 0.22044007089041928, "grad_norm": 0.4039267599582672, "learning_rate": 9.703255712194576e-06, "loss": 0.7617171764373779, "step": 3405, "token_acc": 0.7673115230088794 }, { "epoch": 0.22076377143504544, "grad_norm": 0.3364580273628235, "learning_rate": 9.702392333058088e-06, "loss": 0.774891710281372, "step": 3410, "token_acc": 0.7638734366021542 }, { "epoch": 0.2210874719796716, "grad_norm": 0.38533705472946167, "learning_rate": 9.701527738266653e-06, "loss": 0.7844011306762695, "step": 3415, "token_acc": 0.7627264726411945 }, { "epoch": 0.22141117252429776, "grad_norm": 0.3215116262435913, "learning_rate": 9.700661928043787e-06, "loss": 0.768581485748291, "step": 3420, "token_acc": 0.7673974659298277 }, { "epoch": 0.22173487306892395, "grad_norm": 0.37862545251846313, "learning_rate": 9.699794902613318e-06, "loss": 0.7942867279052734, "step": 3425, "token_acc": 0.7607692783377651 }, { "epoch": 0.2220585736135501, "grad_norm": 0.32449012994766235, "learning_rate": 9.698926662199388e-06, "loss": 0.7795940399169922, "step": 3430, "token_acc": 0.7634628365709143 }, { "epoch": 0.22238227415817627, "grad_norm": 0.3564024865627289, "learning_rate": 9.698057207026452e-06, "loss": 0.7768783569335938, "step": 3435, "token_acc": 0.763997583546146 }, { "epoch": 0.22270597470280243, "grad_norm": 0.3603702485561371, "learning_rate": 9.697186537319283e-06, "loss": 0.786844539642334, "step": 3440, "token_acc": 0.7615362684804301 }, { "epoch": 0.22302967524742862, "grad_norm": 0.3343149423599243, "learning_rate": 9.696314653302962e-06, "loss": 0.7492127418518066, "step": 3445, "token_acc": 0.7706828851370601 }, { "epoch": 0.22335337579205478, "grad_norm": 0.3548935651779175, "learning_rate": 9.69544155520289e-06, "loss": 0.7711752891540528, "step": 3450, "token_acc": 0.7653962389770436 }, { "epoch": 0.22367707633668094, "grad_norm": 0.27545103430747986, "learning_rate": 9.694567243244774e-06, "loss": 0.7768611907958984, "step": 3455, "token_acc": 0.7628346642385017 }, { "epoch": 0.2240007768813071, "grad_norm": 0.3435434103012085, "learning_rate": 9.693691717654645e-06, "loss": 0.7746982574462891, "step": 3460, "token_acc": 0.7648519435622715 }, { "epoch": 0.22432447742593328, "grad_norm": 0.29528704285621643, "learning_rate": 9.692814978658841e-06, "loss": 0.7708262443542481, "step": 3465, "token_acc": 0.7652173307715869 }, { "epoch": 0.22464817797055944, "grad_norm": 0.2978491485118866, "learning_rate": 9.691937026484016e-06, "loss": 0.7895081043243408, "step": 3470, "token_acc": 0.7587709670338184 }, { "epoch": 0.2249718785151856, "grad_norm": 0.3535280227661133, "learning_rate": 9.691057861357132e-06, "loss": 0.7752073287963868, "step": 3475, "token_acc": 0.7642874113294641 }, { "epoch": 0.22529557905981176, "grad_norm": 0.38817495107650757, "learning_rate": 9.690177483505474e-06, "loss": 0.7822907924652099, "step": 3480, "token_acc": 0.7636099064140607 }, { "epoch": 0.22561927960443792, "grad_norm": 0.36674827337265015, "learning_rate": 9.689295893156636e-06, "loss": 0.7629310607910156, "step": 3485, "token_acc": 0.7680846653742517 }, { "epoch": 0.2259429801490641, "grad_norm": 0.3658478856086731, "learning_rate": 9.688413090538522e-06, "loss": 0.7655113220214844, "step": 3490, "token_acc": 0.7664588942573674 }, { "epoch": 0.22626668069369027, "grad_norm": 0.43884772062301636, "learning_rate": 9.687529075879355e-06, "loss": 0.7605056762695312, "step": 3495, "token_acc": 0.7675860550256686 }, { "epoch": 0.22659038123831643, "grad_norm": 0.24116255342960358, "learning_rate": 9.686643849407671e-06, "loss": 0.7749317646026611, "step": 3500, "token_acc": 0.7652844285956869 }, { "epoch": 0.2269140817829426, "grad_norm": 0.2699457108974457, "learning_rate": 9.685757411352313e-06, "loss": 0.7628114700317383, "step": 3505, "token_acc": 0.767349717917126 }, { "epoch": 0.22723778232756878, "grad_norm": 0.382752001285553, "learning_rate": 9.684869761942443e-06, "loss": 0.7921848773956299, "step": 3510, "token_acc": 0.7607131749401631 }, { "epoch": 0.22756148287219494, "grad_norm": 0.43146252632141113, "learning_rate": 9.683980901407539e-06, "loss": 0.7574314117431641, "step": 3515, "token_acc": 0.7693207811611641 }, { "epoch": 0.2278851834168211, "grad_norm": 0.42386820912361145, "learning_rate": 9.683090829977381e-06, "loss": 0.760340690612793, "step": 3520, "token_acc": 0.768620045092787 }, { "epoch": 0.22820888396144726, "grad_norm": 0.3551730513572693, "learning_rate": 9.682199547882073e-06, "loss": 0.7741573333740235, "step": 3525, "token_acc": 0.764930387571897 }, { "epoch": 0.22853258450607344, "grad_norm": 0.4426150619983673, "learning_rate": 9.681307055352027e-06, "loss": 0.7756722927093506, "step": 3530, "token_acc": 0.7650960765155896 }, { "epoch": 0.2288562850506996, "grad_norm": 0.30601051449775696, "learning_rate": 9.680413352617968e-06, "loss": 0.7552934169769288, "step": 3535, "token_acc": 0.7684504670035217 }, { "epoch": 0.22917998559532576, "grad_norm": 0.3541809320449829, "learning_rate": 9.679518439910936e-06, "loss": 0.7707225799560546, "step": 3540, "token_acc": 0.765081559653974 }, { "epoch": 0.22950368613995192, "grad_norm": 0.3265532851219177, "learning_rate": 9.678622317462281e-06, "loss": 0.7771696090698242, "step": 3545, "token_acc": 0.7634056110694208 }, { "epoch": 0.22982738668457808, "grad_norm": 0.29417386651039124, "learning_rate": 9.677724985503667e-06, "loss": 0.788510799407959, "step": 3550, "token_acc": 0.7610851881425292 }, { "epoch": 0.23015108722920427, "grad_norm": 0.4493669271469116, "learning_rate": 9.676826444267073e-06, "loss": 0.7608751773834228, "step": 3555, "token_acc": 0.7685677317874494 }, { "epoch": 0.23047478777383043, "grad_norm": 0.2680685222148895, "learning_rate": 9.675926693984784e-06, "loss": 0.775846004486084, "step": 3560, "token_acc": 0.7628812239786075 }, { "epoch": 0.2307984883184566, "grad_norm": 0.4264129400253296, "learning_rate": 9.675025734889408e-06, "loss": 0.7882899761199951, "step": 3565, "token_acc": 0.7598455752124336 }, { "epoch": 0.23112218886308275, "grad_norm": 0.3520539104938507, "learning_rate": 9.674123567213855e-06, "loss": 0.7710935592651367, "step": 3570, "token_acc": 0.7667284504750034 }, { "epoch": 0.23144588940770894, "grad_norm": 0.4258560240268707, "learning_rate": 9.673220191191354e-06, "loss": 0.7982211112976074, "step": 3575, "token_acc": 0.7582153080443045 }, { "epoch": 0.2317695899523351, "grad_norm": 0.4269665777683258, "learning_rate": 9.672315607055445e-06, "loss": 0.7667811393737793, "step": 3580, "token_acc": 0.7669616722338923 }, { "epoch": 0.23209329049696126, "grad_norm": 0.31774502992630005, "learning_rate": 9.671409815039977e-06, "loss": 0.7614922046661377, "step": 3585, "token_acc": 0.7685193447638473 }, { "epoch": 0.23241699104158742, "grad_norm": 0.3916805386543274, "learning_rate": 9.670502815379116e-06, "loss": 0.783245849609375, "step": 3590, "token_acc": 0.7619236121849389 }, { "epoch": 0.2327406915862136, "grad_norm": 0.328072190284729, "learning_rate": 9.669594608307338e-06, "loss": 0.7826815605163574, "step": 3595, "token_acc": 0.7633984316467709 }, { "epoch": 0.23306439213083976, "grad_norm": 0.28811192512512207, "learning_rate": 9.66868519405943e-06, "loss": 0.7511766910552978, "step": 3600, "token_acc": 0.7709648274050199 }, { "epoch": 0.23338809267546592, "grad_norm": 0.32200124859809875, "learning_rate": 9.667774572870491e-06, "loss": 0.7720124244689941, "step": 3605, "token_acc": 0.7648049678822391 }, { "epoch": 0.23371179322009208, "grad_norm": 0.3774057924747467, "learning_rate": 9.666862744975938e-06, "loss": 0.786480712890625, "step": 3610, "token_acc": 0.7624598257181671 }, { "epoch": 0.23403549376471827, "grad_norm": 0.36267080903053284, "learning_rate": 9.66594971061149e-06, "loss": 0.7807086944580078, "step": 3615, "token_acc": 0.7654681003769632 }, { "epoch": 0.23435919430934443, "grad_norm": 0.29037773609161377, "learning_rate": 9.665035470013189e-06, "loss": 0.7809467792510987, "step": 3620, "token_acc": 0.7623758009538991 }, { "epoch": 0.2346828948539706, "grad_norm": 0.4029487669467926, "learning_rate": 9.664120023417379e-06, "loss": 0.7654164791107178, "step": 3625, "token_acc": 0.7659393065587179 }, { "epoch": 0.23500659539859675, "grad_norm": 0.42339426279067993, "learning_rate": 9.663203371060718e-06, "loss": 0.7960241794586181, "step": 3630, "token_acc": 0.7597844373990388 }, { "epoch": 0.2353302959432229, "grad_norm": 0.3456381857395172, "learning_rate": 9.662285513180183e-06, "loss": 0.7869180679321289, "step": 3635, "token_acc": 0.7613695533457792 }, { "epoch": 0.2356539964878491, "grad_norm": 0.3841954171657562, "learning_rate": 9.661366450013052e-06, "loss": 0.7725898742675781, "step": 3640, "token_acc": 0.7637292378011454 }, { "epoch": 0.23597769703247526, "grad_norm": 0.30910828709602356, "learning_rate": 9.660446181796924e-06, "loss": 0.7932491302490234, "step": 3645, "token_acc": 0.7618217239947622 }, { "epoch": 0.23630139757710142, "grad_norm": 0.3293084502220154, "learning_rate": 9.659524708769701e-06, "loss": 0.7949195861816406, "step": 3650, "token_acc": 0.7604371222361073 }, { "epoch": 0.23662509812172758, "grad_norm": 0.2503681182861328, "learning_rate": 9.658602031169604e-06, "loss": 0.775815486907959, "step": 3655, "token_acc": 0.7630046027794931 }, { "epoch": 0.23694879866635377, "grad_norm": 0.27935168147087097, "learning_rate": 9.657678149235161e-06, "loss": 0.7695698738098145, "step": 3660, "token_acc": 0.76561028263197 }, { "epoch": 0.23727249921097993, "grad_norm": 0.33391526341438293, "learning_rate": 9.656753063205212e-06, "loss": 0.7738601684570312, "step": 3665, "token_acc": 0.7656400608917046 }, { "epoch": 0.23759619975560609, "grad_norm": 0.2976086139678955, "learning_rate": 9.655826773318912e-06, "loss": 0.7757869243621827, "step": 3670, "token_acc": 0.7623792918454936 }, { "epoch": 0.23791990030023225, "grad_norm": 0.4018920958042145, "learning_rate": 9.65489927981572e-06, "loss": 0.7686808109283447, "step": 3675, "token_acc": 0.7659031528787448 }, { "epoch": 0.23824360084485843, "grad_norm": 0.2991305887699127, "learning_rate": 9.65397058293541e-06, "loss": 0.7491635322570801, "step": 3680, "token_acc": 0.7721826879299484 }, { "epoch": 0.2385673013894846, "grad_norm": 0.4172670543193817, "learning_rate": 9.65304068291807e-06, "loss": 0.7463790893554687, "step": 3685, "token_acc": 0.7720192339144941 }, { "epoch": 0.23889100193411075, "grad_norm": 0.30767545104026794, "learning_rate": 9.652109580004094e-06, "loss": 0.7537674903869629, "step": 3690, "token_acc": 0.7699657775736365 }, { "epoch": 0.2392147024787369, "grad_norm": 0.3181091547012329, "learning_rate": 9.651177274434191e-06, "loss": 0.7665512084960937, "step": 3695, "token_acc": 0.7645661811272958 }, { "epoch": 0.2395384030233631, "grad_norm": 0.41872328519821167, "learning_rate": 9.650243766449379e-06, "loss": 0.7562599658966065, "step": 3700, "token_acc": 0.7686442583520146 }, { "epoch": 0.23986210356798926, "grad_norm": 0.4593248665332794, "learning_rate": 9.649309056290985e-06, "loss": 0.7676116943359375, "step": 3705, "token_acc": 0.7658598888817932 }, { "epoch": 0.24018580411261542, "grad_norm": 0.3101935088634491, "learning_rate": 9.648373144200651e-06, "loss": 0.7826481342315674, "step": 3710, "token_acc": 0.7633169020077639 }, { "epoch": 0.24050950465724158, "grad_norm": 0.31913143396377563, "learning_rate": 9.647436030420326e-06, "loss": 0.7388489723205567, "step": 3715, "token_acc": 0.7738597919263348 }, { "epoch": 0.24083320520186774, "grad_norm": 0.34286847710609436, "learning_rate": 9.646497715192272e-06, "loss": 0.7521434783935547, "step": 3720, "token_acc": 0.7696154923378546 }, { "epoch": 0.24115690574649393, "grad_norm": 0.34855198860168457, "learning_rate": 9.64555819875906e-06, "loss": 0.7742067337036133, "step": 3725, "token_acc": 0.7644606496065631 }, { "epoch": 0.2414806062911201, "grad_norm": 0.34138965606689453, "learning_rate": 9.644617481363575e-06, "loss": 0.7563294410705567, "step": 3730, "token_acc": 0.7684100418410041 }, { "epoch": 0.24180430683574625, "grad_norm": 0.3876451551914215, "learning_rate": 9.643675563249004e-06, "loss": 0.753810453414917, "step": 3735, "token_acc": 0.771428193914089 }, { "epoch": 0.2421280073803724, "grad_norm": 0.3747771680355072, "learning_rate": 9.642732444658857e-06, "loss": 0.7759902954101563, "step": 3740, "token_acc": 0.7640729340567612 }, { "epoch": 0.2424517079249986, "grad_norm": 0.3738023042678833, "learning_rate": 9.641788125836943e-06, "loss": 0.7778173446655273, "step": 3745, "token_acc": 0.7645552385892116 }, { "epoch": 0.24277540846962475, "grad_norm": 0.35740774869918823, "learning_rate": 9.640842607027386e-06, "loss": 0.7729969978332519, "step": 3750, "token_acc": 0.7646002808765469 }, { "epoch": 0.2430991090142509, "grad_norm": 0.379341721534729, "learning_rate": 9.639895888474622e-06, "loss": 0.7717373847961426, "step": 3755, "token_acc": 0.7638655745441062 }, { "epoch": 0.24342280955887707, "grad_norm": 0.41117218136787415, "learning_rate": 9.638947970423395e-06, "loss": 0.7474530220031739, "step": 3760, "token_acc": 0.7705025171150884 }, { "epoch": 0.24374651010350326, "grad_norm": 0.3361301124095917, "learning_rate": 9.637998853118758e-06, "loss": 0.767388391494751, "step": 3765, "token_acc": 0.7661200161415161 }, { "epoch": 0.24407021064812942, "grad_norm": 0.4161657392978668, "learning_rate": 9.637048536806076e-06, "loss": 0.7996221065521241, "step": 3770, "token_acc": 0.7576763667143399 }, { "epoch": 0.24439391119275558, "grad_norm": 0.3281700909137726, "learning_rate": 9.63609702173102e-06, "loss": 0.7733657836914063, "step": 3775, "token_acc": 0.7644480392412659 }, { "epoch": 0.24471761173738174, "grad_norm": 0.29677897691726685, "learning_rate": 9.63514430813958e-06, "loss": 0.7635751724243164, "step": 3780, "token_acc": 0.7658325817224484 }, { "epoch": 0.24504131228200793, "grad_norm": 0.30257654190063477, "learning_rate": 9.634190396278047e-06, "loss": 0.7531604766845703, "step": 3785, "token_acc": 0.7688998078679643 }, { "epoch": 0.2453650128266341, "grad_norm": 0.361023485660553, "learning_rate": 9.633235286393024e-06, "loss": 0.7619872093200684, "step": 3790, "token_acc": 0.7677755864646045 }, { "epoch": 0.24568871337126025, "grad_norm": 0.36622029542922974, "learning_rate": 9.632278978731426e-06, "loss": 0.752929973602295, "step": 3795, "token_acc": 0.7687898089171975 }, { "epoch": 0.2460124139158864, "grad_norm": 0.42458462715148926, "learning_rate": 9.631321473540476e-06, "loss": 0.790784215927124, "step": 3800, "token_acc": 0.7600984813210785 }, { "epoch": 0.24633611446051257, "grad_norm": 0.37701699137687683, "learning_rate": 9.630362771067705e-06, "loss": 0.7553232192993165, "step": 3805, "token_acc": 0.7701900923616445 }, { "epoch": 0.24665981500513876, "grad_norm": 0.3702615201473236, "learning_rate": 9.629402871560958e-06, "loss": 0.7548138618469238, "step": 3810, "token_acc": 0.768689556527734 }, { "epoch": 0.24698351554976491, "grad_norm": 0.2521846294403076, "learning_rate": 9.628441775268384e-06, "loss": 0.7614480972290039, "step": 3815, "token_acc": 0.7667995984916307 }, { "epoch": 0.24730721609439107, "grad_norm": 0.4161320626735687, "learning_rate": 9.627479482438445e-06, "loss": 0.767577838897705, "step": 3820, "token_acc": 0.7653526515507887 }, { "epoch": 0.24763091663901723, "grad_norm": 0.3117702305316925, "learning_rate": 9.626515993319912e-06, "loss": 0.7503294944763184, "step": 3825, "token_acc": 0.7703089919836031 }, { "epoch": 0.24795461718364342, "grad_norm": 0.30128854513168335, "learning_rate": 9.625551308161864e-06, "loss": 0.7677359580993652, "step": 3830, "token_acc": 0.7647712352287648 }, { "epoch": 0.24827831772826958, "grad_norm": 0.26579439640045166, "learning_rate": 9.624585427213691e-06, "loss": 0.7719532489776612, "step": 3835, "token_acc": 0.7659104291961917 }, { "epoch": 0.24860201827289574, "grad_norm": 0.378719300031662, "learning_rate": 9.623618350725091e-06, "loss": 0.7858165740966797, "step": 3840, "token_acc": 0.7624440607491455 }, { "epoch": 0.2489257188175219, "grad_norm": 0.3092897832393646, "learning_rate": 9.622650078946068e-06, "loss": 0.7776577472686768, "step": 3845, "token_acc": 0.7625442438649602 }, { "epoch": 0.2492494193621481, "grad_norm": 0.34710195660591125, "learning_rate": 9.621680612126942e-06, "loss": 0.7626083374023438, "step": 3850, "token_acc": 0.7671033478893741 }, { "epoch": 0.24957311990677425, "grad_norm": 0.40255007147789, "learning_rate": 9.620709950518336e-06, "loss": 0.771629810333252, "step": 3855, "token_acc": 0.7648093604459153 }, { "epoch": 0.2498968204514004, "grad_norm": 0.3168726861476898, "learning_rate": 9.619738094371182e-06, "loss": 0.7383884906768798, "step": 3860, "token_acc": 0.7716169032468592 }, { "epoch": 0.2502205209960266, "grad_norm": 0.3355337977409363, "learning_rate": 9.618765043936728e-06, "loss": 0.7615836143493653, "step": 3865, "token_acc": 0.7684724720488132 }, { "epoch": 0.25054422154065276, "grad_norm": 0.3654627203941345, "learning_rate": 9.61779079946652e-06, "loss": 0.7755712509155274, "step": 3870, "token_acc": 0.7638705603788477 }, { "epoch": 0.2508679220852789, "grad_norm": 0.332931786775589, "learning_rate": 9.616815361212422e-06, "loss": 0.7673693656921386, "step": 3875, "token_acc": 0.7666953467159188 }, { "epoch": 0.2511916226299051, "grad_norm": 0.276696115732193, "learning_rate": 9.615838729426601e-06, "loss": 0.7391736030578613, "step": 3880, "token_acc": 0.7730419620764368 }, { "epoch": 0.25151532317453124, "grad_norm": 0.3532024323940277, "learning_rate": 9.614860904361534e-06, "loss": 0.7696560382843017, "step": 3885, "token_acc": 0.7659612862865873 }, { "epoch": 0.2518390237191574, "grad_norm": 0.29248079657554626, "learning_rate": 9.613881886270006e-06, "loss": 0.7868582725524902, "step": 3890, "token_acc": 0.7621401333216895 }, { "epoch": 0.25216272426378356, "grad_norm": 0.3746921420097351, "learning_rate": 9.612901675405116e-06, "loss": 0.7461020946502686, "step": 3895, "token_acc": 0.7696312966079792 }, { "epoch": 0.2524864248084097, "grad_norm": 0.3531264662742615, "learning_rate": 9.61192027202026e-06, "loss": 0.7719437122344971, "step": 3900, "token_acc": 0.7661653265065737 }, { "epoch": 0.25281012535303593, "grad_norm": 0.34245574474334717, "learning_rate": 9.610937676369152e-06, "loss": 0.7767814636230469, "step": 3905, "token_acc": 0.7645204062858847 }, { "epoch": 0.2531338258976621, "grad_norm": 0.3311384320259094, "learning_rate": 9.609953888705812e-06, "loss": 0.7874638557434082, "step": 3910, "token_acc": 0.761386145399963 }, { "epoch": 0.25345752644228825, "grad_norm": 0.2812725901603699, "learning_rate": 9.608968909284566e-06, "loss": 0.7909380912780761, "step": 3915, "token_acc": 0.7598486734722107 }, { "epoch": 0.2537812269869144, "grad_norm": 0.3514128625392914, "learning_rate": 9.60798273836005e-06, "loss": 0.7747740268707275, "step": 3920, "token_acc": 0.7648626122125514 }, { "epoch": 0.25410492753154057, "grad_norm": 0.3025883138179779, "learning_rate": 9.606995376187204e-06, "loss": 0.7541437149047852, "step": 3925, "token_acc": 0.7688731882047583 }, { "epoch": 0.25442862807616673, "grad_norm": 0.34170645475387573, "learning_rate": 9.606006823021283e-06, "loss": 0.7887770175933838, "step": 3930, "token_acc": 0.7624345741103541 }, { "epoch": 0.2547523286207929, "grad_norm": 0.37806960940361023, "learning_rate": 9.605017079117846e-06, "loss": 0.7744997501373291, "step": 3935, "token_acc": 0.7646175128476373 }, { "epoch": 0.25507602916541905, "grad_norm": 0.2222849726676941, "learning_rate": 9.60402614473276e-06, "loss": 0.7683780670166016, "step": 3940, "token_acc": 0.7663436258385503 }, { "epoch": 0.25539972971004526, "grad_norm": 0.4460173547267914, "learning_rate": 9.603034020122197e-06, "loss": 0.7987190246582031, "step": 3945, "token_acc": 0.7588327327288816 }, { "epoch": 0.2557234302546714, "grad_norm": 0.278666228055954, "learning_rate": 9.602040705542643e-06, "loss": 0.8015724182128906, "step": 3950, "token_acc": 0.7564987093097322 }, { "epoch": 0.2560471307992976, "grad_norm": 0.3993418514728546, "learning_rate": 9.601046201250887e-06, "loss": 0.7581057548522949, "step": 3955, "token_acc": 0.769612996283982 }, { "epoch": 0.25637083134392374, "grad_norm": 0.3376043438911438, "learning_rate": 9.600050507504025e-06, "loss": 0.7507676124572754, "step": 3960, "token_acc": 0.769290739447161 }, { "epoch": 0.2566945318885499, "grad_norm": 0.3194694519042969, "learning_rate": 9.599053624559463e-06, "loss": 0.7740999221801758, "step": 3965, "token_acc": 0.7639986235375086 }, { "epoch": 0.25701823243317606, "grad_norm": 0.3425295054912567, "learning_rate": 9.598055552674916e-06, "loss": 0.7650864601135254, "step": 3970, "token_acc": 0.7680302638013866 }, { "epoch": 0.2573419329778022, "grad_norm": 0.39387357234954834, "learning_rate": 9.5970562921084e-06, "loss": 0.7569726467132568, "step": 3975, "token_acc": 0.7707142433293115 }, { "epoch": 0.2576656335224284, "grad_norm": 0.37109559774398804, "learning_rate": 9.596055843118244e-06, "loss": 0.7664441108703614, "step": 3980, "token_acc": 0.7665912569033202 }, { "epoch": 0.25798933406705454, "grad_norm": 0.26436370611190796, "learning_rate": 9.595054205963083e-06, "loss": 0.7488771438598633, "step": 3985, "token_acc": 0.7695040296736715 }, { "epoch": 0.25831303461168076, "grad_norm": 0.34438297152519226, "learning_rate": 9.59405138090186e-06, "loss": 0.7607848167419433, "step": 3990, "token_acc": 0.7694218058140281 }, { "epoch": 0.2586367351563069, "grad_norm": 0.3081933856010437, "learning_rate": 9.593047368193819e-06, "loss": 0.7801331520080567, "step": 3995, "token_acc": 0.7624423637601305 }, { "epoch": 0.2589604357009331, "grad_norm": 0.29408368468284607, "learning_rate": 9.59204216809852e-06, "loss": 0.7605128765106202, "step": 4000, "token_acc": 0.7681002349256069 }, { "epoch": 0.25928413624555924, "grad_norm": 0.34292054176330566, "learning_rate": 9.591035780875824e-06, "loss": 0.7559561729431152, "step": 4005, "token_acc": 0.7677750510976908 }, { "epoch": 0.2596078367901854, "grad_norm": 0.3104279339313507, "learning_rate": 9.590028206785902e-06, "loss": 0.7711165428161622, "step": 4010, "token_acc": 0.763317441115776 }, { "epoch": 0.25993153733481156, "grad_norm": 0.34241580963134766, "learning_rate": 9.589019446089229e-06, "loss": 0.7573083877563477, "step": 4015, "token_acc": 0.7690459225728935 }, { "epoch": 0.2602552378794377, "grad_norm": 0.29140740633010864, "learning_rate": 9.58800949904659e-06, "loss": 0.7672828197479248, "step": 4020, "token_acc": 0.765425295293235 }, { "epoch": 0.2605789384240639, "grad_norm": 0.306139200925827, "learning_rate": 9.586998365919073e-06, "loss": 0.7698581695556641, "step": 4025, "token_acc": 0.7656483208955224 }, { "epoch": 0.26090263896869004, "grad_norm": 0.28749772906303406, "learning_rate": 9.585986046968075e-06, "loss": 0.788268756866455, "step": 4030, "token_acc": 0.7622332372139191 }, { "epoch": 0.26122633951331625, "grad_norm": 0.34925538301467896, "learning_rate": 9.584972542455297e-06, "loss": 0.7403841972351074, "step": 4035, "token_acc": 0.7722847397111798 }, { "epoch": 0.2615500400579424, "grad_norm": 0.24704280495643616, "learning_rate": 9.583957852642754e-06, "loss": 0.7709883689880371, "step": 4040, "token_acc": 0.76428810720268 }, { "epoch": 0.26187374060256857, "grad_norm": 0.39172032475471497, "learning_rate": 9.582941977792757e-06, "loss": 0.7565415382385254, "step": 4045, "token_acc": 0.7693127095781963 }, { "epoch": 0.26219744114719473, "grad_norm": 0.3805525004863739, "learning_rate": 9.581924918167929e-06, "loss": 0.7403270721435546, "step": 4050, "token_acc": 0.7714664168255096 }, { "epoch": 0.2625211416918209, "grad_norm": 0.2700596749782562, "learning_rate": 9.580906674031202e-06, "loss": 0.7854210376739502, "step": 4055, "token_acc": 0.7626674432149098 }, { "epoch": 0.26284484223644705, "grad_norm": 0.3209259808063507, "learning_rate": 9.579887245645806e-06, "loss": 0.7549013137817383, "step": 4060, "token_acc": 0.7681836281543373 }, { "epoch": 0.2631685427810732, "grad_norm": 0.3456316292285919, "learning_rate": 9.578866633275289e-06, "loss": 0.7504077911376953, "step": 4065, "token_acc": 0.7712780198116193 }, { "epoch": 0.26349224332569937, "grad_norm": 0.34698933362960815, "learning_rate": 9.57784483718349e-06, "loss": 0.7637345314025878, "step": 4070, "token_acc": 0.7666450175721856 }, { "epoch": 0.2638159438703256, "grad_norm": 0.3044915497303009, "learning_rate": 9.576821857634566e-06, "loss": 0.7706604480743409, "step": 4075, "token_acc": 0.7666274259190744 }, { "epoch": 0.26413964441495175, "grad_norm": 0.28353336453437805, "learning_rate": 9.575797694892976e-06, "loss": 0.7659365653991699, "step": 4080, "token_acc": 0.7656512605042017 }, { "epoch": 0.2644633449595779, "grad_norm": 0.3424322009086609, "learning_rate": 9.574772349223487e-06, "loss": 0.7558713912963867, "step": 4085, "token_acc": 0.7684203208150573 }, { "epoch": 0.26478704550420407, "grad_norm": 0.3487887978553772, "learning_rate": 9.573745820891165e-06, "loss": 0.7603254318237305, "step": 4090, "token_acc": 0.7655691783046443 }, { "epoch": 0.2651107460488302, "grad_norm": 0.31621527671813965, "learning_rate": 9.57271811016139e-06, "loss": 0.7574943542480469, "step": 4095, "token_acc": 0.7678208022226081 }, { "epoch": 0.2654344465934564, "grad_norm": 0.2969910800457001, "learning_rate": 9.571689217299842e-06, "loss": 0.7433856964111328, "step": 4100, "token_acc": 0.7700425670805511 }, { "epoch": 0.26575814713808255, "grad_norm": 0.4188826382160187, "learning_rate": 9.570659142572509e-06, "loss": 0.760215425491333, "step": 4105, "token_acc": 0.7671055956425302 }, { "epoch": 0.2660818476827087, "grad_norm": 0.33326318860054016, "learning_rate": 9.569627886245687e-06, "loss": 0.7447025299072265, "step": 4110, "token_acc": 0.7705899116557424 }, { "epoch": 0.26640554822733487, "grad_norm": 0.34396451711654663, "learning_rate": 9.56859544858597e-06, "loss": 0.7566027641296387, "step": 4115, "token_acc": 0.7676936529163666 }, { "epoch": 0.2667292487719611, "grad_norm": 0.3253948390483856, "learning_rate": 9.567561829860269e-06, "loss": 0.7931069374084473, "step": 4120, "token_acc": 0.7609399393107923 }, { "epoch": 0.26705294931658724, "grad_norm": 0.2784155309200287, "learning_rate": 9.566527030335787e-06, "loss": 0.7476081848144531, "step": 4125, "token_acc": 0.7696446470721376 }, { "epoch": 0.2673766498612134, "grad_norm": 0.34874802827835083, "learning_rate": 9.56549105028004e-06, "loss": 0.7732120037078858, "step": 4130, "token_acc": 0.766615217590352 }, { "epoch": 0.26770035040583956, "grad_norm": 0.37639009952545166, "learning_rate": 9.56445388996085e-06, "loss": 0.7837844371795655, "step": 4135, "token_acc": 0.7603864800648253 }, { "epoch": 0.2680240509504657, "grad_norm": 0.3696346580982208, "learning_rate": 9.56341554964634e-06, "loss": 0.7693172931671143, "step": 4140, "token_acc": 0.7642418805974399 }, { "epoch": 0.2683477514950919, "grad_norm": 0.32829615473747253, "learning_rate": 9.562376029604943e-06, "loss": 0.7720015048980713, "step": 4145, "token_acc": 0.7640111868872033 }, { "epoch": 0.26867145203971804, "grad_norm": 0.37602725625038147, "learning_rate": 9.561335330105392e-06, "loss": 0.7674998283386231, "step": 4150, "token_acc": 0.7658241687568332 }, { "epoch": 0.2689951525843442, "grad_norm": 0.35780903697013855, "learning_rate": 9.560293451416727e-06, "loss": 0.7562527656555176, "step": 4155, "token_acc": 0.7697760154892782 }, { "epoch": 0.2693188531289704, "grad_norm": 0.31782716512680054, "learning_rate": 9.559250393808292e-06, "loss": 0.7583272933959961, "step": 4160, "token_acc": 0.7684422110552764 }, { "epoch": 0.2696425536735966, "grad_norm": 0.36148396134376526, "learning_rate": 9.558206157549737e-06, "loss": 0.7498702526092529, "step": 4165, "token_acc": 0.7705325869913909 }, { "epoch": 0.26996625421822273, "grad_norm": 0.32653290033340454, "learning_rate": 9.557160742911019e-06, "loss": 0.7549257755279541, "step": 4170, "token_acc": 0.7721951219512195 }, { "epoch": 0.2702899547628489, "grad_norm": 0.31193599104881287, "learning_rate": 9.556114150162392e-06, "loss": 0.7549666881561279, "step": 4175, "token_acc": 0.7699604046321157 }, { "epoch": 0.27061365530747505, "grad_norm": 0.49092578887939453, "learning_rate": 9.555066379574423e-06, "loss": 0.7737460613250733, "step": 4180, "token_acc": 0.7647871752349364 }, { "epoch": 0.2709373558521012, "grad_norm": 0.3040165603160858, "learning_rate": 9.55401743141798e-06, "loss": 0.7537327766418457, "step": 4185, "token_acc": 0.7683616538863272 }, { "epoch": 0.2712610563967274, "grad_norm": 0.3339957594871521, "learning_rate": 9.552967305964233e-06, "loss": 0.7508474349975586, "step": 4190, "token_acc": 0.7690801044609071 }, { "epoch": 0.27158475694135353, "grad_norm": 0.4216665029525757, "learning_rate": 9.551916003484663e-06, "loss": 0.7746268749237061, "step": 4195, "token_acc": 0.7631032661433959 }, { "epoch": 0.2719084574859797, "grad_norm": 0.3385362923145294, "learning_rate": 9.550863524251047e-06, "loss": 0.769188404083252, "step": 4200, "token_acc": 0.7642939753969088 }, { "epoch": 0.2722321580306059, "grad_norm": 0.32607850432395935, "learning_rate": 9.54980986853547e-06, "loss": 0.780689811706543, "step": 4205, "token_acc": 0.7632555125005172 }, { "epoch": 0.27255585857523207, "grad_norm": 0.38808104395866394, "learning_rate": 9.548755036610324e-06, "loss": 0.778179121017456, "step": 4210, "token_acc": 0.7631219536643737 }, { "epoch": 0.27287955911985823, "grad_norm": 0.29116255044937134, "learning_rate": 9.547699028748302e-06, "loss": 0.747612476348877, "step": 4215, "token_acc": 0.7703380215628981 }, { "epoch": 0.2732032596644844, "grad_norm": 0.3658313453197479, "learning_rate": 9.546641845222402e-06, "loss": 0.7368217468261719, "step": 4220, "token_acc": 0.7745736297711363 }, { "epoch": 0.27352696020911055, "grad_norm": 0.24773605167865753, "learning_rate": 9.545583486305922e-06, "loss": 0.7637070655822754, "step": 4225, "token_acc": 0.7681074121758322 }, { "epoch": 0.2738506607537367, "grad_norm": 0.33202674984931946, "learning_rate": 9.54452395227247e-06, "loss": 0.7595718383789063, "step": 4230, "token_acc": 0.7684870427716594 }, { "epoch": 0.27417436129836287, "grad_norm": 0.2661753296852112, "learning_rate": 9.543463243395956e-06, "loss": 0.7758455753326416, "step": 4235, "token_acc": 0.7654639336567047 }, { "epoch": 0.274498061842989, "grad_norm": 0.2950303554534912, "learning_rate": 9.542401359950591e-06, "loss": 0.780217981338501, "step": 4240, "token_acc": 0.7626498652677072 }, { "epoch": 0.27482176238761524, "grad_norm": 0.36475664377212524, "learning_rate": 9.541338302210892e-06, "loss": 0.7668500900268554, "step": 4245, "token_acc": 0.7641336281689082 }, { "epoch": 0.2751454629322414, "grad_norm": 0.3731430470943451, "learning_rate": 9.540274070451677e-06, "loss": 0.7802584171295166, "step": 4250, "token_acc": 0.7625681674064679 }, { "epoch": 0.27546916347686756, "grad_norm": 0.2735031247138977, "learning_rate": 9.539208664948072e-06, "loss": 0.7486495971679688, "step": 4255, "token_acc": 0.7704030703032483 }, { "epoch": 0.2757928640214937, "grad_norm": 0.3168465197086334, "learning_rate": 9.538142085975504e-06, "loss": 0.7653616428375244, "step": 4260, "token_acc": 0.7666675566710277 }, { "epoch": 0.2761165645661199, "grad_norm": 0.3917292356491089, "learning_rate": 9.537074333809702e-06, "loss": 0.7732180118560791, "step": 4265, "token_acc": 0.7646861638447067 }, { "epoch": 0.27644026511074604, "grad_norm": 0.2908684015274048, "learning_rate": 9.536005408726701e-06, "loss": 0.7528514385223388, "step": 4270, "token_acc": 0.7683486662517639 }, { "epoch": 0.2767639656553722, "grad_norm": 0.4976845979690552, "learning_rate": 9.534935311002836e-06, "loss": 0.7671231269836426, "step": 4275, "token_acc": 0.7640015972383234 }, { "epoch": 0.27708766619999836, "grad_norm": 0.2783280909061432, "learning_rate": 9.533864040914746e-06, "loss": 0.7723662376403808, "step": 4280, "token_acc": 0.7653699022121989 }, { "epoch": 0.2774113667446245, "grad_norm": 0.3122170567512512, "learning_rate": 9.532791598739379e-06, "loss": 0.7684160232543945, "step": 4285, "token_acc": 0.7680388282105376 }, { "epoch": 0.27773506728925074, "grad_norm": 0.38330066204071045, "learning_rate": 9.531717984753976e-06, "loss": 0.7601273536682129, "step": 4290, "token_acc": 0.7669856869034838 }, { "epoch": 0.2780587678338769, "grad_norm": 0.287239670753479, "learning_rate": 9.530643199236089e-06, "loss": 0.7588417530059814, "step": 4295, "token_acc": 0.7711903627577759 }, { "epoch": 0.27838246837850306, "grad_norm": 0.32319891452789307, "learning_rate": 9.529567242463566e-06, "loss": 0.7656576633453369, "step": 4300, "token_acc": 0.7663299663299663 }, { "epoch": 0.2787061689231292, "grad_norm": 0.3995298445224762, "learning_rate": 9.528490114714568e-06, "loss": 0.7461750030517578, "step": 4305, "token_acc": 0.7715015021474614 }, { "epoch": 0.2790298694677554, "grad_norm": 0.42257484793663025, "learning_rate": 9.527411816267546e-06, "loss": 0.7557939052581787, "step": 4310, "token_acc": 0.7686897488119484 }, { "epoch": 0.27935357001238154, "grad_norm": 0.3124387562274933, "learning_rate": 9.526332347401264e-06, "loss": 0.754632568359375, "step": 4315, "token_acc": 0.7691410853494836 }, { "epoch": 0.2796772705570077, "grad_norm": 0.4028124213218689, "learning_rate": 9.525251708394783e-06, "loss": 0.7684298038482666, "step": 4320, "token_acc": 0.7656686863104989 }, { "epoch": 0.28000097110163386, "grad_norm": 0.35937926173210144, "learning_rate": 9.524169899527466e-06, "loss": 0.7236238479614258, "step": 4325, "token_acc": 0.7769788352871109 }, { "epoch": 0.28032467164626007, "grad_norm": 0.2807149589061737, "learning_rate": 9.523086921078986e-06, "loss": 0.7607580184936523, "step": 4330, "token_acc": 0.7676815917929379 }, { "epoch": 0.28064837219088623, "grad_norm": 0.3392060101032257, "learning_rate": 9.522002773329309e-06, "loss": 0.7513254165649415, "step": 4335, "token_acc": 0.7707155623221024 }, { "epoch": 0.2809720727355124, "grad_norm": 0.2771196663379669, "learning_rate": 9.520917456558708e-06, "loss": 0.7689661979675293, "step": 4340, "token_acc": 0.7657194176143122 }, { "epoch": 0.28129577328013855, "grad_norm": 0.34664854407310486, "learning_rate": 9.519830971047755e-06, "loss": 0.7595928192138672, "step": 4345, "token_acc": 0.7679024853965752 }, { "epoch": 0.2816194738247647, "grad_norm": 0.3396337926387787, "learning_rate": 9.518743317077331e-06, "loss": 0.7559855937957763, "step": 4350, "token_acc": 0.7683202751273498 }, { "epoch": 0.28194317436939087, "grad_norm": 0.32364189624786377, "learning_rate": 9.51765449492861e-06, "loss": 0.7927253723144532, "step": 4355, "token_acc": 0.7596170134912622 }, { "epoch": 0.28226687491401703, "grad_norm": 0.356838583946228, "learning_rate": 9.516564504883076e-06, "loss": 0.7506668090820312, "step": 4360, "token_acc": 0.7700256977559126 }, { "epoch": 0.2825905754586432, "grad_norm": 0.35648873448371887, "learning_rate": 9.51547334722251e-06, "loss": 0.7532503128051757, "step": 4365, "token_acc": 0.7696969696969697 }, { "epoch": 0.28291427600326935, "grad_norm": 0.35702529549598694, "learning_rate": 9.514381022228997e-06, "loss": 0.7656462669372559, "step": 4370, "token_acc": 0.7675271926701495 }, { "epoch": 0.28323797654789556, "grad_norm": 0.37452611327171326, "learning_rate": 9.513287530184922e-06, "loss": 0.7695687294006348, "step": 4375, "token_acc": 0.7643605643686615 }, { "epoch": 0.2835616770925217, "grad_norm": 0.30398029088974, "learning_rate": 9.512192871372974e-06, "loss": 0.7729438781738281, "step": 4380, "token_acc": 0.7648511608406268 }, { "epoch": 0.2838853776371479, "grad_norm": 0.37224245071411133, "learning_rate": 9.51109704607614e-06, "loss": 0.7583317756652832, "step": 4385, "token_acc": 0.769419409792823 }, { "epoch": 0.28420907818177404, "grad_norm": 0.3722825050354004, "learning_rate": 9.510000054577715e-06, "loss": 0.776151704788208, "step": 4390, "token_acc": 0.763888380715427 }, { "epoch": 0.2845327787264002, "grad_norm": 0.2995399534702301, "learning_rate": 9.50890189716129e-06, "loss": 0.7514435768127441, "step": 4395, "token_acc": 0.7705454545454545 }, { "epoch": 0.28485647927102636, "grad_norm": 0.28348803520202637, "learning_rate": 9.507802574110756e-06, "loss": 0.7562634944915771, "step": 4400, "token_acc": 0.7692847953826362 }, { "epoch": 0.2851801798156525, "grad_norm": 0.29680874943733215, "learning_rate": 9.506702085710314e-06, "loss": 0.761821985244751, "step": 4405, "token_acc": 0.7665358469866851 }, { "epoch": 0.2855038803602787, "grad_norm": 0.33402207493782043, "learning_rate": 9.505600432244453e-06, "loss": 0.7591756343841553, "step": 4410, "token_acc": 0.7693640805259253 }, { "epoch": 0.2858275809049049, "grad_norm": 0.262185662984848, "learning_rate": 9.504497613997977e-06, "loss": 0.7570871829986572, "step": 4415, "token_acc": 0.7692611014645148 }, { "epoch": 0.28615128144953106, "grad_norm": 0.2898060083389282, "learning_rate": 9.503393631255983e-06, "loss": 0.7353084087371826, "step": 4420, "token_acc": 0.7747968878185619 }, { "epoch": 0.2864749819941572, "grad_norm": 0.32718807458877563, "learning_rate": 9.50228848430387e-06, "loss": 0.7678080081939698, "step": 4425, "token_acc": 0.766976923128843 }, { "epoch": 0.2867986825387834, "grad_norm": 0.42393821477890015, "learning_rate": 9.501182173427339e-06, "loss": 0.7843508243560791, "step": 4430, "token_acc": 0.7621252129760991 }, { "epoch": 0.28712238308340954, "grad_norm": 0.29934731125831604, "learning_rate": 9.50007469891239e-06, "loss": 0.7469452857971192, "step": 4435, "token_acc": 0.7706651014797194 }, { "epoch": 0.2874460836280357, "grad_norm": 0.25776609778404236, "learning_rate": 9.49896606104533e-06, "loss": 0.7845798015594483, "step": 4440, "token_acc": 0.7610316484369943 }, { "epoch": 0.28776978417266186, "grad_norm": 0.3114307224750519, "learning_rate": 9.497856260112758e-06, "loss": 0.7515461921691895, "step": 4445, "token_acc": 0.7696968562407178 }, { "epoch": 0.288093484717288, "grad_norm": 0.3745977282524109, "learning_rate": 9.496745296401582e-06, "loss": 0.7617225646972656, "step": 4450, "token_acc": 0.7675006062565678 }, { "epoch": 0.2884171852619142, "grad_norm": 0.3127990961074829, "learning_rate": 9.495633170199004e-06, "loss": 0.7350126743316651, "step": 4455, "token_acc": 0.7735177324387238 }, { "epoch": 0.2887408858065404, "grad_norm": 0.3984585404396057, "learning_rate": 9.494519881792527e-06, "loss": 0.7605657577514648, "step": 4460, "token_acc": 0.7692152406504171 }, { "epoch": 0.28906458635116655, "grad_norm": 0.32210004329681396, "learning_rate": 9.49340543146996e-06, "loss": 0.7560539722442627, "step": 4465, "token_acc": 0.7691488214035277 }, { "epoch": 0.2893882868957927, "grad_norm": 0.35565856099128723, "learning_rate": 9.492289819519408e-06, "loss": 0.7577773571014405, "step": 4470, "token_acc": 0.7671981841800973 }, { "epoch": 0.28971198744041887, "grad_norm": 0.46710148453712463, "learning_rate": 9.491173046229279e-06, "loss": 0.7469536781311035, "step": 4475, "token_acc": 0.7707337116301476 }, { "epoch": 0.29003568798504503, "grad_norm": 0.45637449622154236, "learning_rate": 9.490055111888274e-06, "loss": 0.735362195968628, "step": 4480, "token_acc": 0.7752947557369216 }, { "epoch": 0.2903593885296712, "grad_norm": 0.3416234254837036, "learning_rate": 9.488936016785406e-06, "loss": 0.7745484352111817, "step": 4485, "token_acc": 0.7631936896369678 }, { "epoch": 0.29068308907429735, "grad_norm": 0.3244551420211792, "learning_rate": 9.487815761209977e-06, "loss": 0.7638378143310547, "step": 4490, "token_acc": 0.7650875332259627 }, { "epoch": 0.2910067896189235, "grad_norm": 0.26712438464164734, "learning_rate": 9.486694345451597e-06, "loss": 0.7368363380432129, "step": 4495, "token_acc": 0.7722616130545853 }, { "epoch": 0.2913304901635497, "grad_norm": 0.3685785233974457, "learning_rate": 9.48557176980017e-06, "loss": 0.762933349609375, "step": 4500, "token_acc": 0.7668580351193641 }, { "epoch": 0.2916541907081759, "grad_norm": 0.34293755888938904, "learning_rate": 9.484448034545903e-06, "loss": 0.7510804653167724, "step": 4505, "token_acc": 0.769750540696659 }, { "epoch": 0.29197789125280205, "grad_norm": 0.3475276529788971, "learning_rate": 9.483323139979304e-06, "loss": 0.7585835456848145, "step": 4510, "token_acc": 0.767500189489206 }, { "epoch": 0.2923015917974282, "grad_norm": 0.4156075119972229, "learning_rate": 9.482197086391178e-06, "loss": 0.7404383659362793, "step": 4515, "token_acc": 0.7723585919611207 }, { "epoch": 0.29262529234205437, "grad_norm": 0.41295546293258667, "learning_rate": 9.481069874072628e-06, "loss": 0.7686311721801757, "step": 4520, "token_acc": 0.7658509164117447 }, { "epoch": 0.2929489928866805, "grad_norm": 0.4232020676136017, "learning_rate": 9.479941503315064e-06, "loss": 0.7568188190460206, "step": 4525, "token_acc": 0.7699205163133324 }, { "epoch": 0.2932726934313067, "grad_norm": 0.2787359952926636, "learning_rate": 9.478811974410187e-06, "loss": 0.7496087551116943, "step": 4530, "token_acc": 0.7700200267022697 }, { "epoch": 0.29359639397593285, "grad_norm": 0.37961697578430176, "learning_rate": 9.47768128765e-06, "loss": 0.7397269248962403, "step": 4535, "token_acc": 0.7720329818869965 }, { "epoch": 0.293920094520559, "grad_norm": 0.33942151069641113, "learning_rate": 9.476549443326813e-06, "loss": 0.7579152107238769, "step": 4540, "token_acc": 0.7679549723934487 }, { "epoch": 0.2942437950651852, "grad_norm": 0.2787768244743347, "learning_rate": 9.47541644173322e-06, "loss": 0.7501585006713867, "step": 4545, "token_acc": 0.7701194649116532 }, { "epoch": 0.2945674956098114, "grad_norm": 0.2234603315591812, "learning_rate": 9.47428228316213e-06, "loss": 0.7621867656707764, "step": 4550, "token_acc": 0.7673084227993362 }, { "epoch": 0.29489119615443754, "grad_norm": 0.32674506306648254, "learning_rate": 9.473146967906738e-06, "loss": 0.7742254734039307, "step": 4555, "token_acc": 0.7642621870882741 }, { "epoch": 0.2952148966990637, "grad_norm": 0.3233443796634674, "learning_rate": 9.472010496260545e-06, "loss": 0.7917175769805909, "step": 4560, "token_acc": 0.7598145048992679 }, { "epoch": 0.29553859724368986, "grad_norm": 0.3401756286621094, "learning_rate": 9.470872868517353e-06, "loss": 0.7383203506469727, "step": 4565, "token_acc": 0.771956535790464 }, { "epoch": 0.295862297788316, "grad_norm": 0.30922114849090576, "learning_rate": 9.469734084971259e-06, "loss": 0.7524663925170898, "step": 4570, "token_acc": 0.7695682717312267 }, { "epoch": 0.2961859983329422, "grad_norm": 0.44969606399536133, "learning_rate": 9.468594145916656e-06, "loss": 0.7468699455261231, "step": 4575, "token_acc": 0.7708268465090395 }, { "epoch": 0.29650969887756834, "grad_norm": 0.3021135628223419, "learning_rate": 9.467453051648244e-06, "loss": 0.7422873973846436, "step": 4580, "token_acc": 0.7713611808567298 }, { "epoch": 0.29683339942219455, "grad_norm": 0.3363456130027771, "learning_rate": 9.466310802461013e-06, "loss": 0.7658145427703857, "step": 4585, "token_acc": 0.7664455423559454 }, { "epoch": 0.2971570999668207, "grad_norm": 0.3297275900840759, "learning_rate": 9.46516739865026e-06, "loss": 0.7720347881317139, "step": 4590, "token_acc": 0.7649423336727428 }, { "epoch": 0.2974808005114469, "grad_norm": 0.35934609174728394, "learning_rate": 9.464022840511569e-06, "loss": 0.7512575149536133, "step": 4595, "token_acc": 0.7677122115311557 }, { "epoch": 0.29780450105607303, "grad_norm": 0.30351656675338745, "learning_rate": 9.462877128340836e-06, "loss": 0.7449067592620849, "step": 4600, "token_acc": 0.7704175441052036 }, { "epoch": 0.2981282016006992, "grad_norm": 0.34567752480506897, "learning_rate": 9.461730262434244e-06, "loss": 0.7645637512207031, "step": 4605, "token_acc": 0.767585462684181 }, { "epoch": 0.29845190214532535, "grad_norm": 0.3330216407775879, "learning_rate": 9.460582243088283e-06, "loss": 0.7492887496948242, "step": 4610, "token_acc": 0.7697592378645876 }, { "epoch": 0.2987756026899515, "grad_norm": 0.31386798620224, "learning_rate": 9.459433070599734e-06, "loss": 0.7685280799865722, "step": 4615, "token_acc": 0.7673453784303772 }, { "epoch": 0.2990993032345777, "grad_norm": 0.40239688754081726, "learning_rate": 9.458282745265679e-06, "loss": 0.7832492828369141, "step": 4620, "token_acc": 0.7625704001416198 }, { "epoch": 0.29942300377920383, "grad_norm": 0.30097270011901855, "learning_rate": 9.457131267383501e-06, "loss": 0.7345601558685303, "step": 4625, "token_acc": 0.773723697881807 }, { "epoch": 0.29974670432383005, "grad_norm": 0.35107722878456116, "learning_rate": 9.455978637250876e-06, "loss": 0.7392617702484131, "step": 4630, "token_acc": 0.7737725512091287 }, { "epoch": 0.3000704048684562, "grad_norm": 0.37101438641548157, "learning_rate": 9.45482485516578e-06, "loss": 0.7620770454406738, "step": 4635, "token_acc": 0.7686868830137297 }, { "epoch": 0.30039410541308237, "grad_norm": 0.3342686891555786, "learning_rate": 9.45366992142649e-06, "loss": 0.7410152912139892, "step": 4640, "token_acc": 0.7727499810763757 }, { "epoch": 0.30071780595770853, "grad_norm": 0.23025867342948914, "learning_rate": 9.452513836331574e-06, "loss": 0.7815176010131836, "step": 4645, "token_acc": 0.7630779707184202 }, { "epoch": 0.3010415065023347, "grad_norm": 0.3598760664463043, "learning_rate": 9.451356600179903e-06, "loss": 0.7606159687042237, "step": 4650, "token_acc": 0.7661404290534088 }, { "epoch": 0.30136520704696085, "grad_norm": 0.37481361627578735, "learning_rate": 9.450198213270642e-06, "loss": 0.7660581588745117, "step": 4655, "token_acc": 0.766497297647173 }, { "epoch": 0.301688907591587, "grad_norm": 0.3091394007205963, "learning_rate": 9.44903867590326e-06, "loss": 0.772482967376709, "step": 4660, "token_acc": 0.7648178720713759 }, { "epoch": 0.30201260813621317, "grad_norm": 0.17657539248466492, "learning_rate": 9.447877988377512e-06, "loss": 0.7514633178710938, "step": 4665, "token_acc": 0.7691370858116462 }, { "epoch": 0.3023363086808394, "grad_norm": 0.3306058347225189, "learning_rate": 9.446716150993463e-06, "loss": 0.7604734420776367, "step": 4670, "token_acc": 0.7681991615834526 }, { "epoch": 0.30266000922546554, "grad_norm": 0.2934473156929016, "learning_rate": 9.445553164051467e-06, "loss": 0.7577039718627929, "step": 4675, "token_acc": 0.7675852969366543 }, { "epoch": 0.3029837097700917, "grad_norm": 0.2943495810031891, "learning_rate": 9.444389027852175e-06, "loss": 0.7528042793273926, "step": 4680, "token_acc": 0.7691983478040968 }, { "epoch": 0.30330741031471786, "grad_norm": 0.35073813796043396, "learning_rate": 9.443223742696543e-06, "loss": 0.7494126319885254, "step": 4685, "token_acc": 0.7682064694285315 }, { "epoch": 0.303631110859344, "grad_norm": 0.32853463292121887, "learning_rate": 9.442057308885814e-06, "loss": 0.751197338104248, "step": 4690, "token_acc": 0.7696088470202744 }, { "epoch": 0.3039548114039702, "grad_norm": 0.33259785175323486, "learning_rate": 9.440889726721534e-06, "loss": 0.7555655479431153, "step": 4695, "token_acc": 0.7691704750770539 }, { "epoch": 0.30427851194859634, "grad_norm": 0.33362385630607605, "learning_rate": 9.439720996505546e-06, "loss": 0.7528028011322021, "step": 4700, "token_acc": 0.7681072856675805 }, { "epoch": 0.3046022124932225, "grad_norm": 0.3573032319545746, "learning_rate": 9.438551118539987e-06, "loss": 0.7659957408905029, "step": 4705, "token_acc": 0.7680519864921227 }, { "epoch": 0.30492591303784866, "grad_norm": 0.3027808666229248, "learning_rate": 9.43738009312729e-06, "loss": 0.7561946392059327, "step": 4710, "token_acc": 0.7700904665287236 }, { "epoch": 0.3052496135824749, "grad_norm": 0.27493250370025635, "learning_rate": 9.436207920570192e-06, "loss": 0.7715021133422851, "step": 4715, "token_acc": 0.7647034255205106 }, { "epoch": 0.30557331412710104, "grad_norm": 0.3472560942173004, "learning_rate": 9.435034601171717e-06, "loss": 0.7554847717285156, "step": 4720, "token_acc": 0.7701603961859709 }, { "epoch": 0.3058970146717272, "grad_norm": 0.2517310678958893, "learning_rate": 9.433860135235188e-06, "loss": 0.7821833610534668, "step": 4725, "token_acc": 0.7622435205183585 }, { "epoch": 0.30622071521635336, "grad_norm": 0.25984054803848267, "learning_rate": 9.432684523064232e-06, "loss": 0.751894474029541, "step": 4730, "token_acc": 0.7688516705429677 }, { "epoch": 0.3065444157609795, "grad_norm": 0.2491627186536789, "learning_rate": 9.431507764962761e-06, "loss": 0.7422016143798829, "step": 4735, "token_acc": 0.771712223637373 }, { "epoch": 0.3068681163056057, "grad_norm": 0.34700775146484375, "learning_rate": 9.43032986123499e-06, "loss": 0.7515673637390137, "step": 4740, "token_acc": 0.7703499166222211 }, { "epoch": 0.30719181685023184, "grad_norm": 0.343098521232605, "learning_rate": 9.429150812185432e-06, "loss": 0.772683048248291, "step": 4745, "token_acc": 0.7646412836193858 }, { "epoch": 0.307515517394858, "grad_norm": 0.3118135929107666, "learning_rate": 9.427970618118888e-06, "loss": 0.7637439727783203, "step": 4750, "token_acc": 0.7674476458993806 }, { "epoch": 0.30783921793948416, "grad_norm": 0.3610721528530121, "learning_rate": 9.426789279340462e-06, "loss": 0.7439261436462402, "step": 4755, "token_acc": 0.7710362030330233 }, { "epoch": 0.30816291848411037, "grad_norm": 0.2950749099254608, "learning_rate": 9.425606796155554e-06, "loss": 0.7251086235046387, "step": 4760, "token_acc": 0.7750125070451077 }, { "epoch": 0.30848661902873653, "grad_norm": 0.3504031002521515, "learning_rate": 9.424423168869854e-06, "loss": 0.7496042251586914, "step": 4765, "token_acc": 0.7689564577713945 }, { "epoch": 0.3088103195733627, "grad_norm": 0.39485013484954834, "learning_rate": 9.423238397789354e-06, "loss": 0.7375398635864258, "step": 4770, "token_acc": 0.7722290205828461 }, { "epoch": 0.30913402011798885, "grad_norm": 0.34206637740135193, "learning_rate": 9.422052483220336e-06, "loss": 0.7381638050079345, "step": 4775, "token_acc": 0.7727747636610818 }, { "epoch": 0.309457720662615, "grad_norm": 0.43842846155166626, "learning_rate": 9.420865425469385e-06, "loss": 0.7428875923156738, "step": 4780, "token_acc": 0.7709768256021918 }, { "epoch": 0.30978142120724117, "grad_norm": 0.3032204210758209, "learning_rate": 9.419677224843376e-06, "loss": 0.7515933990478516, "step": 4785, "token_acc": 0.7700405395622693 }, { "epoch": 0.31010512175186733, "grad_norm": 0.33515968918800354, "learning_rate": 9.418487881649477e-06, "loss": 0.7239269256591797, "step": 4790, "token_acc": 0.7755774355937223 }, { "epoch": 0.3104288222964935, "grad_norm": 0.328527569770813, "learning_rate": 9.41729739619516e-06, "loss": 0.7712081909179688, "step": 4795, "token_acc": 0.763825521269794 }, { "epoch": 0.3107525228411197, "grad_norm": 0.24531887471675873, "learning_rate": 9.416105768788184e-06, "loss": 0.746278190612793, "step": 4800, "token_acc": 0.7705406381861933 }, { "epoch": 0.31107622338574586, "grad_norm": 0.3488728106021881, "learning_rate": 9.41491299973661e-06, "loss": 0.7333835601806641, "step": 4805, "token_acc": 0.7721046239830763 }, { "epoch": 0.311399923930372, "grad_norm": 0.4388236999511719, "learning_rate": 9.413719089348787e-06, "loss": 0.759942102432251, "step": 4810, "token_acc": 0.7687935748015017 }, { "epoch": 0.3117236244749982, "grad_norm": 0.2910216748714447, "learning_rate": 9.412524037933365e-06, "loss": 0.7588711261749268, "step": 4815, "token_acc": 0.766387620342538 }, { "epoch": 0.31204732501962434, "grad_norm": 0.32266801595687866, "learning_rate": 9.411327845799286e-06, "loss": 0.7569077491760254, "step": 4820, "token_acc": 0.7685149635915223 }, { "epoch": 0.3123710255642505, "grad_norm": 0.3075399398803711, "learning_rate": 9.410130513255788e-06, "loss": 0.7618816375732422, "step": 4825, "token_acc": 0.768140804425738 }, { "epoch": 0.31269472610887666, "grad_norm": 0.3121853470802307, "learning_rate": 9.408932040612404e-06, "loss": 0.7459824562072754, "step": 4830, "token_acc": 0.7699946185582861 }, { "epoch": 0.3130184266535028, "grad_norm": 0.26783663034439087, "learning_rate": 9.407732428178962e-06, "loss": 0.7745081901550293, "step": 4835, "token_acc": 0.7640255687919251 }, { "epoch": 0.313342127198129, "grad_norm": 0.3841189742088318, "learning_rate": 9.40653167626558e-06, "loss": 0.7464173316955567, "step": 4840, "token_acc": 0.7712021497617596 }, { "epoch": 0.3136658277427552, "grad_norm": 0.31630998849868774, "learning_rate": 9.40532978518268e-06, "loss": 0.725514030456543, "step": 4845, "token_acc": 0.7758219467881231 }, { "epoch": 0.31398952828738136, "grad_norm": 0.33362674713134766, "learning_rate": 9.404126755240967e-06, "loss": 0.7594769477844239, "step": 4850, "token_acc": 0.7671637065881534 }, { "epoch": 0.3143132288320075, "grad_norm": 0.39198893308639526, "learning_rate": 9.402922586751452e-06, "loss": 0.7435703277587891, "step": 4855, "token_acc": 0.7711919364102944 }, { "epoch": 0.3146369293766337, "grad_norm": 0.28572648763656616, "learning_rate": 9.401717280025431e-06, "loss": 0.7877474308013916, "step": 4860, "token_acc": 0.7644527947393143 }, { "epoch": 0.31496062992125984, "grad_norm": 0.29850339889526367, "learning_rate": 9.4005108353745e-06, "loss": 0.7281033515930175, "step": 4865, "token_acc": 0.7750275249066838 }, { "epoch": 0.315284330465886, "grad_norm": 0.3671569526195526, "learning_rate": 9.399303253110543e-06, "loss": 0.7420453548431396, "step": 4870, "token_acc": 0.7710720244288344 }, { "epoch": 0.31560803101051216, "grad_norm": 0.2892451286315918, "learning_rate": 9.39809453354575e-06, "loss": 0.7466976165771484, "step": 4875, "token_acc": 0.7723451608800712 }, { "epoch": 0.3159317315551383, "grad_norm": 0.39761728048324585, "learning_rate": 9.396884676992588e-06, "loss": 0.7300907135009765, "step": 4880, "token_acc": 0.7754329510101078 }, { "epoch": 0.31625543209976453, "grad_norm": 0.3648793399333954, "learning_rate": 9.395673683763835e-06, "loss": 0.7776050567626953, "step": 4885, "token_acc": 0.764844536257217 }, { "epoch": 0.3165791326443907, "grad_norm": 0.30808958411216736, "learning_rate": 9.394461554172552e-06, "loss": 0.7443795204162598, "step": 4890, "token_acc": 0.7705904121532199 }, { "epoch": 0.31690283318901685, "grad_norm": 0.3720353841781616, "learning_rate": 9.393248288532097e-06, "loss": 0.768235158920288, "step": 4895, "token_acc": 0.765957852579384 }, { "epoch": 0.317226533733643, "grad_norm": 0.31279146671295166, "learning_rate": 9.39203388715612e-06, "loss": 0.7466818332672119, "step": 4900, "token_acc": 0.7714658147655358 }, { "epoch": 0.3175502342782692, "grad_norm": 0.3383634686470032, "learning_rate": 9.390818350358567e-06, "loss": 0.7900783061981201, "step": 4905, "token_acc": 0.7603613324479859 }, { "epoch": 0.31787393482289533, "grad_norm": 0.3762018382549286, "learning_rate": 9.389601678453679e-06, "loss": 0.7647094249725341, "step": 4910, "token_acc": 0.766376837984249 }, { "epoch": 0.3181976353675215, "grad_norm": 0.3113105893135071, "learning_rate": 9.388383871755984e-06, "loss": 0.7488543510437011, "step": 4915, "token_acc": 0.7702699241958615 }, { "epoch": 0.31852133591214765, "grad_norm": 0.30427274107933044, "learning_rate": 9.38716493058031e-06, "loss": 0.7652230262756348, "step": 4920, "token_acc": 0.7662854681377317 }, { "epoch": 0.3188450364567738, "grad_norm": 0.38716715574264526, "learning_rate": 9.385944855241775e-06, "loss": 0.7460933208465577, "step": 4925, "token_acc": 0.7718659313470454 }, { "epoch": 0.3191687370014, "grad_norm": 0.326910138130188, "learning_rate": 9.384723646055793e-06, "loss": 0.7666478157043457, "step": 4930, "token_acc": 0.7660659031425318 }, { "epoch": 0.3194924375460262, "grad_norm": 0.3740881085395813, "learning_rate": 9.383501303338065e-06, "loss": 0.7546610832214355, "step": 4935, "token_acc": 0.7703386327399661 }, { "epoch": 0.31981613809065235, "grad_norm": 0.25884896516799927, "learning_rate": 9.38227782740459e-06, "loss": 0.7478791236877441, "step": 4940, "token_acc": 0.770614156973282 }, { "epoch": 0.3201398386352785, "grad_norm": 0.31179192662239075, "learning_rate": 9.381053218571664e-06, "loss": 0.7625912666320801, "step": 4945, "token_acc": 0.7658711844188671 }, { "epoch": 0.32046353917990467, "grad_norm": 0.36305397748947144, "learning_rate": 9.379827477155865e-06, "loss": 0.7680374622344971, "step": 4950, "token_acc": 0.7667875887619636 }, { "epoch": 0.3207872397245308, "grad_norm": 0.3829278349876404, "learning_rate": 9.378600603474073e-06, "loss": 0.7749560356140137, "step": 4955, "token_acc": 0.7636137560943687 }, { "epoch": 0.321110940269157, "grad_norm": 0.33376839756965637, "learning_rate": 9.377372597843455e-06, "loss": 0.7464926242828369, "step": 4960, "token_acc": 0.7715114537084956 }, { "epoch": 0.32143464081378315, "grad_norm": 0.2904198169708252, "learning_rate": 9.376143460581474e-06, "loss": 0.7405898094177246, "step": 4965, "token_acc": 0.7721624028497409 }, { "epoch": 0.32175834135840936, "grad_norm": 0.46108853816986084, "learning_rate": 9.374913192005887e-06, "loss": 0.757814598083496, "step": 4970, "token_acc": 0.7687812208663225 }, { "epoch": 0.3220820419030355, "grad_norm": 0.34461870789527893, "learning_rate": 9.37368179243474e-06, "loss": 0.7432853221893311, "step": 4975, "token_acc": 0.7718382556425818 }, { "epoch": 0.3224057424476617, "grad_norm": 0.3321404457092285, "learning_rate": 9.372449262186368e-06, "loss": 0.769035816192627, "step": 4980, "token_acc": 0.766300540512748 }, { "epoch": 0.32272944299228784, "grad_norm": 0.2778693437576294, "learning_rate": 9.371215601579408e-06, "loss": 0.7501622676849365, "step": 4985, "token_acc": 0.7686990735202244 }, { "epoch": 0.323053143536914, "grad_norm": 0.25782662630081177, "learning_rate": 9.369980810932783e-06, "loss": 0.7563323020935059, "step": 4990, "token_acc": 0.7690152363204923 }, { "epoch": 0.32337684408154016, "grad_norm": 0.30300283432006836, "learning_rate": 9.368744890565707e-06, "loss": 0.779560661315918, "step": 4995, "token_acc": 0.7640083885146296 }, { "epoch": 0.3237005446261663, "grad_norm": 0.3383873701095581, "learning_rate": 9.367507840797691e-06, "loss": 0.7595251083374024, "step": 5000, "token_acc": 0.768001113720553 }, { "epoch": 0.3240242451707925, "grad_norm": 0.31765127182006836, "learning_rate": 9.366269661948532e-06, "loss": 0.7506217002868653, "step": 5005, "token_acc": 0.7704516396789589 }, { "epoch": 0.32434794571541864, "grad_norm": 0.3221018612384796, "learning_rate": 9.365030354338325e-06, "loss": 0.7308801651000977, "step": 5010, "token_acc": 0.7750454903276595 }, { "epoch": 0.32467164626004485, "grad_norm": 0.2926950454711914, "learning_rate": 9.363789918287451e-06, "loss": 0.7348830223083496, "step": 5015, "token_acc": 0.7751076640746918 }, { "epoch": 0.324995346804671, "grad_norm": 0.3100093901157379, "learning_rate": 9.362548354116588e-06, "loss": 0.7492584705352783, "step": 5020, "token_acc": 0.7695559536411258 }, { "epoch": 0.3253190473492972, "grad_norm": 0.32540464401245117, "learning_rate": 9.361305662146702e-06, "loss": 0.7137681007385254, "step": 5025, "token_acc": 0.7790049731370708 }, { "epoch": 0.32564274789392333, "grad_norm": 0.43647801876068115, "learning_rate": 9.360061842699051e-06, "loss": 0.7417917251586914, "step": 5030, "token_acc": 0.7730509483927372 }, { "epoch": 0.3259664484385495, "grad_norm": 0.255608469247818, "learning_rate": 9.358816896095186e-06, "loss": 0.7429444313049316, "step": 5035, "token_acc": 0.7727374832328912 }, { "epoch": 0.32629014898317565, "grad_norm": 0.3288056254386902, "learning_rate": 9.357570822656951e-06, "loss": 0.7390666961669922, "step": 5040, "token_acc": 0.7730914374508102 }, { "epoch": 0.3266138495278018, "grad_norm": 0.30138877034187317, "learning_rate": 9.356323622706476e-06, "loss": 0.7159134387969971, "step": 5045, "token_acc": 0.7800661405978848 }, { "epoch": 0.326937550072428, "grad_norm": 0.2963269054889679, "learning_rate": 9.355075296566185e-06, "loss": 0.7383693218231201, "step": 5050, "token_acc": 0.7723070082519257 }, { "epoch": 0.3272612506170542, "grad_norm": 0.325219064950943, "learning_rate": 9.353825844558793e-06, "loss": 0.7382355690002441, "step": 5055, "token_acc": 0.7729311720835512 }, { "epoch": 0.32758495116168035, "grad_norm": 0.35684481263160706, "learning_rate": 9.352575267007308e-06, "loss": 0.7646784782409668, "step": 5060, "token_acc": 0.7661739747585398 }, { "epoch": 0.3279086517063065, "grad_norm": 0.27295973896980286, "learning_rate": 9.351323564235029e-06, "loss": 0.7462265968322754, "step": 5065, "token_acc": 0.7708965366208704 }, { "epoch": 0.32823235225093267, "grad_norm": 0.2438562661409378, "learning_rate": 9.35007073656554e-06, "loss": 0.7552700042724609, "step": 5070, "token_acc": 0.7690675372372985 }, { "epoch": 0.32855605279555883, "grad_norm": 0.3640128970146179, "learning_rate": 9.348816784322722e-06, "loss": 0.7133142471313476, "step": 5075, "token_acc": 0.7781806472387699 }, { "epoch": 0.328879753340185, "grad_norm": 0.2454872578382492, "learning_rate": 9.347561707830743e-06, "loss": 0.7628555297851562, "step": 5080, "token_acc": 0.767666101823516 }, { "epoch": 0.32920345388481115, "grad_norm": 0.23284439742565155, "learning_rate": 9.346305507414068e-06, "loss": 0.77693772315979, "step": 5085, "token_acc": 0.7652813341212001 }, { "epoch": 0.3295271544294373, "grad_norm": 0.406757116317749, "learning_rate": 9.345048183397443e-06, "loss": 0.7578322410583496, "step": 5090, "token_acc": 0.7687906570756851 }, { "epoch": 0.32985085497406347, "grad_norm": 0.2812391221523285, "learning_rate": 9.343789736105912e-06, "loss": 0.7442141056060791, "step": 5095, "token_acc": 0.7722540577840449 }, { "epoch": 0.3301745555186897, "grad_norm": 0.2793084681034088, "learning_rate": 9.342530165864807e-06, "loss": 0.7536133766174317, "step": 5100, "token_acc": 0.7698494240281964 }, { "epoch": 0.33049825606331584, "grad_norm": 0.2743412256240845, "learning_rate": 9.341269472999747e-06, "loss": 0.7397624015808105, "step": 5105, "token_acc": 0.7706134420428784 }, { "epoch": 0.330821956607942, "grad_norm": 0.3325905203819275, "learning_rate": 9.340007657836649e-06, "loss": 0.7487705230712891, "step": 5110, "token_acc": 0.7710571798460921 }, { "epoch": 0.33114565715256816, "grad_norm": 0.26969608664512634, "learning_rate": 9.338744720701711e-06, "loss": 0.7400599479675293, "step": 5115, "token_acc": 0.7718753099071105 }, { "epoch": 0.3314693576971943, "grad_norm": 0.34980955719947815, "learning_rate": 9.337480661921429e-06, "loss": 0.7761911869049072, "step": 5120, "token_acc": 0.7639732085062312 }, { "epoch": 0.3317930582418205, "grad_norm": 0.30100107192993164, "learning_rate": 9.336215481822583e-06, "loss": 0.7495263576507568, "step": 5125, "token_acc": 0.7717765090261047 }, { "epoch": 0.33211675878644664, "grad_norm": 0.3658154308795929, "learning_rate": 9.334949180732245e-06, "loss": 0.7708467006683349, "step": 5130, "token_acc": 0.7656239565107054 }, { "epoch": 0.3324404593310728, "grad_norm": 0.2883690595626831, "learning_rate": 9.33368175897778e-06, "loss": 0.7629479885101318, "step": 5135, "token_acc": 0.766603261209626 }, { "epoch": 0.332764159875699, "grad_norm": 0.32759708166122437, "learning_rate": 9.332413216886838e-06, "loss": 0.7183190822601319, "step": 5140, "token_acc": 0.7760657881154733 }, { "epoch": 0.3330878604203252, "grad_norm": 0.29106655716896057, "learning_rate": 9.33114355478736e-06, "loss": 0.7575352191925049, "step": 5145, "token_acc": 0.768106973146204 }, { "epoch": 0.33341156096495134, "grad_norm": 0.4193604588508606, "learning_rate": 9.329872773007577e-06, "loss": 0.750111198425293, "step": 5150, "token_acc": 0.7718759223978319 }, { "epoch": 0.3337352615095775, "grad_norm": 0.2878609001636505, "learning_rate": 9.328600871876013e-06, "loss": 0.7272463798522949, "step": 5155, "token_acc": 0.7758843871355049 }, { "epoch": 0.33405896205420366, "grad_norm": 0.4029971659183502, "learning_rate": 9.327327851721473e-06, "loss": 0.7707025051116944, "step": 5160, "token_acc": 0.7668083231025907 }, { "epoch": 0.3343826625988298, "grad_norm": 0.2791098952293396, "learning_rate": 9.326053712873057e-06, "loss": 0.7473790168762207, "step": 5165, "token_acc": 0.7720919589909172 }, { "epoch": 0.334706363143456, "grad_norm": 0.3908941149711609, "learning_rate": 9.324778455660157e-06, "loss": 0.735683536529541, "step": 5170, "token_acc": 0.7759018490073716 }, { "epoch": 0.33503006368808214, "grad_norm": 0.331728458404541, "learning_rate": 9.323502080412445e-06, "loss": 0.761263370513916, "step": 5175, "token_acc": 0.766541814265685 }, { "epoch": 0.3353537642327083, "grad_norm": 0.3309774398803711, "learning_rate": 9.322224587459893e-06, "loss": 0.7605411529541015, "step": 5180, "token_acc": 0.767981710172792 }, { "epoch": 0.3356774647773345, "grad_norm": 0.43165573477745056, "learning_rate": 9.320945977132753e-06, "loss": 0.7371896743774414, "step": 5185, "token_acc": 0.772959201776983 }, { "epoch": 0.33600116532196067, "grad_norm": 0.27504977583885193, "learning_rate": 9.31966624976157e-06, "loss": 0.7607467651367188, "step": 5190, "token_acc": 0.7695345320114266 }, { "epoch": 0.33632486586658683, "grad_norm": 0.23424337804317474, "learning_rate": 9.318385405677176e-06, "loss": 0.7450244903564454, "step": 5195, "token_acc": 0.7712969058591178 }, { "epoch": 0.336648566411213, "grad_norm": 0.2787938117980957, "learning_rate": 9.317103445210696e-06, "loss": 0.7364033699035645, "step": 5200, "token_acc": 0.7723612106934344 }, { "epoch": 0.33697226695583915, "grad_norm": 0.2863621711730957, "learning_rate": 9.315820368693538e-06, "loss": 0.7537503719329834, "step": 5205, "token_acc": 0.7709553307138561 }, { "epoch": 0.3372959675004653, "grad_norm": 0.43339911103248596, "learning_rate": 9.3145361764574e-06, "loss": 0.7327463150024414, "step": 5210, "token_acc": 0.7751247937223109 }, { "epoch": 0.33761966804509147, "grad_norm": 0.3426889479160309, "learning_rate": 9.313250868834272e-06, "loss": 0.7370688915252686, "step": 5215, "token_acc": 0.773614410529748 }, { "epoch": 0.33794336858971763, "grad_norm": 0.2580910325050354, "learning_rate": 9.311964446156427e-06, "loss": 0.7512484550476074, "step": 5220, "token_acc": 0.7698000609232644 }, { "epoch": 0.33826706913434385, "grad_norm": 0.3515351116657257, "learning_rate": 9.310676908756431e-06, "loss": 0.7357866287231445, "step": 5225, "token_acc": 0.7740037689019625 }, { "epoch": 0.33859076967897, "grad_norm": 0.3153398334980011, "learning_rate": 9.309388256967136e-06, "loss": 0.7592241287231445, "step": 5230, "token_acc": 0.768062577256882 }, { "epoch": 0.33891447022359616, "grad_norm": 0.37670236825942993, "learning_rate": 9.30809849112168e-06, "loss": 0.7279008865356446, "step": 5235, "token_acc": 0.7744659320151661 }, { "epoch": 0.3392381707682223, "grad_norm": 0.2851264476776123, "learning_rate": 9.306807611553493e-06, "loss": 0.771290636062622, "step": 5240, "token_acc": 0.7642164037512875 }, { "epoch": 0.3395618713128485, "grad_norm": 0.3635830283164978, "learning_rate": 9.30551561859629e-06, "loss": 0.7504813194274902, "step": 5245, "token_acc": 0.7699198870742066 }, { "epoch": 0.33988557185747464, "grad_norm": 0.3450189530849457, "learning_rate": 9.304222512584078e-06, "loss": 0.7376290321350097, "step": 5250, "token_acc": 0.7742454009644579 }, { "epoch": 0.3402092724021008, "grad_norm": 0.3201906979084015, "learning_rate": 9.302928293851144e-06, "loss": 0.7749539375305176, "step": 5255, "token_acc": 0.7648554790472839 }, { "epoch": 0.34053297294672696, "grad_norm": 0.35550546646118164, "learning_rate": 9.301632962732071e-06, "loss": 0.7389328002929687, "step": 5260, "token_acc": 0.7734677531459134 }, { "epoch": 0.3408566734913531, "grad_norm": 0.37410035729408264, "learning_rate": 9.300336519561724e-06, "loss": 0.7589337825775146, "step": 5265, "token_acc": 0.7682764979533675 }, { "epoch": 0.34118037403597934, "grad_norm": 0.33206069469451904, "learning_rate": 9.29903896467526e-06, "loss": 0.736949872970581, "step": 5270, "token_acc": 0.773695973181147 }, { "epoch": 0.3415040745806055, "grad_norm": 0.32450148463249207, "learning_rate": 9.297740298408118e-06, "loss": 0.769381332397461, "step": 5275, "token_acc": 0.7663215776789654 }, { "epoch": 0.34182777512523166, "grad_norm": 0.4077621400356293, "learning_rate": 9.296440521096027e-06, "loss": 0.7681934356689453, "step": 5280, "token_acc": 0.7660048399516005 }, { "epoch": 0.3421514756698578, "grad_norm": 0.36579397320747375, "learning_rate": 9.295139633075005e-06, "loss": 0.7476099967956543, "step": 5285, "token_acc": 0.7690408883719043 }, { "epoch": 0.342475176214484, "grad_norm": 0.36048686504364014, "learning_rate": 9.293837634681356e-06, "loss": 0.7574872493743896, "step": 5290, "token_acc": 0.768160140155079 }, { "epoch": 0.34279887675911014, "grad_norm": 0.28242501616477966, "learning_rate": 9.292534526251668e-06, "loss": 0.7236353874206543, "step": 5295, "token_acc": 0.7771390715680659 }, { "epoch": 0.3431225773037363, "grad_norm": 0.3186289370059967, "learning_rate": 9.291230308122821e-06, "loss": 0.7602641582489014, "step": 5300, "token_acc": 0.7687071318419677 }, { "epoch": 0.34344627784836246, "grad_norm": 0.26772576570510864, "learning_rate": 9.289924980631977e-06, "loss": 0.7439179420471191, "step": 5305, "token_acc": 0.7723142089628993 }, { "epoch": 0.3437699783929887, "grad_norm": 0.23959138989448547, "learning_rate": 9.28861854411659e-06, "loss": 0.7211201667785645, "step": 5310, "token_acc": 0.7783394374078031 }, { "epoch": 0.34409367893761483, "grad_norm": 0.3219955563545227, "learning_rate": 9.287310998914397e-06, "loss": 0.761004114151001, "step": 5315, "token_acc": 0.7682374172849409 }, { "epoch": 0.344417379482241, "grad_norm": 0.31345972418785095, "learning_rate": 9.286002345363418e-06, "loss": 0.7552276611328125, "step": 5320, "token_acc": 0.7704868840675789 }, { "epoch": 0.34474108002686715, "grad_norm": 0.2951487898826599, "learning_rate": 9.284692583801973e-06, "loss": 0.74688720703125, "step": 5325, "token_acc": 0.7701793790583671 }, { "epoch": 0.3450647805714933, "grad_norm": 0.31764066219329834, "learning_rate": 9.28338171456865e-06, "loss": 0.7449078559875488, "step": 5330, "token_acc": 0.7731115882431433 }, { "epoch": 0.3453884811161195, "grad_norm": 0.3315923511981964, "learning_rate": 9.28206973800234e-06, "loss": 0.7844410896301269, "step": 5335, "token_acc": 0.7608890251379522 }, { "epoch": 0.34571218166074563, "grad_norm": 0.2660062611103058, "learning_rate": 9.28075665444221e-06, "loss": 0.7463003158569336, "step": 5340, "token_acc": 0.7716997052970958 }, { "epoch": 0.3460358822053718, "grad_norm": 0.3237226903438568, "learning_rate": 9.279442464227716e-06, "loss": 0.7253260135650634, "step": 5345, "token_acc": 0.7748088363011865 }, { "epoch": 0.34635958274999795, "grad_norm": 0.33319783210754395, "learning_rate": 9.2781271676986e-06, "loss": 0.7429888725280762, "step": 5350, "token_acc": 0.7734880953990508 }, { "epoch": 0.34668328329462417, "grad_norm": 0.3826179802417755, "learning_rate": 9.276810765194894e-06, "loss": 0.777259111404419, "step": 5355, "token_acc": 0.7640725698748725 }, { "epoch": 0.3470069838392503, "grad_norm": 0.3631054759025574, "learning_rate": 9.275493257056907e-06, "loss": 0.7076324939727783, "step": 5360, "token_acc": 0.7807643041599025 }, { "epoch": 0.3473306843838765, "grad_norm": 0.39584580063819885, "learning_rate": 9.274174643625243e-06, "loss": 0.727519178390503, "step": 5365, "token_acc": 0.7755531911834481 }, { "epoch": 0.34765438492850265, "grad_norm": 0.30004796385765076, "learning_rate": 9.272854925240787e-06, "loss": 0.7387872695922851, "step": 5370, "token_acc": 0.7734342217469578 }, { "epoch": 0.3479780854731288, "grad_norm": 0.2600582540035248, "learning_rate": 9.271534102244707e-06, "loss": 0.7562605857849121, "step": 5375, "token_acc": 0.7685744619245246 }, { "epoch": 0.34830178601775497, "grad_norm": 0.3438197076320648, "learning_rate": 9.270212174978466e-06, "loss": 0.7338788032531738, "step": 5380, "token_acc": 0.7748512110726644 }, { "epoch": 0.3486254865623811, "grad_norm": 0.4325878620147705, "learning_rate": 9.2688891437838e-06, "loss": 0.7337579250335693, "step": 5385, "token_acc": 0.7752920389978518 }, { "epoch": 0.3489491871070073, "grad_norm": 0.34454983472824097, "learning_rate": 9.267565009002746e-06, "loss": 0.7684063911437988, "step": 5390, "token_acc": 0.767369637440416 }, { "epoch": 0.3492728876516335, "grad_norm": 0.44417452812194824, "learning_rate": 9.266239770977608e-06, "loss": 0.7534984588623047, "step": 5395, "token_acc": 0.7688016272179674 }, { "epoch": 0.34959658819625966, "grad_norm": 0.3629584014415741, "learning_rate": 9.264913430050988e-06, "loss": 0.7367576599121094, "step": 5400, "token_acc": 0.7741897230734663 }, { "epoch": 0.3499202887408858, "grad_norm": 0.29686862230300903, "learning_rate": 9.26358598656577e-06, "loss": 0.7640504360198974, "step": 5405, "token_acc": 0.7664757649519948 }, { "epoch": 0.350243989285512, "grad_norm": 0.3085083067417145, "learning_rate": 9.262257440865123e-06, "loss": 0.745479679107666, "step": 5410, "token_acc": 0.7713837721208547 }, { "epoch": 0.35056768983013814, "grad_norm": 0.3177521526813507, "learning_rate": 9.260927793292498e-06, "loss": 0.7460844993591309, "step": 5415, "token_acc": 0.7710647448173907 }, { "epoch": 0.3508913903747643, "grad_norm": 0.23754936456680298, "learning_rate": 9.259597044191635e-06, "loss": 0.7272076606750488, "step": 5420, "token_acc": 0.7760588666981182 }, { "epoch": 0.35121509091939046, "grad_norm": 0.313921183347702, "learning_rate": 9.25826519390656e-06, "loss": 0.7403250217437745, "step": 5425, "token_acc": 0.7736599281760633 }, { "epoch": 0.3515387914640166, "grad_norm": 0.36728596687316895, "learning_rate": 9.256932242781576e-06, "loss": 0.7281265735626221, "step": 5430, "token_acc": 0.7764652430713312 }, { "epoch": 0.3518624920086428, "grad_norm": 0.2783869206905365, "learning_rate": 9.255598191161277e-06, "loss": 0.7374805450439453, "step": 5435, "token_acc": 0.7740739508103971 }, { "epoch": 0.352186192553269, "grad_norm": 0.39277756214141846, "learning_rate": 9.254263039390541e-06, "loss": 0.7444178104400635, "step": 5440, "token_acc": 0.7728411580286753 }, { "epoch": 0.35250989309789516, "grad_norm": 0.30549636483192444, "learning_rate": 9.252926787814528e-06, "loss": 0.7258675575256348, "step": 5445, "token_acc": 0.775560219525231 }, { "epoch": 0.3528335936425213, "grad_norm": 0.42716383934020996, "learning_rate": 9.251589436778685e-06, "loss": 0.7474983692169189, "step": 5450, "token_acc": 0.771207468054959 }, { "epoch": 0.3531572941871475, "grad_norm": 0.28004536032676697, "learning_rate": 9.250250986628739e-06, "loss": 0.7452303886413574, "step": 5455, "token_acc": 0.7727791647325966 }, { "epoch": 0.35348099473177363, "grad_norm": 0.24441690742969513, "learning_rate": 9.248911437710708e-06, "loss": 0.7391646385192872, "step": 5460, "token_acc": 0.7726050631321063 }, { "epoch": 0.3538046952763998, "grad_norm": 0.28953251242637634, "learning_rate": 9.247570790370887e-06, "loss": 0.7587745189666748, "step": 5465, "token_acc": 0.7676676480209356 }, { "epoch": 0.35412839582102595, "grad_norm": 0.3305732011795044, "learning_rate": 9.24622904495586e-06, "loss": 0.741170597076416, "step": 5470, "token_acc": 0.7715399980975934 }, { "epoch": 0.3544520963656521, "grad_norm": 0.315642774105072, "learning_rate": 9.244886201812491e-06, "loss": 0.7347969055175781, "step": 5475, "token_acc": 0.7744687874959528 }, { "epoch": 0.3547757969102783, "grad_norm": 0.2221536785364151, "learning_rate": 9.243542261287931e-06, "loss": 0.7142243385314941, "step": 5480, "token_acc": 0.7782163235711358 }, { "epoch": 0.3550994974549045, "grad_norm": 0.29153507947921753, "learning_rate": 9.242197223729614e-06, "loss": 0.7386149406433106, "step": 5485, "token_acc": 0.7740238259890067 }, { "epoch": 0.35542319799953065, "grad_norm": 0.4217398464679718, "learning_rate": 9.240851089485254e-06, "loss": 0.746129322052002, "step": 5490, "token_acc": 0.7720806851968032 }, { "epoch": 0.3557468985441568, "grad_norm": 0.32437366247177124, "learning_rate": 9.239503858902854e-06, "loss": 0.7283612728118897, "step": 5495, "token_acc": 0.7763054858460608 }, { "epoch": 0.35607059908878297, "grad_norm": 0.2297554910182953, "learning_rate": 9.238155532330698e-06, "loss": 0.7133243083953857, "step": 5500, "token_acc": 0.7773651327878682 }, { "epoch": 0.35639429963340913, "grad_norm": 0.32002028822898865, "learning_rate": 9.236806110117352e-06, "loss": 0.7706611156463623, "step": 5505, "token_acc": 0.7640060909840746 }, { "epoch": 0.3567180001780353, "grad_norm": 0.35641422867774963, "learning_rate": 9.235455592611667e-06, "loss": 0.7850197792053223, "step": 5510, "token_acc": 0.7622056620443284 }, { "epoch": 0.35704170072266145, "grad_norm": 0.3353142738342285, "learning_rate": 9.234103980162776e-06, "loss": 0.731107521057129, "step": 5515, "token_acc": 0.7756803234572115 }, { "epoch": 0.3573654012672876, "grad_norm": 0.4031864106655121, "learning_rate": 9.232751273120097e-06, "loss": 0.7492086887359619, "step": 5520, "token_acc": 0.7693077323082391 }, { "epoch": 0.3576891018119138, "grad_norm": 0.35844939947128296, "learning_rate": 9.23139747183333e-06, "loss": 0.7174859046936035, "step": 5525, "token_acc": 0.7781015667865634 }, { "epoch": 0.35801280235654, "grad_norm": 0.29411450028419495, "learning_rate": 9.230042576652454e-06, "loss": 0.7486249923706054, "step": 5530, "token_acc": 0.7721119832900987 }, { "epoch": 0.35833650290116614, "grad_norm": 0.32751306891441345, "learning_rate": 9.228686587927739e-06, "loss": 0.7433484077453614, "step": 5535, "token_acc": 0.7725594669250003 }, { "epoch": 0.3586602034457923, "grad_norm": 0.31395891308784485, "learning_rate": 9.22732950600973e-06, "loss": 0.742891788482666, "step": 5540, "token_acc": 0.7694986202557665 }, { "epoch": 0.35898390399041846, "grad_norm": 0.3707798421382904, "learning_rate": 9.225971331249258e-06, "loss": 0.7446293830871582, "step": 5545, "token_acc": 0.7730016640147697 }, { "epoch": 0.3593076045350446, "grad_norm": 0.27937543392181396, "learning_rate": 9.224612063997438e-06, "loss": 0.7458698749542236, "step": 5550, "token_acc": 0.7712329146528922 }, { "epoch": 0.3596313050796708, "grad_norm": 0.32804685831069946, "learning_rate": 9.223251704605663e-06, "loss": 0.7500398635864258, "step": 5555, "token_acc": 0.7706921258366639 }, { "epoch": 0.35995500562429694, "grad_norm": 0.331767737865448, "learning_rate": 9.221890253425614e-06, "loss": 0.7643870353698731, "step": 5560, "token_acc": 0.7654168114934539 }, { "epoch": 0.3602787061689231, "grad_norm": 0.35047024488449097, "learning_rate": 9.220527710809248e-06, "loss": 0.7430984497070312, "step": 5565, "token_acc": 0.771083019717585 }, { "epoch": 0.3606024067135493, "grad_norm": 0.30299562215805054, "learning_rate": 9.219164077108809e-06, "loss": 0.7660828590393066, "step": 5570, "token_acc": 0.7665224879376307 }, { "epoch": 0.3609261072581755, "grad_norm": 0.2968966066837311, "learning_rate": 9.21779935267682e-06, "loss": 0.7256419658660889, "step": 5575, "token_acc": 0.7767037024826086 }, { "epoch": 0.36124980780280164, "grad_norm": 0.2905917167663574, "learning_rate": 9.21643353786609e-06, "loss": 0.7618994235992431, "step": 5580, "token_acc": 0.7665694967407587 }, { "epoch": 0.3615735083474278, "grad_norm": 0.302976131439209, "learning_rate": 9.215066633029705e-06, "loss": 0.7353042602539063, "step": 5585, "token_acc": 0.7743223234979915 }, { "epoch": 0.36189720889205396, "grad_norm": 0.34459322690963745, "learning_rate": 9.213698638521036e-06, "loss": 0.7280282974243164, "step": 5590, "token_acc": 0.7756938322643402 }, { "epoch": 0.3622209094366801, "grad_norm": 0.3205491006374359, "learning_rate": 9.212329554693735e-06, "loss": 0.7594081878662109, "step": 5595, "token_acc": 0.768981105830532 }, { "epoch": 0.3625446099813063, "grad_norm": 0.354069322347641, "learning_rate": 9.210959381901735e-06, "loss": 0.7388426303863526, "step": 5600, "token_acc": 0.7694084518008578 }, { "epoch": 0.36286831052593244, "grad_norm": 0.30475306510925293, "learning_rate": 9.20958812049925e-06, "loss": 0.7501628398895264, "step": 5605, "token_acc": 0.7699028830639023 }, { "epoch": 0.36319201107055865, "grad_norm": 0.3142952024936676, "learning_rate": 9.208215770840779e-06, "loss": 0.756736946105957, "step": 5610, "token_acc": 0.7693656215434062 }, { "epoch": 0.3635157116151848, "grad_norm": 0.30909496545791626, "learning_rate": 9.206842333281094e-06, "loss": 0.7404678344726563, "step": 5615, "token_acc": 0.7733055705317692 }, { "epoch": 0.36383941215981097, "grad_norm": 0.2991071045398712, "learning_rate": 9.205467808175262e-06, "loss": 0.7479245662689209, "step": 5620, "token_acc": 0.7712190917962561 }, { "epoch": 0.36416311270443713, "grad_norm": 0.2614854872226715, "learning_rate": 9.204092195878616e-06, "loss": 0.7582926273345947, "step": 5625, "token_acc": 0.7687362319226392 }, { "epoch": 0.3644868132490633, "grad_norm": 0.3580622673034668, "learning_rate": 9.202715496746778e-06, "loss": 0.7337677478790283, "step": 5630, "token_acc": 0.7740202810117506 }, { "epoch": 0.36481051379368945, "grad_norm": 0.43562930822372437, "learning_rate": 9.201337711135656e-06, "loss": 0.7334352970123291, "step": 5635, "token_acc": 0.7736264165435361 }, { "epoch": 0.3651342143383156, "grad_norm": 0.3042621314525604, "learning_rate": 9.199958839401426e-06, "loss": 0.7269857406616211, "step": 5640, "token_acc": 0.7744297929530005 }, { "epoch": 0.36545791488294177, "grad_norm": 0.3351444602012634, "learning_rate": 9.198578881900556e-06, "loss": 0.7401920795440674, "step": 5645, "token_acc": 0.7728061947432494 }, { "epoch": 0.36578161542756793, "grad_norm": 0.26612451672554016, "learning_rate": 9.197197838989789e-06, "loss": 0.7312610626220704, "step": 5650, "token_acc": 0.774854197748542 }, { "epoch": 0.36610531597219415, "grad_norm": 0.2938707172870636, "learning_rate": 9.195815711026148e-06, "loss": 0.7650527954101562, "step": 5655, "token_acc": 0.767043158557186 }, { "epoch": 0.3664290165168203, "grad_norm": 0.5181487798690796, "learning_rate": 9.194432498366943e-06, "loss": 0.7249373912811279, "step": 5660, "token_acc": 0.7769091920795842 }, { "epoch": 0.36675271706144646, "grad_norm": 0.30980396270751953, "learning_rate": 9.193048201369755e-06, "loss": 0.7259238243103028, "step": 5665, "token_acc": 0.7743467775688765 }, { "epoch": 0.3670764176060726, "grad_norm": 0.24724793434143066, "learning_rate": 9.191662820392453e-06, "loss": 0.7240602493286132, "step": 5670, "token_acc": 0.77646335355687 }, { "epoch": 0.3674001181506988, "grad_norm": 0.28200599551200867, "learning_rate": 9.190276355793184e-06, "loss": 0.7338060855865478, "step": 5675, "token_acc": 0.7724165174674575 }, { "epoch": 0.36772381869532494, "grad_norm": 0.2812204360961914, "learning_rate": 9.188888807930372e-06, "loss": 0.7563454627990722, "step": 5680, "token_acc": 0.7701499877059258 }, { "epoch": 0.3680475192399511, "grad_norm": 0.37308478355407715, "learning_rate": 9.187500177162728e-06, "loss": 0.7509055137634277, "step": 5685, "token_acc": 0.7718738511632792 }, { "epoch": 0.36837121978457726, "grad_norm": 0.28826257586479187, "learning_rate": 9.186110463849234e-06, "loss": 0.7367636680603027, "step": 5690, "token_acc": 0.7743711815633604 }, { "epoch": 0.3686949203292035, "grad_norm": 0.365389883518219, "learning_rate": 9.184719668349157e-06, "loss": 0.7757558822631836, "step": 5695, "token_acc": 0.7651544207029701 }, { "epoch": 0.36901862087382964, "grad_norm": 0.41698214411735535, "learning_rate": 9.183327791022048e-06, "loss": 0.7325804233551025, "step": 5700, "token_acc": 0.7743867912387717 }, { "epoch": 0.3693423214184558, "grad_norm": 0.315731018781662, "learning_rate": 9.181934832227728e-06, "loss": 0.7471363544464111, "step": 5705, "token_acc": 0.7694579873666716 }, { "epoch": 0.36966602196308196, "grad_norm": 0.3393206298351288, "learning_rate": 9.180540792326302e-06, "loss": 0.7542563915252686, "step": 5710, "token_acc": 0.7702930796378702 }, { "epoch": 0.3699897225077081, "grad_norm": 0.4009005129337311, "learning_rate": 9.17914567167816e-06, "loss": 0.7330552101135254, "step": 5715, "token_acc": 0.774033853942907 }, { "epoch": 0.3703134230523343, "grad_norm": 0.3737444281578064, "learning_rate": 9.177749470643961e-06, "loss": 0.7249352931976318, "step": 5720, "token_acc": 0.7764003208822915 }, { "epoch": 0.37063712359696044, "grad_norm": 0.2868008613586426, "learning_rate": 9.176352189584654e-06, "loss": 0.7494350433349609, "step": 5725, "token_acc": 0.7699820890716504 }, { "epoch": 0.3709608241415866, "grad_norm": 0.29475489258766174, "learning_rate": 9.174953828861455e-06, "loss": 0.7536908149719238, "step": 5730, "token_acc": 0.7691650543983517 }, { "epoch": 0.37128452468621276, "grad_norm": 0.36773866415023804, "learning_rate": 9.173554388835872e-06, "loss": 0.7727438926696777, "step": 5735, "token_acc": 0.7669247492276593 }, { "epoch": 0.371608225230839, "grad_norm": 0.3169749677181244, "learning_rate": 9.172153869869684e-06, "loss": 0.7488291263580322, "step": 5740, "token_acc": 0.7704844343984383 }, { "epoch": 0.37193192577546513, "grad_norm": 0.25884509086608887, "learning_rate": 9.170752272324949e-06, "loss": 0.732088279724121, "step": 5745, "token_acc": 0.7756262793969582 }, { "epoch": 0.3722556263200913, "grad_norm": 0.4169518053531647, "learning_rate": 9.169349596564008e-06, "loss": 0.7783088207244873, "step": 5750, "token_acc": 0.7636758674774694 }, { "epoch": 0.37257932686471745, "grad_norm": 0.30680060386657715, "learning_rate": 9.16794584294948e-06, "loss": 0.7244553565979004, "step": 5755, "token_acc": 0.7756827338726671 }, { "epoch": 0.3729030274093436, "grad_norm": 0.3081168830394745, "learning_rate": 9.166541011844256e-06, "loss": 0.7474825382232666, "step": 5760, "token_acc": 0.7712150148172539 }, { "epoch": 0.3732267279539698, "grad_norm": 0.4059318006038666, "learning_rate": 9.165135103611517e-06, "loss": 0.7505320549011231, "step": 5765, "token_acc": 0.7692433854450269 }, { "epoch": 0.37355042849859593, "grad_norm": 0.3022467792034149, "learning_rate": 9.163728118614711e-06, "loss": 0.7426325798034668, "step": 5770, "token_acc": 0.7720636454630173 }, { "epoch": 0.3738741290432221, "grad_norm": 0.38016921281814575, "learning_rate": 9.162320057217572e-06, "loss": 0.7235421180725098, "step": 5775, "token_acc": 0.7779147800776197 }, { "epoch": 0.3741978295878483, "grad_norm": 0.2814148962497711, "learning_rate": 9.160910919784109e-06, "loss": 0.7455392837524414, "step": 5780, "token_acc": 0.7708985930448633 }, { "epoch": 0.37452153013247447, "grad_norm": 0.3239682614803314, "learning_rate": 9.15950070667861e-06, "loss": 0.7534763813018799, "step": 5785, "token_acc": 0.7694797285540282 }, { "epoch": 0.3748452306771006, "grad_norm": 0.3113633096218109, "learning_rate": 9.158089418265641e-06, "loss": 0.7325342178344727, "step": 5790, "token_acc": 0.773673909770663 }, { "epoch": 0.3751689312217268, "grad_norm": 0.3479679524898529, "learning_rate": 9.156677054910046e-06, "loss": 0.7334784507751465, "step": 5795, "token_acc": 0.7740186232167724 }, { "epoch": 0.37549263176635295, "grad_norm": 0.30269289016723633, "learning_rate": 9.155263616976948e-06, "loss": 0.7351984977722168, "step": 5800, "token_acc": 0.7751249542850177 }, { "epoch": 0.3758163323109791, "grad_norm": 0.32949545979499817, "learning_rate": 9.153849104831746e-06, "loss": 0.7183050155639649, "step": 5805, "token_acc": 0.7781950859857961 }, { "epoch": 0.37614003285560527, "grad_norm": 0.34065908193588257, "learning_rate": 9.152433518840117e-06, "loss": 0.711034107208252, "step": 5810, "token_acc": 0.7802319603116842 }, { "epoch": 0.3764637334002314, "grad_norm": 0.4108772575855255, "learning_rate": 9.151016859368017e-06, "loss": 0.7600946426391602, "step": 5815, "token_acc": 0.7689859675678359 }, { "epoch": 0.3767874339448576, "grad_norm": 0.3734937310218811, "learning_rate": 9.149599126781676e-06, "loss": 0.7231532573699951, "step": 5820, "token_acc": 0.7761075118733672 }, { "epoch": 0.3771111344894838, "grad_norm": 0.2818101942539215, "learning_rate": 9.148180321447608e-06, "loss": 0.7514182567596436, "step": 5825, "token_acc": 0.7708642916111005 }, { "epoch": 0.37743483503410996, "grad_norm": 0.40397340059280396, "learning_rate": 9.146760443732598e-06, "loss": 0.7524514675140381, "step": 5830, "token_acc": 0.7697616528719895 }, { "epoch": 0.3777585355787361, "grad_norm": 0.2657736837863922, "learning_rate": 9.145339494003708e-06, "loss": 0.7568769931793213, "step": 5835, "token_acc": 0.7693555001735071 }, { "epoch": 0.3780822361233623, "grad_norm": 0.3000619411468506, "learning_rate": 9.143917472628285e-06, "loss": 0.7599202156066894, "step": 5840, "token_acc": 0.7684468793062884 }, { "epoch": 0.37840593666798844, "grad_norm": 0.8530117869377136, "learning_rate": 9.142494379973945e-06, "loss": 0.7461812019348144, "step": 5845, "token_acc": 0.7700403719846546 }, { "epoch": 0.3787296372126146, "grad_norm": 0.3585285246372223, "learning_rate": 9.141070216408582e-06, "loss": 0.7331134796142578, "step": 5850, "token_acc": 0.7727587183828907 }, { "epoch": 0.37905333775724076, "grad_norm": 0.36097630858421326, "learning_rate": 9.13964498230037e-06, "loss": 0.723093843460083, "step": 5855, "token_acc": 0.777194089324257 }, { "epoch": 0.3793770383018669, "grad_norm": 0.31375956535339355, "learning_rate": 9.13821867801776e-06, "loss": 0.7388586521148681, "step": 5860, "token_acc": 0.7737287317873339 }, { "epoch": 0.37970073884649314, "grad_norm": 0.354323148727417, "learning_rate": 9.136791303929476e-06, "loss": 0.7553172588348389, "step": 5865, "token_acc": 0.7695386715363474 }, { "epoch": 0.3800244393911193, "grad_norm": 0.26365742087364197, "learning_rate": 9.13536286040452e-06, "loss": 0.7396434783935547, "step": 5870, "token_acc": 0.773154997534221 }, { "epoch": 0.38034813993574546, "grad_norm": 0.2020253837108612, "learning_rate": 9.133933347812171e-06, "loss": 0.7598512172698975, "step": 5875, "token_acc": 0.7680682455065626 }, { "epoch": 0.3806718404803716, "grad_norm": 0.30831047892570496, "learning_rate": 9.132502766521986e-06, "loss": 0.746427345275879, "step": 5880, "token_acc": 0.7722125487841489 }, { "epoch": 0.3809955410249978, "grad_norm": 0.2647319734096527, "learning_rate": 9.131071116903796e-06, "loss": 0.7389640808105469, "step": 5885, "token_acc": 0.7733029132622631 }, { "epoch": 0.38131924156962393, "grad_norm": 0.3400501608848572, "learning_rate": 9.129638399327707e-06, "loss": 0.7513349056243896, "step": 5890, "token_acc": 0.7693600910751635 }, { "epoch": 0.3816429421142501, "grad_norm": 0.24764610826969147, "learning_rate": 9.128204614164104e-06, "loss": 0.745884895324707, "step": 5895, "token_acc": 0.7718326891613118 }, { "epoch": 0.38196664265887625, "grad_norm": 0.42683807015419006, "learning_rate": 9.126769761783647e-06, "loss": 0.7532097339630127, "step": 5900, "token_acc": 0.770696477033505 }, { "epoch": 0.3822903432035024, "grad_norm": 0.3061276078224182, "learning_rate": 9.125333842557273e-06, "loss": 0.7039780139923095, "step": 5905, "token_acc": 0.7816872257637222 }, { "epoch": 0.38261404374812863, "grad_norm": 0.3279179334640503, "learning_rate": 9.123896856856192e-06, "loss": 0.7285891056060791, "step": 5910, "token_acc": 0.7754933868845648 }, { "epoch": 0.3829377442927548, "grad_norm": 0.32512545585632324, "learning_rate": 9.12245880505189e-06, "loss": 0.7656756401062011, "step": 5915, "token_acc": 0.7661304395597294 }, { "epoch": 0.38326144483738095, "grad_norm": 0.4420869052410126, "learning_rate": 9.121019687516133e-06, "loss": 0.7326736927032471, "step": 5920, "token_acc": 0.7744103482958217 }, { "epoch": 0.3835851453820071, "grad_norm": 0.34341689944267273, "learning_rate": 9.119579504620958e-06, "loss": 0.7136418342590332, "step": 5925, "token_acc": 0.7780519246496541 }, { "epoch": 0.38390884592663327, "grad_norm": 0.3792257010936737, "learning_rate": 9.118138256738679e-06, "loss": 0.7373710632324219, "step": 5930, "token_acc": 0.7735132740346932 }, { "epoch": 0.38423254647125943, "grad_norm": 0.22922497987747192, "learning_rate": 9.116695944241882e-06, "loss": 0.7506214141845703, "step": 5935, "token_acc": 0.7691743797649099 }, { "epoch": 0.3845562470158856, "grad_norm": 0.4400733411312103, "learning_rate": 9.115252567503436e-06, "loss": 0.732882308959961, "step": 5940, "token_acc": 0.7737858947259886 }, { "epoch": 0.38487994756051175, "grad_norm": 0.37058907747268677, "learning_rate": 9.113808126896477e-06, "loss": 0.741168212890625, "step": 5945, "token_acc": 0.7746132836430467 }, { "epoch": 0.38520364810513796, "grad_norm": 0.2634643614292145, "learning_rate": 9.112362622794422e-06, "loss": 0.7604582786560059, "step": 5950, "token_acc": 0.7674712506782061 }, { "epoch": 0.3855273486497641, "grad_norm": 0.371093213558197, "learning_rate": 9.11091605557096e-06, "loss": 0.7559086322784424, "step": 5955, "token_acc": 0.7678239881173412 }, { "epoch": 0.3858510491943903, "grad_norm": 0.236567884683609, "learning_rate": 9.109468425600053e-06, "loss": 0.7214138984680176, "step": 5960, "token_acc": 0.7765587122087839 }, { "epoch": 0.38617474973901644, "grad_norm": 0.3323653042316437, "learning_rate": 9.108019733255941e-06, "loss": 0.739432954788208, "step": 5965, "token_acc": 0.7744625993104483 }, { "epoch": 0.3864984502836426, "grad_norm": 0.3158623278141022, "learning_rate": 9.10656997891314e-06, "loss": 0.74917631149292, "step": 5970, "token_acc": 0.771208403407681 }, { "epoch": 0.38682215082826876, "grad_norm": 0.36304670572280884, "learning_rate": 9.105119162946436e-06, "loss": 0.7343618392944335, "step": 5975, "token_acc": 0.7738362066181362 }, { "epoch": 0.3871458513728949, "grad_norm": 0.3256804645061493, "learning_rate": 9.10366728573089e-06, "loss": 0.726225757598877, "step": 5980, "token_acc": 0.7762237302401431 }, { "epoch": 0.3874695519175211, "grad_norm": 0.28781044483184814, "learning_rate": 9.102214347641843e-06, "loss": 0.7409159183502197, "step": 5985, "token_acc": 0.7728976046397691 }, { "epoch": 0.38779325246214724, "grad_norm": 0.3228725492954254, "learning_rate": 9.100760349054905e-06, "loss": 0.762338924407959, "step": 5990, "token_acc": 0.7658060486871479 }, { "epoch": 0.38811695300677346, "grad_norm": 0.3589574694633484, "learning_rate": 9.099305290345959e-06, "loss": 0.7532686233520508, "step": 5995, "token_acc": 0.767881127087133 }, { "epoch": 0.3884406535513996, "grad_norm": 0.336974561214447, "learning_rate": 9.097849171891164e-06, "loss": 0.7556431770324707, "step": 6000, "token_acc": 0.768856480757861 }, { "epoch": 0.3887643540960258, "grad_norm": 0.3186173737049103, "learning_rate": 9.096391994066957e-06, "loss": 0.7500984191894531, "step": 6005, "token_acc": 0.7693235060415925 }, { "epoch": 0.38908805464065194, "grad_norm": 0.3592252731323242, "learning_rate": 9.094933757250047e-06, "loss": 0.7229254722595215, "step": 6010, "token_acc": 0.7778827563336482 }, { "epoch": 0.3894117551852781, "grad_norm": 0.3010545074939728, "learning_rate": 9.093474461817407e-06, "loss": 0.7612685203552246, "step": 6015, "token_acc": 0.7657959572005708 }, { "epoch": 0.38973545572990426, "grad_norm": 0.28816723823547363, "learning_rate": 9.092014108146299e-06, "loss": 0.7515421867370605, "step": 6020, "token_acc": 0.769781116848295 }, { "epoch": 0.3900591562745304, "grad_norm": 0.42964598536491394, "learning_rate": 9.090552696614247e-06, "loss": 0.7497601509094238, "step": 6025, "token_acc": 0.7703885106569545 }, { "epoch": 0.3903828568191566, "grad_norm": 0.3180561363697052, "learning_rate": 9.089090227599056e-06, "loss": 0.7138723850250244, "step": 6030, "token_acc": 0.7792578871657437 }, { "epoch": 0.3907065573637828, "grad_norm": 0.32726240158081055, "learning_rate": 9.087626701478799e-06, "loss": 0.7556753635406495, "step": 6035, "token_acc": 0.7680699136736652 }, { "epoch": 0.39103025790840895, "grad_norm": 0.3388437032699585, "learning_rate": 9.086162118631825e-06, "loss": 0.750030517578125, "step": 6040, "token_acc": 0.771215122998184 }, { "epoch": 0.3913539584530351, "grad_norm": 0.3830566108226776, "learning_rate": 9.084696479436756e-06, "loss": 0.7279129028320312, "step": 6045, "token_acc": 0.7752225384246646 }, { "epoch": 0.39167765899766127, "grad_norm": 0.395354300737381, "learning_rate": 9.083229784272487e-06, "loss": 0.7371056079864502, "step": 6050, "token_acc": 0.7759626455161827 }, { "epoch": 0.39200135954228743, "grad_norm": 0.256361186504364, "learning_rate": 9.081762033518184e-06, "loss": 0.721054220199585, "step": 6055, "token_acc": 0.7764085426348494 }, { "epoch": 0.3923250600869136, "grad_norm": 0.4437025189399719, "learning_rate": 9.08029322755329e-06, "loss": 0.7140403270721436, "step": 6060, "token_acc": 0.780306389173808 }, { "epoch": 0.39264876063153975, "grad_norm": 0.25292161107063293, "learning_rate": 9.078823366757516e-06, "loss": 0.7109986782073975, "step": 6065, "token_acc": 0.7778054411298719 }, { "epoch": 0.3929724611761659, "grad_norm": 0.41062450408935547, "learning_rate": 9.077352451510847e-06, "loss": 0.7330968856811524, "step": 6070, "token_acc": 0.7751681036820129 }, { "epoch": 0.39329616172079207, "grad_norm": 0.32462379336357117, "learning_rate": 9.075880482193547e-06, "loss": 0.724942970275879, "step": 6075, "token_acc": 0.7747499233748503 }, { "epoch": 0.3936198622654183, "grad_norm": 0.4089123606681824, "learning_rate": 9.074407459186144e-06, "loss": 0.7403882026672364, "step": 6080, "token_acc": 0.7732398457719326 }, { "epoch": 0.39394356281004445, "grad_norm": 0.24906319379806519, "learning_rate": 9.07293338286944e-06, "loss": 0.713163948059082, "step": 6085, "token_acc": 0.7793216924110141 }, { "epoch": 0.3942672633546706, "grad_norm": 0.30153849720954895, "learning_rate": 9.071458253624512e-06, "loss": 0.7465082168579101, "step": 6090, "token_acc": 0.7713261042190083 }, { "epoch": 0.39459096389929676, "grad_norm": 0.3162601590156555, "learning_rate": 9.06998207183271e-06, "loss": 0.7634443283081055, "step": 6095, "token_acc": 0.7672495382064788 }, { "epoch": 0.3949146644439229, "grad_norm": 0.37990424036979675, "learning_rate": 9.068504837875651e-06, "loss": 0.7360931396484375, "step": 6100, "token_acc": 0.7753959244697934 }, { "epoch": 0.3952383649885491, "grad_norm": 0.38741743564605713, "learning_rate": 9.06702655213523e-06, "loss": 0.7290494918823243, "step": 6105, "token_acc": 0.775344310152824 }, { "epoch": 0.39556206553317524, "grad_norm": 0.23664447665214539, "learning_rate": 9.065547214993608e-06, "loss": 0.7467986106872558, "step": 6110, "token_acc": 0.771960365891705 }, { "epoch": 0.3958857660778014, "grad_norm": 0.3143741488456726, "learning_rate": 9.064066826833225e-06, "loss": 0.7535094261169434, "step": 6115, "token_acc": 0.7683847384346553 }, { "epoch": 0.3962094666224276, "grad_norm": 0.37818220257759094, "learning_rate": 9.062585388036783e-06, "loss": 0.7204220294952393, "step": 6120, "token_acc": 0.7785268036418457 }, { "epoch": 0.3965331671670538, "grad_norm": 0.347891628742218, "learning_rate": 9.061102898987269e-06, "loss": 0.7455645084381104, "step": 6125, "token_acc": 0.7718753086013365 }, { "epoch": 0.39685686771167994, "grad_norm": 0.2112126499414444, "learning_rate": 9.059619360067925e-06, "loss": 0.7269421577453613, "step": 6130, "token_acc": 0.7757528549909233 }, { "epoch": 0.3971805682563061, "grad_norm": 0.331256240606308, "learning_rate": 9.058134771662279e-06, "loss": 0.7554508209228515, "step": 6135, "token_acc": 0.7688968875714588 }, { "epoch": 0.39750426880093226, "grad_norm": 0.21733441948890686, "learning_rate": 9.056649134154121e-06, "loss": 0.7322019577026367, "step": 6140, "token_acc": 0.7750391757548074 }, { "epoch": 0.3978279693455584, "grad_norm": 0.30233606696128845, "learning_rate": 9.05516244792752e-06, "loss": 0.7202380180358887, "step": 6145, "token_acc": 0.7781348428026552 }, { "epoch": 0.3981516698901846, "grad_norm": 0.37254098057746887, "learning_rate": 9.053674713366806e-06, "loss": 0.7398562431335449, "step": 6150, "token_acc": 0.7721159275968644 }, { "epoch": 0.39847537043481074, "grad_norm": 0.3938317894935608, "learning_rate": 9.05218593085659e-06, "loss": 0.753170108795166, "step": 6155, "token_acc": 0.7689314903151664 }, { "epoch": 0.3987990709794369, "grad_norm": 0.29912808537483215, "learning_rate": 9.050696100781749e-06, "loss": 0.7346284866333008, "step": 6160, "token_acc": 0.7744853748496066 }, { "epoch": 0.3991227715240631, "grad_norm": 0.3656819760799408, "learning_rate": 9.049205223527431e-06, "loss": 0.7194292545318604, "step": 6165, "token_acc": 0.7786696044486413 }, { "epoch": 0.3994464720686893, "grad_norm": 0.31121817231178284, "learning_rate": 9.047713299479055e-06, "loss": 0.7393862247467041, "step": 6170, "token_acc": 0.7727088614210678 }, { "epoch": 0.39977017261331543, "grad_norm": 0.3194950520992279, "learning_rate": 9.046220329022311e-06, "loss": 0.7466986179351807, "step": 6175, "token_acc": 0.7709136340678913 }, { "epoch": 0.4000938731579416, "grad_norm": 0.2917241156101227, "learning_rate": 9.044726312543158e-06, "loss": 0.737672758102417, "step": 6180, "token_acc": 0.7736945677543362 }, { "epoch": 0.40041757370256775, "grad_norm": 0.3798705041408539, "learning_rate": 9.043231250427828e-06, "loss": 0.7413841247558594, "step": 6185, "token_acc": 0.7720003489722097 }, { "epoch": 0.4007412742471939, "grad_norm": 0.35784712433815, "learning_rate": 9.041735143062824e-06, "loss": 0.7489949703216553, "step": 6190, "token_acc": 0.7716316227392443 }, { "epoch": 0.4010649747918201, "grad_norm": 0.3360874354839325, "learning_rate": 9.040237990834915e-06, "loss": 0.6970431804656982, "step": 6195, "token_acc": 0.7826060808553291 }, { "epoch": 0.40138867533644623, "grad_norm": 0.3387690782546997, "learning_rate": 9.038739794131142e-06, "loss": 0.7164937019348144, "step": 6200, "token_acc": 0.7788799042376104 }, { "epoch": 0.40171237588107245, "grad_norm": 0.3438434302806854, "learning_rate": 9.037240553338818e-06, "loss": 0.7228050231933594, "step": 6205, "token_acc": 0.7769926406386429 }, { "epoch": 0.4020360764256986, "grad_norm": 0.2946946620941162, "learning_rate": 9.035740268845522e-06, "loss": 0.7493712425231933, "step": 6210, "token_acc": 0.7705996054440747 }, { "epoch": 0.40235977697032477, "grad_norm": 0.313900351524353, "learning_rate": 9.034238941039108e-06, "loss": 0.7356785774230957, "step": 6215, "token_acc": 0.7725427237023671 }, { "epoch": 0.4026834775149509, "grad_norm": 0.33479344844818115, "learning_rate": 9.032736570307694e-06, "loss": 0.733295488357544, "step": 6220, "token_acc": 0.7731953329336504 }, { "epoch": 0.4030071780595771, "grad_norm": 0.3443644642829895, "learning_rate": 9.031233157039674e-06, "loss": 0.7353864192962647, "step": 6225, "token_acc": 0.7731767403454418 }, { "epoch": 0.40333087860420325, "grad_norm": 0.2554037570953369, "learning_rate": 9.029728701623705e-06, "loss": 0.7290099143981934, "step": 6230, "token_acc": 0.776065710637462 }, { "epoch": 0.4036545791488294, "grad_norm": 0.2550737261772156, "learning_rate": 9.028223204448718e-06, "loss": 0.7105469226837158, "step": 6235, "token_acc": 0.7801640990407738 }, { "epoch": 0.40397827969345557, "grad_norm": 0.2872796058654785, "learning_rate": 9.02671666590391e-06, "loss": 0.7245826721191406, "step": 6240, "token_acc": 0.776651591791954 }, { "epoch": 0.4043019802380817, "grad_norm": 0.343230277299881, "learning_rate": 9.02520908637875e-06, "loss": 0.7577357292175293, "step": 6245, "token_acc": 0.7679912064543476 }, { "epoch": 0.40462568078270794, "grad_norm": 0.28581780195236206, "learning_rate": 9.023700466262977e-06, "loss": 0.713773536682129, "step": 6250, "token_acc": 0.7783653903483144 }, { "epoch": 0.4049493813273341, "grad_norm": 0.24118535220623016, "learning_rate": 9.022190805946593e-06, "loss": 0.7474263191223145, "step": 6255, "token_acc": 0.7710195327564393 }, { "epoch": 0.40527308187196026, "grad_norm": 0.3826557397842407, "learning_rate": 9.020680105819877e-06, "loss": 0.7314907550811768, "step": 6260, "token_acc": 0.7743508089088086 }, { "epoch": 0.4055967824165864, "grad_norm": 0.32924118638038635, "learning_rate": 9.01916836627337e-06, "loss": 0.7302586555480957, "step": 6265, "token_acc": 0.7745004471815558 }, { "epoch": 0.4059204829612126, "grad_norm": 0.29220762848854065, "learning_rate": 9.017655587697885e-06, "loss": 0.7329822063446045, "step": 6270, "token_acc": 0.7733724451173354 }, { "epoch": 0.40624418350583874, "grad_norm": 0.31129691004753113, "learning_rate": 9.016141770484503e-06, "loss": 0.7295607089996338, "step": 6275, "token_acc": 0.7759446364841083 }, { "epoch": 0.4065678840504649, "grad_norm": 0.342832088470459, "learning_rate": 9.014626915024576e-06, "loss": 0.746448278427124, "step": 6280, "token_acc": 0.7719958989810223 }, { "epoch": 0.40689158459509106, "grad_norm": 0.3731692135334015, "learning_rate": 9.013111021709719e-06, "loss": 0.7193161487579346, "step": 6285, "token_acc": 0.7772100711758357 }, { "epoch": 0.4072152851397172, "grad_norm": 0.40133634209632874, "learning_rate": 9.011594090931818e-06, "loss": 0.7362190246582031, "step": 6290, "token_acc": 0.773817954025493 }, { "epoch": 0.40753898568434344, "grad_norm": 0.29633426666259766, "learning_rate": 9.010076123083031e-06, "loss": 0.7346063137054444, "step": 6295, "token_acc": 0.7742363392965803 }, { "epoch": 0.4078626862289696, "grad_norm": 0.2851264178752899, "learning_rate": 9.008557118555779e-06, "loss": 0.7371465682983398, "step": 6300, "token_acc": 0.7738226403367517 }, { "epoch": 0.40818638677359576, "grad_norm": 0.233809694647789, "learning_rate": 9.00703707774275e-06, "loss": 0.7277594566345215, "step": 6305, "token_acc": 0.774629535722335 }, { "epoch": 0.4085100873182219, "grad_norm": 0.35847207903862, "learning_rate": 9.005516001036908e-06, "loss": 0.7261065483093262, "step": 6310, "token_acc": 0.7769726877759843 }, { "epoch": 0.4088337878628481, "grad_norm": 0.35827410221099854, "learning_rate": 9.003993888831473e-06, "loss": 0.7284585952758789, "step": 6315, "token_acc": 0.7763652344496389 }, { "epoch": 0.40915748840747423, "grad_norm": 0.23413397371768951, "learning_rate": 9.002470741519944e-06, "loss": 0.7369014263153076, "step": 6320, "token_acc": 0.7730613603769719 }, { "epoch": 0.4094811889521004, "grad_norm": 0.34248992800712585, "learning_rate": 9.00094655949608e-06, "loss": 0.7647931575775146, "step": 6325, "token_acc": 0.7662587264350923 }, { "epoch": 0.40980488949672655, "grad_norm": 0.2692128121852875, "learning_rate": 8.99942134315391e-06, "loss": 0.7341650009155274, "step": 6330, "token_acc": 0.7740309645800847 }, { "epoch": 0.41012859004135277, "grad_norm": 0.261578232049942, "learning_rate": 8.997895092887732e-06, "loss": 0.7300757884979248, "step": 6335, "token_acc": 0.7759074353612431 }, { "epoch": 0.41045229058597893, "grad_norm": 0.39239153265953064, "learning_rate": 8.996367809092111e-06, "loss": 0.7477935791015625, "step": 6340, "token_acc": 0.7716098388008289 }, { "epoch": 0.4107759911306051, "grad_norm": 0.3092658817768097, "learning_rate": 8.994839492161873e-06, "loss": 0.7601749897003174, "step": 6345, "token_acc": 0.7683729800912081 }, { "epoch": 0.41109969167523125, "grad_norm": 0.3007875680923462, "learning_rate": 8.993310142492119e-06, "loss": 0.7364577293395996, "step": 6350, "token_acc": 0.7735439107802787 }, { "epoch": 0.4114233922198574, "grad_norm": 0.26631271839141846, "learning_rate": 8.991779760478215e-06, "loss": 0.7330163478851318, "step": 6355, "token_acc": 0.7750903583791489 }, { "epoch": 0.41174709276448357, "grad_norm": 0.31343981623649597, "learning_rate": 8.990248346515792e-06, "loss": 0.7326494216918945, "step": 6360, "token_acc": 0.7747806431860966 }, { "epoch": 0.41207079330910973, "grad_norm": 0.36442676186561584, "learning_rate": 8.988715901000749e-06, "loss": 0.7200027465820312, "step": 6365, "token_acc": 0.7783687943262412 }, { "epoch": 0.4123944938537359, "grad_norm": 0.3219897150993347, "learning_rate": 8.987182424329251e-06, "loss": 0.7359511852264404, "step": 6370, "token_acc": 0.7739432953694181 }, { "epoch": 0.41271819439836205, "grad_norm": 0.3346618115901947, "learning_rate": 8.985647916897728e-06, "loss": 0.7475944519042969, "step": 6375, "token_acc": 0.7711325247414242 }, { "epoch": 0.41304189494298826, "grad_norm": 0.30970388650894165, "learning_rate": 8.984112379102883e-06, "loss": 0.7474925518035889, "step": 6380, "token_acc": 0.7713090465400035 }, { "epoch": 0.4133655954876144, "grad_norm": 0.3264576494693756, "learning_rate": 8.982575811341677e-06, "loss": 0.7094758510589599, "step": 6385, "token_acc": 0.7798908846008885 }, { "epoch": 0.4136892960322406, "grad_norm": 0.36372387409210205, "learning_rate": 8.981038214011341e-06, "loss": 0.7481161117553711, "step": 6390, "token_acc": 0.7716676890719482 }, { "epoch": 0.41401299657686674, "grad_norm": 0.3376249372959137, "learning_rate": 8.979499587509377e-06, "loss": 0.7468792915344238, "step": 6395, "token_acc": 0.7714289497728988 }, { "epoch": 0.4143366971214929, "grad_norm": 0.33177435398101807, "learning_rate": 8.977959932233542e-06, "loss": 0.7461841583251954, "step": 6400, "token_acc": 0.7713413986677332 }, { "epoch": 0.41466039766611906, "grad_norm": 0.3784444034099579, "learning_rate": 8.976419248581867e-06, "loss": 0.7280561447143554, "step": 6405, "token_acc": 0.7765605651243949 }, { "epoch": 0.4149840982107452, "grad_norm": 0.3087449371814728, "learning_rate": 8.97487753695265e-06, "loss": 0.7362638473510742, "step": 6410, "token_acc": 0.7742702147550266 }, { "epoch": 0.4153077987553714, "grad_norm": 0.3325817883014679, "learning_rate": 8.973334797744448e-06, "loss": 0.7212969303131104, "step": 6415, "token_acc": 0.776978316066367 }, { "epoch": 0.4156314992999976, "grad_norm": 0.30345669388771057, "learning_rate": 8.971791031356092e-06, "loss": 0.7123603820800781, "step": 6420, "token_acc": 0.7787940829146607 }, { "epoch": 0.41595519984462376, "grad_norm": 0.3337783217430115, "learning_rate": 8.970246238186668e-06, "loss": 0.7243190765380859, "step": 6425, "token_acc": 0.7770220458610322 }, { "epoch": 0.4162789003892499, "grad_norm": 0.3051930069923401, "learning_rate": 8.968700418635539e-06, "loss": 0.7450730800628662, "step": 6430, "token_acc": 0.773539507448262 }, { "epoch": 0.4166026009338761, "grad_norm": 0.362278550863266, "learning_rate": 8.967153573102325e-06, "loss": 0.7392449378967285, "step": 6435, "token_acc": 0.7726797795366089 }, { "epoch": 0.41692630147850224, "grad_norm": 0.2769290506839752, "learning_rate": 8.965605701986915e-06, "loss": 0.7145302772521973, "step": 6440, "token_acc": 0.7789357938518908 }, { "epoch": 0.4172500020231284, "grad_norm": 0.3477558195590973, "learning_rate": 8.964056805689461e-06, "loss": 0.758892011642456, "step": 6445, "token_acc": 0.768149599143763 }, { "epoch": 0.41757370256775456, "grad_norm": 0.35912081599235535, "learning_rate": 8.96250688461038e-06, "loss": 0.7476851463317871, "step": 6450, "token_acc": 0.7711713273722537 }, { "epoch": 0.4178974031123807, "grad_norm": 0.3449747860431671, "learning_rate": 8.96095593915036e-06, "loss": 0.7219779014587402, "step": 6455, "token_acc": 0.7768722968358752 }, { "epoch": 0.4182211036570069, "grad_norm": 0.31869328022003174, "learning_rate": 8.959403969710346e-06, "loss": 0.7500092029571533, "step": 6460, "token_acc": 0.770926292910567 }, { "epoch": 0.4185448042016331, "grad_norm": 0.23324547708034515, "learning_rate": 8.95785097669155e-06, "loss": 0.7251573085784913, "step": 6465, "token_acc": 0.7764892539234489 }, { "epoch": 0.41886850474625925, "grad_norm": 0.2499793916940689, "learning_rate": 8.956296960495448e-06, "loss": 0.7387531757354736, "step": 6470, "token_acc": 0.7737383401100215 }, { "epoch": 0.4191922052908854, "grad_norm": 0.33678996562957764, "learning_rate": 8.954741921523786e-06, "loss": 0.745181655883789, "step": 6475, "token_acc": 0.7712376165980345 }, { "epoch": 0.41951590583551157, "grad_norm": 0.39874404668807983, "learning_rate": 8.953185860178566e-06, "loss": 0.738694429397583, "step": 6480, "token_acc": 0.7735289279861589 }, { "epoch": 0.41983960638013773, "grad_norm": 0.39232462644577026, "learning_rate": 8.951628776862062e-06, "loss": 0.744883394241333, "step": 6485, "token_acc": 0.7716542629586108 }, { "epoch": 0.4201633069247639, "grad_norm": 0.36812424659729004, "learning_rate": 8.950070671976804e-06, "loss": 0.7287323951721192, "step": 6490, "token_acc": 0.7772282954479727 }, { "epoch": 0.42048700746939005, "grad_norm": 0.3474551737308502, "learning_rate": 8.948511545925598e-06, "loss": 0.7594921112060546, "step": 6495, "token_acc": 0.7677250091438539 }, { "epoch": 0.4208107080140162, "grad_norm": 0.34414738416671753, "learning_rate": 8.946951399111501e-06, "loss": 0.7511009216308594, "step": 6500, "token_acc": 0.7695928500496524 }, { "epoch": 0.4211344085586424, "grad_norm": 0.28702783584594727, "learning_rate": 8.94539023193784e-06, "loss": 0.7302061557769776, "step": 6505, "token_acc": 0.7761894335137164 }, { "epoch": 0.4214581091032686, "grad_norm": 0.44522473216056824, "learning_rate": 8.943828044808208e-06, "loss": 0.7367766380310059, "step": 6510, "token_acc": 0.7718275194204965 }, { "epoch": 0.42178180964789475, "grad_norm": 0.37024444341659546, "learning_rate": 8.942264838126457e-06, "loss": 0.7349027633666992, "step": 6515, "token_acc": 0.7746057296412822 }, { "epoch": 0.4221055101925209, "grad_norm": 0.43366488814353943, "learning_rate": 8.940700612296706e-06, "loss": 0.7236298561096192, "step": 6520, "token_acc": 0.7747691669260297 }, { "epoch": 0.42242921073714707, "grad_norm": 0.2898455262184143, "learning_rate": 8.939135367723336e-06, "loss": 0.7187947273254395, "step": 6525, "token_acc": 0.7770136907081704 }, { "epoch": 0.4227529112817732, "grad_norm": 0.39141160249710083, "learning_rate": 8.937569104810992e-06, "loss": 0.7389766693115234, "step": 6530, "token_acc": 0.7747041757668611 }, { "epoch": 0.4230766118263994, "grad_norm": 0.3366338312625885, "learning_rate": 8.936001823964579e-06, "loss": 0.7818307876586914, "step": 6535, "token_acc": 0.7623479647458351 }, { "epoch": 0.42340031237102554, "grad_norm": 0.32215484976768494, "learning_rate": 8.93443352558927e-06, "loss": 0.7534949302673339, "step": 6540, "token_acc": 0.7693517080745341 }, { "epoch": 0.4237240129156517, "grad_norm": 0.30833232402801514, "learning_rate": 8.9328642100905e-06, "loss": 0.7409784317016601, "step": 6545, "token_acc": 0.7728070737489589 }, { "epoch": 0.4240477134602779, "grad_norm": 0.27574607729911804, "learning_rate": 8.931293877873965e-06, "loss": 0.7275968074798584, "step": 6550, "token_acc": 0.7748590664661729 }, { "epoch": 0.4243714140049041, "grad_norm": 0.30601274967193604, "learning_rate": 8.929722529345624e-06, "loss": 0.7415097236633301, "step": 6555, "token_acc": 0.7701011923438971 }, { "epoch": 0.42469511454953024, "grad_norm": 0.32560908794403076, "learning_rate": 8.9281501649117e-06, "loss": 0.7248705863952637, "step": 6560, "token_acc": 0.7772317117427434 }, { "epoch": 0.4250188150941564, "grad_norm": 0.3428451120853424, "learning_rate": 8.92657678497868e-06, "loss": 0.724180030822754, "step": 6565, "token_acc": 0.7767087962815574 }, { "epoch": 0.42534251563878256, "grad_norm": 0.20504295825958252, "learning_rate": 8.925002389953307e-06, "loss": 0.7333839893341064, "step": 6570, "token_acc": 0.7743081075405625 }, { "epoch": 0.4256662161834087, "grad_norm": 0.3214343786239624, "learning_rate": 8.923426980242596e-06, "loss": 0.709323787689209, "step": 6575, "token_acc": 0.7800671127971609 }, { "epoch": 0.4259899167280349, "grad_norm": 0.2869703769683838, "learning_rate": 8.921850556253818e-06, "loss": 0.7111658096313477, "step": 6580, "token_acc": 0.7794375985741213 }, { "epoch": 0.42631361727266104, "grad_norm": 0.37978342175483704, "learning_rate": 8.920273118394504e-06, "loss": 0.7398200035095215, "step": 6585, "token_acc": 0.7725095369485773 }, { "epoch": 0.42663731781728725, "grad_norm": 0.40413138270378113, "learning_rate": 8.918694667072456e-06, "loss": 0.7445460796356201, "step": 6590, "token_acc": 0.7715556881167202 }, { "epoch": 0.4269610183619134, "grad_norm": 0.3363731801509857, "learning_rate": 8.91711520269573e-06, "loss": 0.7196575164794922, "step": 6595, "token_acc": 0.7764589854050092 }, { "epoch": 0.4272847189065396, "grad_norm": 0.30086296796798706, "learning_rate": 8.915534725672648e-06, "loss": 0.7283071517944336, "step": 6600, "token_acc": 0.7750841542880084 }, { "epoch": 0.42760841945116573, "grad_norm": 0.27939504384994507, "learning_rate": 8.91395323641179e-06, "loss": 0.7554414749145508, "step": 6605, "token_acc": 0.7690138209426043 }, { "epoch": 0.4279321199957919, "grad_norm": 0.3775722086429596, "learning_rate": 8.912370735322001e-06, "loss": 0.7472012996673584, "step": 6610, "token_acc": 0.77142011200635 }, { "epoch": 0.42825582054041805, "grad_norm": 0.3459763824939728, "learning_rate": 8.91078722281239e-06, "loss": 0.7459381580352783, "step": 6615, "token_acc": 0.7719725888791795 }, { "epoch": 0.4285795210850442, "grad_norm": 0.3496129810810089, "learning_rate": 8.909202699292319e-06, "loss": 0.7236249923706055, "step": 6620, "token_acc": 0.7772626698977979 }, { "epoch": 0.4289032216296704, "grad_norm": 0.38436153531074524, "learning_rate": 8.907617165171419e-06, "loss": 0.7182631015777587, "step": 6625, "token_acc": 0.7774875282321114 }, { "epoch": 0.42922692217429653, "grad_norm": 0.28887540102005005, "learning_rate": 8.906030620859578e-06, "loss": 0.7385179042816162, "step": 6630, "token_acc": 0.773875011804703 }, { "epoch": 0.42955062271892275, "grad_norm": 0.27928680181503296, "learning_rate": 8.90444306676695e-06, "loss": 0.7314334869384765, "step": 6635, "token_acc": 0.7740564313591397 }, { "epoch": 0.4298743232635489, "grad_norm": 0.2705102562904358, "learning_rate": 8.902854503303946e-06, "loss": 0.7474337100982666, "step": 6640, "token_acc": 0.7707820044519892 }, { "epoch": 0.43019802380817507, "grad_norm": 0.24389833211898804, "learning_rate": 8.901264930881237e-06, "loss": 0.7424828052520752, "step": 6645, "token_acc": 0.7733715881873392 }, { "epoch": 0.4305217243528012, "grad_norm": 0.24970240890979767, "learning_rate": 8.899674349909759e-06, "loss": 0.7572746753692627, "step": 6650, "token_acc": 0.7686385354829368 }, { "epoch": 0.4308454248974274, "grad_norm": 0.2834174335002899, "learning_rate": 8.898082760800705e-06, "loss": 0.7388201236724854, "step": 6655, "token_acc": 0.7726357763165462 }, { "epoch": 0.43116912544205355, "grad_norm": 0.3260691165924072, "learning_rate": 8.89649016396553e-06, "loss": 0.728091049194336, "step": 6660, "token_acc": 0.7753030786409316 }, { "epoch": 0.4314928259866797, "grad_norm": 0.2919974625110626, "learning_rate": 8.894896559815951e-06, "loss": 0.7343770027160644, "step": 6665, "token_acc": 0.7745628511135005 }, { "epoch": 0.43181652653130587, "grad_norm": 0.20536719262599945, "learning_rate": 8.893301948763941e-06, "loss": 0.7381988048553467, "step": 6670, "token_acc": 0.773649568913637 }, { "epoch": 0.4321402270759321, "grad_norm": 0.32382774353027344, "learning_rate": 8.89170633122174e-06, "loss": 0.7412338256835938, "step": 6675, "token_acc": 0.771292373620698 }, { "epoch": 0.43246392762055824, "grad_norm": 0.2661289870738983, "learning_rate": 8.890109707601844e-06, "loss": 0.7607123374938964, "step": 6680, "token_acc": 0.7669068265620013 }, { "epoch": 0.4327876281651844, "grad_norm": 0.3755648732185364, "learning_rate": 8.888512078317006e-06, "loss": 0.7477588653564453, "step": 6685, "token_acc": 0.7738255826241554 }, { "epoch": 0.43311132870981056, "grad_norm": 0.27375301718711853, "learning_rate": 8.886913443780248e-06, "loss": 0.7360215187072754, "step": 6690, "token_acc": 0.7735077187535395 }, { "epoch": 0.4334350292544367, "grad_norm": 0.2980822026729584, "learning_rate": 8.88531380440484e-06, "loss": 0.7166489124298095, "step": 6695, "token_acc": 0.7797752507283541 }, { "epoch": 0.4337587297990629, "grad_norm": 0.3330109417438507, "learning_rate": 8.883713160604323e-06, "loss": 0.7180768966674804, "step": 6700, "token_acc": 0.777669462847634 }, { "epoch": 0.43408243034368904, "grad_norm": 0.3631215989589691, "learning_rate": 8.882111512792494e-06, "loss": 0.7298660278320312, "step": 6705, "token_acc": 0.7733581060158208 }, { "epoch": 0.4344061308883152, "grad_norm": 0.30749157071113586, "learning_rate": 8.880508861383404e-06, "loss": 0.727174949645996, "step": 6710, "token_acc": 0.7765250374082193 }, { "epoch": 0.43472983143294136, "grad_norm": 0.26084622740745544, "learning_rate": 8.878905206791369e-06, "loss": 0.7323581218719483, "step": 6715, "token_acc": 0.7746080480794356 }, { "epoch": 0.4350535319775676, "grad_norm": 0.24008041620254517, "learning_rate": 8.877300549430964e-06, "loss": 0.7268571376800537, "step": 6720, "token_acc": 0.775814599810392 }, { "epoch": 0.43537723252219374, "grad_norm": 0.2924354076385498, "learning_rate": 8.875694889717024e-06, "loss": 0.7498863220214844, "step": 6725, "token_acc": 0.770102532808487 }, { "epoch": 0.4357009330668199, "grad_norm": 0.2438260018825531, "learning_rate": 8.874088228064638e-06, "loss": 0.7215539932250976, "step": 6730, "token_acc": 0.7768140349100026 }, { "epoch": 0.43602463361144606, "grad_norm": 0.3935315012931824, "learning_rate": 8.872480564889161e-06, "loss": 0.745756721496582, "step": 6735, "token_acc": 0.7718940522964368 }, { "epoch": 0.4363483341560722, "grad_norm": 0.4201851189136505, "learning_rate": 8.870871900606201e-06, "loss": 0.7328583240509033, "step": 6740, "token_acc": 0.7733924698618628 }, { "epoch": 0.4366720347006984, "grad_norm": 0.3513701856136322, "learning_rate": 8.869262235631631e-06, "loss": 0.7300845146179199, "step": 6745, "token_acc": 0.7756020706729687 }, { "epoch": 0.43699573524532453, "grad_norm": 0.401743620634079, "learning_rate": 8.867651570381574e-06, "loss": 0.7394275188446044, "step": 6750, "token_acc": 0.7729606303913082 }, { "epoch": 0.4373194357899507, "grad_norm": 0.30277296900749207, "learning_rate": 8.866039905272422e-06, "loss": 0.7323748588562011, "step": 6755, "token_acc": 0.7768888672576063 }, { "epoch": 0.4376431363345769, "grad_norm": 0.37816259264945984, "learning_rate": 8.864427240720816e-06, "loss": 0.7708847522735596, "step": 6760, "token_acc": 0.7636657047906894 }, { "epoch": 0.43796683687920307, "grad_norm": 0.307727187871933, "learning_rate": 8.862813577143659e-06, "loss": 0.7290449619293213, "step": 6765, "token_acc": 0.7753801810261627 }, { "epoch": 0.43829053742382923, "grad_norm": 0.3152691125869751, "learning_rate": 8.861198914958115e-06, "loss": 0.733992052078247, "step": 6770, "token_acc": 0.7746533298703273 }, { "epoch": 0.4386142379684554, "grad_norm": 0.3865210711956024, "learning_rate": 8.859583254581604e-06, "loss": 0.7425102710723877, "step": 6775, "token_acc": 0.7719844208175862 }, { "epoch": 0.43893793851308155, "grad_norm": 0.2902456223964691, "learning_rate": 8.857966596431805e-06, "loss": 0.7003990173339844, "step": 6780, "token_acc": 0.7824440641201658 }, { "epoch": 0.4392616390577077, "grad_norm": 0.24756775796413422, "learning_rate": 8.85634894092665e-06, "loss": 0.7486584663391114, "step": 6785, "token_acc": 0.770362598676518 }, { "epoch": 0.43958533960233387, "grad_norm": 0.3592889606952667, "learning_rate": 8.854730288484335e-06, "loss": 0.7419243335723877, "step": 6790, "token_acc": 0.7730610794969361 }, { "epoch": 0.43990904014696003, "grad_norm": 0.7355027794837952, "learning_rate": 8.853110639523313e-06, "loss": 0.731814193725586, "step": 6795, "token_acc": 0.7767504174338871 }, { "epoch": 0.4402327406915862, "grad_norm": 0.3437013626098633, "learning_rate": 8.851489994462287e-06, "loss": 0.7326210021972657, "step": 6800, "token_acc": 0.7744066718113264 }, { "epoch": 0.4405564412362124, "grad_norm": 0.3165207505226135, "learning_rate": 8.849868353720233e-06, "loss": 0.7472399234771728, "step": 6805, "token_acc": 0.76974069019302 }, { "epoch": 0.44088014178083856, "grad_norm": 0.39069223403930664, "learning_rate": 8.848245717716367e-06, "loss": 0.7495824813842773, "step": 6810, "token_acc": 0.770272028308637 }, { "epoch": 0.4412038423254647, "grad_norm": 0.30168479681015015, "learning_rate": 8.846622086870174e-06, "loss": 0.7212768077850342, "step": 6815, "token_acc": 0.7765345541119295 }, { "epoch": 0.4415275428700909, "grad_norm": 0.31636959314346313, "learning_rate": 8.84499746160139e-06, "loss": 0.7398929119110107, "step": 6820, "token_acc": 0.7731218993621545 }, { "epoch": 0.44185124341471704, "grad_norm": 0.4080216884613037, "learning_rate": 8.843371842330013e-06, "loss": 0.7227908611297608, "step": 6825, "token_acc": 0.7754207697186754 }, { "epoch": 0.4421749439593432, "grad_norm": 0.38378870487213135, "learning_rate": 8.841745229476298e-06, "loss": 0.7293608665466309, "step": 6830, "token_acc": 0.7758786711603274 }, { "epoch": 0.44249864450396936, "grad_norm": 0.3203992247581482, "learning_rate": 8.840117623460747e-06, "loss": 0.7290853500366211, "step": 6835, "token_acc": 0.7744107744107744 }, { "epoch": 0.4428223450485955, "grad_norm": 0.3553474247455597, "learning_rate": 8.838489024704131e-06, "loss": 0.7359612464904786, "step": 6840, "token_acc": 0.7732979420179944 }, { "epoch": 0.44314604559322174, "grad_norm": 0.3063249886035919, "learning_rate": 8.836859433627472e-06, "loss": 0.7548156261444092, "step": 6845, "token_acc": 0.7699714617152861 }, { "epoch": 0.4434697461378479, "grad_norm": 0.4219306409358978, "learning_rate": 8.835228850652048e-06, "loss": 0.7237010478973389, "step": 6850, "token_acc": 0.7759653981392165 }, { "epoch": 0.44379344668247406, "grad_norm": 0.4721439480781555, "learning_rate": 8.833597276199397e-06, "loss": 0.7157509803771973, "step": 6855, "token_acc": 0.77817380552735 }, { "epoch": 0.4441171472271002, "grad_norm": 0.27615639567375183, "learning_rate": 8.83196471069131e-06, "loss": 0.7379691123962402, "step": 6860, "token_acc": 0.7736491707015556 }, { "epoch": 0.4444408477717264, "grad_norm": 0.329436719417572, "learning_rate": 8.830331154549834e-06, "loss": 0.7266415119171142, "step": 6865, "token_acc": 0.776271252006731 }, { "epoch": 0.44476454831635254, "grad_norm": 0.41062965989112854, "learning_rate": 8.828696608197276e-06, "loss": 0.7471168994903564, "step": 6870, "token_acc": 0.7721702332163024 }, { "epoch": 0.4450882488609787, "grad_norm": 0.29589056968688965, "learning_rate": 8.827061072056194e-06, "loss": 0.7394560813903809, "step": 6875, "token_acc": 0.7724041693145264 }, { "epoch": 0.44541194940560486, "grad_norm": 0.45598313212394714, "learning_rate": 8.825424546549403e-06, "loss": 0.7283579349517822, "step": 6880, "token_acc": 0.7765963174329709 }, { "epoch": 0.445735649950231, "grad_norm": 0.3389948308467865, "learning_rate": 8.823787032099978e-06, "loss": 0.7288188934326172, "step": 6885, "token_acc": 0.7753914411424919 }, { "epoch": 0.44605935049485723, "grad_norm": 0.32050514221191406, "learning_rate": 8.822148529131246e-06, "loss": 0.7153533458709717, "step": 6890, "token_acc": 0.7776031985410163 }, { "epoch": 0.4463830510394834, "grad_norm": 0.35918280482292175, "learning_rate": 8.82050903806679e-06, "loss": 0.7350781440734864, "step": 6895, "token_acc": 0.775321744109403 }, { "epoch": 0.44670675158410955, "grad_norm": 0.3972082734107971, "learning_rate": 8.818868559330447e-06, "loss": 0.7398908138275146, "step": 6900, "token_acc": 0.771321254971277 }, { "epoch": 0.4470304521287357, "grad_norm": 0.3761273920536041, "learning_rate": 8.817227093346312e-06, "loss": 0.7326708793640136, "step": 6905, "token_acc": 0.774827178671174 }, { "epoch": 0.44735415267336187, "grad_norm": 0.33204910159111023, "learning_rate": 8.815584640538734e-06, "loss": 0.719734001159668, "step": 6910, "token_acc": 0.7783517136289677 }, { "epoch": 0.44767785321798803, "grad_norm": 0.3687607944011688, "learning_rate": 8.81394120133232e-06, "loss": 0.7538261413574219, "step": 6915, "token_acc": 0.7693443143097574 }, { "epoch": 0.4480015537626142, "grad_norm": 0.35191479325294495, "learning_rate": 8.812296776151925e-06, "loss": 0.7648440837860108, "step": 6920, "token_acc": 0.7671822016375817 }, { "epoch": 0.44832525430724035, "grad_norm": 0.2841516137123108, "learning_rate": 8.810651365422666e-06, "loss": 0.7295875549316406, "step": 6925, "token_acc": 0.7732277935590949 }, { "epoch": 0.44864895485186657, "grad_norm": 0.35718834400177, "learning_rate": 8.80900496956991e-06, "loss": 0.7051815986633301, "step": 6930, "token_acc": 0.7827289130287522 }, { "epoch": 0.4489726553964927, "grad_norm": 0.2887440025806427, "learning_rate": 8.80735758901928e-06, "loss": 0.7166306972503662, "step": 6935, "token_acc": 0.7801389429944163 }, { "epoch": 0.4492963559411189, "grad_norm": 0.3559567928314209, "learning_rate": 8.805709224196659e-06, "loss": 0.738471508026123, "step": 6940, "token_acc": 0.7736050920910076 }, { "epoch": 0.44962005648574505, "grad_norm": 0.28402918577194214, "learning_rate": 8.804059875528175e-06, "loss": 0.7283227920532227, "step": 6945, "token_acc": 0.7759779951100244 }, { "epoch": 0.4499437570303712, "grad_norm": 0.35772326588630676, "learning_rate": 8.802409543440217e-06, "loss": 0.7443663597106933, "step": 6950, "token_acc": 0.7715228270988622 }, { "epoch": 0.45026745757499737, "grad_norm": 0.2973904013633728, "learning_rate": 8.800758228359426e-06, "loss": 0.7121762275695801, "step": 6955, "token_acc": 0.7802159388459078 }, { "epoch": 0.4505911581196235, "grad_norm": 0.279411256313324, "learning_rate": 8.799105930712695e-06, "loss": 0.7241015911102295, "step": 6960, "token_acc": 0.775475261565406 }, { "epoch": 0.4509148586642497, "grad_norm": 0.32940539717674255, "learning_rate": 8.797452650927177e-06, "loss": 0.7329633712768555, "step": 6965, "token_acc": 0.7759348495278668 }, { "epoch": 0.45123855920887584, "grad_norm": 0.3050759732723236, "learning_rate": 8.795798389430273e-06, "loss": 0.7545974731445313, "step": 6970, "token_acc": 0.7694559452417643 }, { "epoch": 0.45156225975350206, "grad_norm": 0.2698078453540802, "learning_rate": 8.794143146649639e-06, "loss": 0.744051170349121, "step": 6975, "token_acc": 0.7727930097604366 }, { "epoch": 0.4518859602981282, "grad_norm": 0.30005943775177, "learning_rate": 8.792486923013188e-06, "loss": 0.7039380073547363, "step": 6980, "token_acc": 0.7818159733543021 }, { "epoch": 0.4522096608427544, "grad_norm": 0.32686847448349, "learning_rate": 8.790829718949085e-06, "loss": 0.7133976936340332, "step": 6985, "token_acc": 0.7782889302288097 }, { "epoch": 0.45253336138738054, "grad_norm": 0.3120647370815277, "learning_rate": 8.789171534885746e-06, "loss": 0.7188449382781983, "step": 6990, "token_acc": 0.7810157710088855 }, { "epoch": 0.4528570619320067, "grad_norm": 0.29364848136901855, "learning_rate": 8.78751237125184e-06, "loss": 0.7306705951690674, "step": 6995, "token_acc": 0.7752440768183466 }, { "epoch": 0.45318076247663286, "grad_norm": 0.36750391125679016, "learning_rate": 8.785852228476298e-06, "loss": 0.7630218505859375, "step": 7000, "token_acc": 0.7689415384615385 }, { "epoch": 0.453504463021259, "grad_norm": 0.27948737144470215, "learning_rate": 8.78419110698829e-06, "loss": 0.7375415802001953, "step": 7005, "token_acc": 0.7734331821025333 }, { "epoch": 0.4538281635658852, "grad_norm": 0.3768216371536255, "learning_rate": 8.78252900721725e-06, "loss": 0.7266280174255371, "step": 7010, "token_acc": 0.7753152744820967 }, { "epoch": 0.45415186411051134, "grad_norm": 0.30240824818611145, "learning_rate": 8.780865929592861e-06, "loss": 0.7425758361816406, "step": 7015, "token_acc": 0.7726154877131315 }, { "epoch": 0.45447556465513755, "grad_norm": 0.31587740778923035, "learning_rate": 8.77920187454506e-06, "loss": 0.740117359161377, "step": 7020, "token_acc": 0.7710177833463703 }, { "epoch": 0.4547992651997637, "grad_norm": 0.35702160000801086, "learning_rate": 8.777536842504035e-06, "loss": 0.7269446372985839, "step": 7025, "token_acc": 0.7743991158118582 }, { "epoch": 0.4551229657443899, "grad_norm": 0.39020922780036926, "learning_rate": 8.775870833900226e-06, "loss": 0.7475565910339356, "step": 7030, "token_acc": 0.7712347905293542 }, { "epoch": 0.45544666628901603, "grad_norm": 0.33192068338394165, "learning_rate": 8.77420384916433e-06, "loss": 0.7281889915466309, "step": 7035, "token_acc": 0.7752731156105235 }, { "epoch": 0.4557703668336422, "grad_norm": 0.2892034947872162, "learning_rate": 8.772535888727292e-06, "loss": 0.7109617233276367, "step": 7040, "token_acc": 0.7789337301485492 }, { "epoch": 0.45609406737826835, "grad_norm": 0.31705623865127563, "learning_rate": 8.77086695302031e-06, "loss": 0.722216796875, "step": 7045, "token_acc": 0.7768947670334062 }, { "epoch": 0.4564177679228945, "grad_norm": 0.31907039880752563, "learning_rate": 8.769197042474832e-06, "loss": 0.7230689048767089, "step": 7050, "token_acc": 0.7774006951497221 }, { "epoch": 0.4567414684675207, "grad_norm": 0.3029007315635681, "learning_rate": 8.767526157522566e-06, "loss": 0.718068790435791, "step": 7055, "token_acc": 0.7780465140800981 }, { "epoch": 0.4570651690121469, "grad_norm": 0.45432883501052856, "learning_rate": 8.765854298595463e-06, "loss": 0.7255395412445068, "step": 7060, "token_acc": 0.7757366105295099 }, { "epoch": 0.45738886955677305, "grad_norm": 0.3286454379558563, "learning_rate": 8.76418146612573e-06, "loss": 0.7378214836120606, "step": 7065, "token_acc": 0.7726377768193666 }, { "epoch": 0.4577125701013992, "grad_norm": 0.3597126603126526, "learning_rate": 8.762507660545824e-06, "loss": 0.7089639663696289, "step": 7070, "token_acc": 0.7818202032621349 }, { "epoch": 0.45803627064602537, "grad_norm": 0.26505374908447266, "learning_rate": 8.760832882288456e-06, "loss": 0.7238893508911133, "step": 7075, "token_acc": 0.7766798924868809 }, { "epoch": 0.4583599711906515, "grad_norm": 0.29638999700546265, "learning_rate": 8.759157131786587e-06, "loss": 0.7753232002258301, "step": 7080, "token_acc": 0.7630096121975473 }, { "epoch": 0.4586836717352777, "grad_norm": 0.330782949924469, "learning_rate": 8.757480409473429e-06, "loss": 0.7142833232879638, "step": 7085, "token_acc": 0.7774821272024596 }, { "epoch": 0.45900737227990385, "grad_norm": 0.33453837037086487, "learning_rate": 8.755802715782445e-06, "loss": 0.7369888305664063, "step": 7090, "token_acc": 0.7736634784959386 }, { "epoch": 0.45933107282453, "grad_norm": 0.32279565930366516, "learning_rate": 8.75412405114735e-06, "loss": 0.7302018165588379, "step": 7095, "token_acc": 0.7735306103256951 }, { "epoch": 0.45965477336915617, "grad_norm": 0.37426403164863586, "learning_rate": 8.75244441600211e-06, "loss": 0.7444536685943604, "step": 7100, "token_acc": 0.7728326629938824 }, { "epoch": 0.4599784739137824, "grad_norm": 0.3077737092971802, "learning_rate": 8.750763810780941e-06, "loss": 0.7311462879180908, "step": 7105, "token_acc": 0.7757899613899614 }, { "epoch": 0.46030217445840854, "grad_norm": 0.3345005214214325, "learning_rate": 8.749082235918311e-06, "loss": 0.7386135578155517, "step": 7110, "token_acc": 0.7728862304555643 }, { "epoch": 0.4606258750030347, "grad_norm": 0.32441073656082153, "learning_rate": 8.74739969184894e-06, "loss": 0.7135906219482422, "step": 7115, "token_acc": 0.7786493608016767 }, { "epoch": 0.46094957554766086, "grad_norm": 0.37722253799438477, "learning_rate": 8.74571617900779e-06, "loss": 0.7585948944091797, "step": 7120, "token_acc": 0.7697293073015616 }, { "epoch": 0.461273276092287, "grad_norm": 0.3153426945209503, "learning_rate": 8.744031697830089e-06, "loss": 0.732717227935791, "step": 7125, "token_acc": 0.7759775315560812 }, { "epoch": 0.4615969766369132, "grad_norm": 0.3734087646007538, "learning_rate": 8.742346248751298e-06, "loss": 0.7585455894470214, "step": 7130, "token_acc": 0.7680593984513406 }, { "epoch": 0.46192067718153934, "grad_norm": 0.2876527011394501, "learning_rate": 8.740659832207144e-06, "loss": 0.733354139328003, "step": 7135, "token_acc": 0.7756941539426898 }, { "epoch": 0.4622443777261655, "grad_norm": 0.3836149573326111, "learning_rate": 8.738972448633591e-06, "loss": 0.7350052833557129, "step": 7140, "token_acc": 0.7753306878306878 }, { "epoch": 0.4625680782707917, "grad_norm": 0.3792794644832611, "learning_rate": 8.737284098466862e-06, "loss": 0.7153319835662841, "step": 7145, "token_acc": 0.7783509336506348 }, { "epoch": 0.4628917788154179, "grad_norm": 0.245896577835083, "learning_rate": 8.735594782143425e-06, "loss": 0.7254416942596436, "step": 7150, "token_acc": 0.7758053752350907 }, { "epoch": 0.46321547936004404, "grad_norm": 0.34703680872917175, "learning_rate": 8.7339045001e-06, "loss": 0.7298006534576416, "step": 7155, "token_acc": 0.774369367964828 }, { "epoch": 0.4635391799046702, "grad_norm": 0.3378243148326874, "learning_rate": 8.732213252773556e-06, "loss": 0.7238222122192383, "step": 7160, "token_acc": 0.7769981657024846 }, { "epoch": 0.46386288044929636, "grad_norm": 0.38326025009155273, "learning_rate": 8.730521040601311e-06, "loss": 0.7528732776641845, "step": 7165, "token_acc": 0.768974713750025 }, { "epoch": 0.4641865809939225, "grad_norm": 0.32092976570129395, "learning_rate": 8.728827864020732e-06, "loss": 0.7378933906555176, "step": 7170, "token_acc": 0.7737471421065337 }, { "epoch": 0.4645102815385487, "grad_norm": 0.2562826871871948, "learning_rate": 8.72713372346954e-06, "loss": 0.7413804054260253, "step": 7175, "token_acc": 0.7727182609474229 }, { "epoch": 0.46483398208317483, "grad_norm": 0.348671019077301, "learning_rate": 8.725438619385697e-06, "loss": 0.745553731918335, "step": 7180, "token_acc": 0.770594558193144 }, { "epoch": 0.465157682627801, "grad_norm": 0.3188018202781677, "learning_rate": 8.723742552207423e-06, "loss": 0.7221375942230225, "step": 7185, "token_acc": 0.7768062389863476 }, { "epoch": 0.4654813831724272, "grad_norm": 0.4276670813560486, "learning_rate": 8.72204552237318e-06, "loss": 0.7282296180725097, "step": 7190, "token_acc": 0.7748302732774881 }, { "epoch": 0.46580508371705337, "grad_norm": 0.39038917422294617, "learning_rate": 8.72034753032168e-06, "loss": 0.7310921669006347, "step": 7195, "token_acc": 0.7748136010960187 }, { "epoch": 0.46612878426167953, "grad_norm": 0.2803533971309662, "learning_rate": 8.718648576491889e-06, "loss": 0.7069942474365234, "step": 7200, "token_acc": 0.7801015651832589 }, { "epoch": 0.4664524848063057, "grad_norm": 0.3634547293186188, "learning_rate": 8.716948661323014e-06, "loss": 0.7047886848449707, "step": 7205, "token_acc": 0.7813689763950832 }, { "epoch": 0.46677618535093185, "grad_norm": 0.36389005184173584, "learning_rate": 8.715247785254517e-06, "loss": 0.7416224479675293, "step": 7210, "token_acc": 0.7734994409432812 }, { "epoch": 0.467099885895558, "grad_norm": 0.27264541387557983, "learning_rate": 8.713545948726105e-06, "loss": 0.7403824806213379, "step": 7215, "token_acc": 0.7718755775436801 }, { "epoch": 0.46742358644018417, "grad_norm": 0.2705870568752289, "learning_rate": 8.711843152177735e-06, "loss": 0.7254685401916504, "step": 7220, "token_acc": 0.776807165826793 }, { "epoch": 0.46774728698481033, "grad_norm": 0.33330780267715454, "learning_rate": 8.710139396049609e-06, "loss": 0.722419261932373, "step": 7225, "token_acc": 0.7776493007331805 }, { "epoch": 0.46807098752943654, "grad_norm": 0.3176495134830475, "learning_rate": 8.708434680782182e-06, "loss": 0.7367023468017578, "step": 7230, "token_acc": 0.7734154336725928 }, { "epoch": 0.4683946880740627, "grad_norm": 0.29769444465637207, "learning_rate": 8.70672900681615e-06, "loss": 0.7346791744232177, "step": 7235, "token_acc": 0.7733303303091942 }, { "epoch": 0.46871838861868886, "grad_norm": 0.31984347105026245, "learning_rate": 8.705022374592466e-06, "loss": 0.7173590660095215, "step": 7240, "token_acc": 0.776973063480884 }, { "epoch": 0.469042089163315, "grad_norm": 0.30152982473373413, "learning_rate": 8.703314784552323e-06, "loss": 0.7271594047546387, "step": 7245, "token_acc": 0.7759936225942375 }, { "epoch": 0.4693657897079412, "grad_norm": 0.3781645894050598, "learning_rate": 8.701606237137165e-06, "loss": 0.7500449180603027, "step": 7250, "token_acc": 0.7694646904969485 }, { "epoch": 0.46968949025256734, "grad_norm": 0.33728793263435364, "learning_rate": 8.699896732788682e-06, "loss": 0.7298801898956299, "step": 7255, "token_acc": 0.7765136919238179 }, { "epoch": 0.4700131907971935, "grad_norm": 0.29820966720581055, "learning_rate": 8.698186271948816e-06, "loss": 0.7273096084594727, "step": 7260, "token_acc": 0.7749251626629722 }, { "epoch": 0.47033689134181966, "grad_norm": 0.33616456389427185, "learning_rate": 8.69647485505975e-06, "loss": 0.7191568374633789, "step": 7265, "token_acc": 0.7778265684065829 }, { "epoch": 0.4706605918864458, "grad_norm": 0.36932018399238586, "learning_rate": 8.694762482563914e-06, "loss": 0.7532989025115967, "step": 7270, "token_acc": 0.7713470862249263 }, { "epoch": 0.47098429243107204, "grad_norm": 0.28893542289733887, "learning_rate": 8.693049154903993e-06, "loss": 0.7114723682403564, "step": 7275, "token_acc": 0.7793208343680159 }, { "epoch": 0.4713079929756982, "grad_norm": 0.33276620507240295, "learning_rate": 8.69133487252291e-06, "loss": 0.7170600414276123, "step": 7280, "token_acc": 0.7765837867002383 }, { "epoch": 0.47163169352032436, "grad_norm": 0.28388604521751404, "learning_rate": 8.689619635863841e-06, "loss": 0.7263010025024415, "step": 7285, "token_acc": 0.7760810545700779 }, { "epoch": 0.4719553940649505, "grad_norm": 0.27445414662361145, "learning_rate": 8.687903445370205e-06, "loss": 0.7473569869995117, "step": 7290, "token_acc": 0.7716544097419626 }, { "epoch": 0.4722790946095767, "grad_norm": 0.3289570212364197, "learning_rate": 8.686186301485668e-06, "loss": 0.7507019996643066, "step": 7295, "token_acc": 0.7696334432139462 }, { "epoch": 0.47260279515420284, "grad_norm": 0.29242005944252014, "learning_rate": 8.684468204654145e-06, "loss": 0.7453699111938477, "step": 7300, "token_acc": 0.7713127525777675 }, { "epoch": 0.472926495698829, "grad_norm": 0.30669811367988586, "learning_rate": 8.682749155319794e-06, "loss": 0.7272584915161133, "step": 7305, "token_acc": 0.7750883495429189 }, { "epoch": 0.47325019624345516, "grad_norm": 0.36447763442993164, "learning_rate": 8.681029153927023e-06, "loss": 0.7242580890655518, "step": 7310, "token_acc": 0.7754694515416863 }, { "epoch": 0.47357389678808137, "grad_norm": 0.30411216616630554, "learning_rate": 8.679308200920483e-06, "loss": 0.7077113628387451, "step": 7315, "token_acc": 0.7805422021648843 }, { "epoch": 0.47389759733270753, "grad_norm": 0.346680223941803, "learning_rate": 8.67758629674507e-06, "loss": 0.7363236904144287, "step": 7320, "token_acc": 0.7733539315955179 }, { "epoch": 0.4742212978773337, "grad_norm": 0.2942834496498108, "learning_rate": 8.675863441845931e-06, "loss": 0.7188056468963623, "step": 7325, "token_acc": 0.7772213857918858 }, { "epoch": 0.47454499842195985, "grad_norm": 0.3536609411239624, "learning_rate": 8.674139636668453e-06, "loss": 0.7162767887115479, "step": 7330, "token_acc": 0.7788761438329682 }, { "epoch": 0.474868698966586, "grad_norm": 0.3313062787055969, "learning_rate": 8.672414881658274e-06, "loss": 0.7362083435058594, "step": 7335, "token_acc": 0.7735777139590055 }, { "epoch": 0.47519239951121217, "grad_norm": 0.3922167122364044, "learning_rate": 8.670689177261273e-06, "loss": 0.7448938369750977, "step": 7340, "token_acc": 0.7726002709763576 }, { "epoch": 0.47551610005583833, "grad_norm": 0.35644954442977905, "learning_rate": 8.668962523923577e-06, "loss": 0.7525474548339843, "step": 7345, "token_acc": 0.7695748560334763 }, { "epoch": 0.4758398006004645, "grad_norm": 0.29999446868896484, "learning_rate": 8.66723492209156e-06, "loss": 0.7034809589385986, "step": 7350, "token_acc": 0.7812093628088427 }, { "epoch": 0.47616350114509065, "grad_norm": 0.2897339165210724, "learning_rate": 8.665506372211832e-06, "loss": 0.7153469085693359, "step": 7355, "token_acc": 0.7803314125814772 }, { "epoch": 0.47648720168971687, "grad_norm": 0.3501684069633484, "learning_rate": 8.663776874731263e-06, "loss": 0.7077465057373047, "step": 7360, "token_acc": 0.7793037775199673 }, { "epoch": 0.476810902234343, "grad_norm": 0.307882696390152, "learning_rate": 8.662046430096954e-06, "loss": 0.7149639129638672, "step": 7365, "token_acc": 0.7797362326477971 }, { "epoch": 0.4771346027789692, "grad_norm": 0.31252333521842957, "learning_rate": 8.66031503875626e-06, "loss": 0.6925961017608643, "step": 7370, "token_acc": 0.7855933390199499 }, { "epoch": 0.47745830332359535, "grad_norm": 0.24276381731033325, "learning_rate": 8.658582701156778e-06, "loss": 0.7197559833526611, "step": 7375, "token_acc": 0.7787264531152044 }, { "epoch": 0.4777820038682215, "grad_norm": 0.3101383447647095, "learning_rate": 8.656849417746347e-06, "loss": 0.7328402519226074, "step": 7380, "token_acc": 0.77502739316665 }, { "epoch": 0.47810570441284767, "grad_norm": 0.32640546560287476, "learning_rate": 8.655115188973053e-06, "loss": 0.7129056930541993, "step": 7385, "token_acc": 0.7803701380175658 }, { "epoch": 0.4784294049574738, "grad_norm": 0.28207361698150635, "learning_rate": 8.653380015285226e-06, "loss": 0.7073612213134766, "step": 7390, "token_acc": 0.7813912454210112 }, { "epoch": 0.4787531055021, "grad_norm": 0.3575875163078308, "learning_rate": 8.651643897131442e-06, "loss": 0.7242006301879883, "step": 7395, "token_acc": 0.7775278594818361 }, { "epoch": 0.4790768060467262, "grad_norm": 0.35474133491516113, "learning_rate": 8.64990683496052e-06, "loss": 0.7110791206359863, "step": 7400, "token_acc": 0.7794902929366798 }, { "epoch": 0.47940050659135236, "grad_norm": 0.24732382595539093, "learning_rate": 8.648168829221519e-06, "loss": 0.7271557807922363, "step": 7405, "token_acc": 0.7765654182640322 }, { "epoch": 0.4797242071359785, "grad_norm": 0.2727389633655548, "learning_rate": 8.646429880363746e-06, "loss": 0.7268882274627686, "step": 7410, "token_acc": 0.776302235748566 }, { "epoch": 0.4800479076806047, "grad_norm": 0.30033624172210693, "learning_rate": 8.644689988836754e-06, "loss": 0.742429542541504, "step": 7415, "token_acc": 0.7719184301042488 }, { "epoch": 0.48037160822523084, "grad_norm": 0.2907771170139313, "learning_rate": 8.642949155090337e-06, "loss": 0.7645539760589599, "step": 7420, "token_acc": 0.7675900971885432 }, { "epoch": 0.480695308769857, "grad_norm": 0.2717818021774292, "learning_rate": 8.641207379574529e-06, "loss": 0.7327534675598144, "step": 7425, "token_acc": 0.7743361563704627 }, { "epoch": 0.48101900931448316, "grad_norm": 0.34415319561958313, "learning_rate": 8.639464662739614e-06, "loss": 0.7584229946136475, "step": 7430, "token_acc": 0.7680896780515448 }, { "epoch": 0.4813427098591093, "grad_norm": 0.3355472683906555, "learning_rate": 8.637721005036115e-06, "loss": 0.7384639263153077, "step": 7435, "token_acc": 0.773478918192508 }, { "epoch": 0.4816664104037355, "grad_norm": 0.2733626663684845, "learning_rate": 8.6359764069148e-06, "loss": 0.6927659034729003, "step": 7440, "token_acc": 0.7837272188472366 }, { "epoch": 0.4819901109483617, "grad_norm": 0.2568553686141968, "learning_rate": 8.634230868826681e-06, "loss": 0.7254952430725098, "step": 7445, "token_acc": 0.776522517517054 }, { "epoch": 0.48231381149298785, "grad_norm": 0.355074018239975, "learning_rate": 8.632484391223009e-06, "loss": 0.7369062423706054, "step": 7450, "token_acc": 0.7730365340737279 }, { "epoch": 0.482637512037614, "grad_norm": 0.3690916895866394, "learning_rate": 8.630736974555284e-06, "loss": 0.7317777633666992, "step": 7455, "token_acc": 0.7738872829541079 }, { "epoch": 0.4829612125822402, "grad_norm": 0.3059186637401581, "learning_rate": 8.628988619275243e-06, "loss": 0.714203929901123, "step": 7460, "token_acc": 0.7795748993398888 }, { "epoch": 0.48328491312686633, "grad_norm": 0.37797489762306213, "learning_rate": 8.627239325834868e-06, "loss": 0.7234478950500488, "step": 7465, "token_acc": 0.7764669254514381 }, { "epoch": 0.4836086136714925, "grad_norm": 0.36215606331825256, "learning_rate": 8.625489094686383e-06, "loss": 0.7321911811828613, "step": 7470, "token_acc": 0.7767368027888446 }, { "epoch": 0.48393231421611865, "grad_norm": 0.35627198219299316, "learning_rate": 8.623737926282257e-06, "loss": 0.7399896621704102, "step": 7475, "token_acc": 0.7723666191842661 }, { "epoch": 0.4842560147607448, "grad_norm": 0.2924339175224304, "learning_rate": 8.6219858210752e-06, "loss": 0.7060407638549805, "step": 7480, "token_acc": 0.780522082164761 }, { "epoch": 0.48457971530537103, "grad_norm": 0.31774434447288513, "learning_rate": 8.62023277951816e-06, "loss": 0.7218176841735839, "step": 7485, "token_acc": 0.7773506527759462 }, { "epoch": 0.4849034158499972, "grad_norm": 0.318968266248703, "learning_rate": 8.618478802064331e-06, "loss": 0.7188496589660645, "step": 7490, "token_acc": 0.777228543533125 }, { "epoch": 0.48522711639462335, "grad_norm": 0.39045003056526184, "learning_rate": 8.616723889167152e-06, "loss": 0.7301769733428956, "step": 7495, "token_acc": 0.7748329469521342 }, { "epoch": 0.4855508169392495, "grad_norm": 0.3264017701148987, "learning_rate": 8.614968041280297e-06, "loss": 0.7085381507873535, "step": 7500, "token_acc": 0.7814540539511508 }, { "epoch": 0.48587451748387567, "grad_norm": 0.3679475784301758, "learning_rate": 8.613211258857686e-06, "loss": 0.7179369926452637, "step": 7505, "token_acc": 0.7780796728555157 }, { "epoch": 0.4861982180285018, "grad_norm": 0.3820839524269104, "learning_rate": 8.61145354235348e-06, "loss": 0.7230009078979492, "step": 7510, "token_acc": 0.7771724588994262 }, { "epoch": 0.486521918573128, "grad_norm": 0.3611642122268677, "learning_rate": 8.60969489222208e-06, "loss": 0.7179866790771484, "step": 7515, "token_acc": 0.7769212429468331 }, { "epoch": 0.48684561911775415, "grad_norm": 0.27970659732818604, "learning_rate": 8.60793530891813e-06, "loss": 0.7313918113708496, "step": 7520, "token_acc": 0.7746166390655221 }, { "epoch": 0.4871693196623803, "grad_norm": 0.33458366990089417, "learning_rate": 8.606174792896515e-06, "loss": 0.7160063266754151, "step": 7525, "token_acc": 0.7784393505500629 }, { "epoch": 0.4874930202070065, "grad_norm": 0.3379761278629303, "learning_rate": 8.60441334461236e-06, "loss": 0.7397793769836426, "step": 7530, "token_acc": 0.7723147579158446 }, { "epoch": 0.4878167207516327, "grad_norm": 0.2530553638935089, "learning_rate": 8.602650964521033e-06, "loss": 0.7295376777648925, "step": 7535, "token_acc": 0.7758160528968372 }, { "epoch": 0.48814042129625884, "grad_norm": 0.32262158393859863, "learning_rate": 8.60088765307814e-06, "loss": 0.7677196025848388, "step": 7540, "token_acc": 0.7657866077239833 }, { "epoch": 0.488464121840885, "grad_norm": 0.28920936584472656, "learning_rate": 8.599123410739532e-06, "loss": 0.7216648578643798, "step": 7545, "token_acc": 0.7782973492945703 }, { "epoch": 0.48878782238551116, "grad_norm": 0.3372686505317688, "learning_rate": 8.597358237961294e-06, "loss": 0.7137586593627929, "step": 7550, "token_acc": 0.7792356027650146 }, { "epoch": 0.4891115229301373, "grad_norm": 0.3436397910118103, "learning_rate": 8.59559213519976e-06, "loss": 0.7230586528778076, "step": 7555, "token_acc": 0.7762160403448837 }, { "epoch": 0.4894352234747635, "grad_norm": 0.32276609539985657, "learning_rate": 8.593825102911497e-06, "loss": 0.7460453987121582, "step": 7560, "token_acc": 0.7722604932264591 }, { "epoch": 0.48975892401938964, "grad_norm": 0.3820543885231018, "learning_rate": 8.592057141553316e-06, "loss": 0.720996618270874, "step": 7565, "token_acc": 0.7754037555057569 }, { "epoch": 0.49008262456401586, "grad_norm": 0.308052122592926, "learning_rate": 8.59028825158227e-06, "loss": 0.7232877731323242, "step": 7570, "token_acc": 0.7787027309167074 }, { "epoch": 0.490406325108642, "grad_norm": 0.3027189075946808, "learning_rate": 8.588518433455646e-06, "loss": 0.7061433792114258, "step": 7575, "token_acc": 0.7816847134985164 }, { "epoch": 0.4907300256532682, "grad_norm": 0.3580743968486786, "learning_rate": 8.586747687630978e-06, "loss": 0.7105226516723633, "step": 7580, "token_acc": 0.7793249655079584 }, { "epoch": 0.49105372619789434, "grad_norm": 0.3160305321216583, "learning_rate": 8.584976014566034e-06, "loss": 0.7103857517242431, "step": 7585, "token_acc": 0.7805440295066851 }, { "epoch": 0.4913774267425205, "grad_norm": 0.3836548924446106, "learning_rate": 8.583203414718824e-06, "loss": 0.6882116317749023, "step": 7590, "token_acc": 0.7862829838200251 }, { "epoch": 0.49170112728714666, "grad_norm": 0.4635947048664093, "learning_rate": 8.581429888547599e-06, "loss": 0.7236625671386718, "step": 7595, "token_acc": 0.7763263332412269 }, { "epoch": 0.4920248278317728, "grad_norm": 0.3295288681983948, "learning_rate": 8.579655436510847e-06, "loss": 0.718168067932129, "step": 7600, "token_acc": 0.7783076074972437 }, { "epoch": 0.492348528376399, "grad_norm": 0.2399771511554718, "learning_rate": 8.577880059067297e-06, "loss": 0.7343140602111816, "step": 7605, "token_acc": 0.7732818691078016 }, { "epoch": 0.49267222892102513, "grad_norm": 0.32807156443595886, "learning_rate": 8.576103756675918e-06, "loss": 0.7265021800994873, "step": 7610, "token_acc": 0.7768002692731605 }, { "epoch": 0.49299592946565135, "grad_norm": 0.319618821144104, "learning_rate": 8.574326529795915e-06, "loss": 0.7482998847961426, "step": 7615, "token_acc": 0.7717877147066686 }, { "epoch": 0.4933196300102775, "grad_norm": 0.35488221049308777, "learning_rate": 8.572548378886734e-06, "loss": 0.7309318542480469, "step": 7620, "token_acc": 0.7753325157364809 }, { "epoch": 0.49364333055490367, "grad_norm": 0.3403109908103943, "learning_rate": 8.57076930440806e-06, "loss": 0.7270782947540283, "step": 7625, "token_acc": 0.7764655453690493 }, { "epoch": 0.49396703109952983, "grad_norm": 0.2992241680622101, "learning_rate": 8.568989306819817e-06, "loss": 0.7200432777404785, "step": 7630, "token_acc": 0.7777273004658227 }, { "epoch": 0.494290731644156, "grad_norm": 0.22273290157318115, "learning_rate": 8.567208386582168e-06, "loss": 0.7508433341979981, "step": 7635, "token_acc": 0.7723248165949912 }, { "epoch": 0.49461443218878215, "grad_norm": 0.34116530418395996, "learning_rate": 8.565426544155511e-06, "loss": 0.703242015838623, "step": 7640, "token_acc": 0.7807525058962265 }, { "epoch": 0.4949381327334083, "grad_norm": 0.33680593967437744, "learning_rate": 8.563643780000488e-06, "loss": 0.7310538768768311, "step": 7645, "token_acc": 0.7753916563985214 }, { "epoch": 0.49526183327803447, "grad_norm": 0.24313871562480927, "learning_rate": 8.561860094577973e-06, "loss": 0.7064368247985839, "step": 7650, "token_acc": 0.7819697355189668 }, { "epoch": 0.4955855338226607, "grad_norm": 0.36686602234840393, "learning_rate": 8.560075488349085e-06, "loss": 0.7353762626647949, "step": 7655, "token_acc": 0.7740100253856166 }, { "epoch": 0.49590923436728684, "grad_norm": 0.36244475841522217, "learning_rate": 8.558289961775175e-06, "loss": 0.7057140350341797, "step": 7660, "token_acc": 0.7817509732726867 }, { "epoch": 0.496232934911913, "grad_norm": 0.3769449293613434, "learning_rate": 8.556503515317835e-06, "loss": 0.7383426189422607, "step": 7665, "token_acc": 0.7745126064833343 }, { "epoch": 0.49655663545653916, "grad_norm": 0.25474074482917786, "learning_rate": 8.554716149438896e-06, "loss": 0.7212244987487793, "step": 7670, "token_acc": 0.7784284772199443 }, { "epoch": 0.4968803360011653, "grad_norm": 0.2769406735897064, "learning_rate": 8.552927864600422e-06, "loss": 0.7213240146636963, "step": 7675, "token_acc": 0.7760786416443253 }, { "epoch": 0.4972040365457915, "grad_norm": 0.23823687434196472, "learning_rate": 8.55113866126472e-06, "loss": 0.7150887012481689, "step": 7680, "token_acc": 0.7789484840738916 }, { "epoch": 0.49752773709041764, "grad_norm": 0.2998489737510681, "learning_rate": 8.549348539894331e-06, "loss": 0.7169617176055908, "step": 7685, "token_acc": 0.778275454458324 }, { "epoch": 0.4978514376350438, "grad_norm": 0.3231947720050812, "learning_rate": 8.547557500952034e-06, "loss": 0.7215970993041992, "step": 7690, "token_acc": 0.7762037042740202 }, { "epoch": 0.49817513817966996, "grad_norm": 0.2964543402194977, "learning_rate": 8.545765544900847e-06, "loss": 0.7230289936065674, "step": 7695, "token_acc": 0.7763989212228656 }, { "epoch": 0.4984988387242962, "grad_norm": 0.3348003029823303, "learning_rate": 8.543972672204022e-06, "loss": 0.7500216007232666, "step": 7700, "token_acc": 0.7702582957506183 }, { "epoch": 0.49882253926892234, "grad_norm": 0.21540570259094238, "learning_rate": 8.542178883325052e-06, "loss": 0.752434253692627, "step": 7705, "token_acc": 0.7690634206351775 }, { "epoch": 0.4991462398135485, "grad_norm": 0.3774763345718384, "learning_rate": 8.54038417872766e-06, "loss": 0.7160764694213867, "step": 7710, "token_acc": 0.7794297046754822 }, { "epoch": 0.49946994035817466, "grad_norm": 0.3492315113544464, "learning_rate": 8.538588558875814e-06, "loss": 0.7169010162353515, "step": 7715, "token_acc": 0.7780997518086286 }, { "epoch": 0.4997936409028008, "grad_norm": 0.33352553844451904, "learning_rate": 8.536792024233713e-06, "loss": 0.6947062969207763, "step": 7720, "token_acc": 0.7835071392062238 }, { "epoch": 0.500117341447427, "grad_norm": 0.3805858790874481, "learning_rate": 8.534994575265796e-06, "loss": 0.7196789741516113, "step": 7725, "token_acc": 0.7783147186407599 }, { "epoch": 0.5004410419920532, "grad_norm": 0.2748148441314697, "learning_rate": 8.533196212436735e-06, "loss": 0.7278986930847168, "step": 7730, "token_acc": 0.7758300552911727 }, { "epoch": 0.5007647425366794, "grad_norm": 0.249155655503273, "learning_rate": 8.53139693621144e-06, "loss": 0.740022611618042, "step": 7735, "token_acc": 0.7737560219654348 }, { "epoch": 0.5010884430813055, "grad_norm": 0.3577895164489746, "learning_rate": 8.529596747055058e-06, "loss": 0.6925640106201172, "step": 7740, "token_acc": 0.7849048926864002 }, { "epoch": 0.5014121436259317, "grad_norm": 0.24813270568847656, "learning_rate": 8.527795645432968e-06, "loss": 0.7388140678405761, "step": 7745, "token_acc": 0.7743385717127511 }, { "epoch": 0.5017358441705578, "grad_norm": 0.32636043429374695, "learning_rate": 8.525993631810793e-06, "loss": 0.7282320976257324, "step": 7750, "token_acc": 0.7752082968042757 }, { "epoch": 0.502059544715184, "grad_norm": 0.27802228927612305, "learning_rate": 8.524190706654383e-06, "loss": 0.7166013717651367, "step": 7755, "token_acc": 0.7787796720165739 }, { "epoch": 0.5023832452598102, "grad_norm": 0.3178902566432953, "learning_rate": 8.522386870429829e-06, "loss": 0.7220643043518067, "step": 7760, "token_acc": 0.7776785170446471 }, { "epoch": 0.5027069458044363, "grad_norm": 0.35057172179222107, "learning_rate": 8.520582123603454e-06, "loss": 0.7159008979797363, "step": 7765, "token_acc": 0.7791027351567712 }, { "epoch": 0.5030306463490625, "grad_norm": 0.3125157356262207, "learning_rate": 8.518776466641821e-06, "loss": 0.7195859909057617, "step": 7770, "token_acc": 0.7790349945683352 }, { "epoch": 0.5033543468936886, "grad_norm": 0.40603721141815186, "learning_rate": 8.51696990001172e-06, "loss": 0.7349606037139893, "step": 7775, "token_acc": 0.7728907403850611 }, { "epoch": 0.5036780474383148, "grad_norm": 0.3267045319080353, "learning_rate": 8.51516242418019e-06, "loss": 0.7033059120178222, "step": 7780, "token_acc": 0.780764922387582 }, { "epoch": 0.504001747982941, "grad_norm": 0.21467211842536926, "learning_rate": 8.51335403961449e-06, "loss": 0.7230311870574951, "step": 7785, "token_acc": 0.7767561963262192 }, { "epoch": 0.5043254485275671, "grad_norm": 0.23998239636421204, "learning_rate": 8.511544746782124e-06, "loss": 0.7554429531097412, "step": 7790, "token_acc": 0.7699595412571876 }, { "epoch": 0.5046491490721933, "grad_norm": 0.38544195890426636, "learning_rate": 8.509734546150828e-06, "loss": 0.7347024440765381, "step": 7795, "token_acc": 0.7736771508442918 }, { "epoch": 0.5049728496168194, "grad_norm": 0.33054444193840027, "learning_rate": 8.50792343818857e-06, "loss": 0.7369155883789062, "step": 7800, "token_acc": 0.773442259229097 }, { "epoch": 0.5052965501614457, "grad_norm": 0.32268500328063965, "learning_rate": 8.506111423363555e-06, "loss": 0.7077400207519531, "step": 7805, "token_acc": 0.7797598627787307 }, { "epoch": 0.5056202507060719, "grad_norm": 0.3164202570915222, "learning_rate": 8.504298502144222e-06, "loss": 0.7270961284637452, "step": 7810, "token_acc": 0.7763564417218852 }, { "epoch": 0.505943951250698, "grad_norm": 0.3067602813243866, "learning_rate": 8.502484674999244e-06, "loss": 0.7366915702819824, "step": 7815, "token_acc": 0.7722643497262074 }, { "epoch": 0.5062676517953242, "grad_norm": 0.29189151525497437, "learning_rate": 8.500669942397532e-06, "loss": 0.7274762153625488, "step": 7820, "token_acc": 0.7757976251935983 }, { "epoch": 0.5065913523399503, "grad_norm": 0.3306396007537842, "learning_rate": 8.498854304808226e-06, "loss": 0.7002435207366944, "step": 7825, "token_acc": 0.7830388128764609 }, { "epoch": 0.5069150528845765, "grad_norm": 0.2928186058998108, "learning_rate": 8.4970377627007e-06, "loss": 0.7316717624664306, "step": 7830, "token_acc": 0.7752206042443104 }, { "epoch": 0.5072387534292027, "grad_norm": 0.2668305039405823, "learning_rate": 8.495220316544567e-06, "loss": 0.7348612785339356, "step": 7835, "token_acc": 0.7743240366191186 }, { "epoch": 0.5075624539738288, "grad_norm": 0.2784634828567505, "learning_rate": 8.493401966809667e-06, "loss": 0.725911283493042, "step": 7840, "token_acc": 0.7768937205123158 }, { "epoch": 0.507886154518455, "grad_norm": 0.3391234874725342, "learning_rate": 8.491582713966078e-06, "loss": 0.7191521644592285, "step": 7845, "token_acc": 0.7777258992949714 }, { "epoch": 0.5082098550630811, "grad_norm": 0.3569187819957733, "learning_rate": 8.489762558484108e-06, "loss": 0.7436305999755859, "step": 7850, "token_acc": 0.7715199600667306 }, { "epoch": 0.5085335556077073, "grad_norm": 0.38456910848617554, "learning_rate": 8.487941500834306e-06, "loss": 0.731657886505127, "step": 7855, "token_acc": 0.7758184278158643 }, { "epoch": 0.5088572561523335, "grad_norm": 0.2781025469303131, "learning_rate": 8.486119541487447e-06, "loss": 0.7194704055786133, "step": 7860, "token_acc": 0.7775500296671881 }, { "epoch": 0.5091809566969596, "grad_norm": 0.32215091586112976, "learning_rate": 8.484296680914538e-06, "loss": 0.7340805053710937, "step": 7865, "token_acc": 0.7738590753679203 }, { "epoch": 0.5095046572415858, "grad_norm": 0.2980114817619324, "learning_rate": 8.482472919586824e-06, "loss": 0.7314675331115723, "step": 7870, "token_acc": 0.7731163631343115 }, { "epoch": 0.5098283577862119, "grad_norm": 0.30388373136520386, "learning_rate": 8.480648257975781e-06, "loss": 0.7281493663787841, "step": 7875, "token_acc": 0.7753607640931585 }, { "epoch": 0.5101520583308381, "grad_norm": 0.3429846167564392, "learning_rate": 8.478822696553117e-06, "loss": 0.7136037349700928, "step": 7880, "token_acc": 0.7793628653211786 }, { "epoch": 0.5104757588754643, "grad_norm": 0.2881467938423157, "learning_rate": 8.476996235790775e-06, "loss": 0.7183002471923828, "step": 7885, "token_acc": 0.7782858114693512 }, { "epoch": 0.5107994594200905, "grad_norm": 0.4104873538017273, "learning_rate": 8.475168876160927e-06, "loss": 0.7278268337249756, "step": 7890, "token_acc": 0.7758295277565135 }, { "epoch": 0.5111231599647167, "grad_norm": 0.2985634505748749, "learning_rate": 8.47334061813598e-06, "loss": 0.7257148742675781, "step": 7895, "token_acc": 0.7763343235290016 }, { "epoch": 0.5114468605093428, "grad_norm": 0.3181833028793335, "learning_rate": 8.471511462188571e-06, "loss": 0.745460319519043, "step": 7900, "token_acc": 0.7709550840522935 }, { "epoch": 0.511770561053969, "grad_norm": 0.32455721497535706, "learning_rate": 8.46968140879157e-06, "loss": 0.7083456993103028, "step": 7905, "token_acc": 0.7806410477797112 }, { "epoch": 0.5120942615985952, "grad_norm": 0.3318222165107727, "learning_rate": 8.467850458418084e-06, "loss": 0.7077003002166748, "step": 7910, "token_acc": 0.7784175815417721 }, { "epoch": 0.5124179621432213, "grad_norm": 0.3505253791809082, "learning_rate": 8.466018611541443e-06, "loss": 0.7161325931549072, "step": 7915, "token_acc": 0.7793350652767272 }, { "epoch": 0.5127416626878475, "grad_norm": 0.264869749546051, "learning_rate": 8.464185868635213e-06, "loss": 0.7287005424499512, "step": 7920, "token_acc": 0.776096100294779 }, { "epoch": 0.5130653632324736, "grad_norm": 0.47360944747924805, "learning_rate": 8.462352230173193e-06, "loss": 0.7405227661132813, "step": 7925, "token_acc": 0.772136797454931 }, { "epoch": 0.5133890637770998, "grad_norm": 0.3761557638645172, "learning_rate": 8.460517696629413e-06, "loss": 0.7010916709899903, "step": 7930, "token_acc": 0.7832343535861124 }, { "epoch": 0.513712764321726, "grad_norm": 0.26094427704811096, "learning_rate": 8.458682268478133e-06, "loss": 0.7385284423828125, "step": 7935, "token_acc": 0.7738550804272883 }, { "epoch": 0.5140364648663521, "grad_norm": 0.3514659106731415, "learning_rate": 8.456845946193846e-06, "loss": 0.7397677421569824, "step": 7940, "token_acc": 0.7721727060198714 }, { "epoch": 0.5143601654109783, "grad_norm": 0.34777316451072693, "learning_rate": 8.455008730251273e-06, "loss": 0.7031905651092529, "step": 7945, "token_acc": 0.7815933789326013 }, { "epoch": 0.5146838659556044, "grad_norm": 0.37632569670677185, "learning_rate": 8.453170621125368e-06, "loss": 0.746152114868164, "step": 7950, "token_acc": 0.7716124652729764 }, { "epoch": 0.5150075665002306, "grad_norm": 0.39355534315109253, "learning_rate": 8.451331619291319e-06, "loss": 0.7311530113220215, "step": 7955, "token_acc": 0.7741752869126654 }, { "epoch": 0.5153312670448568, "grad_norm": 0.3225843608379364, "learning_rate": 8.44949172522454e-06, "loss": 0.6839897155761718, "step": 7960, "token_acc": 0.7871327003697572 }, { "epoch": 0.5156549675894829, "grad_norm": 0.3197377920150757, "learning_rate": 8.447650939400676e-06, "loss": 0.703974723815918, "step": 7965, "token_acc": 0.781749979027097 }, { "epoch": 0.5159786681341091, "grad_norm": 0.3555358946323395, "learning_rate": 8.445809262295608e-06, "loss": 0.7156561851501465, "step": 7970, "token_acc": 0.779394677142699 }, { "epoch": 0.5163023686787354, "grad_norm": 0.29046714305877686, "learning_rate": 8.443966694385438e-06, "loss": 0.7190324783325195, "step": 7975, "token_acc": 0.7772836448247392 }, { "epoch": 0.5166260692233615, "grad_norm": 0.40294763445854187, "learning_rate": 8.442123236146509e-06, "loss": 0.7087681770324707, "step": 7980, "token_acc": 0.7809733780893929 }, { "epoch": 0.5169497697679877, "grad_norm": 0.30017656087875366, "learning_rate": 8.440278888055384e-06, "loss": 0.7026546955108642, "step": 7985, "token_acc": 0.7817353974242227 }, { "epoch": 0.5172734703126138, "grad_norm": 0.2973948121070862, "learning_rate": 8.438433650588865e-06, "loss": 0.714244031906128, "step": 7990, "token_acc": 0.7808735235254876 }, { "epoch": 0.51759717085724, "grad_norm": 0.3714640438556671, "learning_rate": 8.436587524223977e-06, "loss": 0.7332727909088135, "step": 7995, "token_acc": 0.7747916823061332 }, { "epoch": 0.5179208714018662, "grad_norm": 0.27598515152931213, "learning_rate": 8.434740509437981e-06, "loss": 0.7570387840270996, "step": 8000, "token_acc": 0.7685998342999172 }, { "epoch": 0.5182445719464923, "grad_norm": 0.3476305603981018, "learning_rate": 8.432892606708363e-06, "loss": 0.7109724521636963, "step": 8005, "token_acc": 0.7801445165043666 }, { "epoch": 0.5185682724911185, "grad_norm": 0.3312680721282959, "learning_rate": 8.431043816512836e-06, "loss": 0.6853629112243652, "step": 8010, "token_acc": 0.7866919297344166 }, { "epoch": 0.5188919730357446, "grad_norm": 0.3489920496940613, "learning_rate": 8.429194139329352e-06, "loss": 0.7255148887634277, "step": 8015, "token_acc": 0.7767708513670081 }, { "epoch": 0.5192156735803708, "grad_norm": 0.36220210790634155, "learning_rate": 8.427343575636082e-06, "loss": 0.7464191913604736, "step": 8020, "token_acc": 0.7716282596091973 }, { "epoch": 0.519539374124997, "grad_norm": 0.35747745633125305, "learning_rate": 8.425492125911431e-06, "loss": 0.7440428733825684, "step": 8025, "token_acc": 0.7721924337205839 }, { "epoch": 0.5198630746696231, "grad_norm": 0.3123791515827179, "learning_rate": 8.42363979063404e-06, "loss": 0.7336483001708984, "step": 8030, "token_acc": 0.77536494148872 }, { "epoch": 0.5201867752142493, "grad_norm": 0.3378223180770874, "learning_rate": 8.421786570282761e-06, "loss": 0.7434004306793213, "step": 8035, "token_acc": 0.7734402768370296 }, { "epoch": 0.5205104757588754, "grad_norm": 0.30943718552589417, "learning_rate": 8.419932465336694e-06, "loss": 0.7041497230529785, "step": 8040, "token_acc": 0.7821609286635579 }, { "epoch": 0.5208341763035016, "grad_norm": 0.2311657816171646, "learning_rate": 8.418077476275154e-06, "loss": 0.6909452438354492, "step": 8045, "token_acc": 0.7840122278493495 }, { "epoch": 0.5211578768481278, "grad_norm": 0.2549237012863159, "learning_rate": 8.416221603577692e-06, "loss": 0.7292591094970703, "step": 8050, "token_acc": 0.7757313310783184 }, { "epoch": 0.5214815773927539, "grad_norm": 0.30805525183677673, "learning_rate": 8.414364847724087e-06, "loss": 0.7335431098937988, "step": 8055, "token_acc": 0.7747181423422355 }, { "epoch": 0.5218052779373801, "grad_norm": 0.38069450855255127, "learning_rate": 8.412507209194341e-06, "loss": 0.7454710960388183, "step": 8060, "token_acc": 0.770992883309295 }, { "epoch": 0.5221289784820063, "grad_norm": 0.34367290139198303, "learning_rate": 8.41064868846869e-06, "loss": 0.7058260917663575, "step": 8065, "token_acc": 0.7812145589281563 }, { "epoch": 0.5224526790266325, "grad_norm": 0.2979225814342499, "learning_rate": 8.408789286027597e-06, "loss": 0.7127815246582031, "step": 8070, "token_acc": 0.779268787060513 }, { "epoch": 0.5227763795712587, "grad_norm": 0.3198571503162384, "learning_rate": 8.406929002351746e-06, "loss": 0.710666561126709, "step": 8075, "token_acc": 0.7798542507901033 }, { "epoch": 0.5231000801158848, "grad_norm": 0.43449774384498596, "learning_rate": 8.405067837922063e-06, "loss": 0.7162444114685058, "step": 8080, "token_acc": 0.7782215751088725 }, { "epoch": 0.523423780660511, "grad_norm": 0.34884902834892273, "learning_rate": 8.403205793219685e-06, "loss": 0.7517850875854493, "step": 8085, "token_acc": 0.7694362078765177 }, { "epoch": 0.5237474812051371, "grad_norm": 0.32751867175102234, "learning_rate": 8.40134286872599e-06, "loss": 0.7251294136047364, "step": 8090, "token_acc": 0.77693068543829 }, { "epoch": 0.5240711817497633, "grad_norm": 0.28462326526641846, "learning_rate": 8.399479064922577e-06, "loss": 0.715778112411499, "step": 8095, "token_acc": 0.780151535651468 }, { "epoch": 0.5243948822943895, "grad_norm": 0.2671545743942261, "learning_rate": 8.397614382291274e-06, "loss": 0.6918652534484864, "step": 8100, "token_acc": 0.7862030494607661 }, { "epoch": 0.5247185828390156, "grad_norm": 0.3161453604698181, "learning_rate": 8.395748821314135e-06, "loss": 0.735614538192749, "step": 8105, "token_acc": 0.775177900610038 }, { "epoch": 0.5250422833836418, "grad_norm": 0.36445745825767517, "learning_rate": 8.393882382473441e-06, "loss": 0.7301141738891601, "step": 8110, "token_acc": 0.7752169733047108 }, { "epoch": 0.5253659839282679, "grad_norm": 0.2857678532600403, "learning_rate": 8.392015066251703e-06, "loss": 0.7290078163146972, "step": 8115, "token_acc": 0.773215353667156 }, { "epoch": 0.5256896844728941, "grad_norm": 0.29898837208747864, "learning_rate": 8.390146873131656e-06, "loss": 0.7003008842468261, "step": 8120, "token_acc": 0.7841880201525233 }, { "epoch": 0.5260133850175203, "grad_norm": 0.29893720149993896, "learning_rate": 8.38827780359626e-06, "loss": 0.7035915374755859, "step": 8125, "token_acc": 0.7809054047371804 }, { "epoch": 0.5263370855621464, "grad_norm": 0.37036025524139404, "learning_rate": 8.386407858128707e-06, "loss": 0.7077181816101075, "step": 8130, "token_acc": 0.7801227234153666 }, { "epoch": 0.5266607861067726, "grad_norm": 0.3917335569858551, "learning_rate": 8.384537037212409e-06, "loss": 0.6896116256713867, "step": 8135, "token_acc": 0.7844558356503749 }, { "epoch": 0.5269844866513987, "grad_norm": 0.23919977247714996, "learning_rate": 8.382665341331011e-06, "loss": 0.7197952270507812, "step": 8140, "token_acc": 0.7781701078308938 }, { "epoch": 0.5273081871960249, "grad_norm": 0.3701108396053314, "learning_rate": 8.38079277096838e-06, "loss": 0.7301431179046631, "step": 8145, "token_acc": 0.7747983746209856 }, { "epoch": 0.5276318877406512, "grad_norm": 0.2134304791688919, "learning_rate": 8.378919326608607e-06, "loss": 0.7265449523925781, "step": 8150, "token_acc": 0.7769516496160485 }, { "epoch": 0.5279555882852773, "grad_norm": 0.29255345463752747, "learning_rate": 8.377045008736016e-06, "loss": 0.7054561614990235, "step": 8155, "token_acc": 0.7808294509459843 }, { "epoch": 0.5282792888299035, "grad_norm": 0.31790414452552795, "learning_rate": 8.37516981783515e-06, "loss": 0.7399944305419922, "step": 8160, "token_acc": 0.7726455871251344 }, { "epoch": 0.5286029893745297, "grad_norm": 0.3371061086654663, "learning_rate": 8.373293754390783e-06, "loss": 0.7220523834228516, "step": 8165, "token_acc": 0.7774791854565088 }, { "epoch": 0.5289266899191558, "grad_norm": 0.27833351492881775, "learning_rate": 8.371416818887907e-06, "loss": 0.7096945762634277, "step": 8170, "token_acc": 0.781448403371878 }, { "epoch": 0.529250390463782, "grad_norm": 0.3504354953765869, "learning_rate": 8.36953901181175e-06, "loss": 0.7236246109008789, "step": 8175, "token_acc": 0.7773160449923081 }, { "epoch": 0.5295740910084081, "grad_norm": 0.33741143345832825, "learning_rate": 8.367660333647755e-06, "loss": 0.7529371738433838, "step": 8180, "token_acc": 0.7691987079295614 }, { "epoch": 0.5298977915530343, "grad_norm": 0.26804742217063904, "learning_rate": 8.365780784881597e-06, "loss": 0.6807032585144043, "step": 8185, "token_acc": 0.7871813937613515 }, { "epoch": 0.5302214920976605, "grad_norm": 0.3132619261741638, "learning_rate": 8.363900365999175e-06, "loss": 0.7275388717651368, "step": 8190, "token_acc": 0.7750948557600627 }, { "epoch": 0.5305451926422866, "grad_norm": 0.29658785462379456, "learning_rate": 8.36201907748661e-06, "loss": 0.7098901748657227, "step": 8195, "token_acc": 0.7793463833296821 }, { "epoch": 0.5308688931869128, "grad_norm": 0.30776235461235046, "learning_rate": 8.360136919830252e-06, "loss": 0.7038509368896484, "step": 8200, "token_acc": 0.782182797402186 }, { "epoch": 0.5311925937315389, "grad_norm": 0.319026917219162, "learning_rate": 8.35825389351667e-06, "loss": 0.7208901405334472, "step": 8205, "token_acc": 0.7757226411289011 }, { "epoch": 0.5315162942761651, "grad_norm": 0.2761310040950775, "learning_rate": 8.356369999032664e-06, "loss": 0.70390625, "step": 8210, "token_acc": 0.7799954440692501 }, { "epoch": 0.5318399948207913, "grad_norm": 0.2708093523979187, "learning_rate": 8.354485236865254e-06, "loss": 0.7231690406799316, "step": 8215, "token_acc": 0.7772492929730315 }, { "epoch": 0.5321636953654174, "grad_norm": 0.37704572081565857, "learning_rate": 8.352599607501685e-06, "loss": 0.7260942459106445, "step": 8220, "token_acc": 0.7753409970814223 }, { "epoch": 0.5324873959100436, "grad_norm": 0.3356550335884094, "learning_rate": 8.350713111429429e-06, "loss": 0.6991239547729492, "step": 8225, "token_acc": 0.7827049115722973 }, { "epoch": 0.5328110964546697, "grad_norm": 0.26515936851501465, "learning_rate": 8.34882574913618e-06, "loss": 0.7286260604858399, "step": 8230, "token_acc": 0.7761963881173926 }, { "epoch": 0.533134796999296, "grad_norm": 0.31351739168167114, "learning_rate": 8.346937521109852e-06, "loss": 0.7168455123901367, "step": 8235, "token_acc": 0.7784870986698007 }, { "epoch": 0.5334584975439222, "grad_norm": 0.3749552071094513, "learning_rate": 8.34504842783859e-06, "loss": 0.7050519943237304, "step": 8240, "token_acc": 0.7820676822886382 }, { "epoch": 0.5337821980885483, "grad_norm": 0.3576638698577881, "learning_rate": 8.34315846981076e-06, "loss": 0.721881914138794, "step": 8245, "token_acc": 0.7772798684812366 }, { "epoch": 0.5341058986331745, "grad_norm": 0.27424517273902893, "learning_rate": 8.341267647514947e-06, "loss": 0.737413740158081, "step": 8250, "token_acc": 0.7732275070366686 }, { "epoch": 0.5344295991778006, "grad_norm": 0.29704445600509644, "learning_rate": 8.339375961439968e-06, "loss": 0.7262219429016114, "step": 8255, "token_acc": 0.7757613408057523 }, { "epoch": 0.5347532997224268, "grad_norm": 0.35184967517852783, "learning_rate": 8.337483412074855e-06, "loss": 0.7365896224975585, "step": 8260, "token_acc": 0.7740663202362705 }, { "epoch": 0.535077000267053, "grad_norm": 0.32056716084480286, "learning_rate": 8.33558999990887e-06, "loss": 0.711580467224121, "step": 8265, "token_acc": 0.7794686748248091 }, { "epoch": 0.5354007008116791, "grad_norm": 0.36427193880081177, "learning_rate": 8.333695725431492e-06, "loss": 0.6843968391418457, "step": 8270, "token_acc": 0.7868399418200215 }, { "epoch": 0.5357244013563053, "grad_norm": 0.2933364510536194, "learning_rate": 8.33180058913243e-06, "loss": 0.7426023960113526, "step": 8275, "token_acc": 0.7738392114950718 }, { "epoch": 0.5360481019009314, "grad_norm": 0.2562108337879181, "learning_rate": 8.329904591501605e-06, "loss": 0.7160224914550781, "step": 8280, "token_acc": 0.7778210116731518 }, { "epoch": 0.5363718024455576, "grad_norm": 0.32193389534950256, "learning_rate": 8.328007733029173e-06, "loss": 0.7281524658203125, "step": 8285, "token_acc": 0.7775888726676892 }, { "epoch": 0.5366955029901838, "grad_norm": 0.26964107155799866, "learning_rate": 8.326110014205507e-06, "loss": 0.7128536224365234, "step": 8290, "token_acc": 0.781447434168646 }, { "epoch": 0.5370192035348099, "grad_norm": 0.29572996497154236, "learning_rate": 8.324211435521196e-06, "loss": 0.7122024059295654, "step": 8295, "token_acc": 0.7789678608772219 }, { "epoch": 0.5373429040794361, "grad_norm": 0.3563816249370575, "learning_rate": 8.322311997467063e-06, "loss": 0.68817138671875, "step": 8300, "token_acc": 0.7853067914791172 }, { "epoch": 0.5376666046240622, "grad_norm": 0.276177316904068, "learning_rate": 8.320411700534146e-06, "loss": 0.6904624938964844, "step": 8305, "token_acc": 0.7863849619387914 }, { "epoch": 0.5379903051686884, "grad_norm": 0.26761966943740845, "learning_rate": 8.318510545213708e-06, "loss": 0.7073079109191894, "step": 8310, "token_acc": 0.7802710993615323 }, { "epoch": 0.5383140057133146, "grad_norm": 0.4326242506504059, "learning_rate": 8.316608531997233e-06, "loss": 0.7310648441314698, "step": 8315, "token_acc": 0.7761105842876942 }, { "epoch": 0.5386377062579408, "grad_norm": 0.3581404685974121, "learning_rate": 8.314705661376421e-06, "loss": 0.6811367988586425, "step": 8320, "token_acc": 0.7875609207011737 }, { "epoch": 0.538961406802567, "grad_norm": 0.27693048119544983, "learning_rate": 8.312801933843206e-06, "loss": 0.7112035274505615, "step": 8325, "token_acc": 0.7805391418530104 }, { "epoch": 0.5392851073471931, "grad_norm": 0.27158287167549133, "learning_rate": 8.310897349889733e-06, "loss": 0.7336244106292724, "step": 8330, "token_acc": 0.7747517849174476 }, { "epoch": 0.5396088078918193, "grad_norm": 0.33877795934677124, "learning_rate": 8.308991910008373e-06, "loss": 0.7390645027160645, "step": 8335, "token_acc": 0.774217740369485 }, { "epoch": 0.5399325084364455, "grad_norm": 0.318997323513031, "learning_rate": 8.307085614691716e-06, "loss": 0.7235530853271485, "step": 8340, "token_acc": 0.7761661986422749 }, { "epoch": 0.5402562089810716, "grad_norm": 0.3228658437728882, "learning_rate": 8.305178464432578e-06, "loss": 0.7099175453186035, "step": 8345, "token_acc": 0.7790461610144107 }, { "epoch": 0.5405799095256978, "grad_norm": 0.2645137310028076, "learning_rate": 8.303270459723988e-06, "loss": 0.7195240974426269, "step": 8350, "token_acc": 0.7781908456941828 }, { "epoch": 0.540903610070324, "grad_norm": 0.2853059768676758, "learning_rate": 8.3013616010592e-06, "loss": 0.731591796875, "step": 8355, "token_acc": 0.7755883366900731 }, { "epoch": 0.5412273106149501, "grad_norm": 0.35887429118156433, "learning_rate": 8.299451888931696e-06, "loss": 0.7324929237365723, "step": 8360, "token_acc": 0.7733038527162001 }, { "epoch": 0.5415510111595763, "grad_norm": 0.3305198848247528, "learning_rate": 8.297541323835165e-06, "loss": 0.6904058456420898, "step": 8365, "token_acc": 0.7864154082416176 }, { "epoch": 0.5418747117042024, "grad_norm": 0.42549073696136475, "learning_rate": 8.295629906263523e-06, "loss": 0.7100571155548095, "step": 8370, "token_acc": 0.7799477555061918 }, { "epoch": 0.5421984122488286, "grad_norm": 0.3445259928703308, "learning_rate": 8.293717636710912e-06, "loss": 0.7284932136535645, "step": 8375, "token_acc": 0.7753336266314709 }, { "epoch": 0.5425221127934547, "grad_norm": 0.2507377564907074, "learning_rate": 8.291804515671685e-06, "loss": 0.7076729774475098, "step": 8380, "token_acc": 0.7803369897690117 }, { "epoch": 0.5428458133380809, "grad_norm": 0.3714258670806885, "learning_rate": 8.289890543640417e-06, "loss": 0.7109793663024903, "step": 8385, "token_acc": 0.7788591672637529 }, { "epoch": 0.5431695138827071, "grad_norm": 0.3504641652107239, "learning_rate": 8.287975721111912e-06, "loss": 0.7488052368164062, "step": 8390, "token_acc": 0.7692850923202447 }, { "epoch": 0.5434932144273332, "grad_norm": 0.29783982038497925, "learning_rate": 8.286060048581179e-06, "loss": 0.7165843963623046, "step": 8395, "token_acc": 0.7809022659277366 }, { "epoch": 0.5438169149719594, "grad_norm": 0.23721642792224884, "learning_rate": 8.28414352654346e-06, "loss": 0.7202577114105224, "step": 8400, "token_acc": 0.7787686979188666 }, { "epoch": 0.5441406155165857, "grad_norm": 0.29067346453666687, "learning_rate": 8.282226155494207e-06, "loss": 0.7016945362091065, "step": 8405, "token_acc": 0.782508017960231 }, { "epoch": 0.5444643160612118, "grad_norm": 0.3359452486038208, "learning_rate": 8.280307935929101e-06, "loss": 0.746329402923584, "step": 8410, "token_acc": 0.7698407296487885 }, { "epoch": 0.544788016605838, "grad_norm": 0.37392890453338623, "learning_rate": 8.278388868344031e-06, "loss": 0.7229859828948975, "step": 8415, "token_acc": 0.7770189826370213 }, { "epoch": 0.5451117171504641, "grad_norm": 0.2791455388069153, "learning_rate": 8.276468953235118e-06, "loss": 0.7346478939056397, "step": 8420, "token_acc": 0.7739943432890524 }, { "epoch": 0.5454354176950903, "grad_norm": 0.3200777769088745, "learning_rate": 8.27454819109869e-06, "loss": 0.7175819396972656, "step": 8425, "token_acc": 0.7781813137618381 }, { "epoch": 0.5457591182397165, "grad_norm": 0.35204777121543884, "learning_rate": 8.2726265824313e-06, "loss": 0.7466344833374023, "step": 8430, "token_acc": 0.7710447091762883 }, { "epoch": 0.5460828187843426, "grad_norm": 0.24243584275245667, "learning_rate": 8.270704127729724e-06, "loss": 0.7293092727661132, "step": 8435, "token_acc": 0.7752751712064606 }, { "epoch": 0.5464065193289688, "grad_norm": 0.3119598627090454, "learning_rate": 8.268780827490943e-06, "loss": 0.7353401184082031, "step": 8440, "token_acc": 0.7747937048585799 }, { "epoch": 0.5467302198735949, "grad_norm": 0.33524638414382935, "learning_rate": 8.266856682212174e-06, "loss": 0.7724015235900878, "step": 8445, "token_acc": 0.7645021047546753 }, { "epoch": 0.5470539204182211, "grad_norm": 0.3321323096752167, "learning_rate": 8.264931692390841e-06, "loss": 0.7232684135437012, "step": 8450, "token_acc": 0.7768755379340511 }, { "epoch": 0.5473776209628473, "grad_norm": 0.3014828860759735, "learning_rate": 8.263005858524586e-06, "loss": 0.7374260902404786, "step": 8455, "token_acc": 0.7729471527466266 }, { "epoch": 0.5477013215074734, "grad_norm": 0.2835388481616974, "learning_rate": 8.261079181111277e-06, "loss": 0.7129883289337158, "step": 8460, "token_acc": 0.7783301747189698 }, { "epoch": 0.5480250220520996, "grad_norm": 0.2453444004058838, "learning_rate": 8.259151660648997e-06, "loss": 0.7119335651397705, "step": 8465, "token_acc": 0.7786299685835268 }, { "epoch": 0.5483487225967257, "grad_norm": 0.34199100732803345, "learning_rate": 8.257223297636038e-06, "loss": 0.7125219345092774, "step": 8470, "token_acc": 0.7796177768018032 }, { "epoch": 0.5486724231413519, "grad_norm": 0.25449588894844055, "learning_rate": 8.255294092570925e-06, "loss": 0.7092867851257324, "step": 8475, "token_acc": 0.7804583152286854 }, { "epoch": 0.548996123685978, "grad_norm": 0.2012474536895752, "learning_rate": 8.253364045952389e-06, "loss": 0.7226297855377197, "step": 8480, "token_acc": 0.7761963773830536 }, { "epoch": 0.5493198242306042, "grad_norm": 0.34282100200653076, "learning_rate": 8.251433158279382e-06, "loss": 0.7133074760437011, "step": 8485, "token_acc": 0.7794540559307711 }, { "epoch": 0.5496435247752305, "grad_norm": 0.36899498105049133, "learning_rate": 8.249501430051078e-06, "loss": 0.72314453125, "step": 8490, "token_acc": 0.7772381892033878 }, { "epoch": 0.5499672253198566, "grad_norm": 0.28755030035972595, "learning_rate": 8.247568861766861e-06, "loss": 0.6949819564819336, "step": 8495, "token_acc": 0.7829293549591205 }, { "epoch": 0.5502909258644828, "grad_norm": 0.33142295479774475, "learning_rate": 8.245635453926336e-06, "loss": 0.7147089958190918, "step": 8500, "token_acc": 0.7803704382410631 }, { "epoch": 0.550614626409109, "grad_norm": 0.31540271639823914, "learning_rate": 8.243701207029323e-06, "loss": 0.7107624530792236, "step": 8505, "token_acc": 0.779763055425147 }, { "epoch": 0.5509383269537351, "grad_norm": 0.3051817715167999, "learning_rate": 8.241766121575865e-06, "loss": 0.6955248832702636, "step": 8510, "token_acc": 0.7846238303489369 }, { "epoch": 0.5512620274983613, "grad_norm": 0.35377243161201477, "learning_rate": 8.239830198066212e-06, "loss": 0.730610466003418, "step": 8515, "token_acc": 0.7748350069836563 }, { "epoch": 0.5515857280429874, "grad_norm": 0.4021252393722534, "learning_rate": 8.237893437000839e-06, "loss": 0.7180781364440918, "step": 8520, "token_acc": 0.7789577519307249 }, { "epoch": 0.5519094285876136, "grad_norm": 0.3419954180717468, "learning_rate": 8.235955838880434e-06, "loss": 0.7075779914855957, "step": 8525, "token_acc": 0.7805860075742476 }, { "epoch": 0.5522331291322398, "grad_norm": 0.31742164492607117, "learning_rate": 8.234017404205899e-06, "loss": 0.7219500541687012, "step": 8530, "token_acc": 0.7769403908156299 }, { "epoch": 0.5525568296768659, "grad_norm": 0.37340232729911804, "learning_rate": 8.232078133478359e-06, "loss": 0.7121810913085938, "step": 8535, "token_acc": 0.7809989823976443 }, { "epoch": 0.5528805302214921, "grad_norm": 0.30303332209587097, "learning_rate": 8.23013802719915e-06, "loss": 0.7262393951416015, "step": 8540, "token_acc": 0.7755631442087785 }, { "epoch": 0.5532042307661182, "grad_norm": 0.24926522374153137, "learning_rate": 8.228197085869824e-06, "loss": 0.7150409698486329, "step": 8545, "token_acc": 0.777605674275822 }, { "epoch": 0.5535279313107444, "grad_norm": 0.3395698070526123, "learning_rate": 8.22625530999215e-06, "loss": 0.7051973819732666, "step": 8550, "token_acc": 0.7809331922110713 }, { "epoch": 0.5538516318553706, "grad_norm": 0.2724555730819702, "learning_rate": 8.224312700068116e-06, "loss": 0.7281934261322022, "step": 8555, "token_acc": 0.7760241246964831 }, { "epoch": 0.5541753323999967, "grad_norm": 0.3099055886268616, "learning_rate": 8.222369256599918e-06, "loss": 0.7234626770019531, "step": 8560, "token_acc": 0.7758465447900063 }, { "epoch": 0.5544990329446229, "grad_norm": 0.34649503231048584, "learning_rate": 8.220424980089972e-06, "loss": 0.707574987411499, "step": 8565, "token_acc": 0.7809465900398171 }, { "epoch": 0.554822733489249, "grad_norm": 0.37107643485069275, "learning_rate": 8.218479871040914e-06, "loss": 0.6775558471679688, "step": 8570, "token_acc": 0.787624554375622 }, { "epoch": 0.5551464340338753, "grad_norm": 0.30320078134536743, "learning_rate": 8.216533929955586e-06, "loss": 0.7195709705352783, "step": 8575, "token_acc": 0.7767529864307079 }, { "epoch": 0.5554701345785015, "grad_norm": 0.31631433963775635, "learning_rate": 8.214587157337053e-06, "loss": 0.7219887733459472, "step": 8580, "token_acc": 0.7781148675553196 }, { "epoch": 0.5557938351231276, "grad_norm": 0.3829580843448639, "learning_rate": 8.212639553688588e-06, "loss": 0.6808233261108398, "step": 8585, "token_acc": 0.7870441232217319 }, { "epoch": 0.5561175356677538, "grad_norm": 0.27696898579597473, "learning_rate": 8.210691119513684e-06, "loss": 0.7439567565917968, "step": 8590, "token_acc": 0.7737655976374951 }, { "epoch": 0.55644123621238, "grad_norm": 0.297525018453598, "learning_rate": 8.208741855316047e-06, "loss": 0.710416316986084, "step": 8595, "token_acc": 0.782007037488158 }, { "epoch": 0.5567649367570061, "grad_norm": 0.34995636343955994, "learning_rate": 8.2067917615996e-06, "loss": 0.6970073699951171, "step": 8600, "token_acc": 0.7830626063173343 }, { "epoch": 0.5570886373016323, "grad_norm": 0.3230840563774109, "learning_rate": 8.204840838868474e-06, "loss": 0.6968931198120117, "step": 8605, "token_acc": 0.7851591437817605 }, { "epoch": 0.5574123378462584, "grad_norm": 0.23794567584991455, "learning_rate": 8.202889087627021e-06, "loss": 0.7273038387298584, "step": 8610, "token_acc": 0.7746185286103542 }, { "epoch": 0.5577360383908846, "grad_norm": 0.2650205194950104, "learning_rate": 8.200936508379803e-06, "loss": 0.710533857345581, "step": 8615, "token_acc": 0.77781036604416 }, { "epoch": 0.5580597389355108, "grad_norm": 0.2972160577774048, "learning_rate": 8.1989831016316e-06, "loss": 0.7159016132354736, "step": 8620, "token_acc": 0.7794227404534387 }, { "epoch": 0.5583834394801369, "grad_norm": 0.2955903112888336, "learning_rate": 8.1970288678874e-06, "loss": 0.7231910705566407, "step": 8625, "token_acc": 0.7774375585191183 }, { "epoch": 0.5587071400247631, "grad_norm": 0.23874486982822418, "learning_rate": 8.195073807652412e-06, "loss": 0.7159028053283691, "step": 8630, "token_acc": 0.7806449880508042 }, { "epoch": 0.5590308405693892, "grad_norm": 0.3541858196258545, "learning_rate": 8.193117921432055e-06, "loss": 0.7179537773132324, "step": 8635, "token_acc": 0.7800242485610744 }, { "epoch": 0.5593545411140154, "grad_norm": 0.23034094274044037, "learning_rate": 8.191161209731957e-06, "loss": 0.7148286819458007, "step": 8640, "token_acc": 0.7784111349567677 }, { "epoch": 0.5596782416586416, "grad_norm": 0.3777572512626648, "learning_rate": 8.18920367305797e-06, "loss": 0.7341243267059326, "step": 8645, "token_acc": 0.7740919786673139 }, { "epoch": 0.5600019422032677, "grad_norm": 0.2670612335205078, "learning_rate": 8.187245311916147e-06, "loss": 0.7077706336975098, "step": 8650, "token_acc": 0.7806272470677608 }, { "epoch": 0.5603256427478939, "grad_norm": 0.2784823477268219, "learning_rate": 8.185286126812768e-06, "loss": 0.7128144264221191, "step": 8655, "token_acc": 0.7795566889222478 }, { "epoch": 0.5606493432925201, "grad_norm": 0.2996900975704193, "learning_rate": 8.183326118254312e-06, "loss": 0.719419002532959, "step": 8660, "token_acc": 0.7779263076025666 }, { "epoch": 0.5609730438371463, "grad_norm": 0.290927916765213, "learning_rate": 8.181365286747478e-06, "loss": 0.7316623210906983, "step": 8665, "token_acc": 0.7743919603648238 }, { "epoch": 0.5612967443817725, "grad_norm": 0.32842007279396057, "learning_rate": 8.179403632799182e-06, "loss": 0.7370459556579589, "step": 8670, "token_acc": 0.7746738665526091 }, { "epoch": 0.5616204449263986, "grad_norm": 0.2942446172237396, "learning_rate": 8.177441156916541e-06, "loss": 0.698547649383545, "step": 8675, "token_acc": 0.7830934369635345 }, { "epoch": 0.5619441454710248, "grad_norm": 0.32569172978401184, "learning_rate": 8.175477859606898e-06, "loss": 0.7289684295654297, "step": 8680, "token_acc": 0.7750987212008682 }, { "epoch": 0.5622678460156509, "grad_norm": 0.3354617655277252, "learning_rate": 8.173513741377794e-06, "loss": 0.737144660949707, "step": 8685, "token_acc": 0.7741568991308629 }, { "epoch": 0.5625915465602771, "grad_norm": 0.3586123585700989, "learning_rate": 8.171548802736994e-06, "loss": 0.7147418022155761, "step": 8690, "token_acc": 0.777862076700291 }, { "epoch": 0.5629152471049033, "grad_norm": 0.36084967851638794, "learning_rate": 8.169583044192473e-06, "loss": 0.6996880054473877, "step": 8695, "token_acc": 0.7815796919843163 }, { "epoch": 0.5632389476495294, "grad_norm": 0.2704005241394043, "learning_rate": 8.16761646625241e-06, "loss": 0.7207859039306641, "step": 8700, "token_acc": 0.7789404923534083 }, { "epoch": 0.5635626481941556, "grad_norm": 0.29660090804100037, "learning_rate": 8.165649069425205e-06, "loss": 0.7288466930389405, "step": 8705, "token_acc": 0.7751341553267652 }, { "epoch": 0.5638863487387817, "grad_norm": 0.3579671382904053, "learning_rate": 8.163680854219468e-06, "loss": 0.6975024700164795, "step": 8710, "token_acc": 0.7843131307769884 }, { "epoch": 0.5642100492834079, "grad_norm": 0.3529984951019287, "learning_rate": 8.161711821144016e-06, "loss": 0.7091600894927979, "step": 8715, "token_acc": 0.7795374383069704 }, { "epoch": 0.5645337498280341, "grad_norm": 0.3049182891845703, "learning_rate": 8.15974197070788e-06, "loss": 0.7130808353424072, "step": 8720, "token_acc": 0.7775391224301933 }, { "epoch": 0.5648574503726602, "grad_norm": 0.38310131430625916, "learning_rate": 8.157771303420303e-06, "loss": 0.7301400184631348, "step": 8725, "token_acc": 0.7759697269572247 }, { "epoch": 0.5651811509172864, "grad_norm": 0.32523590326309204, "learning_rate": 8.155799819790741e-06, "loss": 0.7397863388061523, "step": 8730, "token_acc": 0.7734437956823548 }, { "epoch": 0.5655048514619125, "grad_norm": 0.3566470146179199, "learning_rate": 8.153827520328857e-06, "loss": 0.683634090423584, "step": 8735, "token_acc": 0.78554425449037 }, { "epoch": 0.5658285520065387, "grad_norm": 0.3826215863227844, "learning_rate": 8.151854405544526e-06, "loss": 0.7307916641235351, "step": 8740, "token_acc": 0.77689131454176 }, { "epoch": 0.566152252551165, "grad_norm": 0.3092617988586426, "learning_rate": 8.149880475947835e-06, "loss": 0.7100277900695801, "step": 8745, "token_acc": 0.7808046159473804 }, { "epoch": 0.5664759530957911, "grad_norm": 0.3329782783985138, "learning_rate": 8.147905732049083e-06, "loss": 0.7188400268554688, "step": 8750, "token_acc": 0.7785681490008717 }, { "epoch": 0.5667996536404173, "grad_norm": 0.3100889027118683, "learning_rate": 8.145930174358774e-06, "loss": 0.6883630752563477, "step": 8755, "token_acc": 0.7850944783706877 }, { "epoch": 0.5671233541850434, "grad_norm": 0.35058334469795227, "learning_rate": 8.143953803387628e-06, "loss": 0.7398802280426026, "step": 8760, "token_acc": 0.7717780714061925 }, { "epoch": 0.5674470547296696, "grad_norm": 0.3910297453403473, "learning_rate": 8.141976619646575e-06, "loss": 0.7352688312530518, "step": 8765, "token_acc": 0.7762517797816801 }, { "epoch": 0.5677707552742958, "grad_norm": 0.2532813847064972, "learning_rate": 8.139998623646752e-06, "loss": 0.716763973236084, "step": 8770, "token_acc": 0.7784624722079434 }, { "epoch": 0.5680944558189219, "grad_norm": 0.3109566271305084, "learning_rate": 8.138019815899507e-06, "loss": 0.7023462295532227, "step": 8775, "token_acc": 0.7820288720464869 }, { "epoch": 0.5684181563635481, "grad_norm": 0.32980409264564514, "learning_rate": 8.136040196916398e-06, "loss": 0.7153275012969971, "step": 8780, "token_acc": 0.7773851811871619 }, { "epoch": 0.5687418569081742, "grad_norm": 0.4016779363155365, "learning_rate": 8.134059767209191e-06, "loss": 0.7211848735809326, "step": 8785, "token_acc": 0.7768088196461579 }, { "epoch": 0.5690655574528004, "grad_norm": 0.25350043177604675, "learning_rate": 8.132078527289868e-06, "loss": 0.733649206161499, "step": 8790, "token_acc": 0.7728847105393369 }, { "epoch": 0.5693892579974266, "grad_norm": 0.3031075596809387, "learning_rate": 8.130096477670613e-06, "loss": 0.7209248542785645, "step": 8795, "token_acc": 0.7780899759251227 }, { "epoch": 0.5697129585420527, "grad_norm": 0.3561631441116333, "learning_rate": 8.128113618863825e-06, "loss": 0.7381692886352539, "step": 8800, "token_acc": 0.7729311261843945 }, { "epoch": 0.5700366590866789, "grad_norm": 0.29240483045578003, "learning_rate": 8.126129951382105e-06, "loss": 0.7363293647766114, "step": 8805, "token_acc": 0.7736228680349189 }, { "epoch": 0.570360359631305, "grad_norm": 0.270211398601532, "learning_rate": 8.12414547573827e-06, "loss": 0.7018904685974121, "step": 8810, "token_acc": 0.7836704381634704 }, { "epoch": 0.5706840601759312, "grad_norm": 0.28634974360466003, "learning_rate": 8.122160192445346e-06, "loss": 0.7059898376464844, "step": 8815, "token_acc": 0.7815361449869094 }, { "epoch": 0.5710077607205574, "grad_norm": 0.3070394992828369, "learning_rate": 8.12017410201656e-06, "loss": 0.7197509765625, "step": 8820, "token_acc": 0.7767814714572013 }, { "epoch": 0.5713314612651835, "grad_norm": 0.35696640610694885, "learning_rate": 8.118187204965357e-06, "loss": 0.6957496643066406, "step": 8825, "token_acc": 0.7841884417318329 }, { "epoch": 0.5716551618098098, "grad_norm": 0.4249090552330017, "learning_rate": 8.116199501805387e-06, "loss": 0.7079154014587402, "step": 8830, "token_acc": 0.7805182485396176 }, { "epoch": 0.571978862354436, "grad_norm": 0.2875366806983948, "learning_rate": 8.114210993050502e-06, "loss": 0.6893965721130371, "step": 8835, "token_acc": 0.7847358775766817 }, { "epoch": 0.5723025628990621, "grad_norm": 0.32286712527275085, "learning_rate": 8.112221679214776e-06, "loss": 0.707103967666626, "step": 8840, "token_acc": 0.7787255087937996 }, { "epoch": 0.5726262634436883, "grad_norm": 0.2684534192085266, "learning_rate": 8.110231560812477e-06, "loss": 0.7477083683013916, "step": 8845, "token_acc": 0.7707947292567429 }, { "epoch": 0.5729499639883144, "grad_norm": 0.32064884901046753, "learning_rate": 8.10824063835809e-06, "loss": 0.7062807083129883, "step": 8850, "token_acc": 0.7811381449279183 }, { "epoch": 0.5732736645329406, "grad_norm": 0.29701143503189087, "learning_rate": 8.106248912366306e-06, "loss": 0.7431596279144287, "step": 8855, "token_acc": 0.7723885897286896 }, { "epoch": 0.5735973650775668, "grad_norm": 0.27170872688293457, "learning_rate": 8.104256383352019e-06, "loss": 0.7038516998291016, "step": 8860, "token_acc": 0.7813733905579399 }, { "epoch": 0.5739210656221929, "grad_norm": 0.339040607213974, "learning_rate": 8.10226305183034e-06, "loss": 0.7097872734069824, "step": 8865, "token_acc": 0.77993204461252 }, { "epoch": 0.5742447661668191, "grad_norm": 0.38296303153038025, "learning_rate": 8.100268918316575e-06, "loss": 0.7115644454956055, "step": 8870, "token_acc": 0.7801300240652276 }, { "epoch": 0.5745684667114452, "grad_norm": 0.3222683370113373, "learning_rate": 8.09827398332625e-06, "loss": 0.7250466823577881, "step": 8875, "token_acc": 0.7764845983951036 }, { "epoch": 0.5748921672560714, "grad_norm": 0.2548254132270813, "learning_rate": 8.096278247375092e-06, "loss": 0.7145826339721679, "step": 8880, "token_acc": 0.7778449540785827 }, { "epoch": 0.5752158678006976, "grad_norm": 0.34956619143486023, "learning_rate": 8.09428171097903e-06, "loss": 0.694239330291748, "step": 8885, "token_acc": 0.7832583724316453 }, { "epoch": 0.5755395683453237, "grad_norm": 0.4392073452472687, "learning_rate": 8.092284374654213e-06, "loss": 0.7242573738098145, "step": 8890, "token_acc": 0.7768290063716653 }, { "epoch": 0.5758632688899499, "grad_norm": 0.384492963552475, "learning_rate": 8.090286238916982e-06, "loss": 0.7284932613372803, "step": 8895, "token_acc": 0.7749090836029013 }, { "epoch": 0.576186969434576, "grad_norm": 0.36581191420555115, "learning_rate": 8.088287304283897e-06, "loss": 0.7456165790557862, "step": 8900, "token_acc": 0.7712826224722985 }, { "epoch": 0.5765106699792022, "grad_norm": 0.2616037428379059, "learning_rate": 8.086287571271719e-06, "loss": 0.7317816734313964, "step": 8905, "token_acc": 0.775006788228168 }, { "epoch": 0.5768343705238284, "grad_norm": 0.3315645754337311, "learning_rate": 8.084287040397411e-06, "loss": 0.718636417388916, "step": 8910, "token_acc": 0.7794170317106097 }, { "epoch": 0.5771580710684546, "grad_norm": 0.30027103424072266, "learning_rate": 8.082285712178154e-06, "loss": 0.7064117431640625, "step": 8915, "token_acc": 0.7801870939912312 }, { "epoch": 0.5774817716130808, "grad_norm": 0.4316336214542389, "learning_rate": 8.080283587131324e-06, "loss": 0.6994407176971436, "step": 8920, "token_acc": 0.7832646805249545 }, { "epoch": 0.577805472157707, "grad_norm": 0.28970855474472046, "learning_rate": 8.078280665774507e-06, "loss": 0.7419707775115967, "step": 8925, "token_acc": 0.7725115566197426 }, { "epoch": 0.5781291727023331, "grad_norm": 0.300471693277359, "learning_rate": 8.076276948625495e-06, "loss": 0.7171789169311523, "step": 8930, "token_acc": 0.7792828685258965 }, { "epoch": 0.5784528732469593, "grad_norm": 0.28053343296051025, "learning_rate": 8.074272436202288e-06, "loss": 0.7262537002563476, "step": 8935, "token_acc": 0.7762551120909512 }, { "epoch": 0.5787765737915854, "grad_norm": 0.30795279145240784, "learning_rate": 8.072267129023088e-06, "loss": 0.7005711555480957, "step": 8940, "token_acc": 0.7834454701924581 }, { "epoch": 0.5791002743362116, "grad_norm": 0.305843323469162, "learning_rate": 8.070261027606303e-06, "loss": 0.7068312644958497, "step": 8945, "token_acc": 0.7807856624660773 }, { "epoch": 0.5794239748808377, "grad_norm": 0.31346946954727173, "learning_rate": 8.068254132470548e-06, "loss": 0.7149824142456055, "step": 8950, "token_acc": 0.778815827041958 }, { "epoch": 0.5797476754254639, "grad_norm": 0.3396275043487549, "learning_rate": 8.066246444134643e-06, "loss": 0.7123062133789062, "step": 8955, "token_acc": 0.7797059257569863 }, { "epoch": 0.5800713759700901, "grad_norm": 0.3323579728603363, "learning_rate": 8.06423796311761e-06, "loss": 0.7245826721191406, "step": 8960, "token_acc": 0.7771147237185116 }, { "epoch": 0.5803950765147162, "grad_norm": 0.3349960744380951, "learning_rate": 8.06222868993868e-06, "loss": 0.722327709197998, "step": 8965, "token_acc": 0.7770894736140191 }, { "epoch": 0.5807187770593424, "grad_norm": 0.372202605009079, "learning_rate": 8.060218625117288e-06, "loss": 0.6991800785064697, "step": 8970, "token_acc": 0.7823648800031631 }, { "epoch": 0.5810424776039685, "grad_norm": 0.3441289961338043, "learning_rate": 8.058207769173072e-06, "loss": 0.7030133247375489, "step": 8975, "token_acc": 0.7817556582105345 }, { "epoch": 0.5813661781485947, "grad_norm": 0.336079478263855, "learning_rate": 8.056196122625875e-06, "loss": 0.7212955474853515, "step": 8980, "token_acc": 0.7787282769769635 }, { "epoch": 0.5816898786932209, "grad_norm": 0.3110930919647217, "learning_rate": 8.054183685995743e-06, "loss": 0.7113111019134521, "step": 8985, "token_acc": 0.7794161350085044 }, { "epoch": 0.582013579237847, "grad_norm": 0.2731608748435974, "learning_rate": 8.05217045980293e-06, "loss": 0.7251669406890869, "step": 8990, "token_acc": 0.7770836517820946 }, { "epoch": 0.5823372797824732, "grad_norm": 0.27049902081489563, "learning_rate": 8.050156444567893e-06, "loss": 0.7154459476470947, "step": 8995, "token_acc": 0.7793765632984588 }, { "epoch": 0.5826609803270995, "grad_norm": 0.33188703656196594, "learning_rate": 8.04814164081129e-06, "loss": 0.7077015399932861, "step": 9000, "token_acc": 0.7832542486126663 }, { "epoch": 0.5829846808717256, "grad_norm": 0.3125072121620178, "learning_rate": 8.046126049053984e-06, "loss": 0.6999375343322753, "step": 9005, "token_acc": 0.7821093486974584 }, { "epoch": 0.5833083814163518, "grad_norm": 0.34473317861557007, "learning_rate": 8.044109669817045e-06, "loss": 0.7498338699340821, "step": 9010, "token_acc": 0.7709701853133611 }, { "epoch": 0.5836320819609779, "grad_norm": 0.20728696882724762, "learning_rate": 8.042092503621743e-06, "loss": 0.701277780532837, "step": 9015, "token_acc": 0.7834768717877483 }, { "epoch": 0.5839557825056041, "grad_norm": 0.3356564939022064, "learning_rate": 8.040074550989552e-06, "loss": 0.7088142395019531, "step": 9020, "token_acc": 0.779863277826468 }, { "epoch": 0.5842794830502303, "grad_norm": 0.2935311496257782, "learning_rate": 8.038055812442152e-06, "loss": 0.7289516925811768, "step": 9025, "token_acc": 0.7741196149033428 }, { "epoch": 0.5846031835948564, "grad_norm": 0.2290104329586029, "learning_rate": 8.036036288501422e-06, "loss": 0.6883270263671875, "step": 9030, "token_acc": 0.7849320866011559 }, { "epoch": 0.5849268841394826, "grad_norm": 0.4034990966320038, "learning_rate": 8.034015979689446e-06, "loss": 0.725661325454712, "step": 9035, "token_acc": 0.7772247817652764 }, { "epoch": 0.5852505846841087, "grad_norm": 0.2596222162246704, "learning_rate": 8.031994886528512e-06, "loss": 0.715999698638916, "step": 9040, "token_acc": 0.7780313432739603 }, { "epoch": 0.5855742852287349, "grad_norm": 0.30254286527633667, "learning_rate": 8.029973009541108e-06, "loss": 0.7198817729949951, "step": 9045, "token_acc": 0.7781719165957217 }, { "epoch": 0.585897985773361, "grad_norm": 0.2429238110780716, "learning_rate": 8.027950349249931e-06, "loss": 0.7252613067626953, "step": 9050, "token_acc": 0.775610056102611 }, { "epoch": 0.5862216863179872, "grad_norm": 0.36439335346221924, "learning_rate": 8.02592690617787e-06, "loss": 0.7165390968322753, "step": 9055, "token_acc": 0.7795642861169043 }, { "epoch": 0.5865453868626134, "grad_norm": 0.3784506916999817, "learning_rate": 8.023902680848027e-06, "loss": 0.7296024322509765, "step": 9060, "token_acc": 0.7758201744132504 }, { "epoch": 0.5868690874072395, "grad_norm": 0.35986819863319397, "learning_rate": 8.021877673783699e-06, "loss": 0.7145451068878174, "step": 9065, "token_acc": 0.7804655791562501 }, { "epoch": 0.5871927879518657, "grad_norm": 0.3263111114501953, "learning_rate": 8.019851885508387e-06, "loss": 0.7232638359069824, "step": 9070, "token_acc": 0.7764182068612063 }, { "epoch": 0.5875164884964919, "grad_norm": 0.3846198320388794, "learning_rate": 8.017825316545797e-06, "loss": 0.7019801139831543, "step": 9075, "token_acc": 0.781933068102036 }, { "epoch": 0.587840189041118, "grad_norm": 0.30614763498306274, "learning_rate": 8.015797967419833e-06, "loss": 0.7030675411224365, "step": 9080, "token_acc": 0.7804823788954599 }, { "epoch": 0.5881638895857443, "grad_norm": 0.34250420331954956, "learning_rate": 8.013769838654602e-06, "loss": 0.7023459911346436, "step": 9085, "token_acc": 0.7814895654294262 }, { "epoch": 0.5884875901303704, "grad_norm": 0.2593022286891937, "learning_rate": 8.011740930774412e-06, "loss": 0.7154379844665527, "step": 9090, "token_acc": 0.7793012231214479 }, { "epoch": 0.5888112906749966, "grad_norm": 0.4533991813659668, "learning_rate": 8.009711244303774e-06, "loss": 0.7112353324890137, "step": 9095, "token_acc": 0.7806659465434084 }, { "epoch": 0.5891349912196228, "grad_norm": 0.35934358835220337, "learning_rate": 8.0076807797674e-06, "loss": 0.6900768280029297, "step": 9100, "token_acc": 0.7855769531861594 }, { "epoch": 0.5894586917642489, "grad_norm": 0.29123827815055847, "learning_rate": 8.005649537690199e-06, "loss": 0.7154661178588867, "step": 9105, "token_acc": 0.7779129984464008 }, { "epoch": 0.5897823923088751, "grad_norm": 0.3951794505119324, "learning_rate": 8.003617518597288e-06, "loss": 0.6972992420196533, "step": 9110, "token_acc": 0.7835730858468678 }, { "epoch": 0.5901060928535012, "grad_norm": 0.3698597252368927, "learning_rate": 8.00158472301398e-06, "loss": 0.732127571105957, "step": 9115, "token_acc": 0.77629897083822 }, { "epoch": 0.5904297933981274, "grad_norm": 0.4734044075012207, "learning_rate": 7.999551151465793e-06, "loss": 0.7270448207855225, "step": 9120, "token_acc": 0.7759106453318343 }, { "epoch": 0.5907534939427536, "grad_norm": 0.28557515144348145, "learning_rate": 7.997516804478439e-06, "loss": 0.699376106262207, "step": 9125, "token_acc": 0.783255274291455 }, { "epoch": 0.5910771944873797, "grad_norm": 0.2841170132160187, "learning_rate": 7.995481682577833e-06, "loss": 0.7242827415466309, "step": 9130, "token_acc": 0.7761624328649265 }, { "epoch": 0.5914008950320059, "grad_norm": 0.27248072624206543, "learning_rate": 7.993445786290094e-06, "loss": 0.7073811054229736, "step": 9135, "token_acc": 0.7786757003115519 }, { "epoch": 0.591724595576632, "grad_norm": 0.30747488141059875, "learning_rate": 7.991409116141538e-06, "loss": 0.705565071105957, "step": 9140, "token_acc": 0.7810284732279591 }, { "epoch": 0.5920482961212582, "grad_norm": 0.4273202419281006, "learning_rate": 7.989371672658683e-06, "loss": 0.734284782409668, "step": 9145, "token_acc": 0.7751476371016617 }, { "epoch": 0.5923719966658844, "grad_norm": 0.30653542280197144, "learning_rate": 7.987333456368244e-06, "loss": 0.7039167404174804, "step": 9150, "token_acc": 0.780182140554481 }, { "epoch": 0.5926956972105105, "grad_norm": 0.3266286849975586, "learning_rate": 7.985294467797138e-06, "loss": 0.7111073493957519, "step": 9155, "token_acc": 0.7799774322968906 }, { "epoch": 0.5930193977551367, "grad_norm": 0.25154703855514526, "learning_rate": 7.983254707472481e-06, "loss": 0.69639892578125, "step": 9160, "token_acc": 0.7839593214545144 }, { "epoch": 0.5933430982997628, "grad_norm": 0.2633860111236572, "learning_rate": 7.981214175921588e-06, "loss": 0.7326744079589844, "step": 9165, "token_acc": 0.7752026115111261 }, { "epoch": 0.5936667988443891, "grad_norm": 0.3110649287700653, "learning_rate": 7.979172873671976e-06, "loss": 0.7157981395721436, "step": 9170, "token_acc": 0.7784601873184113 }, { "epoch": 0.5939904993890153, "grad_norm": 0.23349279165267944, "learning_rate": 7.977130801251356e-06, "loss": 0.7086912155151367, "step": 9175, "token_acc": 0.7801152926728943 }, { "epoch": 0.5943141999336414, "grad_norm": 0.2622513473033905, "learning_rate": 7.975087959187645e-06, "loss": 0.7118157863616943, "step": 9180, "token_acc": 0.7791015568793347 }, { "epoch": 0.5946379004782676, "grad_norm": 0.28430044651031494, "learning_rate": 7.973044348008953e-06, "loss": 0.7075395584106445, "step": 9185, "token_acc": 0.7790979546646466 }, { "epoch": 0.5949616010228937, "grad_norm": 0.2828938663005829, "learning_rate": 7.970999968243592e-06, "loss": 0.7255178451538086, "step": 9190, "token_acc": 0.776706002431971 }, { "epoch": 0.5952853015675199, "grad_norm": 0.25250980257987976, "learning_rate": 7.968954820420068e-06, "loss": 0.7229998588562012, "step": 9195, "token_acc": 0.7769916888900397 }, { "epoch": 0.5956090021121461, "grad_norm": 0.3726862370967865, "learning_rate": 7.966908905067095e-06, "loss": 0.701653528213501, "step": 9200, "token_acc": 0.782157357480436 }, { "epoch": 0.5959327026567722, "grad_norm": 0.3288676142692566, "learning_rate": 7.964862222713576e-06, "loss": 0.6985023498535157, "step": 9205, "token_acc": 0.7847956541354313 }, { "epoch": 0.5962564032013984, "grad_norm": 0.2953642010688782, "learning_rate": 7.96281477388862e-06, "loss": 0.6825022220611572, "step": 9210, "token_acc": 0.7868880629311881 }, { "epoch": 0.5965801037460245, "grad_norm": 0.3223644495010376, "learning_rate": 7.960766559121524e-06, "loss": 0.7169285774230957, "step": 9215, "token_acc": 0.7772980160257532 }, { "epoch": 0.5969038042906507, "grad_norm": 0.4325467348098755, "learning_rate": 7.958717578941795e-06, "loss": 0.6958502769470215, "step": 9220, "token_acc": 0.7833853648975935 }, { "epoch": 0.5972275048352769, "grad_norm": 0.3849504590034485, "learning_rate": 7.956667833879128e-06, "loss": 0.7106756687164306, "step": 9225, "token_acc": 0.7802869650408621 }, { "epoch": 0.597551205379903, "grad_norm": 0.28310924768447876, "learning_rate": 7.954617324463424e-06, "loss": 0.7003703117370605, "step": 9230, "token_acc": 0.7811500330469267 }, { "epoch": 0.5978749059245292, "grad_norm": 0.3170873820781708, "learning_rate": 7.952566051224774e-06, "loss": 0.7318376064300537, "step": 9235, "token_acc": 0.7749855877574551 }, { "epoch": 0.5981986064691553, "grad_norm": 0.3759816884994507, "learning_rate": 7.95051401469347e-06, "loss": 0.7195002555847168, "step": 9240, "token_acc": 0.7772332729285508 }, { "epoch": 0.5985223070137815, "grad_norm": 0.3218652606010437, "learning_rate": 7.948461215400003e-06, "loss": 0.7347631454467773, "step": 9245, "token_acc": 0.7734296747532143 }, { "epoch": 0.5988460075584077, "grad_norm": 0.30179667472839355, "learning_rate": 7.946407653875059e-06, "loss": 0.6961427688598633, "step": 9250, "token_acc": 0.7830985165259542 }, { "epoch": 0.5991697081030339, "grad_norm": 0.29002439975738525, "learning_rate": 7.94435333064952e-06, "loss": 0.6902447700500488, "step": 9255, "token_acc": 0.7852338333195216 }, { "epoch": 0.5994934086476601, "grad_norm": 0.34752216935157776, "learning_rate": 7.942298246254468e-06, "loss": 0.7308642387390136, "step": 9260, "token_acc": 0.774752901014859 }, { "epoch": 0.5998171091922863, "grad_norm": 0.28839200735092163, "learning_rate": 7.94024240122118e-06, "loss": 0.7186160087585449, "step": 9265, "token_acc": 0.77771062322548 }, { "epoch": 0.6001408097369124, "grad_norm": 0.34252262115478516, "learning_rate": 7.938185796081127e-06, "loss": 0.6822614669799805, "step": 9270, "token_acc": 0.787171193965723 }, { "epoch": 0.6004645102815386, "grad_norm": 0.3084203600883484, "learning_rate": 7.936128431365982e-06, "loss": 0.7039435386657715, "step": 9275, "token_acc": 0.780796064727441 }, { "epoch": 0.6007882108261647, "grad_norm": 0.36292973160743713, "learning_rate": 7.934070307607613e-06, "loss": 0.7159090042114258, "step": 9280, "token_acc": 0.7794912751082292 }, { "epoch": 0.6011119113707909, "grad_norm": 0.35780850052833557, "learning_rate": 7.93201142533808e-06, "loss": 0.7096000671386719, "step": 9285, "token_acc": 0.7810787461477957 }, { "epoch": 0.6014356119154171, "grad_norm": 0.2944369912147522, "learning_rate": 7.929951785089643e-06, "loss": 0.7173113346099853, "step": 9290, "token_acc": 0.7782761814161243 }, { "epoch": 0.6017593124600432, "grad_norm": 0.2948727011680603, "learning_rate": 7.927891387394756e-06, "loss": 0.7174944877624512, "step": 9295, "token_acc": 0.7786674046059712 }, { "epoch": 0.6020830130046694, "grad_norm": 0.31804510951042175, "learning_rate": 7.925830232786072e-06, "loss": 0.7050154685974122, "step": 9300, "token_acc": 0.7811593936384756 }, { "epoch": 0.6024067135492955, "grad_norm": 0.3995617628097534, "learning_rate": 7.923768321796434e-06, "loss": 0.7410070419311523, "step": 9305, "token_acc": 0.7744530786755297 }, { "epoch": 0.6027304140939217, "grad_norm": 0.26591044664382935, "learning_rate": 7.921705654958886e-06, "loss": 0.6983999729156494, "step": 9310, "token_acc": 0.7827068570515211 }, { "epoch": 0.6030541146385479, "grad_norm": 0.28715217113494873, "learning_rate": 7.919642232806668e-06, "loss": 0.720771598815918, "step": 9315, "token_acc": 0.7767097841872403 }, { "epoch": 0.603377815183174, "grad_norm": 0.3636694550514221, "learning_rate": 7.917578055873207e-06, "loss": 0.7007680892944336, "step": 9320, "token_acc": 0.7825117432838972 }, { "epoch": 0.6037015157278002, "grad_norm": 0.32483139634132385, "learning_rate": 7.915513124692136e-06, "loss": 0.7373773574829101, "step": 9325, "token_acc": 0.7747774355512426 }, { "epoch": 0.6040252162724263, "grad_norm": 0.2675258219242096, "learning_rate": 7.913447439797273e-06, "loss": 0.7121474266052246, "step": 9330, "token_acc": 0.7810596247322723 }, { "epoch": 0.6043489168170525, "grad_norm": 0.3202700912952423, "learning_rate": 7.911381001722638e-06, "loss": 0.6987751483917236, "step": 9335, "token_acc": 0.7829804514959 }, { "epoch": 0.6046726173616788, "grad_norm": 0.3043469190597534, "learning_rate": 7.909313811002445e-06, "loss": 0.7063388347625732, "step": 9340, "token_acc": 0.7817612540692973 }, { "epoch": 0.6049963179063049, "grad_norm": 0.36505988240242004, "learning_rate": 7.907245868171098e-06, "loss": 0.72496657371521, "step": 9345, "token_acc": 0.7764709468934821 }, { "epoch": 0.6053200184509311, "grad_norm": 0.2344142198562622, "learning_rate": 7.905177173763197e-06, "loss": 0.7292106628417969, "step": 9350, "token_acc": 0.7750264760391845 }, { "epoch": 0.6056437189955572, "grad_norm": 0.3023131489753723, "learning_rate": 7.903107728313541e-06, "loss": 0.7193609237670898, "step": 9355, "token_acc": 0.7775029284541034 }, { "epoch": 0.6059674195401834, "grad_norm": 0.3166407644748688, "learning_rate": 7.90103753235712e-06, "loss": 0.7085772514343261, "step": 9360, "token_acc": 0.7816328975828777 }, { "epoch": 0.6062911200848096, "grad_norm": 0.25611358880996704, "learning_rate": 7.898966586429116e-06, "loss": 0.68788743019104, "step": 9365, "token_acc": 0.7855133474982956 }, { "epoch": 0.6066148206294357, "grad_norm": 0.23463664948940277, "learning_rate": 7.896894891064906e-06, "loss": 0.7132390975952149, "step": 9370, "token_acc": 0.7800597261661933 }, { "epoch": 0.6069385211740619, "grad_norm": 0.2255818396806717, "learning_rate": 7.89482244680006e-06, "loss": 0.7162216186523438, "step": 9375, "token_acc": 0.777207845969012 }, { "epoch": 0.607262221718688, "grad_norm": 0.236253559589386, "learning_rate": 7.89274925417035e-06, "loss": 0.7178863525390625, "step": 9380, "token_acc": 0.7782601248978946 }, { "epoch": 0.6075859222633142, "grad_norm": 0.32254183292388916, "learning_rate": 7.890675313711724e-06, "loss": 0.7102278709411621, "step": 9385, "token_acc": 0.7815879254017432 }, { "epoch": 0.6079096228079404, "grad_norm": 0.36168548464775085, "learning_rate": 7.888600625960342e-06, "loss": 0.7289630889892578, "step": 9390, "token_acc": 0.7742829285150079 }, { "epoch": 0.6082333233525665, "grad_norm": 0.2705021798610687, "learning_rate": 7.886525191452548e-06, "loss": 0.6904186725616455, "step": 9395, "token_acc": 0.7856932381045926 }, { "epoch": 0.6085570238971927, "grad_norm": 0.2764722406864166, "learning_rate": 7.884449010724878e-06, "loss": 0.7033662796020508, "step": 9400, "token_acc": 0.7813005143277002 }, { "epoch": 0.6088807244418188, "grad_norm": 0.2751152217388153, "learning_rate": 7.88237208431406e-06, "loss": 0.7376873016357421, "step": 9405, "token_acc": 0.7753604090346046 }, { "epoch": 0.609204424986445, "grad_norm": 0.24812132120132446, "learning_rate": 7.880294412757024e-06, "loss": 0.6755517005920411, "step": 9410, "token_acc": 0.7892623243070802 }, { "epoch": 0.6095281255310712, "grad_norm": 0.32935020327568054, "learning_rate": 7.878215996590883e-06, "loss": 0.7400174140930176, "step": 9415, "token_acc": 0.7739186711250134 }, { "epoch": 0.6098518260756973, "grad_norm": 0.20553426444530487, "learning_rate": 7.876136836352945e-06, "loss": 0.7237281799316406, "step": 9420, "token_acc": 0.7760082586883038 }, { "epoch": 0.6101755266203236, "grad_norm": 0.3271462321281433, "learning_rate": 7.874056932580713e-06, "loss": 0.7073060512542725, "step": 9425, "token_acc": 0.7812907084939519 }, { "epoch": 0.6104992271649498, "grad_norm": 0.3445647060871124, "learning_rate": 7.871976285811879e-06, "loss": 0.681760597229004, "step": 9430, "token_acc": 0.7846198875060446 }, { "epoch": 0.6108229277095759, "grad_norm": 0.3195056915283203, "learning_rate": 7.869894896584332e-06, "loss": 0.7125679969787597, "step": 9435, "token_acc": 0.7786476234120013 }, { "epoch": 0.6111466282542021, "grad_norm": 0.4243233799934387, "learning_rate": 7.867812765436143e-06, "loss": 0.7180163383483886, "step": 9440, "token_acc": 0.7784626635672682 }, { "epoch": 0.6114703287988282, "grad_norm": 0.29321080446243286, "learning_rate": 7.865729892905586e-06, "loss": 0.7207383155822754, "step": 9445, "token_acc": 0.7778652890870641 }, { "epoch": 0.6117940293434544, "grad_norm": 0.3121204376220703, "learning_rate": 7.863646279531121e-06, "loss": 0.6962215423583984, "step": 9450, "token_acc": 0.7827133086978104 }, { "epoch": 0.6121177298880806, "grad_norm": 0.37437790632247925, "learning_rate": 7.8615619258514e-06, "loss": 0.7004046440124512, "step": 9455, "token_acc": 0.7819563654683862 }, { "epoch": 0.6124414304327067, "grad_norm": 0.37039923667907715, "learning_rate": 7.859476832405269e-06, "loss": 0.7164533615112305, "step": 9460, "token_acc": 0.7783566671371925 }, { "epoch": 0.6127651309773329, "grad_norm": 0.33815813064575195, "learning_rate": 7.857390999731757e-06, "loss": 0.6850069999694824, "step": 9465, "token_acc": 0.7864458572334944 }, { "epoch": 0.613088831521959, "grad_norm": 0.34648555517196655, "learning_rate": 7.855304428370096e-06, "loss": 0.700870132446289, "step": 9470, "token_acc": 0.7823732185662869 }, { "epoch": 0.6134125320665852, "grad_norm": 0.26239755749702454, "learning_rate": 7.853217118859701e-06, "loss": 0.7058534622192383, "step": 9475, "token_acc": 0.7809998164661507 }, { "epoch": 0.6137362326112114, "grad_norm": 0.38902172446250916, "learning_rate": 7.85112907174018e-06, "loss": 0.7149907112121582, "step": 9480, "token_acc": 0.7794374649652125 }, { "epoch": 0.6140599331558375, "grad_norm": 0.4889015555381775, "learning_rate": 7.849040287551331e-06, "loss": 0.7081920623779296, "step": 9485, "token_acc": 0.7809065400083403 }, { "epoch": 0.6143836337004637, "grad_norm": 0.3036576509475708, "learning_rate": 7.846950766833145e-06, "loss": 0.6960248947143555, "step": 9490, "token_acc": 0.782497437888693 }, { "epoch": 0.6147073342450898, "grad_norm": 0.23296155035495758, "learning_rate": 7.8448605101258e-06, "loss": 0.7054732322692872, "step": 9495, "token_acc": 0.7817626357357489 }, { "epoch": 0.615031034789716, "grad_norm": 0.30839988589286804, "learning_rate": 7.842769517969665e-06, "loss": 0.716112756729126, "step": 9500, "token_acc": 0.7799625714963494 }, { "epoch": 0.6153547353343422, "grad_norm": 0.32120364904403687, "learning_rate": 7.840677790905301e-06, "loss": 0.6983295917510987, "step": 9505, "token_acc": 0.782251734033381 }, { "epoch": 0.6156784358789683, "grad_norm": 0.3269573748111725, "learning_rate": 7.83858532947346e-06, "loss": 0.706196403503418, "step": 9510, "token_acc": 0.7809801144863076 }, { "epoch": 0.6160021364235946, "grad_norm": 0.3076878786087036, "learning_rate": 7.83649213421508e-06, "loss": 0.7359274387359619, "step": 9515, "token_acc": 0.7730906326990618 }, { "epoch": 0.6163258369682207, "grad_norm": 0.2981308400630951, "learning_rate": 7.834398205671287e-06, "loss": 0.7113299369812012, "step": 9520, "token_acc": 0.7796173995247035 }, { "epoch": 0.6166495375128469, "grad_norm": 0.30661287903785706, "learning_rate": 7.832303544383406e-06, "loss": 0.6839289665222168, "step": 9525, "token_acc": 0.7866459689938109 }, { "epoch": 0.6169732380574731, "grad_norm": 0.2232719510793686, "learning_rate": 7.830208150892941e-06, "loss": 0.7013051033020019, "step": 9530, "token_acc": 0.7820599673817589 }, { "epoch": 0.6172969386020992, "grad_norm": 0.2918705642223358, "learning_rate": 7.828112025741594e-06, "loss": 0.7299245357513428, "step": 9535, "token_acc": 0.7762931772494658 }, { "epoch": 0.6176206391467254, "grad_norm": 0.33953213691711426, "learning_rate": 7.826015169471249e-06, "loss": 0.7183742523193359, "step": 9540, "token_acc": 0.7787968952134541 }, { "epoch": 0.6179443396913515, "grad_norm": 0.4424287974834442, "learning_rate": 7.82391758262398e-06, "loss": 0.7199279308319092, "step": 9545, "token_acc": 0.7768007029692582 }, { "epoch": 0.6182680402359777, "grad_norm": 0.3410221040248871, "learning_rate": 7.821819265742056e-06, "loss": 0.7143287181854248, "step": 9550, "token_acc": 0.7778936731966491 }, { "epoch": 0.6185917407806039, "grad_norm": 0.37617427110671997, "learning_rate": 7.81972021936793e-06, "loss": 0.7240738868713379, "step": 9555, "token_acc": 0.7761039888310182 }, { "epoch": 0.61891544132523, "grad_norm": 0.36224910616874695, "learning_rate": 7.81762044404424e-06, "loss": 0.7212194442749024, "step": 9560, "token_acc": 0.7774796049806784 }, { "epoch": 0.6192391418698562, "grad_norm": 0.33091801404953003, "learning_rate": 7.815519940313823e-06, "loss": 0.6938478469848632, "step": 9565, "token_acc": 0.7853762439301687 }, { "epoch": 0.6195628424144823, "grad_norm": 0.30263006687164307, "learning_rate": 7.813418708719692e-06, "loss": 0.7105530261993408, "step": 9570, "token_acc": 0.7794358602771739 }, { "epoch": 0.6198865429591085, "grad_norm": 0.32904091477394104, "learning_rate": 7.811316749805057e-06, "loss": 0.6834980010986328, "step": 9575, "token_acc": 0.7867894840776909 }, { "epoch": 0.6202102435037347, "grad_norm": 0.24396291375160217, "learning_rate": 7.809214064113311e-06, "loss": 0.7153246879577637, "step": 9580, "token_acc": 0.7786395109848813 }, { "epoch": 0.6205339440483608, "grad_norm": 0.3435192406177521, "learning_rate": 7.80711065218804e-06, "loss": 0.700968074798584, "step": 9585, "token_acc": 0.7810113694213474 }, { "epoch": 0.620857644592987, "grad_norm": 0.22906611859798431, "learning_rate": 7.805006514573012e-06, "loss": 0.710277795791626, "step": 9590, "token_acc": 0.7797882823439922 }, { "epoch": 0.6211813451376131, "grad_norm": 0.308420866727829, "learning_rate": 7.802901651812187e-06, "loss": 0.71780424118042, "step": 9595, "token_acc": 0.7773167106500439 }, { "epoch": 0.6215050456822394, "grad_norm": 0.2831084132194519, "learning_rate": 7.800796064449711e-06, "loss": 0.7044413566589356, "step": 9600, "token_acc": 0.780862355530742 }, { "epoch": 0.6218287462268656, "grad_norm": 0.3427039086818695, "learning_rate": 7.798689753029914e-06, "loss": 0.7126708984375, "step": 9605, "token_acc": 0.7790306118906609 }, { "epoch": 0.6221524467714917, "grad_norm": 0.2857578694820404, "learning_rate": 7.796582718097321e-06, "loss": 0.7030078887939453, "step": 9610, "token_acc": 0.7815655057577057 }, { "epoch": 0.6224761473161179, "grad_norm": 0.26336273550987244, "learning_rate": 7.794474960196634e-06, "loss": 0.7025856971740723, "step": 9615, "token_acc": 0.7822346948113351 }, { "epoch": 0.622799847860744, "grad_norm": 0.3697330057621002, "learning_rate": 7.792366479872752e-06, "loss": 0.7221188545227051, "step": 9620, "token_acc": 0.7776913131659733 }, { "epoch": 0.6231235484053702, "grad_norm": 0.2590338885784149, "learning_rate": 7.790257277670752e-06, "loss": 0.7168818473815918, "step": 9625, "token_acc": 0.7782173159635206 }, { "epoch": 0.6234472489499964, "grad_norm": 0.3348991870880127, "learning_rate": 7.788147354135904e-06, "loss": 0.7187107086181641, "step": 9630, "token_acc": 0.7795833280208081 }, { "epoch": 0.6237709494946225, "grad_norm": 0.30452147126197815, "learning_rate": 7.786036709813662e-06, "loss": 0.7230438232421875, "step": 9635, "token_acc": 0.7763842305283976 }, { "epoch": 0.6240946500392487, "grad_norm": 0.34099188446998596, "learning_rate": 7.783925345249667e-06, "loss": 0.7358894348144531, "step": 9640, "token_acc": 0.7728891532249397 }, { "epoch": 0.6244183505838748, "grad_norm": 0.2890385389328003, "learning_rate": 7.781813260989743e-06, "loss": 0.6962027549743652, "step": 9645, "token_acc": 0.7842389443780443 }, { "epoch": 0.624742051128501, "grad_norm": 0.23422636091709137, "learning_rate": 7.779700457579905e-06, "loss": 0.7042006492614746, "step": 9650, "token_acc": 0.7813237798046675 }, { "epoch": 0.6250657516731272, "grad_norm": 0.40099331736564636, "learning_rate": 7.77758693556635e-06, "loss": 0.6839713096618653, "step": 9655, "token_acc": 0.7872552874144247 }, { "epoch": 0.6253894522177533, "grad_norm": 0.35252025723457336, "learning_rate": 7.775472695495464e-06, "loss": 0.7187199592590332, "step": 9660, "token_acc": 0.778250172501516 }, { "epoch": 0.6257131527623795, "grad_norm": 0.37180906534194946, "learning_rate": 7.773357737913816e-06, "loss": 0.7308553218841553, "step": 9665, "token_acc": 0.7757379522806577 }, { "epoch": 0.6260368533070056, "grad_norm": 0.2786276638507843, "learning_rate": 7.77124206336816e-06, "loss": 0.6871025085449218, "step": 9670, "token_acc": 0.7852620234406574 }, { "epoch": 0.6263605538516318, "grad_norm": 0.3066733777523041, "learning_rate": 7.769125672405438e-06, "loss": 0.7314146041870118, "step": 9675, "token_acc": 0.7747099937790464 }, { "epoch": 0.626684254396258, "grad_norm": 0.3732783794403076, "learning_rate": 7.767008565572778e-06, "loss": 0.6935017108917236, "step": 9680, "token_acc": 0.7832690592455227 }, { "epoch": 0.6270079549408842, "grad_norm": 0.40411150455474854, "learning_rate": 7.764890743417487e-06, "loss": 0.7128164768218994, "step": 9685, "token_acc": 0.779407282199069 }, { "epoch": 0.6273316554855104, "grad_norm": 0.35112693905830383, "learning_rate": 7.762772206487066e-06, "loss": 0.701027774810791, "step": 9690, "token_acc": 0.7824856858686594 }, { "epoch": 0.6276553560301366, "grad_norm": 0.3385133147239685, "learning_rate": 7.760652955329193e-06, "loss": 0.7136346340179444, "step": 9695, "token_acc": 0.7781356561666498 }, { "epoch": 0.6279790565747627, "grad_norm": 0.2740802466869354, "learning_rate": 7.758532990491732e-06, "loss": 0.7046008586883545, "step": 9700, "token_acc": 0.7824672235647823 }, { "epoch": 0.6283027571193889, "grad_norm": 0.3379974365234375, "learning_rate": 7.756412312522733e-06, "loss": 0.7069510459899903, "step": 9705, "token_acc": 0.7810736947492322 }, { "epoch": 0.628626457664015, "grad_norm": 0.18300144374370575, "learning_rate": 7.754290921970436e-06, "loss": 0.7170768737792969, "step": 9710, "token_acc": 0.7772754229452163 }, { "epoch": 0.6289501582086412, "grad_norm": 0.26490461826324463, "learning_rate": 7.752168819383252e-06, "loss": 0.7137721061706543, "step": 9715, "token_acc": 0.7804625495654081 }, { "epoch": 0.6292738587532674, "grad_norm": 0.3793764114379883, "learning_rate": 7.750046005309788e-06, "loss": 0.6838833332061768, "step": 9720, "token_acc": 0.7852183783641091 }, { "epoch": 0.6295975592978935, "grad_norm": 0.32827192544937134, "learning_rate": 7.74792248029883e-06, "loss": 0.7134094715118409, "step": 9725, "token_acc": 0.7781370997504207 }, { "epoch": 0.6299212598425197, "grad_norm": 0.3781633973121643, "learning_rate": 7.745798244899345e-06, "loss": 0.7010651588439941, "step": 9730, "token_acc": 0.7826190253349556 }, { "epoch": 0.6302449603871458, "grad_norm": 0.266594797372818, "learning_rate": 7.743673299660492e-06, "loss": 0.7141504287719727, "step": 9735, "token_acc": 0.7800997063443283 }, { "epoch": 0.630568660931772, "grad_norm": 0.3389758765697479, "learning_rate": 7.741547645131605e-06, "loss": 0.6841473579406738, "step": 9740, "token_acc": 0.7855547093170856 }, { "epoch": 0.6308923614763982, "grad_norm": 0.22590194642543793, "learning_rate": 7.739421281862205e-06, "loss": 0.7043570518493653, "step": 9745, "token_acc": 0.7828054945762154 }, { "epoch": 0.6312160620210243, "grad_norm": 0.35060998797416687, "learning_rate": 7.737294210401998e-06, "loss": 0.7106153488159179, "step": 9750, "token_acc": 0.7785500101646676 }, { "epoch": 0.6315397625656505, "grad_norm": 0.3018825054168701, "learning_rate": 7.73516643130087e-06, "loss": 0.7249809265136719, "step": 9755, "token_acc": 0.7765213287694963 }, { "epoch": 0.6318634631102766, "grad_norm": 0.38264936208724976, "learning_rate": 7.733037945108888e-06, "loss": 0.6813340187072754, "step": 9760, "token_acc": 0.7879084072930106 }, { "epoch": 0.6321871636549028, "grad_norm": 0.3224806785583496, "learning_rate": 7.73090875237631e-06, "loss": 0.704338788986206, "step": 9765, "token_acc": 0.7824547510013887 }, { "epoch": 0.6325108641995291, "grad_norm": 0.29332172870635986, "learning_rate": 7.72877885365357e-06, "loss": 0.6869424819946289, "step": 9770, "token_acc": 0.7849087704956479 }, { "epoch": 0.6328345647441552, "grad_norm": 0.39631906151771545, "learning_rate": 7.726648249491286e-06, "loss": 0.6924001693725585, "step": 9775, "token_acc": 0.7832505135750375 }, { "epoch": 0.6331582652887814, "grad_norm": 0.3335081934928894, "learning_rate": 7.724516940440255e-06, "loss": 0.6918114185333252, "step": 9780, "token_acc": 0.7842091694820966 }, { "epoch": 0.6334819658334075, "grad_norm": 0.27285635471343994, "learning_rate": 7.722384927051464e-06, "loss": 0.6935969352722168, "step": 9785, "token_acc": 0.7845064639350994 }, { "epoch": 0.6338056663780337, "grad_norm": 0.2553056478500366, "learning_rate": 7.720252209876075e-06, "loss": 0.6893881797790528, "step": 9790, "token_acc": 0.7859397236014042 }, { "epoch": 0.6341293669226599, "grad_norm": 0.3073090612888336, "learning_rate": 7.718118789465436e-06, "loss": 0.7196452140808105, "step": 9795, "token_acc": 0.7765455712620036 }, { "epoch": 0.634453067467286, "grad_norm": 0.2924577593803406, "learning_rate": 7.715984666371075e-06, "loss": 0.7031521797180176, "step": 9800, "token_acc": 0.7808514603690194 }, { "epoch": 0.6347767680119122, "grad_norm": 0.36118853092193604, "learning_rate": 7.713849841144704e-06, "loss": 0.6943472862243653, "step": 9805, "token_acc": 0.7848453296611023 }, { "epoch": 0.6351004685565383, "grad_norm": 0.3595423400402069, "learning_rate": 7.71171431433821e-06, "loss": 0.725434398651123, "step": 9810, "token_acc": 0.776618630628146 }, { "epoch": 0.6354241691011645, "grad_norm": 0.3355553448200226, "learning_rate": 7.709578086503671e-06, "loss": 0.7323379516601562, "step": 9815, "token_acc": 0.7740240589317622 }, { "epoch": 0.6357478696457907, "grad_norm": 0.3409242630004883, "learning_rate": 7.707441158193338e-06, "loss": 0.7201201438903808, "step": 9820, "token_acc": 0.7770689534964791 }, { "epoch": 0.6360715701904168, "grad_norm": 0.25348103046417236, "learning_rate": 7.705303529959645e-06, "loss": 0.7156942844390869, "step": 9825, "token_acc": 0.779463608992233 }, { "epoch": 0.636395270735043, "grad_norm": 0.2947019040584564, "learning_rate": 7.703165202355214e-06, "loss": 0.6805661678314209, "step": 9830, "token_acc": 0.7867179916317991 }, { "epoch": 0.6367189712796691, "grad_norm": 0.42821481823921204, "learning_rate": 7.701026175932837e-06, "loss": 0.6847376823425293, "step": 9835, "token_acc": 0.7854319327731093 }, { "epoch": 0.6370426718242953, "grad_norm": 0.27276331186294556, "learning_rate": 7.698886451245493e-06, "loss": 0.7017903327941895, "step": 9840, "token_acc": 0.7828457586243054 }, { "epoch": 0.6373663723689215, "grad_norm": 0.33250170946121216, "learning_rate": 7.69674602884634e-06, "loss": 0.7059990882873535, "step": 9845, "token_acc": 0.7814387874225712 }, { "epoch": 0.6376900729135476, "grad_norm": 0.3866088092327118, "learning_rate": 7.694604909288717e-06, "loss": 0.6943732261657715, "step": 9850, "token_acc": 0.7839986153757396 }, { "epoch": 0.6380137734581739, "grad_norm": 0.3051607310771942, "learning_rate": 7.692463093126143e-06, "loss": 0.678246545791626, "step": 9855, "token_acc": 0.7880176936816253 }, { "epoch": 0.6383374740028, "grad_norm": 0.36764347553253174, "learning_rate": 7.690320580912318e-06, "loss": 0.7232205390930175, "step": 9860, "token_acc": 0.7776189201752285 }, { "epoch": 0.6386611745474262, "grad_norm": 0.3580184578895569, "learning_rate": 7.688177373201118e-06, "loss": 0.6894497394561767, "step": 9865, "token_acc": 0.7846736908094861 }, { "epoch": 0.6389848750920524, "grad_norm": 0.31645411252975464, "learning_rate": 7.686033470546603e-06, "loss": 0.7014567852020264, "step": 9870, "token_acc": 0.7824074914251493 }, { "epoch": 0.6393085756366785, "grad_norm": 0.34210219979286194, "learning_rate": 7.683888873503011e-06, "loss": 0.7025083065032959, "step": 9875, "token_acc": 0.7821278759374602 }, { "epoch": 0.6396322761813047, "grad_norm": 0.36374807357788086, "learning_rate": 7.681743582624761e-06, "loss": 0.7051816940307617, "step": 9880, "token_acc": 0.7802461566558176 }, { "epoch": 0.6399559767259309, "grad_norm": 0.33456867933273315, "learning_rate": 7.67959759846645e-06, "loss": 0.700702714920044, "step": 9885, "token_acc": 0.7825183990321605 }, { "epoch": 0.640279677270557, "grad_norm": 0.25516125559806824, "learning_rate": 7.677450921582852e-06, "loss": 0.699535322189331, "step": 9890, "token_acc": 0.782639740256241 }, { "epoch": 0.6406033778151832, "grad_norm": 0.26720985770225525, "learning_rate": 7.675303552528925e-06, "loss": 0.6860030174255372, "step": 9895, "token_acc": 0.7856786675974868 }, { "epoch": 0.6409270783598093, "grad_norm": 0.3277592957019806, "learning_rate": 7.673155491859803e-06, "loss": 0.6873698234558105, "step": 9900, "token_acc": 0.7854722932540661 }, { "epoch": 0.6412507789044355, "grad_norm": 0.35469719767570496, "learning_rate": 7.671006740130797e-06, "loss": 0.7327771186828613, "step": 9905, "token_acc": 0.7762418041938168 }, { "epoch": 0.6415744794490617, "grad_norm": 0.33306148648262024, "learning_rate": 7.668857297897403e-06, "loss": 0.6908498764038086, "step": 9910, "token_acc": 0.7852114199533955 }, { "epoch": 0.6418981799936878, "grad_norm": 0.29405251145362854, "learning_rate": 7.666707165715287e-06, "loss": 0.7029991149902344, "step": 9915, "token_acc": 0.7844136974107915 }, { "epoch": 0.642221880538314, "grad_norm": 0.4193579852581024, "learning_rate": 7.664556344140302e-06, "loss": 0.6848590850830079, "step": 9920, "token_acc": 0.7859428392855929 }, { "epoch": 0.6425455810829401, "grad_norm": 0.2839663326740265, "learning_rate": 7.662404833728471e-06, "loss": 0.7016404151916504, "step": 9925, "token_acc": 0.780850284648933 }, { "epoch": 0.6428692816275663, "grad_norm": 0.3428364098072052, "learning_rate": 7.660252635036004e-06, "loss": 0.6782346725463867, "step": 9930, "token_acc": 0.7879125388358051 }, { "epoch": 0.6431929821721925, "grad_norm": 0.31118902564048767, "learning_rate": 7.658099748619277e-06, "loss": 0.6909263610839844, "step": 9935, "token_acc": 0.7841884663398169 }, { "epoch": 0.6435166827168187, "grad_norm": 0.32777532935142517, "learning_rate": 7.655946175034856e-06, "loss": 0.7054266452789306, "step": 9940, "token_acc": 0.7808518800180363 }, { "epoch": 0.6438403832614449, "grad_norm": 0.25009462237358093, "learning_rate": 7.653791914839478e-06, "loss": 0.7081635475158692, "step": 9945, "token_acc": 0.7809783454312986 }, { "epoch": 0.644164083806071, "grad_norm": 0.3202921152114868, "learning_rate": 7.651636968590058e-06, "loss": 0.699359130859375, "step": 9950, "token_acc": 0.7839565316053554 }, { "epoch": 0.6444877843506972, "grad_norm": 0.3035810887813568, "learning_rate": 7.64948133684369e-06, "loss": 0.7010254859924316, "step": 9955, "token_acc": 0.7829120256119523 }, { "epoch": 0.6448114848953234, "grad_norm": 0.2854520380496979, "learning_rate": 7.647325020157645e-06, "loss": 0.6898749828338623, "step": 9960, "token_acc": 0.7866070160488567 }, { "epoch": 0.6451351854399495, "grad_norm": 0.3059357702732086, "learning_rate": 7.645168019089372e-06, "loss": 0.6854417800903321, "step": 9965, "token_acc": 0.78574601482384 }, { "epoch": 0.6454588859845757, "grad_norm": 0.3981678783893585, "learning_rate": 7.64301033419649e-06, "loss": 0.6831725120544434, "step": 9970, "token_acc": 0.7884600333924658 }, { "epoch": 0.6457825865292018, "grad_norm": 0.2908366024494171, "learning_rate": 7.640851966036807e-06, "loss": 0.6723813056945801, "step": 9975, "token_acc": 0.7907421882212471 }, { "epoch": 0.646106287073828, "grad_norm": 0.27583250403404236, "learning_rate": 7.638692915168296e-06, "loss": 0.7177243232727051, "step": 9980, "token_acc": 0.7792614119834007 }, { "epoch": 0.6464299876184542, "grad_norm": 0.37656885385513306, "learning_rate": 7.636533182149112e-06, "loss": 0.7091771125793457, "step": 9985, "token_acc": 0.7809161314973474 }, { "epoch": 0.6467536881630803, "grad_norm": 0.423343688249588, "learning_rate": 7.634372767537588e-06, "loss": 0.7206572532653809, "step": 9990, "token_acc": 0.7782707451920077 }, { "epoch": 0.6470773887077065, "grad_norm": 0.233306422829628, "learning_rate": 7.632211671892229e-06, "loss": 0.7041025161743164, "step": 9995, "token_acc": 0.7811255589777956 }, { "epoch": 0.6474010892523326, "grad_norm": 0.34182119369506836, "learning_rate": 7.63004989577172e-06, "loss": 0.7243337631225586, "step": 10000, "token_acc": 0.7765364920881406 }, { "epoch": 0.6477247897969588, "grad_norm": 0.3255411982536316, "learning_rate": 7.627887439734918e-06, "loss": 0.6996337890625, "step": 10005, "token_acc": 0.7828133808307246 }, { "epoch": 0.648048490341585, "grad_norm": 0.35574871301651, "learning_rate": 7.625724304340858e-06, "loss": 0.7057741641998291, "step": 10010, "token_acc": 0.7801938285216492 }, { "epoch": 0.6483721908862111, "grad_norm": 0.3120684325695038, "learning_rate": 7.623560490148751e-06, "loss": 0.6885069847106934, "step": 10015, "token_acc": 0.7852622984282507 }, { "epoch": 0.6486958914308373, "grad_norm": 0.29537802934646606, "learning_rate": 7.621395997717982e-06, "loss": 0.7123191833496094, "step": 10020, "token_acc": 0.7806729495382027 }, { "epoch": 0.6490195919754636, "grad_norm": 0.36193782091140747, "learning_rate": 7.61923082760811e-06, "loss": 0.706165885925293, "step": 10025, "token_acc": 0.782096827495043 }, { "epoch": 0.6493432925200897, "grad_norm": 0.21654969453811646, "learning_rate": 7.617064980378878e-06, "loss": 0.7028169631958008, "step": 10030, "token_acc": 0.7826590498002525 }, { "epoch": 0.6496669930647159, "grad_norm": 0.24289897084236145, "learning_rate": 7.614898456590191e-06, "loss": 0.728818702697754, "step": 10035, "token_acc": 0.7758098655714266 }, { "epoch": 0.649990693609342, "grad_norm": 0.23034371435642242, "learning_rate": 7.6127312568021375e-06, "loss": 0.6984751701354981, "step": 10040, "token_acc": 0.7831755322945937 }, { "epoch": 0.6503143941539682, "grad_norm": 0.4147498905658722, "learning_rate": 7.610563381574979e-06, "loss": 0.6999992847442627, "step": 10045, "token_acc": 0.7837194449282936 }, { "epoch": 0.6506380946985943, "grad_norm": 0.34747442603111267, "learning_rate": 7.608394831469151e-06, "loss": 0.7056380271911621, "step": 10050, "token_acc": 0.7795817715525745 }, { "epoch": 0.6509617952432205, "grad_norm": 0.29817110300064087, "learning_rate": 7.606225607045261e-06, "loss": 0.7128059387207031, "step": 10055, "token_acc": 0.7798632074783801 }, { "epoch": 0.6512854957878467, "grad_norm": 0.3617613613605499, "learning_rate": 7.604055708864098e-06, "loss": 0.7316349983215332, "step": 10060, "token_acc": 0.7751039689909961 }, { "epoch": 0.6516091963324728, "grad_norm": 0.3784034252166748, "learning_rate": 7.601885137486617e-06, "loss": 0.6833817481994628, "step": 10065, "token_acc": 0.7870123777063296 }, { "epoch": 0.651932896877099, "grad_norm": 0.30848830938339233, "learning_rate": 7.59971389347395e-06, "loss": 0.6795994281768799, "step": 10070, "token_acc": 0.7875825644128472 }, { "epoch": 0.6522565974217251, "grad_norm": 0.391329288482666, "learning_rate": 7.597541977387408e-06, "loss": 0.7097649574279785, "step": 10075, "token_acc": 0.7806558935361216 }, { "epoch": 0.6525802979663513, "grad_norm": 0.350898414850235, "learning_rate": 7.59536938978847e-06, "loss": 0.6796722412109375, "step": 10080, "token_acc": 0.7875808091210492 }, { "epoch": 0.6529039985109775, "grad_norm": 0.37305405735969543, "learning_rate": 7.5931961312387846e-06, "loss": 0.7178545951843261, "step": 10085, "token_acc": 0.7775507284876474 }, { "epoch": 0.6532276990556036, "grad_norm": 0.28935474157333374, "learning_rate": 7.591022202300186e-06, "loss": 0.685245418548584, "step": 10090, "token_acc": 0.7858371541299775 }, { "epoch": 0.6535513996002298, "grad_norm": 0.2635488212108612, "learning_rate": 7.58884760353467e-06, "loss": 0.6948014259338379, "step": 10095, "token_acc": 0.7844250854310054 }, { "epoch": 0.653875100144856, "grad_norm": 1.2750020027160645, "learning_rate": 7.586672335504414e-06, "loss": 0.6859303951263428, "step": 10100, "token_acc": 0.7855185752276573 }, { "epoch": 0.6541988006894821, "grad_norm": 0.36207109689712524, "learning_rate": 7.584496398771761e-06, "loss": 0.6944615364074707, "step": 10105, "token_acc": 0.7835789024129831 }, { "epoch": 0.6545225012341084, "grad_norm": 0.40913674235343933, "learning_rate": 7.582319793899234e-06, "loss": 0.6992920875549317, "step": 10110, "token_acc": 0.7826159093003964 }, { "epoch": 0.6548462017787345, "grad_norm": 0.24518215656280518, "learning_rate": 7.580142521449525e-06, "loss": 0.6713218212127685, "step": 10115, "token_acc": 0.7890157588081179 }, { "epoch": 0.6551699023233607, "grad_norm": 0.40014398097991943, "learning_rate": 7.577964581985498e-06, "loss": 0.6979668617248536, "step": 10120, "token_acc": 0.7838488688448246 }, { "epoch": 0.6554936028679869, "grad_norm": 0.36252090334892273, "learning_rate": 7.575785976070189e-06, "loss": 0.6992114067077637, "step": 10125, "token_acc": 0.7835682995852017 }, { "epoch": 0.655817303412613, "grad_norm": 0.28920596837997437, "learning_rate": 7.573606704266811e-06, "loss": 0.7052535057067871, "step": 10130, "token_acc": 0.7820954288536465 }, { "epoch": 0.6561410039572392, "grad_norm": 0.3680652379989624, "learning_rate": 7.571426767138743e-06, "loss": 0.7003217697143554, "step": 10135, "token_acc": 0.7816536217053406 }, { "epoch": 0.6564647045018653, "grad_norm": 0.26246729493141174, "learning_rate": 7.56924616524954e-06, "loss": 0.7169714450836182, "step": 10140, "token_acc": 0.7784233635560256 }, { "epoch": 0.6567884050464915, "grad_norm": 0.2351849526166916, "learning_rate": 7.567064899162928e-06, "loss": 0.6969699382781982, "step": 10145, "token_acc": 0.781965242499109 }, { "epoch": 0.6571121055911177, "grad_norm": 0.36554181575775146, "learning_rate": 7.564882969442804e-06, "loss": 0.6886820793151855, "step": 10150, "token_acc": 0.784788919724272 }, { "epoch": 0.6574358061357438, "grad_norm": 0.30798104405403137, "learning_rate": 7.562700376653238e-06, "loss": 0.6918981552124024, "step": 10155, "token_acc": 0.7839943725988854 }, { "epoch": 0.65775950668037, "grad_norm": 0.2773052752017975, "learning_rate": 7.560517121358468e-06, "loss": 0.7018735885620118, "step": 10160, "token_acc": 0.7817493126189697 }, { "epoch": 0.6580832072249961, "grad_norm": 0.34875956177711487, "learning_rate": 7.5583332041229094e-06, "loss": 0.712430477142334, "step": 10165, "token_acc": 0.7803075894349716 }, { "epoch": 0.6584069077696223, "grad_norm": 0.27368253469467163, "learning_rate": 7.556148625511141e-06, "loss": 0.6846489906311035, "step": 10170, "token_acc": 0.7865552970755763 }, { "epoch": 0.6587306083142485, "grad_norm": 0.2971063554286957, "learning_rate": 7.5539633860879194e-06, "loss": 0.6894997596740723, "step": 10175, "token_acc": 0.7850273728645868 }, { "epoch": 0.6590543088588746, "grad_norm": 0.2906727194786072, "learning_rate": 7.5517774864181684e-06, "loss": 0.6800830364227295, "step": 10180, "token_acc": 0.7863381646440212 }, { "epoch": 0.6593780094035008, "grad_norm": 0.31255748867988586, "learning_rate": 7.549590927066981e-06, "loss": 0.7044157028198242, "step": 10185, "token_acc": 0.7814662279158647 }, { "epoch": 0.6597017099481269, "grad_norm": 0.32539495825767517, "learning_rate": 7.547403708599628e-06, "loss": 0.6808621883392334, "step": 10190, "token_acc": 0.7873823795332017 }, { "epoch": 0.6600254104927532, "grad_norm": 0.22185613214969635, "learning_rate": 7.54521583158154e-06, "loss": 0.7039869785308838, "step": 10195, "token_acc": 0.78306743555693 }, { "epoch": 0.6603491110373794, "grad_norm": 0.26158756017684937, "learning_rate": 7.543027296578328e-06, "loss": 0.7181489944458008, "step": 10200, "token_acc": 0.7789908938858948 }, { "epoch": 0.6606728115820055, "grad_norm": 0.21660135686397552, "learning_rate": 7.540838104155767e-06, "loss": 0.7263253688812256, "step": 10205, "token_acc": 0.7755453748167773 }, { "epoch": 0.6609965121266317, "grad_norm": 0.35337725281715393, "learning_rate": 7.538648254879801e-06, "loss": 0.7032235145568848, "step": 10210, "token_acc": 0.7813837116542172 }, { "epoch": 0.6613202126712578, "grad_norm": 0.27680906653404236, "learning_rate": 7.53645774931655e-06, "loss": 0.7052440643310547, "step": 10215, "token_acc": 0.7811937234955818 }, { "epoch": 0.661643913215884, "grad_norm": 0.4029751718044281, "learning_rate": 7.534266588032299e-06, "loss": 0.7047163009643554, "step": 10220, "token_acc": 0.7819366630905551 }, { "epoch": 0.6619676137605102, "grad_norm": 0.29114460945129395, "learning_rate": 7.532074771593503e-06, "loss": 0.7083124637603759, "step": 10225, "token_acc": 0.7809109535066981 }, { "epoch": 0.6622913143051363, "grad_norm": 0.27010107040405273, "learning_rate": 7.5298823005667864e-06, "loss": 0.7288601875305176, "step": 10230, "token_acc": 0.776026132651612 }, { "epoch": 0.6626150148497625, "grad_norm": 0.3095983862876892, "learning_rate": 7.527689175518944e-06, "loss": 0.7080515861511231, "step": 10235, "token_acc": 0.7806933189872567 }, { "epoch": 0.6629387153943886, "grad_norm": 0.33298614621162415, "learning_rate": 7.52549539701694e-06, "loss": 0.7071399211883544, "step": 10240, "token_acc": 0.7805679718124324 }, { "epoch": 0.6632624159390148, "grad_norm": 0.35421493649482727, "learning_rate": 7.523300965627904e-06, "loss": 0.7150492668151855, "step": 10245, "token_acc": 0.7792013366750209 }, { "epoch": 0.663586116483641, "grad_norm": 0.3351483643054962, "learning_rate": 7.5211058819191395e-06, "loss": 0.699808931350708, "step": 10250, "token_acc": 0.7841271777357647 }, { "epoch": 0.6639098170282671, "grad_norm": 0.29657065868377686, "learning_rate": 7.518910146458113e-06, "loss": 0.7097601413726806, "step": 10255, "token_acc": 0.7785382481703038 }, { "epoch": 0.6642335175728933, "grad_norm": 0.45105037093162537, "learning_rate": 7.516713759812465e-06, "loss": 0.729555892944336, "step": 10260, "token_acc": 0.7760006375635264 }, { "epoch": 0.6645572181175194, "grad_norm": 0.39397791028022766, "learning_rate": 7.514516722550002e-06, "loss": 0.6964335441589355, "step": 10265, "token_acc": 0.7828410707526854 }, { "epoch": 0.6648809186621456, "grad_norm": 0.4056485891342163, "learning_rate": 7.512319035238696e-06, "loss": 0.71956787109375, "step": 10270, "token_acc": 0.7757394693371877 }, { "epoch": 0.6652046192067718, "grad_norm": 0.22382338345050812, "learning_rate": 7.510120698446694e-06, "loss": 0.7142232894897461, "step": 10275, "token_acc": 0.7790598657328255 }, { "epoch": 0.665528319751398, "grad_norm": 0.29091453552246094, "learning_rate": 7.507921712742301e-06, "loss": 0.6992561340332031, "step": 10280, "token_acc": 0.7823234598490821 }, { "epoch": 0.6658520202960242, "grad_norm": 0.31568294763565063, "learning_rate": 7.505722078694e-06, "loss": 0.6953860282897949, "step": 10285, "token_acc": 0.7848354873299848 }, { "epoch": 0.6661757208406504, "grad_norm": 0.25217700004577637, "learning_rate": 7.503521796870434e-06, "loss": 0.6784409523010254, "step": 10290, "token_acc": 0.788411305237602 }, { "epoch": 0.6664994213852765, "grad_norm": 0.2764016389846802, "learning_rate": 7.5013208678404185e-06, "loss": 0.7315855979919433, "step": 10295, "token_acc": 0.7756526385757295 }, { "epoch": 0.6668231219299027, "grad_norm": 0.4191224277019501, "learning_rate": 7.499119292172932e-06, "loss": 0.7077093124389648, "step": 10300, "token_acc": 0.7807379795877987 }, { "epoch": 0.6671468224745288, "grad_norm": 0.24772964417934418, "learning_rate": 7.496917070437123e-06, "loss": 0.6855806350708008, "step": 10305, "token_acc": 0.7850118351707273 }, { "epoch": 0.667470523019155, "grad_norm": 0.28304213285446167, "learning_rate": 7.494714203202308e-06, "loss": 0.7222174167633056, "step": 10310, "token_acc": 0.7766850425462438 }, { "epoch": 0.6677942235637812, "grad_norm": 0.3447459042072296, "learning_rate": 7.4925106910379655e-06, "loss": 0.6913362503051758, "step": 10315, "token_acc": 0.7846296555141873 }, { "epoch": 0.6681179241084073, "grad_norm": 0.360443115234375, "learning_rate": 7.490306534513747e-06, "loss": 0.7129812240600586, "step": 10320, "token_acc": 0.7813644535177794 }, { "epoch": 0.6684416246530335, "grad_norm": 0.40979859232902527, "learning_rate": 7.488101734199467e-06, "loss": 0.7129000663757324, "step": 10325, "token_acc": 0.7811591996664173 }, { "epoch": 0.6687653251976596, "grad_norm": 0.3723706901073456, "learning_rate": 7.485896290665104e-06, "loss": 0.7021889686584473, "step": 10330, "token_acc": 0.7827303994175684 }, { "epoch": 0.6690890257422858, "grad_norm": 0.3819648027420044, "learning_rate": 7.483690204480811e-06, "loss": 0.6785342216491699, "step": 10335, "token_acc": 0.7890471544715447 }, { "epoch": 0.669412726286912, "grad_norm": 0.3803238868713379, "learning_rate": 7.481483476216896e-06, "loss": 0.6939605712890625, "step": 10340, "token_acc": 0.7842020750988142 }, { "epoch": 0.6697364268315381, "grad_norm": 0.28052088618278503, "learning_rate": 7.479276106443844e-06, "loss": 0.6817453384399415, "step": 10345, "token_acc": 0.7863209655789003 }, { "epoch": 0.6700601273761643, "grad_norm": 0.41602376103401184, "learning_rate": 7.477068095732298e-06, "loss": 0.7162375450134277, "step": 10350, "token_acc": 0.7806447065758533 }, { "epoch": 0.6703838279207904, "grad_norm": 0.34564125537872314, "learning_rate": 7.474859444653068e-06, "loss": 0.6918745040893555, "step": 10355, "token_acc": 0.7862542539311032 }, { "epoch": 0.6707075284654166, "grad_norm": 0.34751707315444946, "learning_rate": 7.4726501537771345e-06, "loss": 0.6588020324707031, "step": 10360, "token_acc": 0.7924962227065477 }, { "epoch": 0.6710312290100429, "grad_norm": 0.28858116269111633, "learning_rate": 7.470440223675638e-06, "loss": 0.6959164142608643, "step": 10365, "token_acc": 0.7823237952009453 }, { "epoch": 0.671354929554669, "grad_norm": 0.29387718439102173, "learning_rate": 7.468229654919886e-06, "loss": 0.7053950309753418, "step": 10370, "token_acc": 0.7808690131236787 }, { "epoch": 0.6716786300992952, "grad_norm": 0.3478764593601227, "learning_rate": 7.466018448081353e-06, "loss": 0.7110350608825684, "step": 10375, "token_acc": 0.7808695183708652 }, { "epoch": 0.6720023306439213, "grad_norm": 0.3086705803871155, "learning_rate": 7.463806603731671e-06, "loss": 0.7074977874755859, "step": 10380, "token_acc": 0.7808510341751687 }, { "epoch": 0.6723260311885475, "grad_norm": 0.3013884127140045, "learning_rate": 7.4615941224426504e-06, "loss": 0.7012791156768798, "step": 10385, "token_acc": 0.7814613315000033 }, { "epoch": 0.6726497317331737, "grad_norm": 0.29125404357910156, "learning_rate": 7.459381004786253e-06, "loss": 0.7143424987792969, "step": 10390, "token_acc": 0.7794171779141105 }, { "epoch": 0.6729734322777998, "grad_norm": 0.3248315453529358, "learning_rate": 7.457167251334611e-06, "loss": 0.69498291015625, "step": 10395, "token_acc": 0.7829187706502089 }, { "epoch": 0.673297132822426, "grad_norm": 0.30164945125579834, "learning_rate": 7.454952862660023e-06, "loss": 0.6883280277252197, "step": 10400, "token_acc": 0.7847390151305386 }, { "epoch": 0.6736208333670521, "grad_norm": 0.4000806510448456, "learning_rate": 7.452737839334947e-06, "loss": 0.7118727684020996, "step": 10405, "token_acc": 0.7808023463659022 }, { "epoch": 0.6739445339116783, "grad_norm": 0.3384380638599396, "learning_rate": 7.450522181932008e-06, "loss": 0.7035902500152588, "step": 10410, "token_acc": 0.7796197831375641 }, { "epoch": 0.6742682344563045, "grad_norm": 0.3735594153404236, "learning_rate": 7.448305891023993e-06, "loss": 0.7063961029052734, "step": 10415, "token_acc": 0.780952013280315 }, { "epoch": 0.6745919350009306, "grad_norm": 0.25268182158470154, "learning_rate": 7.446088967183856e-06, "loss": 0.7069631576538086, "step": 10420, "token_acc": 0.7809363900548918 }, { "epoch": 0.6749156355455568, "grad_norm": 0.3297654390335083, "learning_rate": 7.4438714109847125e-06, "loss": 0.6941992759704589, "step": 10425, "token_acc": 0.783660099883402 }, { "epoch": 0.6752393360901829, "grad_norm": 0.21722625195980072, "learning_rate": 7.441653222999839e-06, "loss": 0.7006170749664307, "step": 10430, "token_acc": 0.7820903294560735 }, { "epoch": 0.6755630366348091, "grad_norm": 0.2623775899410248, "learning_rate": 7.43943440380268e-06, "loss": 0.7047742366790771, "step": 10435, "token_acc": 0.7805198298831728 }, { "epoch": 0.6758867371794353, "grad_norm": 0.3184356093406677, "learning_rate": 7.437214953966841e-06, "loss": 0.7087725162506103, "step": 10440, "token_acc": 0.7811402817611649 }, { "epoch": 0.6762104377240614, "grad_norm": 0.36882996559143066, "learning_rate": 7.4349948740660895e-06, "loss": 0.7091902732849121, "step": 10445, "token_acc": 0.7817497323248023 }, { "epoch": 0.6765341382686877, "grad_norm": 0.2709851562976837, "learning_rate": 7.432774164674359e-06, "loss": 0.7102497100830079, "step": 10450, "token_acc": 0.7798441433560597 }, { "epoch": 0.6768578388133139, "grad_norm": 0.27318283915519714, "learning_rate": 7.4305528263657415e-06, "loss": 0.6942050933837891, "step": 10455, "token_acc": 0.7849210335398181 }, { "epoch": 0.67718153935794, "grad_norm": 0.34737491607666016, "learning_rate": 7.428330859714495e-06, "loss": 0.6956123828887939, "step": 10460, "token_acc": 0.7838231612998466 }, { "epoch": 0.6775052399025662, "grad_norm": 0.30862152576446533, "learning_rate": 7.426108265295039e-06, "loss": 0.6970366954803466, "step": 10465, "token_acc": 0.7825657649601312 }, { "epoch": 0.6778289404471923, "grad_norm": 0.3227487802505493, "learning_rate": 7.423885043681954e-06, "loss": 0.7313361644744873, "step": 10470, "token_acc": 0.7763878622467353 }, { "epoch": 0.6781526409918185, "grad_norm": 0.2965201437473297, "learning_rate": 7.421661195449986e-06, "loss": 0.7181426048278808, "step": 10475, "token_acc": 0.7789436817997651 }, { "epoch": 0.6784763415364446, "grad_norm": 0.23069150745868683, "learning_rate": 7.419436721174038e-06, "loss": 0.7035395622253418, "step": 10480, "token_acc": 0.7808521801562974 }, { "epoch": 0.6788000420810708, "grad_norm": 0.3358045518398285, "learning_rate": 7.417211621429179e-06, "loss": 0.6969357490539551, "step": 10485, "token_acc": 0.7830854582866669 }, { "epoch": 0.679123742625697, "grad_norm": 0.3312821388244629, "learning_rate": 7.414985896790637e-06, "loss": 0.6813709735870361, "step": 10490, "token_acc": 0.7869439514333557 }, { "epoch": 0.6794474431703231, "grad_norm": 0.2753281891345978, "learning_rate": 7.412759547833805e-06, "loss": 0.7013861179351807, "step": 10495, "token_acc": 0.7845480257797856 }, { "epoch": 0.6797711437149493, "grad_norm": 0.3101905584335327, "learning_rate": 7.410532575134232e-06, "loss": 0.7141872882843018, "step": 10500, "token_acc": 0.7789187014069529 }, { "epoch": 0.6800948442595754, "grad_norm": 0.3357197940349579, "learning_rate": 7.4083049792676356e-06, "loss": 0.6882461547851563, "step": 10505, "token_acc": 0.786525546591079 }, { "epoch": 0.6804185448042016, "grad_norm": 0.2317933738231659, "learning_rate": 7.406076760809886e-06, "loss": 0.6964920997619629, "step": 10510, "token_acc": 0.7839327700099449 }, { "epoch": 0.6807422453488278, "grad_norm": 0.40377292037010193, "learning_rate": 7.40384792033702e-06, "loss": 0.7081129074096679, "step": 10515, "token_acc": 0.7802092462751972 }, { "epoch": 0.6810659458934539, "grad_norm": 0.23602920770645142, "learning_rate": 7.401618458425237e-06, "loss": 0.7234807968139648, "step": 10520, "token_acc": 0.7755390989462695 }, { "epoch": 0.6813896464380801, "grad_norm": 0.3280966281890869, "learning_rate": 7.399388375650889e-06, "loss": 0.7057219505310058, "step": 10525, "token_acc": 0.7812341585718396 }, { "epoch": 0.6817133469827062, "grad_norm": 0.29809021949768066, "learning_rate": 7.397157672590497e-06, "loss": 0.7163875579833985, "step": 10530, "token_acc": 0.7793910022786522 }, { "epoch": 0.6820370475273325, "grad_norm": 0.2714220881462097, "learning_rate": 7.394926349820738e-06, "loss": 0.718202781677246, "step": 10535, "token_acc": 0.7800475844293173 }, { "epoch": 0.6823607480719587, "grad_norm": 0.3399449586868286, "learning_rate": 7.392694407918448e-06, "loss": 0.7240474700927735, "step": 10540, "token_acc": 0.7760308134923303 }, { "epoch": 0.6826844486165848, "grad_norm": 0.36051997542381287, "learning_rate": 7.390461847460628e-06, "loss": 0.6944803237915039, "step": 10545, "token_acc": 0.7840290837730912 }, { "epoch": 0.683008149161211, "grad_norm": 0.3842979967594147, "learning_rate": 7.388228669024434e-06, "loss": 0.6956440925598144, "step": 10550, "token_acc": 0.7840210767292701 }, { "epoch": 0.6833318497058372, "grad_norm": 0.31872937083244324, "learning_rate": 7.385994873187185e-06, "loss": 0.6983090400695801, "step": 10555, "token_acc": 0.7831389044925473 }, { "epoch": 0.6836555502504633, "grad_norm": 0.2974884808063507, "learning_rate": 7.383760460526357e-06, "loss": 0.6901850700378418, "step": 10560, "token_acc": 0.7852511359449834 }, { "epoch": 0.6839792507950895, "grad_norm": 0.2613639831542969, "learning_rate": 7.3815254316195885e-06, "loss": 0.7204180240631104, "step": 10565, "token_acc": 0.7777655936234228 }, { "epoch": 0.6843029513397156, "grad_norm": 0.2964121699333191, "learning_rate": 7.379289787044674e-06, "loss": 0.7151192665100098, "step": 10570, "token_acc": 0.7799234249912983 }, { "epoch": 0.6846266518843418, "grad_norm": 0.2887992262840271, "learning_rate": 7.377053527379569e-06, "loss": 0.7133140087127685, "step": 10575, "token_acc": 0.7812345548841163 }, { "epoch": 0.684950352428968, "grad_norm": 0.32154929637908936, "learning_rate": 7.374816653202388e-06, "loss": 0.6891469478607177, "step": 10580, "token_acc": 0.7846347684459605 }, { "epoch": 0.6852740529735941, "grad_norm": 0.40433552861213684, "learning_rate": 7.372579165091403e-06, "loss": 0.6956737518310547, "step": 10585, "token_acc": 0.7838066175728841 }, { "epoch": 0.6855977535182203, "grad_norm": 0.3094051480293274, "learning_rate": 7.370341063625049e-06, "loss": 0.6931437492370606, "step": 10590, "token_acc": 0.7834884181350228 }, { "epoch": 0.6859214540628464, "grad_norm": 0.39704465866088867, "learning_rate": 7.368102349381915e-06, "loss": 0.6939141273498535, "step": 10595, "token_acc": 0.7829794012938259 }, { "epoch": 0.6862451546074726, "grad_norm": 0.30415061116218567, "learning_rate": 7.365863022940748e-06, "loss": 0.7016851902008057, "step": 10600, "token_acc": 0.7825057419208747 }, { "epoch": 0.6865688551520988, "grad_norm": 0.3727577328681946, "learning_rate": 7.3636230848804564e-06, "loss": 0.7032808303833008, "step": 10605, "token_acc": 0.7811186301650774 }, { "epoch": 0.6868925556967249, "grad_norm": 0.3756391704082489, "learning_rate": 7.361382535780106e-06, "loss": 0.7273723602294921, "step": 10610, "token_acc": 0.7757696586197431 }, { "epoch": 0.6872162562413511, "grad_norm": 0.30724823474884033, "learning_rate": 7.359141376218919e-06, "loss": 0.7040385723114013, "step": 10615, "token_acc": 0.7819302108918438 }, { "epoch": 0.6875399567859773, "grad_norm": 0.41172489523887634, "learning_rate": 7.356899606776278e-06, "loss": 0.7425724029541015, "step": 10620, "token_acc": 0.7722577471716675 }, { "epoch": 0.6878636573306035, "grad_norm": 0.36540380120277405, "learning_rate": 7.3546572280317175e-06, "loss": 0.6951195240020752, "step": 10625, "token_acc": 0.7850881561908557 }, { "epoch": 0.6881873578752297, "grad_norm": 0.22588223218917847, "learning_rate": 7.352414240564939e-06, "loss": 0.6880623817443847, "step": 10630, "token_acc": 0.7860018286643131 }, { "epoch": 0.6885110584198558, "grad_norm": 0.37047919631004333, "learning_rate": 7.350170644955792e-06, "loss": 0.6756914138793946, "step": 10635, "token_acc": 0.7886348774025659 }, { "epoch": 0.688834758964482, "grad_norm": 0.3321722447872162, "learning_rate": 7.34792644178429e-06, "loss": 0.6912676811218261, "step": 10640, "token_acc": 0.7849737160164839 }, { "epoch": 0.6891584595091081, "grad_norm": 0.41266822814941406, "learning_rate": 7.3456816316306e-06, "loss": 0.7073948860168457, "step": 10645, "token_acc": 0.7809056438476175 }, { "epoch": 0.6894821600537343, "grad_norm": 0.34657078981399536, "learning_rate": 7.343436215075045e-06, "loss": 0.661536693572998, "step": 10650, "token_acc": 0.7922095725066314 }, { "epoch": 0.6898058605983605, "grad_norm": 0.26882219314575195, "learning_rate": 7.3411901926981086e-06, "loss": 0.6944403648376465, "step": 10655, "token_acc": 0.7842927127985303 }, { "epoch": 0.6901295611429866, "grad_norm": 0.259158194065094, "learning_rate": 7.338943565080429e-06, "loss": 0.7007663726806641, "step": 10660, "token_acc": 0.7815293557384856 }, { "epoch": 0.6904532616876128, "grad_norm": 0.45847001671791077, "learning_rate": 7.3366963328027994e-06, "loss": 0.6892756462097168, "step": 10665, "token_acc": 0.7856534681116281 }, { "epoch": 0.690776962232239, "grad_norm": 0.40400129556655884, "learning_rate": 7.334448496446171e-06, "loss": 0.6921749591827393, "step": 10670, "token_acc": 0.7832215085762649 }, { "epoch": 0.6911006627768651, "grad_norm": 0.292949378490448, "learning_rate": 7.332200056591651e-06, "loss": 0.7031766414642334, "step": 10675, "token_acc": 0.7830959306276674 }, { "epoch": 0.6914243633214913, "grad_norm": 0.34089091420173645, "learning_rate": 7.329951013820503e-06, "loss": 0.6857758045196534, "step": 10680, "token_acc": 0.7866531204273455 }, { "epoch": 0.6917480638661174, "grad_norm": 0.45981842279434204, "learning_rate": 7.327701368714145e-06, "loss": 0.7265476226806641, "step": 10685, "token_acc": 0.7763286574941584 }, { "epoch": 0.6920717644107436, "grad_norm": 0.24958620965480804, "learning_rate": 7.325451121854153e-06, "loss": 0.7216471672058106, "step": 10690, "token_acc": 0.7768414422925524 }, { "epoch": 0.6923954649553697, "grad_norm": 0.3621610701084137, "learning_rate": 7.3232002738222565e-06, "loss": 0.6842240810394287, "step": 10695, "token_acc": 0.7864249027786766 }, { "epoch": 0.6927191654999959, "grad_norm": 0.24469180405139923, "learning_rate": 7.32094882520034e-06, "loss": 0.6896920680999756, "step": 10700, "token_acc": 0.7845575353587146 }, { "epoch": 0.6930428660446222, "grad_norm": 0.29653480648994446, "learning_rate": 7.318696776570446e-06, "loss": 0.7018002510070801, "step": 10705, "token_acc": 0.7823276007817731 }, { "epoch": 0.6933665665892483, "grad_norm": 0.33931612968444824, "learning_rate": 7.316444128514771e-06, "loss": 0.708716869354248, "step": 10710, "token_acc": 0.7802705603292114 }, { "epoch": 0.6936902671338745, "grad_norm": 0.2589603066444397, "learning_rate": 7.314190881615664e-06, "loss": 0.6897697448730469, "step": 10715, "token_acc": 0.7855748217062761 }, { "epoch": 0.6940139676785007, "grad_norm": 0.28406551480293274, "learning_rate": 7.311937036455631e-06, "loss": 0.7079075813293457, "step": 10720, "token_acc": 0.7814034211006139 }, { "epoch": 0.6943376682231268, "grad_norm": 0.30840253829956055, "learning_rate": 7.309682593617334e-06, "loss": 0.7025496959686279, "step": 10725, "token_acc": 0.7805404545982669 }, { "epoch": 0.694661368767753, "grad_norm": 0.2931775748729706, "learning_rate": 7.307427553683588e-06, "loss": 0.6902694702148438, "step": 10730, "token_acc": 0.7855213096875736 }, { "epoch": 0.6949850693123791, "grad_norm": 0.2779039144515991, "learning_rate": 7.3051719172373594e-06, "loss": 0.7017487525939942, "step": 10735, "token_acc": 0.7833852224827357 }, { "epoch": 0.6953087698570053, "grad_norm": 0.31754058599472046, "learning_rate": 7.302915684861775e-06, "loss": 0.6965675354003906, "step": 10740, "token_acc": 0.7832591140826377 }, { "epoch": 0.6956324704016315, "grad_norm": 0.3249080181121826, "learning_rate": 7.300658857140111e-06, "loss": 0.7003520488739013, "step": 10745, "token_acc": 0.7803155168354132 }, { "epoch": 0.6959561709462576, "grad_norm": 0.27932438254356384, "learning_rate": 7.2984014346557985e-06, "loss": 0.6866867065429687, "step": 10750, "token_acc": 0.7855418393841388 }, { "epoch": 0.6962798714908838, "grad_norm": 0.3244665563106537, "learning_rate": 7.296143417992425e-06, "loss": 0.7098618984222412, "step": 10755, "token_acc": 0.781157925254691 }, { "epoch": 0.6966035720355099, "grad_norm": 0.25001710653305054, "learning_rate": 7.2938848077337256e-06, "loss": 0.7055132865905762, "step": 10760, "token_acc": 0.78070472322503 }, { "epoch": 0.6969272725801361, "grad_norm": 0.26143139600753784, "learning_rate": 7.2916256044635954e-06, "loss": 0.694080924987793, "step": 10765, "token_acc": 0.7832652796681574 }, { "epoch": 0.6972509731247623, "grad_norm": 0.3046739399433136, "learning_rate": 7.289365808766079e-06, "loss": 0.6893465518951416, "step": 10770, "token_acc": 0.7856695892871604 }, { "epoch": 0.6975746736693884, "grad_norm": 0.19633661210536957, "learning_rate": 7.287105421225375e-06, "loss": 0.6986988067626954, "step": 10775, "token_acc": 0.7832932860393862 }, { "epoch": 0.6978983742140146, "grad_norm": 0.3092215955257416, "learning_rate": 7.284844442425838e-06, "loss": 0.6822858333587647, "step": 10780, "token_acc": 0.7840490008290689 }, { "epoch": 0.6982220747586407, "grad_norm": 0.26470330357551575, "learning_rate": 7.282582872951968e-06, "loss": 0.717623233795166, "step": 10785, "token_acc": 0.7776353442359736 }, { "epoch": 0.698545775303267, "grad_norm": 0.3111676275730133, "learning_rate": 7.280320713388426e-06, "loss": 0.7009413719177247, "step": 10790, "token_acc": 0.7800926075416379 }, { "epoch": 0.6988694758478932, "grad_norm": 0.34130170941352844, "learning_rate": 7.278057964320019e-06, "loss": 0.672237777709961, "step": 10795, "token_acc": 0.7877247956403269 }, { "epoch": 0.6991931763925193, "grad_norm": 0.2897387444972992, "learning_rate": 7.275794626331711e-06, "loss": 0.727114200592041, "step": 10800, "token_acc": 0.776729498323404 }, { "epoch": 0.6995168769371455, "grad_norm": 0.3346269726753235, "learning_rate": 7.273530700008618e-06, "loss": 0.7046049118041993, "step": 10805, "token_acc": 0.78175548710796 }, { "epoch": 0.6998405774817716, "grad_norm": 0.24223579466342926, "learning_rate": 7.2712661859360025e-06, "loss": 0.6952134609222412, "step": 10810, "token_acc": 0.7834258919683554 }, { "epoch": 0.7001642780263978, "grad_norm": 0.32198330760002136, "learning_rate": 7.269001084699286e-06, "loss": 0.6914742469787598, "step": 10815, "token_acc": 0.7853080387815864 }, { "epoch": 0.700487978571024, "grad_norm": 0.2834770083427429, "learning_rate": 7.2667353968840384e-06, "loss": 0.6990771770477295, "step": 10820, "token_acc": 0.7826819728431965 }, { "epoch": 0.7008116791156501, "grad_norm": 0.27659058570861816, "learning_rate": 7.264469123075983e-06, "loss": 0.7065982818603516, "step": 10825, "token_acc": 0.7810659714575948 }, { "epoch": 0.7011353796602763, "grad_norm": 0.37985479831695557, "learning_rate": 7.262202263860989e-06, "loss": 0.6932723522186279, "step": 10830, "token_acc": 0.7842687898005282 }, { "epoch": 0.7014590802049024, "grad_norm": 0.292643666267395, "learning_rate": 7.259934819825086e-06, "loss": 0.7078663825988769, "step": 10835, "token_acc": 0.7814747270940038 }, { "epoch": 0.7017827807495286, "grad_norm": 0.2996508777141571, "learning_rate": 7.257666791554448e-06, "loss": 0.6876142501831055, "step": 10840, "token_acc": 0.7856250440487708 }, { "epoch": 0.7021064812941548, "grad_norm": 0.29863759875297546, "learning_rate": 7.255398179635401e-06, "loss": 0.6945540428161621, "step": 10845, "token_acc": 0.785326814894187 }, { "epoch": 0.7024301818387809, "grad_norm": 0.3437801003456116, "learning_rate": 7.2531289846544254e-06, "loss": 0.6905171871185303, "step": 10850, "token_acc": 0.784965443774683 }, { "epoch": 0.7027538823834071, "grad_norm": 0.2832697033882141, "learning_rate": 7.250859207198147e-06, "loss": 0.6940440654754638, "step": 10855, "token_acc": 0.7853623519430939 }, { "epoch": 0.7030775829280332, "grad_norm": 0.35680562257766724, "learning_rate": 7.248588847853347e-06, "loss": 0.6749974727630615, "step": 10860, "token_acc": 0.7897628158235327 }, { "epoch": 0.7034012834726594, "grad_norm": 0.3631800711154938, "learning_rate": 7.246317907206956e-06, "loss": 0.6673038959503174, "step": 10865, "token_acc": 0.7895917639905227 }, { "epoch": 0.7037249840172856, "grad_norm": 0.3828136920928955, "learning_rate": 7.24404638584605e-06, "loss": 0.707616138458252, "step": 10870, "token_acc": 0.7808995128582757 }, { "epoch": 0.7040486845619118, "grad_norm": 0.25781601667404175, "learning_rate": 7.241774284357863e-06, "loss": 0.6670195579528808, "step": 10875, "token_acc": 0.7915022547914318 }, { "epoch": 0.704372385106538, "grad_norm": 0.35714685916900635, "learning_rate": 7.239501603329773e-06, "loss": 0.6664073467254639, "step": 10880, "token_acc": 0.7900231633580896 }, { "epoch": 0.7046960856511642, "grad_norm": 0.3582805395126343, "learning_rate": 7.237228343349312e-06, "loss": 0.6975104331970214, "step": 10885, "token_acc": 0.7839143129955856 }, { "epoch": 0.7050197861957903, "grad_norm": 0.3469228744506836, "learning_rate": 7.234954505004157e-06, "loss": 0.7064181804656983, "step": 10890, "token_acc": 0.7805396626643442 }, { "epoch": 0.7053434867404165, "grad_norm": 0.231539785861969, "learning_rate": 7.2326800888821365e-06, "loss": 0.694401741027832, "step": 10895, "token_acc": 0.7848995801353195 }, { "epoch": 0.7056671872850426, "grad_norm": 0.33589956164360046, "learning_rate": 7.230405095571234e-06, "loss": 0.7252227783203125, "step": 10900, "token_acc": 0.7766663200582302 }, { "epoch": 0.7059908878296688, "grad_norm": 0.38463249802589417, "learning_rate": 7.22812952565957e-06, "loss": 0.6924760818481446, "step": 10905, "token_acc": 0.7839766752568417 }, { "epoch": 0.706314588374295, "grad_norm": 0.3319380581378937, "learning_rate": 7.225853379735427e-06, "loss": 0.6971343040466309, "step": 10910, "token_acc": 0.784461738658042 }, { "epoch": 0.7066382889189211, "grad_norm": 0.2641454041004181, "learning_rate": 7.223576658387228e-06, "loss": 0.6957699298858643, "step": 10915, "token_acc": 0.7832587676951739 }, { "epoch": 0.7069619894635473, "grad_norm": 0.38999468088150024, "learning_rate": 7.221299362203547e-06, "loss": 0.7108757972717286, "step": 10920, "token_acc": 0.7793671404174841 }, { "epoch": 0.7072856900081734, "grad_norm": 0.333016961812973, "learning_rate": 7.219021491773108e-06, "loss": 0.6805377006530762, "step": 10925, "token_acc": 0.788150352431365 }, { "epoch": 0.7076093905527996, "grad_norm": 0.40249374508857727, "learning_rate": 7.216743047684782e-06, "loss": 0.704395866394043, "step": 10930, "token_acc": 0.7821932859706953 }, { "epoch": 0.7079330910974257, "grad_norm": 0.38231953978538513, "learning_rate": 7.21446403052759e-06, "loss": 0.7058059692382812, "step": 10935, "token_acc": 0.78161241015968 }, { "epoch": 0.7082567916420519, "grad_norm": 0.38634562492370605, "learning_rate": 7.2121844408907e-06, "loss": 0.7066027164459229, "step": 10940, "token_acc": 0.7814268785467714 }, { "epoch": 0.7085804921866781, "grad_norm": 0.2935837209224701, "learning_rate": 7.209904279363425e-06, "loss": 0.6876996040344239, "step": 10945, "token_acc": 0.7853686016439198 }, { "epoch": 0.7089041927313042, "grad_norm": 0.333649218082428, "learning_rate": 7.207623546535228e-06, "loss": 0.6870033740997314, "step": 10950, "token_acc": 0.786044503606699 }, { "epoch": 0.7092278932759304, "grad_norm": 0.41563868522644043, "learning_rate": 7.205342242995725e-06, "loss": 0.7115380764007568, "step": 10955, "token_acc": 0.7798781440399938 }, { "epoch": 0.7095515938205565, "grad_norm": 0.3733367919921875, "learning_rate": 7.203060369334673e-06, "loss": 0.6844311714172363, "step": 10960, "token_acc": 0.7862998963703383 }, { "epoch": 0.7098752943651828, "grad_norm": 0.31070780754089355, "learning_rate": 7.2007779261419775e-06, "loss": 0.6997838020324707, "step": 10965, "token_acc": 0.7821799216350735 }, { "epoch": 0.710198994909809, "grad_norm": 0.37607982754707336, "learning_rate": 7.198494914007693e-06, "loss": 0.6762419700622558, "step": 10970, "token_acc": 0.7887590141296918 }, { "epoch": 0.7105226954544351, "grad_norm": 0.39349880814552307, "learning_rate": 7.19621133352202e-06, "loss": 0.6778247833251954, "step": 10975, "token_acc": 0.7880608099252981 }, { "epoch": 0.7108463959990613, "grad_norm": 0.3529576361179352, "learning_rate": 7.193927185275305e-06, "loss": 0.7020941734313965, "step": 10980, "token_acc": 0.7824812807460042 }, { "epoch": 0.7111700965436875, "grad_norm": 0.3358972370624542, "learning_rate": 7.191642469858043e-06, "loss": 0.7225744247436523, "step": 10985, "token_acc": 0.7758326553108842 }, { "epoch": 0.7114937970883136, "grad_norm": 0.32925307750701904, "learning_rate": 7.189357187860875e-06, "loss": 0.6959399223327637, "step": 10990, "token_acc": 0.7838620463040293 }, { "epoch": 0.7118174976329398, "grad_norm": 0.2997693419456482, "learning_rate": 7.187071339874589e-06, "loss": 0.7057787895202636, "step": 10995, "token_acc": 0.7819901935698034 }, { "epoch": 0.7121411981775659, "grad_norm": 0.2933364510536194, "learning_rate": 7.1847849264901195e-06, "loss": 0.7030967235565185, "step": 11000, "token_acc": 0.7822110269327898 }, { "epoch": 0.7124648987221921, "grad_norm": 0.2849995791912079, "learning_rate": 7.1824979482985436e-06, "loss": 0.7400997638702392, "step": 11005, "token_acc": 0.7726615317345532 }, { "epoch": 0.7127885992668183, "grad_norm": 0.29460668563842773, "learning_rate": 7.1802104058910895e-06, "loss": 0.699927806854248, "step": 11010, "token_acc": 0.7834992085413449 }, { "epoch": 0.7131122998114444, "grad_norm": 0.3512343168258667, "learning_rate": 7.177922299859127e-06, "loss": 0.6934566020965576, "step": 11015, "token_acc": 0.7858015000872144 }, { "epoch": 0.7134360003560706, "grad_norm": 0.3478737473487854, "learning_rate": 7.175633630794176e-06, "loss": 0.6906216621398926, "step": 11020, "token_acc": 0.7852601711713504 }, { "epoch": 0.7137597009006967, "grad_norm": 0.3960379660129547, "learning_rate": 7.173344399287901e-06, "loss": 0.6857695579528809, "step": 11025, "token_acc": 0.7879260525089328 }, { "epoch": 0.7140834014453229, "grad_norm": 0.37769556045532227, "learning_rate": 7.171054605932104e-06, "loss": 0.7050976276397705, "step": 11030, "token_acc": 0.780715898097388 }, { "epoch": 0.7144071019899491, "grad_norm": 0.34325912594795227, "learning_rate": 7.168764251318745e-06, "loss": 0.6985239028930664, "step": 11035, "token_acc": 0.782632491106449 }, { "epoch": 0.7147308025345752, "grad_norm": 0.2664780020713806, "learning_rate": 7.1664733360399196e-06, "loss": 0.7025772571563721, "step": 11040, "token_acc": 0.781348175798192 }, { "epoch": 0.7150545030792014, "grad_norm": 0.2656174898147583, "learning_rate": 7.164181860687874e-06, "loss": 0.6840400218963623, "step": 11045, "token_acc": 0.7863079878524286 }, { "epoch": 0.7153782036238276, "grad_norm": 0.2860715389251709, "learning_rate": 7.161889825854995e-06, "loss": 0.700363302230835, "step": 11050, "token_acc": 0.7837155627896922 }, { "epoch": 0.7157019041684538, "grad_norm": 0.23988264799118042, "learning_rate": 7.159597232133814e-06, "loss": 0.6674179077148438, "step": 11055, "token_acc": 0.7900212801598183 }, { "epoch": 0.71602560471308, "grad_norm": 0.3434235155582428, "learning_rate": 7.157304080117014e-06, "loss": 0.6992228507995606, "step": 11060, "token_acc": 0.7831799448421183 }, { "epoch": 0.7163493052577061, "grad_norm": 0.33692124485969543, "learning_rate": 7.15501037039741e-06, "loss": 0.6701244354248047, "step": 11065, "token_acc": 0.790711118410248 }, { "epoch": 0.7166730058023323, "grad_norm": 0.2773958742618561, "learning_rate": 7.152716103567975e-06, "loss": 0.697595739364624, "step": 11070, "token_acc": 0.7830883278374908 }, { "epoch": 0.7169967063469584, "grad_norm": 0.2920120358467102, "learning_rate": 7.1504212802218145e-06, "loss": 0.6752278804779053, "step": 11075, "token_acc": 0.7887190417658289 }, { "epoch": 0.7173204068915846, "grad_norm": 0.31026017665863037, "learning_rate": 7.148125900952185e-06, "loss": 0.7021394729614258, "step": 11080, "token_acc": 0.7815768762059511 }, { "epoch": 0.7176441074362108, "grad_norm": 0.25427910685539246, "learning_rate": 7.145829966352483e-06, "loss": 0.6773245811462403, "step": 11085, "token_acc": 0.7881987332790202 }, { "epoch": 0.7179678079808369, "grad_norm": 0.33144986629486084, "learning_rate": 7.14353347701625e-06, "loss": 0.691243839263916, "step": 11090, "token_acc": 0.7850162239807108 }, { "epoch": 0.7182915085254631, "grad_norm": 0.334199458360672, "learning_rate": 7.141236433537171e-06, "loss": 0.6670697212219239, "step": 11095, "token_acc": 0.7900116548555199 }, { "epoch": 0.7186152090700892, "grad_norm": 0.25680962204933167, "learning_rate": 7.138938836509074e-06, "loss": 0.6657922744750977, "step": 11100, "token_acc": 0.7910171599720291 }, { "epoch": 0.7189389096147154, "grad_norm": 0.31218886375427246, "learning_rate": 7.13664068652593e-06, "loss": 0.6771598815917969, "step": 11105, "token_acc": 0.7880235472699326 }, { "epoch": 0.7192626101593416, "grad_norm": 0.3222391605377197, "learning_rate": 7.134341984181854e-06, "loss": 0.6716754913330079, "step": 11110, "token_acc": 0.7888810744282294 }, { "epoch": 0.7195863107039677, "grad_norm": 0.3324079215526581, "learning_rate": 7.132042730071101e-06, "loss": 0.6752067565917969, "step": 11115, "token_acc": 0.7881611683737763 }, { "epoch": 0.7199100112485939, "grad_norm": 0.19501861929893494, "learning_rate": 7.129742924788073e-06, "loss": 0.6791040420532226, "step": 11120, "token_acc": 0.7882898628663619 }, { "epoch": 0.72023371179322, "grad_norm": 0.23507191240787506, "learning_rate": 7.127442568927309e-06, "loss": 0.6833227157592774, "step": 11125, "token_acc": 0.7876801092500209 }, { "epoch": 0.7205574123378462, "grad_norm": 0.3926204741001129, "learning_rate": 7.125141663083496e-06, "loss": 0.6973988533020019, "step": 11130, "token_acc": 0.7823003252620166 }, { "epoch": 0.7208811128824725, "grad_norm": 0.33557841181755066, "learning_rate": 7.122840207851458e-06, "loss": 0.7137186527252197, "step": 11135, "token_acc": 0.7785991954214181 }, { "epoch": 0.7212048134270986, "grad_norm": 0.32069841027259827, "learning_rate": 7.120538203826166e-06, "loss": 0.6764998435974121, "step": 11140, "token_acc": 0.7885147898146957 }, { "epoch": 0.7215285139717248, "grad_norm": 0.34081214666366577, "learning_rate": 7.118235651602728e-06, "loss": 0.6995198726654053, "step": 11145, "token_acc": 0.7841824584515606 }, { "epoch": 0.721852214516351, "grad_norm": 0.3001910448074341, "learning_rate": 7.115932551776399e-06, "loss": 0.6869388580322265, "step": 11150, "token_acc": 0.7865374246053143 }, { "epoch": 0.7221759150609771, "grad_norm": 0.2654194235801697, "learning_rate": 7.1136289049425696e-06, "loss": 0.6991874694824218, "step": 11155, "token_acc": 0.7823424397391125 }, { "epoch": 0.7224996156056033, "grad_norm": 0.3912668228149414, "learning_rate": 7.111324711696777e-06, "loss": 0.7015204906463623, "step": 11160, "token_acc": 0.7818393734706536 }, { "epoch": 0.7228233161502294, "grad_norm": 0.3067978620529175, "learning_rate": 7.109019972634696e-06, "loss": 0.7133719444274902, "step": 11165, "token_acc": 0.7784694731321103 }, { "epoch": 0.7231470166948556, "grad_norm": 0.38264894485473633, "learning_rate": 7.106714688352146e-06, "loss": 0.7069947719573975, "step": 11170, "token_acc": 0.7817614297779096 }, { "epoch": 0.7234707172394818, "grad_norm": 0.3512846827507019, "learning_rate": 7.1044088594450855e-06, "loss": 0.6972456932067871, "step": 11175, "token_acc": 0.7831394426201491 }, { "epoch": 0.7237944177841079, "grad_norm": 0.3580314517021179, "learning_rate": 7.10210248650961e-06, "loss": 0.7183121681213379, "step": 11180, "token_acc": 0.7774123344133351 }, { "epoch": 0.7241181183287341, "grad_norm": 0.39473268389701843, "learning_rate": 7.099795570141964e-06, "loss": 0.6860939025878906, "step": 11185, "token_acc": 0.7859965423561374 }, { "epoch": 0.7244418188733602, "grad_norm": 0.35208001732826233, "learning_rate": 7.097488110938525e-06, "loss": 0.6853257179260254, "step": 11190, "token_acc": 0.7859251968503937 }, { "epoch": 0.7247655194179864, "grad_norm": 0.2888683080673218, "learning_rate": 7.095180109495814e-06, "loss": 0.6720586776733398, "step": 11195, "token_acc": 0.7880687109109281 }, { "epoch": 0.7250892199626126, "grad_norm": 0.3192536234855652, "learning_rate": 7.092871566410493e-06, "loss": 0.7051493167877197, "step": 11200, "token_acc": 0.7800659736368296 }, { "epoch": 0.7254129205072387, "grad_norm": 0.2933700978755951, "learning_rate": 7.090562482279362e-06, "loss": 0.6962050437927246, "step": 11205, "token_acc": 0.7849381668678826 }, { "epoch": 0.7257366210518649, "grad_norm": 0.25426533818244934, "learning_rate": 7.08825285769936e-06, "loss": 0.6812012195587158, "step": 11210, "token_acc": 0.7886403234601727 }, { "epoch": 0.726060321596491, "grad_norm": 0.3082749843597412, "learning_rate": 7.085942693267571e-06, "loss": 0.7116921424865723, "step": 11215, "token_acc": 0.7808311801212239 }, { "epoch": 0.7263840221411173, "grad_norm": 0.3658837378025055, "learning_rate": 7.083631989581213e-06, "loss": 0.735959243774414, "step": 11220, "token_acc": 0.7743497278707135 }, { "epoch": 0.7267077226857435, "grad_norm": 0.2950148284435272, "learning_rate": 7.0813207472376455e-06, "loss": 0.6782294273376465, "step": 11225, "token_acc": 0.788511396011396 }, { "epoch": 0.7270314232303696, "grad_norm": 0.26820608973503113, "learning_rate": 7.079008966834367e-06, "loss": 0.6933098316192627, "step": 11230, "token_acc": 0.7840067503581575 }, { "epoch": 0.7273551237749958, "grad_norm": 0.20252279937267303, "learning_rate": 7.076696648969017e-06, "loss": 0.6872670173645019, "step": 11235, "token_acc": 0.7861098393863946 }, { "epoch": 0.7276788243196219, "grad_norm": 0.4191763997077942, "learning_rate": 7.07438379423937e-06, "loss": 0.7124451160430908, "step": 11240, "token_acc": 0.7811949482668784 }, { "epoch": 0.7280025248642481, "grad_norm": 0.4290662109851837, "learning_rate": 7.072070403243343e-06, "loss": 0.6765633583068847, "step": 11245, "token_acc": 0.7881900904585962 }, { "epoch": 0.7283262254088743, "grad_norm": 0.34750670194625854, "learning_rate": 7.069756476578988e-06, "loss": 0.7025739192962647, "step": 11250, "token_acc": 0.7829450756954871 }, { "epoch": 0.7286499259535004, "grad_norm": 0.34316638112068176, "learning_rate": 7.067442014844501e-06, "loss": 0.6968125343322754, "step": 11255, "token_acc": 0.7831244529693291 }, { "epoch": 0.7289736264981266, "grad_norm": 0.2989064157009125, "learning_rate": 7.0651270186382096e-06, "loss": 0.7087778091430664, "step": 11260, "token_acc": 0.7811103455686681 }, { "epoch": 0.7292973270427527, "grad_norm": 0.2867511212825775, "learning_rate": 7.062811488558585e-06, "loss": 0.6962722778320313, "step": 11265, "token_acc": 0.7821628578385336 }, { "epoch": 0.7296210275873789, "grad_norm": 0.3205612897872925, "learning_rate": 7.060495425204234e-06, "loss": 0.6969576835632324, "step": 11270, "token_acc": 0.7828222598964746 }, { "epoch": 0.7299447281320051, "grad_norm": 0.2871786653995514, "learning_rate": 7.058178829173901e-06, "loss": 0.6823434829711914, "step": 11275, "token_acc": 0.7861957730097224 }, { "epoch": 0.7302684286766312, "grad_norm": 0.29667752981185913, "learning_rate": 7.05586170106647e-06, "loss": 0.7033775806427002, "step": 11280, "token_acc": 0.7809278185985049 }, { "epoch": 0.7305921292212574, "grad_norm": 0.30306732654571533, "learning_rate": 7.053544041480958e-06, "loss": 0.6880815029144287, "step": 11285, "token_acc": 0.7850440128906426 }, { "epoch": 0.7309158297658835, "grad_norm": 0.3462101221084595, "learning_rate": 7.0512258510165275e-06, "loss": 0.6985841751098633, "step": 11290, "token_acc": 0.7840578951501034 }, { "epoch": 0.7312395303105097, "grad_norm": 0.324708491563797, "learning_rate": 7.04890713027247e-06, "loss": 0.7199876785278321, "step": 11295, "token_acc": 0.7777245062394289 }, { "epoch": 0.7315632308551359, "grad_norm": 0.3889947533607483, "learning_rate": 7.046587879848218e-06, "loss": 0.7008983612060546, "step": 11300, "token_acc": 0.7818836829476485 }, { "epoch": 0.7318869313997621, "grad_norm": 0.2604006826877594, "learning_rate": 7.044268100343341e-06, "loss": 0.6741209983825683, "step": 11305, "token_acc": 0.789493078912458 }, { "epoch": 0.7322106319443883, "grad_norm": 0.3135935366153717, "learning_rate": 7.0419477923575445e-06, "loss": 0.6923880577087402, "step": 11310, "token_acc": 0.7848923827939265 }, { "epoch": 0.7325343324890145, "grad_norm": 0.26629355549812317, "learning_rate": 7.0396269564906695e-06, "loss": 0.6871541023254395, "step": 11315, "token_acc": 0.7860490599522383 }, { "epoch": 0.7328580330336406, "grad_norm": 0.28195616602897644, "learning_rate": 7.037305593342696e-06, "loss": 0.6591653823852539, "step": 11320, "token_acc": 0.7920901623973297 }, { "epoch": 0.7331817335782668, "grad_norm": 0.40620842576026917, "learning_rate": 7.03498370351374e-06, "loss": 0.7044369220733643, "step": 11325, "token_acc": 0.7801595648475024 }, { "epoch": 0.7335054341228929, "grad_norm": 0.3054576516151428, "learning_rate": 7.032661287604053e-06, "loss": 0.6772851943969727, "step": 11330, "token_acc": 0.7875149394413573 }, { "epoch": 0.7338291346675191, "grad_norm": 0.4312109351158142, "learning_rate": 7.030338346214019e-06, "loss": 0.689300537109375, "step": 11335, "token_acc": 0.7854710404303291 }, { "epoch": 0.7341528352121452, "grad_norm": 0.2705629765987396, "learning_rate": 7.028014879944165e-06, "loss": 0.6883586883544922, "step": 11340, "token_acc": 0.7848276029850928 }, { "epoch": 0.7344765357567714, "grad_norm": 0.276772141456604, "learning_rate": 7.025690889395146e-06, "loss": 0.6956624984741211, "step": 11345, "token_acc": 0.7836356100379311 }, { "epoch": 0.7348002363013976, "grad_norm": 0.2739902436733246, "learning_rate": 7.023366375167759e-06, "loss": 0.6525004386901856, "step": 11350, "token_acc": 0.7932262308537218 }, { "epoch": 0.7351239368460237, "grad_norm": 0.2779752314090729, "learning_rate": 7.021041337862935e-06, "loss": 0.6802953243255615, "step": 11355, "token_acc": 0.7884000781648901 }, { "epoch": 0.7354476373906499, "grad_norm": 0.3527182340621948, "learning_rate": 7.018715778081734e-06, "loss": 0.6948832511901856, "step": 11360, "token_acc": 0.7849281975573749 }, { "epoch": 0.735771337935276, "grad_norm": 0.3897794485092163, "learning_rate": 7.016389696425361e-06, "loss": 0.6859676837921143, "step": 11365, "token_acc": 0.7857344361095082 }, { "epoch": 0.7360950384799022, "grad_norm": 0.25950726866722107, "learning_rate": 7.014063093495147e-06, "loss": 0.6809250831604003, "step": 11370, "token_acc": 0.7870279062023744 }, { "epoch": 0.7364187390245284, "grad_norm": 0.39291855692863464, "learning_rate": 7.011735969892565e-06, "loss": 0.6948355674743653, "step": 11375, "token_acc": 0.7846660737386805 }, { "epoch": 0.7367424395691545, "grad_norm": 0.3755841553211212, "learning_rate": 7.009408326219217e-06, "loss": 0.7002836227416992, "step": 11380, "token_acc": 0.7818937055344077 }, { "epoch": 0.7370661401137807, "grad_norm": 0.3348650336265564, "learning_rate": 7.0070801630768415e-06, "loss": 0.6764755249023438, "step": 11385, "token_acc": 0.7873779213756917 }, { "epoch": 0.737389840658407, "grad_norm": 0.308284729719162, "learning_rate": 7.004751481067314e-06, "loss": 0.7021903991699219, "step": 11390, "token_acc": 0.7827597887315109 }, { "epoch": 0.7377135412030331, "grad_norm": 0.30344197154045105, "learning_rate": 7.002422280792639e-06, "loss": 0.6758485794067383, "step": 11395, "token_acc": 0.7889138391600228 }, { "epoch": 0.7380372417476593, "grad_norm": 0.3219272792339325, "learning_rate": 7.0000925628549595e-06, "loss": 0.6950940132141114, "step": 11400, "token_acc": 0.7829423669876802 }, { "epoch": 0.7383609422922854, "grad_norm": 0.35531648993492126, "learning_rate": 6.99776232785655e-06, "loss": 0.6855839729309082, "step": 11405, "token_acc": 0.7868808438562911 }, { "epoch": 0.7386846428369116, "grad_norm": 0.2647290825843811, "learning_rate": 6.995431576399818e-06, "loss": 0.6965156078338623, "step": 11410, "token_acc": 0.7840476359804233 }, { "epoch": 0.7390083433815378, "grad_norm": 0.35146188735961914, "learning_rate": 6.993100309087306e-06, "loss": 0.6750298500061035, "step": 11415, "token_acc": 0.7881603469892583 }, { "epoch": 0.7393320439261639, "grad_norm": 0.2576020658016205, "learning_rate": 6.990768526521691e-06, "loss": 0.6924915790557862, "step": 11420, "token_acc": 0.7834100767434101 }, { "epoch": 0.7396557444707901, "grad_norm": 0.32065480947494507, "learning_rate": 6.9884362293057805e-06, "loss": 0.6694830417633056, "step": 11425, "token_acc": 0.789301650843785 }, { "epoch": 0.7399794450154162, "grad_norm": 0.34150534868240356, "learning_rate": 6.986103418042517e-06, "loss": 0.6883581638336181, "step": 11430, "token_acc": 0.7850790637256126 }, { "epoch": 0.7403031455600424, "grad_norm": 0.34996604919433594, "learning_rate": 6.983770093334974e-06, "loss": 0.6994807720184326, "step": 11435, "token_acc": 0.7823784527099393 }, { "epoch": 0.7406268461046686, "grad_norm": 0.300802618265152, "learning_rate": 6.981436255786359e-06, "loss": 0.6791632652282715, "step": 11440, "token_acc": 0.7884224166291803 }, { "epoch": 0.7409505466492947, "grad_norm": 0.27643483877182007, "learning_rate": 6.979101906000013e-06, "loss": 0.6990305423736572, "step": 11445, "token_acc": 0.7820575657693203 }, { "epoch": 0.7412742471939209, "grad_norm": 0.34154823422431946, "learning_rate": 6.976767044579408e-06, "loss": 0.6645144462585449, "step": 11450, "token_acc": 0.7907608174843 }, { "epoch": 0.741597947738547, "grad_norm": 0.3293319046497345, "learning_rate": 6.974431672128147e-06, "loss": 0.6669802665710449, "step": 11455, "token_acc": 0.7921729564024277 }, { "epoch": 0.7419216482831732, "grad_norm": 0.3350527882575989, "learning_rate": 6.972095789249968e-06, "loss": 0.6840936183929444, "step": 11460, "token_acc": 0.7853897680482662 }, { "epoch": 0.7422453488277994, "grad_norm": 0.2943665683269501, "learning_rate": 6.969759396548742e-06, "loss": 0.6823256969451904, "step": 11465, "token_acc": 0.7866951967296884 }, { "epoch": 0.7425690493724255, "grad_norm": 0.39729395508766174, "learning_rate": 6.967422494628466e-06, "loss": 0.6795262336730957, "step": 11470, "token_acc": 0.7878466376544583 }, { "epoch": 0.7428927499170518, "grad_norm": 0.22031660377979279, "learning_rate": 6.965085084093274e-06, "loss": 0.6762574195861817, "step": 11475, "token_acc": 0.7895378641236467 }, { "epoch": 0.743216450461678, "grad_norm": 0.31234118342399597, "learning_rate": 6.962747165547427e-06, "loss": 0.6868303298950196, "step": 11480, "token_acc": 0.7871156139019772 }, { "epoch": 0.7435401510063041, "grad_norm": 0.3212778568267822, "learning_rate": 6.960408739595324e-06, "loss": 0.6841253757476806, "step": 11485, "token_acc": 0.787213465574715 }, { "epoch": 0.7438638515509303, "grad_norm": 0.3349907696247101, "learning_rate": 6.958069806841489e-06, "loss": 0.7085608005523681, "step": 11490, "token_acc": 0.7796218876511524 }, { "epoch": 0.7441875520955564, "grad_norm": 0.312134712934494, "learning_rate": 6.95573036789058e-06, "loss": 0.6995549678802491, "step": 11495, "token_acc": 0.7826884986134953 }, { "epoch": 0.7445112526401826, "grad_norm": 0.33080634474754333, "learning_rate": 6.953390423347383e-06, "loss": 0.6853311061859131, "step": 11500, "token_acc": 0.7860640801761446 }, { "epoch": 0.7448349531848087, "grad_norm": 0.41753122210502625, "learning_rate": 6.951049973816819e-06, "loss": 0.6803149223327637, "step": 11505, "token_acc": 0.787486793449551 }, { "epoch": 0.7451586537294349, "grad_norm": 0.19919739663600922, "learning_rate": 6.9487090199039365e-06, "loss": 0.7022896766662597, "step": 11510, "token_acc": 0.7818331362771809 }, { "epoch": 0.7454823542740611, "grad_norm": 0.3364715576171875, "learning_rate": 6.946367562213916e-06, "loss": 0.6990689277648926, "step": 11515, "token_acc": 0.7835208458876665 }, { "epoch": 0.7458060548186872, "grad_norm": 0.26520484685897827, "learning_rate": 6.944025601352065e-06, "loss": 0.6876467704772949, "step": 11520, "token_acc": 0.7856174730689407 }, { "epoch": 0.7461297553633134, "grad_norm": 0.3597560226917267, "learning_rate": 6.941683137923825e-06, "loss": 0.6978174209594726, "step": 11525, "token_acc": 0.7837053127750803 }, { "epoch": 0.7464534559079395, "grad_norm": 0.31320300698280334, "learning_rate": 6.939340172534765e-06, "loss": 0.6894657611846924, "step": 11530, "token_acc": 0.7828525641025641 }, { "epoch": 0.7467771564525657, "grad_norm": 0.2945833206176758, "learning_rate": 6.936996705790586e-06, "loss": 0.6977723598480224, "step": 11535, "token_acc": 0.7837276376031141 }, { "epoch": 0.7471008569971919, "grad_norm": 0.36056217551231384, "learning_rate": 6.934652738297118e-06, "loss": 0.6915800094604492, "step": 11540, "token_acc": 0.7842025487003873 }, { "epoch": 0.747424557541818, "grad_norm": 0.37379521131515503, "learning_rate": 6.9323082706603175e-06, "loss": 0.7048818588256835, "step": 11545, "token_acc": 0.7817939149620026 }, { "epoch": 0.7477482580864442, "grad_norm": 0.36774346232414246, "learning_rate": 6.929963303486273e-06, "loss": 0.6971989631652832, "step": 11550, "token_acc": 0.7837082098275117 }, { "epoch": 0.7480719586310703, "grad_norm": 0.2994951903820038, "learning_rate": 6.927617837381203e-06, "loss": 0.6858552932739258, "step": 11555, "token_acc": 0.7857625395466433 }, { "epoch": 0.7483956591756966, "grad_norm": 0.30974483489990234, "learning_rate": 6.9252718729514535e-06, "loss": 0.6944795608520508, "step": 11560, "token_acc": 0.7838599826801492 }, { "epoch": 0.7487193597203228, "grad_norm": 0.3413969576358795, "learning_rate": 6.922925410803498e-06, "loss": 0.6857965469360352, "step": 11565, "token_acc": 0.7863450226093452 }, { "epoch": 0.7490430602649489, "grad_norm": 0.38337334990501404, "learning_rate": 6.92057845154394e-06, "loss": 0.6656208992004394, "step": 11570, "token_acc": 0.7921342346051181 }, { "epoch": 0.7493667608095751, "grad_norm": 0.3111017048358917, "learning_rate": 6.918230995779513e-06, "loss": 0.703745985031128, "step": 11575, "token_acc": 0.7828449839542347 }, { "epoch": 0.7496904613542013, "grad_norm": 0.3402426540851593, "learning_rate": 6.915883044117078e-06, "loss": 0.6689400672912598, "step": 11580, "token_acc": 0.7900580983014664 }, { "epoch": 0.7500141618988274, "grad_norm": 0.22153466939926147, "learning_rate": 6.913534597163622e-06, "loss": 0.6956572532653809, "step": 11585, "token_acc": 0.7826191216881837 }, { "epoch": 0.7503378624434536, "grad_norm": 0.34548142552375793, "learning_rate": 6.911185655526263e-06, "loss": 0.6986305713653564, "step": 11590, "token_acc": 0.7830383191202872 }, { "epoch": 0.7506615629880797, "grad_norm": 0.3383607566356659, "learning_rate": 6.908836219812245e-06, "loss": 0.675139045715332, "step": 11595, "token_acc": 0.7895694493160295 }, { "epoch": 0.7509852635327059, "grad_norm": 0.32548990845680237, "learning_rate": 6.906486290628941e-06, "loss": 0.7043625831604003, "step": 11600, "token_acc": 0.7823379583542157 }, { "epoch": 0.751308964077332, "grad_norm": 0.2542969584465027, "learning_rate": 6.9041358685838486e-06, "loss": 0.6877474308013916, "step": 11605, "token_acc": 0.7850180753214662 }, { "epoch": 0.7516326646219582, "grad_norm": 0.27835017442703247, "learning_rate": 6.9017849542846e-06, "loss": 0.7096066951751709, "step": 11610, "token_acc": 0.7797835137385513 }, { "epoch": 0.7519563651665844, "grad_norm": 0.3325425982475281, "learning_rate": 6.899433548338944e-06, "loss": 0.6924894332885743, "step": 11615, "token_acc": 0.784046399023731 }, { "epoch": 0.7522800657112105, "grad_norm": 0.2904037535190582, "learning_rate": 6.897081651354767e-06, "loss": 0.7044779300689697, "step": 11620, "token_acc": 0.7823152124953212 }, { "epoch": 0.7526037662558367, "grad_norm": 0.3469848334789276, "learning_rate": 6.8947292639400755e-06, "loss": 0.6683724403381348, "step": 11625, "token_acc": 0.790720154664089 }, { "epoch": 0.7529274668004629, "grad_norm": 0.41857802867889404, "learning_rate": 6.8923763867030034e-06, "loss": 0.6971990585327148, "step": 11630, "token_acc": 0.7831134599592042 }, { "epoch": 0.753251167345089, "grad_norm": 0.35420575737953186, "learning_rate": 6.890023020251817e-06, "loss": 0.7030528545379638, "step": 11635, "token_acc": 0.7823486343273395 }, { "epoch": 0.7535748678897152, "grad_norm": 0.260063111782074, "learning_rate": 6.887669165194901e-06, "loss": 0.6845844745635986, "step": 11640, "token_acc": 0.7863022535962633 }, { "epoch": 0.7538985684343414, "grad_norm": 0.3265446722507477, "learning_rate": 6.885314822140773e-06, "loss": 0.6844653129577637, "step": 11645, "token_acc": 0.7865945853421961 }, { "epoch": 0.7542222689789676, "grad_norm": 0.3378748297691345, "learning_rate": 6.8829599916980714e-06, "loss": 0.707357120513916, "step": 11650, "token_acc": 0.7809774500803305 }, { "epoch": 0.7545459695235938, "grad_norm": 0.2577255964279175, "learning_rate": 6.880604674475564e-06, "loss": 0.6775975227355957, "step": 11655, "token_acc": 0.7866645871758706 }, { "epoch": 0.7548696700682199, "grad_norm": 0.27818143367767334, "learning_rate": 6.878248871082146e-06, "loss": 0.6851932525634765, "step": 11660, "token_acc": 0.7864304344635745 }, { "epoch": 0.7551933706128461, "grad_norm": 0.4225546419620514, "learning_rate": 6.875892582126833e-06, "loss": 0.7002041339874268, "step": 11665, "token_acc": 0.7833229188363535 }, { "epoch": 0.7555170711574722, "grad_norm": 0.3133987784385681, "learning_rate": 6.87353580821877e-06, "loss": 0.6692646026611329, "step": 11670, "token_acc": 0.7904416443935345 }, { "epoch": 0.7558407717020984, "grad_norm": 0.3307327926158905, "learning_rate": 6.8711785499672265e-06, "loss": 0.6791464328765869, "step": 11675, "token_acc": 0.7881239626071523 }, { "epoch": 0.7561644722467246, "grad_norm": 0.2960691452026367, "learning_rate": 6.868820807981598e-06, "loss": 0.706554651260376, "step": 11680, "token_acc": 0.7808258906502323 }, { "epoch": 0.7564881727913507, "grad_norm": 0.37959644198417664, "learning_rate": 6.866462582871402e-06, "loss": 0.6985528945922852, "step": 11685, "token_acc": 0.7830286896588079 }, { "epoch": 0.7568118733359769, "grad_norm": 0.3193274438381195, "learning_rate": 6.864103875246284e-06, "loss": 0.6950427055358886, "step": 11690, "token_acc": 0.784451696240397 }, { "epoch": 0.757135573880603, "grad_norm": 0.31898000836372375, "learning_rate": 6.861744685716016e-06, "loss": 0.6899413108825684, "step": 11695, "token_acc": 0.7877322065101222 }, { "epoch": 0.7574592744252292, "grad_norm": 0.32083991169929504, "learning_rate": 6.859385014890487e-06, "loss": 0.6609613418579101, "step": 11700, "token_acc": 0.7908802926872797 }, { "epoch": 0.7577829749698554, "grad_norm": 0.33158740401268005, "learning_rate": 6.85702486337972e-06, "loss": 0.7027965068817139, "step": 11705, "token_acc": 0.7821773396518081 }, { "epoch": 0.7581066755144815, "grad_norm": 0.3177436888217926, "learning_rate": 6.854664231793855e-06, "loss": 0.6913980007171631, "step": 11710, "token_acc": 0.7847541262548919 }, { "epoch": 0.7584303760591077, "grad_norm": 0.3469499945640564, "learning_rate": 6.852303120743158e-06, "loss": 0.6784321784973144, "step": 11715, "token_acc": 0.7888692086692143 }, { "epoch": 0.7587540766037338, "grad_norm": 0.3148435950279236, "learning_rate": 6.849941530838022e-06, "loss": 0.6524443626403809, "step": 11720, "token_acc": 0.7948663175303198 }, { "epoch": 0.75907777714836, "grad_norm": 0.40278124809265137, "learning_rate": 6.847579462688959e-06, "loss": 0.6766862869262695, "step": 11725, "token_acc": 0.788844209410274 }, { "epoch": 0.7594014776929863, "grad_norm": 0.38430675864219666, "learning_rate": 6.84521691690661e-06, "loss": 0.6990705966949463, "step": 11730, "token_acc": 0.7832794879200446 }, { "epoch": 0.7597251782376124, "grad_norm": 0.3194971978664398, "learning_rate": 6.8428538941017354e-06, "loss": 0.6920210838317871, "step": 11735, "token_acc": 0.7849326091329712 }, { "epoch": 0.7600488787822386, "grad_norm": 0.3903074562549591, "learning_rate": 6.840490394885218e-06, "loss": 0.6668098449707032, "step": 11740, "token_acc": 0.7922131173002491 }, { "epoch": 0.7603725793268648, "grad_norm": 0.26827606558799744, "learning_rate": 6.838126419868068e-06, "loss": 0.6889304161071778, "step": 11745, "token_acc": 0.7855357046326829 }, { "epoch": 0.7606962798714909, "grad_norm": 0.3538379669189453, "learning_rate": 6.835761969661416e-06, "loss": 0.6886892318725586, "step": 11750, "token_acc": 0.7851383513868103 }, { "epoch": 0.7610199804161171, "grad_norm": 0.2707831561565399, "learning_rate": 6.833397044876516e-06, "loss": 0.6765990257263184, "step": 11755, "token_acc": 0.788734636482426 }, { "epoch": 0.7613436809607432, "grad_norm": 0.280803382396698, "learning_rate": 6.831031646124745e-06, "loss": 0.6703029155731202, "step": 11760, "token_acc": 0.7895411068093828 }, { "epoch": 0.7616673815053694, "grad_norm": 0.38970959186553955, "learning_rate": 6.8286657740176e-06, "loss": 0.6968432426452636, "step": 11765, "token_acc": 0.7832569573407794 }, { "epoch": 0.7619910820499955, "grad_norm": 0.26100099086761475, "learning_rate": 6.826299429166705e-06, "loss": 0.6695964813232422, "step": 11770, "token_acc": 0.7893213735389549 }, { "epoch": 0.7623147825946217, "grad_norm": 0.33783096075057983, "learning_rate": 6.823932612183802e-06, "loss": 0.7026718139648438, "step": 11775, "token_acc": 0.7829610938953625 }, { "epoch": 0.7626384831392479, "grad_norm": 0.2901504635810852, "learning_rate": 6.821565323680759e-06, "loss": 0.6762861251831055, "step": 11780, "token_acc": 0.7885744382924604 }, { "epoch": 0.762962183683874, "grad_norm": 0.4199409782886505, "learning_rate": 6.8191975642695605e-06, "loss": 0.6782888412475586, "step": 11785, "token_acc": 0.7882217668634416 }, { "epoch": 0.7632858842285002, "grad_norm": 0.27325090765953064, "learning_rate": 6.8168293345623185e-06, "loss": 0.673558521270752, "step": 11790, "token_acc": 0.7890832110776517 }, { "epoch": 0.7636095847731263, "grad_norm": 0.39274948835372925, "learning_rate": 6.814460635171262e-06, "loss": 0.6816121101379394, "step": 11795, "token_acc": 0.7858117601188516 }, { "epoch": 0.7639332853177525, "grad_norm": 0.28104057908058167, "learning_rate": 6.8120914667087435e-06, "loss": 0.7031686782836915, "step": 11800, "token_acc": 0.7813133452827115 }, { "epoch": 0.7642569858623787, "grad_norm": 0.30111563205718994, "learning_rate": 6.809721829787239e-06, "loss": 0.6946416854858398, "step": 11805, "token_acc": 0.7832476976467558 }, { "epoch": 0.7645806864070048, "grad_norm": 0.2751866579055786, "learning_rate": 6.807351725019341e-06, "loss": 0.6876721858978272, "step": 11810, "token_acc": 0.7851864669653215 }, { "epoch": 0.7649043869516311, "grad_norm": 0.3503452241420746, "learning_rate": 6.804981153017765e-06, "loss": 0.6598246574401856, "step": 11815, "token_acc": 0.7933858094043369 }, { "epoch": 0.7652280874962573, "grad_norm": 0.24638742208480835, "learning_rate": 6.802610114395349e-06, "loss": 0.6722506523132324, "step": 11820, "token_acc": 0.7896481164670759 }, { "epoch": 0.7655517880408834, "grad_norm": 0.4163661301136017, "learning_rate": 6.80023860976505e-06, "loss": 0.6682561874389649, "step": 11825, "token_acc": 0.7911224788481106 }, { "epoch": 0.7658754885855096, "grad_norm": 0.3514799177646637, "learning_rate": 6.797866639739944e-06, "loss": 0.6735667705535888, "step": 11830, "token_acc": 0.7890269180332492 }, { "epoch": 0.7661991891301357, "grad_norm": 0.2750486731529236, "learning_rate": 6.79549420493323e-06, "loss": 0.7200023651123046, "step": 11835, "token_acc": 0.7784672224327397 }, { "epoch": 0.7665228896747619, "grad_norm": 0.3452169895172119, "learning_rate": 6.793121305958227e-06, "loss": 0.6771662712097168, "step": 11840, "token_acc": 0.7867892761669751 }, { "epoch": 0.7668465902193881, "grad_norm": 0.33293387293815613, "learning_rate": 6.790747943428371e-06, "loss": 0.6653157234191894, "step": 11845, "token_acc": 0.7904045345659435 }, { "epoch": 0.7671702907640142, "grad_norm": 0.29660528898239136, "learning_rate": 6.78837411795722e-06, "loss": 0.6984358787536621, "step": 11850, "token_acc": 0.7827470607035272 }, { "epoch": 0.7674939913086404, "grad_norm": 0.2711728811264038, "learning_rate": 6.785999830158455e-06, "loss": 0.6737759113311768, "step": 11855, "token_acc": 0.7905421793367464 }, { "epoch": 0.7678176918532665, "grad_norm": 0.33491429686546326, "learning_rate": 6.783625080645868e-06, "loss": 0.655181884765625, "step": 11860, "token_acc": 0.7929296645085344 }, { "epoch": 0.7681413923978927, "grad_norm": 0.3635607659816742, "learning_rate": 6.781249870033379e-06, "loss": 0.685731315612793, "step": 11865, "token_acc": 0.7857239596158582 }, { "epoch": 0.7684650929425189, "grad_norm": 0.2636720538139343, "learning_rate": 6.778874198935024e-06, "loss": 0.6828212738037109, "step": 11870, "token_acc": 0.7869177730023336 }, { "epoch": 0.768788793487145, "grad_norm": 0.3671611547470093, "learning_rate": 6.776498067964954e-06, "loss": 0.677855110168457, "step": 11875, "token_acc": 0.7883780170665035 }, { "epoch": 0.7691124940317712, "grad_norm": 0.3743009865283966, "learning_rate": 6.774121477737446e-06, "loss": 0.7221907615661621, "step": 11880, "token_acc": 0.7760283503211346 }, { "epoch": 0.7694361945763973, "grad_norm": 0.41670840978622437, "learning_rate": 6.771744428866891e-06, "loss": 0.6737419128417969, "step": 11885, "token_acc": 0.7872730185485725 }, { "epoch": 0.7697598951210235, "grad_norm": 0.3375736176967621, "learning_rate": 6.7693669219678e-06, "loss": 0.671241283416748, "step": 11890, "token_acc": 0.7893902754714837 }, { "epoch": 0.7700835956656497, "grad_norm": 0.28882160782814026, "learning_rate": 6.766988957654803e-06, "loss": 0.6595510482788086, "step": 11895, "token_acc": 0.7922359690397119 }, { "epoch": 0.7704072962102759, "grad_norm": 0.4193069636821747, "learning_rate": 6.764610536542646e-06, "loss": 0.6766715049743652, "step": 11900, "token_acc": 0.7874848027849934 }, { "epoch": 0.7707309967549021, "grad_norm": 0.3782324492931366, "learning_rate": 6.762231659246197e-06, "loss": 0.692892599105835, "step": 11905, "token_acc": 0.7847068898612394 }, { "epoch": 0.7710546972995282, "grad_norm": 0.27146342396736145, "learning_rate": 6.7598523263804376e-06, "loss": 0.6868206024169922, "step": 11910, "token_acc": 0.7858408183632735 }, { "epoch": 0.7713783978441544, "grad_norm": 0.3069952130317688, "learning_rate": 6.757472538560469e-06, "loss": 0.6736130714416504, "step": 11915, "token_acc": 0.7889767575783955 }, { "epoch": 0.7717020983887806, "grad_norm": 0.2687031030654907, "learning_rate": 6.75509229640151e-06, "loss": 0.6824464797973633, "step": 11920, "token_acc": 0.7873347436899248 }, { "epoch": 0.7720257989334067, "grad_norm": 0.33525753021240234, "learning_rate": 6.752711600518899e-06, "loss": 0.6602446556091308, "step": 11925, "token_acc": 0.7903759069623836 }, { "epoch": 0.7723494994780329, "grad_norm": 0.39442381262779236, "learning_rate": 6.750330451528088e-06, "loss": 0.708896541595459, "step": 11930, "token_acc": 0.7808568704172558 }, { "epoch": 0.772673200022659, "grad_norm": 0.3176683187484741, "learning_rate": 6.747948850044648e-06, "loss": 0.7090949058532715, "step": 11935, "token_acc": 0.7791463305279069 }, { "epoch": 0.7729969005672852, "grad_norm": 0.2624117434024811, "learning_rate": 6.745566796684267e-06, "loss": 0.6805416584014893, "step": 11940, "token_acc": 0.7868989942649232 }, { "epoch": 0.7733206011119114, "grad_norm": 0.4469066262245178, "learning_rate": 6.74318429206275e-06, "loss": 0.6854318618774414, "step": 11945, "token_acc": 0.7861972353531929 }, { "epoch": 0.7736443016565375, "grad_norm": 0.27657368779182434, "learning_rate": 6.740801336796017e-06, "loss": 0.7015717506408692, "step": 11950, "token_acc": 0.7823103825720159 }, { "epoch": 0.7739680022011637, "grad_norm": 0.3003157675266266, "learning_rate": 6.738417931500107e-06, "loss": 0.7199992656707763, "step": 11955, "token_acc": 0.7805243255589676 }, { "epoch": 0.7742917027457898, "grad_norm": 0.2790113389492035, "learning_rate": 6.736034076791174e-06, "loss": 0.6768310546875, "step": 11960, "token_acc": 0.7877862066576604 }, { "epoch": 0.774615403290416, "grad_norm": 0.25510358810424805, "learning_rate": 6.7336497732854885e-06, "loss": 0.6702408790588379, "step": 11965, "token_acc": 0.7902161348423344 }, { "epoch": 0.7749391038350422, "grad_norm": 0.3005713224411011, "learning_rate": 6.731265021599437e-06, "loss": 0.6914591312408447, "step": 11970, "token_acc": 0.7858696863253326 }, { "epoch": 0.7752628043796683, "grad_norm": 0.37350961565971375, "learning_rate": 6.728879822349521e-06, "loss": 0.6812215805053711, "step": 11975, "token_acc": 0.7856843265785468 }, { "epoch": 0.7755865049242945, "grad_norm": 0.3372076749801636, "learning_rate": 6.726494176152358e-06, "loss": 0.7003336906433105, "step": 11980, "token_acc": 0.7819872973537276 }, { "epoch": 0.7759102054689208, "grad_norm": 0.2926456928253174, "learning_rate": 6.724108083624682e-06, "loss": 0.6816311836242676, "step": 11985, "token_acc": 0.7874395232847029 }, { "epoch": 0.7762339060135469, "grad_norm": 0.3232796788215637, "learning_rate": 6.721721545383342e-06, "loss": 0.663241958618164, "step": 11990, "token_acc": 0.7906051006780689 }, { "epoch": 0.7765576065581731, "grad_norm": 0.2999582886695862, "learning_rate": 6.719334562045302e-06, "loss": 0.652825117111206, "step": 11995, "token_acc": 0.7932500449955625 }, { "epoch": 0.7768813071027992, "grad_norm": 0.2283712774515152, "learning_rate": 6.716947134227642e-06, "loss": 0.6864194393157959, "step": 12000, "token_acc": 0.7865565252148424 }, { "epoch": 0.7772050076474254, "grad_norm": 0.2899554371833801, "learning_rate": 6.714559262547553e-06, "loss": 0.6898063659667969, "step": 12005, "token_acc": 0.7846841811067635 }, { "epoch": 0.7775287081920516, "grad_norm": 0.22880412638187408, "learning_rate": 6.712170947622347e-06, "loss": 0.694465160369873, "step": 12010, "token_acc": 0.7839110030532624 }, { "epoch": 0.7778524087366777, "grad_norm": 0.35139036178588867, "learning_rate": 6.709782190069446e-06, "loss": 0.6978641510009765, "step": 12015, "token_acc": 0.78139877395725 }, { "epoch": 0.7781761092813039, "grad_norm": 0.3853876292705536, "learning_rate": 6.707392990506387e-06, "loss": 0.6888265132904052, "step": 12020, "token_acc": 0.7856873381987537 }, { "epoch": 0.77849980982593, "grad_norm": 0.32667458057403564, "learning_rate": 6.705003349550825e-06, "loss": 0.7059396743774414, "step": 12025, "token_acc": 0.7806140966391638 }, { "epoch": 0.7788235103705562, "grad_norm": 0.2427159994840622, "learning_rate": 6.702613267820523e-06, "loss": 0.6659607410430908, "step": 12030, "token_acc": 0.7896652156607552 }, { "epoch": 0.7791472109151824, "grad_norm": 0.38464781641960144, "learning_rate": 6.700222745933362e-06, "loss": 0.6922057151794434, "step": 12035, "token_acc": 0.7847374179431073 }, { "epoch": 0.7794709114598085, "grad_norm": 0.2806623578071594, "learning_rate": 6.697831784507337e-06, "loss": 0.6589295387268066, "step": 12040, "token_acc": 0.79249972179977 }, { "epoch": 0.7797946120044347, "grad_norm": 0.2736212909221649, "learning_rate": 6.6954403841605545e-06, "loss": 0.6714110374450684, "step": 12045, "token_acc": 0.7885667170537309 }, { "epoch": 0.7801183125490608, "grad_norm": 0.319729208946228, "learning_rate": 6.693048545511235e-06, "loss": 0.6620662212371826, "step": 12050, "token_acc": 0.7914211673946038 }, { "epoch": 0.780442013093687, "grad_norm": 0.30538704991340637, "learning_rate": 6.690656269177714e-06, "loss": 0.6857226848602295, "step": 12055, "token_acc": 0.7865349063897011 }, { "epoch": 0.7807657136383132, "grad_norm": 0.40959370136260986, "learning_rate": 6.688263555778438e-06, "loss": 0.7024106502532959, "step": 12060, "token_acc": 0.7814586743575753 }, { "epoch": 0.7810894141829393, "grad_norm": 0.34428390860557556, "learning_rate": 6.685870405931968e-06, "loss": 0.6815733432769775, "step": 12065, "token_acc": 0.7874020952443901 }, { "epoch": 0.7814131147275656, "grad_norm": 0.36180663108825684, "learning_rate": 6.683476820256977e-06, "loss": 0.6824251174926758, "step": 12070, "token_acc": 0.787391240623043 }, { "epoch": 0.7817368152721917, "grad_norm": 0.2970356345176697, "learning_rate": 6.681082799372252e-06, "loss": 0.7009668827056885, "step": 12075, "token_acc": 0.7820506971014398 }, { "epoch": 0.7820605158168179, "grad_norm": 0.40936726331710815, "learning_rate": 6.678688343896688e-06, "loss": 0.6956674575805664, "step": 12080, "token_acc": 0.7846814142100917 }, { "epoch": 0.7823842163614441, "grad_norm": 0.37984898686408997, "learning_rate": 6.676293454449301e-06, "loss": 0.7108073234558105, "step": 12085, "token_acc": 0.7801718384465692 }, { "epoch": 0.7827079169060702, "grad_norm": 0.25853830575942993, "learning_rate": 6.67389813164921e-06, "loss": 0.6717611312866211, "step": 12090, "token_acc": 0.789464904639223 }, { "epoch": 0.7830316174506964, "grad_norm": 0.2860022485256195, "learning_rate": 6.671502376115652e-06, "loss": 0.6728862762451172, "step": 12095, "token_acc": 0.7904337674703745 }, { "epoch": 0.7833553179953225, "grad_norm": 0.23620067536830902, "learning_rate": 6.669106188467973e-06, "loss": 0.688990592956543, "step": 12100, "token_acc": 0.7854006302629539 }, { "epoch": 0.7836790185399487, "grad_norm": 0.33916279673576355, "learning_rate": 6.666709569325631e-06, "loss": 0.6903863906860351, "step": 12105, "token_acc": 0.7861285069737206 }, { "epoch": 0.7840027190845749, "grad_norm": 0.35848763585090637, "learning_rate": 6.664312519308198e-06, "loss": 0.6924323558807373, "step": 12110, "token_acc": 0.7841889018120755 }, { "epoch": 0.784326419629201, "grad_norm": 0.2713026702404022, "learning_rate": 6.661915039035355e-06, "loss": 0.6823801517486572, "step": 12115, "token_acc": 0.7864158968565162 }, { "epoch": 0.7846501201738272, "grad_norm": 0.3930278420448303, "learning_rate": 6.6595171291268924e-06, "loss": 0.7101337432861328, "step": 12120, "token_acc": 0.7798326875896556 }, { "epoch": 0.7849738207184533, "grad_norm": 0.33000653982162476, "learning_rate": 6.657118790202717e-06, "loss": 0.6836549758911132, "step": 12125, "token_acc": 0.7858639356635349 }, { "epoch": 0.7852975212630795, "grad_norm": 0.22945818305015564, "learning_rate": 6.654720022882844e-06, "loss": 0.6686802864074707, "step": 12130, "token_acc": 0.7907433686278791 }, { "epoch": 0.7856212218077057, "grad_norm": 0.35576480627059937, "learning_rate": 6.652320827787394e-06, "loss": 0.6863958835601807, "step": 12135, "token_acc": 0.7859327815498203 }, { "epoch": 0.7859449223523318, "grad_norm": 0.3188275396823883, "learning_rate": 6.649921205536609e-06, "loss": 0.6927359580993653, "step": 12140, "token_acc": 0.7847513123707514 }, { "epoch": 0.786268622896958, "grad_norm": 0.342239111661911, "learning_rate": 6.647521156750832e-06, "loss": 0.682007122039795, "step": 12145, "token_acc": 0.7866095205288889 }, { "epoch": 0.7865923234415841, "grad_norm": 0.25992441177368164, "learning_rate": 6.645120682050521e-06, "loss": 0.6939102172851562, "step": 12150, "token_acc": 0.7848845897808633 }, { "epoch": 0.7869160239862104, "grad_norm": 0.2839870750904083, "learning_rate": 6.642719782056242e-06, "loss": 0.6722286701202392, "step": 12155, "token_acc": 0.7885911607301952 }, { "epoch": 0.7872397245308366, "grad_norm": 0.31256765127182007, "learning_rate": 6.640318457388672e-06, "loss": 0.6711128234863282, "step": 12160, "token_acc": 0.7895430779722664 }, { "epoch": 0.7875634250754627, "grad_norm": 0.4113253951072693, "learning_rate": 6.637916708668599e-06, "loss": 0.6894619941711426, "step": 12165, "token_acc": 0.7858151144775348 }, { "epoch": 0.7878871256200889, "grad_norm": 0.3584689199924469, "learning_rate": 6.635514536516918e-06, "loss": 0.6859591960906982, "step": 12170, "token_acc": 0.7871429993034132 }, { "epoch": 0.788210826164715, "grad_norm": 0.2979208528995514, "learning_rate": 6.6331119415546356e-06, "loss": 0.6521944522857666, "step": 12175, "token_acc": 0.7935426597448714 }, { "epoch": 0.7885345267093412, "grad_norm": 0.30947205424308777, "learning_rate": 6.630708924402865e-06, "loss": 0.6971765518188476, "step": 12180, "token_acc": 0.7830726808234547 }, { "epoch": 0.7888582272539674, "grad_norm": 0.37979191541671753, "learning_rate": 6.628305485682832e-06, "loss": 0.6977438449859619, "step": 12185, "token_acc": 0.7827645220497048 }, { "epoch": 0.7891819277985935, "grad_norm": 0.264157772064209, "learning_rate": 6.625901626015869e-06, "loss": 0.6749530792236328, "step": 12190, "token_acc": 0.7894663596568913 }, { "epoch": 0.7895056283432197, "grad_norm": 0.3261201083660126, "learning_rate": 6.6234973460234184e-06, "loss": 0.6635005950927735, "step": 12195, "token_acc": 0.7914013053471816 }, { "epoch": 0.7898293288878458, "grad_norm": 0.23991374671459198, "learning_rate": 6.621092646327031e-06, "loss": 0.6846953392028808, "step": 12200, "token_acc": 0.7874669216862735 }, { "epoch": 0.790153029432472, "grad_norm": 0.33999133110046387, "learning_rate": 6.618687527548364e-06, "loss": 0.6856285572052002, "step": 12205, "token_acc": 0.7856132762134509 }, { "epoch": 0.7904767299770982, "grad_norm": 0.4188295602798462, "learning_rate": 6.616281990309188e-06, "loss": 0.6951774597167969, "step": 12210, "token_acc": 0.7834710743801653 }, { "epoch": 0.7908004305217243, "grad_norm": 0.35423627495765686, "learning_rate": 6.613876035231375e-06, "loss": 0.7147263526916504, "step": 12215, "token_acc": 0.7774440734996452 }, { "epoch": 0.7911241310663505, "grad_norm": 0.3114321827888489, "learning_rate": 6.611469662936914e-06, "loss": 0.681172227859497, "step": 12220, "token_acc": 0.786777810782712 }, { "epoch": 0.7914478316109766, "grad_norm": 0.27223411202430725, "learning_rate": 6.609062874047891e-06, "loss": 0.6996353149414063, "step": 12225, "token_acc": 0.7824224632087767 }, { "epoch": 0.7917715321556028, "grad_norm": 0.31597810983657837, "learning_rate": 6.606655669186508e-06, "loss": 0.7015753269195557, "step": 12230, "token_acc": 0.7830242616246612 }, { "epoch": 0.792095232700229, "grad_norm": 0.27536019682884216, "learning_rate": 6.604248048975071e-06, "loss": 0.6883232116699218, "step": 12235, "token_acc": 0.7848611452445319 }, { "epoch": 0.7924189332448552, "grad_norm": 0.2938600182533264, "learning_rate": 6.6018400140359935e-06, "loss": 0.695641040802002, "step": 12240, "token_acc": 0.7828188613131326 }, { "epoch": 0.7927426337894814, "grad_norm": 0.27390310168266296, "learning_rate": 6.5994315649918e-06, "loss": 0.6551305770874023, "step": 12245, "token_acc": 0.7936559180624659 }, { "epoch": 0.7930663343341076, "grad_norm": 0.3363940417766571, "learning_rate": 6.597022702465114e-06, "loss": 0.691101360321045, "step": 12250, "token_acc": 0.7867826041680226 }, { "epoch": 0.7933900348787337, "grad_norm": 0.249482661485672, "learning_rate": 6.594613427078674e-06, "loss": 0.6901363372802735, "step": 12255, "token_acc": 0.7853865183229296 }, { "epoch": 0.7937137354233599, "grad_norm": 0.3531523644924164, "learning_rate": 6.592203739455322e-06, "loss": 0.686889362335205, "step": 12260, "token_acc": 0.7855544316601341 }, { "epoch": 0.794037435967986, "grad_norm": 0.25914129614830017, "learning_rate": 6.589793640218005e-06, "loss": 0.7003605365753174, "step": 12265, "token_acc": 0.7827826215358181 }, { "epoch": 0.7943611365126122, "grad_norm": 0.23274800181388855, "learning_rate": 6.587383129989779e-06, "loss": 0.6894157409667969, "step": 12270, "token_acc": 0.7847194760257044 }, { "epoch": 0.7946848370572384, "grad_norm": 0.36510637402534485, "learning_rate": 6.5849722093938076e-06, "loss": 0.6846214294433594, "step": 12275, "token_acc": 0.7846747292093299 }, { "epoch": 0.7950085376018645, "grad_norm": 0.2938500940799713, "learning_rate": 6.5825608790533524e-06, "loss": 0.6813262939453125, "step": 12280, "token_acc": 0.7872090992990946 }, { "epoch": 0.7953322381464907, "grad_norm": 0.33149266242980957, "learning_rate": 6.580149139591792e-06, "loss": 0.6778995513916015, "step": 12285, "token_acc": 0.7892017713182695 }, { "epoch": 0.7956559386911168, "grad_norm": 0.38188257813453674, "learning_rate": 6.577736991632602e-06, "loss": 0.6686759948730469, "step": 12290, "token_acc": 0.7911425064851747 }, { "epoch": 0.795979639235743, "grad_norm": 0.4170480966567993, "learning_rate": 6.57532443579937e-06, "loss": 0.6858258247375488, "step": 12295, "token_acc": 0.7866875743484373 }, { "epoch": 0.7963033397803692, "grad_norm": 0.32139402627944946, "learning_rate": 6.572911472715784e-06, "loss": 0.7081386089324951, "step": 12300, "token_acc": 0.7819806538381957 }, { "epoch": 0.7966270403249953, "grad_norm": 0.349036306142807, "learning_rate": 6.570498103005638e-06, "loss": 0.6751226902008056, "step": 12305, "token_acc": 0.7894261303995429 }, { "epoch": 0.7969507408696215, "grad_norm": 0.2639642357826233, "learning_rate": 6.5680843272928365e-06, "loss": 0.678010082244873, "step": 12310, "token_acc": 0.7881465050165092 }, { "epoch": 0.7972744414142476, "grad_norm": 0.3489009737968445, "learning_rate": 6.565670146201382e-06, "loss": 0.6911464691162109, "step": 12315, "token_acc": 0.7857787121013047 }, { "epoch": 0.7975981419588738, "grad_norm": 0.36487579345703125, "learning_rate": 6.563255560355386e-06, "loss": 0.692056941986084, "step": 12320, "token_acc": 0.7853603329987148 }, { "epoch": 0.7979218425035001, "grad_norm": 0.353083074092865, "learning_rate": 6.560840570379061e-06, "loss": 0.6869108200073242, "step": 12325, "token_acc": 0.7865081225925306 }, { "epoch": 0.7982455430481262, "grad_norm": 0.35180941224098206, "learning_rate": 6.558425176896731e-06, "loss": 0.6822014808654785, "step": 12330, "token_acc": 0.7880889087179869 }, { "epoch": 0.7985692435927524, "grad_norm": 0.2580888569355011, "learning_rate": 6.556009380532816e-06, "loss": 0.6882936000823975, "step": 12335, "token_acc": 0.7849382256161918 }, { "epoch": 0.7988929441373785, "grad_norm": 0.27051544189453125, "learning_rate": 6.553593181911844e-06, "loss": 0.7097321510314941, "step": 12340, "token_acc": 0.7803463725145118 }, { "epoch": 0.7992166446820047, "grad_norm": 0.3560402989387512, "learning_rate": 6.551176581658448e-06, "loss": 0.7093486309051513, "step": 12345, "token_acc": 0.7823483067620628 }, { "epoch": 0.7995403452266309, "grad_norm": 0.28940820693969727, "learning_rate": 6.548759580397363e-06, "loss": 0.681489372253418, "step": 12350, "token_acc": 0.7874298554746497 }, { "epoch": 0.799864045771257, "grad_norm": 0.3202396333217621, "learning_rate": 6.546342178753429e-06, "loss": 0.6920594215393067, "step": 12355, "token_acc": 0.7837872830479253 }, { "epoch": 0.8001877463158832, "grad_norm": 0.30287837982177734, "learning_rate": 6.543924377351588e-06, "loss": 0.6946981906890869, "step": 12360, "token_acc": 0.7827934254913711 }, { "epoch": 0.8005114468605093, "grad_norm": 0.38869190216064453, "learning_rate": 6.541506176816885e-06, "loss": 0.6979753971099854, "step": 12365, "token_acc": 0.7835596236349454 }, { "epoch": 0.8008351474051355, "grad_norm": 0.19702954590320587, "learning_rate": 6.539087577774473e-06, "loss": 0.6835294246673584, "step": 12370, "token_acc": 0.7871940776752666 }, { "epoch": 0.8011588479497617, "grad_norm": 0.35242608189582825, "learning_rate": 6.536668580849601e-06, "loss": 0.6623527526855468, "step": 12375, "token_acc": 0.7909458639941481 }, { "epoch": 0.8014825484943878, "grad_norm": 0.26571124792099, "learning_rate": 6.534249186667625e-06, "loss": 0.696987247467041, "step": 12380, "token_acc": 0.7834920923704696 }, { "epoch": 0.801806249039014, "grad_norm": 0.44252532720565796, "learning_rate": 6.531829395854004e-06, "loss": 0.7052000999450684, "step": 12385, "token_acc": 0.7795729055947435 }, { "epoch": 0.8021299495836401, "grad_norm": 0.3007616400718689, "learning_rate": 6.529409209034298e-06, "loss": 0.6856272220611572, "step": 12390, "token_acc": 0.7848824319565982 }, { "epoch": 0.8024536501282663, "grad_norm": 0.2384425401687622, "learning_rate": 6.526988626834168e-06, "loss": 0.672909927368164, "step": 12395, "token_acc": 0.7890060185127971 }, { "epoch": 0.8027773506728925, "grad_norm": 0.3613186478614807, "learning_rate": 6.524567649879381e-06, "loss": 0.6877284526824952, "step": 12400, "token_acc": 0.7857281248538539 }, { "epoch": 0.8031010512175186, "grad_norm": 0.33795827627182007, "learning_rate": 6.5221462787958045e-06, "loss": 0.6881209373474121, "step": 12405, "token_acc": 0.7844480284163995 }, { "epoch": 0.8034247517621449, "grad_norm": 0.3104264736175537, "learning_rate": 6.5197245142094046e-06, "loss": 0.6859311103820801, "step": 12410, "token_acc": 0.785460372423701 }, { "epoch": 0.803748452306771, "grad_norm": 0.30156630277633667, "learning_rate": 6.5173023567462554e-06, "loss": 0.67037353515625, "step": 12415, "token_acc": 0.7909028074910311 }, { "epoch": 0.8040721528513972, "grad_norm": 0.3094288408756256, "learning_rate": 6.514879807032528e-06, "loss": 0.6845757961273193, "step": 12420, "token_acc": 0.785713860956334 }, { "epoch": 0.8043958533960234, "grad_norm": 0.22691883146762848, "learning_rate": 6.5124568656944955e-06, "loss": 0.6764000415802002, "step": 12425, "token_acc": 0.7886944385487615 }, { "epoch": 0.8047195539406495, "grad_norm": 0.3118674159049988, "learning_rate": 6.510033533358534e-06, "loss": 0.669029951095581, "step": 12430, "token_acc": 0.7912194478345482 }, { "epoch": 0.8050432544852757, "grad_norm": 0.2913663685321808, "learning_rate": 6.5076098106511184e-06, "loss": 0.6755701065063476, "step": 12435, "token_acc": 0.7885173820896466 }, { "epoch": 0.8053669550299019, "grad_norm": 0.3577260375022888, "learning_rate": 6.5051856981988245e-06, "loss": 0.6979390621185303, "step": 12440, "token_acc": 0.78323420893221 }, { "epoch": 0.805690655574528, "grad_norm": 0.29793262481689453, "learning_rate": 6.502761196628333e-06, "loss": 0.6690213203430175, "step": 12445, "token_acc": 0.7919503108919382 }, { "epoch": 0.8060143561191542, "grad_norm": 0.2924577593803406, "learning_rate": 6.500336306566419e-06, "loss": 0.6625056266784668, "step": 12450, "token_acc": 0.7916884108699803 }, { "epoch": 0.8063380566637803, "grad_norm": 0.31544387340545654, "learning_rate": 6.497911028639964e-06, "loss": 0.7017776489257812, "step": 12455, "token_acc": 0.7824020016680567 }, { "epoch": 0.8066617572084065, "grad_norm": 0.2984519898891449, "learning_rate": 6.4954853634759455e-06, "loss": 0.6817046165466308, "step": 12460, "token_acc": 0.7874481864436746 }, { "epoch": 0.8069854577530327, "grad_norm": 0.2897152900695801, "learning_rate": 6.4930593117014416e-06, "loss": 0.7136102676391601, "step": 12465, "token_acc": 0.7794520547945205 }, { "epoch": 0.8073091582976588, "grad_norm": 0.3532564640045166, "learning_rate": 6.490632873943634e-06, "loss": 0.6929144382476806, "step": 12470, "token_acc": 0.7846703274018414 }, { "epoch": 0.807632858842285, "grad_norm": 0.22436031699180603, "learning_rate": 6.4882060508298e-06, "loss": 0.6763038635253906, "step": 12475, "token_acc": 0.7889960464837666 }, { "epoch": 0.8079565593869111, "grad_norm": 0.4251091480255127, "learning_rate": 6.4857788429873185e-06, "loss": 0.7005990505218506, "step": 12480, "token_acc": 0.7826083998857158 }, { "epoch": 0.8082802599315373, "grad_norm": 0.2925569713115692, "learning_rate": 6.4833512510436645e-06, "loss": 0.6931022644042969, "step": 12485, "token_acc": 0.7843021190955369 }, { "epoch": 0.8086039604761635, "grad_norm": 0.312190443277359, "learning_rate": 6.48092327562642e-06, "loss": 0.6704995155334472, "step": 12490, "token_acc": 0.7895791583166333 }, { "epoch": 0.8089276610207896, "grad_norm": 0.316854864358902, "learning_rate": 6.4784949173632585e-06, "loss": 0.6980659484863281, "step": 12495, "token_acc": 0.7828514883934931 }, { "epoch": 0.8092513615654159, "grad_norm": 0.33109548687934875, "learning_rate": 6.476066176881954e-06, "loss": 0.6680304527282714, "step": 12500, "token_acc": 0.7907843089746075 }, { "epoch": 0.809575062110042, "grad_norm": 0.3633016049861908, "learning_rate": 6.4736370548103845e-06, "loss": 0.6881482124328613, "step": 12505, "token_acc": 0.7863136816303569 }, { "epoch": 0.8098987626546682, "grad_norm": 0.298589825630188, "learning_rate": 6.471207551776519e-06, "loss": 0.6796819686889648, "step": 12510, "token_acc": 0.7868328517216169 }, { "epoch": 0.8102224631992944, "grad_norm": 0.32082056999206543, "learning_rate": 6.468777668408431e-06, "loss": 0.6916508674621582, "step": 12515, "token_acc": 0.7855724211581916 }, { "epoch": 0.8105461637439205, "grad_norm": 0.29645994305610657, "learning_rate": 6.46634740533429e-06, "loss": 0.690831470489502, "step": 12520, "token_acc": 0.7867876043319766 }, { "epoch": 0.8108698642885467, "grad_norm": 0.26741090416908264, "learning_rate": 6.463916763182363e-06, "loss": 0.6833619117736817, "step": 12525, "token_acc": 0.7880226558920591 }, { "epoch": 0.8111935648331728, "grad_norm": 0.30953627824783325, "learning_rate": 6.4614857425810155e-06, "loss": 0.7069775581359863, "step": 12530, "token_acc": 0.7802938553880142 }, { "epoch": 0.811517265377799, "grad_norm": 0.3656438887119293, "learning_rate": 6.45905434415871e-06, "loss": 0.6923176765441894, "step": 12535, "token_acc": 0.7848617176128093 }, { "epoch": 0.8118409659224252, "grad_norm": 0.3402882516384125, "learning_rate": 6.456622568544012e-06, "loss": 0.6700879573822022, "step": 12540, "token_acc": 0.7893233194426621 }, { "epoch": 0.8121646664670513, "grad_norm": 0.2948051691055298, "learning_rate": 6.454190416365575e-06, "loss": 0.6797530174255371, "step": 12545, "token_acc": 0.7869178644478148 }, { "epoch": 0.8124883670116775, "grad_norm": 0.2918376326560974, "learning_rate": 6.4517578882521595e-06, "loss": 0.6891386032104492, "step": 12550, "token_acc": 0.7851072022884491 }, { "epoch": 0.8128120675563036, "grad_norm": 0.30940142273902893, "learning_rate": 6.449324984832616e-06, "loss": 0.6775012016296387, "step": 12555, "token_acc": 0.7876650641228927 }, { "epoch": 0.8131357681009298, "grad_norm": 0.38646775484085083, "learning_rate": 6.446891706735894e-06, "loss": 0.6695359230041504, "step": 12560, "token_acc": 0.7883617209427506 }, { "epoch": 0.813459468645556, "grad_norm": 0.2948129177093506, "learning_rate": 6.444458054591044e-06, "loss": 0.6751255989074707, "step": 12565, "token_acc": 0.7892988194770225 }, { "epoch": 0.8137831691901821, "grad_norm": 0.28972184658050537, "learning_rate": 6.442024029027208e-06, "loss": 0.6781459808349609, "step": 12570, "token_acc": 0.7857115205946114 }, { "epoch": 0.8141068697348083, "grad_norm": 0.33661124110221863, "learning_rate": 6.439589630673625e-06, "loss": 0.7160888195037842, "step": 12575, "token_acc": 0.7784357149609064 }, { "epoch": 0.8144305702794344, "grad_norm": 0.259562611579895, "learning_rate": 6.4371548601596345e-06, "loss": 0.6695462226867676, "step": 12580, "token_acc": 0.7901727972626176 }, { "epoch": 0.8147542708240607, "grad_norm": 0.32911041378974915, "learning_rate": 6.434719718114667e-06, "loss": 0.6788654804229737, "step": 12585, "token_acc": 0.7886051774431959 }, { "epoch": 0.8150779713686869, "grad_norm": 0.23805758357048035, "learning_rate": 6.432284205168254e-06, "loss": 0.6615854263305664, "step": 12590, "token_acc": 0.7917600303043922 }, { "epoch": 0.815401671913313, "grad_norm": 0.20772899687290192, "learning_rate": 6.429848321950019e-06, "loss": 0.6794787406921386, "step": 12595, "token_acc": 0.7891634129168533 }, { "epoch": 0.8157253724579392, "grad_norm": 0.3225072920322418, "learning_rate": 6.427412069089682e-06, "loss": 0.6652027606964112, "step": 12600, "token_acc": 0.789097470418821 }, { "epoch": 0.8160490730025654, "grad_norm": 0.4244724214076996, "learning_rate": 6.424975447217061e-06, "loss": 0.6813885688781738, "step": 12605, "token_acc": 0.7873896528797225 }, { "epoch": 0.8163727735471915, "grad_norm": 0.22364090383052826, "learning_rate": 6.4225384569620665e-06, "loss": 0.6548244476318359, "step": 12610, "token_acc": 0.7933031218529708 }, { "epoch": 0.8166964740918177, "grad_norm": 0.2565661072731018, "learning_rate": 6.420101098954705e-06, "loss": 0.6878178596496582, "step": 12615, "token_acc": 0.7869145404763636 }, { "epoch": 0.8170201746364438, "grad_norm": 0.33540770411491394, "learning_rate": 6.417663373825079e-06, "loss": 0.690857219696045, "step": 12620, "token_acc": 0.7844903016484324 }, { "epoch": 0.81734387518107, "grad_norm": 0.3558627665042877, "learning_rate": 6.4152252822033845e-06, "loss": 0.6874423027038574, "step": 12625, "token_acc": 0.7851874592271384 }, { "epoch": 0.8176675757256961, "grad_norm": 0.33028802275657654, "learning_rate": 6.412786824719914e-06, "loss": 0.6858492851257324, "step": 12630, "token_acc": 0.7860657724893033 }, { "epoch": 0.8179912762703223, "grad_norm": 0.2567249536514282, "learning_rate": 6.410348002005053e-06, "loss": 0.678082275390625, "step": 12635, "token_acc": 0.7884100436007795 }, { "epoch": 0.8183149768149485, "grad_norm": 0.3083679974079132, "learning_rate": 6.407908814689283e-06, "loss": 0.6649519920349121, "step": 12640, "token_acc": 0.7911912074798798 }, { "epoch": 0.8186386773595746, "grad_norm": 0.27807343006134033, "learning_rate": 6.405469263403178e-06, "loss": 0.6608863830566406, "step": 12645, "token_acc": 0.7908799138688817 }, { "epoch": 0.8189623779042008, "grad_norm": 0.27789053320884705, "learning_rate": 6.4030293487774065e-06, "loss": 0.6851679801940918, "step": 12650, "token_acc": 0.7857307840369563 }, { "epoch": 0.819286078448827, "grad_norm": 0.3143354654312134, "learning_rate": 6.400589071442732e-06, "loss": 0.714022445678711, "step": 12655, "token_acc": 0.779196292055482 }, { "epoch": 0.8196097789934531, "grad_norm": 0.3102145195007324, "learning_rate": 6.398148432030011e-06, "loss": 0.7023561477661133, "step": 12660, "token_acc": 0.7836332179930796 }, { "epoch": 0.8199334795380793, "grad_norm": 0.327587753534317, "learning_rate": 6.3957074311701935e-06, "loss": 0.700311279296875, "step": 12665, "token_acc": 0.7835057883413584 }, { "epoch": 0.8202571800827055, "grad_norm": 0.3599390685558319, "learning_rate": 6.393266069494322e-06, "loss": 0.7016695976257324, "step": 12670, "token_acc": 0.7823077450778624 }, { "epoch": 0.8205808806273317, "grad_norm": 0.3486582636833191, "learning_rate": 6.390824347633538e-06, "loss": 0.6899495124816895, "step": 12675, "token_acc": 0.7851455263121953 }, { "epoch": 0.8209045811719579, "grad_norm": 0.2109387069940567, "learning_rate": 6.388382266219067e-06, "loss": 0.6919900417327881, "step": 12680, "token_acc": 0.7855023528596536 }, { "epoch": 0.821228281716584, "grad_norm": 0.225439190864563, "learning_rate": 6.385939825882231e-06, "loss": 0.6970671653747559, "step": 12685, "token_acc": 0.7838221725829165 }, { "epoch": 0.8215519822612102, "grad_norm": 0.3799644708633423, "learning_rate": 6.38349702725445e-06, "loss": 0.686211109161377, "step": 12690, "token_acc": 0.7875294024367683 }, { "epoch": 0.8218756828058363, "grad_norm": 0.2989232838153839, "learning_rate": 6.381053870967229e-06, "loss": 0.6870298385620117, "step": 12695, "token_acc": 0.7841923194247032 }, { "epoch": 0.8221993833504625, "grad_norm": 0.2872537076473236, "learning_rate": 6.378610357652171e-06, "loss": 0.6553873062133789, "step": 12700, "token_acc": 0.7933658871552283 }, { "epoch": 0.8225230838950887, "grad_norm": 0.3846650719642639, "learning_rate": 6.3761664879409665e-06, "loss": 0.6924439907073975, "step": 12705, "token_acc": 0.7849078556141283 }, { "epoch": 0.8228467844397148, "grad_norm": 0.25284725427627563, "learning_rate": 6.373722262465405e-06, "loss": 0.653708028793335, "step": 12710, "token_acc": 0.7946853380654785 }, { "epoch": 0.823170484984341, "grad_norm": 0.3846852779388428, "learning_rate": 6.371277681857362e-06, "loss": 0.659457778930664, "step": 12715, "token_acc": 0.7928834075903162 }, { "epoch": 0.8234941855289671, "grad_norm": 0.29964765906333923, "learning_rate": 6.368832746748803e-06, "loss": 0.6542153358459473, "step": 12720, "token_acc": 0.7932805641007915 }, { "epoch": 0.8238178860735933, "grad_norm": 0.3826247453689575, "learning_rate": 6.366387457771795e-06, "loss": 0.6856192588806153, "step": 12725, "token_acc": 0.7869735235274249 }, { "epoch": 0.8241415866182195, "grad_norm": 0.32987529039382935, "learning_rate": 6.363941815558484e-06, "loss": 0.6670921325683594, "step": 12730, "token_acc": 0.7892971639950678 }, { "epoch": 0.8244652871628456, "grad_norm": 0.28085747361183167, "learning_rate": 6.361495820741118e-06, "loss": 0.712874174118042, "step": 12735, "token_acc": 0.780849326510132 }, { "epoch": 0.8247889877074718, "grad_norm": 0.3291465938091278, "learning_rate": 6.35904947395203e-06, "loss": 0.6575396537780762, "step": 12740, "token_acc": 0.7946361493225564 }, { "epoch": 0.8251126882520979, "grad_norm": 0.33178648352622986, "learning_rate": 6.356602775823646e-06, "loss": 0.694333553314209, "step": 12745, "token_acc": 0.7848062825746126 }, { "epoch": 0.8254363887967241, "grad_norm": 0.23364219069480896, "learning_rate": 6.354155726988481e-06, "loss": 0.6647615909576416, "step": 12750, "token_acc": 0.7903443821098338 }, { "epoch": 0.8257600893413504, "grad_norm": 0.23846110701560974, "learning_rate": 6.351708328079144e-06, "loss": 0.7087404251098632, "step": 12755, "token_acc": 0.7799250792431083 }, { "epoch": 0.8260837898859765, "grad_norm": 0.3489242196083069, "learning_rate": 6.349260579728332e-06, "loss": 0.6902613639831543, "step": 12760, "token_acc": 0.785445185282833 }, { "epoch": 0.8264074904306027, "grad_norm": 0.31130319833755493, "learning_rate": 6.3468124825688336e-06, "loss": 0.6852584838867187, "step": 12765, "token_acc": 0.7854033238476219 }, { "epoch": 0.8267311909752288, "grad_norm": 0.2640541195869446, "learning_rate": 6.344364037233526e-06, "loss": 0.6605954647064209, "step": 12770, "token_acc": 0.7918235575741107 }, { "epoch": 0.827054891519855, "grad_norm": 0.24590960144996643, "learning_rate": 6.341915244355378e-06, "loss": 0.6665030479431152, "step": 12775, "token_acc": 0.7911490413660447 }, { "epoch": 0.8273785920644812, "grad_norm": 0.32488906383514404, "learning_rate": 6.339466104567447e-06, "loss": 0.682484769821167, "step": 12780, "token_acc": 0.7867588209382116 }, { "epoch": 0.8277022926091073, "grad_norm": 0.32425564527511597, "learning_rate": 6.3370166185028805e-06, "loss": 0.6575445175170899, "step": 12785, "token_acc": 0.7932877188018469 }, { "epoch": 0.8280259931537335, "grad_norm": 0.4486282467842102, "learning_rate": 6.334566786794918e-06, "loss": 0.7081238746643066, "step": 12790, "token_acc": 0.7829354613902516 }, { "epoch": 0.8283496936983596, "grad_norm": 0.36533957719802856, "learning_rate": 6.332116610076882e-06, "loss": 0.6759886741638184, "step": 12795, "token_acc": 0.7883363391018507 }, { "epoch": 0.8286733942429858, "grad_norm": 0.3043826222419739, "learning_rate": 6.329666088982192e-06, "loss": 0.6755225181579589, "step": 12800, "token_acc": 0.7893495829077873 }, { "epoch": 0.828997094787612, "grad_norm": 0.26657846570014954, "learning_rate": 6.327215224144351e-06, "loss": 0.6544332504272461, "step": 12805, "token_acc": 0.7944927097788271 }, { "epoch": 0.8293207953322381, "grad_norm": 0.3346325755119324, "learning_rate": 6.324764016196954e-06, "loss": 0.6692419052124023, "step": 12810, "token_acc": 0.790818061106015 }, { "epoch": 0.8296444958768643, "grad_norm": 0.2528521716594696, "learning_rate": 6.322312465773681e-06, "loss": 0.6914934635162353, "step": 12815, "token_acc": 0.7854366906193352 }, { "epoch": 0.8299681964214904, "grad_norm": 0.3034854829311371, "learning_rate": 6.319860573508306e-06, "loss": 0.6712990760803222, "step": 12820, "token_acc": 0.7889422007562518 }, { "epoch": 0.8302918969661166, "grad_norm": 0.3180408179759979, "learning_rate": 6.317408340034685e-06, "loss": 0.6870962142944336, "step": 12825, "token_acc": 0.7851112243165224 }, { "epoch": 0.8306155975107428, "grad_norm": 0.34436339139938354, "learning_rate": 6.314955765986766e-06, "loss": 0.6860225677490235, "step": 12830, "token_acc": 0.785597819163843 }, { "epoch": 0.8309392980553689, "grad_norm": 0.33807894587516785, "learning_rate": 6.312502851998589e-06, "loss": 0.6674195766448975, "step": 12835, "token_acc": 0.7893172235168695 }, { "epoch": 0.8312629985999952, "grad_norm": 0.34180259704589844, "learning_rate": 6.310049598704271e-06, "loss": 0.7047930717468261, "step": 12840, "token_acc": 0.7814314384862703 }, { "epoch": 0.8315866991446214, "grad_norm": 0.2785908579826355, "learning_rate": 6.307596006738028e-06, "loss": 0.6904669761657715, "step": 12845, "token_acc": 0.7849482634424165 }, { "epoch": 0.8319103996892475, "grad_norm": 0.2906307280063629, "learning_rate": 6.305142076734156e-06, "loss": 0.6849628448486328, "step": 12850, "token_acc": 0.7863609765077946 }, { "epoch": 0.8322341002338737, "grad_norm": 0.2953764796257019, "learning_rate": 6.302687809327042e-06, "loss": 0.6641704559326171, "step": 12855, "token_acc": 0.7901227899607505 }, { "epoch": 0.8325578007784998, "grad_norm": 0.3314530849456787, "learning_rate": 6.300233205151159e-06, "loss": 0.6686367511749267, "step": 12860, "token_acc": 0.7907135541140321 }, { "epoch": 0.832881501323126, "grad_norm": 0.2449316382408142, "learning_rate": 6.297778264841068e-06, "loss": 0.6587115287780761, "step": 12865, "token_acc": 0.7930445681170085 }, { "epoch": 0.8332052018677522, "grad_norm": 0.3713175654411316, "learning_rate": 6.295322989031415e-06, "loss": 0.6771846771240234, "step": 12870, "token_acc": 0.7900810880845389 }, { "epoch": 0.8335289024123783, "grad_norm": 0.31218937039375305, "learning_rate": 6.292867378356935e-06, "loss": 0.6773028373718262, "step": 12875, "token_acc": 0.7882217973231358 }, { "epoch": 0.8338526029570045, "grad_norm": 0.3559461236000061, "learning_rate": 6.290411433452449e-06, "loss": 0.6662465095520019, "step": 12880, "token_acc": 0.7905607501818868 }, { "epoch": 0.8341763035016306, "grad_norm": 0.3110193908214569, "learning_rate": 6.2879551549528624e-06, "loss": 0.696503734588623, "step": 12885, "token_acc": 0.784728954788835 }, { "epoch": 0.8345000040462568, "grad_norm": 0.42476528882980347, "learning_rate": 6.285498543493169e-06, "loss": 0.6964376449584961, "step": 12890, "token_acc": 0.7825747865421524 }, { "epoch": 0.834823704590883, "grad_norm": 0.34205442667007446, "learning_rate": 6.283041599708448e-06, "loss": 0.6795777797698974, "step": 12895, "token_acc": 0.7869127736033976 }, { "epoch": 0.8351474051355091, "grad_norm": 0.3488917350769043, "learning_rate": 6.280584324233866e-06, "loss": 0.6754095077514648, "step": 12900, "token_acc": 0.7897115674344952 }, { "epoch": 0.8354711056801353, "grad_norm": 0.24512475728988647, "learning_rate": 6.278126717704672e-06, "loss": 0.685191297531128, "step": 12905, "token_acc": 0.7860932194927102 }, { "epoch": 0.8357948062247614, "grad_norm": 0.2870425581932068, "learning_rate": 6.275668780756204e-06, "loss": 0.6572205066680908, "step": 12910, "token_acc": 0.7941973678391134 }, { "epoch": 0.8361185067693876, "grad_norm": 0.3179922103881836, "learning_rate": 6.27321051402388e-06, "loss": 0.6675985813140869, "step": 12915, "token_acc": 0.7914719050154824 }, { "epoch": 0.8364422073140138, "grad_norm": 0.3765808939933777, "learning_rate": 6.270751918143213e-06, "loss": 0.6766658782958984, "step": 12920, "token_acc": 0.7894894916893144 }, { "epoch": 0.83676590785864, "grad_norm": 0.4017617702484131, "learning_rate": 6.268292993749793e-06, "loss": 0.6602784156799316, "step": 12925, "token_acc": 0.7911216104398138 }, { "epoch": 0.8370896084032662, "grad_norm": 0.2266622632741928, "learning_rate": 6.265833741479296e-06, "loss": 0.6834920883178711, "step": 12930, "token_acc": 0.78661113002383 }, { "epoch": 0.8374133089478923, "grad_norm": 0.33423247933387756, "learning_rate": 6.263374161967485e-06, "loss": 0.6783041954040527, "step": 12935, "token_acc": 0.7879826461167532 }, { "epoch": 0.8377370094925185, "grad_norm": 0.34632474184036255, "learning_rate": 6.260914255850205e-06, "loss": 0.699703311920166, "step": 12940, "token_acc": 0.7819434127895198 }, { "epoch": 0.8380607100371447, "grad_norm": 0.32106298208236694, "learning_rate": 6.25845402376339e-06, "loss": 0.6941333770751953, "step": 12945, "token_acc": 0.7829933247604216 }, { "epoch": 0.8383844105817708, "grad_norm": 0.41167011857032776, "learning_rate": 6.255993466343053e-06, "loss": 0.6470194816589355, "step": 12950, "token_acc": 0.7953876567694528 }, { "epoch": 0.838708111126397, "grad_norm": 0.3606986105442047, "learning_rate": 6.253532584225295e-06, "loss": 0.6795406341552734, "step": 12955, "token_acc": 0.7872180080433298 }, { "epoch": 0.8390318116710231, "grad_norm": 1.6386380195617676, "learning_rate": 6.2510713780462974e-06, "loss": 0.661961030960083, "step": 12960, "token_acc": 0.7910063678447985 }, { "epoch": 0.8393555122156493, "grad_norm": 0.32850003242492676, "learning_rate": 6.248609848442327e-06, "loss": 0.680992317199707, "step": 12965, "token_acc": 0.7872806872296881 }, { "epoch": 0.8396792127602755, "grad_norm": 0.3125588893890381, "learning_rate": 6.246147996049738e-06, "loss": 0.6793941497802735, "step": 12970, "token_acc": 0.7871486462070567 }, { "epoch": 0.8400029133049016, "grad_norm": 0.30015090107917786, "learning_rate": 6.24368582150496e-06, "loss": 0.7161270618438721, "step": 12975, "token_acc": 0.7789864831774328 }, { "epoch": 0.8403266138495278, "grad_norm": 0.24604323506355286, "learning_rate": 6.241223325444514e-06, "loss": 0.693380069732666, "step": 12980, "token_acc": 0.7848762535197352 }, { "epoch": 0.8406503143941539, "grad_norm": 0.3335859477519989, "learning_rate": 6.238760508505e-06, "loss": 0.6862723350524902, "step": 12985, "token_acc": 0.7850696067736741 }, { "epoch": 0.8409740149387801, "grad_norm": 0.33347731828689575, "learning_rate": 6.236297371323099e-06, "loss": 0.658928394317627, "step": 12990, "token_acc": 0.7927153578956354 }, { "epoch": 0.8412977154834063, "grad_norm": 0.312436044216156, "learning_rate": 6.23383391453558e-06, "loss": 0.6658100128173828, "step": 12995, "token_acc": 0.791112686448402 }, { "epoch": 0.8416214160280324, "grad_norm": 0.3890238106250763, "learning_rate": 6.231370138779289e-06, "loss": 0.7077276229858398, "step": 13000, "token_acc": 0.7804934141752038 }, { "epoch": 0.8419451165726586, "grad_norm": 0.32118934392929077, "learning_rate": 6.228906044691162e-06, "loss": 0.671383285522461, "step": 13005, "token_acc": 0.7895351642351985 }, { "epoch": 0.8422688171172849, "grad_norm": 0.27837759256362915, "learning_rate": 6.226441632908209e-06, "loss": 0.693614387512207, "step": 13010, "token_acc": 0.7846577083058629 }, { "epoch": 0.842592517661911, "grad_norm": 0.33871322870254517, "learning_rate": 6.223976904067526e-06, "loss": 0.6558265209197998, "step": 13015, "token_acc": 0.7934597878533336 }, { "epoch": 0.8429162182065372, "grad_norm": 0.31052058935165405, "learning_rate": 6.221511858806292e-06, "loss": 0.6727995872497559, "step": 13020, "token_acc": 0.7877383586888633 }, { "epoch": 0.8432399187511633, "grad_norm": 0.2937929928302765, "learning_rate": 6.219046497761765e-06, "loss": 0.6792856216430664, "step": 13025, "token_acc": 0.7879883581578497 }, { "epoch": 0.8435636192957895, "grad_norm": 0.42624208331108093, "learning_rate": 6.216580821571288e-06, "loss": 0.6908164024353027, "step": 13030, "token_acc": 0.7848549389822703 }, { "epoch": 0.8438873198404157, "grad_norm": 0.25888791680336, "learning_rate": 6.214114830872283e-06, "loss": 0.6825175762176514, "step": 13035, "token_acc": 0.7865164851754852 }, { "epoch": 0.8442110203850418, "grad_norm": 0.2974259853363037, "learning_rate": 6.211648526302253e-06, "loss": 0.66322021484375, "step": 13040, "token_acc": 0.792033872099523 }, { "epoch": 0.844534720929668, "grad_norm": 0.3090469539165497, "learning_rate": 6.2091819084987845e-06, "loss": 0.6963265895843506, "step": 13045, "token_acc": 0.7843964356689531 }, { "epoch": 0.8448584214742941, "grad_norm": 0.25593098998069763, "learning_rate": 6.206714978099544e-06, "loss": 0.6982105255126954, "step": 13050, "token_acc": 0.7836190911289672 }, { "epoch": 0.8451821220189203, "grad_norm": 0.3167698383331299, "learning_rate": 6.204247735742277e-06, "loss": 0.6669906616210938, "step": 13055, "token_acc": 0.7916723764628498 }, { "epoch": 0.8455058225635464, "grad_norm": 0.3520139157772064, "learning_rate": 6.201780182064811e-06, "loss": 0.6790815353393554, "step": 13060, "token_acc": 0.7881049122258686 }, { "epoch": 0.8458295231081726, "grad_norm": 0.2556784749031067, "learning_rate": 6.199312317705054e-06, "loss": 0.677468204498291, "step": 13065, "token_acc": 0.7893414091657347 }, { "epoch": 0.8461532236527988, "grad_norm": 0.3304975628852844, "learning_rate": 6.196844143300996e-06, "loss": 0.6712728977203369, "step": 13070, "token_acc": 0.7886171025727524 }, { "epoch": 0.8464769241974249, "grad_norm": 0.3364717662334442, "learning_rate": 6.194375659490703e-06, "loss": 0.6883803367614746, "step": 13075, "token_acc": 0.7859313442493989 }, { "epoch": 0.8468006247420511, "grad_norm": 0.26865631341934204, "learning_rate": 6.191906866912326e-06, "loss": 0.6639264106750489, "step": 13080, "token_acc": 0.7911527677013275 }, { "epoch": 0.8471243252866772, "grad_norm": 0.37427181005477905, "learning_rate": 6.189437766204091e-06, "loss": 0.6751561164855957, "step": 13085, "token_acc": 0.7881448351071907 }, { "epoch": 0.8474480258313034, "grad_norm": 0.36573827266693115, "learning_rate": 6.186968358004308e-06, "loss": 0.6838676452636718, "step": 13090, "token_acc": 0.7864903420346294 }, { "epoch": 0.8477717263759297, "grad_norm": 0.2656306326389313, "learning_rate": 6.184498642951364e-06, "loss": 0.6494647979736328, "step": 13095, "token_acc": 0.7960619324669675 }, { "epoch": 0.8480954269205558, "grad_norm": 0.3884562849998474, "learning_rate": 6.1820286216837265e-06, "loss": 0.6706669330596924, "step": 13100, "token_acc": 0.7901557240209092 }, { "epoch": 0.848419127465182, "grad_norm": 0.44546377658843994, "learning_rate": 6.179558294839938e-06, "loss": 0.6868110656738281, "step": 13105, "token_acc": 0.7855658604916715 }, { "epoch": 0.8487428280098082, "grad_norm": 0.2718636989593506, "learning_rate": 6.177087663058626e-06, "loss": 0.6719456672668457, "step": 13110, "token_acc": 0.7913143931457436 }, { "epoch": 0.8490665285544343, "grad_norm": 0.33088573813438416, "learning_rate": 6.174616726978496e-06, "loss": 0.6609073162078858, "step": 13115, "token_acc": 0.7913777257916284 }, { "epoch": 0.8493902290990605, "grad_norm": 0.3411378562450409, "learning_rate": 6.1721454872383255e-06, "loss": 0.6623459815979004, "step": 13120, "token_acc": 0.7912895736169118 }, { "epoch": 0.8497139296436866, "grad_norm": 0.27759483456611633, "learning_rate": 6.169673944476982e-06, "loss": 0.671971607208252, "step": 13125, "token_acc": 0.7894981969154613 }, { "epoch": 0.8500376301883128, "grad_norm": 0.2529904246330261, "learning_rate": 6.167202099333399e-06, "loss": 0.6862969875335694, "step": 13130, "token_acc": 0.7872171598238968 }, { "epoch": 0.850361330732939, "grad_norm": 0.33919557929039, "learning_rate": 6.164729952446595e-06, "loss": 0.6622485160827637, "step": 13135, "token_acc": 0.7937318711515954 }, { "epoch": 0.8506850312775651, "grad_norm": 0.3589496314525604, "learning_rate": 6.1622575044556684e-06, "loss": 0.6723602294921875, "step": 13140, "token_acc": 0.7896195111529499 }, { "epoch": 0.8510087318221913, "grad_norm": 0.34002435207366943, "learning_rate": 6.159784755999792e-06, "loss": 0.6658127784729004, "step": 13145, "token_acc": 0.7908145898248279 }, { "epoch": 0.8513324323668174, "grad_norm": 0.35950231552124023, "learning_rate": 6.1573117077182125e-06, "loss": 0.6753517150878906, "step": 13150, "token_acc": 0.7882704201322244 }, { "epoch": 0.8516561329114436, "grad_norm": 0.39046740531921387, "learning_rate": 6.154838360250263e-06, "loss": 0.6751292228698731, "step": 13155, "token_acc": 0.7887197796467723 }, { "epoch": 0.8519798334560698, "grad_norm": 0.33125993609428406, "learning_rate": 6.152364714235347e-06, "loss": 0.6658978462219238, "step": 13160, "token_acc": 0.7911266726074784 }, { "epoch": 0.8523035340006959, "grad_norm": 0.33902662992477417, "learning_rate": 6.1498907703129486e-06, "loss": 0.701125955581665, "step": 13165, "token_acc": 0.7824477366818353 }, { "epoch": 0.8526272345453221, "grad_norm": 0.2725330889225006, "learning_rate": 6.147416529122628e-06, "loss": 0.6741889953613281, "step": 13170, "token_acc": 0.789216609616846 }, { "epoch": 0.8529509350899482, "grad_norm": 0.387229323387146, "learning_rate": 6.144941991304021e-06, "loss": 0.6800642013549805, "step": 13175, "token_acc": 0.7876471803346417 }, { "epoch": 0.8532746356345745, "grad_norm": 0.3427697718143463, "learning_rate": 6.142467157496842e-06, "loss": 0.6853678703308106, "step": 13180, "token_acc": 0.7894134690893336 }, { "epoch": 0.8535983361792007, "grad_norm": 0.32565659284591675, "learning_rate": 6.13999202834088e-06, "loss": 0.6962497234344482, "step": 13185, "token_acc": 0.7831192356265387 }, { "epoch": 0.8539220367238268, "grad_norm": 0.19023175537586212, "learning_rate": 6.137516604476003e-06, "loss": 0.6779755592346192, "step": 13190, "token_acc": 0.7897744661816983 }, { "epoch": 0.854245737268453, "grad_norm": 0.3137117028236389, "learning_rate": 6.135040886542152e-06, "loss": 0.6675435066223144, "step": 13195, "token_acc": 0.7913443130261467 }, { "epoch": 0.8545694378130791, "grad_norm": 0.25568804144859314, "learning_rate": 6.132564875179347e-06, "loss": 0.6733108043670655, "step": 13200, "token_acc": 0.7883321851318345 }, { "epoch": 0.8548931383577053, "grad_norm": 0.3560190796852112, "learning_rate": 6.130088571027681e-06, "loss": 0.6758867740631104, "step": 13205, "token_acc": 0.789628292888108 }, { "epoch": 0.8552168389023315, "grad_norm": 0.2988918125629425, "learning_rate": 6.127611974727327e-06, "loss": 0.6705421447753906, "step": 13210, "token_acc": 0.7886686655030438 }, { "epoch": 0.8555405394469576, "grad_norm": 0.3213658630847931, "learning_rate": 6.125135086918528e-06, "loss": 0.6656377792358399, "step": 13215, "token_acc": 0.790836970720362 }, { "epoch": 0.8558642399915838, "grad_norm": 0.3343450427055359, "learning_rate": 6.122657908241605e-06, "loss": 0.6697820663452149, "step": 13220, "token_acc": 0.7891570820643617 }, { "epoch": 0.85618794053621, "grad_norm": 0.3295578956604004, "learning_rate": 6.120180439336956e-06, "loss": 0.6788230419158936, "step": 13225, "token_acc": 0.7899863131425662 }, { "epoch": 0.8565116410808361, "grad_norm": 0.2928363084793091, "learning_rate": 6.117702680845052e-06, "loss": 0.6661265373229981, "step": 13230, "token_acc": 0.7884838115293499 }, { "epoch": 0.8568353416254623, "grad_norm": 0.3143980801105499, "learning_rate": 6.115224633406438e-06, "loss": 0.6717872619628906, "step": 13235, "token_acc": 0.7907846884053504 }, { "epoch": 0.8571590421700884, "grad_norm": 0.3575431704521179, "learning_rate": 6.112746297661736e-06, "loss": 0.6856663703918457, "step": 13240, "token_acc": 0.7860654947456375 }, { "epoch": 0.8574827427147146, "grad_norm": 0.36258798837661743, "learning_rate": 6.11026767425164e-06, "loss": 0.6802250862121582, "step": 13245, "token_acc": 0.786705370468746 }, { "epoch": 0.8578064432593407, "grad_norm": 0.28126516938209534, "learning_rate": 6.107788763816922e-06, "loss": 0.6774702072143555, "step": 13250, "token_acc": 0.7902039665003324 }, { "epoch": 0.8581301438039669, "grad_norm": 0.33497175574302673, "learning_rate": 6.105309566998424e-06, "loss": 0.683821153640747, "step": 13255, "token_acc": 0.7865384732852404 }, { "epoch": 0.8584538443485931, "grad_norm": 0.30546534061431885, "learning_rate": 6.102830084437064e-06, "loss": 0.6750622749328613, "step": 13260, "token_acc": 0.7888157183037646 }, { "epoch": 0.8587775448932193, "grad_norm": 0.34971389174461365, "learning_rate": 6.100350316773836e-06, "loss": 0.6884439945220947, "step": 13265, "token_acc": 0.7867987113384507 }, { "epoch": 0.8591012454378455, "grad_norm": 0.3747946321964264, "learning_rate": 6.0978702646498016e-06, "loss": 0.674128532409668, "step": 13270, "token_acc": 0.7902060119119507 }, { "epoch": 0.8594249459824717, "grad_norm": 0.2838088870048523, "learning_rate": 6.095389928706104e-06, "loss": 0.694204044342041, "step": 13275, "token_acc": 0.7848731011670309 }, { "epoch": 0.8597486465270978, "grad_norm": 0.34308451414108276, "learning_rate": 6.092909309583954e-06, "loss": 0.6856171607971191, "step": 13280, "token_acc": 0.7871668769158576 }, { "epoch": 0.860072347071724, "grad_norm": 0.24314568936824799, "learning_rate": 6.090428407924637e-06, "loss": 0.6608022212982178, "step": 13285, "token_acc": 0.7926428983437251 }, { "epoch": 0.8603960476163501, "grad_norm": 0.25304436683654785, "learning_rate": 6.087947224369512e-06, "loss": 0.6773757934570312, "step": 13290, "token_acc": 0.7883930220896783 }, { "epoch": 0.8607197481609763, "grad_norm": 0.3754327893257141, "learning_rate": 6.085465759560011e-06, "loss": 0.6868418693542481, "step": 13295, "token_acc": 0.7866268631789904 }, { "epoch": 0.8610434487056025, "grad_norm": 0.3747979402542114, "learning_rate": 6.0829840141376385e-06, "loss": 0.6868167400360108, "step": 13300, "token_acc": 0.7862168985335983 }, { "epoch": 0.8613671492502286, "grad_norm": 0.30572420358657837, "learning_rate": 6.080501988743971e-06, "loss": 0.6598917007446289, "step": 13305, "token_acc": 0.7937584991535537 }, { "epoch": 0.8616908497948548, "grad_norm": 0.36343222856521606, "learning_rate": 6.0780196840206565e-06, "loss": 0.6621333599090576, "step": 13310, "token_acc": 0.7928318520124287 }, { "epoch": 0.8620145503394809, "grad_norm": 0.3162235915660858, "learning_rate": 6.075537100609417e-06, "loss": 0.6823290824890137, "step": 13315, "token_acc": 0.7872450664818689 }, { "epoch": 0.8623382508841071, "grad_norm": 0.32426613569259644, "learning_rate": 6.0730542391520475e-06, "loss": 0.677309513092041, "step": 13320, "token_acc": 0.7873311655827914 }, { "epoch": 0.8626619514287333, "grad_norm": 0.3003862500190735, "learning_rate": 6.0705711002904134e-06, "loss": 0.6863716125488282, "step": 13325, "token_acc": 0.7862426344602783 }, { "epoch": 0.8629856519733594, "grad_norm": 0.22589761018753052, "learning_rate": 6.068087684666449e-06, "loss": 0.6838098049163819, "step": 13330, "token_acc": 0.7867600178040829 }, { "epoch": 0.8633093525179856, "grad_norm": 0.3186478316783905, "learning_rate": 6.065603992922166e-06, "loss": 0.6648507118225098, "step": 13335, "token_acc": 0.7910468520260157 }, { "epoch": 0.8636330530626117, "grad_norm": 0.32731157541275024, "learning_rate": 6.063120025699642e-06, "loss": 0.6621493339538574, "step": 13340, "token_acc": 0.7911069388618575 }, { "epoch": 0.8639567536072379, "grad_norm": 0.3398662209510803, "learning_rate": 6.060635783641031e-06, "loss": 0.6621633529663086, "step": 13345, "token_acc": 0.7935306056275445 }, { "epoch": 0.8642804541518642, "grad_norm": 0.36305883526802063, "learning_rate": 6.058151267388552e-06, "loss": 0.6728216648101807, "step": 13350, "token_acc": 0.7891759987893463 }, { "epoch": 0.8646041546964903, "grad_norm": 0.28079986572265625, "learning_rate": 6.055666477584501e-06, "loss": 0.6839167594909668, "step": 13355, "token_acc": 0.7870541541601235 }, { "epoch": 0.8649278552411165, "grad_norm": 0.3609100580215454, "learning_rate": 6.05318141487124e-06, "loss": 0.7031753063201904, "step": 13360, "token_acc": 0.7811069089180479 }, { "epoch": 0.8652515557857426, "grad_norm": 0.3146940767765045, "learning_rate": 6.050696079891204e-06, "loss": 0.668912410736084, "step": 13365, "token_acc": 0.7900613546243703 }, { "epoch": 0.8655752563303688, "grad_norm": 0.3522130250930786, "learning_rate": 6.048210473286899e-06, "loss": 0.6638010978698731, "step": 13370, "token_acc": 0.7913743829566121 }, { "epoch": 0.865898956874995, "grad_norm": 0.25797373056411743, "learning_rate": 6.045724595700898e-06, "loss": 0.6802741050720215, "step": 13375, "token_acc": 0.7872143491475816 }, { "epoch": 0.8662226574196211, "grad_norm": 0.3931603729724884, "learning_rate": 6.043238447775847e-06, "loss": 0.6627309799194336, "step": 13380, "token_acc": 0.7925164594982367 }, { "epoch": 0.8665463579642473, "grad_norm": 0.33387741446495056, "learning_rate": 6.040752030154462e-06, "loss": 0.6677012920379639, "step": 13385, "token_acc": 0.7911279625932823 }, { "epoch": 0.8668700585088734, "grad_norm": 0.3029365837574005, "learning_rate": 6.038265343479526e-06, "loss": 0.664194917678833, "step": 13390, "token_acc": 0.7907284598806684 }, { "epoch": 0.8671937590534996, "grad_norm": 0.37088730931282043, "learning_rate": 6.035778388393894e-06, "loss": 0.6813662052154541, "step": 13395, "token_acc": 0.7877038678162454 }, { "epoch": 0.8675174595981258, "grad_norm": 0.341035395860672, "learning_rate": 6.03329116554049e-06, "loss": 0.6856020450592041, "step": 13400, "token_acc": 0.7857612693639756 }, { "epoch": 0.8678411601427519, "grad_norm": 0.2561202049255371, "learning_rate": 6.030803675562306e-06, "loss": 0.6641447067260742, "step": 13405, "token_acc": 0.791947455806231 }, { "epoch": 0.8681648606873781, "grad_norm": 0.3068896234035492, "learning_rate": 6.028315919102406e-06, "loss": 0.6733848571777343, "step": 13410, "token_acc": 0.7876783220271348 }, { "epoch": 0.8684885612320042, "grad_norm": 0.305524080991745, "learning_rate": 6.0258278968039185e-06, "loss": 0.6900015830993652, "step": 13415, "token_acc": 0.7852576787115729 }, { "epoch": 0.8688122617766304, "grad_norm": 0.3033575713634491, "learning_rate": 6.0233396093100424e-06, "loss": 0.6891444206237793, "step": 13420, "token_acc": 0.7854213852259295 }, { "epoch": 0.8691359623212566, "grad_norm": 0.32817310094833374, "learning_rate": 6.02085105726405e-06, "loss": 0.6991082191467285, "step": 13425, "token_acc": 0.782475671367417 }, { "epoch": 0.8694596628658827, "grad_norm": 0.4015379250049591, "learning_rate": 6.0183622413092725e-06, "loss": 0.6772729873657226, "step": 13430, "token_acc": 0.7880207591856808 }, { "epoch": 0.869783363410509, "grad_norm": 0.2810695171356201, "learning_rate": 6.015873162089119e-06, "loss": 0.6741743087768555, "step": 13435, "token_acc": 0.7884020568419824 }, { "epoch": 0.8701070639551352, "grad_norm": 0.2541773021221161, "learning_rate": 6.013383820247061e-06, "loss": 0.6661395072937012, "step": 13440, "token_acc": 0.7912679076113439 }, { "epoch": 0.8704307644997613, "grad_norm": 0.29272034764289856, "learning_rate": 6.0108942164266375e-06, "loss": 0.6879295349121094, "step": 13445, "token_acc": 0.7862715620585529 }, { "epoch": 0.8707544650443875, "grad_norm": 0.2930138409137726, "learning_rate": 6.008404351271457e-06, "loss": 0.6697036743164062, "step": 13450, "token_acc": 0.7902969316196982 }, { "epoch": 0.8710781655890136, "grad_norm": 0.32279834151268005, "learning_rate": 6.005914225425198e-06, "loss": 0.7005119323730469, "step": 13455, "token_acc": 0.7823980568426333 }, { "epoch": 0.8714018661336398, "grad_norm": 0.3488389849662781, "learning_rate": 6.003423839531601e-06, "loss": 0.6808321952819825, "step": 13460, "token_acc": 0.7876479160242108 }, { "epoch": 0.871725566678266, "grad_norm": 0.3359745442867279, "learning_rate": 6.000933194234479e-06, "loss": 0.6766925811767578, "step": 13465, "token_acc": 0.7882087471793878 }, { "epoch": 0.8720492672228921, "grad_norm": 0.2747151255607605, "learning_rate": 5.998442290177708e-06, "loss": 0.6677323341369629, "step": 13470, "token_acc": 0.7904674443293799 }, { "epoch": 0.8723729677675183, "grad_norm": 0.3285481929779053, "learning_rate": 5.995951128005235e-06, "loss": 0.6581139087677002, "step": 13475, "token_acc": 0.7938301327620961 }, { "epoch": 0.8726966683121444, "grad_norm": 0.33176445960998535, "learning_rate": 5.993459708361067e-06, "loss": 0.6818974494934082, "step": 13480, "token_acc": 0.7871702342537626 }, { "epoch": 0.8730203688567706, "grad_norm": 0.3369429409503937, "learning_rate": 5.990968031889286e-06, "loss": 0.6732425212860107, "step": 13485, "token_acc": 0.7886325009805203 }, { "epoch": 0.8733440694013967, "grad_norm": 0.2888895869255066, "learning_rate": 5.988476099234033e-06, "loss": 0.6880913734436035, "step": 13490, "token_acc": 0.7848715868484124 }, { "epoch": 0.8736677699460229, "grad_norm": 0.3170129060745239, "learning_rate": 5.98598391103952e-06, "loss": 0.6847944736480713, "step": 13495, "token_acc": 0.786069846489082 }, { "epoch": 0.8739914704906491, "grad_norm": 0.26136061549186707, "learning_rate": 5.9834914679500246e-06, "loss": 0.6614060878753663, "step": 13500, "token_acc": 0.7911347684770832 }, { "epoch": 0.8743151710352752, "grad_norm": 0.3577335476875305, "learning_rate": 5.980998770609887e-06, "loss": 0.6664634704589844, "step": 13505, "token_acc": 0.791261737940429 }, { "epoch": 0.8746388715799014, "grad_norm": 0.3266409933567047, "learning_rate": 5.978505819663516e-06, "loss": 0.6804569721221924, "step": 13510, "token_acc": 0.7883366450184699 }, { "epoch": 0.8749625721245275, "grad_norm": 0.2473011165857315, "learning_rate": 5.976012615755385e-06, "loss": 0.6523775100708008, "step": 13515, "token_acc": 0.7934759072208282 }, { "epoch": 0.8752862726691538, "grad_norm": 0.4891335368156433, "learning_rate": 5.973519159530035e-06, "loss": 0.674739408493042, "step": 13520, "token_acc": 0.7893179197176641 }, { "epoch": 0.87560997321378, "grad_norm": 0.3431224822998047, "learning_rate": 5.97102545163207e-06, "loss": 0.6665802001953125, "step": 13525, "token_acc": 0.7910662552552363 }, { "epoch": 0.8759336737584061, "grad_norm": 0.32839682698249817, "learning_rate": 5.968531492706155e-06, "loss": 0.6663459777832031, "step": 13530, "token_acc": 0.7917259555736246 }, { "epoch": 0.8762573743030323, "grad_norm": 0.2668903172016144, "learning_rate": 5.9660372833970306e-06, "loss": 0.6812942504882813, "step": 13535, "token_acc": 0.7884024745042582 }, { "epoch": 0.8765810748476585, "grad_norm": 0.2597770094871521, "learning_rate": 5.963542824349491e-06, "loss": 0.6582338809967041, "step": 13540, "token_acc": 0.7930659432761147 }, { "epoch": 0.8769047753922846, "grad_norm": 0.24606038630008698, "learning_rate": 5.961048116208403e-06, "loss": 0.6652160167694092, "step": 13545, "token_acc": 0.7910015581428008 }, { "epoch": 0.8772284759369108, "grad_norm": 0.3341737687587738, "learning_rate": 5.958553159618693e-06, "loss": 0.6671675682067871, "step": 13550, "token_acc": 0.7908822251726944 }, { "epoch": 0.8775521764815369, "grad_norm": 0.2091977447271347, "learning_rate": 5.956057955225352e-06, "loss": 0.6576939582824707, "step": 13555, "token_acc": 0.7916408105956612 }, { "epoch": 0.8778758770261631, "grad_norm": 0.29438096284866333, "learning_rate": 5.953562503673439e-06, "loss": 0.6755308151245117, "step": 13560, "token_acc": 0.7897660672868294 }, { "epoch": 0.8781995775707893, "grad_norm": 0.3937159478664398, "learning_rate": 5.951066805608071e-06, "loss": 0.6963639259338379, "step": 13565, "token_acc": 0.784299392365077 }, { "epoch": 0.8785232781154154, "grad_norm": 0.307392954826355, "learning_rate": 5.948570861674435e-06, "loss": 0.6771231174468995, "step": 13570, "token_acc": 0.789910742330646 }, { "epoch": 0.8788469786600416, "grad_norm": 0.33206188678741455, "learning_rate": 5.946074672517778e-06, "loss": 0.6836671829223633, "step": 13575, "token_acc": 0.7867787349218122 }, { "epoch": 0.8791706792046677, "grad_norm": 0.26204657554626465, "learning_rate": 5.943578238783407e-06, "loss": 0.6835948944091796, "step": 13580, "token_acc": 0.7861524201573 }, { "epoch": 0.8794943797492939, "grad_norm": 0.33222365379333496, "learning_rate": 5.941081561116702e-06, "loss": 0.6611870288848877, "step": 13585, "token_acc": 0.792091530520703 }, { "epoch": 0.8798180802939201, "grad_norm": 0.38184854388237, "learning_rate": 5.938584640163097e-06, "loss": 0.6956467628479004, "step": 13590, "token_acc": 0.7853328138580035 }, { "epoch": 0.8801417808385462, "grad_norm": 0.31582242250442505, "learning_rate": 5.936087476568089e-06, "loss": 0.6565232276916504, "step": 13595, "token_acc": 0.7942451118726064 }, { "epoch": 0.8804654813831724, "grad_norm": 0.38542279601097107, "learning_rate": 5.933590070977246e-06, "loss": 0.6707451343536377, "step": 13600, "token_acc": 0.7914917703324938 }, { "epoch": 0.8807891819277986, "grad_norm": 0.28761371970176697, "learning_rate": 5.9310924240361915e-06, "loss": 0.6730297565460205, "step": 13605, "token_acc": 0.788537523378026 }, { "epoch": 0.8811128824724248, "grad_norm": 0.2843751311302185, "learning_rate": 5.928594536390611e-06, "loss": 0.6547617435455322, "step": 13610, "token_acc": 0.7934799740258103 }, { "epoch": 0.881436583017051, "grad_norm": 0.2735103964805603, "learning_rate": 5.926096408686257e-06, "loss": 0.6791866779327392, "step": 13615, "token_acc": 0.786615322465043 }, { "epoch": 0.8817602835616771, "grad_norm": 0.30500590801239014, "learning_rate": 5.9235980415689405e-06, "loss": 0.6572086334228515, "step": 13620, "token_acc": 0.7932040490278418 }, { "epoch": 0.8820839841063033, "grad_norm": 0.30425265431404114, "learning_rate": 5.921099435684535e-06, "loss": 0.668804931640625, "step": 13625, "token_acc": 0.789629600819364 }, { "epoch": 0.8824076846509294, "grad_norm": 0.3265846073627472, "learning_rate": 5.918600591678978e-06, "loss": 0.6687122344970703, "step": 13630, "token_acc": 0.7899352484186588 }, { "epoch": 0.8827313851955556, "grad_norm": 0.3287780284881592, "learning_rate": 5.916101510198266e-06, "loss": 0.6807910442352295, "step": 13635, "token_acc": 0.7884236372565068 }, { "epoch": 0.8830550857401818, "grad_norm": 0.24815811216831207, "learning_rate": 5.913602191888453e-06, "loss": 0.6826091766357422, "step": 13640, "token_acc": 0.7868936010407865 }, { "epoch": 0.8833787862848079, "grad_norm": 0.33609896898269653, "learning_rate": 5.911102637395666e-06, "loss": 0.6670809745788574, "step": 13645, "token_acc": 0.7906022413621097 }, { "epoch": 0.8837024868294341, "grad_norm": 0.29377099871635437, "learning_rate": 5.908602847366082e-06, "loss": 0.6729038238525391, "step": 13650, "token_acc": 0.7905565643315476 }, { "epoch": 0.8840261873740602, "grad_norm": 0.3176758587360382, "learning_rate": 5.906102822445943e-06, "loss": 0.6660021781921387, "step": 13655, "token_acc": 0.7907378190255221 }, { "epoch": 0.8843498879186864, "grad_norm": 0.3569759726524353, "learning_rate": 5.903602563281551e-06, "loss": 0.6785246849060058, "step": 13660, "token_acc": 0.7882964993280732 }, { "epoch": 0.8846735884633126, "grad_norm": 0.30956271290779114, "learning_rate": 5.901102070519269e-06, "loss": 0.6811991691589355, "step": 13665, "token_acc": 0.7863071934993475 }, { "epoch": 0.8849972890079387, "grad_norm": 0.35618969798088074, "learning_rate": 5.898601344805523e-06, "loss": 0.6717731475830078, "step": 13670, "token_acc": 0.7900919580466657 }, { "epoch": 0.8853209895525649, "grad_norm": 0.32129573822021484, "learning_rate": 5.8961003867867925e-06, "loss": 0.6735696792602539, "step": 13675, "token_acc": 0.7889177919242886 }, { "epoch": 0.885644690097191, "grad_norm": 0.28871017694473267, "learning_rate": 5.893599197109625e-06, "loss": 0.6490561962127686, "step": 13680, "token_acc": 0.7935449502185973 }, { "epoch": 0.8859683906418172, "grad_norm": 0.3165975511074066, "learning_rate": 5.891097776420622e-06, "loss": 0.7181078910827636, "step": 13685, "token_acc": 0.7785485969676398 }, { "epoch": 0.8862920911864435, "grad_norm": 0.32345592975616455, "learning_rate": 5.888596125366446e-06, "loss": 0.6633003711700439, "step": 13690, "token_acc": 0.7906926465421723 }, { "epoch": 0.8866157917310696, "grad_norm": 0.24439828097820282, "learning_rate": 5.886094244593822e-06, "loss": 0.681956672668457, "step": 13695, "token_acc": 0.7871237683897961 }, { "epoch": 0.8869394922756958, "grad_norm": 0.29448696970939636, "learning_rate": 5.8835921347495305e-06, "loss": 0.6774829387664795, "step": 13700, "token_acc": 0.7883255486261515 }, { "epoch": 0.887263192820322, "grad_norm": 0.3688531517982483, "learning_rate": 5.8810897964804135e-06, "loss": 0.6885070323944091, "step": 13705, "token_acc": 0.7870311466232378 }, { "epoch": 0.8875868933649481, "grad_norm": 0.2589508593082428, "learning_rate": 5.878587230433372e-06, "loss": 0.6756592273712159, "step": 13710, "token_acc": 0.7888452358190913 }, { "epoch": 0.8879105939095743, "grad_norm": 0.391707181930542, "learning_rate": 5.876084437255365e-06, "loss": 0.6746979236602784, "step": 13715, "token_acc": 0.7905390068162215 }, { "epoch": 0.8882342944542004, "grad_norm": 0.3425661325454712, "learning_rate": 5.873581417593412e-06, "loss": 0.6887935161590576, "step": 13720, "token_acc": 0.7860490025438479 }, { "epoch": 0.8885579949988266, "grad_norm": 0.3399907648563385, "learning_rate": 5.871078172094585e-06, "loss": 0.6837080001831055, "step": 13725, "token_acc": 0.786592724166452 }, { "epoch": 0.8888816955434528, "grad_norm": 0.3304192125797272, "learning_rate": 5.868574701406025e-06, "loss": 0.6649666786193847, "step": 13730, "token_acc": 0.7912025444948231 }, { "epoch": 0.8892053960880789, "grad_norm": 0.3225023150444031, "learning_rate": 5.8660710061749205e-06, "loss": 0.656136417388916, "step": 13735, "token_acc": 0.7935416720207653 }, { "epoch": 0.8895290966327051, "grad_norm": 0.3498989939689636, "learning_rate": 5.8635670870485255e-06, "loss": 0.6800776481628418, "step": 13740, "token_acc": 0.7875131934881835 }, { "epoch": 0.8898527971773312, "grad_norm": 0.3734721839427948, "learning_rate": 5.861062944674148e-06, "loss": 0.6861187934875488, "step": 13745, "token_acc": 0.7853049257750833 }, { "epoch": 0.8901764977219574, "grad_norm": 0.39744189381599426, "learning_rate": 5.858558579699156e-06, "loss": 0.677789831161499, "step": 13750, "token_acc": 0.7879574569302389 }, { "epoch": 0.8905001982665836, "grad_norm": 0.47516483068466187, "learning_rate": 5.8560539927709725e-06, "loss": 0.6673545837402344, "step": 13755, "token_acc": 0.791170912761675 }, { "epoch": 0.8908238988112097, "grad_norm": 0.3097265064716339, "learning_rate": 5.8535491845370795e-06, "loss": 0.6759142875671387, "step": 13760, "token_acc": 0.7885234676375076 }, { "epoch": 0.8911475993558359, "grad_norm": 0.4034174680709839, "learning_rate": 5.851044155645018e-06, "loss": 0.7169693946838379, "step": 13765, "token_acc": 0.7799443806141634 }, { "epoch": 0.891471299900462, "grad_norm": 0.3071991503238678, "learning_rate": 5.848538906742382e-06, "loss": 0.6535534381866455, "step": 13770, "token_acc": 0.7921612699304629 }, { "epoch": 0.8917950004450883, "grad_norm": 0.3405417203903198, "learning_rate": 5.846033438476826e-06, "loss": 0.6719321250915528, "step": 13775, "token_acc": 0.7878957377782749 }, { "epoch": 0.8921187009897145, "grad_norm": 0.30216720700263977, "learning_rate": 5.843527751496058e-06, "loss": 0.6582840919494629, "step": 13780, "token_acc": 0.7918455695008021 }, { "epoch": 0.8924424015343406, "grad_norm": 0.30555158853530884, "learning_rate": 5.841021846447843e-06, "loss": 0.6769416809082032, "step": 13785, "token_acc": 0.789014399205561 }, { "epoch": 0.8927661020789668, "grad_norm": 0.30717602372169495, "learning_rate": 5.8385157239800074e-06, "loss": 0.6697983741760254, "step": 13790, "token_acc": 0.7915960935529208 }, { "epoch": 0.8930898026235929, "grad_norm": 0.34984591603279114, "learning_rate": 5.836009384740429e-06, "loss": 0.6832991123199463, "step": 13795, "token_acc": 0.7877623669274944 }, { "epoch": 0.8934135031682191, "grad_norm": 0.40262171626091003, "learning_rate": 5.833502829377039e-06, "loss": 0.6585962295532226, "step": 13800, "token_acc": 0.7914493274637617 }, { "epoch": 0.8937372037128453, "grad_norm": 0.2557849586009979, "learning_rate": 5.8309960585378325e-06, "loss": 0.6754191875457763, "step": 13805, "token_acc": 0.7898618162213508 }, { "epoch": 0.8940609042574714, "grad_norm": 0.3670249283313751, "learning_rate": 5.828489072870852e-06, "loss": 0.696669626235962, "step": 13810, "token_acc": 0.7831917929207147 }, { "epoch": 0.8943846048020976, "grad_norm": 0.26436275243759155, "learning_rate": 5.8259818730242035e-06, "loss": 0.6875093460083008, "step": 13815, "token_acc": 0.7868381336771926 }, { "epoch": 0.8947083053467237, "grad_norm": 0.30203473567962646, "learning_rate": 5.823474459646042e-06, "loss": 0.6702649116516113, "step": 13820, "token_acc": 0.7911893403520316 }, { "epoch": 0.8950320058913499, "grad_norm": 0.263439416885376, "learning_rate": 5.82096683338458e-06, "loss": 0.673521614074707, "step": 13825, "token_acc": 0.7880459289369294 }, { "epoch": 0.8953557064359761, "grad_norm": 0.36857253313064575, "learning_rate": 5.818458994888086e-06, "loss": 0.6784576416015625, "step": 13830, "token_acc": 0.7881290526857392 }, { "epoch": 0.8956794069806022, "grad_norm": 0.2889501750469208, "learning_rate": 5.815950944804881e-06, "loss": 0.6733293533325195, "step": 13835, "token_acc": 0.7889793282479843 }, { "epoch": 0.8960031075252284, "grad_norm": 0.27148810029029846, "learning_rate": 5.813442683783344e-06, "loss": 0.6619246006011963, "step": 13840, "token_acc": 0.7927298675101374 }, { "epoch": 0.8963268080698545, "grad_norm": 0.24706432223320007, "learning_rate": 5.810934212471904e-06, "loss": 0.6834254264831543, "step": 13845, "token_acc": 0.7882888825624753 }, { "epoch": 0.8966505086144807, "grad_norm": 0.382659912109375, "learning_rate": 5.808425531519049e-06, "loss": 0.6562941074371338, "step": 13850, "token_acc": 0.7926068073931926 }, { "epoch": 0.8969742091591069, "grad_norm": 0.3032199740409851, "learning_rate": 5.805916641573318e-06, "loss": 0.6472848892211914, "step": 13855, "token_acc": 0.7962734172108621 }, { "epoch": 0.8972979097037331, "grad_norm": 0.3291858732700348, "learning_rate": 5.8034075432833056e-06, "loss": 0.6538081169128418, "step": 13860, "token_acc": 0.7950420270434888 }, { "epoch": 0.8976216102483593, "grad_norm": 0.25762805342674255, "learning_rate": 5.800898237297662e-06, "loss": 0.6397839069366456, "step": 13865, "token_acc": 0.7976065868862295 }, { "epoch": 0.8979453107929855, "grad_norm": 0.36070165038108826, "learning_rate": 5.798388724265085e-06, "loss": 0.676146411895752, "step": 13870, "token_acc": 0.7888178482979825 }, { "epoch": 0.8982690113376116, "grad_norm": 0.3335185647010803, "learning_rate": 5.795879004834334e-06, "loss": 0.6758838653564453, "step": 13875, "token_acc": 0.788449079461326 }, { "epoch": 0.8985927118822378, "grad_norm": 0.3192083239555359, "learning_rate": 5.793369079654214e-06, "loss": 0.6815458297729492, "step": 13880, "token_acc": 0.7872096303959372 }, { "epoch": 0.8989164124268639, "grad_norm": 0.34199538826942444, "learning_rate": 5.790858949373589e-06, "loss": 0.6432165145874024, "step": 13885, "token_acc": 0.7967737453103091 }, { "epoch": 0.8992401129714901, "grad_norm": 0.30181580781936646, "learning_rate": 5.788348614641374e-06, "loss": 0.6873315811157227, "step": 13890, "token_acc": 0.786854839261637 }, { "epoch": 0.8995638135161163, "grad_norm": 0.3088257908821106, "learning_rate": 5.785838076106535e-06, "loss": 0.6535165309906006, "step": 13895, "token_acc": 0.7948992772143898 }, { "epoch": 0.8998875140607424, "grad_norm": 0.3188956379890442, "learning_rate": 5.783327334418094e-06, "loss": 0.6754303455352784, "step": 13900, "token_acc": 0.7909172633203058 }, { "epoch": 0.9002112146053686, "grad_norm": 0.3046541213989258, "learning_rate": 5.780816390225124e-06, "loss": 0.6807552337646484, "step": 13905, "token_acc": 0.7891082607932494 }, { "epoch": 0.9005349151499947, "grad_norm": 0.33299893140792847, "learning_rate": 5.778305244176747e-06, "loss": 0.6450786590576172, "step": 13910, "token_acc": 0.7959257135187241 }, { "epoch": 0.9008586156946209, "grad_norm": 0.24938076734542847, "learning_rate": 5.775793896922146e-06, "loss": 0.6606608390808105, "step": 13915, "token_acc": 0.7931560592850916 }, { "epoch": 0.901182316239247, "grad_norm": 0.33047041296958923, "learning_rate": 5.773282349110546e-06, "loss": 0.6728289127349854, "step": 13920, "token_acc": 0.7890200169524679 }, { "epoch": 0.9015060167838732, "grad_norm": 0.2641415596008301, "learning_rate": 5.770770601391231e-06, "loss": 0.6800199508666992, "step": 13925, "token_acc": 0.786997824603859 }, { "epoch": 0.9018297173284994, "grad_norm": 0.34966328740119934, "learning_rate": 5.768258654413533e-06, "loss": 0.6827391147613525, "step": 13930, "token_acc": 0.7881940690523584 }, { "epoch": 0.9021534178731255, "grad_norm": 0.2635694146156311, "learning_rate": 5.765746508826836e-06, "loss": 0.664461898803711, "step": 13935, "token_acc": 0.7922102341987188 }, { "epoch": 0.9024771184177517, "grad_norm": 0.37107163667678833, "learning_rate": 5.763234165280577e-06, "loss": 0.6677616119384766, "step": 13940, "token_acc": 0.7908500292831752 }, { "epoch": 0.9028008189623778, "grad_norm": 0.2966479957103729, "learning_rate": 5.760721624424242e-06, "loss": 0.6799795150756835, "step": 13945, "token_acc": 0.7868826005008908 }, { "epoch": 0.9031245195070041, "grad_norm": 0.37259241938591003, "learning_rate": 5.758208886907368e-06, "loss": 0.6651219367980957, "step": 13950, "token_acc": 0.7902089700515353 }, { "epoch": 0.9034482200516303, "grad_norm": 0.2688922584056854, "learning_rate": 5.755695953379548e-06, "loss": 0.6448179244995117, "step": 13955, "token_acc": 0.7953663618329944 }, { "epoch": 0.9037719205962564, "grad_norm": 0.32213282585144043, "learning_rate": 5.753182824490417e-06, "loss": 0.6962852954864502, "step": 13960, "token_acc": 0.7836877381709755 }, { "epoch": 0.9040956211408826, "grad_norm": 0.28111666440963745, "learning_rate": 5.750669500889666e-06, "loss": 0.6856455326080322, "step": 13965, "token_acc": 0.7860516792584598 }, { "epoch": 0.9044193216855088, "grad_norm": 0.33070725202560425, "learning_rate": 5.748155983227037e-06, "loss": 0.6808856010437012, "step": 13970, "token_acc": 0.7879436597174982 }, { "epoch": 0.9047430222301349, "grad_norm": 0.3503435254096985, "learning_rate": 5.745642272152321e-06, "loss": 0.6750656127929687, "step": 13975, "token_acc": 0.7891222598046166 }, { "epoch": 0.9050667227747611, "grad_norm": 0.3738996982574463, "learning_rate": 5.743128368315356e-06, "loss": 0.6725114345550537, "step": 13980, "token_acc": 0.7892182147627927 }, { "epoch": 0.9053904233193872, "grad_norm": 0.33019620180130005, "learning_rate": 5.740614272366035e-06, "loss": 0.6588165283203125, "step": 13985, "token_acc": 0.7931536733623775 }, { "epoch": 0.9057141238640134, "grad_norm": 0.4149957299232483, "learning_rate": 5.738099984954297e-06, "loss": 0.6810334205627442, "step": 13990, "token_acc": 0.7872961239651277 }, { "epoch": 0.9060378244086396, "grad_norm": 0.297578364610672, "learning_rate": 5.73558550673013e-06, "loss": 0.6369699478149414, "step": 13995, "token_acc": 0.7989036574601185 }, { "epoch": 0.9063615249532657, "grad_norm": 0.3067704141139984, "learning_rate": 5.733070838343575e-06, "loss": 0.6566893577575683, "step": 14000, "token_acc": 0.793151417870519 }, { "epoch": 0.9066852254978919, "grad_norm": 0.37997666001319885, "learning_rate": 5.73055598044472e-06, "loss": 0.6768090724945068, "step": 14005, "token_acc": 0.7874048580316367 }, { "epoch": 0.907008926042518, "grad_norm": 0.31187018752098083, "learning_rate": 5.728040933683701e-06, "loss": 0.6642518997192383, "step": 14010, "token_acc": 0.792339019236534 }, { "epoch": 0.9073326265871442, "grad_norm": 0.2832997441291809, "learning_rate": 5.725525698710704e-06, "loss": 0.6756316184997558, "step": 14015, "token_acc": 0.7878224929614989 }, { "epoch": 0.9076563271317704, "grad_norm": 0.26794302463531494, "learning_rate": 5.723010276175964e-06, "loss": 0.6537430763244629, "step": 14020, "token_acc": 0.7944779103839431 }, { "epoch": 0.9079800276763965, "grad_norm": 0.2664666473865509, "learning_rate": 5.720494666729764e-06, "loss": 0.6405961990356446, "step": 14025, "token_acc": 0.7965519170172963 }, { "epoch": 0.9083037282210227, "grad_norm": 0.3482978343963623, "learning_rate": 5.717978871022435e-06, "loss": 0.6648573875427246, "step": 14030, "token_acc": 0.7910734421273063 }, { "epoch": 0.908627428765649, "grad_norm": 0.3037799596786499, "learning_rate": 5.715462889704357e-06, "loss": 0.6677248001098632, "step": 14035, "token_acc": 0.78929252377027 }, { "epoch": 0.9089511293102751, "grad_norm": 0.4207105338573456, "learning_rate": 5.712946723425957e-06, "loss": 0.6634857654571533, "step": 14040, "token_acc": 0.7916030117852466 }, { "epoch": 0.9092748298549013, "grad_norm": 0.3886242210865021, "learning_rate": 5.71043037283771e-06, "loss": 0.6786141395568848, "step": 14045, "token_acc": 0.7881073325836597 }, { "epoch": 0.9095985303995274, "grad_norm": 0.33514848351478577, "learning_rate": 5.70791383859014e-06, "loss": 0.6477683067321778, "step": 14050, "token_acc": 0.7961640229774749 }, { "epoch": 0.9099222309441536, "grad_norm": 0.34152838587760925, "learning_rate": 5.705397121333815e-06, "loss": 0.6482287406921386, "step": 14055, "token_acc": 0.7942634841091916 }, { "epoch": 0.9102459314887797, "grad_norm": 0.2709685266017914, "learning_rate": 5.7028802217193565e-06, "loss": 0.6667448520660401, "step": 14060, "token_acc": 0.791287570579678 }, { "epoch": 0.9105696320334059, "grad_norm": 0.35012829303741455, "learning_rate": 5.700363140397427e-06, "loss": 0.6772259712219239, "step": 14065, "token_acc": 0.7881379641101475 }, { "epoch": 0.9108933325780321, "grad_norm": 0.3110218048095703, "learning_rate": 5.6978458780187386e-06, "loss": 0.6666254997253418, "step": 14070, "token_acc": 0.7926089628585795 }, { "epoch": 0.9112170331226582, "grad_norm": 0.37699222564697266, "learning_rate": 5.695328435234049e-06, "loss": 0.6690099239349365, "step": 14075, "token_acc": 0.7900222808410378 }, { "epoch": 0.9115407336672844, "grad_norm": 0.3474813401699066, "learning_rate": 5.692810812694165e-06, "loss": 0.6657419204711914, "step": 14080, "token_acc": 0.791174933289318 }, { "epoch": 0.9118644342119105, "grad_norm": 0.3700346350669861, "learning_rate": 5.690293011049937e-06, "loss": 0.6663958549499511, "step": 14085, "token_acc": 0.7927196758673082 }, { "epoch": 0.9121881347565367, "grad_norm": 0.31775808334350586, "learning_rate": 5.687775030952265e-06, "loss": 0.6572722911834716, "step": 14090, "token_acc": 0.7928545428322219 }, { "epoch": 0.9125118353011629, "grad_norm": 0.2834157347679138, "learning_rate": 5.685256873052092e-06, "loss": 0.6745006561279296, "step": 14095, "token_acc": 0.7879585586759628 }, { "epoch": 0.912835535845789, "grad_norm": 0.2667924165725708, "learning_rate": 5.682738538000409e-06, "loss": 0.6615484237670899, "step": 14100, "token_acc": 0.791394832369724 }, { "epoch": 0.9131592363904152, "grad_norm": 0.37801119685173035, "learning_rate": 5.680220026448249e-06, "loss": 0.6496705055236817, "step": 14105, "token_acc": 0.7946144796791826 }, { "epoch": 0.9134829369350413, "grad_norm": 0.38328880071640015, "learning_rate": 5.6777013390466975e-06, "loss": 0.6386053562164307, "step": 14110, "token_acc": 0.7975841133316468 }, { "epoch": 0.9138066374796675, "grad_norm": 0.29991745948791504, "learning_rate": 5.675182476446879e-06, "loss": 0.6791599750518799, "step": 14115, "token_acc": 0.7891304487364644 }, { "epoch": 0.9141303380242938, "grad_norm": 0.40243032574653625, "learning_rate": 5.6726634392999665e-06, "loss": 0.6733151912689209, "step": 14120, "token_acc": 0.7883165573169241 }, { "epoch": 0.9144540385689199, "grad_norm": 0.26294365525245667, "learning_rate": 5.670144228257179e-06, "loss": 0.6530462265014648, "step": 14125, "token_acc": 0.7948550739404808 }, { "epoch": 0.9147777391135461, "grad_norm": 0.30818697810173035, "learning_rate": 5.667624843969774e-06, "loss": 0.670479679107666, "step": 14130, "token_acc": 0.7903457316074062 }, { "epoch": 0.9151014396581723, "grad_norm": 0.3310618996620178, "learning_rate": 5.665105287089065e-06, "loss": 0.6593600273132324, "step": 14135, "token_acc": 0.7947908494681017 }, { "epoch": 0.9154251402027984, "grad_norm": 0.28894364833831787, "learning_rate": 5.6625855582664005e-06, "loss": 0.704717493057251, "step": 14140, "token_acc": 0.7814998796142587 }, { "epoch": 0.9157488407474246, "grad_norm": 0.27531057596206665, "learning_rate": 5.660065658153177e-06, "loss": 0.6364203453063965, "step": 14145, "token_acc": 0.798837443938891 }, { "epoch": 0.9160725412920507, "grad_norm": 0.29010236263275146, "learning_rate": 5.657545587400837e-06, "loss": 0.6982431888580323, "step": 14150, "token_acc": 0.7861196348556242 }, { "epoch": 0.9163962418366769, "grad_norm": 0.3585869371891022, "learning_rate": 5.6550253466608605e-06, "loss": 0.6767502784729004, "step": 14155, "token_acc": 0.7887916074574185 }, { "epoch": 0.916719942381303, "grad_norm": 0.3645000159740448, "learning_rate": 5.65250493658478e-06, "loss": 0.6999550819396972, "step": 14160, "token_acc": 0.7823786867146838 }, { "epoch": 0.9170436429259292, "grad_norm": 0.29241687059402466, "learning_rate": 5.649984357824167e-06, "loss": 0.6621688842773438, "step": 14165, "token_acc": 0.7912443599662357 }, { "epoch": 0.9173673434705554, "grad_norm": 0.397258460521698, "learning_rate": 5.647463611030639e-06, "loss": 0.6784389972686767, "step": 14170, "token_acc": 0.7886823034573293 }, { "epoch": 0.9176910440151815, "grad_norm": 0.3151560127735138, "learning_rate": 5.644942696855853e-06, "loss": 0.6745148658752441, "step": 14175, "token_acc": 0.7891592083700996 }, { "epoch": 0.9180147445598077, "grad_norm": 0.257720410823822, "learning_rate": 5.6424216159515125e-06, "loss": 0.6579457283020019, "step": 14180, "token_acc": 0.793670314399861 }, { "epoch": 0.9183384451044339, "grad_norm": 0.36867132782936096, "learning_rate": 5.639900368969364e-06, "loss": 0.6834515571594239, "step": 14185, "token_acc": 0.7866028833380233 }, { "epoch": 0.91866214564906, "grad_norm": 0.4279583990573883, "learning_rate": 5.637378956561192e-06, "loss": 0.6442219257354737, "step": 14190, "token_acc": 0.7963307948895463 }, { "epoch": 0.9189858461936862, "grad_norm": 0.36893942952156067, "learning_rate": 5.634857379378835e-06, "loss": 0.6565260887145996, "step": 14195, "token_acc": 0.7935353145503666 }, { "epoch": 0.9193095467383123, "grad_norm": 0.31839054822921753, "learning_rate": 5.632335638074165e-06, "loss": 0.6486944198608399, "step": 14200, "token_acc": 0.7957257301773221 }, { "epoch": 0.9196332472829386, "grad_norm": 0.34951022267341614, "learning_rate": 5.6298137332990946e-06, "loss": 0.6615038871765136, "step": 14205, "token_acc": 0.791401725452632 }, { "epoch": 0.9199569478275648, "grad_norm": 0.3457949459552765, "learning_rate": 5.627291665705585e-06, "loss": 0.6824810028076171, "step": 14210, "token_acc": 0.7872944917601215 }, { "epoch": 0.9202806483721909, "grad_norm": 0.2637552320957184, "learning_rate": 5.624769435945639e-06, "loss": 0.6671661853790283, "step": 14215, "token_acc": 0.7912529698636989 }, { "epoch": 0.9206043489168171, "grad_norm": 0.3497336804866791, "learning_rate": 5.622247044671297e-06, "loss": 0.6641841888427734, "step": 14220, "token_acc": 0.7906580848192183 }, { "epoch": 0.9209280494614432, "grad_norm": 0.21557657420635223, "learning_rate": 5.619724492534643e-06, "loss": 0.6612845420837402, "step": 14225, "token_acc": 0.7936384376328569 }, { "epoch": 0.9212517500060694, "grad_norm": 0.29152217507362366, "learning_rate": 5.617201780187806e-06, "loss": 0.6603916645050049, "step": 14230, "token_acc": 0.792574964302713 }, { "epoch": 0.9215754505506956, "grad_norm": 0.34456801414489746, "learning_rate": 5.614678908282952e-06, "loss": 0.6657940864562988, "step": 14235, "token_acc": 0.7910646030453036 }, { "epoch": 0.9218991510953217, "grad_norm": 0.3403018116950989, "learning_rate": 5.61215587747229e-06, "loss": 0.6509439468383789, "step": 14240, "token_acc": 0.7952690256907416 }, { "epoch": 0.9222228516399479, "grad_norm": 0.3475635051727295, "learning_rate": 5.609632688408069e-06, "loss": 0.6608295440673828, "step": 14245, "token_acc": 0.7919273339749759 }, { "epoch": 0.922546552184574, "grad_norm": 0.3164980709552765, "learning_rate": 5.607109341742579e-06, "loss": 0.6760335445404053, "step": 14250, "token_acc": 0.7886263865616042 }, { "epoch": 0.9228702527292002, "grad_norm": 0.25013285875320435, "learning_rate": 5.6045858381281546e-06, "loss": 0.6690093040466308, "step": 14255, "token_acc": 0.7900797165633304 }, { "epoch": 0.9231939532738264, "grad_norm": 0.2966543138027191, "learning_rate": 5.602062178217167e-06, "loss": 0.6674171447753906, "step": 14260, "token_acc": 0.7909588401587261 }, { "epoch": 0.9235176538184525, "grad_norm": 0.3420983552932739, "learning_rate": 5.599538362662027e-06, "loss": 0.6506765365600586, "step": 14265, "token_acc": 0.7962989766822505 }, { "epoch": 0.9238413543630787, "grad_norm": 0.35606440901756287, "learning_rate": 5.5970143921151885e-06, "loss": 0.6736151218414307, "step": 14270, "token_acc": 0.7890627342564662 }, { "epoch": 0.9241650549077048, "grad_norm": 0.3347908854484558, "learning_rate": 5.594490267229144e-06, "loss": 0.68399019241333, "step": 14275, "token_acc": 0.7865076367413423 }, { "epoch": 0.924488755452331, "grad_norm": 0.28994321823120117, "learning_rate": 5.591965988656428e-06, "loss": 0.6753104209899903, "step": 14280, "token_acc": 0.7894469309885003 }, { "epoch": 0.9248124559969572, "grad_norm": 0.35737377405166626, "learning_rate": 5.589441557049611e-06, "loss": 0.6734366416931152, "step": 14285, "token_acc": 0.7890579529392201 }, { "epoch": 0.9251361565415834, "grad_norm": 0.31299805641174316, "learning_rate": 5.5869169730613035e-06, "loss": 0.6773434638977051, "step": 14290, "token_acc": 0.7886212951073142 }, { "epoch": 0.9254598570862096, "grad_norm": 0.34826239943504333, "learning_rate": 5.5843922373441605e-06, "loss": 0.6743147373199463, "step": 14295, "token_acc": 0.7888421272303572 }, { "epoch": 0.9257835576308358, "grad_norm": 0.3144206702709198, "learning_rate": 5.5818673505508715e-06, "loss": 0.6713189125061035, "step": 14300, "token_acc": 0.787724361537399 }, { "epoch": 0.9261072581754619, "grad_norm": 0.339722216129303, "learning_rate": 5.579342313334164e-06, "loss": 0.6729937076568604, "step": 14305, "token_acc": 0.7893933638550684 }, { "epoch": 0.9264309587200881, "grad_norm": 0.3161884844303131, "learning_rate": 5.576817126346809e-06, "loss": 0.6764582633972168, "step": 14310, "token_acc": 0.7889897178600107 }, { "epoch": 0.9267546592647142, "grad_norm": 0.29172956943511963, "learning_rate": 5.574291790241615e-06, "loss": 0.6755400657653808, "step": 14315, "token_acc": 0.7902914040133646 }, { "epoch": 0.9270783598093404, "grad_norm": 0.35448509454727173, "learning_rate": 5.571766305671423e-06, "loss": 0.6608341693878174, "step": 14320, "token_acc": 0.7941889446549899 }, { "epoch": 0.9274020603539666, "grad_norm": 0.3053842782974243, "learning_rate": 5.5692406732891224e-06, "loss": 0.6724028587341309, "step": 14325, "token_acc": 0.7889039334755731 }, { "epoch": 0.9277257608985927, "grad_norm": 0.3415672779083252, "learning_rate": 5.566714893747632e-06, "loss": 0.6757538795471192, "step": 14330, "token_acc": 0.7879166341425338 }, { "epoch": 0.9280494614432189, "grad_norm": 0.4096389412879944, "learning_rate": 5.564188967699914e-06, "loss": 0.6795554161071777, "step": 14335, "token_acc": 0.7875668040366385 }, { "epoch": 0.928373161987845, "grad_norm": 0.366100013256073, "learning_rate": 5.5616628957989674e-06, "loss": 0.670654296875, "step": 14340, "token_acc": 0.7909373713898371 }, { "epoch": 0.9286968625324712, "grad_norm": 0.31533151865005493, "learning_rate": 5.5591366786978265e-06, "loss": 0.6755365371704102, "step": 14345, "token_acc": 0.7878719290190321 }, { "epoch": 0.9290205630770973, "grad_norm": 0.2650679051876068, "learning_rate": 5.556610317049565e-06, "loss": 0.6601793766021729, "step": 14350, "token_acc": 0.7916334168019592 }, { "epoch": 0.9293442636217235, "grad_norm": 0.3728824555873871, "learning_rate": 5.554083811507296e-06, "loss": 0.6816617488861084, "step": 14355, "token_acc": 0.7882404445192793 }, { "epoch": 0.9296679641663497, "grad_norm": 0.3336527347564697, "learning_rate": 5.551557162724165e-06, "loss": 0.6430809497833252, "step": 14360, "token_acc": 0.7960113844001114 }, { "epoch": 0.9299916647109758, "grad_norm": 0.26824134588241577, "learning_rate": 5.549030371353359e-06, "loss": 0.6790889739990235, "step": 14365, "token_acc": 0.7893004815705299 }, { "epoch": 0.930315365255602, "grad_norm": 0.3951908349990845, "learning_rate": 5.546503438048101e-06, "loss": 0.6659536361694336, "step": 14370, "token_acc": 0.791575249438437 }, { "epoch": 0.9306390658002283, "grad_norm": 0.39815664291381836, "learning_rate": 5.543976363461646e-06, "loss": 0.6785416603088379, "step": 14375, "token_acc": 0.7880189138446562 }, { "epoch": 0.9309627663448544, "grad_norm": 0.2606036961078644, "learning_rate": 5.541449148247293e-06, "loss": 0.6781274318695069, "step": 14380, "token_acc": 0.7899403470715836 }, { "epoch": 0.9312864668894806, "grad_norm": 0.2953452169895172, "learning_rate": 5.538921793058371e-06, "loss": 0.6788852691650391, "step": 14385, "token_acc": 0.7891888257639426 }, { "epoch": 0.9316101674341067, "grad_norm": 0.2870110869407654, "learning_rate": 5.53639429854825e-06, "loss": 0.6766571998596191, "step": 14390, "token_acc": 0.7890055287283925 }, { "epoch": 0.9319338679787329, "grad_norm": 0.2853415310382843, "learning_rate": 5.533866665370333e-06, "loss": 0.6932077884674073, "step": 14395, "token_acc": 0.7847142258976237 }, { "epoch": 0.9322575685233591, "grad_norm": 0.4257553219795227, "learning_rate": 5.531338894178059e-06, "loss": 0.6668412208557128, "step": 14400, "token_acc": 0.7901157917610903 }, { "epoch": 0.9325812690679852, "grad_norm": 0.28314462304115295, "learning_rate": 5.528810985624904e-06, "loss": 0.7064944744110108, "step": 14405, "token_acc": 0.7816596170315697 }, { "epoch": 0.9329049696126114, "grad_norm": 0.3708263039588928, "learning_rate": 5.526282940364378e-06, "loss": 0.6680779457092285, "step": 14410, "token_acc": 0.7906922476719681 }, { "epoch": 0.9332286701572375, "grad_norm": 0.28671136498451233, "learning_rate": 5.5237547590500294e-06, "loss": 0.6486115455627441, "step": 14415, "token_acc": 0.7960705123320378 }, { "epoch": 0.9335523707018637, "grad_norm": 0.3698433041572571, "learning_rate": 5.521226442335439e-06, "loss": 0.6835256099700928, "step": 14420, "token_acc": 0.7869456639948443 }, { "epoch": 0.9338760712464899, "grad_norm": 0.36936208605766296, "learning_rate": 5.51869799087422e-06, "loss": 0.679211950302124, "step": 14425, "token_acc": 0.7882666066380206 }, { "epoch": 0.934199771791116, "grad_norm": 0.3169941008090973, "learning_rate": 5.516169405320027e-06, "loss": 0.6680860996246338, "step": 14430, "token_acc": 0.7907592102584978 }, { "epoch": 0.9345234723357422, "grad_norm": 0.2507658898830414, "learning_rate": 5.513640686326546e-06, "loss": 0.6676731586456299, "step": 14435, "token_acc": 0.7910163908713043 }, { "epoch": 0.9348471728803683, "grad_norm": 0.2962701618671417, "learning_rate": 5.511111834547496e-06, "loss": 0.6636064529418946, "step": 14440, "token_acc": 0.7918721002471812 }, { "epoch": 0.9351708734249945, "grad_norm": 0.28417280316352844, "learning_rate": 5.508582850636631e-06, "loss": 0.651491117477417, "step": 14445, "token_acc": 0.794849868952524 }, { "epoch": 0.9354945739696207, "grad_norm": 0.32729190587997437, "learning_rate": 5.50605373524774e-06, "loss": 0.6651254653930664, "step": 14450, "token_acc": 0.7910073531322265 }, { "epoch": 0.9358182745142468, "grad_norm": 0.32785049080848694, "learning_rate": 5.50352448903465e-06, "loss": 0.6779924392700195, "step": 14455, "token_acc": 0.7886088983505897 }, { "epoch": 0.9361419750588731, "grad_norm": 0.34257781505584717, "learning_rate": 5.500995112651212e-06, "loss": 0.6606395721435547, "step": 14460, "token_acc": 0.7922147683052021 }, { "epoch": 0.9364656756034992, "grad_norm": 0.24798762798309326, "learning_rate": 5.49846560675132e-06, "loss": 0.6559141159057618, "step": 14465, "token_acc": 0.7936542655909208 }, { "epoch": 0.9367893761481254, "grad_norm": 0.30016064643859863, "learning_rate": 5.495935971988896e-06, "loss": 0.6513136863708496, "step": 14470, "token_acc": 0.79528081369638 }, { "epoch": 0.9371130766927516, "grad_norm": 0.25372347235679626, "learning_rate": 5.4934062090178976e-06, "loss": 0.6736308097839355, "step": 14475, "token_acc": 0.7903480053352734 }, { "epoch": 0.9374367772373777, "grad_norm": 0.290272980928421, "learning_rate": 5.490876318492315e-06, "loss": 0.7002813816070557, "step": 14480, "token_acc": 0.7834080054509575 }, { "epoch": 0.9377604777820039, "grad_norm": 0.4082582890987396, "learning_rate": 5.488346301066172e-06, "loss": 0.6769568443298339, "step": 14485, "token_acc": 0.7898487188211585 }, { "epoch": 0.93808417832663, "grad_norm": 0.29019391536712646, "learning_rate": 5.485816157393524e-06, "loss": 0.6752697944641113, "step": 14490, "token_acc": 0.7899959239822694 }, { "epoch": 0.9384078788712562, "grad_norm": 0.302147775888443, "learning_rate": 5.48328588812846e-06, "loss": 0.6527182579040527, "step": 14495, "token_acc": 0.793544450546098 }, { "epoch": 0.9387315794158824, "grad_norm": 0.32866430282592773, "learning_rate": 5.480755493925103e-06, "loss": 0.6729860305786133, "step": 14500, "token_acc": 0.7877701533177803 }, { "epoch": 0.9390552799605085, "grad_norm": 0.19774921238422394, "learning_rate": 5.4782249754376035e-06, "loss": 0.6560230255126953, "step": 14505, "token_acc": 0.7923683244980326 }, { "epoch": 0.9393789805051347, "grad_norm": 0.41373559832572937, "learning_rate": 5.4756943333201476e-06, "loss": 0.6840857982635498, "step": 14510, "token_acc": 0.78659007650709 }, { "epoch": 0.9397026810497608, "grad_norm": 0.37679994106292725, "learning_rate": 5.4731635682269535e-06, "loss": 0.659324836730957, "step": 14515, "token_acc": 0.7927338314867303 }, { "epoch": 0.940026381594387, "grad_norm": 0.23604723811149597, "learning_rate": 5.470632680812271e-06, "loss": 0.6723376274108886, "step": 14520, "token_acc": 0.7897529408538759 }, { "epoch": 0.9403500821390132, "grad_norm": 0.345459520816803, "learning_rate": 5.468101671730381e-06, "loss": 0.6538982391357422, "step": 14525, "token_acc": 0.7938789659612401 }, { "epoch": 0.9406737826836393, "grad_norm": 0.2618601322174072, "learning_rate": 5.465570541635595e-06, "loss": 0.689029312133789, "step": 14530, "token_acc": 0.7855434971134072 }, { "epoch": 0.9409974832282655, "grad_norm": 0.29249700903892517, "learning_rate": 5.463039291182257e-06, "loss": 0.685941219329834, "step": 14535, "token_acc": 0.7866994532516416 }, { "epoch": 0.9413211837728916, "grad_norm": 0.3659474849700928, "learning_rate": 5.4605079210247426e-06, "loss": 0.6844266891479492, "step": 14540, "token_acc": 0.7854428453973988 }, { "epoch": 0.9416448843175179, "grad_norm": 0.311128169298172, "learning_rate": 5.457976431817458e-06, "loss": 0.6907683372497558, "step": 14545, "token_acc": 0.7849117591697119 }, { "epoch": 0.9419685848621441, "grad_norm": 0.41420507431030273, "learning_rate": 5.455444824214836e-06, "loss": 0.6727490425109863, "step": 14550, "token_acc": 0.7891446623035603 }, { "epoch": 0.9422922854067702, "grad_norm": 0.2876022160053253, "learning_rate": 5.4529130988713485e-06, "loss": 0.6541815757751465, "step": 14555, "token_acc": 0.7946456081126337 }, { "epoch": 0.9426159859513964, "grad_norm": 0.30496466159820557, "learning_rate": 5.4503812564414915e-06, "loss": 0.7002952575683594, "step": 14560, "token_acc": 0.7848388939127124 }, { "epoch": 0.9429396864960226, "grad_norm": 0.32218801975250244, "learning_rate": 5.447849297579792e-06, "loss": 0.6637728691101075, "step": 14565, "token_acc": 0.7913430147472701 }, { "epoch": 0.9432633870406487, "grad_norm": 0.30706697702407837, "learning_rate": 5.445317222940808e-06, "loss": 0.6613682746887207, "step": 14570, "token_acc": 0.79214477655659 }, { "epoch": 0.9435870875852749, "grad_norm": 0.36007925868034363, "learning_rate": 5.442785033179128e-06, "loss": 0.6902333259582519, "step": 14575, "token_acc": 0.7852350271368267 }, { "epoch": 0.943910788129901, "grad_norm": 0.30701735615730286, "learning_rate": 5.440252728949369e-06, "loss": 0.6603033065795898, "step": 14580, "token_acc": 0.792698988107657 }, { "epoch": 0.9442344886745272, "grad_norm": 0.27951231598854065, "learning_rate": 5.437720310906179e-06, "loss": 0.6704083442687988, "step": 14585, "token_acc": 0.7901647277566588 }, { "epoch": 0.9445581892191534, "grad_norm": 0.22474519908428192, "learning_rate": 5.435187779704235e-06, "loss": 0.6729208946228027, "step": 14590, "token_acc": 0.7891342082423796 }, { "epoch": 0.9448818897637795, "grad_norm": 0.389051228761673, "learning_rate": 5.43265513599824e-06, "loss": 0.6457104206085205, "step": 14595, "token_acc": 0.7960511192430276 }, { "epoch": 0.9452055903084057, "grad_norm": 0.323453426361084, "learning_rate": 5.430122380442934e-06, "loss": 0.6756159782409668, "step": 14600, "token_acc": 0.7882823171593333 }, { "epoch": 0.9455292908530318, "grad_norm": 0.3683980703353882, "learning_rate": 5.427589513693075e-06, "loss": 0.690049695968628, "step": 14605, "token_acc": 0.7850524119155052 }, { "epoch": 0.945852991397658, "grad_norm": 0.34512409567832947, "learning_rate": 5.425056536403463e-06, "loss": 0.6709839820861816, "step": 14610, "token_acc": 0.7893379366368806 }, { "epoch": 0.9461766919422842, "grad_norm": 0.32720810174942017, "learning_rate": 5.422523449228912e-06, "loss": 0.6569516658782959, "step": 14615, "token_acc": 0.7937452975236351 }, { "epoch": 0.9465003924869103, "grad_norm": 0.3702901601791382, "learning_rate": 5.419990252824275e-06, "loss": 0.6615277290344238, "step": 14620, "token_acc": 0.7903082547835607 }, { "epoch": 0.9468240930315365, "grad_norm": 0.3488028645515442, "learning_rate": 5.417456947844431e-06, "loss": 0.6464654445648194, "step": 14625, "token_acc": 0.7971066250235379 }, { "epoch": 0.9471477935761627, "grad_norm": 0.29639530181884766, "learning_rate": 5.414923534944283e-06, "loss": 0.6597803115844727, "step": 14630, "token_acc": 0.7935002554931017 }, { "epoch": 0.9474714941207889, "grad_norm": 0.4306718707084656, "learning_rate": 5.412390014778768e-06, "loss": 0.6652422428131104, "step": 14635, "token_acc": 0.7912837707315727 }, { "epoch": 0.9477951946654151, "grad_norm": 0.25578999519348145, "learning_rate": 5.4098563880028455e-06, "loss": 0.6708498954772949, "step": 14640, "token_acc": 0.7910682454368616 }, { "epoch": 0.9481188952100412, "grad_norm": 0.3368075489997864, "learning_rate": 5.407322655271504e-06, "loss": 0.6616267204284668, "step": 14645, "token_acc": 0.7922746322128721 }, { "epoch": 0.9484425957546674, "grad_norm": 0.29427391290664673, "learning_rate": 5.404788817239762e-06, "loss": 0.6786455154418946, "step": 14650, "token_acc": 0.7877868769588515 }, { "epoch": 0.9487662962992935, "grad_norm": 0.33547428250312805, "learning_rate": 5.4022548745626615e-06, "loss": 0.6696356773376465, "step": 14655, "token_acc": 0.791098353624336 }, { "epoch": 0.9490899968439197, "grad_norm": 0.33915257453918457, "learning_rate": 5.399720827895275e-06, "loss": 0.6720324993133545, "step": 14660, "token_acc": 0.789560994070897 }, { "epoch": 0.9494136973885459, "grad_norm": 0.2899579703807831, "learning_rate": 5.3971866778927e-06, "loss": 0.656298828125, "step": 14665, "token_acc": 0.793477662473506 }, { "epoch": 0.949737397933172, "grad_norm": 0.2924170196056366, "learning_rate": 5.39465242521006e-06, "loss": 0.6707776069641114, "step": 14670, "token_acc": 0.7888525334291604 }, { "epoch": 0.9500610984777982, "grad_norm": 0.24576221406459808, "learning_rate": 5.392118070502506e-06, "loss": 0.6769818305969239, "step": 14675, "token_acc": 0.7888813550729689 }, { "epoch": 0.9503847990224243, "grad_norm": 0.2934085726737976, "learning_rate": 5.389583614425215e-06, "loss": 0.6522407531738281, "step": 14680, "token_acc": 0.7958316858203339 }, { "epoch": 0.9507084995670505, "grad_norm": 0.3127482235431671, "learning_rate": 5.3870490576333916e-06, "loss": 0.6678886413574219, "step": 14685, "token_acc": 0.7902414693141288 }, { "epoch": 0.9510322001116767, "grad_norm": 0.3367077708244324, "learning_rate": 5.384514400782266e-06, "loss": 0.6948380470275879, "step": 14690, "token_acc": 0.78418911335578 }, { "epoch": 0.9513559006563028, "grad_norm": 0.4087182283401489, "learning_rate": 5.38197964452709e-06, "loss": 0.6894660949707031, "step": 14695, "token_acc": 0.786704160163608 }, { "epoch": 0.951679601200929, "grad_norm": 0.319281667470932, "learning_rate": 5.379444789523149e-06, "loss": 0.6746093273162842, "step": 14700, "token_acc": 0.790841840700627 }, { "epoch": 0.9520033017455551, "grad_norm": 0.262763649225235, "learning_rate": 5.376909836425747e-06, "loss": 0.6550492286682129, "step": 14705, "token_acc": 0.7943618765536574 }, { "epoch": 0.9523270022901813, "grad_norm": 0.33966487646102905, "learning_rate": 5.374374785890218e-06, "loss": 0.6390082836151123, "step": 14710, "token_acc": 0.797575175256168 }, { "epoch": 0.9526507028348076, "grad_norm": 0.3605267405509949, "learning_rate": 5.371839638571918e-06, "loss": 0.667157506942749, "step": 14715, "token_acc": 0.7916359292070062 }, { "epoch": 0.9529744033794337, "grad_norm": 0.312874972820282, "learning_rate": 5.3693043951262295e-06, "loss": 0.659355354309082, "step": 14720, "token_acc": 0.7919267285346421 }, { "epoch": 0.9532981039240599, "grad_norm": 0.3519321382045746, "learning_rate": 5.3667690562085586e-06, "loss": 0.6466772079467773, "step": 14725, "token_acc": 0.7946946490256143 }, { "epoch": 0.953621804468686, "grad_norm": 0.2680005431175232, "learning_rate": 5.364233622474337e-06, "loss": 0.6802158355712891, "step": 14730, "token_acc": 0.7877959927140255 }, { "epoch": 0.9539455050133122, "grad_norm": 0.35894545912742615, "learning_rate": 5.361698094579024e-06, "loss": 0.6555273056030273, "step": 14735, "token_acc": 0.7922340650381956 }, { "epoch": 0.9542692055579384, "grad_norm": 0.37294480204582214, "learning_rate": 5.359162473178096e-06, "loss": 0.7029618263244629, "step": 14740, "token_acc": 0.7823498456134567 }, { "epoch": 0.9545929061025645, "grad_norm": 0.34459489583969116, "learning_rate": 5.356626758927063e-06, "loss": 0.6682205200195312, "step": 14745, "token_acc": 0.7905284378201527 }, { "epoch": 0.9549166066471907, "grad_norm": 0.3463466167449951, "learning_rate": 5.354090952481449e-06, "loss": 0.6596237659454346, "step": 14750, "token_acc": 0.7931895880580848 }, { "epoch": 0.9552403071918169, "grad_norm": 0.3422788381576538, "learning_rate": 5.351555054496807e-06, "loss": 0.6681172847747803, "step": 14755, "token_acc": 0.7909903900010699 }, { "epoch": 0.955564007736443, "grad_norm": 0.322788268327713, "learning_rate": 5.349019065628718e-06, "loss": 0.6570014953613281, "step": 14760, "token_acc": 0.7930715552763993 }, { "epoch": 0.9558877082810692, "grad_norm": 0.3288570046424866, "learning_rate": 5.346482986532775e-06, "loss": 0.6454138278961181, "step": 14765, "token_acc": 0.7954618499710742 }, { "epoch": 0.9562114088256953, "grad_norm": 0.31927138566970825, "learning_rate": 5.343946817864606e-06, "loss": 0.6701896667480469, "step": 14770, "token_acc": 0.7898967023959209 }, { "epoch": 0.9565351093703215, "grad_norm": 0.30849748849868774, "learning_rate": 5.341410560279856e-06, "loss": 0.6649511337280274, "step": 14775, "token_acc": 0.7912693485494255 }, { "epoch": 0.9568588099149477, "grad_norm": 0.2703787088394165, "learning_rate": 5.338874214434193e-06, "loss": 0.674449348449707, "step": 14780, "token_acc": 0.7891220410841366 }, { "epoch": 0.9571825104595738, "grad_norm": 0.30061104893684387, "learning_rate": 5.336337780983311e-06, "loss": 0.6498327255249023, "step": 14785, "token_acc": 0.7943468296409473 }, { "epoch": 0.9575062110042, "grad_norm": 0.24680264294147491, "learning_rate": 5.333801260582923e-06, "loss": 0.6633977890014648, "step": 14790, "token_acc": 0.7912345331649512 }, { "epoch": 0.9578299115488261, "grad_norm": 0.30654340982437134, "learning_rate": 5.331264653888768e-06, "loss": 0.630457592010498, "step": 14795, "token_acc": 0.8002346237640355 }, { "epoch": 0.9581536120934524, "grad_norm": 0.3529623746871948, "learning_rate": 5.328727961556604e-06, "loss": 0.6598852157592774, "step": 14800, "token_acc": 0.790979657874166 }, { "epoch": 0.9584773126380786, "grad_norm": 0.31959769129753113, "learning_rate": 5.326191184242214e-06, "loss": 0.6637480735778809, "step": 14805, "token_acc": 0.7906682196297075 }, { "epoch": 0.9588010131827047, "grad_norm": 0.24111516773700714, "learning_rate": 5.323654322601401e-06, "loss": 0.6571897506713867, "step": 14810, "token_acc": 0.7930816310719727 }, { "epoch": 0.9591247137273309, "grad_norm": 0.31731393933296204, "learning_rate": 5.321117377289987e-06, "loss": 0.656403923034668, "step": 14815, "token_acc": 0.7932277797273772 }, { "epoch": 0.959448414271957, "grad_norm": 0.2954949736595154, "learning_rate": 5.318580348963826e-06, "loss": 0.663869047164917, "step": 14820, "token_acc": 0.7926585698495905 }, { "epoch": 0.9597721148165832, "grad_norm": 0.21960894763469696, "learning_rate": 5.3160432382787805e-06, "loss": 0.6507866859436036, "step": 14825, "token_acc": 0.7958879729078348 }, { "epoch": 0.9600958153612094, "grad_norm": 0.3701690137386322, "learning_rate": 5.313506045890743e-06, "loss": 0.644749927520752, "step": 14830, "token_acc": 0.7954366545155078 }, { "epoch": 0.9604195159058355, "grad_norm": 0.24017222225666046, "learning_rate": 5.310968772455624e-06, "loss": 0.6412138938903809, "step": 14835, "token_acc": 0.7957831123048514 }, { "epoch": 0.9607432164504617, "grad_norm": 0.41699036955833435, "learning_rate": 5.308431418629355e-06, "loss": 0.6456043720245361, "step": 14840, "token_acc": 0.7957238438162364 }, { "epoch": 0.9610669169950878, "grad_norm": 0.30407604575157166, "learning_rate": 5.3058939850678905e-06, "loss": 0.6407659530639649, "step": 14845, "token_acc": 0.7982013337230001 }, { "epoch": 0.961390617539714, "grad_norm": 0.3389900028705597, "learning_rate": 5.3033564724272015e-06, "loss": 0.6780079364776611, "step": 14850, "token_acc": 0.7887166730450312 }, { "epoch": 0.9617143180843402, "grad_norm": 0.33816108107566833, "learning_rate": 5.300818881363281e-06, "loss": 0.6737504482269288, "step": 14855, "token_acc": 0.7894989605536696 }, { "epoch": 0.9620380186289663, "grad_norm": 0.2806033790111542, "learning_rate": 5.298281212532146e-06, "loss": 0.6696857929229736, "step": 14860, "token_acc": 0.7899074609600926 }, { "epoch": 0.9623617191735925, "grad_norm": 0.34419625997543335, "learning_rate": 5.295743466589828e-06, "loss": 0.6788959503173828, "step": 14865, "token_acc": 0.7879321611949588 }, { "epoch": 0.9626854197182186, "grad_norm": 0.33342859148979187, "learning_rate": 5.293205644192383e-06, "loss": 0.7037768363952637, "step": 14870, "token_acc": 0.7821404618185303 }, { "epoch": 0.9630091202628448, "grad_norm": 0.268681138753891, "learning_rate": 5.290667745995883e-06, "loss": 0.6721550464630127, "step": 14875, "token_acc": 0.7895379470062444 }, { "epoch": 0.963332820807471, "grad_norm": 0.26866021752357483, "learning_rate": 5.288129772656423e-06, "loss": 0.6612221717834472, "step": 14880, "token_acc": 0.7911369694484314 }, { "epoch": 0.9636565213520972, "grad_norm": 0.3427763283252716, "learning_rate": 5.285591724830115e-06, "loss": 0.6963351726531982, "step": 14885, "token_acc": 0.784306513204973 }, { "epoch": 0.9639802218967234, "grad_norm": 0.2579770088195801, "learning_rate": 5.283053603173091e-06, "loss": 0.656895923614502, "step": 14890, "token_acc": 0.7928675984818063 }, { "epoch": 0.9643039224413495, "grad_norm": 0.29951903223991394, "learning_rate": 5.280515408341501e-06, "loss": 0.649224853515625, "step": 14895, "token_acc": 0.794080228998529 }, { "epoch": 0.9646276229859757, "grad_norm": 0.3413303792476654, "learning_rate": 5.277977140991517e-06, "loss": 0.6848490238189697, "step": 14900, "token_acc": 0.7871686766676471 }, { "epoch": 0.9649513235306019, "grad_norm": 0.3605070412158966, "learning_rate": 5.275438801779328e-06, "loss": 0.6319713592529297, "step": 14905, "token_acc": 0.7991785531512853 }, { "epoch": 0.965275024075228, "grad_norm": 0.40737608075141907, "learning_rate": 5.2729003913611395e-06, "loss": 0.6672478675842285, "step": 14910, "token_acc": 0.7911346406448989 }, { "epoch": 0.9655987246198542, "grad_norm": 0.2970772087574005, "learning_rate": 5.270361910393179e-06, "loss": 0.6576307773590088, "step": 14915, "token_acc": 0.7928975968161641 }, { "epoch": 0.9659224251644803, "grad_norm": 0.3080081641674042, "learning_rate": 5.26782335953169e-06, "loss": 0.689776086807251, "step": 14920, "token_acc": 0.7859466743671191 }, { "epoch": 0.9662461257091065, "grad_norm": 0.347887247800827, "learning_rate": 5.265284739432933e-06, "loss": 0.663941478729248, "step": 14925, "token_acc": 0.7912369456524955 }, { "epoch": 0.9665698262537327, "grad_norm": 0.281374454498291, "learning_rate": 5.2627460507531914e-06, "loss": 0.6502024173736572, "step": 14930, "token_acc": 0.7949683116496545 }, { "epoch": 0.9668935267983588, "grad_norm": 0.32095807790756226, "learning_rate": 5.260207294148761e-06, "loss": 0.6566662788391113, "step": 14935, "token_acc": 0.7932378689837115 }, { "epoch": 0.967217227342985, "grad_norm": 0.3423624634742737, "learning_rate": 5.257668470275955e-06, "loss": 0.6850198745727539, "step": 14940, "token_acc": 0.7848681971676135 }, { "epoch": 0.9675409278876111, "grad_norm": 0.26754331588745117, "learning_rate": 5.25512957979111e-06, "loss": 0.6924562454223633, "step": 14945, "token_acc": 0.7835977134456484 }, { "epoch": 0.9678646284322373, "grad_norm": 0.29116472601890564, "learning_rate": 5.252590623350573e-06, "loss": 0.6710959434509277, "step": 14950, "token_acc": 0.7893767144787303 }, { "epoch": 0.9681883289768635, "grad_norm": 0.31184858083724976, "learning_rate": 5.2500516016107125e-06, "loss": 0.6506438732147217, "step": 14955, "token_acc": 0.7967027305512623 }, { "epoch": 0.9685120295214896, "grad_norm": 0.3329819440841675, "learning_rate": 5.247512515227913e-06, "loss": 0.6625034809112549, "step": 14960, "token_acc": 0.7905525720746184 }, { "epoch": 0.9688357300661158, "grad_norm": 0.3125683069229126, "learning_rate": 5.244973364858572e-06, "loss": 0.6775298118591309, "step": 14965, "token_acc": 0.790307921866522 }, { "epoch": 0.9691594306107421, "grad_norm": 0.34277480840682983, "learning_rate": 5.24243415115911e-06, "loss": 0.6661547183990478, "step": 14970, "token_acc": 0.792191766966724 }, { "epoch": 0.9694831311553682, "grad_norm": 0.38562318682670593, "learning_rate": 5.239894874785958e-06, "loss": 0.6694736480712891, "step": 14975, "token_acc": 0.7912490375280372 }, { "epoch": 0.9698068316999944, "grad_norm": 0.35375937819480896, "learning_rate": 5.2373555363955675e-06, "loss": 0.6861386775970459, "step": 14980, "token_acc": 0.78471403399531 }, { "epoch": 0.9701305322446205, "grad_norm": 0.31698498129844666, "learning_rate": 5.234816136644403e-06, "loss": 0.6408156871795654, "step": 14985, "token_acc": 0.7989884435994177 }, { "epoch": 0.9704542327892467, "grad_norm": 0.38014456629753113, "learning_rate": 5.232276676188946e-06, "loss": 0.6599198341369629, "step": 14990, "token_acc": 0.7938041117022951 }, { "epoch": 0.9707779333338729, "grad_norm": 0.3212147057056427, "learning_rate": 5.2297371556856955e-06, "loss": 0.6905433654785156, "step": 14995, "token_acc": 0.785117051555933 }, { "epoch": 0.971101633878499, "grad_norm": 0.34621959924697876, "learning_rate": 5.227197575791161e-06, "loss": 0.6851595878601074, "step": 15000, "token_acc": 0.7868336025848142 }, { "epoch": 0.9714253344231252, "grad_norm": 0.2934918701648712, "learning_rate": 5.224657937161874e-06, "loss": 0.6612208366394043, "step": 15005, "token_acc": 0.7926833236792951 }, { "epoch": 0.9717490349677513, "grad_norm": 0.357023149728775, "learning_rate": 5.222118240454376e-06, "loss": 0.6794561862945556, "step": 15010, "token_acc": 0.7876762555259905 }, { "epoch": 0.9720727355123775, "grad_norm": 0.2274692803621292, "learning_rate": 5.219578486325226e-06, "loss": 0.6485671997070312, "step": 15015, "token_acc": 0.7947220570184873 }, { "epoch": 0.9723964360570037, "grad_norm": 0.38017526268959045, "learning_rate": 5.2170386754309975e-06, "loss": 0.6478226661682129, "step": 15020, "token_acc": 0.7963084799693769 }, { "epoch": 0.9727201366016298, "grad_norm": 0.3167446553707123, "learning_rate": 5.2144988084282765e-06, "loss": 0.6668299674987793, "step": 15025, "token_acc": 0.7907914681680381 }, { "epoch": 0.973043837146256, "grad_norm": 0.3421189785003662, "learning_rate": 5.211958885973668e-06, "loss": 0.6441211700439453, "step": 15030, "token_acc": 0.7975347686281775 }, { "epoch": 0.9733675376908821, "grad_norm": 0.3143780529499054, "learning_rate": 5.209418908723787e-06, "loss": 0.662264633178711, "step": 15035, "token_acc": 0.7908925292425141 }, { "epoch": 0.9736912382355083, "grad_norm": 0.3752315044403076, "learning_rate": 5.206878877335264e-06, "loss": 0.6627510547637939, "step": 15040, "token_acc": 0.7916913353924289 }, { "epoch": 0.9740149387801345, "grad_norm": 0.2514249384403229, "learning_rate": 5.204338792464744e-06, "loss": 0.6723125457763672, "step": 15045, "token_acc": 0.7887810690172321 }, { "epoch": 0.9743386393247606, "grad_norm": 0.2877331078052521, "learning_rate": 5.2017986547688885e-06, "loss": 0.6556427955627442, "step": 15050, "token_acc": 0.7936647101735411 }, { "epoch": 0.9746623398693869, "grad_norm": 0.34707924723625183, "learning_rate": 5.199258464904366e-06, "loss": 0.6442834854125976, "step": 15055, "token_acc": 0.7961878322104479 }, { "epoch": 0.974986040414013, "grad_norm": 0.3749079704284668, "learning_rate": 5.196718223527863e-06, "loss": 0.6849906921386719, "step": 15060, "token_acc": 0.7873751686909581 }, { "epoch": 0.9753097409586392, "grad_norm": 0.2619023025035858, "learning_rate": 5.19417793129608e-06, "loss": 0.6926636219024658, "step": 15065, "token_acc": 0.7854492473396469 }, { "epoch": 0.9756334415032654, "grad_norm": 0.31140199303627014, "learning_rate": 5.19163758886573e-06, "loss": 0.6589768409729004, "step": 15070, "token_acc": 0.7918695519496889 }, { "epoch": 0.9759571420478915, "grad_norm": 0.3640776574611664, "learning_rate": 5.1890971968935355e-06, "loss": 0.6580170631408692, "step": 15075, "token_acc": 0.7937423237533775 }, { "epoch": 0.9762808425925177, "grad_norm": 0.3271177411079407, "learning_rate": 5.186556756036238e-06, "loss": 0.6501950263977051, "step": 15080, "token_acc": 0.7958963560257826 }, { "epoch": 0.9766045431371438, "grad_norm": 0.4037432074546814, "learning_rate": 5.184016266950584e-06, "loss": 0.6399930000305176, "step": 15085, "token_acc": 0.7980742607154724 }, { "epoch": 0.97692824368177, "grad_norm": 0.29226580262184143, "learning_rate": 5.1814757302933395e-06, "loss": 0.6648877143859864, "step": 15090, "token_acc": 0.7905618312541082 }, { "epoch": 0.9772519442263962, "grad_norm": 0.2985530495643616, "learning_rate": 5.1789351467212815e-06, "loss": 0.6617331981658936, "step": 15095, "token_acc": 0.7917405465223023 }, { "epoch": 0.9775756447710223, "grad_norm": 0.2753552198410034, "learning_rate": 5.176394516891192e-06, "loss": 0.6501534461975098, "step": 15100, "token_acc": 0.7954315623027279 }, { "epoch": 0.9778993453156485, "grad_norm": 0.2984485626220703, "learning_rate": 5.173853841459877e-06, "loss": 0.6595430850982666, "step": 15105, "token_acc": 0.7919995950626568 }, { "epoch": 0.9782230458602746, "grad_norm": 0.3103773295879364, "learning_rate": 5.171313121084144e-06, "loss": 0.6798683166503906, "step": 15110, "token_acc": 0.7872999483737739 }, { "epoch": 0.9785467464049008, "grad_norm": 0.3201811611652374, "learning_rate": 5.168772356420817e-06, "loss": 0.6734682559967041, "step": 15115, "token_acc": 0.7889912859026543 }, { "epoch": 0.978870446949527, "grad_norm": 0.268969863653183, "learning_rate": 5.16623154812673e-06, "loss": 0.646311092376709, "step": 15120, "token_acc": 0.7970605325653075 }, { "epoch": 0.9791941474941531, "grad_norm": 0.31001099944114685, "learning_rate": 5.16369069685873e-06, "loss": 0.6589035987854004, "step": 15125, "token_acc": 0.7943623518451426 }, { "epoch": 0.9795178480387793, "grad_norm": 0.3085540533065796, "learning_rate": 5.161149803273673e-06, "loss": 0.6592518806457519, "step": 15130, "token_acc": 0.7934566199555861 }, { "epoch": 0.9798415485834054, "grad_norm": 0.4240838885307312, "learning_rate": 5.158608868028425e-06, "loss": 0.6667633056640625, "step": 15135, "token_acc": 0.7905717689472141 }, { "epoch": 0.9801652491280317, "grad_norm": 0.28253406286239624, "learning_rate": 5.156067891779868e-06, "loss": 0.6472945213317871, "step": 15140, "token_acc": 0.796246930684496 }, { "epoch": 0.9804889496726579, "grad_norm": 0.3053953945636749, "learning_rate": 5.153526875184888e-06, "loss": 0.6618912696838379, "step": 15145, "token_acc": 0.7932521148381618 }, { "epoch": 0.980812650217284, "grad_norm": 0.292632520198822, "learning_rate": 5.150985818900386e-06, "loss": 0.6706259250640869, "step": 15150, "token_acc": 0.7901021765773796 }, { "epoch": 0.9811363507619102, "grad_norm": 0.33377358317375183, "learning_rate": 5.148444723583272e-06, "loss": 0.6516970634460449, "step": 15155, "token_acc": 0.7943214802936223 }, { "epoch": 0.9814600513065364, "grad_norm": 0.3250926733016968, "learning_rate": 5.145903589890465e-06, "loss": 0.6895273685455322, "step": 15160, "token_acc": 0.7851940530092762 }, { "epoch": 0.9817837518511625, "grad_norm": 0.41539132595062256, "learning_rate": 5.143362418478896e-06, "loss": 0.6415585517883301, "step": 15165, "token_acc": 0.7977103846324983 }, { "epoch": 0.9821074523957887, "grad_norm": 0.40713733434677124, "learning_rate": 5.140821210005504e-06, "loss": 0.6497566223144531, "step": 15170, "token_acc": 0.7953121461462973 }, { "epoch": 0.9824311529404148, "grad_norm": 0.30023956298828125, "learning_rate": 5.138279965127237e-06, "loss": 0.6511775493621826, "step": 15175, "token_acc": 0.7961349935963201 }, { "epoch": 0.982754853485041, "grad_norm": 0.24076500535011292, "learning_rate": 5.135738684501055e-06, "loss": 0.6552127838134766, "step": 15180, "token_acc": 0.7941351809655026 }, { "epoch": 0.9830785540296672, "grad_norm": 0.3451707065105438, "learning_rate": 5.133197368783926e-06, "loss": 0.6358956336975098, "step": 15185, "token_acc": 0.7980883388670893 }, { "epoch": 0.9834022545742933, "grad_norm": 0.28789687156677246, "learning_rate": 5.1306560186328244e-06, "loss": 0.6452177047729493, "step": 15190, "token_acc": 0.796000866727157 }, { "epoch": 0.9837259551189195, "grad_norm": 0.3333769142627716, "learning_rate": 5.1281146347047395e-06, "loss": 0.6680662155151367, "step": 15195, "token_acc": 0.791884154460719 }, { "epoch": 0.9840496556635456, "grad_norm": 0.3009397089481354, "learning_rate": 5.125573217656664e-06, "loss": 0.6687232971191406, "step": 15200, "token_acc": 0.7900614400291889 }, { "epoch": 0.9843733562081718, "grad_norm": 0.29827868938446045, "learning_rate": 5.123031768145601e-06, "loss": 0.6742939949035645, "step": 15205, "token_acc": 0.7879572196655286 }, { "epoch": 0.984697056752798, "grad_norm": 0.27247899770736694, "learning_rate": 5.120490286828561e-06, "loss": 0.6553325653076172, "step": 15210, "token_acc": 0.7949648946840522 }, { "epoch": 0.9850207572974241, "grad_norm": 0.4108053147792816, "learning_rate": 5.117948774362566e-06, "loss": 0.6509995937347413, "step": 15215, "token_acc": 0.7952538162324715 }, { "epoch": 0.9853444578420503, "grad_norm": 0.28701722621917725, "learning_rate": 5.115407231404642e-06, "loss": 0.6491232872009277, "step": 15220, "token_acc": 0.7958451521186639 }, { "epoch": 0.9856681583866765, "grad_norm": 0.23055751621723175, "learning_rate": 5.112865658611827e-06, "loss": 0.6311569213867188, "step": 15225, "token_acc": 0.7981459880901222 }, { "epoch": 0.9859918589313027, "grad_norm": 0.28742456436157227, "learning_rate": 5.110324056641161e-06, "loss": 0.6814746379852294, "step": 15230, "token_acc": 0.7858523233189328 }, { "epoch": 0.9863155594759289, "grad_norm": 0.27242526412010193, "learning_rate": 5.1077824261496945e-06, "loss": 0.6724103927612305, "step": 15235, "token_acc": 0.7885528109922383 }, { "epoch": 0.986639260020555, "grad_norm": 0.24839039146900177, "learning_rate": 5.105240767794491e-06, "loss": 0.6652225971221923, "step": 15240, "token_acc": 0.7932773907966381 }, { "epoch": 0.9869629605651812, "grad_norm": 0.3200397491455078, "learning_rate": 5.10269908223261e-06, "loss": 0.6613811492919922, "step": 15245, "token_acc": 0.7940770172890143 }, { "epoch": 0.9872866611098073, "grad_norm": 0.3624633848667145, "learning_rate": 5.1001573701211275e-06, "loss": 0.6877257347106933, "step": 15250, "token_acc": 0.7861675735687167 }, { "epoch": 0.9876103616544335, "grad_norm": 0.3021615743637085, "learning_rate": 5.097615632117121e-06, "loss": 0.6658391952514648, "step": 15255, "token_acc": 0.7916888357598414 }, { "epoch": 0.9879340621990597, "grad_norm": 0.2385323941707611, "learning_rate": 5.095073868877678e-06, "loss": 0.6481048107147217, "step": 15260, "token_acc": 0.7966146892354051 }, { "epoch": 0.9882577627436858, "grad_norm": 0.32410311698913574, "learning_rate": 5.092532081059891e-06, "loss": 0.6521430969238281, "step": 15265, "token_acc": 0.7937470683275134 }, { "epoch": 0.988581463288312, "grad_norm": 0.35183095932006836, "learning_rate": 5.089990269320858e-06, "loss": 0.6592678546905517, "step": 15270, "token_acc": 0.7924299722231518 }, { "epoch": 0.9889051638329381, "grad_norm": 0.36123061180114746, "learning_rate": 5.087448434317685e-06, "loss": 0.656126594543457, "step": 15275, "token_acc": 0.7935898684851437 }, { "epoch": 0.9892288643775643, "grad_norm": 0.37695637345314026, "learning_rate": 5.084906576707482e-06, "loss": 0.6494476318359375, "step": 15280, "token_acc": 0.7958937360028967 }, { "epoch": 0.9895525649221905, "grad_norm": 0.49187058210372925, "learning_rate": 5.082364697147368e-06, "loss": 0.6452417850494385, "step": 15285, "token_acc": 0.79580712211103 }, { "epoch": 0.9898762654668166, "grad_norm": 0.30540093779563904, "learning_rate": 5.079822796294461e-06, "loss": 0.661917781829834, "step": 15290, "token_acc": 0.7920345466355523 }, { "epoch": 0.9901999660114428, "grad_norm": 0.3211400508880615, "learning_rate": 5.0772808748058955e-06, "loss": 0.6249293804168701, "step": 15295, "token_acc": 0.800409312881198 }, { "epoch": 0.9905236665560689, "grad_norm": 0.3634622395038605, "learning_rate": 5.074738933338801e-06, "loss": 0.6406310081481934, "step": 15300, "token_acc": 0.7988242654756521 }, { "epoch": 0.9908473671006951, "grad_norm": 0.2531498372554779, "learning_rate": 5.072196972550316e-06, "loss": 0.6616634368896485, "step": 15305, "token_acc": 0.7922485485642554 }, { "epoch": 0.9911710676453214, "grad_norm": 0.28313910961151123, "learning_rate": 5.0696549930975854e-06, "loss": 0.6425573825836182, "step": 15310, "token_acc": 0.7980699696761608 }, { "epoch": 0.9914947681899475, "grad_norm": 0.35250431299209595, "learning_rate": 5.067112995637758e-06, "loss": 0.6526059627532959, "step": 15315, "token_acc": 0.7944364405068063 }, { "epoch": 0.9918184687345737, "grad_norm": 0.28465536236763, "learning_rate": 5.0645709808279865e-06, "loss": 0.6610931396484375, "step": 15320, "token_acc": 0.7925926856539819 }, { "epoch": 0.9921421692791998, "grad_norm": 0.3459881842136383, "learning_rate": 5.062028949325428e-06, "loss": 0.6597230434417725, "step": 15325, "token_acc": 0.7922596817600539 }, { "epoch": 0.992465869823826, "grad_norm": 0.4395890533924103, "learning_rate": 5.059486901787244e-06, "loss": 0.6555239200592041, "step": 15330, "token_acc": 0.793338681171046 }, { "epoch": 0.9927895703684522, "grad_norm": 0.2934178411960602, "learning_rate": 5.056944838870603e-06, "loss": 0.6628669738769531, "step": 15335, "token_acc": 0.791974953593558 }, { "epoch": 0.9931132709130783, "grad_norm": 0.273532897233963, "learning_rate": 5.054402761232673e-06, "loss": 0.6761190891265869, "step": 15340, "token_acc": 0.7895201058413182 }, { "epoch": 0.9934369714577045, "grad_norm": 0.42267173528671265, "learning_rate": 5.051860669530626e-06, "loss": 0.647489595413208, "step": 15345, "token_acc": 0.7960499001601392 }, { "epoch": 0.9937606720023306, "grad_norm": 0.28241175413131714, "learning_rate": 5.049318564421644e-06, "loss": 0.6569812774658204, "step": 15350, "token_acc": 0.7949371281515549 }, { "epoch": 0.9940843725469568, "grad_norm": 0.3225806653499603, "learning_rate": 5.046776446562904e-06, "loss": 0.6751925468444824, "step": 15355, "token_acc": 0.7877968492828592 }, { "epoch": 0.994408073091583, "grad_norm": 0.3367162346839905, "learning_rate": 5.044234316611593e-06, "loss": 0.6864947319030762, "step": 15360, "token_acc": 0.7837879069273832 }, { "epoch": 0.9947317736362091, "grad_norm": 0.32462409138679504, "learning_rate": 5.041692175224896e-06, "loss": 0.6385750293731689, "step": 15365, "token_acc": 0.7976191238939754 }, { "epoch": 0.9950554741808353, "grad_norm": 0.25748345255851746, "learning_rate": 5.039150023060007e-06, "loss": 0.6686809539794922, "step": 15370, "token_acc": 0.7907080546384241 }, { "epoch": 0.9953791747254614, "grad_norm": 0.30336475372314453, "learning_rate": 5.036607860774114e-06, "loss": 0.6597367763519287, "step": 15375, "token_acc": 0.791016670666642 }, { "epoch": 0.9957028752700876, "grad_norm": 0.3351178765296936, "learning_rate": 5.034065689024417e-06, "loss": 0.6508700847625732, "step": 15380, "token_acc": 0.7947680623464297 }, { "epoch": 0.9960265758147138, "grad_norm": 0.24506399035453796, "learning_rate": 5.031523508468111e-06, "loss": 0.6633452415466309, "step": 15385, "token_acc": 0.7925934006699437 }, { "epoch": 0.9963502763593399, "grad_norm": 0.3551746606826782, "learning_rate": 5.028981319762399e-06, "loss": 0.6535005569458008, "step": 15390, "token_acc": 0.7937989416618629 }, { "epoch": 0.9966739769039661, "grad_norm": 0.3211950361728668, "learning_rate": 5.026439123564483e-06, "loss": 0.667381477355957, "step": 15395, "token_acc": 0.7911432829465617 }, { "epoch": 0.9969976774485924, "grad_norm": 0.4022502303123474, "learning_rate": 5.023896920531567e-06, "loss": 0.6782580375671386, "step": 15400, "token_acc": 0.7885228630620311 }, { "epoch": 0.9973213779932185, "grad_norm": 0.3912368416786194, "learning_rate": 5.021354711320856e-06, "loss": 0.6622738838195801, "step": 15405, "token_acc": 0.7914537734451009 }, { "epoch": 0.9976450785378447, "grad_norm": 0.30768099427223206, "learning_rate": 5.018812496589561e-06, "loss": 0.6704260826110839, "step": 15410, "token_acc": 0.7903510237419019 }, { "epoch": 0.9979687790824708, "grad_norm": 0.3824826180934906, "learning_rate": 5.0162702769948875e-06, "loss": 0.6703650951385498, "step": 15415, "token_acc": 0.7883471809264456 }, { "epoch": 0.998292479627097, "grad_norm": 0.2666589915752411, "learning_rate": 5.01372805319405e-06, "loss": 0.6777822971343994, "step": 15420, "token_acc": 0.7888640884119238 }, { "epoch": 0.9986161801717232, "grad_norm": 0.36229410767555237, "learning_rate": 5.011185825844258e-06, "loss": 0.6428610324859619, "step": 15425, "token_acc": 0.7962612083689155 }, { "epoch": 0.9989398807163493, "grad_norm": 0.35624873638153076, "learning_rate": 5.008643595602722e-06, "loss": 0.6743216991424561, "step": 15430, "token_acc": 0.7896062971186959 }, { "epoch": 0.9992635812609755, "grad_norm": 0.2766810953617096, "learning_rate": 5.00610136312666e-06, "loss": 0.6712108612060547, "step": 15435, "token_acc": 0.7905407655572503 }, { "epoch": 0.9995872818056016, "grad_norm": 0.3249049484729767, "learning_rate": 5.003559129073281e-06, "loss": 0.6902999877929688, "step": 15440, "token_acc": 0.7872584387195408 }, { "epoch": 0.9999109823502278, "grad_norm": 0.3110852539539337, "learning_rate": 5.001016894099804e-06, "loss": 0.6656507968902587, "step": 15445, "token_acc": 0.7908991667472743 }, { "epoch": 1.0001942203267757, "grad_norm": 0.3202550411224365, "learning_rate": 4.998474658863441e-06, "loss": 0.653147029876709, "step": 15450, "token_acc": 0.7921741732754751 }, { "epoch": 1.000517920871402, "grad_norm": 0.34154412150382996, "learning_rate": 4.995932424021404e-06, "loss": 0.6529194355010987, "step": 15455, "token_acc": 0.7945017958958129 }, { "epoch": 1.000841621416028, "grad_norm": 0.2913389503955841, "learning_rate": 4.993390190230912e-06, "loss": 0.6631742954254151, "step": 15460, "token_acc": 0.7945226601511072 }, { "epoch": 1.0011653219606542, "grad_norm": 0.3201363682746887, "learning_rate": 4.990847958149179e-06, "loss": 0.6254738807678223, "step": 15465, "token_acc": 0.8015893097717932 }, { "epoch": 1.0014890225052804, "grad_norm": 0.3432430624961853, "learning_rate": 4.9883057284334155e-06, "loss": 0.6492923736572266, "step": 15470, "token_acc": 0.795772370600619 }, { "epoch": 1.0018127230499065, "grad_norm": 0.3468867242336273, "learning_rate": 4.985763501740836e-06, "loss": 0.6278500556945801, "step": 15475, "token_acc": 0.8021574213806685 }, { "epoch": 1.0021364235945327, "grad_norm": 0.42295175790786743, "learning_rate": 4.983221278728655e-06, "loss": 0.6136363983154297, "step": 15480, "token_acc": 0.8034917191606524 }, { "epoch": 1.0024601241391589, "grad_norm": 0.2797074615955353, "learning_rate": 4.980679060054081e-06, "loss": 0.6445404052734375, "step": 15485, "token_acc": 0.7953682925743928 }, { "epoch": 1.002783824683785, "grad_norm": 0.26327717304229736, "learning_rate": 4.978136846374325e-06, "loss": 0.6355785846710205, "step": 15490, "token_acc": 0.7998917459389173 }, { "epoch": 1.0031075252284112, "grad_norm": 0.41197752952575684, "learning_rate": 4.975594638346597e-06, "loss": 0.6335012435913085, "step": 15495, "token_acc": 0.7992423022157505 }, { "epoch": 1.0034312257730373, "grad_norm": 0.3478529453277588, "learning_rate": 4.973052436628104e-06, "loss": 0.6362147331237793, "step": 15500, "token_acc": 0.7980383819090573 }, { "epoch": 1.0037549263176635, "grad_norm": 0.35190549492836, "learning_rate": 4.970510241876052e-06, "loss": 0.6420605182647705, "step": 15505, "token_acc": 0.7976793686074328 }, { "epoch": 1.0040786268622897, "grad_norm": 0.3378640115261078, "learning_rate": 4.967968054747646e-06, "loss": 0.6361777305603027, "step": 15510, "token_acc": 0.798107275476186 }, { "epoch": 1.0044023274069158, "grad_norm": 0.3326471447944641, "learning_rate": 4.965425875900087e-06, "loss": 0.6437950611114502, "step": 15515, "token_acc": 0.7967185038021511 }, { "epoch": 1.004726027951542, "grad_norm": 0.33982232213020325, "learning_rate": 4.962883705990574e-06, "loss": 0.626479196548462, "step": 15520, "token_acc": 0.8014125355819325 }, { "epoch": 1.0050497284961681, "grad_norm": 0.25187698006629944, "learning_rate": 4.960341545676307e-06, "loss": 0.6254870414733886, "step": 15525, "token_acc": 0.8017160728128091 }, { "epoch": 1.0053734290407943, "grad_norm": 0.2557846009731293, "learning_rate": 4.957799395614481e-06, "loss": 0.6222665309906006, "step": 15530, "token_acc": 0.8030917925989214 }, { "epoch": 1.0056971295854205, "grad_norm": 0.36653921008110046, "learning_rate": 4.955257256462285e-06, "loss": 0.6489649295806885, "step": 15535, "token_acc": 0.7946976192046429 }, { "epoch": 1.0060208301300466, "grad_norm": 0.26315560936927795, "learning_rate": 4.952715128876914e-06, "loss": 0.6630708694458007, "step": 15540, "token_acc": 0.792073806877459 }, { "epoch": 1.0063445306746728, "grad_norm": 0.30887967348098755, "learning_rate": 4.950173013515551e-06, "loss": 0.6403450965881348, "step": 15545, "token_acc": 0.7972408736328271 }, { "epoch": 1.006668231219299, "grad_norm": 0.22990764677524567, "learning_rate": 4.947630911035381e-06, "loss": 0.644466781616211, "step": 15550, "token_acc": 0.7972931294109109 }, { "epoch": 1.006991931763925, "grad_norm": 0.4803391993045807, "learning_rate": 4.945088822093585e-06, "loss": 0.6101676464080811, "step": 15555, "token_acc": 0.8061028621183237 }, { "epoch": 1.0073156323085513, "grad_norm": 0.37497395277023315, "learning_rate": 4.942546747347338e-06, "loss": 0.6504141807556152, "step": 15560, "token_acc": 0.7956176948310456 }, { "epoch": 1.0076393328531774, "grad_norm": 0.39361852407455444, "learning_rate": 4.9400046874538156e-06, "loss": 0.651695728302002, "step": 15565, "token_acc": 0.7930577793591492 }, { "epoch": 1.0079630333978038, "grad_norm": 0.2162349820137024, "learning_rate": 4.937462643070183e-06, "loss": 0.6333465576171875, "step": 15570, "token_acc": 0.7985654036462657 }, { "epoch": 1.00828673394243, "grad_norm": 0.251123309135437, "learning_rate": 4.934920614853609e-06, "loss": 0.6552522659301758, "step": 15575, "token_acc": 0.7944633000374428 }, { "epoch": 1.0086104344870561, "grad_norm": 0.34090718626976013, "learning_rate": 4.932378603461253e-06, "loss": 0.6863268852233887, "step": 15580, "token_acc": 0.7869280428491443 }, { "epoch": 1.0089341350316823, "grad_norm": 0.2984141707420349, "learning_rate": 4.929836609550274e-06, "loss": 0.6395855903625488, "step": 15585, "token_acc": 0.7970826827131813 }, { "epoch": 1.0092578355763084, "grad_norm": 0.27034446597099304, "learning_rate": 4.927294633777821e-06, "loss": 0.6502932548522949, "step": 15590, "token_acc": 0.7949437630931315 }, { "epoch": 1.0095815361209346, "grad_norm": 0.35832807421684265, "learning_rate": 4.924752676801042e-06, "loss": 0.6417821884155274, "step": 15595, "token_acc": 0.7969881765667014 }, { "epoch": 1.0099052366655608, "grad_norm": 0.3114849030971527, "learning_rate": 4.922210739277083e-06, "loss": 0.6803587436676025, "step": 15600, "token_acc": 0.786251550351413 }, { "epoch": 1.010228937210187, "grad_norm": 0.2383250892162323, "learning_rate": 4.919668821863077e-06, "loss": 0.6315587043762207, "step": 15605, "token_acc": 0.7997157581553501 }, { "epoch": 1.010552637754813, "grad_norm": 0.28881940245628357, "learning_rate": 4.91712692521616e-06, "loss": 0.6501009941101075, "step": 15610, "token_acc": 0.7953430161709976 }, { "epoch": 1.0108763382994392, "grad_norm": 0.2576662302017212, "learning_rate": 4.914585049993459e-06, "loss": 0.659115982055664, "step": 15615, "token_acc": 0.7926869325400514 }, { "epoch": 1.0112000388440654, "grad_norm": 0.35790306329727173, "learning_rate": 4.912043196852092e-06, "loss": 0.6122112274169922, "step": 15620, "token_acc": 0.8062095156105723 }, { "epoch": 1.0115237393886916, "grad_norm": 0.24888131022453308, "learning_rate": 4.909501366449178e-06, "loss": 0.6476584911346436, "step": 15625, "token_acc": 0.7964162681885958 }, { "epoch": 1.0118474399333177, "grad_norm": 0.304617315530777, "learning_rate": 4.906959559441825e-06, "loss": 0.6472938537597657, "step": 15630, "token_acc": 0.7960281063105104 }, { "epoch": 1.0121711404779439, "grad_norm": 0.25579777359962463, "learning_rate": 4.904417776487141e-06, "loss": 0.6525937080383301, "step": 15635, "token_acc": 0.7955174081837689 }, { "epoch": 1.01249484102257, "grad_norm": 0.42801633477211, "learning_rate": 4.901876018242217e-06, "loss": 0.6472385406494141, "step": 15640, "token_acc": 0.7951952793853588 }, { "epoch": 1.0128185415671962, "grad_norm": 0.2754896879196167, "learning_rate": 4.899334285364148e-06, "loss": 0.641113567352295, "step": 15645, "token_acc": 0.7977942084084232 }, { "epoch": 1.0131422421118224, "grad_norm": 0.28580543398857117, "learning_rate": 4.896792578510022e-06, "loss": 0.625841474533081, "step": 15650, "token_acc": 0.8004392963748662 }, { "epoch": 1.0134659426564485, "grad_norm": 0.2760554850101471, "learning_rate": 4.89425089833691e-06, "loss": 0.6332650184631348, "step": 15655, "token_acc": 0.7992952560078859 }, { "epoch": 1.0137896432010747, "grad_norm": 0.27296677231788635, "learning_rate": 4.891709245501887e-06, "loss": 0.6395422935485839, "step": 15660, "token_acc": 0.7978709265855085 }, { "epoch": 1.0141133437457008, "grad_norm": 0.2967386245727539, "learning_rate": 4.889167620662019e-06, "loss": 0.6485885143280029, "step": 15665, "token_acc": 0.7966903557457964 }, { "epoch": 1.014437044290327, "grad_norm": 0.27577218413352966, "learning_rate": 4.886626024474358e-06, "loss": 0.6373697757720947, "step": 15670, "token_acc": 0.7987918601578132 }, { "epoch": 1.0147607448349532, "grad_norm": 0.3713255822658539, "learning_rate": 4.8840844575959565e-06, "loss": 0.6417015075683594, "step": 15675, "token_acc": 0.7976422625696561 }, { "epoch": 1.0150844453795793, "grad_norm": 0.322103887796402, "learning_rate": 4.881542920683856e-06, "loss": 0.6527330875396729, "step": 15680, "token_acc": 0.7956697105611307 }, { "epoch": 1.0154081459242055, "grad_norm": 0.2829621732234955, "learning_rate": 4.8790014143950905e-06, "loss": 0.6515660762786866, "step": 15685, "token_acc": 0.7951836002297826 }, { "epoch": 1.0157318464688316, "grad_norm": 0.36498144268989563, "learning_rate": 4.876459939386685e-06, "loss": 0.636810302734375, "step": 15690, "token_acc": 0.797736703130894 }, { "epoch": 1.0160555470134578, "grad_norm": 0.32075947523117065, "learning_rate": 4.873918496315658e-06, "loss": 0.6474423408508301, "step": 15695, "token_acc": 0.795874265956863 }, { "epoch": 1.016379247558084, "grad_norm": 0.2935772240161896, "learning_rate": 4.871377085839023e-06, "loss": 0.6444916725158691, "step": 15700, "token_acc": 0.7974836293943319 }, { "epoch": 1.0167029481027101, "grad_norm": 0.25698527693748474, "learning_rate": 4.868835708613774e-06, "loss": 0.6497626304626465, "step": 15705, "token_acc": 0.7953136921573615 }, { "epoch": 1.0170266486473363, "grad_norm": 0.3365549147129059, "learning_rate": 4.866294365296909e-06, "loss": 0.6411726474761963, "step": 15710, "token_acc": 0.7981956378942853 }, { "epoch": 1.0173503491919624, "grad_norm": 0.2687922716140747, "learning_rate": 4.863753056545411e-06, "loss": 0.6640188217163085, "step": 15715, "token_acc": 0.7907209182357493 }, { "epoch": 1.0176740497365886, "grad_norm": 0.3342791795730591, "learning_rate": 4.861211783016256e-06, "loss": 0.6534811496734619, "step": 15720, "token_acc": 0.794026299713854 }, { "epoch": 1.0179977502812148, "grad_norm": 0.30909326672554016, "learning_rate": 4.858670545366407e-06, "loss": 0.6421111583709717, "step": 15725, "token_acc": 0.7965407571994946 }, { "epoch": 1.018321450825841, "grad_norm": 0.4094979166984558, "learning_rate": 4.856129344252824e-06, "loss": 0.6438141822814941, "step": 15730, "token_acc": 0.7974677048991059 }, { "epoch": 1.018645151370467, "grad_norm": 0.2922459542751312, "learning_rate": 4.853588180332452e-06, "loss": 0.6338470458984375, "step": 15735, "token_acc": 0.799982230796568 }, { "epoch": 1.0189688519150935, "grad_norm": 0.37791505455970764, "learning_rate": 4.851047054262229e-06, "loss": 0.6331180095672607, "step": 15740, "token_acc": 0.7993457206770369 }, { "epoch": 1.0192925524597196, "grad_norm": 0.29602864384651184, "learning_rate": 4.848505966699084e-06, "loss": 0.6359106063842773, "step": 15745, "token_acc": 0.7996698186015609 }, { "epoch": 1.0196162530043458, "grad_norm": 0.28909796476364136, "learning_rate": 4.845964918299935e-06, "loss": 0.653119707107544, "step": 15750, "token_acc": 0.795167197651958 }, { "epoch": 1.019939953548972, "grad_norm": 0.39752310514450073, "learning_rate": 4.843423909721688e-06, "loss": 0.6312860965728759, "step": 15755, "token_acc": 0.8009206278170252 }, { "epoch": 1.020263654093598, "grad_norm": 0.32694026827812195, "learning_rate": 4.8408829416212414e-06, "loss": 0.6257385730743408, "step": 15760, "token_acc": 0.8006222342186201 }, { "epoch": 1.0205873546382243, "grad_norm": 0.2991727292537689, "learning_rate": 4.8383420146554824e-06, "loss": 0.6328621864318847, "step": 15765, "token_acc": 0.7988372093023256 }, { "epoch": 1.0209110551828504, "grad_norm": 0.3596811592578888, "learning_rate": 4.835801129481287e-06, "loss": 0.6455683708190918, "step": 15770, "token_acc": 0.7974285903638412 }, { "epoch": 1.0212347557274766, "grad_norm": 0.3670375347137451, "learning_rate": 4.833260286755521e-06, "loss": 0.6504391670227051, "step": 15775, "token_acc": 0.7956405828932254 }, { "epoch": 1.0215584562721027, "grad_norm": 0.389199823141098, "learning_rate": 4.830719487135039e-06, "loss": 0.6315677165985107, "step": 15780, "token_acc": 0.8011857546452243 }, { "epoch": 1.021882156816729, "grad_norm": 0.2760383188724518, "learning_rate": 4.828178731276686e-06, "loss": 0.6276272296905517, "step": 15785, "token_acc": 0.802269346435954 }, { "epoch": 1.022205857361355, "grad_norm": 0.3393191397190094, "learning_rate": 4.825638019837291e-06, "loss": 0.6526288986206055, "step": 15790, "token_acc": 0.7968712336691897 }, { "epoch": 1.0225295579059812, "grad_norm": 0.2854517102241516, "learning_rate": 4.823097353473675e-06, "loss": 0.6228813171386719, "step": 15795, "token_acc": 0.8037634775954193 }, { "epoch": 1.0228532584506074, "grad_norm": 0.36328741908073425, "learning_rate": 4.820556732842651e-06, "loss": 0.664785099029541, "step": 15800, "token_acc": 0.7911547911547911 }, { "epoch": 1.0231769589952335, "grad_norm": 0.3878428637981415, "learning_rate": 4.818016158601011e-06, "loss": 0.6492916107177734, "step": 15805, "token_acc": 0.7946823937644043 }, { "epoch": 1.0235006595398597, "grad_norm": 0.2673211097717285, "learning_rate": 4.815475631405544e-06, "loss": 0.6264103412628174, "step": 15810, "token_acc": 0.802344231955583 }, { "epoch": 1.0238243600844859, "grad_norm": 0.26710087060928345, "learning_rate": 4.8129351519130205e-06, "loss": 0.6274779796600342, "step": 15815, "token_acc": 0.7995824360523137 }, { "epoch": 1.024148060629112, "grad_norm": 0.337446391582489, "learning_rate": 4.810394720780205e-06, "loss": 0.6424118041992187, "step": 15820, "token_acc": 0.7954729844895176 }, { "epoch": 1.0244717611737382, "grad_norm": 0.36659693717956543, "learning_rate": 4.8078543386638395e-06, "loss": 0.661394453048706, "step": 15825, "token_acc": 0.7921568362162857 }, { "epoch": 1.0247954617183643, "grad_norm": 0.33711758255958557, "learning_rate": 4.8053140062206645e-06, "loss": 0.6374249458312988, "step": 15830, "token_acc": 0.7982237487104237 }, { "epoch": 1.0251191622629905, "grad_norm": 0.3687794506549835, "learning_rate": 4.802773724107402e-06, "loss": 0.6396578788757324, "step": 15835, "token_acc": 0.7986351651760327 }, { "epoch": 1.0254428628076167, "grad_norm": 0.3770722448825836, "learning_rate": 4.80023349298076e-06, "loss": 0.632948923110962, "step": 15840, "token_acc": 0.7989013451392332 }, { "epoch": 1.0257665633522428, "grad_norm": 0.34946227073669434, "learning_rate": 4.797693313497436e-06, "loss": 0.6446344375610351, "step": 15845, "token_acc": 0.7962486252613514 }, { "epoch": 1.026090263896869, "grad_norm": 0.3355104625225067, "learning_rate": 4.7951531863141125e-06, "loss": 0.6246145248413086, "step": 15850, "token_acc": 0.8019119111659135 }, { "epoch": 1.0264139644414951, "grad_norm": 0.35207533836364746, "learning_rate": 4.792613112087461e-06, "loss": 0.6350555419921875, "step": 15855, "token_acc": 0.7992344192352168 }, { "epoch": 1.0267376649861213, "grad_norm": 0.36527320742607117, "learning_rate": 4.790073091474135e-06, "loss": 0.6428610801696777, "step": 15860, "token_acc": 0.7976907786923552 }, { "epoch": 1.0270613655307474, "grad_norm": 0.27563056349754333, "learning_rate": 4.787533125130777e-06, "loss": 0.6337900161743164, "step": 15865, "token_acc": 0.7999712871472533 }, { "epoch": 1.0273850660753736, "grad_norm": 0.3737109899520874, "learning_rate": 4.784993213714018e-06, "loss": 0.6432722091674805, "step": 15870, "token_acc": 0.7949652850537139 }, { "epoch": 1.0277087666199998, "grad_norm": 0.31641122698783875, "learning_rate": 4.7824533578804675e-06, "loss": 0.6547872066497803, "step": 15875, "token_acc": 0.7948711189027806 }, { "epoch": 1.028032467164626, "grad_norm": 0.30354270339012146, "learning_rate": 4.7799135582867274e-06, "loss": 0.6343920707702637, "step": 15880, "token_acc": 0.7991135656936 }, { "epoch": 1.028356167709252, "grad_norm": 0.23791706562042236, "learning_rate": 4.777373815589383e-06, "loss": 0.620660400390625, "step": 15885, "token_acc": 0.8036539427423405 }, { "epoch": 1.0286798682538782, "grad_norm": 0.27572739124298096, "learning_rate": 4.774834130445003e-06, "loss": 0.6372406959533692, "step": 15890, "token_acc": 0.7967428346872645 }, { "epoch": 1.0290035687985044, "grad_norm": 0.3144340515136719, "learning_rate": 4.7722945035101435e-06, "loss": 0.6341968059539795, "step": 15895, "token_acc": 0.7981290962484685 }, { "epoch": 1.0293272693431306, "grad_norm": 0.29201075434684753, "learning_rate": 4.769754935441343e-06, "loss": 0.6672430992126465, "step": 15900, "token_acc": 0.7917676692442073 }, { "epoch": 1.0296509698877567, "grad_norm": 0.33740320801734924, "learning_rate": 4.767215426895132e-06, "loss": 0.6613070487976074, "step": 15905, "token_acc": 0.7922844673969324 }, { "epoch": 1.029974670432383, "grad_norm": 0.4029899835586548, "learning_rate": 4.764675978528014e-06, "loss": 0.6257753372192383, "step": 15910, "token_acc": 0.8014782860962905 }, { "epoch": 1.0302983709770093, "grad_norm": 0.25754448771476746, "learning_rate": 4.762136590996486e-06, "loss": 0.6235474109649658, "step": 15915, "token_acc": 0.8024912539007277 }, { "epoch": 1.0306220715216354, "grad_norm": 0.366045206785202, "learning_rate": 4.759597264957027e-06, "loss": 0.6280375003814698, "step": 15920, "token_acc": 0.8009868851600743 }, { "epoch": 1.0309457720662616, "grad_norm": 0.31802988052368164, "learning_rate": 4.7570580010660975e-06, "loss": 0.6646952629089355, "step": 15925, "token_acc": 0.7920521404940668 }, { "epoch": 1.0312694726108877, "grad_norm": 0.30163902044296265, "learning_rate": 4.754518799980144e-06, "loss": 0.6517912864685058, "step": 15930, "token_acc": 0.7959723587578789 }, { "epoch": 1.031593173155514, "grad_norm": 0.3353748619556427, "learning_rate": 4.751979662355599e-06, "loss": 0.6289876937866211, "step": 15935, "token_acc": 0.8011575410782719 }, { "epoch": 1.03191687370014, "grad_norm": 0.23409602046012878, "learning_rate": 4.749440588848876e-06, "loss": 0.6265591144561767, "step": 15940, "token_acc": 0.8011496293059898 }, { "epoch": 1.0322405742447662, "grad_norm": 0.22845660150051117, "learning_rate": 4.74690158011637e-06, "loss": 0.6315669059753418, "step": 15945, "token_acc": 0.8008930027216515 }, { "epoch": 1.0325642747893924, "grad_norm": 0.2802457809448242, "learning_rate": 4.744362636814462e-06, "loss": 0.6325824737548829, "step": 15950, "token_acc": 0.8003760679280885 }, { "epoch": 1.0328879753340185, "grad_norm": 0.36399978399276733, "learning_rate": 4.741823759599519e-06, "loss": 0.6423224449157715, "step": 15955, "token_acc": 0.7972945627579271 }, { "epoch": 1.0332116758786447, "grad_norm": 0.3050110638141632, "learning_rate": 4.7392849491278825e-06, "loss": 0.6483078956604004, "step": 15960, "token_acc": 0.7963400979706088 }, { "epoch": 1.0335353764232709, "grad_norm": 0.2864549160003662, "learning_rate": 4.736746206055884e-06, "loss": 0.640544319152832, "step": 15965, "token_acc": 0.7993884231250262 }, { "epoch": 1.033859076967897, "grad_norm": 0.2608305513858795, "learning_rate": 4.734207531039837e-06, "loss": 0.6421225070953369, "step": 15970, "token_acc": 0.798205697373289 }, { "epoch": 1.0341827775125232, "grad_norm": 0.38505589962005615, "learning_rate": 4.731668924736031e-06, "loss": 0.6334835052490234, "step": 15975, "token_acc": 0.7996605014676239 }, { "epoch": 1.0345064780571493, "grad_norm": 0.30796074867248535, "learning_rate": 4.729130387800747e-06, "loss": 0.6220541954040527, "step": 15980, "token_acc": 0.8023913818742135 }, { "epoch": 1.0348301786017755, "grad_norm": 0.2813141345977783, "learning_rate": 4.726591920890242e-06, "loss": 0.6292692184448242, "step": 15985, "token_acc": 0.8011343666223304 }, { "epoch": 1.0351538791464017, "grad_norm": 0.35262829065322876, "learning_rate": 4.724053524660757e-06, "loss": 0.6302877902984619, "step": 15990, "token_acc": 0.8023470435725623 }, { "epoch": 1.0354775796910278, "grad_norm": 0.3629734516143799, "learning_rate": 4.7215151997685115e-06, "loss": 0.6520500183105469, "step": 15995, "token_acc": 0.7942937188619154 }, { "epoch": 1.035801280235654, "grad_norm": 0.31159383058547974, "learning_rate": 4.718976946869713e-06, "loss": 0.6569159507751465, "step": 16000, "token_acc": 0.7947381500470859 }, { "epoch": 1.0361249807802801, "grad_norm": 0.4056605398654938, "learning_rate": 4.7164387666205445e-06, "loss": 0.6521588325500488, "step": 16005, "token_acc": 0.7944219221507605 }, { "epoch": 1.0364486813249063, "grad_norm": 0.3129880428314209, "learning_rate": 4.713900659677172e-06, "loss": 0.6597915649414062, "step": 16010, "token_acc": 0.7937612005724379 }, { "epoch": 1.0367723818695325, "grad_norm": 0.3262636661529541, "learning_rate": 4.711362626695743e-06, "loss": 0.641474723815918, "step": 16015, "token_acc": 0.7988137223469061 }, { "epoch": 1.0370960824141586, "grad_norm": 0.30047255754470825, "learning_rate": 4.7088246683323866e-06, "loss": 0.6409108161926269, "step": 16020, "token_acc": 0.7976568005637773 }, { "epoch": 1.0374197829587848, "grad_norm": 0.2998305559158325, "learning_rate": 4.706286785243211e-06, "loss": 0.6162043571472168, "step": 16025, "token_acc": 0.8033251093417069 }, { "epoch": 1.037743483503411, "grad_norm": 0.35681986808776855, "learning_rate": 4.703748978084306e-06, "loss": 0.6254749298095703, "step": 16030, "token_acc": 0.8016247085375129 }, { "epoch": 1.038067184048037, "grad_norm": 0.3297930061817169, "learning_rate": 4.701211247511741e-06, "loss": 0.6373942852020263, "step": 16035, "token_acc": 0.7987376985014538 }, { "epoch": 1.0383908845926633, "grad_norm": 0.25308531522750854, "learning_rate": 4.698673594181568e-06, "loss": 0.6309360504150391, "step": 16040, "token_acc": 0.8011552735544116 }, { "epoch": 1.0387145851372894, "grad_norm": 0.22784774005413055, "learning_rate": 4.696136018749813e-06, "loss": 0.648825740814209, "step": 16045, "token_acc": 0.7966937354988399 }, { "epoch": 1.0390382856819156, "grad_norm": 0.32834598422050476, "learning_rate": 4.693598521872489e-06, "loss": 0.6185405731201172, "step": 16050, "token_acc": 0.8044113904363318 }, { "epoch": 1.0393619862265417, "grad_norm": 0.2538762390613556, "learning_rate": 4.691061104205587e-06, "loss": 0.6300791740417481, "step": 16055, "token_acc": 0.8016232715164409 }, { "epoch": 1.039685686771168, "grad_norm": 0.3156016767024994, "learning_rate": 4.688523766405072e-06, "loss": 0.6204427242279053, "step": 16060, "token_acc": 0.8041270478274096 }, { "epoch": 1.040009387315794, "grad_norm": 0.30811867117881775, "learning_rate": 4.6859865091268955e-06, "loss": 0.6520961284637451, "step": 16065, "token_acc": 0.7946625643769647 }, { "epoch": 1.0403330878604202, "grad_norm": 0.33363935351371765, "learning_rate": 4.683449333026984e-06, "loss": 0.6429319858551026, "step": 16070, "token_acc": 0.7981035626487689 }, { "epoch": 1.0406567884050464, "grad_norm": 0.3022553026676178, "learning_rate": 4.680912238761246e-06, "loss": 0.6406399726867675, "step": 16075, "token_acc": 0.7985978566354736 }, { "epoch": 1.0409804889496725, "grad_norm": 0.3459247052669525, "learning_rate": 4.678375226985564e-06, "loss": 0.6439824104309082, "step": 16080, "token_acc": 0.7983894898702419 }, { "epoch": 1.041304189494299, "grad_norm": 0.3258695900440216, "learning_rate": 4.675838298355804e-06, "loss": 0.6297721862792969, "step": 16085, "token_acc": 0.8019956892074375 }, { "epoch": 1.041627890038925, "grad_norm": 0.410390704870224, "learning_rate": 4.673301453527811e-06, "loss": 0.6512630939483642, "step": 16090, "token_acc": 0.7948403537495119 }, { "epoch": 1.0419515905835512, "grad_norm": 0.25334617495536804, "learning_rate": 4.6707646931574016e-06, "loss": 0.6698915004730225, "step": 16095, "token_acc": 0.7916076465057975 }, { "epoch": 1.0422752911281774, "grad_norm": 0.40392762422561646, "learning_rate": 4.6682280179003765e-06, "loss": 0.6398199081420899, "step": 16100, "token_acc": 0.7988856371757868 }, { "epoch": 1.0425989916728036, "grad_norm": 0.25628209114074707, "learning_rate": 4.665691428412516e-06, "loss": 0.6547086715698243, "step": 16105, "token_acc": 0.7939417910939714 }, { "epoch": 1.0429226922174297, "grad_norm": 0.3168643116950989, "learning_rate": 4.663154925349571e-06, "loss": 0.632042121887207, "step": 16110, "token_acc": 0.7977438226017634 }, { "epoch": 1.0432463927620559, "grad_norm": 0.3763976991176605, "learning_rate": 4.660618509367275e-06, "loss": 0.6366244792938233, "step": 16115, "token_acc": 0.7976606461391942 }, { "epoch": 1.043570093306682, "grad_norm": 0.3693247437477112, "learning_rate": 4.658082181121339e-06, "loss": 0.6230560779571533, "step": 16120, "token_acc": 0.8025539660814407 }, { "epoch": 1.0438937938513082, "grad_norm": 0.28083130717277527, "learning_rate": 4.655545941267454e-06, "loss": 0.6410291194915771, "step": 16125, "token_acc": 0.7986838480609715 }, { "epoch": 1.0442174943959344, "grad_norm": 0.35084617137908936, "learning_rate": 4.653009790461278e-06, "loss": 0.6459152221679687, "step": 16130, "token_acc": 0.7973242621766975 }, { "epoch": 1.0445411949405605, "grad_norm": 0.24557100236415863, "learning_rate": 4.650473729358457e-06, "loss": 0.6315649032592774, "step": 16135, "token_acc": 0.8000771561019725 }, { "epoch": 1.0448648954851867, "grad_norm": 0.29146483540534973, "learning_rate": 4.6479377586146105e-06, "loss": 0.6355103492736817, "step": 16140, "token_acc": 0.7989855091963457 }, { "epoch": 1.0451885960298128, "grad_norm": 0.35461705923080444, "learning_rate": 4.64540187888533e-06, "loss": 0.6497774124145508, "step": 16145, "token_acc": 0.7965917141132947 }, { "epoch": 1.045512296574439, "grad_norm": 0.41119584441185, "learning_rate": 4.642866090826187e-06, "loss": 0.665977668762207, "step": 16150, "token_acc": 0.7931998452968197 }, { "epoch": 1.0458359971190652, "grad_norm": 0.3458676040172577, "learning_rate": 4.640330395092734e-06, "loss": 0.6077310562133789, "step": 16155, "token_acc": 0.8055759948198729 }, { "epoch": 1.0461596976636913, "grad_norm": 0.31368908286094666, "learning_rate": 4.637794792340489e-06, "loss": 0.6256333351135254, "step": 16160, "token_acc": 0.801640253974809 }, { "epoch": 1.0464833982083175, "grad_norm": 0.4223470985889435, "learning_rate": 4.635259283224956e-06, "loss": 0.6479896545410156, "step": 16165, "token_acc": 0.7952103689503727 }, { "epoch": 1.0468070987529436, "grad_norm": 0.24630075693130493, "learning_rate": 4.63272386840161e-06, "loss": 0.6344763755798339, "step": 16170, "token_acc": 0.7982091066342389 }, { "epoch": 1.0471307992975698, "grad_norm": 0.23803412914276123, "learning_rate": 4.630188548525903e-06, "loss": 0.6316813945770263, "step": 16175, "token_acc": 0.8009651328756882 }, { "epoch": 1.047454499842196, "grad_norm": 0.24984832108020782, "learning_rate": 4.62765332425326e-06, "loss": 0.6356700897216797, "step": 16180, "token_acc": 0.7989504263892794 }, { "epoch": 1.0477782003868221, "grad_norm": 0.3053905963897705, "learning_rate": 4.625118196239083e-06, "loss": 0.6228386878967285, "step": 16185, "token_acc": 0.8031328328794383 }, { "epoch": 1.0481019009314483, "grad_norm": 0.28131839632987976, "learning_rate": 4.622583165138753e-06, "loss": 0.6234171867370606, "step": 16190, "token_acc": 0.8021138418438813 }, { "epoch": 1.0484256014760744, "grad_norm": 0.3304670751094818, "learning_rate": 4.6200482316076165e-06, "loss": 0.6377764225006104, "step": 16195, "token_acc": 0.7989161312879682 }, { "epoch": 1.0487493020207006, "grad_norm": 0.3299176096916199, "learning_rate": 4.617513396301005e-06, "loss": 0.6605055809020997, "step": 16200, "token_acc": 0.7930844380625144 }, { "epoch": 1.0490730025653268, "grad_norm": 0.3123266398906708, "learning_rate": 4.614978659874219e-06, "loss": 0.6388386249542236, "step": 16205, "token_acc": 0.7975954471281574 }, { "epoch": 1.049396703109953, "grad_norm": 0.3513127565383911, "learning_rate": 4.6124440229825336e-06, "loss": 0.6299392700195312, "step": 16210, "token_acc": 0.8006648732001361 }, { "epoch": 1.049720403654579, "grad_norm": 0.2927079200744629, "learning_rate": 4.6099094862811984e-06, "loss": 0.6270839691162109, "step": 16215, "token_acc": 0.8003367390817198 }, { "epoch": 1.0500441041992052, "grad_norm": 0.3581523895263672, "learning_rate": 4.60737505042544e-06, "loss": 0.6436834335327148, "step": 16220, "token_acc": 0.7969408144367938 }, { "epoch": 1.0503678047438314, "grad_norm": 0.4082167148590088, "learning_rate": 4.6048407160704565e-06, "loss": 0.6491001129150391, "step": 16225, "token_acc": 0.7958876720768826 }, { "epoch": 1.0506915052884576, "grad_norm": 0.35110750794410706, "learning_rate": 4.602306483871416e-06, "loss": 0.6153587341308594, "step": 16230, "token_acc": 0.804647611158926 }, { "epoch": 1.0510152058330837, "grad_norm": 0.32634270191192627, "learning_rate": 4.59977235448347e-06, "loss": 0.6486783027648926, "step": 16235, "token_acc": 0.7952610510627354 }, { "epoch": 1.0513389063777099, "grad_norm": 0.2750050127506256, "learning_rate": 4.597238328561734e-06, "loss": 0.634598684310913, "step": 16240, "token_acc": 0.7995486560485943 }, { "epoch": 1.051662606922336, "grad_norm": 0.3644012212753296, "learning_rate": 4.594704406761301e-06, "loss": 0.6508404731750488, "step": 16245, "token_acc": 0.7958461070713725 }, { "epoch": 1.0519863074669624, "grad_norm": 0.3770143687725067, "learning_rate": 4.592170589737237e-06, "loss": 0.640921688079834, "step": 16250, "token_acc": 0.799017653854729 }, { "epoch": 1.0523100080115886, "grad_norm": 0.33589017391204834, "learning_rate": 4.589636878144579e-06, "loss": 0.6273042678833007, "step": 16255, "token_acc": 0.8020514989012115 }, { "epoch": 1.0526337085562147, "grad_norm": 0.2867448925971985, "learning_rate": 4.587103272638339e-06, "loss": 0.6571349143981934, "step": 16260, "token_acc": 0.7947487976826377 }, { "epoch": 1.052957409100841, "grad_norm": 0.318212628364563, "learning_rate": 4.5845697738735015e-06, "loss": 0.6462741374969483, "step": 16265, "token_acc": 0.7971268964889349 }, { "epoch": 1.053281109645467, "grad_norm": 0.42015188932418823, "learning_rate": 4.58203638250502e-06, "loss": 0.6259598731994629, "step": 16270, "token_acc": 0.8013482574408547 }, { "epoch": 1.0536048101900932, "grad_norm": 0.33700403571128845, "learning_rate": 4.579503099187826e-06, "loss": 0.6416770458221436, "step": 16275, "token_acc": 0.7979866840814246 }, { "epoch": 1.0539285107347194, "grad_norm": 0.4108504354953766, "learning_rate": 4.576969924576818e-06, "loss": 0.6384095668792724, "step": 16280, "token_acc": 0.7984531446019836 }, { "epoch": 1.0542522112793455, "grad_norm": 0.25669148564338684, "learning_rate": 4.574436859326866e-06, "loss": 0.6443956375122071, "step": 16285, "token_acc": 0.7967355565993424 }, { "epoch": 1.0545759118239717, "grad_norm": 0.27766841650009155, "learning_rate": 4.5719039040928195e-06, "loss": 0.6158721923828125, "step": 16290, "token_acc": 0.8045637879829328 }, { "epoch": 1.0548996123685979, "grad_norm": 0.3539871275424957, "learning_rate": 4.5693710595294904e-06, "loss": 0.6311295509338379, "step": 16295, "token_acc": 0.7984347558980455 }, { "epoch": 1.055223312913224, "grad_norm": 0.311497300863266, "learning_rate": 4.566838326291665e-06, "loss": 0.6557769775390625, "step": 16300, "token_acc": 0.7948721285872323 }, { "epoch": 1.0555470134578502, "grad_norm": 0.3518669307231903, "learning_rate": 4.564305705034103e-06, "loss": 0.6260739326477051, "step": 16305, "token_acc": 0.800292507057583 }, { "epoch": 1.0558707140024763, "grad_norm": 0.285751610994339, "learning_rate": 4.561773196411535e-06, "loss": 0.6523067474365234, "step": 16310, "token_acc": 0.7969516967714926 }, { "epoch": 1.0561944145471025, "grad_norm": 0.3346266746520996, "learning_rate": 4.559240801078658e-06, "loss": 0.6267722129821778, "step": 16315, "token_acc": 0.7999790286324703 }, { "epoch": 1.0565181150917287, "grad_norm": 0.3222896456718445, "learning_rate": 4.556708519690143e-06, "loss": 0.6338886260986328, "step": 16320, "token_acc": 0.7990536533853215 }, { "epoch": 1.0568418156363548, "grad_norm": 0.20442649722099304, "learning_rate": 4.554176352900635e-06, "loss": 0.6369258403778076, "step": 16325, "token_acc": 0.7981530737276232 }, { "epoch": 1.057165516180981, "grad_norm": 0.34135857224464417, "learning_rate": 4.551644301364742e-06, "loss": 0.6377176284790039, "step": 16330, "token_acc": 0.7984958623314133 }, { "epoch": 1.0574892167256071, "grad_norm": 0.291952520608902, "learning_rate": 4.549112365737046e-06, "loss": 0.6320829868316651, "step": 16335, "token_acc": 0.7997016762317561 }, { "epoch": 1.0578129172702333, "grad_norm": 0.3784465491771698, "learning_rate": 4.5465805466721e-06, "loss": 0.6169294357299805, "step": 16340, "token_acc": 0.805754006564974 }, { "epoch": 1.0581366178148595, "grad_norm": 0.2816925644874573, "learning_rate": 4.544048844824428e-06, "loss": 0.6127999305725098, "step": 16345, "token_acc": 0.8042617267079174 }, { "epoch": 1.0584603183594856, "grad_norm": 0.30519381165504456, "learning_rate": 4.541517260848518e-06, "loss": 0.6120930194854737, "step": 16350, "token_acc": 0.8042783948996354 }, { "epoch": 1.0587840189041118, "grad_norm": 0.26095259189605713, "learning_rate": 4.538985795398832e-06, "loss": 0.6262161254882812, "step": 16355, "token_acc": 0.8027781041527957 }, { "epoch": 1.059107719448738, "grad_norm": 0.33536115288734436, "learning_rate": 4.536454449129803e-06, "loss": 0.6332845687866211, "step": 16360, "token_acc": 0.8007655288780341 }, { "epoch": 1.059431419993364, "grad_norm": 0.3418472409248352, "learning_rate": 4.533923222695825e-06, "loss": 0.6173822402954101, "step": 16365, "token_acc": 0.8027033159776522 }, { "epoch": 1.0597551205379903, "grad_norm": 0.4490620195865631, "learning_rate": 4.531392116751272e-06, "loss": 0.6254627704620361, "step": 16370, "token_acc": 0.8016591868977108 }, { "epoch": 1.0600788210826164, "grad_norm": 0.2928144037723541, "learning_rate": 4.52886113195048e-06, "loss": 0.6292794704437256, "step": 16375, "token_acc": 0.8016609118632961 }, { "epoch": 1.0604025216272426, "grad_norm": 0.26256611943244934, "learning_rate": 4.526330268947753e-06, "loss": 0.6521354198455811, "step": 16380, "token_acc": 0.7942197622491981 }, { "epoch": 1.0607262221718687, "grad_norm": 0.25329872965812683, "learning_rate": 4.523799528397368e-06, "loss": 0.6233049392700195, "step": 16385, "token_acc": 0.8028820215555639 }, { "epoch": 1.061049922716495, "grad_norm": 0.4260338246822357, "learning_rate": 4.521268910953566e-06, "loss": 0.6202184200286865, "step": 16390, "token_acc": 0.8048204852279397 }, { "epoch": 1.061373623261121, "grad_norm": 0.2692222595214844, "learning_rate": 4.518738417270563e-06, "loss": 0.6376333713531495, "step": 16395, "token_acc": 0.7985496456834037 }, { "epoch": 1.0616973238057472, "grad_norm": 0.25942716002464294, "learning_rate": 4.516208048002531e-06, "loss": 0.6086790084838867, "step": 16400, "token_acc": 0.8053326353236524 }, { "epoch": 1.0620210243503734, "grad_norm": 0.39477020502090454, "learning_rate": 4.513677803803621e-06, "loss": 0.6286334037780762, "step": 16405, "token_acc": 0.8028860587218882 }, { "epoch": 1.0623447248949995, "grad_norm": 0.3111456334590912, "learning_rate": 4.511147685327951e-06, "loss": 0.6310556411743165, "step": 16410, "token_acc": 0.8004617165286969 }, { "epoch": 1.0626684254396257, "grad_norm": 0.3194500207901001, "learning_rate": 4.508617693229596e-06, "loss": 0.6593181610107421, "step": 16415, "token_acc": 0.7937533585855276 }, { "epoch": 1.0629921259842519, "grad_norm": 0.3676314353942871, "learning_rate": 4.5060878281626086e-06, "loss": 0.6243091583251953, "step": 16420, "token_acc": 0.8022543411298785 }, { "epoch": 1.0633158265288782, "grad_norm": 0.27400991320610046, "learning_rate": 4.503558090781009e-06, "loss": 0.6380270481109619, "step": 16425, "token_acc": 0.7971693470600972 }, { "epoch": 1.0636395270735044, "grad_norm": 0.3494253158569336, "learning_rate": 4.501028481738775e-06, "loss": 0.6663628578186035, "step": 16430, "token_acc": 0.7925163585540944 }, { "epoch": 1.0639632276181306, "grad_norm": 0.3297283351421356, "learning_rate": 4.49849900168986e-06, "loss": 0.6292379856109619, "step": 16435, "token_acc": 0.8005436379665002 }, { "epoch": 1.0642869281627567, "grad_norm": 0.28246599435806274, "learning_rate": 4.495969651288181e-06, "loss": 0.63758544921875, "step": 16440, "token_acc": 0.7982018284234537 }, { "epoch": 1.0646106287073829, "grad_norm": 0.30716997385025024, "learning_rate": 4.493440431187624e-06, "loss": 0.6377083778381347, "step": 16445, "token_acc": 0.7983220221236573 }, { "epoch": 1.064934329252009, "grad_norm": 0.363542377948761, "learning_rate": 4.4909113420420335e-06, "loss": 0.6396713256835938, "step": 16450, "token_acc": 0.7982380308179629 }, { "epoch": 1.0652580297966352, "grad_norm": 0.3189302384853363, "learning_rate": 4.48838238450523e-06, "loss": 0.643496322631836, "step": 16455, "token_acc": 0.7966778847100038 }, { "epoch": 1.0655817303412614, "grad_norm": 0.30237820744514465, "learning_rate": 4.485853559230995e-06, "loss": 0.6297380447387695, "step": 16460, "token_acc": 0.8013793848105708 }, { "epoch": 1.0659054308858875, "grad_norm": 0.4215993285179138, "learning_rate": 4.483324866873073e-06, "loss": 0.6292178630828857, "step": 16465, "token_acc": 0.8021111713920202 }, { "epoch": 1.0662291314305137, "grad_norm": 0.3433960974216461, "learning_rate": 4.480796308085183e-06, "loss": 0.6346290111541748, "step": 16470, "token_acc": 0.8003946578542263 }, { "epoch": 1.0665528319751398, "grad_norm": 0.2956365644931793, "learning_rate": 4.478267883520998e-06, "loss": 0.6391337394714356, "step": 16475, "token_acc": 0.7973537395806493 }, { "epoch": 1.066876532519766, "grad_norm": 0.36080172657966614, "learning_rate": 4.475739593834167e-06, "loss": 0.6407111167907715, "step": 16480, "token_acc": 0.7988287134679121 }, { "epoch": 1.0672002330643922, "grad_norm": 0.32474616169929504, "learning_rate": 4.4732114396782975e-06, "loss": 0.6425565719604492, "step": 16485, "token_acc": 0.7974723642963207 }, { "epoch": 1.0675239336090183, "grad_norm": 0.3961443603038788, "learning_rate": 4.4706834217069635e-06, "loss": 0.6559712886810303, "step": 16490, "token_acc": 0.7962369540986929 }, { "epoch": 1.0678476341536445, "grad_norm": 0.32286208868026733, "learning_rate": 4.468155540573706e-06, "loss": 0.663200569152832, "step": 16495, "token_acc": 0.7936665463731505 }, { "epoch": 1.0681713346982706, "grad_norm": 0.31098824739456177, "learning_rate": 4.4656277969320265e-06, "loss": 0.6196110725402832, "step": 16500, "token_acc": 0.8032236735406765 }, { "epoch": 1.0684950352428968, "grad_norm": 0.41812416911125183, "learning_rate": 4.463100191435394e-06, "loss": 0.6448896884918213, "step": 16505, "token_acc": 0.7978767380683953 }, { "epoch": 1.068818735787523, "grad_norm": 0.28256651759147644, "learning_rate": 4.460572724737242e-06, "loss": 0.6219181537628173, "step": 16510, "token_acc": 0.8033975688911724 }, { "epoch": 1.0691424363321491, "grad_norm": 0.2957235276699066, "learning_rate": 4.458045397490966e-06, "loss": 0.6454328536987305, "step": 16515, "token_acc": 0.7971907770259437 }, { "epoch": 1.0694661368767753, "grad_norm": 0.2880256772041321, "learning_rate": 4.455518210349928e-06, "loss": 0.6344416618347168, "step": 16520, "token_acc": 0.7996417426750302 }, { "epoch": 1.0697898374214014, "grad_norm": 0.39887309074401855, "learning_rate": 4.452991163967449e-06, "loss": 0.6249287605285645, "step": 16525, "token_acc": 0.8020030627871363 }, { "epoch": 1.0701135379660276, "grad_norm": 0.3311615288257599, "learning_rate": 4.450464258996822e-06, "loss": 0.6361305236816406, "step": 16530, "token_acc": 0.800091383973227 }, { "epoch": 1.0704372385106538, "grad_norm": 0.32912492752075195, "learning_rate": 4.447937496091294e-06, "loss": 0.6311804771423339, "step": 16535, "token_acc": 0.7993304369345835 }, { "epoch": 1.07076093905528, "grad_norm": 0.454203337430954, "learning_rate": 4.445410875904082e-06, "loss": 0.6410037994384765, "step": 16540, "token_acc": 0.7966238885833802 }, { "epoch": 1.071084639599906, "grad_norm": 0.35878536105155945, "learning_rate": 4.442884399088364e-06, "loss": 0.6302627563476563, "step": 16545, "token_acc": 0.8006225999828157 }, { "epoch": 1.0714083401445322, "grad_norm": 0.36674582958221436, "learning_rate": 4.44035806629728e-06, "loss": 0.6637833595275879, "step": 16550, "token_acc": 0.7912749543770392 }, { "epoch": 1.0717320406891584, "grad_norm": 0.3073451817035675, "learning_rate": 4.437831878183932e-06, "loss": 0.6529882431030274, "step": 16555, "token_acc": 0.7939448554323756 }, { "epoch": 1.0720557412337846, "grad_norm": 0.2522496283054352, "learning_rate": 4.4353058354013875e-06, "loss": 0.6495131492614746, "step": 16560, "token_acc": 0.7965554813539067 }, { "epoch": 1.0723794417784107, "grad_norm": 0.2645590603351593, "learning_rate": 4.432779938602678e-06, "loss": 0.6409818172454834, "step": 16565, "token_acc": 0.7979818243826108 }, { "epoch": 1.0727031423230369, "grad_norm": 0.2867981791496277, "learning_rate": 4.43025418844079e-06, "loss": 0.6209900856018067, "step": 16570, "token_acc": 0.8031286639925949 }, { "epoch": 1.073026842867663, "grad_norm": 0.38946086168289185, "learning_rate": 4.427728585568677e-06, "loss": 0.6070923328399658, "step": 16575, "token_acc": 0.8061342085576995 }, { "epoch": 1.0733505434122892, "grad_norm": 0.37189459800720215, "learning_rate": 4.425203130639257e-06, "loss": 0.6117024421691895, "step": 16580, "token_acc": 0.8052358141330279 }, { "epoch": 1.0736742439569156, "grad_norm": 0.4139450788497925, "learning_rate": 4.422677824305403e-06, "loss": 0.6318854331970215, "step": 16585, "token_acc": 0.8000841568535237 }, { "epoch": 1.0739979445015417, "grad_norm": 0.2826310396194458, "learning_rate": 4.420152667219953e-06, "loss": 0.6155695438385009, "step": 16590, "token_acc": 0.8044017590723408 }, { "epoch": 1.074321645046168, "grad_norm": 0.3093758523464203, "learning_rate": 4.4176276600357116e-06, "loss": 0.6294687271118165, "step": 16595, "token_acc": 0.8025076569678408 }, { "epoch": 1.074645345590794, "grad_norm": 0.25719979405403137, "learning_rate": 4.415102803405434e-06, "loss": 0.6384210109710693, "step": 16600, "token_acc": 0.7987856725301589 }, { "epoch": 1.0749690461354202, "grad_norm": 0.3256029784679413, "learning_rate": 4.412578097981843e-06, "loss": 0.655895471572876, "step": 16605, "token_acc": 0.7942674592891802 }, { "epoch": 1.0752927466800464, "grad_norm": 0.29941385984420776, "learning_rate": 4.410053544417623e-06, "loss": 0.6427043914794922, "step": 16610, "token_acc": 0.7973842766230309 }, { "epoch": 1.0756164472246725, "grad_norm": 0.37795382738113403, "learning_rate": 4.4075291433654194e-06, "loss": 0.6467493057250977, "step": 16615, "token_acc": 0.797459879347685 }, { "epoch": 1.0759401477692987, "grad_norm": 0.23961585760116577, "learning_rate": 4.4050048954778314e-06, "loss": 0.6231935977935791, "step": 16620, "token_acc": 0.8020931334064351 }, { "epoch": 1.0762638483139249, "grad_norm": 0.29769328236579895, "learning_rate": 4.402480801407427e-06, "loss": 0.6540305614471436, "step": 16625, "token_acc": 0.79462285287528 }, { "epoch": 1.076587548858551, "grad_norm": 0.33686545491218567, "learning_rate": 4.3999568618067315e-06, "loss": 0.6424110889434814, "step": 16630, "token_acc": 0.7976713465024116 }, { "epoch": 1.0769112494031772, "grad_norm": 0.32580268383026123, "learning_rate": 4.397433077328226e-06, "loss": 0.6461454391479492, "step": 16635, "token_acc": 0.7964304006373777 }, { "epoch": 1.0772349499478033, "grad_norm": 0.3688269853591919, "learning_rate": 4.394909448624359e-06, "loss": 0.6384961128234863, "step": 16640, "token_acc": 0.8009927322519486 }, { "epoch": 1.0775586504924295, "grad_norm": 0.37156155705451965, "learning_rate": 4.392385976347535e-06, "loss": 0.6339005470275879, "step": 16645, "token_acc": 0.7998018846358995 }, { "epoch": 1.0778823510370557, "grad_norm": 0.2633236050605774, "learning_rate": 4.389862661150114e-06, "loss": 0.6332530975341797, "step": 16650, "token_acc": 0.7995565712726405 }, { "epoch": 1.0782060515816818, "grad_norm": 0.3278004229068756, "learning_rate": 4.387339503684421e-06, "loss": 0.6395978927612305, "step": 16655, "token_acc": 0.7989997269560932 }, { "epoch": 1.078529752126308, "grad_norm": 0.3365667462348938, "learning_rate": 4.3848165046027415e-06, "loss": 0.6348399639129638, "step": 16660, "token_acc": 0.8000844802259531 }, { "epoch": 1.0788534526709341, "grad_norm": 0.3870064616203308, "learning_rate": 4.382293664557317e-06, "loss": 0.6337923049926758, "step": 16665, "token_acc": 0.7998382393921064 }, { "epoch": 1.0791771532155603, "grad_norm": 0.3054414689540863, "learning_rate": 4.379770984200343e-06, "loss": 0.6222289562225342, "step": 16670, "token_acc": 0.8022469800337986 }, { "epoch": 1.0795008537601865, "grad_norm": 0.405843049287796, "learning_rate": 4.377248464183983e-06, "loss": 0.630165958404541, "step": 16675, "token_acc": 0.799429394689964 }, { "epoch": 1.0798245543048126, "grad_norm": 0.22899392247200012, "learning_rate": 4.374726105160356e-06, "loss": 0.6496975898742676, "step": 16680, "token_acc": 0.7967046494744484 }, { "epoch": 1.0801482548494388, "grad_norm": 0.28668490052223206, "learning_rate": 4.3722039077815346e-06, "loss": 0.65682053565979, "step": 16685, "token_acc": 0.7944903544578586 }, { "epoch": 1.080471955394065, "grad_norm": 0.32972317934036255, "learning_rate": 4.369681872699554e-06, "loss": 0.6427178859710694, "step": 16690, "token_acc": 0.797983471742337 }, { "epoch": 1.080795655938691, "grad_norm": 0.35441985726356506, "learning_rate": 4.367160000566409e-06, "loss": 0.6377843379974365, "step": 16695, "token_acc": 0.7998006850625994 }, { "epoch": 1.0811193564833173, "grad_norm": 0.275566965341568, "learning_rate": 4.364638292034048e-06, "loss": 0.6146842956542968, "step": 16700, "token_acc": 0.802943520101341 }, { "epoch": 1.0814430570279434, "grad_norm": 0.30713576078414917, "learning_rate": 4.362116747754379e-06, "loss": 0.6203895092010498, "step": 16705, "token_acc": 0.803361098349413 }, { "epoch": 1.0817667575725696, "grad_norm": 0.260280966758728, "learning_rate": 4.359595368379269e-06, "loss": 0.6469169616699219, "step": 16710, "token_acc": 0.7966773232778643 }, { "epoch": 1.0820904581171957, "grad_norm": 0.33365505933761597, "learning_rate": 4.3570741545605395e-06, "loss": 0.6365656852722168, "step": 16715, "token_acc": 0.7987289651538707 }, { "epoch": 1.082414158661822, "grad_norm": 0.31203195452690125, "learning_rate": 4.354553106949972e-06, "loss": 0.6172197341918946, "step": 16720, "token_acc": 0.8016870772138195 }, { "epoch": 1.082737859206448, "grad_norm": 0.3817504346370697, "learning_rate": 4.3520322261993016e-06, "loss": 0.6566632270812989, "step": 16725, "token_acc": 0.7946573588703256 }, { "epoch": 1.0830615597510742, "grad_norm": 0.43125367164611816, "learning_rate": 4.349511512960225e-06, "loss": 0.638688611984253, "step": 16730, "token_acc": 0.7986393163269229 }, { "epoch": 1.0833852602957004, "grad_norm": 0.3095104992389679, "learning_rate": 4.3469909678843905e-06, "loss": 0.6498106479644775, "step": 16735, "token_acc": 0.7953469307851366 }, { "epoch": 1.0837089608403265, "grad_norm": 0.36629894375801086, "learning_rate": 4.344470591623407e-06, "loss": 0.6647075653076172, "step": 16740, "token_acc": 0.7916115663044812 }, { "epoch": 1.0840326613849527, "grad_norm": 0.2218264937400818, "learning_rate": 4.341950384828838e-06, "loss": 0.6512644767761231, "step": 16745, "token_acc": 0.7945192885682968 }, { "epoch": 1.0843563619295788, "grad_norm": 0.3209570348262787, "learning_rate": 4.339430348152204e-06, "loss": 0.6566817760467529, "step": 16750, "token_acc": 0.7936089825457642 }, { "epoch": 1.084680062474205, "grad_norm": 0.2920648157596588, "learning_rate": 4.3369104822449785e-06, "loss": 0.6262044906616211, "step": 16755, "token_acc": 0.8017613291974186 }, { "epoch": 1.0850037630188312, "grad_norm": 0.35042044520378113, "learning_rate": 4.3343907877585935e-06, "loss": 0.6613402366638184, "step": 16760, "token_acc": 0.7935159997706582 }, { "epoch": 1.0853274635634573, "grad_norm": 0.3193618953227997, "learning_rate": 4.33187126534444e-06, "loss": 0.640734052658081, "step": 16765, "token_acc": 0.7981386242180009 }, { "epoch": 1.0856511641080837, "grad_norm": 0.36012306809425354, "learning_rate": 4.329351915653857e-06, "loss": 0.6515525817871094, "step": 16770, "token_acc": 0.7944013173370972 }, { "epoch": 1.0859748646527099, "grad_norm": 0.43937063217163086, "learning_rate": 4.326832739338142e-06, "loss": 0.6384566307067872, "step": 16775, "token_acc": 0.7974514688773428 }, { "epoch": 1.086298565197336, "grad_norm": 0.3062227666378021, "learning_rate": 4.324313737048555e-06, "loss": 0.6504551410675049, "step": 16780, "token_acc": 0.7967888257743331 }, { "epoch": 1.0866222657419622, "grad_norm": 0.3467024266719818, "learning_rate": 4.321794909436296e-06, "loss": 0.6260688304901123, "step": 16785, "token_acc": 0.8020803619405212 }, { "epoch": 1.0869459662865883, "grad_norm": 0.35973060131073, "learning_rate": 4.319276257152534e-06, "loss": 0.6642887115478515, "step": 16790, "token_acc": 0.7929814869708157 }, { "epoch": 1.0872696668312145, "grad_norm": 0.24780744314193726, "learning_rate": 4.3167577808483845e-06, "loss": 0.6198185443878174, "step": 16795, "token_acc": 0.8018194559800664 }, { "epoch": 1.0875933673758407, "grad_norm": 0.3393402099609375, "learning_rate": 4.314239481174922e-06, "loss": 0.6262846469879151, "step": 16800, "token_acc": 0.8014912997353949 }, { "epoch": 1.0879170679204668, "grad_norm": 0.3847734034061432, "learning_rate": 4.31172135878317e-06, "loss": 0.6582685470581054, "step": 16805, "token_acc": 0.7946822632050616 }, { "epoch": 1.088240768465093, "grad_norm": 0.3433970510959625, "learning_rate": 4.309203414324113e-06, "loss": 0.6368390560150147, "step": 16810, "token_acc": 0.8001294390775388 }, { "epoch": 1.0885644690097191, "grad_norm": 0.28165388107299805, "learning_rate": 4.3066856484486854e-06, "loss": 0.6324426651000976, "step": 16815, "token_acc": 0.8005083007206372 }, { "epoch": 1.0888881695543453, "grad_norm": 0.32650548219680786, "learning_rate": 4.304168061807773e-06, "loss": 0.6261529922485352, "step": 16820, "token_acc": 0.8028691518126018 }, { "epoch": 1.0892118700989715, "grad_norm": 0.35719284415245056, "learning_rate": 4.3016506550522205e-06, "loss": 0.636882209777832, "step": 16825, "token_acc": 0.7983106162411211 }, { "epoch": 1.0895355706435976, "grad_norm": 0.4680505692958832, "learning_rate": 4.299133428832824e-06, "loss": 0.6511064529418945, "step": 16830, "token_acc": 0.7955110718870346 }, { "epoch": 1.0898592711882238, "grad_norm": 0.3542165458202362, "learning_rate": 4.296616383800334e-06, "loss": 0.6265166282653809, "step": 16835, "token_acc": 0.8012245100102765 }, { "epoch": 1.09018297173285, "grad_norm": 0.4049393832683563, "learning_rate": 4.294099520605449e-06, "loss": 0.6166383743286132, "step": 16840, "token_acc": 0.8036129244679706 }, { "epoch": 1.090506672277476, "grad_norm": 0.2792539894580841, "learning_rate": 4.291582839898827e-06, "loss": 0.6247190952301025, "step": 16845, "token_acc": 0.8030894232764217 }, { "epoch": 1.0908303728221023, "grad_norm": 0.21383777260780334, "learning_rate": 4.289066342331079e-06, "loss": 0.6174498558044433, "step": 16850, "token_acc": 0.8031635759239547 }, { "epoch": 1.0911540733667284, "grad_norm": 0.3244486451148987, "learning_rate": 4.28655002855276e-06, "loss": 0.6266671180725097, "step": 16855, "token_acc": 0.8007132080647373 }, { "epoch": 1.0914777739113546, "grad_norm": 0.35654714703559875, "learning_rate": 4.284033899214388e-06, "loss": 0.6273147583007812, "step": 16860, "token_acc": 0.799597364568082 }, { "epoch": 1.0918014744559807, "grad_norm": 0.3923335373401642, "learning_rate": 4.281517954966428e-06, "loss": 0.6234444618225098, "step": 16865, "token_acc": 0.8022712510738157 }, { "epoch": 1.092125175000607, "grad_norm": 0.3285733461380005, "learning_rate": 4.279002196459295e-06, "loss": 0.5838597297668457, "step": 16870, "token_acc": 0.8113637223855364 }, { "epoch": 1.092448875545233, "grad_norm": 0.32733649015426636, "learning_rate": 4.276486624343362e-06, "loss": 0.6379953384399414, "step": 16875, "token_acc": 0.7973810203661524 }, { "epoch": 1.0927725760898592, "grad_norm": 0.39188992977142334, "learning_rate": 4.273971239268949e-06, "loss": 0.6625822067260743, "step": 16880, "token_acc": 0.7910279246553248 }, { "epoch": 1.0930962766344854, "grad_norm": 0.2613958716392517, "learning_rate": 4.271456041886332e-06, "loss": 0.6408207893371582, "step": 16885, "token_acc": 0.7967164360281622 }, { "epoch": 1.0934199771791115, "grad_norm": 0.36299261450767517, "learning_rate": 4.2689410328457316e-06, "loss": 0.6349635601043702, "step": 16890, "token_acc": 0.8018063655233765 }, { "epoch": 1.0937436777237377, "grad_norm": 0.3743771016597748, "learning_rate": 4.266426212797326e-06, "loss": 0.6109324932098389, "step": 16895, "token_acc": 0.806814240939101 }, { "epoch": 1.0940673782683639, "grad_norm": 0.42411452531814575, "learning_rate": 4.263911582391245e-06, "loss": 0.6601704597473145, "step": 16900, "token_acc": 0.7923994489432479 }, { "epoch": 1.09439107881299, "grad_norm": 0.30550193786621094, "learning_rate": 4.261397142277562e-06, "loss": 0.6559443473815918, "step": 16905, "token_acc": 0.7938045191150377 }, { "epoch": 1.0947147793576162, "grad_norm": 0.33040061593055725, "learning_rate": 4.258882893106308e-06, "loss": 0.6301165580749511, "step": 16910, "token_acc": 0.7988235532200508 }, { "epoch": 1.0950384799022423, "grad_norm": 0.26064568758010864, "learning_rate": 4.256368835527467e-06, "loss": 0.6338404178619385, "step": 16915, "token_acc": 0.7983721910567787 }, { "epoch": 1.0953621804468685, "grad_norm": 0.34315377473831177, "learning_rate": 4.253854970190962e-06, "loss": 0.644322395324707, "step": 16920, "token_acc": 0.7988139996126801 }, { "epoch": 1.0956858809914947, "grad_norm": 0.3177453279495239, "learning_rate": 4.251341297746676e-06, "loss": 0.6567091941833496, "step": 16925, "token_acc": 0.7954679509200864 }, { "epoch": 1.096009581536121, "grad_norm": 0.3363495469093323, "learning_rate": 4.248827818844442e-06, "loss": 0.6258600234985352, "step": 16930, "token_acc": 0.8039020421051353 }, { "epoch": 1.0963332820807472, "grad_norm": 0.30895090103149414, "learning_rate": 4.246314534134039e-06, "loss": 0.6373097419738769, "step": 16935, "token_acc": 0.7985820327369623 }, { "epoch": 1.0966569826253734, "grad_norm": 0.22442783415317535, "learning_rate": 4.2438014442651955e-06, "loss": 0.6306097030639648, "step": 16940, "token_acc": 0.8003272921174084 }, { "epoch": 1.0969806831699995, "grad_norm": 0.2969503104686737, "learning_rate": 4.241288549887595e-06, "loss": 0.6306890487670899, "step": 16945, "token_acc": 0.800621341310379 }, { "epoch": 1.0973043837146257, "grad_norm": 0.28628188371658325, "learning_rate": 4.238775851650864e-06, "loss": 0.6231947422027588, "step": 16950, "token_acc": 0.803609356467051 }, { "epoch": 1.0976280842592518, "grad_norm": 0.3563075065612793, "learning_rate": 4.236263350204583e-06, "loss": 0.6347060680389405, "step": 16955, "token_acc": 0.8007345821229424 }, { "epoch": 1.097951784803878, "grad_norm": 0.3426429033279419, "learning_rate": 4.233751046198278e-06, "loss": 0.6168000221252441, "step": 16960, "token_acc": 0.8041970282395042 }, { "epoch": 1.0982754853485042, "grad_norm": 0.2831653356552124, "learning_rate": 4.231238940281427e-06, "loss": 0.6125071525573731, "step": 16965, "token_acc": 0.8062891420810383 }, { "epoch": 1.0985991858931303, "grad_norm": 0.37958791851997375, "learning_rate": 4.228727033103457e-06, "loss": 0.6210590362548828, "step": 16970, "token_acc": 0.8034804029940309 }, { "epoch": 1.0989228864377565, "grad_norm": 0.3463228940963745, "learning_rate": 4.22621532531374e-06, "loss": 0.6089860916137695, "step": 16975, "token_acc": 0.8063581938366038 }, { "epoch": 1.0992465869823826, "grad_norm": 0.1844792664051056, "learning_rate": 4.223703817561599e-06, "loss": 0.6119343757629394, "step": 16980, "token_acc": 0.8054910981523705 }, { "epoch": 1.0995702875270088, "grad_norm": 0.3938171863555908, "learning_rate": 4.221192510496306e-06, "loss": 0.6371758460998536, "step": 16985, "token_acc": 0.7981793597027972 }, { "epoch": 1.099893988071635, "grad_norm": 0.31940731406211853, "learning_rate": 4.21868140476708e-06, "loss": 0.6010542869567871, "step": 16990, "token_acc": 0.809809527392193 }, { "epoch": 1.1002176886162611, "grad_norm": 0.3336130976676941, "learning_rate": 4.216170501023086e-06, "loss": 0.6458580970764161, "step": 16995, "token_acc": 0.7963712471931916 }, { "epoch": 1.1005413891608873, "grad_norm": 0.3336929678916931, "learning_rate": 4.213659799913442e-06, "loss": 0.6267448425292969, "step": 17000, "token_acc": 0.8012050921940833 }, { "epoch": 1.1008650897055134, "grad_norm": 0.3369252681732178, "learning_rate": 4.2111493020872085e-06, "loss": 0.6354800224304199, "step": 17005, "token_acc": 0.8008363343754534 }, { "epoch": 1.1011887902501396, "grad_norm": 0.23680822551250458, "learning_rate": 4.2086390081933944e-06, "loss": 0.6229899406433106, "step": 17010, "token_acc": 0.8027499193627028 }, { "epoch": 1.1015124907947658, "grad_norm": 0.24158859252929688, "learning_rate": 4.206128918880959e-06, "loss": 0.6100326538085937, "step": 17015, "token_acc": 0.8058334574302463 }, { "epoch": 1.101836191339392, "grad_norm": 0.3213755488395691, "learning_rate": 4.203619034798807e-06, "loss": 0.6236833572387696, "step": 17020, "token_acc": 0.8036689482840849 }, { "epoch": 1.102159891884018, "grad_norm": 0.36585691571235657, "learning_rate": 4.201109356595786e-06, "loss": 0.6218218803405762, "step": 17025, "token_acc": 0.8019913803855268 }, { "epoch": 1.1024835924286442, "grad_norm": 0.3242790997028351, "learning_rate": 4.198599884920697e-06, "loss": 0.642811918258667, "step": 17030, "token_acc": 0.7968490176003756 }, { "epoch": 1.1028072929732704, "grad_norm": 0.28507721424102783, "learning_rate": 4.196090620422286e-06, "loss": 0.6447638988494873, "step": 17035, "token_acc": 0.7965404989690448 }, { "epoch": 1.1031309935178966, "grad_norm": 0.31926652789115906, "learning_rate": 4.19358156374924e-06, "loss": 0.620182466506958, "step": 17040, "token_acc": 0.8026892761048872 }, { "epoch": 1.1034546940625227, "grad_norm": 0.23245859146118164, "learning_rate": 4.191072715550198e-06, "loss": 0.6285380363464356, "step": 17045, "token_acc": 0.8016291964150084 }, { "epoch": 1.1037783946071489, "grad_norm": 0.33326417207717896, "learning_rate": 4.188564076473745e-06, "loss": 0.6097933769226074, "step": 17050, "token_acc": 0.806344696969697 }, { "epoch": 1.104102095151775, "grad_norm": 0.2533007264137268, "learning_rate": 4.186055647168409e-06, "loss": 0.6313573837280273, "step": 17055, "token_acc": 0.7997242713118021 }, { "epoch": 1.1044257956964012, "grad_norm": 0.22252702713012695, "learning_rate": 4.183547428282664e-06, "loss": 0.6430218696594239, "step": 17060, "token_acc": 0.7981628144012054 }, { "epoch": 1.1047494962410274, "grad_norm": 0.24430829286575317, "learning_rate": 4.181039420464932e-06, "loss": 0.6449082374572754, "step": 17065, "token_acc": 0.7967217649906633 }, { "epoch": 1.1050731967856535, "grad_norm": 0.2961544394493103, "learning_rate": 4.1785316243635815e-06, "loss": 0.6551376342773437, "step": 17070, "token_acc": 0.7941385984247735 }, { "epoch": 1.1053968973302797, "grad_norm": 0.28937795758247375, "learning_rate": 4.176024040626919e-06, "loss": 0.6428128242492676, "step": 17075, "token_acc": 0.7967162048153676 }, { "epoch": 1.1057205978749058, "grad_norm": 0.3190450370311737, "learning_rate": 4.173516669903204e-06, "loss": 0.6468802928924561, "step": 17080, "token_acc": 0.7964127761186884 }, { "epoch": 1.106044298419532, "grad_norm": 0.33403730392456055, "learning_rate": 4.17100951284064e-06, "loss": 0.634453010559082, "step": 17085, "token_acc": 0.7997954644865973 }, { "epoch": 1.1063679989641582, "grad_norm": 0.27143192291259766, "learning_rate": 4.168502570087368e-06, "loss": 0.6227934837341309, "step": 17090, "token_acc": 0.8026020310150438 }, { "epoch": 1.1066916995087843, "grad_norm": 0.21216587722301483, "learning_rate": 4.165995842291482e-06, "loss": 0.6401435375213623, "step": 17095, "token_acc": 0.7991778539694804 }, { "epoch": 1.1070154000534105, "grad_norm": 0.3082888126373291, "learning_rate": 4.163489330101017e-06, "loss": 0.6318731784820557, "step": 17100, "token_acc": 0.798818852513407 }, { "epoch": 1.1073391005980366, "grad_norm": 0.29453128576278687, "learning_rate": 4.160983034163955e-06, "loss": 0.6340540885925293, "step": 17105, "token_acc": 0.8000831480577698 }, { "epoch": 1.107662801142663, "grad_norm": 0.265860378742218, "learning_rate": 4.158476955128213e-06, "loss": 0.618009090423584, "step": 17110, "token_acc": 0.8050235174319934 }, { "epoch": 1.1079865016872892, "grad_norm": 0.33351099491119385, "learning_rate": 4.1559710936416645e-06, "loss": 0.6165409088134766, "step": 17115, "token_acc": 0.8032901490770074 }, { "epoch": 1.1083102022319153, "grad_norm": 0.3892093896865845, "learning_rate": 4.153465450352121e-06, "loss": 0.6158510684967041, "step": 17120, "token_acc": 0.8035669501787774 }, { "epoch": 1.1086339027765415, "grad_norm": 0.34437504410743713, "learning_rate": 4.150960025907332e-06, "loss": 0.6529333114624023, "step": 17125, "token_acc": 0.7943340115824072 }, { "epoch": 1.1089576033211677, "grad_norm": 0.3143128752708435, "learning_rate": 4.148454820954999e-06, "loss": 0.6378551006317139, "step": 17130, "token_acc": 0.7979519417346694 }, { "epoch": 1.1092813038657938, "grad_norm": 0.37566807866096497, "learning_rate": 4.145949836142768e-06, "loss": 0.6329913139343262, "step": 17135, "token_acc": 0.7996287067559841 }, { "epoch": 1.10960500441042, "grad_norm": 0.2564731240272522, "learning_rate": 4.143445072118215e-06, "loss": 0.6177279949188232, "step": 17140, "token_acc": 0.8034684035739166 }, { "epoch": 1.1099287049550461, "grad_norm": 0.3297005593776703, "learning_rate": 4.1409405295288725e-06, "loss": 0.6314210891723633, "step": 17145, "token_acc": 0.7997763899956143 }, { "epoch": 1.1102524054996723, "grad_norm": 0.24731044471263885, "learning_rate": 4.1384362090222105e-06, "loss": 0.6295613765716552, "step": 17150, "token_acc": 0.8006753510590109 }, { "epoch": 1.1105761060442985, "grad_norm": 0.2933962941169739, "learning_rate": 4.135932111245644e-06, "loss": 0.6293589115142822, "step": 17155, "token_acc": 0.803569293712889 }, { "epoch": 1.1108998065889246, "grad_norm": 0.33815303444862366, "learning_rate": 4.1334282368465235e-06, "loss": 0.6443977355957031, "step": 17160, "token_acc": 0.7969887811228844 }, { "epoch": 1.1112235071335508, "grad_norm": 0.34819114208221436, "learning_rate": 4.1309245864721495e-06, "loss": 0.6202760219573975, "step": 17165, "token_acc": 0.8034482071580848 }, { "epoch": 1.111547207678177, "grad_norm": 0.3030586540699005, "learning_rate": 4.128421160769763e-06, "loss": 0.6303119659423828, "step": 17170, "token_acc": 0.8002360016748506 }, { "epoch": 1.111870908222803, "grad_norm": 0.3705332577228546, "learning_rate": 4.125917960386542e-06, "loss": 0.6582852363586426, "step": 17175, "token_acc": 0.7928600661527417 }, { "epoch": 1.1121946087674293, "grad_norm": 0.2869294285774231, "learning_rate": 4.123414985969613e-06, "loss": 0.6211794853210449, "step": 17180, "token_acc": 0.8037588990454736 }, { "epoch": 1.1125183093120554, "grad_norm": 0.35927608609199524, "learning_rate": 4.120912238166041e-06, "loss": 0.6273469924926758, "step": 17185, "token_acc": 0.8009166150990099 }, { "epoch": 1.1128420098566816, "grad_norm": 0.2890036106109619, "learning_rate": 4.118409717622829e-06, "loss": 0.6459012031555176, "step": 17190, "token_acc": 0.797397583279339 }, { "epoch": 1.1131657104013077, "grad_norm": 0.36393991112709045, "learning_rate": 4.115907424986928e-06, "loss": 0.66348295211792, "step": 17195, "token_acc": 0.7936246184038378 }, { "epoch": 1.113489410945934, "grad_norm": 0.3224203586578369, "learning_rate": 4.1134053609052235e-06, "loss": 0.6306861400604248, "step": 17200, "token_acc": 0.8000315138463963 }, { "epoch": 1.11381311149056, "grad_norm": 0.34134453535079956, "learning_rate": 4.110903526024549e-06, "loss": 0.6194273948669433, "step": 17205, "token_acc": 0.8028965030024726 }, { "epoch": 1.1141368120351862, "grad_norm": 0.35099703073501587, "learning_rate": 4.108401920991673e-06, "loss": 0.6167825698852539, "step": 17210, "token_acc": 0.8045821921486493 }, { "epoch": 1.1144605125798124, "grad_norm": 0.26279664039611816, "learning_rate": 4.105900546453304e-06, "loss": 0.656202745437622, "step": 17215, "token_acc": 0.79537616388542 }, { "epoch": 1.1147842131244385, "grad_norm": 0.3224867582321167, "learning_rate": 4.103399403056097e-06, "loss": 0.6536104679107666, "step": 17220, "token_acc": 0.7936198733483448 }, { "epoch": 1.1151079136690647, "grad_norm": 0.3142645061016083, "learning_rate": 4.1008984914466436e-06, "loss": 0.6276374340057373, "step": 17225, "token_acc": 0.8005380526384027 }, { "epoch": 1.1154316142136909, "grad_norm": 0.2567101716995239, "learning_rate": 4.098397812271472e-06, "loss": 0.6398070335388184, "step": 17230, "token_acc": 0.7989157065497355 }, { "epoch": 1.115755314758317, "grad_norm": 0.25446224212646484, "learning_rate": 4.095897366177056e-06, "loss": 0.619364595413208, "step": 17235, "token_acc": 0.802154814983956 }, { "epoch": 1.1160790153029432, "grad_norm": 0.3808722198009491, "learning_rate": 4.093397153809809e-06, "loss": 0.6182703495025634, "step": 17240, "token_acc": 0.8026948872472783 }, { "epoch": 1.1164027158475693, "grad_norm": 0.36085081100463867, "learning_rate": 4.090897175816079e-06, "loss": 0.606046199798584, "step": 17245, "token_acc": 0.806621694967822 }, { "epoch": 1.1167264163921955, "grad_norm": 0.23902882635593414, "learning_rate": 4.0883974328421546e-06, "loss": 0.6337944507598877, "step": 17250, "token_acc": 0.7989914598396256 }, { "epoch": 1.1170501169368217, "grad_norm": 0.30995041131973267, "learning_rate": 4.085897925534272e-06, "loss": 0.6324714660644531, "step": 17255, "token_acc": 0.8022577429003312 }, { "epoch": 1.1173738174814478, "grad_norm": 0.23089738190174103, "learning_rate": 4.083398654538592e-06, "loss": 0.630949592590332, "step": 17260, "token_acc": 0.8019973498340607 }, { "epoch": 1.117697518026074, "grad_norm": 0.32197821140289307, "learning_rate": 4.080899620501227e-06, "loss": 0.6470325469970704, "step": 17265, "token_acc": 0.7952263021391939 }, { "epoch": 1.1180212185707004, "grad_norm": 0.35166993737220764, "learning_rate": 4.078400824068224e-06, "loss": 0.6451519012451172, "step": 17270, "token_acc": 0.7957653664846044 }, { "epoch": 1.1183449191153265, "grad_norm": 0.19652222096920013, "learning_rate": 4.075902265885563e-06, "loss": 0.6258218288421631, "step": 17275, "token_acc": 0.8019049220495328 }, { "epoch": 1.1186686196599527, "grad_norm": 0.3487391471862793, "learning_rate": 4.07340394659917e-06, "loss": 0.6332843780517579, "step": 17280, "token_acc": 0.7996993541682133 }, { "epoch": 1.1189923202045788, "grad_norm": 0.34234845638275146, "learning_rate": 4.070905866854907e-06, "loss": 0.602126932144165, "step": 17285, "token_acc": 0.807728717952066 }, { "epoch": 1.119316020749205, "grad_norm": 0.3541707992553711, "learning_rate": 4.068408027298576e-06, "loss": 0.6243826866149902, "step": 17290, "token_acc": 0.8007499328075938 }, { "epoch": 1.1196397212938312, "grad_norm": 0.48753878474235535, "learning_rate": 4.065910428575909e-06, "loss": 0.635319185256958, "step": 17295, "token_acc": 0.8002903848705061 }, { "epoch": 1.1199634218384573, "grad_norm": 0.3420034348964691, "learning_rate": 4.0634130713325845e-06, "loss": 0.62655611038208, "step": 17300, "token_acc": 0.8017546215478268 }, { "epoch": 1.1202871223830835, "grad_norm": 0.36154624819755554, "learning_rate": 4.0609159562142166e-06, "loss": 0.6323591709136963, "step": 17305, "token_acc": 0.8005942332365453 }, { "epoch": 1.1206108229277096, "grad_norm": 0.34610792994499207, "learning_rate": 4.058419083866352e-06, "loss": 0.6379585266113281, "step": 17310, "token_acc": 0.7998367859384808 }, { "epoch": 1.1209345234723358, "grad_norm": 0.3322572708129883, "learning_rate": 4.055922454934479e-06, "loss": 0.6088457584381104, "step": 17315, "token_acc": 0.8057325447696246 }, { "epoch": 1.121258224016962, "grad_norm": 0.3033502399921417, "learning_rate": 4.053426070064023e-06, "loss": 0.6297279834747315, "step": 17320, "token_acc": 0.8005451860333487 }, { "epoch": 1.1215819245615881, "grad_norm": 0.27377256751060486, "learning_rate": 4.050929929900348e-06, "loss": 0.6102638721466065, "step": 17325, "token_acc": 0.8053758120586288 }, { "epoch": 1.1219056251062143, "grad_norm": 0.3317011296749115, "learning_rate": 4.048434035088748e-06, "loss": 0.6327754497528076, "step": 17330, "token_acc": 0.8006220611285266 }, { "epoch": 1.1222293256508404, "grad_norm": 0.28884291648864746, "learning_rate": 4.045938386274458e-06, "loss": 0.631410789489746, "step": 17335, "token_acc": 0.8006603412921837 }, { "epoch": 1.1225530261954666, "grad_norm": 0.29030299186706543, "learning_rate": 4.043442984102653e-06, "loss": 0.6226320743560791, "step": 17340, "token_acc": 0.8029870070424837 }, { "epoch": 1.1228767267400928, "grad_norm": 0.3240726590156555, "learning_rate": 4.040947829218436e-06, "loss": 0.604121208190918, "step": 17345, "token_acc": 0.8069638714403939 }, { "epoch": 1.123200427284719, "grad_norm": 0.21787533164024353, "learning_rate": 4.0384529222668514e-06, "loss": 0.643525218963623, "step": 17350, "token_acc": 0.7965756788997264 }, { "epoch": 1.123524127829345, "grad_norm": 0.3121788203716278, "learning_rate": 4.035958263892882e-06, "loss": 0.6029401779174804, "step": 17355, "token_acc": 0.8071505327619467 }, { "epoch": 1.1238478283739712, "grad_norm": 0.29397478699684143, "learning_rate": 4.033463854741438e-06, "loss": 0.6683907508850098, "step": 17360, "token_acc": 0.7907454104691249 }, { "epoch": 1.1241715289185974, "grad_norm": 0.2800607979297638, "learning_rate": 4.030969695457372e-06, "loss": 0.6243995666503906, "step": 17365, "token_acc": 0.8020304238818379 }, { "epoch": 1.1244952294632236, "grad_norm": 0.3622298538684845, "learning_rate": 4.028475786685472e-06, "loss": 0.6212163925170898, "step": 17370, "token_acc": 0.8022495673908864 }, { "epoch": 1.1248189300078497, "grad_norm": 0.25284916162490845, "learning_rate": 4.025982129070458e-06, "loss": 0.6351929187774659, "step": 17375, "token_acc": 0.8011552283721104 }, { "epoch": 1.1251426305524759, "grad_norm": 0.2933962643146515, "learning_rate": 4.023488723256985e-06, "loss": 0.6243463039398194, "step": 17380, "token_acc": 0.8009872806990345 }, { "epoch": 1.125466331097102, "grad_norm": 0.3925606608390808, "learning_rate": 4.020995569889645e-06, "loss": 0.6534315586090088, "step": 17385, "token_acc": 0.7947711969218084 }, { "epoch": 1.1257900316417282, "grad_norm": 0.2891114354133606, "learning_rate": 4.018502669612967e-06, "loss": 0.6370165348052979, "step": 17390, "token_acc": 0.7995334642468512 }, { "epoch": 1.1261137321863544, "grad_norm": 0.4153020977973938, "learning_rate": 4.016010023071406e-06, "loss": 0.644650936126709, "step": 17395, "token_acc": 0.7975501448592935 }, { "epoch": 1.1264374327309805, "grad_norm": 0.29677388072013855, "learning_rate": 4.013517630909361e-06, "loss": 0.6326135635375977, "step": 17400, "token_acc": 0.7996310875565565 }, { "epoch": 1.1267611332756067, "grad_norm": 0.2969479262828827, "learning_rate": 4.011025493771162e-06, "loss": 0.6208539009094238, "step": 17405, "token_acc": 0.8038399813630833 }, { "epoch": 1.1270848338202328, "grad_norm": 0.2658613622188568, "learning_rate": 4.008533612301068e-06, "loss": 0.6430323600769043, "step": 17410, "token_acc": 0.7967765761748147 }, { "epoch": 1.127408534364859, "grad_norm": 0.28164198994636536, "learning_rate": 4.006041987143278e-06, "loss": 0.6249609470367432, "step": 17415, "token_acc": 0.8024333903924351 }, { "epoch": 1.1277322349094852, "grad_norm": 0.34668442606925964, "learning_rate": 4.003550618941927e-06, "loss": 0.6206781387329101, "step": 17420, "token_acc": 0.8029152847191905 }, { "epoch": 1.1280559354541113, "grad_norm": 0.3973550796508789, "learning_rate": 4.0010595083410745e-06, "loss": 0.6280682563781739, "step": 17425, "token_acc": 0.8005460346699121 }, { "epoch": 1.1283796359987375, "grad_norm": 0.28714078664779663, "learning_rate": 3.9985686559847195e-06, "loss": 0.6044458866119384, "step": 17430, "token_acc": 0.8061691503421157 }, { "epoch": 1.1287033365433636, "grad_norm": 0.2175639271736145, "learning_rate": 3.996078062516795e-06, "loss": 0.6271538257598877, "step": 17435, "token_acc": 0.8010110264257357 }, { "epoch": 1.1290270370879898, "grad_norm": 0.28869953751564026, "learning_rate": 3.993587728581164e-06, "loss": 0.6174797534942627, "step": 17440, "token_acc": 0.8043459313045169 }, { "epoch": 1.129350737632616, "grad_norm": 0.26673999428749084, "learning_rate": 3.991097654821623e-06, "loss": 0.6448476314544678, "step": 17445, "token_acc": 0.7973052056626909 }, { "epoch": 1.1296744381772421, "grad_norm": 0.3182733356952667, "learning_rate": 3.988607841881904e-06, "loss": 0.6306012153625489, "step": 17450, "token_acc": 0.8003567075889539 }, { "epoch": 1.1299981387218685, "grad_norm": 0.2449588179588318, "learning_rate": 3.986118290405665e-06, "loss": 0.6162115097045898, "step": 17455, "token_acc": 0.8041635641598411 }, { "epoch": 1.1303218392664947, "grad_norm": 0.3238876760005951, "learning_rate": 3.983629001036507e-06, "loss": 0.6269847393035889, "step": 17460, "token_acc": 0.800998321680054 }, { "epoch": 1.1306455398111208, "grad_norm": 0.26990705728530884, "learning_rate": 3.981139974417953e-06, "loss": 0.6224109649658203, "step": 17465, "token_acc": 0.8021945392020109 }, { "epoch": 1.130969240355747, "grad_norm": 0.2716718018054962, "learning_rate": 3.978651211193463e-06, "loss": 0.6294331550598145, "step": 17470, "token_acc": 0.8004864039415058 }, { "epoch": 1.1312929409003731, "grad_norm": 0.3478405177593231, "learning_rate": 3.9761627120064285e-06, "loss": 0.6335397720336914, "step": 17475, "token_acc": 0.7997190697796536 }, { "epoch": 1.1316166414449993, "grad_norm": 0.2711343765258789, "learning_rate": 3.973674477500172e-06, "loss": 0.6172452926635742, "step": 17480, "token_acc": 0.8037709583235805 }, { "epoch": 1.1319403419896255, "grad_norm": 0.282619833946228, "learning_rate": 3.971186508317948e-06, "loss": 0.6153830051422119, "step": 17485, "token_acc": 0.8034997057995855 }, { "epoch": 1.1322640425342516, "grad_norm": 0.348406583070755, "learning_rate": 3.968698805102944e-06, "loss": 0.6464880466461181, "step": 17490, "token_acc": 0.797576459262921 }, { "epoch": 1.1325877430788778, "grad_norm": 0.3191855251789093, "learning_rate": 3.966211368498272e-06, "loss": 0.6124787330627441, "step": 17495, "token_acc": 0.8053601527562679 }, { "epoch": 1.132911443623504, "grad_norm": 0.3239556849002838, "learning_rate": 3.963724199146985e-06, "loss": 0.62551851272583, "step": 17500, "token_acc": 0.8018181936754512 }, { "epoch": 1.13323514416813, "grad_norm": 0.32529547810554504, "learning_rate": 3.96123729769206e-06, "loss": 0.6590601921081543, "step": 17505, "token_acc": 0.7945388811366231 }, { "epoch": 1.1335588447127563, "grad_norm": 0.3347705900669098, "learning_rate": 3.95875066477641e-06, "loss": 0.6136857986450195, "step": 17510, "token_acc": 0.8047879889290599 }, { "epoch": 1.1338825452573824, "grad_norm": 0.3497665524482727, "learning_rate": 3.956264301042871e-06, "loss": 0.64329833984375, "step": 17515, "token_acc": 0.7961095820082429 }, { "epoch": 1.1342062458020086, "grad_norm": 0.3169841766357422, "learning_rate": 3.953778207134214e-06, "loss": 0.6478572845458984, "step": 17520, "token_acc": 0.7954025617566332 }, { "epoch": 1.1345299463466347, "grad_norm": 0.24266961216926575, "learning_rate": 3.951292383693144e-06, "loss": 0.6515658855438232, "step": 17525, "token_acc": 0.7936837190688988 }, { "epoch": 1.134853646891261, "grad_norm": 0.28751394152641296, "learning_rate": 3.948806831362288e-06, "loss": 0.6377011775970459, "step": 17530, "token_acc": 0.7997276382344041 }, { "epoch": 1.135177347435887, "grad_norm": 0.28576889634132385, "learning_rate": 3.946321550784209e-06, "loss": 0.6282138347625732, "step": 17535, "token_acc": 0.8004312044468753 }, { "epoch": 1.1355010479805132, "grad_norm": 0.3735952079296112, "learning_rate": 3.943836542601398e-06, "loss": 0.6479159832000733, "step": 17540, "token_acc": 0.7975849763904408 }, { "epoch": 1.1358247485251394, "grad_norm": 0.38726183772087097, "learning_rate": 3.941351807456274e-06, "loss": 0.6189100265502929, "step": 17545, "token_acc": 0.8056828002053241 }, { "epoch": 1.1361484490697655, "grad_norm": 0.22722381353378296, "learning_rate": 3.938867345991187e-06, "loss": 0.6359026908874512, "step": 17550, "token_acc": 0.7983951591686398 }, { "epoch": 1.1364721496143917, "grad_norm": 0.3535536527633667, "learning_rate": 3.936383158848416e-06, "loss": 0.6430107116699219, "step": 17555, "token_acc": 0.7975660616005196 }, { "epoch": 1.1367958501590179, "grad_norm": 0.35084396600723267, "learning_rate": 3.933899246670172e-06, "loss": 0.6289040565490722, "step": 17560, "token_acc": 0.8008798912654697 }, { "epoch": 1.137119550703644, "grad_norm": 0.3573242723941803, "learning_rate": 3.931415610098588e-06, "loss": 0.6505696296691894, "step": 17565, "token_acc": 0.7963826279660559 }, { "epoch": 1.1374432512482702, "grad_norm": 0.2534804940223694, "learning_rate": 3.928932249775731e-06, "loss": 0.6478356838226318, "step": 17570, "token_acc": 0.7978834440935936 }, { "epoch": 1.1377669517928963, "grad_norm": 0.3204472064971924, "learning_rate": 3.926449166343598e-06, "loss": 0.6224665641784668, "step": 17575, "token_acc": 0.802828726868127 }, { "epoch": 1.1380906523375225, "grad_norm": 0.3996559977531433, "learning_rate": 3.923966360444107e-06, "loss": 0.6265724658966064, "step": 17580, "token_acc": 0.801589554357082 }, { "epoch": 1.1384143528821487, "grad_norm": 0.2854803204536438, "learning_rate": 3.921483832719111e-06, "loss": 0.639336633682251, "step": 17585, "token_acc": 0.797895910166786 }, { "epoch": 1.1387380534267748, "grad_norm": 0.40507301688194275, "learning_rate": 3.919001583810391e-06, "loss": 0.581410026550293, "step": 17590, "token_acc": 0.812775590414488 }, { "epoch": 1.139061753971401, "grad_norm": 0.3341205418109894, "learning_rate": 3.916519614359653e-06, "loss": 0.6000150203704834, "step": 17595, "token_acc": 0.8078991196764216 }, { "epoch": 1.1393854545160271, "grad_norm": 0.32138195633888245, "learning_rate": 3.91403792500853e-06, "loss": 0.6367621421813965, "step": 17600, "token_acc": 0.7991754161998802 }, { "epoch": 1.1397091550606535, "grad_norm": 0.4299418330192566, "learning_rate": 3.911556516398586e-06, "loss": 0.6368072509765625, "step": 17605, "token_acc": 0.7985459447432827 }, { "epoch": 1.1400328556052797, "grad_norm": 0.34450066089630127, "learning_rate": 3.9090753891713115e-06, "loss": 0.6355154991149903, "step": 17610, "token_acc": 0.7996229189071454 }, { "epoch": 1.1403565561499058, "grad_norm": 0.34802064299583435, "learning_rate": 3.906594543968122e-06, "loss": 0.6161609172821045, "step": 17615, "token_acc": 0.8057157943370075 }, { "epoch": 1.140680256694532, "grad_norm": 0.31920918822288513, "learning_rate": 3.904113981430361e-06, "loss": 0.5950478553771973, "step": 17620, "token_acc": 0.8091174722965813 }, { "epoch": 1.1410039572391582, "grad_norm": 0.4198804497718811, "learning_rate": 3.901633702199303e-06, "loss": 0.6242969512939454, "step": 17625, "token_acc": 0.8027465171458491 }, { "epoch": 1.1413276577837843, "grad_norm": 0.32511118054389954, "learning_rate": 3.899153706916141e-06, "loss": 0.6415914535522461, "step": 17630, "token_acc": 0.7983725074817579 }, { "epoch": 1.1416513583284105, "grad_norm": 0.2882392108440399, "learning_rate": 3.896673996222003e-06, "loss": 0.6160400390625, "step": 17635, "token_acc": 0.804092755345185 }, { "epoch": 1.1419750588730366, "grad_norm": 0.34563520550727844, "learning_rate": 3.894194570757939e-06, "loss": 0.6246143341064453, "step": 17640, "token_acc": 0.8024196655621484 }, { "epoch": 1.1422987594176628, "grad_norm": 0.28036946058273315, "learning_rate": 3.891715431164926e-06, "loss": 0.619227409362793, "step": 17645, "token_acc": 0.802324445064917 }, { "epoch": 1.142622459962289, "grad_norm": 0.3614591956138611, "learning_rate": 3.889236578083866e-06, "loss": 0.6269837379455566, "step": 17650, "token_acc": 0.8013414937679892 }, { "epoch": 1.142946160506915, "grad_norm": 0.2997419536113739, "learning_rate": 3.88675801215559e-06, "loss": 0.6416619300842286, "step": 17655, "token_acc": 0.8001125524473034 }, { "epoch": 1.1432698610515413, "grad_norm": 0.3076433539390564, "learning_rate": 3.884279734020853e-06, "loss": 0.6320203304290771, "step": 17660, "token_acc": 0.8009352897981269 }, { "epoch": 1.1435935615961674, "grad_norm": 0.39682838320732117, "learning_rate": 3.881801744320333e-06, "loss": 0.6104652404785156, "step": 17665, "token_acc": 0.8045378850957535 }, { "epoch": 1.1439172621407936, "grad_norm": 0.2998174726963043, "learning_rate": 3.8793240436946385e-06, "loss": 0.6384211540222168, "step": 17670, "token_acc": 0.7995234747771343 }, { "epoch": 1.1442409626854197, "grad_norm": 0.3110867440700531, "learning_rate": 3.8768466327843005e-06, "loss": 0.62611083984375, "step": 17675, "token_acc": 0.802673211502106 }, { "epoch": 1.144564663230046, "grad_norm": 0.34756264090538025, "learning_rate": 3.874369512229773e-06, "loss": 0.6327883243560791, "step": 17680, "token_acc": 0.8014668842813677 }, { "epoch": 1.144888363774672, "grad_norm": 0.31806308031082153, "learning_rate": 3.87189268267144e-06, "loss": 0.6069827556610108, "step": 17685, "token_acc": 0.8071326775348465 }, { "epoch": 1.1452120643192982, "grad_norm": 0.2721869647502899, "learning_rate": 3.8694161447496045e-06, "loss": 0.6497135639190674, "step": 17690, "token_acc": 0.7953315982394702 }, { "epoch": 1.1455357648639244, "grad_norm": 0.24171775579452515, "learning_rate": 3.866939899104501e-06, "loss": 0.6196253299713135, "step": 17695, "token_acc": 0.8035988462106758 }, { "epoch": 1.1458594654085505, "grad_norm": 0.31804507970809937, "learning_rate": 3.864463946376282e-06, "loss": 0.639048719406128, "step": 17700, "token_acc": 0.7974902338185295 }, { "epoch": 1.1461831659531767, "grad_norm": 0.3073073923587799, "learning_rate": 3.861988287205026e-06, "loss": 0.6016207218170166, "step": 17705, "token_acc": 0.8081267755442758 }, { "epoch": 1.1465068664978029, "grad_norm": 0.3729858696460724, "learning_rate": 3.8595129222307395e-06, "loss": 0.6198077201843262, "step": 17710, "token_acc": 0.802918065597262 }, { "epoch": 1.146830567042429, "grad_norm": 0.39223697781562805, "learning_rate": 3.857037852093348e-06, "loss": 0.6520905494689941, "step": 17715, "token_acc": 0.7957056789322959 }, { "epoch": 1.1471542675870552, "grad_norm": 0.32152262330055237, "learning_rate": 3.854563077432702e-06, "loss": 0.6022985935211181, "step": 17720, "token_acc": 0.8073157143131592 }, { "epoch": 1.1474779681316813, "grad_norm": 0.2771701514720917, "learning_rate": 3.852088598888577e-06, "loss": 0.611702823638916, "step": 17725, "token_acc": 0.8060465862594604 }, { "epoch": 1.1478016686763075, "grad_norm": 0.24699445068836212, "learning_rate": 3.849614417100673e-06, "loss": 0.6346300601959228, "step": 17730, "token_acc": 0.7989971365101378 }, { "epoch": 1.1481253692209337, "grad_norm": 0.2831287682056427, "learning_rate": 3.847140532708608e-06, "loss": 0.6235229969024658, "step": 17735, "token_acc": 0.802963349803827 }, { "epoch": 1.1484490697655598, "grad_norm": 0.3186875581741333, "learning_rate": 3.8446669463519294e-06, "loss": 0.6337946891784668, "step": 17740, "token_acc": 0.7992470990988756 }, { "epoch": 1.148772770310186, "grad_norm": 0.30172228813171387, "learning_rate": 3.8421936586701055e-06, "loss": 0.6276732921600342, "step": 17745, "token_acc": 0.8018412661936632 }, { "epoch": 1.1490964708548121, "grad_norm": 0.31132861971855164, "learning_rate": 3.8397206703025226e-06, "loss": 0.6337716102600097, "step": 17750, "token_acc": 0.8011225794380866 }, { "epoch": 1.1494201713994383, "grad_norm": 0.35947445034980774, "learning_rate": 3.837247981888497e-06, "loss": 0.5940141677856445, "step": 17755, "token_acc": 0.8098963048051891 }, { "epoch": 1.1497438719440645, "grad_norm": 0.3387150168418884, "learning_rate": 3.834775594067264e-06, "loss": 0.6440943717956543, "step": 17760, "token_acc": 0.7971124421311433 }, { "epoch": 1.1500675724886906, "grad_norm": 0.2964377999305725, "learning_rate": 3.8323035074779805e-06, "loss": 0.6094282150268555, "step": 17765, "token_acc": 0.8069840986470461 }, { "epoch": 1.1503912730333168, "grad_norm": 0.30005234479904175, "learning_rate": 3.829831722759725e-06, "loss": 0.6094355583190918, "step": 17770, "token_acc": 0.8055409504550051 }, { "epoch": 1.150714973577943, "grad_norm": 0.3812306821346283, "learning_rate": 3.827360240551501e-06, "loss": 0.6320053100585937, "step": 17775, "token_acc": 0.8015619387363284 }, { "epoch": 1.151038674122569, "grad_norm": 0.2777543067932129, "learning_rate": 3.824889061492235e-06, "loss": 0.6008527755737305, "step": 17780, "token_acc": 0.8100709937200326 }, { "epoch": 1.1513623746671953, "grad_norm": 0.28689053654670715, "learning_rate": 3.822418186220767e-06, "loss": 0.6262730598449707, "step": 17785, "token_acc": 0.8021128718376425 }, { "epoch": 1.1516860752118214, "grad_norm": 0.4422758221626282, "learning_rate": 3.819947615375867e-06, "loss": 0.5966697692871094, "step": 17790, "token_acc": 0.8088153728419678 }, { "epoch": 1.1520097757564478, "grad_norm": 0.32223808765411377, "learning_rate": 3.817477349596222e-06, "loss": 0.6439035892486572, "step": 17795, "token_acc": 0.7976961453699822 }, { "epoch": 1.152333476301074, "grad_norm": 0.2492702156305313, "learning_rate": 3.81500738952044e-06, "loss": 0.6414392948150635, "step": 17800, "token_acc": 0.7992602902136653 }, { "epoch": 1.1526571768457001, "grad_norm": 0.28097012639045715, "learning_rate": 3.8125377357870525e-06, "loss": 0.6298377990722657, "step": 17805, "token_acc": 0.8003697886392025 }, { "epoch": 1.1529808773903263, "grad_norm": 0.29316872358322144, "learning_rate": 3.8100683890345125e-06, "loss": 0.6235093116760254, "step": 17810, "token_acc": 0.8024613564465934 }, { "epoch": 1.1533045779349524, "grad_norm": 0.2934940457344055, "learning_rate": 3.807599349901187e-06, "loss": 0.6228618621826172, "step": 17815, "token_acc": 0.8046216255070725 }, { "epoch": 1.1536282784795786, "grad_norm": 0.33746081590652466, "learning_rate": 3.80513061902537e-06, "loss": 0.6485002517700196, "step": 17820, "token_acc": 0.7956167408032728 }, { "epoch": 1.1539519790242048, "grad_norm": 0.341886967420578, "learning_rate": 3.8026621970452748e-06, "loss": 0.6142402648925781, "step": 17825, "token_acc": 0.8050860916634682 }, { "epoch": 1.154275679568831, "grad_norm": 0.3498091995716095, "learning_rate": 3.8001940845990354e-06, "loss": 0.612810468673706, "step": 17830, "token_acc": 0.8053840627165737 }, { "epoch": 1.154599380113457, "grad_norm": 0.24348945915699005, "learning_rate": 3.7977262823247e-06, "loss": 0.638456916809082, "step": 17835, "token_acc": 0.7979064203110461 }, { "epoch": 1.1549230806580832, "grad_norm": 0.34580615162849426, "learning_rate": 3.795258790860243e-06, "loss": 0.6477031707763672, "step": 17840, "token_acc": 0.7951787747512246 }, { "epoch": 1.1552467812027094, "grad_norm": 0.33241501450538635, "learning_rate": 3.7927916108435586e-06, "loss": 0.6477176189422608, "step": 17845, "token_acc": 0.797529349361248 }, { "epoch": 1.1555704817473356, "grad_norm": 0.2582421600818634, "learning_rate": 3.790324742912454e-06, "loss": 0.6321061134338379, "step": 17850, "token_acc": 0.7991765865218942 }, { "epoch": 1.1558941822919617, "grad_norm": 0.3063017725944519, "learning_rate": 3.787858187704662e-06, "loss": 0.6000324726104737, "step": 17855, "token_acc": 0.8074021343652271 }, { "epoch": 1.1562178828365879, "grad_norm": 0.2768416404724121, "learning_rate": 3.7853919458578327e-06, "loss": 0.6480801582336426, "step": 17860, "token_acc": 0.7959666406554818 }, { "epoch": 1.156541583381214, "grad_norm": 0.3370257019996643, "learning_rate": 3.782926018009537e-06, "loss": 0.628258228302002, "step": 17865, "token_acc": 0.8004115091936379 }, { "epoch": 1.1568652839258402, "grad_norm": 0.3478708267211914, "learning_rate": 3.7804604047972583e-06, "loss": 0.6267428874969483, "step": 17870, "token_acc": 0.8013522255119051 }, { "epoch": 1.1571889844704664, "grad_norm": 0.3361816704273224, "learning_rate": 3.777995106858405e-06, "loss": 0.619469690322876, "step": 17875, "token_acc": 0.8030690370293078 }, { "epoch": 1.1575126850150925, "grad_norm": 0.47924715280532837, "learning_rate": 3.7755301248303046e-06, "loss": 0.6164510726928711, "step": 17880, "token_acc": 0.8046475244540451 }, { "epoch": 1.1578363855597187, "grad_norm": 0.30265286564826965, "learning_rate": 3.7730654593501953e-06, "loss": 0.6304508209228515, "step": 17885, "token_acc": 0.7978975137370832 }, { "epoch": 1.1581600861043448, "grad_norm": 0.39390578866004944, "learning_rate": 3.7706011110552416e-06, "loss": 0.6469450950622558, "step": 17890, "token_acc": 0.7956519700362238 }, { "epoch": 1.158483786648971, "grad_norm": 0.300874263048172, "learning_rate": 3.768137080582524e-06, "loss": 0.6305343627929687, "step": 17895, "token_acc": 0.8003557763308049 }, { "epoch": 1.1588074871935972, "grad_norm": 0.23784063756465912, "learning_rate": 3.765673368569036e-06, "loss": 0.6132318019866944, "step": 17900, "token_acc": 0.8056666293370927 }, { "epoch": 1.1591311877382233, "grad_norm": 0.24766221642494202, "learning_rate": 3.763209975651694e-06, "loss": 0.6370031833648682, "step": 17905, "token_acc": 0.7977955555555556 }, { "epoch": 1.1594548882828495, "grad_norm": 0.23720189929008484, "learning_rate": 3.7607469024673326e-06, "loss": 0.6208002090454101, "step": 17910, "token_acc": 0.8045935175017582 }, { "epoch": 1.1597785888274756, "grad_norm": 0.3679155111312866, "learning_rate": 3.7582841496527e-06, "loss": 0.6557391166687012, "step": 17915, "token_acc": 0.7930808508314448 }, { "epoch": 1.1601022893721018, "grad_norm": 0.27434128522872925, "learning_rate": 3.755821717844461e-06, "loss": 0.6394874095916748, "step": 17920, "token_acc": 0.7969969158177997 }, { "epoch": 1.160425989916728, "grad_norm": 0.31814688444137573, "learning_rate": 3.7533596076792036e-06, "loss": 0.6185743808746338, "step": 17925, "token_acc": 0.8033092413291514 }, { "epoch": 1.1607496904613541, "grad_norm": 0.3366129994392395, "learning_rate": 3.750897819793426e-06, "loss": 0.6234057426452637, "step": 17930, "token_acc": 0.8025781149976753 }, { "epoch": 1.1610733910059803, "grad_norm": 0.36471807956695557, "learning_rate": 3.7484363548235463e-06, "loss": 0.6249545574188232, "step": 17935, "token_acc": 0.8026686111963975 }, { "epoch": 1.1613970915506064, "grad_norm": 0.35781556367874146, "learning_rate": 3.745975213405897e-06, "loss": 0.6300130367279053, "step": 17940, "token_acc": 0.8009742649351945 }, { "epoch": 1.1617207920952328, "grad_norm": 0.3389548063278198, "learning_rate": 3.7435143961767313e-06, "loss": 0.6396436214447021, "step": 17945, "token_acc": 0.7984286138771223 }, { "epoch": 1.162044492639859, "grad_norm": 0.3749615252017975, "learning_rate": 3.741053903772214e-06, "loss": 0.6008647918701172, "step": 17950, "token_acc": 0.8081555341124335 }, { "epoch": 1.1623681931844851, "grad_norm": 0.28306829929351807, "learning_rate": 3.7385937368284264e-06, "loss": 0.6109221458435059, "step": 17955, "token_acc": 0.8052078150842421 }, { "epoch": 1.1626918937291113, "grad_norm": 0.31870535016059875, "learning_rate": 3.7361338959813685e-06, "loss": 0.6267580032348633, "step": 17960, "token_acc": 0.8017115734351421 }, { "epoch": 1.1630155942737375, "grad_norm": 0.2525756359100342, "learning_rate": 3.7336743818669573e-06, "loss": 0.6015397071838379, "step": 17965, "token_acc": 0.8078507514162904 }, { "epoch": 1.1633392948183636, "grad_norm": 0.39544597268104553, "learning_rate": 3.731215195121016e-06, "loss": 0.5979800224304199, "step": 17970, "token_acc": 0.8083552789083074 }, { "epoch": 1.1636629953629898, "grad_norm": 0.2830205261707306, "learning_rate": 3.7287563363792944e-06, "loss": 0.5989291667938232, "step": 17975, "token_acc": 0.8076420774793105 }, { "epoch": 1.163986695907616, "grad_norm": 0.28045013546943665, "learning_rate": 3.726297806277453e-06, "loss": 0.6253519058227539, "step": 17980, "token_acc": 0.8017224278160463 }, { "epoch": 1.164310396452242, "grad_norm": 0.3344160318374634, "learning_rate": 3.7238396054510626e-06, "loss": 0.6041710376739502, "step": 17985, "token_acc": 0.8071280656670243 }, { "epoch": 1.1646340969968683, "grad_norm": 0.37079674005508423, "learning_rate": 3.7213817345356176e-06, "loss": 0.6051477909088134, "step": 17990, "token_acc": 0.805345235976286 }, { "epoch": 1.1649577975414944, "grad_norm": 0.34874194860458374, "learning_rate": 3.718924194166521e-06, "loss": 0.6237995624542236, "step": 17995, "token_acc": 0.8019082997372361 }, { "epoch": 1.1652814980861206, "grad_norm": 0.309796541929245, "learning_rate": 3.7164669849790947e-06, "loss": 0.6343730449676513, "step": 18000, "token_acc": 0.799340034831495 }, { "epoch": 1.1656051986307467, "grad_norm": 0.32362058758735657, "learning_rate": 3.7140101076085685e-06, "loss": 0.6246116161346436, "step": 18005, "token_acc": 0.8006295243101516 }, { "epoch": 1.165928899175373, "grad_norm": 0.38493070006370544, "learning_rate": 3.711553562690092e-06, "loss": 0.6041284561157226, "step": 18010, "token_acc": 0.8069539870914012 }, { "epoch": 1.166252599719999, "grad_norm": 0.3403018116950989, "learning_rate": 3.70909735085873e-06, "loss": 0.6311247825622559, "step": 18015, "token_acc": 0.8005196244847057 }, { "epoch": 1.1665763002646252, "grad_norm": 0.2811448276042938, "learning_rate": 3.7066414727494542e-06, "loss": 0.6192705631256104, "step": 18020, "token_acc": 0.802642596163605 }, { "epoch": 1.1669000008092514, "grad_norm": 0.3284502923488617, "learning_rate": 3.704185928997156e-06, "loss": 0.6361506462097168, "step": 18025, "token_acc": 0.7983005648011875 }, { "epoch": 1.1672237013538775, "grad_norm": 0.3073340356349945, "learning_rate": 3.7017307202366416e-06, "loss": 0.6271340370178222, "step": 18030, "token_acc": 0.8020063784263857 }, { "epoch": 1.1675474018985037, "grad_norm": 0.30035433173179626, "learning_rate": 3.6992758471026215e-06, "loss": 0.6247113227844239, "step": 18035, "token_acc": 0.8018988020261035 }, { "epoch": 1.1678711024431299, "grad_norm": 0.2662406265735626, "learning_rate": 3.69682131022973e-06, "loss": 0.6458621978759765, "step": 18040, "token_acc": 0.7970739443256488 }, { "epoch": 1.168194802987756, "grad_norm": 0.37375202775001526, "learning_rate": 3.6943671102525086e-06, "loss": 0.6207202434539795, "step": 18045, "token_acc": 0.8033435745829693 }, { "epoch": 1.1685185035323822, "grad_norm": 0.2029048651456833, "learning_rate": 3.6919132478054153e-06, "loss": 0.628760290145874, "step": 18050, "token_acc": 0.800489891897188 }, { "epoch": 1.1688422040770083, "grad_norm": 0.3315669596195221, "learning_rate": 3.689459723522816e-06, "loss": 0.6471742630004883, "step": 18055, "token_acc": 0.7966667705055918 }, { "epoch": 1.1691659046216345, "grad_norm": 0.34132251143455505, "learning_rate": 3.6870065380389917e-06, "loss": 0.6195165157318115, "step": 18060, "token_acc": 0.801691158721683 }, { "epoch": 1.1694896051662607, "grad_norm": 0.3515819013118744, "learning_rate": 3.68455369198814e-06, "loss": 0.6821880340576172, "step": 18065, "token_acc": 0.7878009214197651 }, { "epoch": 1.1698133057108868, "grad_norm": 0.3268868923187256, "learning_rate": 3.682101186004361e-06, "loss": 0.6398346424102783, "step": 18070, "token_acc": 0.7989326803430861 }, { "epoch": 1.170137006255513, "grad_norm": 0.2970620095729828, "learning_rate": 3.679649020721676e-06, "loss": 0.6313673496246338, "step": 18075, "token_acc": 0.8007159825129921 }, { "epoch": 1.1704607068001391, "grad_norm": 0.4231732487678528, "learning_rate": 3.6771971967740146e-06, "loss": 0.6359798431396484, "step": 18080, "token_acc": 0.7992852776009529 }, { "epoch": 1.1707844073447653, "grad_norm": 0.3893990218639374, "learning_rate": 3.6747457147952193e-06, "loss": 0.6257203102111817, "step": 18085, "token_acc": 0.8013992725803193 }, { "epoch": 1.1711081078893915, "grad_norm": 0.4509531259536743, "learning_rate": 3.672294575419041e-06, "loss": 0.6268735885620117, "step": 18090, "token_acc": 0.8027219512813846 }, { "epoch": 1.1714318084340176, "grad_norm": 0.3166007399559021, "learning_rate": 3.6698437792791453e-06, "loss": 0.6238627433776855, "step": 18095, "token_acc": 0.8023942061086501 }, { "epoch": 1.1717555089786438, "grad_norm": 0.5745898485183716, "learning_rate": 3.66739332700911e-06, "loss": 0.6529868125915528, "step": 18100, "token_acc": 0.7947364335067153 }, { "epoch": 1.17207920952327, "grad_norm": 0.3065313696861267, "learning_rate": 3.6649432192424183e-06, "loss": 0.6170097827911377, "step": 18105, "token_acc": 0.8054231435698553 }, { "epoch": 1.172402910067896, "grad_norm": 0.31016606092453003, "learning_rate": 3.6624934566124705e-06, "loss": 0.6170984268188476, "step": 18110, "token_acc": 0.8029157164074298 }, { "epoch": 1.1727266106125223, "grad_norm": 0.29914021492004395, "learning_rate": 3.660044039752576e-06, "loss": 0.6365799903869629, "step": 18115, "token_acc": 0.7984769825892646 }, { "epoch": 1.1730503111571484, "grad_norm": 0.35559436678886414, "learning_rate": 3.6575949692959522e-06, "loss": 0.6189830780029297, "step": 18120, "token_acc": 0.8034814564720548 }, { "epoch": 1.1733740117017746, "grad_norm": 0.3106246888637543, "learning_rate": 3.65514624587573e-06, "loss": 0.6010378837585449, "step": 18125, "token_acc": 0.8067633864522314 }, { "epoch": 1.1736977122464007, "grad_norm": 0.32197725772857666, "learning_rate": 3.6526978701249495e-06, "loss": 0.646580982208252, "step": 18130, "token_acc": 0.7980415038101397 }, { "epoch": 1.174021412791027, "grad_norm": 0.3131415545940399, "learning_rate": 3.6502498426765608e-06, "loss": 0.6159579753875732, "step": 18135, "token_acc": 0.8044341472605847 }, { "epoch": 1.1743451133356533, "grad_norm": 0.3276073634624481, "learning_rate": 3.647802164163423e-06, "loss": 0.6085810661315918, "step": 18140, "token_acc": 0.8057728296380879 }, { "epoch": 1.1746688138802794, "grad_norm": 0.2971009612083435, "learning_rate": 3.645354835218309e-06, "loss": 0.6528825759887695, "step": 18145, "token_acc": 0.7957264444577743 }, { "epoch": 1.1749925144249056, "grad_norm": 0.3335481286048889, "learning_rate": 3.642907856473895e-06, "loss": 0.6191198348999023, "step": 18150, "token_acc": 0.8034309750324703 }, { "epoch": 1.1753162149695318, "grad_norm": 0.3394891321659088, "learning_rate": 3.6404612285627705e-06, "loss": 0.6027643203735351, "step": 18155, "token_acc": 0.8076330246222351 }, { "epoch": 1.175639915514158, "grad_norm": 0.27683815360069275, "learning_rate": 3.6380149521174362e-06, "loss": 0.6250537872314453, "step": 18160, "token_acc": 0.8018219889940118 }, { "epoch": 1.175963616058784, "grad_norm": 0.2816827893257141, "learning_rate": 3.635569027770298e-06, "loss": 0.6293312072753906, "step": 18165, "token_acc": 0.8000037707864603 }, { "epoch": 1.1762873166034102, "grad_norm": 0.34000495076179504, "learning_rate": 3.6331234561536712e-06, "loss": 0.6053825378417969, "step": 18170, "token_acc": 0.8067109496208635 }, { "epoch": 1.1766110171480364, "grad_norm": 0.40058279037475586, "learning_rate": 3.6306782378997827e-06, "loss": 0.6271512985229493, "step": 18175, "token_acc": 0.8009344179493314 }, { "epoch": 1.1769347176926626, "grad_norm": 0.336906760931015, "learning_rate": 3.628233373640766e-06, "loss": 0.6207760810852051, "step": 18180, "token_acc": 0.8028407507698463 }, { "epoch": 1.1772584182372887, "grad_norm": 0.26465675234794617, "learning_rate": 3.625788864008664e-06, "loss": 0.64649658203125, "step": 18185, "token_acc": 0.797905551722489 }, { "epoch": 1.1775821187819149, "grad_norm": 0.32631915807724, "learning_rate": 3.6233447096354267e-06, "loss": 0.6063895225524902, "step": 18190, "token_acc": 0.8079622241112925 }, { "epoch": 1.177905819326541, "grad_norm": 0.26628896594047546, "learning_rate": 3.6209009111529127e-06, "loss": 0.6201493263244628, "step": 18195, "token_acc": 0.8037368599525263 }, { "epoch": 1.1782295198711672, "grad_norm": 0.30835381150245667, "learning_rate": 3.6184574691928897e-06, "loss": 0.626304817199707, "step": 18200, "token_acc": 0.7985616651941168 }, { "epoch": 1.1785532204157934, "grad_norm": 0.39459770917892456, "learning_rate": 3.616014384387032e-06, "loss": 0.6158320426940918, "step": 18205, "token_acc": 0.8038252418160936 }, { "epoch": 1.1788769209604195, "grad_norm": 0.3388548195362091, "learning_rate": 3.6135716573669216e-06, "loss": 0.6405583381652832, "step": 18210, "token_acc": 0.79785561845855 }, { "epoch": 1.1792006215050457, "grad_norm": 0.31678512692451477, "learning_rate": 3.6111292887640487e-06, "loss": 0.6298822402954102, "step": 18215, "token_acc": 0.7997140192726142 }, { "epoch": 1.1795243220496718, "grad_norm": 0.2592395842075348, "learning_rate": 3.6086872792098126e-06, "loss": 0.618657398223877, "step": 18220, "token_acc": 0.80406525342406 }, { "epoch": 1.179848022594298, "grad_norm": 0.3425615131855011, "learning_rate": 3.6062456293355137e-06, "loss": 0.6437272071838379, "step": 18225, "token_acc": 0.7978023329711557 }, { "epoch": 1.1801717231389242, "grad_norm": 0.3759364187717438, "learning_rate": 3.6038043397723656e-06, "loss": 0.6308758735656739, "step": 18230, "token_acc": 0.8011906597982664 }, { "epoch": 1.1804954236835503, "grad_norm": 0.2947409749031067, "learning_rate": 3.6013634111514883e-06, "loss": 0.6315862655639648, "step": 18235, "token_acc": 0.800277073877085 }, { "epoch": 1.1808191242281765, "grad_norm": 0.23514117300510406, "learning_rate": 3.5989228441039024e-06, "loss": 0.6204164505004883, "step": 18240, "token_acc": 0.8026363496696881 }, { "epoch": 1.1811428247728026, "grad_norm": 0.24191096425056458, "learning_rate": 3.5964826392605423e-06, "loss": 0.6087211608886719, "step": 18245, "token_acc": 0.8056670026995393 }, { "epoch": 1.1814665253174288, "grad_norm": 0.3326449692249298, "learning_rate": 3.594042797252248e-06, "loss": 0.6228662490844726, "step": 18250, "token_acc": 0.8031655928235514 }, { "epoch": 1.181790225862055, "grad_norm": 0.3141813576221466, "learning_rate": 3.5916033187097586e-06, "loss": 0.6126882076263428, "step": 18255, "token_acc": 0.8032239336088248 }, { "epoch": 1.1821139264066811, "grad_norm": 0.3442113697528839, "learning_rate": 3.5891642042637263e-06, "loss": 0.60869140625, "step": 18260, "token_acc": 0.8045476410249743 }, { "epoch": 1.1824376269513073, "grad_norm": 0.3420962691307068, "learning_rate": 3.586725454544707e-06, "loss": 0.594904613494873, "step": 18265, "token_acc": 0.8092470799869868 }, { "epoch": 1.1827613274959334, "grad_norm": 0.3286748230457306, "learning_rate": 3.5842870701831654e-06, "loss": 0.6166954040527344, "step": 18270, "token_acc": 0.804099798976731 }, { "epoch": 1.1830850280405596, "grad_norm": 0.30248352885246277, "learning_rate": 3.581849051809464e-06, "loss": 0.607480812072754, "step": 18275, "token_acc": 0.8055810644764922 }, { "epoch": 1.1834087285851858, "grad_norm": 0.3456331193447113, "learning_rate": 3.5794114000538775e-06, "loss": 0.6013114929199219, "step": 18280, "token_acc": 0.8094384079257395 }, { "epoch": 1.183732429129812, "grad_norm": 0.30623388290405273, "learning_rate": 3.5769741155465853e-06, "loss": 0.6278313636779785, "step": 18285, "token_acc": 0.8001421482992023 }, { "epoch": 1.1840561296744383, "grad_norm": 0.36084839701652527, "learning_rate": 3.574537198917667e-06, "loss": 0.6108824253082276, "step": 18290, "token_acc": 0.8064963819335516 }, { "epoch": 1.1843798302190645, "grad_norm": 0.30286073684692383, "learning_rate": 3.5721006507971123e-06, "loss": 0.6390522480010986, "step": 18295, "token_acc": 0.7983478183865296 }, { "epoch": 1.1847035307636906, "grad_norm": 0.3398091495037079, "learning_rate": 3.5696644718148155e-06, "loss": 0.6197310447692871, "step": 18300, "token_acc": 0.8030736447873955 }, { "epoch": 1.1850272313083168, "grad_norm": 0.26229897141456604, "learning_rate": 3.567228662600569e-06, "loss": 0.626304292678833, "step": 18305, "token_acc": 0.8014839525195031 }, { "epoch": 1.185350931852943, "grad_norm": 0.3126380145549774, "learning_rate": 3.5647932237840775e-06, "loss": 0.6308605194091796, "step": 18310, "token_acc": 0.7999949232458228 }, { "epoch": 1.185674632397569, "grad_norm": 0.2809014618396759, "learning_rate": 3.562358155994946e-06, "loss": 0.6353949546813965, "step": 18315, "token_acc": 0.7994174058193958 }, { "epoch": 1.1859983329421953, "grad_norm": 0.2839220464229584, "learning_rate": 3.5599234598626875e-06, "loss": 0.6171249389648438, "step": 18320, "token_acc": 0.8036485869068599 }, { "epoch": 1.1863220334868214, "grad_norm": 0.3632126748561859, "learning_rate": 3.5574891360167096e-06, "loss": 0.6103187561035156, "step": 18325, "token_acc": 0.8048282338725036 }, { "epoch": 1.1866457340314476, "grad_norm": 0.28395143151283264, "learning_rate": 3.5550551850863334e-06, "loss": 0.626039695739746, "step": 18330, "token_acc": 0.801837752690995 }, { "epoch": 1.1869694345760737, "grad_norm": 0.28557088971138, "learning_rate": 3.552621607700782e-06, "loss": 0.6239523410797119, "step": 18335, "token_acc": 0.8009558671357616 }, { "epoch": 1.1872931351207, "grad_norm": 0.2509283423423767, "learning_rate": 3.5501884044891753e-06, "loss": 0.633674144744873, "step": 18340, "token_acc": 0.7987773171245872 }, { "epoch": 1.187616835665326, "grad_norm": 0.3945109248161316, "learning_rate": 3.547755576080543e-06, "loss": 0.6068243980407715, "step": 18345, "token_acc": 0.8069501594402311 }, { "epoch": 1.1879405362099522, "grad_norm": 0.3604813516139984, "learning_rate": 3.545323123103817e-06, "loss": 0.6120574474334717, "step": 18350, "token_acc": 0.8049946290893605 }, { "epoch": 1.1882642367545784, "grad_norm": 0.26959192752838135, "learning_rate": 3.5428910461878324e-06, "loss": 0.6232982158660889, "step": 18355, "token_acc": 0.8031795479769953 }, { "epoch": 1.1885879372992045, "grad_norm": 0.35260117053985596, "learning_rate": 3.540459345961322e-06, "loss": 0.6111516952514648, "step": 18360, "token_acc": 0.8053427468101715 }, { "epoch": 1.1889116378438307, "grad_norm": 0.3038347065448761, "learning_rate": 3.5380280230529264e-06, "loss": 0.6144962310791016, "step": 18365, "token_acc": 0.8058179806779683 }, { "epoch": 1.1892353383884569, "grad_norm": 0.2793915867805481, "learning_rate": 3.535597078091191e-06, "loss": 0.6341189384460449, "step": 18370, "token_acc": 0.8004264996825906 }, { "epoch": 1.189559038933083, "grad_norm": 0.2742547392845154, "learning_rate": 3.533166511704554e-06, "loss": 0.6159374713897705, "step": 18375, "token_acc": 0.804766793510669 }, { "epoch": 1.1898827394777092, "grad_norm": 0.3364936113357544, "learning_rate": 3.5307363245213657e-06, "loss": 0.6182650089263916, "step": 18380, "token_acc": 0.803883772885789 }, { "epoch": 1.1902064400223353, "grad_norm": 0.3043070435523987, "learning_rate": 3.5283065171698716e-06, "loss": 0.6470640659332275, "step": 18385, "token_acc": 0.7961764373282956 }, { "epoch": 1.1905301405669615, "grad_norm": 0.3163464367389679, "learning_rate": 3.525877090278223e-06, "loss": 0.6015620231628418, "step": 18390, "token_acc": 0.8072389834963036 }, { "epoch": 1.1908538411115877, "grad_norm": 0.3805944323539734, "learning_rate": 3.5234480444744717e-06, "loss": 0.621337604522705, "step": 18395, "token_acc": 0.802731401355941 }, { "epoch": 1.1911775416562138, "grad_norm": 0.32260823249816895, "learning_rate": 3.5210193803865696e-06, "loss": 0.6330990791320801, "step": 18400, "token_acc": 0.80042232893975 }, { "epoch": 1.19150124220084, "grad_norm": 0.2861813008785248, "learning_rate": 3.518591098642372e-06, "loss": 0.6183062553405761, "step": 18405, "token_acc": 0.8030666925810751 }, { "epoch": 1.1918249427454661, "grad_norm": 0.33524879813194275, "learning_rate": 3.5161631998696355e-06, "loss": 0.6329079627990722, "step": 18410, "token_acc": 0.7994245733342052 }, { "epoch": 1.1921486432900923, "grad_norm": 0.33636975288391113, "learning_rate": 3.513735684696013e-06, "loss": 0.6235993385314942, "step": 18415, "token_acc": 0.802115880063586 }, { "epoch": 1.1924723438347185, "grad_norm": 0.3175586760044098, "learning_rate": 3.5113085537490653e-06, "loss": 0.6310193538665771, "step": 18420, "token_acc": 0.7991278562707134 }, { "epoch": 1.1927960443793446, "grad_norm": 0.38310155272483826, "learning_rate": 3.50888180765625e-06, "loss": 0.6139036178588867, "step": 18425, "token_acc": 0.804894154453719 }, { "epoch": 1.1931197449239708, "grad_norm": 0.45050615072250366, "learning_rate": 3.506455447044923e-06, "loss": 0.6133008480072022, "step": 18430, "token_acc": 0.8075267072683706 }, { "epoch": 1.193443445468597, "grad_norm": 0.3399742543697357, "learning_rate": 3.5040294725423463e-06, "loss": 0.6484033107757569, "step": 18435, "token_acc": 0.7962535968138422 }, { "epoch": 1.193767146013223, "grad_norm": 0.2801969349384308, "learning_rate": 3.5016038847756774e-06, "loss": 0.6263909339904785, "step": 18440, "token_acc": 0.8025328867777962 }, { "epoch": 1.1940908465578493, "grad_norm": 0.4252049922943115, "learning_rate": 3.499178684371975e-06, "loss": 0.622339916229248, "step": 18445, "token_acc": 0.803437862358083 }, { "epoch": 1.1944145471024754, "grad_norm": 0.38760820031166077, "learning_rate": 3.496753871958198e-06, "loss": 0.6322976112365722, "step": 18450, "token_acc": 0.7994029296442575 }, { "epoch": 1.1947382476471016, "grad_norm": 0.328746497631073, "learning_rate": 3.4943294481612084e-06, "loss": 0.6299934387207031, "step": 18455, "token_acc": 0.8021761018545585 }, { "epoch": 1.1950619481917277, "grad_norm": 0.3770844340324402, "learning_rate": 3.491905413607759e-06, "loss": 0.6221279621124267, "step": 18460, "token_acc": 0.8027619498213784 }, { "epoch": 1.195385648736354, "grad_norm": 0.2897202670574188, "learning_rate": 3.4894817689245104e-06, "loss": 0.629144287109375, "step": 18465, "token_acc": 0.8009599814103449 }, { "epoch": 1.19570934928098, "grad_norm": 0.228946253657341, "learning_rate": 3.4870585147380208e-06, "loss": 0.6213212966918945, "step": 18470, "token_acc": 0.8025478853631607 }, { "epoch": 1.1960330498256062, "grad_norm": 0.28549912571907043, "learning_rate": 3.4846356516747417e-06, "loss": 0.6074892520904541, "step": 18475, "token_acc": 0.8067665168480943 }, { "epoch": 1.1963567503702326, "grad_norm": 0.3056447505950928, "learning_rate": 3.4822131803610303e-06, "loss": 0.6260987281799316, "step": 18480, "token_acc": 0.8017662208535583 }, { "epoch": 1.1966804509148588, "grad_norm": 0.32103267312049866, "learning_rate": 3.47979110142314e-06, "loss": 0.6398476123809814, "step": 18485, "token_acc": 0.7975657722493166 }, { "epoch": 1.197004151459485, "grad_norm": 0.3658161759376526, "learning_rate": 3.4773694154872253e-06, "loss": 0.6222392082214355, "step": 18490, "token_acc": 0.8015930632543813 }, { "epoch": 1.197327852004111, "grad_norm": 0.33758312463760376, "learning_rate": 3.474948123179331e-06, "loss": 0.5998080730438232, "step": 18495, "token_acc": 0.8079255046656854 }, { "epoch": 1.1976515525487372, "grad_norm": 0.3033229112625122, "learning_rate": 3.472527225125409e-06, "loss": 0.6124261856079102, "step": 18500, "token_acc": 0.8056433438679308 }, { "epoch": 1.1979752530933634, "grad_norm": 0.2915695011615753, "learning_rate": 3.4701067219513075e-06, "loss": 0.6338050365447998, "step": 18505, "token_acc": 0.7989655265429435 }, { "epoch": 1.1982989536379896, "grad_norm": 0.30442437529563904, "learning_rate": 3.467686614282767e-06, "loss": 0.6164204597473144, "step": 18510, "token_acc": 0.8041074682486402 }, { "epoch": 1.1986226541826157, "grad_norm": 0.31107041239738464, "learning_rate": 3.4652669027454327e-06, "loss": 0.614501953125, "step": 18515, "token_acc": 0.804055947619169 }, { "epoch": 1.1989463547272419, "grad_norm": 0.33090052008628845, "learning_rate": 3.462847587964846e-06, "loss": 0.6210686683654785, "step": 18520, "token_acc": 0.8026423724179075 }, { "epoch": 1.199270055271868, "grad_norm": 0.3755040168762207, "learning_rate": 3.46042867056644e-06, "loss": 0.625601863861084, "step": 18525, "token_acc": 0.8019353362319788 }, { "epoch": 1.1995937558164942, "grad_norm": 0.29945632815361023, "learning_rate": 3.4580101511755517e-06, "loss": 0.6414291381835937, "step": 18530, "token_acc": 0.798179942329568 }, { "epoch": 1.1999174563611203, "grad_norm": 0.31669357419013977, "learning_rate": 3.455592030417413e-06, "loss": 0.6219508647918701, "step": 18535, "token_acc": 0.8027673827058557 }, { "epoch": 1.2002411569057465, "grad_norm": 0.35519903898239136, "learning_rate": 3.453174308917154e-06, "loss": 0.5987130165100097, "step": 18540, "token_acc": 0.8094704797732926 }, { "epoch": 1.2005648574503727, "grad_norm": 0.28589823842048645, "learning_rate": 3.4507569872997963e-06, "loss": 0.6383769035339355, "step": 18545, "token_acc": 0.7969307136023976 }, { "epoch": 1.2008885579949988, "grad_norm": 0.2764604985713959, "learning_rate": 3.4483400661902643e-06, "loss": 0.5961105823516846, "step": 18550, "token_acc": 0.8094053930867143 }, { "epoch": 1.201212258539625, "grad_norm": 0.270622581243515, "learning_rate": 3.4459235462133794e-06, "loss": 0.6077772617340088, "step": 18555, "token_acc": 0.8056145982003393 }, { "epoch": 1.2015359590842511, "grad_norm": 0.3425070345401764, "learning_rate": 3.4435074279938514e-06, "loss": 0.6371966361999511, "step": 18560, "token_acc": 0.7987915918728374 }, { "epoch": 1.2018596596288773, "grad_norm": 0.29685261845588684, "learning_rate": 3.4410917121562936e-06, "loss": 0.6223530769348145, "step": 18565, "token_acc": 0.8032383767804354 }, { "epoch": 1.2021833601735035, "grad_norm": 0.40367838740348816, "learning_rate": 3.4386763993252147e-06, "loss": 0.6112751007080078, "step": 18570, "token_acc": 0.805438811777946 }, { "epoch": 1.2025070607181296, "grad_norm": 0.24587619304656982, "learning_rate": 3.4362614901250135e-06, "loss": 0.6364842414855957, "step": 18575, "token_acc": 0.7990889818369334 }, { "epoch": 1.2028307612627558, "grad_norm": 0.41353532671928406, "learning_rate": 3.4338469851799917e-06, "loss": 0.6109614372253418, "step": 18580, "token_acc": 0.8057168378740509 }, { "epoch": 1.203154461807382, "grad_norm": 0.29880213737487793, "learning_rate": 3.4314328851143415e-06, "loss": 0.5970928192138671, "step": 18585, "token_acc": 0.8078769599572669 }, { "epoch": 1.203478162352008, "grad_norm": 0.2606927454471588, "learning_rate": 3.4290191905521554e-06, "loss": 0.5868335723876953, "step": 18590, "token_acc": 0.8107765975012384 }, { "epoch": 1.2038018628966343, "grad_norm": 0.43218618631362915, "learning_rate": 3.426605902117413e-06, "loss": 0.6157674789428711, "step": 18595, "token_acc": 0.8039562713571944 }, { "epoch": 1.2041255634412604, "grad_norm": 0.30620744824409485, "learning_rate": 3.4241930204339967e-06, "loss": 0.6191299438476563, "step": 18600, "token_acc": 0.8033647551715108 }, { "epoch": 1.2044492639858866, "grad_norm": 0.39460325241088867, "learning_rate": 3.421780546125682e-06, "loss": 0.6457043170928956, "step": 18605, "token_acc": 0.7980170367267141 }, { "epoch": 1.2047729645305127, "grad_norm": 0.4983987510204315, "learning_rate": 3.4193684798161344e-06, "loss": 0.6228716373443604, "step": 18610, "token_acc": 0.802968739138952 }, { "epoch": 1.205096665075139, "grad_norm": 0.20249317586421967, "learning_rate": 3.4169568221289196e-06, "loss": 0.6217720985412598, "step": 18615, "token_acc": 0.8042036558357033 }, { "epoch": 1.205420365619765, "grad_norm": 0.39047276973724365, "learning_rate": 3.4145455736874957e-06, "loss": 0.598570728302002, "step": 18620, "token_acc": 0.8084812726487788 }, { "epoch": 1.2057440661643912, "grad_norm": 0.37759122252464294, "learning_rate": 3.412134735115214e-06, "loss": 0.644978141784668, "step": 18625, "token_acc": 0.7949539684524318 }, { "epoch": 1.2060677667090176, "grad_norm": 0.5356863141059875, "learning_rate": 3.4097243070353203e-06, "loss": 0.6084518432617188, "step": 18630, "token_acc": 0.8077150497896873 }, { "epoch": 1.2063914672536438, "grad_norm": 0.3367661237716675, "learning_rate": 3.4073142900709555e-06, "loss": 0.6286903381347656, "step": 18635, "token_acc": 0.8016014062388925 }, { "epoch": 1.20671516779827, "grad_norm": 0.236423522233963, "learning_rate": 3.404904684845154e-06, "loss": 0.624141788482666, "step": 18640, "token_acc": 0.8030960648148148 }, { "epoch": 1.207038868342896, "grad_norm": 0.4352697432041168, "learning_rate": 3.4024954919808407e-06, "loss": 0.6246809959411621, "step": 18645, "token_acc": 0.8019012613374937 }, { "epoch": 1.2073625688875222, "grad_norm": 0.3646283447742462, "learning_rate": 3.4000867121008384e-06, "loss": 0.6250272750854492, "step": 18650, "token_acc": 0.8029949241955548 }, { "epoch": 1.2076862694321484, "grad_norm": 0.3750302791595459, "learning_rate": 3.3976783458278606e-06, "loss": 0.6583444118499756, "step": 18655, "token_acc": 0.7932122446819769 }, { "epoch": 1.2080099699767746, "grad_norm": 0.4120241105556488, "learning_rate": 3.3952703937845134e-06, "loss": 0.635031795501709, "step": 18660, "token_acc": 0.8000297584391052 }, { "epoch": 1.2083336705214007, "grad_norm": 0.28929653763771057, "learning_rate": 3.3928628565932976e-06, "loss": 0.6446566104888916, "step": 18665, "token_acc": 0.7984683464750588 }, { "epoch": 1.2086573710660269, "grad_norm": 0.3717767000198364, "learning_rate": 3.3904557348766043e-06, "loss": 0.6312966346740723, "step": 18670, "token_acc": 0.8009141466130609 }, { "epoch": 1.208981071610653, "grad_norm": 0.3473663330078125, "learning_rate": 3.388049029256722e-06, "loss": 0.6251789093017578, "step": 18675, "token_acc": 0.8010611106808148 }, { "epoch": 1.2093047721552792, "grad_norm": 0.3731670081615448, "learning_rate": 3.3856427403558257e-06, "loss": 0.6270302772521973, "step": 18680, "token_acc": 0.8007318627551755 }, { "epoch": 1.2096284726999054, "grad_norm": 0.3265925943851471, "learning_rate": 3.3832368687959856e-06, "loss": 0.6246404647827148, "step": 18685, "token_acc": 0.8012840129548874 }, { "epoch": 1.2099521732445315, "grad_norm": 0.31788745522499084, "learning_rate": 3.3808314151991663e-06, "loss": 0.6194518089294434, "step": 18690, "token_acc": 0.8046154235017567 }, { "epoch": 1.2102758737891577, "grad_norm": 0.3469173014163971, "learning_rate": 3.3784263801872173e-06, "loss": 0.6267891883850097, "step": 18695, "token_acc": 0.8015317429279103 }, { "epoch": 1.2105995743337838, "grad_norm": 0.3908179700374603, "learning_rate": 3.376021764381887e-06, "loss": 0.6108788013458252, "step": 18700, "token_acc": 0.8038278775079197 }, { "epoch": 1.21092327487841, "grad_norm": 0.22625261545181274, "learning_rate": 3.3736175684048144e-06, "loss": 0.6100198268890381, "step": 18705, "token_acc": 0.8066574257688405 }, { "epoch": 1.2112469754230362, "grad_norm": 0.33648356795310974, "learning_rate": 3.3712137928775254e-06, "loss": 0.63448166847229, "step": 18710, "token_acc": 0.7990338225828039 }, { "epoch": 1.2115706759676623, "grad_norm": 0.2898252606391907, "learning_rate": 3.368810438421441e-06, "loss": 0.6338737487792969, "step": 18715, "token_acc": 0.8005715464897416 }, { "epoch": 1.2118943765122885, "grad_norm": 0.2802310585975647, "learning_rate": 3.366407505657873e-06, "loss": 0.6307639122009278, "step": 18720, "token_acc": 0.8012200707361136 }, { "epoch": 1.2122180770569146, "grad_norm": 0.32673728466033936, "learning_rate": 3.3640049952080257e-06, "loss": 0.616549015045166, "step": 18725, "token_acc": 0.8035293955703607 }, { "epoch": 1.2125417776015408, "grad_norm": 0.36775490641593933, "learning_rate": 3.361602907692989e-06, "loss": 0.614573860168457, "step": 18730, "token_acc": 0.804529091005347 }, { "epoch": 1.212865478146167, "grad_norm": 0.2613057792186737, "learning_rate": 3.3592012437337473e-06, "loss": 0.6193789482116699, "step": 18735, "token_acc": 0.8038763689080733 }, { "epoch": 1.2131891786907931, "grad_norm": 0.23184624314308167, "learning_rate": 3.3568000039511785e-06, "loss": 0.6405375003814697, "step": 18740, "token_acc": 0.7975442484081793 }, { "epoch": 1.2135128792354193, "grad_norm": 0.2805694043636322, "learning_rate": 3.354399188966042e-06, "loss": 0.6266468524932861, "step": 18745, "token_acc": 0.8026738276368157 }, { "epoch": 1.2138365797800454, "grad_norm": 0.3150549530982971, "learning_rate": 3.351998799398995e-06, "loss": 0.6338257789611816, "step": 18750, "token_acc": 0.8000570598609814 }, { "epoch": 1.2141602803246716, "grad_norm": 0.3180781900882721, "learning_rate": 3.3495988358705824e-06, "loss": 0.6395044326782227, "step": 18755, "token_acc": 0.7980090288227805 }, { "epoch": 1.2144839808692978, "grad_norm": 0.3807620704174042, "learning_rate": 3.3471992990012413e-06, "loss": 0.6249759674072266, "step": 18760, "token_acc": 0.8000518295188072 }, { "epoch": 1.214807681413924, "grad_norm": 0.29496338963508606, "learning_rate": 3.344800189411292e-06, "loss": 0.5989662170410156, "step": 18765, "token_acc": 0.8100875359020585 }, { "epoch": 1.21513138195855, "grad_norm": 0.41203176975250244, "learning_rate": 3.34240150772095e-06, "loss": 0.6085089683532715, "step": 18770, "token_acc": 0.8054759630690863 }, { "epoch": 1.2154550825031762, "grad_norm": 0.30576398968696594, "learning_rate": 3.3400032545503215e-06, "loss": 0.6147603511810302, "step": 18775, "token_acc": 0.803464269640446 }, { "epoch": 1.2157787830478024, "grad_norm": 0.33139172196388245, "learning_rate": 3.337605430519394e-06, "loss": 0.625623369216919, "step": 18780, "token_acc": 0.8009907373716095 }, { "epoch": 1.2161024835924286, "grad_norm": 0.30986613035202026, "learning_rate": 3.335208036248051e-06, "loss": 0.6371818542480469, "step": 18785, "token_acc": 0.7963621395248947 }, { "epoch": 1.2164261841370547, "grad_norm": 0.32478538155555725, "learning_rate": 3.332811072356067e-06, "loss": 0.633676815032959, "step": 18790, "token_acc": 0.7989247785660777 }, { "epoch": 1.2167498846816809, "grad_norm": 0.24808689951896667, "learning_rate": 3.3304145394630956e-06, "loss": 0.6231534004211425, "step": 18795, "token_acc": 0.8013952444737575 }, { "epoch": 1.217073585226307, "grad_norm": 0.2889174818992615, "learning_rate": 3.328018438188687e-06, "loss": 0.631342887878418, "step": 18800, "token_acc": 0.8002797434077707 }, { "epoch": 1.2173972857709332, "grad_norm": 0.3878679573535919, "learning_rate": 3.325622769152277e-06, "loss": 0.6179977893829346, "step": 18805, "token_acc": 0.8030751426969881 }, { "epoch": 1.2177209863155594, "grad_norm": 0.32273438572883606, "learning_rate": 3.323227532973193e-06, "loss": 0.615810775756836, "step": 18810, "token_acc": 0.8042626857026257 }, { "epoch": 1.2180446868601855, "grad_norm": 0.2748754322528839, "learning_rate": 3.3208327302706435e-06, "loss": 0.5945996761322021, "step": 18815, "token_acc": 0.8088291307991163 }, { "epoch": 1.218368387404812, "grad_norm": 0.2937580943107605, "learning_rate": 3.3184383616637308e-06, "loss": 0.6171652793884277, "step": 18820, "token_acc": 0.8021692982509804 }, { "epoch": 1.218692087949438, "grad_norm": 0.3073596954345703, "learning_rate": 3.3160444277714454e-06, "loss": 0.6229289054870606, "step": 18825, "token_acc": 0.8034262791003551 }, { "epoch": 1.2190157884940642, "grad_norm": 0.37123748660087585, "learning_rate": 3.3136509292126585e-06, "loss": 0.6197457313537598, "step": 18830, "token_acc": 0.8039492055929434 }, { "epoch": 1.2193394890386904, "grad_norm": 0.3117351233959198, "learning_rate": 3.311257866606137e-06, "loss": 0.6319702625274658, "step": 18835, "token_acc": 0.8008394431337428 }, { "epoch": 1.2196631895833165, "grad_norm": 0.3139258623123169, "learning_rate": 3.3088652405705312e-06, "loss": 0.6018089294433594, "step": 18840, "token_acc": 0.8076644841707742 }, { "epoch": 1.2199868901279427, "grad_norm": 0.26976627111434937, "learning_rate": 3.306473051724378e-06, "loss": 0.6371292114257813, "step": 18845, "token_acc": 0.7991487892489825 }, { "epoch": 1.2203105906725689, "grad_norm": 0.3826313614845276, "learning_rate": 3.304081300686103e-06, "loss": 0.6328818321228027, "step": 18850, "token_acc": 0.8000828366643501 }, { "epoch": 1.220634291217195, "grad_norm": 0.26813164353370667, "learning_rate": 3.3016899880740173e-06, "loss": 0.6129944801330567, "step": 18855, "token_acc": 0.8057895481081955 }, { "epoch": 1.2209579917618212, "grad_norm": 0.36768317222595215, "learning_rate": 3.29929911450632e-06, "loss": 0.6602572441101074, "step": 18860, "token_acc": 0.7944982143781377 }, { "epoch": 1.2212816923064473, "grad_norm": 0.23766718804836273, "learning_rate": 3.296908680601095e-06, "loss": 0.6256033897399902, "step": 18865, "token_acc": 0.8025288497158714 }, { "epoch": 1.2216053928510735, "grad_norm": 0.31890448927879333, "learning_rate": 3.2945186869763145e-06, "loss": 0.6277640342712403, "step": 18870, "token_acc": 0.8017608323934952 }, { "epoch": 1.2219290933956997, "grad_norm": 0.34700462222099304, "learning_rate": 3.292129134249835e-06, "loss": 0.6295609474182129, "step": 18875, "token_acc": 0.8012123086040415 }, { "epoch": 1.2222527939403258, "grad_norm": 0.47757792472839355, "learning_rate": 3.2897400230393994e-06, "loss": 0.6303866386413575, "step": 18880, "token_acc": 0.800712232096184 }, { "epoch": 1.222576494484952, "grad_norm": 0.26521795988082886, "learning_rate": 3.287351353962639e-06, "loss": 0.6263755798339844, "step": 18885, "token_acc": 0.8017328749428668 }, { "epoch": 1.2229001950295781, "grad_norm": 0.3856441080570221, "learning_rate": 3.2849631276370654e-06, "loss": 0.6344245910644531, "step": 18890, "token_acc": 0.7993673230927071 }, { "epoch": 1.2232238955742043, "grad_norm": 0.3444088399410248, "learning_rate": 3.2825753446800824e-06, "loss": 0.6299821853637695, "step": 18895, "token_acc": 0.8012388330991453 }, { "epoch": 1.2235475961188305, "grad_norm": 0.3032453954219818, "learning_rate": 3.280188005708974e-06, "loss": 0.5996214866638183, "step": 18900, "token_acc": 0.8078627303204345 }, { "epoch": 1.2238712966634566, "grad_norm": 0.2357558012008667, "learning_rate": 3.27780111134091e-06, "loss": 0.615103816986084, "step": 18905, "token_acc": 0.803053656590567 }, { "epoch": 1.2241949972080828, "grad_norm": 0.36387407779693604, "learning_rate": 3.2754146621929508e-06, "loss": 0.6272562503814697, "step": 18910, "token_acc": 0.802043012909221 }, { "epoch": 1.224518697752709, "grad_norm": 0.4208310544490814, "learning_rate": 3.273028658882034e-06, "loss": 0.6387053489685058, "step": 18915, "token_acc": 0.8003422955193265 }, { "epoch": 1.224842398297335, "grad_norm": 0.25859567523002625, "learning_rate": 3.2706431020249844e-06, "loss": 0.6069917678833008, "step": 18920, "token_acc": 0.8053171962459219 }, { "epoch": 1.2251660988419613, "grad_norm": 0.31561923027038574, "learning_rate": 3.268257992238516e-06, "loss": 0.6201354026794433, "step": 18925, "token_acc": 0.8025909851495503 }, { "epoch": 1.2254897993865874, "grad_norm": 0.2542497515678406, "learning_rate": 3.265873330139221e-06, "loss": 0.6087800979614257, "step": 18930, "token_acc": 0.8065770236869882 }, { "epoch": 1.2258134999312136, "grad_norm": 0.27839455008506775, "learning_rate": 3.263489116343578e-06, "loss": 0.6098904609680176, "step": 18935, "token_acc": 0.8042162021698175 }, { "epoch": 1.2261372004758397, "grad_norm": 0.30196985602378845, "learning_rate": 3.2611053514679514e-06, "loss": 0.6160216331481934, "step": 18940, "token_acc": 0.8038717018899225 }, { "epoch": 1.226460901020466, "grad_norm": 0.25067248940467834, "learning_rate": 3.25872203612859e-06, "loss": 0.6282790660858154, "step": 18945, "token_acc": 0.8010515206004222 }, { "epoch": 1.226784601565092, "grad_norm": 0.40800240635871887, "learning_rate": 3.2563391709416208e-06, "loss": 0.6310308456420899, "step": 18950, "token_acc": 0.8003810078185979 }, { "epoch": 1.2271083021097182, "grad_norm": 0.34009960293769836, "learning_rate": 3.25395675652306e-06, "loss": 0.6243535995483398, "step": 18955, "token_acc": 0.8031911612509681 }, { "epoch": 1.2274320026543444, "grad_norm": 0.36196669936180115, "learning_rate": 3.2515747934888086e-06, "loss": 0.6353584289550781, "step": 18960, "token_acc": 0.7978876965180304 }, { "epoch": 1.2277557031989705, "grad_norm": 0.2994627356529236, "learning_rate": 3.2491932824546425e-06, "loss": 0.6179667472839355, "step": 18965, "token_acc": 0.8045144637526236 }, { "epoch": 1.228079403743597, "grad_norm": 0.34697574377059937, "learning_rate": 3.2468122240362287e-06, "loss": 0.6020749092102051, "step": 18970, "token_acc": 0.8087412142125084 }, { "epoch": 1.228403104288223, "grad_norm": 0.4198412597179413, "learning_rate": 3.2444316188491145e-06, "loss": 0.6308735847473145, "step": 18975, "token_acc": 0.8015654856751078 }, { "epoch": 1.2287268048328492, "grad_norm": 0.28651565313339233, "learning_rate": 3.2420514675087323e-06, "loss": 0.622983741760254, "step": 18980, "token_acc": 0.8008466764535181 }, { "epoch": 1.2290505053774754, "grad_norm": 0.36606407165527344, "learning_rate": 3.239671770630391e-06, "loss": 0.6020960807800293, "step": 18985, "token_acc": 0.8077641752577319 }, { "epoch": 1.2293742059221016, "grad_norm": 0.2668049931526184, "learning_rate": 3.237292528829288e-06, "loss": 0.6104489803314209, "step": 18990, "token_acc": 0.8050521951781274 }, { "epoch": 1.2296979064667277, "grad_norm": 0.23527289927005768, "learning_rate": 3.234913742720503e-06, "loss": 0.6216144561767578, "step": 18995, "token_acc": 0.803420735883812 }, { "epoch": 1.2300216070113539, "grad_norm": 0.3481377363204956, "learning_rate": 3.2325354129189923e-06, "loss": 0.6248671054840088, "step": 19000, "token_acc": 0.8026757668066514 }, { "epoch": 1.23034530755598, "grad_norm": 0.2662349045276642, "learning_rate": 3.230157540039599e-06, "loss": 0.6460274696350098, "step": 19005, "token_acc": 0.796726869259693 }, { "epoch": 1.2306690081006062, "grad_norm": 0.32007667422294617, "learning_rate": 3.2277801246970507e-06, "loss": 0.6221335411071778, "step": 19010, "token_acc": 0.8035697421852867 }, { "epoch": 1.2309927086452324, "grad_norm": 0.277351051568985, "learning_rate": 3.225403167505947e-06, "loss": 0.598116111755371, "step": 19015, "token_acc": 0.8081941290158846 }, { "epoch": 1.2313164091898585, "grad_norm": 0.29838094115257263, "learning_rate": 3.223026669080779e-06, "loss": 0.5976141929626465, "step": 19020, "token_acc": 0.8085059134508621 }, { "epoch": 1.2316401097344847, "grad_norm": 0.2737061679363251, "learning_rate": 3.2206506300359135e-06, "loss": 0.617525863647461, "step": 19025, "token_acc": 0.802133107522329 }, { "epoch": 1.2319638102791108, "grad_norm": 0.2665901780128479, "learning_rate": 3.218275050985604e-06, "loss": 0.619525146484375, "step": 19030, "token_acc": 0.8018823178664354 }, { "epoch": 1.232287510823737, "grad_norm": 0.3440539836883545, "learning_rate": 3.2158999325439753e-06, "loss": 0.6372980117797852, "step": 19035, "token_acc": 0.8016888806533162 }, { "epoch": 1.2326112113683632, "grad_norm": 0.303699791431427, "learning_rate": 3.2135252753250435e-06, "loss": 0.609926414489746, "step": 19040, "token_acc": 0.8050140584212964 }, { "epoch": 1.2329349119129893, "grad_norm": 0.2997934818267822, "learning_rate": 3.211151079942702e-06, "loss": 0.6427441596984863, "step": 19045, "token_acc": 0.7967457008528596 }, { "epoch": 1.2332586124576155, "grad_norm": 0.3484754264354706, "learning_rate": 3.20877734701072e-06, "loss": 0.6402244567871094, "step": 19050, "token_acc": 0.7977249902360096 }, { "epoch": 1.2335823130022416, "grad_norm": 0.3178541958332062, "learning_rate": 3.2064040771427528e-06, "loss": 0.6410377025604248, "step": 19055, "token_acc": 0.796236592260988 }, { "epoch": 1.2339060135468678, "grad_norm": 0.2652462422847748, "learning_rate": 3.204031270952338e-06, "loss": 0.6117690563201904, "step": 19060, "token_acc": 0.804405818714766 }, { "epoch": 1.234229714091494, "grad_norm": 0.2904297113418579, "learning_rate": 3.2016589290528834e-06, "loss": 0.5922319889068604, "step": 19065, "token_acc": 0.8107539291897213 }, { "epoch": 1.2345534146361201, "grad_norm": 0.36943307518959045, "learning_rate": 3.199287052057687e-06, "loss": 0.6179083824157715, "step": 19070, "token_acc": 0.802709931516915 }, { "epoch": 1.2348771151807463, "grad_norm": 0.2691804766654968, "learning_rate": 3.1969156405799205e-06, "loss": 0.5904866695404053, "step": 19075, "token_acc": 0.8114527626294931 }, { "epoch": 1.2352008157253724, "grad_norm": 0.3139227330684662, "learning_rate": 3.1945446952326415e-06, "loss": 0.6171134948730469, "step": 19080, "token_acc": 0.805242181086306 }, { "epoch": 1.2355245162699986, "grad_norm": 0.3757123351097107, "learning_rate": 3.192174216628778e-06, "loss": 0.6150058269500732, "step": 19085, "token_acc": 0.8039387668398043 }, { "epoch": 1.2358482168146248, "grad_norm": 0.4168417751789093, "learning_rate": 3.1898042053811448e-06, "loss": 0.6055020332336426, "step": 19090, "token_acc": 0.8058475849038321 }, { "epoch": 1.236171917359251, "grad_norm": 0.24963533878326416, "learning_rate": 3.187434662102434e-06, "loss": 0.6135873794555664, "step": 19095, "token_acc": 0.8053272422035411 }, { "epoch": 1.236495617903877, "grad_norm": 0.3444659411907196, "learning_rate": 3.1850655874052146e-06, "loss": 0.6207131385803223, "step": 19100, "token_acc": 0.8039840839074134 }, { "epoch": 1.2368193184485032, "grad_norm": 0.2798454165458679, "learning_rate": 3.182696981901936e-06, "loss": 0.6189391136169433, "step": 19105, "token_acc": 0.8042206162457282 }, { "epoch": 1.2371430189931294, "grad_norm": 0.2812933623790741, "learning_rate": 3.1803288462049274e-06, "loss": 0.6076537132263183, "step": 19110, "token_acc": 0.8063169715337157 }, { "epoch": 1.2374667195377556, "grad_norm": 0.3030747175216675, "learning_rate": 3.1779611809263962e-06, "loss": 0.6221494674682617, "step": 19115, "token_acc": 0.8031994392053646 }, { "epoch": 1.2377904200823817, "grad_norm": 0.3674096465110779, "learning_rate": 3.175593986678425e-06, "loss": 0.609901762008667, "step": 19120, "token_acc": 0.8066110323975839 }, { "epoch": 1.2381141206270079, "grad_norm": 0.3580731451511383, "learning_rate": 3.173227264072979e-06, "loss": 0.596552562713623, "step": 19125, "token_acc": 0.8103309427334006 }, { "epoch": 1.238437821171634, "grad_norm": 0.3267006576061249, "learning_rate": 3.1708610137218986e-06, "loss": 0.6314499855041504, "step": 19130, "token_acc": 0.7988174314662201 }, { "epoch": 1.2387615217162602, "grad_norm": 0.3199635446071625, "learning_rate": 3.1684952362369036e-06, "loss": 0.6211413860321044, "step": 19135, "token_acc": 0.8024562960803927 }, { "epoch": 1.2390852222608864, "grad_norm": 0.3279268443584442, "learning_rate": 3.166129932229589e-06, "loss": 0.621574592590332, "step": 19140, "token_acc": 0.8018287505714845 }, { "epoch": 1.2394089228055125, "grad_norm": 0.29808756709098816, "learning_rate": 3.1637651023114336e-06, "loss": 0.6155692100524902, "step": 19145, "token_acc": 0.8048159281166166 }, { "epoch": 1.2397326233501387, "grad_norm": 0.27250972390174866, "learning_rate": 3.161400747093786e-06, "loss": 0.6305953979492187, "step": 19150, "token_acc": 0.8018307817557236 }, { "epoch": 1.2400563238947648, "grad_norm": 0.3636341094970703, "learning_rate": 3.159036867187876e-06, "loss": 0.6243887901306152, "step": 19155, "token_acc": 0.803717864377414 }, { "epoch": 1.2403800244393912, "grad_norm": 0.2986609935760498, "learning_rate": 3.15667346320481e-06, "loss": 0.6178470134735108, "step": 19160, "token_acc": 0.8033433039494605 }, { "epoch": 1.2407037249840174, "grad_norm": 0.26871585845947266, "learning_rate": 3.1543105357555744e-06, "loss": 0.6005047798156739, "step": 19165, "token_acc": 0.8081584987717956 }, { "epoch": 1.2410274255286435, "grad_norm": 0.3183102011680603, "learning_rate": 3.1519480854510244e-06, "loss": 0.6214500427246094, "step": 19170, "token_acc": 0.8022404761616724 }, { "epoch": 1.2413511260732697, "grad_norm": 0.3520636558532715, "learning_rate": 3.1495861129019003e-06, "loss": 0.5988668441772461, "step": 19175, "token_acc": 0.8092901598716532 }, { "epoch": 1.2416748266178959, "grad_norm": 0.3568309545516968, "learning_rate": 3.147224618718816e-06, "loss": 0.6182838439941406, "step": 19180, "token_acc": 0.8048201654339762 }, { "epoch": 1.241998527162522, "grad_norm": 0.3637233078479767, "learning_rate": 3.1448636035122584e-06, "loss": 0.6306174278259278, "step": 19185, "token_acc": 0.7998815988241539 }, { "epoch": 1.2423222277071482, "grad_norm": 0.4156244397163391, "learning_rate": 3.142503067892594e-06, "loss": 0.6465287208557129, "step": 19190, "token_acc": 0.7975770737003917 }, { "epoch": 1.2426459282517743, "grad_norm": 0.28284013271331787, "learning_rate": 3.140143012470068e-06, "loss": 0.6254690647125244, "step": 19195, "token_acc": 0.8012840474660271 }, { "epoch": 1.2429696287964005, "grad_norm": 0.29677605628967285, "learning_rate": 3.1377834378547945e-06, "loss": 0.5814340591430665, "step": 19200, "token_acc": 0.8135017212897694 }, { "epoch": 1.2432933293410267, "grad_norm": 0.28114083409309387, "learning_rate": 3.1354243446567668e-06, "loss": 0.6461165904998779, "step": 19205, "token_acc": 0.7969093596414281 }, { "epoch": 1.2436170298856528, "grad_norm": 0.35215410590171814, "learning_rate": 3.133065733485856e-06, "loss": 0.6468104362487793, "step": 19210, "token_acc": 0.7969530599500416 }, { "epoch": 1.243940730430279, "grad_norm": 0.3434752821922302, "learning_rate": 3.1307076049518075e-06, "loss": 0.6112377166748046, "step": 19215, "token_acc": 0.8053593834020434 }, { "epoch": 1.2442644309749051, "grad_norm": 0.2804746925830841, "learning_rate": 3.128349959664237e-06, "loss": 0.6045788764953614, "step": 19220, "token_acc": 0.8072810420916496 }, { "epoch": 1.2445881315195313, "grad_norm": 0.2971060872077942, "learning_rate": 3.1259927982326416e-06, "loss": 0.6065140247344971, "step": 19225, "token_acc": 0.8066430620918551 }, { "epoch": 1.2449118320641575, "grad_norm": 0.3075355887413025, "learning_rate": 3.1236361212663924e-06, "loss": 0.6141580581665039, "step": 19230, "token_acc": 0.8055134398175899 }, { "epoch": 1.2452355326087836, "grad_norm": 0.38255926966667175, "learning_rate": 3.12127992937473e-06, "loss": 0.6194339752197265, "step": 19235, "token_acc": 0.8024276020261876 }, { "epoch": 1.2455592331534098, "grad_norm": 0.27667751908302307, "learning_rate": 3.118924223166775e-06, "loss": 0.629131555557251, "step": 19240, "token_acc": 0.8013171598358145 }, { "epoch": 1.245882933698036, "grad_norm": 0.3214813768863678, "learning_rate": 3.1165690032515216e-06, "loss": 0.6205561637878418, "step": 19245, "token_acc": 0.8025248161183587 }, { "epoch": 1.246206634242662, "grad_norm": 0.3909700810909271, "learning_rate": 3.1142142702378393e-06, "loss": 0.6072228431701661, "step": 19250, "token_acc": 0.8059964607050113 }, { "epoch": 1.2465303347872883, "grad_norm": 0.3747158348560333, "learning_rate": 3.111860024734465e-06, "loss": 0.587615966796875, "step": 19255, "token_acc": 0.8118452190598018 }, { "epoch": 1.2468540353319144, "grad_norm": 0.3419308364391327, "learning_rate": 3.1095062673500177e-06, "loss": 0.6208330154418945, "step": 19260, "token_acc": 0.8030348005540949 }, { "epoch": 1.2471777358765406, "grad_norm": 0.2782246172428131, "learning_rate": 3.1071529986929878e-06, "loss": 0.6156245231628418, "step": 19265, "token_acc": 0.8039041358140863 }, { "epoch": 1.2475014364211667, "grad_norm": 0.3290284276008606, "learning_rate": 3.104800219371735e-06, "loss": 0.6284926414489747, "step": 19270, "token_acc": 0.8012916862376702 }, { "epoch": 1.247825136965793, "grad_norm": 0.32093149423599243, "learning_rate": 3.1024479299944987e-06, "loss": 0.6164314270019531, "step": 19275, "token_acc": 0.8037180635503247 }, { "epoch": 1.248148837510419, "grad_norm": 0.3365514874458313, "learning_rate": 3.100096131169391e-06, "loss": 0.6291670322418212, "step": 19280, "token_acc": 0.8018245341614907 }, { "epoch": 1.2484725380550452, "grad_norm": 0.2848471403121948, "learning_rate": 3.09774482350439e-06, "loss": 0.6361137390136719, "step": 19285, "token_acc": 0.7996590692999375 }, { "epoch": 1.2487962385996714, "grad_norm": 0.27741739153862, "learning_rate": 3.095394007607355e-06, "loss": 0.6463765144348145, "step": 19290, "token_acc": 0.7975836651276396 }, { "epoch": 1.2491199391442975, "grad_norm": 0.290103942155838, "learning_rate": 3.0930436840860144e-06, "loss": 0.6097134590148926, "step": 19295, "token_acc": 0.8064573716559129 }, { "epoch": 1.2494436396889237, "grad_norm": 0.32424089312553406, "learning_rate": 3.0906938535479727e-06, "loss": 0.6023729801177978, "step": 19300, "token_acc": 0.8071463043164882 }, { "epoch": 1.2497673402335499, "grad_norm": 0.34114569425582886, "learning_rate": 3.0883445166007e-06, "loss": 0.6090749263763428, "step": 19305, "token_acc": 0.8064681240823803 }, { "epoch": 1.2500910407781762, "grad_norm": 0.3601621091365814, "learning_rate": 3.085995673851545e-06, "loss": 0.6225173473358154, "step": 19310, "token_acc": 0.8024931655265379 }, { "epoch": 1.2504147413228024, "grad_norm": 0.22402358055114746, "learning_rate": 3.0836473259077297e-06, "loss": 0.6326221942901611, "step": 19315, "token_acc": 0.8015636589132206 }, { "epoch": 1.2507384418674286, "grad_norm": 0.3093034327030182, "learning_rate": 3.0812994733763403e-06, "loss": 0.6266666412353515, "step": 19320, "token_acc": 0.8023970949392331 }, { "epoch": 1.2510621424120547, "grad_norm": 0.26374542713165283, "learning_rate": 3.078952116864342e-06, "loss": 0.6147754669189454, "step": 19325, "token_acc": 0.8049239755594554 }, { "epoch": 1.2513858429566809, "grad_norm": 0.27802661061286926, "learning_rate": 3.0766052569785724e-06, "loss": 0.6241950988769531, "step": 19330, "token_acc": 0.8019960779292544 }, { "epoch": 1.251709543501307, "grad_norm": 0.3545980453491211, "learning_rate": 3.0742588943257334e-06, "loss": 0.6215571880340576, "step": 19335, "token_acc": 0.8027073005409285 }, { "epoch": 1.2520332440459332, "grad_norm": 0.3724703788757324, "learning_rate": 3.0719130295124044e-06, "loss": 0.6122665405273438, "step": 19340, "token_acc": 0.805207734564353 }, { "epoch": 1.2523569445905594, "grad_norm": 0.4111080467700958, "learning_rate": 3.069567663145036e-06, "loss": 0.6162185668945312, "step": 19345, "token_acc": 0.8034557903990689 }, { "epoch": 1.2526806451351855, "grad_norm": 0.36017361283302307, "learning_rate": 3.067222795829948e-06, "loss": 0.6020730018615723, "step": 19350, "token_acc": 0.8070929452741341 }, { "epoch": 1.2530043456798117, "grad_norm": 0.36970770359039307, "learning_rate": 3.0648784281733302e-06, "loss": 0.6183114528656006, "step": 19355, "token_acc": 0.8053691275167785 }, { "epoch": 1.2533280462244378, "grad_norm": 0.3600511848926544, "learning_rate": 3.062534560781247e-06, "loss": 0.6156142234802247, "step": 19360, "token_acc": 0.8037501400043484 }, { "epoch": 1.253651746769064, "grad_norm": 0.25911441445350647, "learning_rate": 3.060191194259631e-06, "loss": 0.6128152370452881, "step": 19365, "token_acc": 0.804284977089175 }, { "epoch": 1.2539754473136902, "grad_norm": 0.27928099036216736, "learning_rate": 3.0578483292142837e-06, "loss": 0.5847885131835937, "step": 19370, "token_acc": 0.8123248974087722 }, { "epoch": 1.2542991478583163, "grad_norm": 0.26584869623184204, "learning_rate": 3.05550596625088e-06, "loss": 0.6065710067749024, "step": 19375, "token_acc": 0.8073130733708891 }, { "epoch": 1.2546228484029425, "grad_norm": 0.2730410099029541, "learning_rate": 3.053164105974964e-06, "loss": 0.6438397407531739, "step": 19380, "token_acc": 0.7975580747839598 }, { "epoch": 1.2549465489475686, "grad_norm": 0.24624764919281006, "learning_rate": 3.0508227489919497e-06, "loss": 0.6248265266418457, "step": 19385, "token_acc": 0.8014605449996619 }, { "epoch": 1.2552702494921948, "grad_norm": 0.34175771474838257, "learning_rate": 3.0484818959071204e-06, "loss": 0.6332680225372315, "step": 19390, "token_acc": 0.7988252256859361 }, { "epoch": 1.255593950036821, "grad_norm": 0.3572083115577698, "learning_rate": 3.0461415473256295e-06, "loss": 0.6210708618164062, "step": 19395, "token_acc": 0.8025714713951503 }, { "epoch": 1.255917650581447, "grad_norm": 0.37425389885902405, "learning_rate": 3.0438017038525013e-06, "loss": 0.6327019214630127, "step": 19400, "token_acc": 0.7994596158144549 }, { "epoch": 1.2562413511260733, "grad_norm": 0.3467825651168823, "learning_rate": 3.0414623660926286e-06, "loss": 0.610308837890625, "step": 19405, "token_acc": 0.8066273831022351 }, { "epoch": 1.2565650516706994, "grad_norm": 0.28783559799194336, "learning_rate": 3.0391235346507706e-06, "loss": 0.6310204029083252, "step": 19410, "token_acc": 0.7998207063621868 }, { "epoch": 1.2568887522153256, "grad_norm": 0.26033294200897217, "learning_rate": 3.0367852101315614e-06, "loss": 0.6055438995361329, "step": 19415, "token_acc": 0.806760924034252 }, { "epoch": 1.2572124527599517, "grad_norm": 0.31837061047554016, "learning_rate": 3.0344473931395004e-06, "loss": 0.5982202529907227, "step": 19420, "token_acc": 0.8101356928257784 }, { "epoch": 1.257536153304578, "grad_norm": 0.2818829417228699, "learning_rate": 3.032110084278953e-06, "loss": 0.6274510860443115, "step": 19425, "token_acc": 0.8017541098536334 }, { "epoch": 1.257859853849204, "grad_norm": 0.3749551475048065, "learning_rate": 3.02977328415416e-06, "loss": 0.6090528488159179, "step": 19430, "token_acc": 0.8065335932295393 }, { "epoch": 1.2581835543938302, "grad_norm": 0.34855952858924866, "learning_rate": 3.0274369933692283e-06, "loss": 0.6347358226776123, "step": 19435, "token_acc": 0.8012105623484398 }, { "epoch": 1.2585072549384564, "grad_norm": 0.3299182653427124, "learning_rate": 3.025101212528128e-06, "loss": 0.6112741470336914, "step": 19440, "token_acc": 0.8072764726956344 }, { "epoch": 1.2588309554830825, "grad_norm": 0.2684144973754883, "learning_rate": 3.0227659422347035e-06, "loss": 0.6146764755249023, "step": 19445, "token_acc": 0.8053673788431475 }, { "epoch": 1.2591546560277087, "grad_norm": 0.32486772537231445, "learning_rate": 3.0204311830926667e-06, "loss": 0.6273011207580567, "step": 19450, "token_acc": 0.8011878874427965 }, { "epoch": 1.2594783565723349, "grad_norm": 0.3680625259876251, "learning_rate": 3.0180969357055924e-06, "loss": 0.6243034839630127, "step": 19455, "token_acc": 0.8013703285797795 }, { "epoch": 1.259802057116961, "grad_norm": 0.25200721621513367, "learning_rate": 3.0157632006769283e-06, "loss": 0.5933506965637207, "step": 19460, "token_acc": 0.810075034106412 }, { "epoch": 1.2601257576615872, "grad_norm": 0.34103164076805115, "learning_rate": 3.0134299786099903e-06, "loss": 0.5887683391571045, "step": 19465, "token_acc": 0.8117542925404068 }, { "epoch": 1.2604494582062133, "grad_norm": 0.332650363445282, "learning_rate": 3.0110972701079542e-06, "loss": 0.6281244277954101, "step": 19470, "token_acc": 0.8010512398826223 }, { "epoch": 1.2607731587508395, "grad_norm": 0.39359918236732483, "learning_rate": 3.008765075773871e-06, "loss": 0.6417391777038575, "step": 19475, "token_acc": 0.7966066294812886 }, { "epoch": 1.2610968592954657, "grad_norm": 0.2957621216773987, "learning_rate": 3.0064333962106556e-06, "loss": 0.6318447113037109, "step": 19480, "token_acc": 0.8001738622549119 }, { "epoch": 1.2614205598400918, "grad_norm": 0.30030107498168945, "learning_rate": 3.004102232021092e-06, "loss": 0.6170343399047852, "step": 19485, "token_acc": 0.8040431338261399 }, { "epoch": 1.261744260384718, "grad_norm": 0.4751039147377014, "learning_rate": 3.001771583807825e-06, "loss": 0.6115421295166016, "step": 19490, "token_acc": 0.8051629911027935 }, { "epoch": 1.2620679609293441, "grad_norm": 0.3429533541202545, "learning_rate": 2.9994414521733716e-06, "loss": 0.606267261505127, "step": 19495, "token_acc": 0.8070004984132793 }, { "epoch": 1.2623916614739703, "grad_norm": 0.2817710340023041, "learning_rate": 2.997111837720117e-06, "loss": 0.6296887397766113, "step": 19500, "token_acc": 0.8004085015302493 }, { "epoch": 1.2627153620185965, "grad_norm": 0.26054659485816956, "learning_rate": 2.9947827410503037e-06, "loss": 0.603855037689209, "step": 19505, "token_acc": 0.8077009467930872 }, { "epoch": 1.2630390625632226, "grad_norm": 0.30132725834846497, "learning_rate": 2.99245416276605e-06, "loss": 0.5847749710083008, "step": 19510, "token_acc": 0.8127560093512098 }, { "epoch": 1.263362763107849, "grad_norm": 0.3201838731765747, "learning_rate": 2.990126103469334e-06, "loss": 0.625638484954834, "step": 19515, "token_acc": 0.8016819977292351 }, { "epoch": 1.2636864636524752, "grad_norm": 0.2587350904941559, "learning_rate": 2.987798563762006e-06, "loss": 0.6136750698089599, "step": 19520, "token_acc": 0.8048178381905712 }, { "epoch": 1.2640101641971013, "grad_norm": 0.3198261260986328, "learning_rate": 2.9854715442457727e-06, "loss": 0.6142924308776856, "step": 19525, "token_acc": 0.80354751623737 }, { "epoch": 1.2643338647417275, "grad_norm": 0.31724289059638977, "learning_rate": 2.9831450455222133e-06, "loss": 0.6291851043701172, "step": 19530, "token_acc": 0.8021570499823407 }, { "epoch": 1.2646575652863536, "grad_norm": 0.2563813626766205, "learning_rate": 2.980819068192773e-06, "loss": 0.6035582542419433, "step": 19535, "token_acc": 0.8064664315728318 }, { "epoch": 1.2649812658309798, "grad_norm": 0.32174357771873474, "learning_rate": 2.978493612858756e-06, "loss": 0.6082185745239258, "step": 19540, "token_acc": 0.8058177076865765 }, { "epoch": 1.265304966375606, "grad_norm": 0.3817827105522156, "learning_rate": 2.9761686801213365e-06, "loss": 0.5843557834625244, "step": 19545, "token_acc": 0.8123855211513301 }, { "epoch": 1.2656286669202321, "grad_norm": 0.30674323439598083, "learning_rate": 2.973844270581555e-06, "loss": 0.6091116905212403, "step": 19550, "token_acc": 0.805147155346688 }, { "epoch": 1.2659523674648583, "grad_norm": 0.3875325322151184, "learning_rate": 2.9715203848403097e-06, "loss": 0.6020811080932618, "step": 19555, "token_acc": 0.8091441725570779 }, { "epoch": 1.2662760680094844, "grad_norm": 0.40584591031074524, "learning_rate": 2.9691970234983702e-06, "loss": 0.6283939361572266, "step": 19560, "token_acc": 0.8011117018055061 }, { "epoch": 1.2665997685541106, "grad_norm": 0.29301217198371887, "learning_rate": 2.9668741871563678e-06, "loss": 0.6048903942108155, "step": 19565, "token_acc": 0.8066981733943647 }, { "epoch": 1.2669234690987368, "grad_norm": 0.33918604254722595, "learning_rate": 2.964551876414801e-06, "loss": 0.6276168346405029, "step": 19570, "token_acc": 0.801896788540781 }, { "epoch": 1.267247169643363, "grad_norm": 0.33262595534324646, "learning_rate": 2.9622300918740255e-06, "loss": 0.6144407272338868, "step": 19575, "token_acc": 0.8047895222000307 }, { "epoch": 1.267570870187989, "grad_norm": 0.2982296645641327, "learning_rate": 2.9599088341342673e-06, "loss": 0.6156074523925781, "step": 19580, "token_acc": 0.8046692200101959 }, { "epoch": 1.2678945707326152, "grad_norm": 0.355374276638031, "learning_rate": 2.9575881037956155e-06, "loss": 0.6037055969238281, "step": 19585, "token_acc": 0.8065225403845909 }, { "epoch": 1.2682182712772414, "grad_norm": 0.34012889862060547, "learning_rate": 2.955267901458019e-06, "loss": 0.6368214130401612, "step": 19590, "token_acc": 0.7973235271282265 }, { "epoch": 1.2685419718218676, "grad_norm": 0.30499517917633057, "learning_rate": 2.952948227721295e-06, "loss": 0.6097678184509278, "step": 19595, "token_acc": 0.805375992144669 }, { "epoch": 1.2688656723664937, "grad_norm": 0.2894386947154999, "learning_rate": 2.9506290831851202e-06, "loss": 0.6136563301086426, "step": 19600, "token_acc": 0.8047264865452864 }, { "epoch": 1.2691893729111199, "grad_norm": 0.36650556325912476, "learning_rate": 2.948310468449038e-06, "loss": 0.6188548564910888, "step": 19605, "token_acc": 0.8032638930984085 }, { "epoch": 1.269513073455746, "grad_norm": 0.27668800950050354, "learning_rate": 2.9459923841124514e-06, "loss": 0.6173726081848144, "step": 19610, "token_acc": 0.8042351287233108 }, { "epoch": 1.2698367740003722, "grad_norm": 0.3506864309310913, "learning_rate": 2.9436748307746284e-06, "loss": 0.6135253429412841, "step": 19615, "token_acc": 0.8049810469596818 }, { "epoch": 1.2701604745449984, "grad_norm": 0.36539021134376526, "learning_rate": 2.9413578090346996e-06, "loss": 0.6399974822998047, "step": 19620, "token_acc": 0.7984455043278572 }, { "epoch": 1.2704841750896245, "grad_norm": 0.32859334349632263, "learning_rate": 2.939041319491657e-06, "loss": 0.596885871887207, "step": 19625, "token_acc": 0.8087777754782453 }, { "epoch": 1.2708078756342507, "grad_norm": 0.40463021397590637, "learning_rate": 2.936725362744356e-06, "loss": 0.6122856140136719, "step": 19630, "token_acc": 0.8048362815205119 }, { "epoch": 1.2711315761788768, "grad_norm": 0.28254812955856323, "learning_rate": 2.934409939391514e-06, "loss": 0.6175810813903808, "step": 19635, "token_acc": 0.8036613879935387 }, { "epoch": 1.2714552767235032, "grad_norm": 0.3617466390132904, "learning_rate": 2.9320950500317115e-06, "loss": 0.629428482055664, "step": 19640, "token_acc": 0.8019320043691972 }, { "epoch": 1.2717789772681294, "grad_norm": 0.25395551323890686, "learning_rate": 2.9297806952633877e-06, "loss": 0.5925555229187012, "step": 19645, "token_acc": 0.8100112303300093 }, { "epoch": 1.2721026778127555, "grad_norm": 0.3795483708381653, "learning_rate": 2.9274668756848466e-06, "loss": 0.6131149291992187, "step": 19650, "token_acc": 0.8061071049061345 }, { "epoch": 1.2724263783573817, "grad_norm": 0.2965032160282135, "learning_rate": 2.9251535918942574e-06, "loss": 0.6303469181060791, "step": 19655, "token_acc": 0.8011230316429084 }, { "epoch": 1.2727500789020079, "grad_norm": 0.291687935590744, "learning_rate": 2.9228408444896407e-06, "loss": 0.6358710765838623, "step": 19660, "token_acc": 0.7997186365278227 }, { "epoch": 1.273073779446634, "grad_norm": 0.3534797728061676, "learning_rate": 2.9205286340688855e-06, "loss": 0.6548282623291015, "step": 19665, "token_acc": 0.7938749057626939 }, { "epoch": 1.2733974799912602, "grad_norm": 0.30745962262153625, "learning_rate": 2.9182169612297453e-06, "loss": 0.6251636028289795, "step": 19670, "token_acc": 0.8019898788367269 }, { "epoch": 1.2737211805358863, "grad_norm": 0.3933420777320862, "learning_rate": 2.915905826569822e-06, "loss": 0.6039423465728759, "step": 19675, "token_acc": 0.8065229807711245 }, { "epoch": 1.2740448810805125, "grad_norm": 0.25150570273399353, "learning_rate": 2.9135952306865937e-06, "loss": 0.5822381973266602, "step": 19680, "token_acc": 0.8124097665218691 }, { "epoch": 1.2743685816251387, "grad_norm": 0.32777294516563416, "learning_rate": 2.9112851741773896e-06, "loss": 0.6134076595306397, "step": 19685, "token_acc": 0.8052412471577299 }, { "epoch": 1.2746922821697648, "grad_norm": 0.2735702395439148, "learning_rate": 2.908975657639401e-06, "loss": 0.6626788139343261, "step": 19690, "token_acc": 0.7935891003399077 }, { "epoch": 1.275015982714391, "grad_norm": 0.4319666624069214, "learning_rate": 2.9066666816696793e-06, "loss": 0.6198909759521485, "step": 19695, "token_acc": 0.8016168492713541 }, { "epoch": 1.2753396832590171, "grad_norm": 0.30319201946258545, "learning_rate": 2.904358246865141e-06, "loss": 0.6127245903015137, "step": 19700, "token_acc": 0.8060373187356896 }, { "epoch": 1.2756633838036433, "grad_norm": 0.3804927468299866, "learning_rate": 2.9020503538225566e-06, "loss": 0.6270597457885743, "step": 19705, "token_acc": 0.8034886247245414 }, { "epoch": 1.2759870843482695, "grad_norm": 0.3744599223136902, "learning_rate": 2.8997430031385587e-06, "loss": 0.5944416046142578, "step": 19710, "token_acc": 0.808867380976448 }, { "epoch": 1.2763107848928956, "grad_norm": 0.30946260690689087, "learning_rate": 2.897436195409641e-06, "loss": 0.6271055221557618, "step": 19715, "token_acc": 0.8022204303583209 }, { "epoch": 1.2766344854375218, "grad_norm": 0.25997939705848694, "learning_rate": 2.8951299312321547e-06, "loss": 0.6079424858093262, "step": 19720, "token_acc": 0.8076076830066007 }, { "epoch": 1.276958185982148, "grad_norm": 0.25716984272003174, "learning_rate": 2.89282421120231e-06, "loss": 0.6058628559112549, "step": 19725, "token_acc": 0.8069213031835764 }, { "epoch": 1.277281886526774, "grad_norm": 0.3040500283241272, "learning_rate": 2.8905190359161816e-06, "loss": 0.5872179985046386, "step": 19730, "token_acc": 0.8107727809984804 }, { "epoch": 1.2776055870714003, "grad_norm": 0.3412404954433441, "learning_rate": 2.8882144059696988e-06, "loss": 0.6342556953430176, "step": 19735, "token_acc": 0.7997281750662402 }, { "epoch": 1.2779292876160264, "grad_norm": 0.32072481513023376, "learning_rate": 2.8859103219586493e-06, "loss": 0.6502019882202148, "step": 19740, "token_acc": 0.7952165794655773 }, { "epoch": 1.2782529881606526, "grad_norm": 0.32665035128593445, "learning_rate": 2.883606784478683e-06, "loss": 0.6254508972167969, "step": 19745, "token_acc": 0.8013294227641236 }, { "epoch": 1.2785766887052787, "grad_norm": 0.40677937865257263, "learning_rate": 2.881303794125303e-06, "loss": 0.6175901412963867, "step": 19750, "token_acc": 0.8033784600507675 }, { "epoch": 1.278900389249905, "grad_norm": 0.2375747114419937, "learning_rate": 2.8790013514938797e-06, "loss": 0.6108678340911865, "step": 19755, "token_acc": 0.8051977262503578 }, { "epoch": 1.279224089794531, "grad_norm": 0.36438506841659546, "learning_rate": 2.8766994571796336e-06, "loss": 0.6051643371582032, "step": 19760, "token_acc": 0.8074272031740617 }, { "epoch": 1.2795477903391572, "grad_norm": 0.39469262957572937, "learning_rate": 2.8743981117776487e-06, "loss": 0.638046407699585, "step": 19765, "token_acc": 0.798921832884097 }, { "epoch": 1.2798714908837834, "grad_norm": 0.36272838711738586, "learning_rate": 2.8720973158828642e-06, "loss": 0.6360801696777344, "step": 19770, "token_acc": 0.7987768309641023 }, { "epoch": 1.2801951914284095, "grad_norm": 0.38685908913612366, "learning_rate": 2.869797070090078e-06, "loss": 0.6326559066772461, "step": 19775, "token_acc": 0.8003604602800499 }, { "epoch": 1.2805188919730357, "grad_norm": 0.2698027789592743, "learning_rate": 2.8674973749939437e-06, "loss": 0.6393569946289063, "step": 19780, "token_acc": 0.7992851755910417 }, { "epoch": 1.2808425925176619, "grad_norm": 0.38282573223114014, "learning_rate": 2.865198231188979e-06, "loss": 0.6089982986450195, "step": 19785, "token_acc": 0.8055000966059123 }, { "epoch": 1.281166293062288, "grad_norm": 0.5256662964820862, "learning_rate": 2.862899639269554e-06, "loss": 0.6158491611480713, "step": 19790, "token_acc": 0.8029785025149014 }, { "epoch": 1.2814899936069142, "grad_norm": 0.36770519614219666, "learning_rate": 2.860601599829895e-06, "loss": 0.6221898078918457, "step": 19795, "token_acc": 0.800850222810583 }, { "epoch": 1.2818136941515403, "grad_norm": 0.3310930132865906, "learning_rate": 2.8583041134640875e-06, "loss": 0.603096866607666, "step": 19800, "token_acc": 0.807139268693397 }, { "epoch": 1.2821373946961665, "grad_norm": 0.3108057975769043, "learning_rate": 2.8560071807660783e-06, "loss": 0.5830102443695069, "step": 19805, "token_acc": 0.8120203704768659 }, { "epoch": 1.2824610952407927, "grad_norm": 0.2537987530231476, "learning_rate": 2.85371080232966e-06, "loss": 0.6451860904693604, "step": 19810, "token_acc": 0.7972362915657344 }, { "epoch": 1.2827847957854188, "grad_norm": 0.28481602668762207, "learning_rate": 2.851414978748494e-06, "loss": 0.6441250324249268, "step": 19815, "token_acc": 0.7977833336614367 }, { "epoch": 1.283108496330045, "grad_norm": 0.3186216354370117, "learning_rate": 2.8491197106160916e-06, "loss": 0.6269597053527832, "step": 19820, "token_acc": 0.8030892726830455 }, { "epoch": 1.2834321968746711, "grad_norm": 0.2950790524482727, "learning_rate": 2.8468249985258205e-06, "loss": 0.6255053520202637, "step": 19825, "token_acc": 0.8012307692307692 }, { "epoch": 1.2837558974192973, "grad_norm": 0.34559667110443115, "learning_rate": 2.8445308430709058e-06, "loss": 0.6075922012329101, "step": 19830, "token_acc": 0.8053378100589283 }, { "epoch": 1.2840795979639235, "grad_norm": 0.2629946172237396, "learning_rate": 2.8422372448444314e-06, "loss": 0.6181730270385742, "step": 19835, "token_acc": 0.8037180304282803 }, { "epoch": 1.2844032985085496, "grad_norm": 0.3114810585975647, "learning_rate": 2.839944204439333e-06, "loss": 0.608968448638916, "step": 19840, "token_acc": 0.8054441972963844 }, { "epoch": 1.2847269990531758, "grad_norm": 0.5443430542945862, "learning_rate": 2.837651722448405e-06, "loss": 0.6480495929718018, "step": 19845, "token_acc": 0.7962385525436608 }, { "epoch": 1.285050699597802, "grad_norm": 0.24456220865249634, "learning_rate": 2.835359799464292e-06, "loss": 0.6069840431213379, "step": 19850, "token_acc": 0.8064773983826488 }, { "epoch": 1.2853744001424283, "grad_norm": 0.3817525804042816, "learning_rate": 2.8330684360795058e-06, "loss": 0.6035751342773438, "step": 19855, "token_acc": 0.806811118017938 }, { "epoch": 1.2856981006870545, "grad_norm": 0.3464655876159668, "learning_rate": 2.8307776328863978e-06, "loss": 0.6139922618865967, "step": 19860, "token_acc": 0.8040104291965487 }, { "epoch": 1.2860218012316806, "grad_norm": 0.3488127589225769, "learning_rate": 2.828487390477188e-06, "loss": 0.6049383640289306, "step": 19865, "token_acc": 0.8067898994088977 }, { "epoch": 1.2863455017763068, "grad_norm": 0.32594892382621765, "learning_rate": 2.8261977094439437e-06, "loss": 0.6257717132568359, "step": 19870, "token_acc": 0.8021176470588235 }, { "epoch": 1.286669202320933, "grad_norm": 0.4351291358470917, "learning_rate": 2.823908590378594e-06, "loss": 0.621153450012207, "step": 19875, "token_acc": 0.8026027517307861 }, { "epoch": 1.2869929028655591, "grad_norm": 0.2893708050251007, "learning_rate": 2.8216200338729114e-06, "loss": 0.5961470603942871, "step": 19880, "token_acc": 0.8086882757389052 }, { "epoch": 1.2873166034101853, "grad_norm": 0.4021143615245819, "learning_rate": 2.8193320405185354e-06, "loss": 0.5976414680480957, "step": 19885, "token_acc": 0.8097308383947077 }, { "epoch": 1.2876403039548114, "grad_norm": 0.27047425508499146, "learning_rate": 2.8170446109069518e-06, "loss": 0.6107495307922364, "step": 19890, "token_acc": 0.8042542432218663 }, { "epoch": 1.2879640044994376, "grad_norm": 0.4200265407562256, "learning_rate": 2.8147577456295044e-06, "loss": 0.6206868648529053, "step": 19895, "token_acc": 0.8020505314327534 }, { "epoch": 1.2882877050440638, "grad_norm": 0.2971755266189575, "learning_rate": 2.812471445277387e-06, "loss": 0.6028240203857422, "step": 19900, "token_acc": 0.8074453757338808 }, { "epoch": 1.28861140558869, "grad_norm": 0.31178247928619385, "learning_rate": 2.8101857104416576e-06, "loss": 0.6461045265197753, "step": 19905, "token_acc": 0.79775 }, { "epoch": 1.288935106133316, "grad_norm": 0.29862502217292786, "learning_rate": 2.807900541713211e-06, "loss": 0.6337502002716064, "step": 19910, "token_acc": 0.7999550384217123 }, { "epoch": 1.2892588066779422, "grad_norm": 0.3046669065952301, "learning_rate": 2.805615939682812e-06, "loss": 0.6182963848114014, "step": 19915, "token_acc": 0.8032013880143839 }, { "epoch": 1.2895825072225684, "grad_norm": 0.4014977514743805, "learning_rate": 2.803331904941069e-06, "loss": 0.5911067962646485, "step": 19920, "token_acc": 0.8116487090872129 }, { "epoch": 1.2899062077671946, "grad_norm": 0.23965665698051453, "learning_rate": 2.8010484380784523e-06, "loss": 0.5997551918029785, "step": 19925, "token_acc": 0.8070677570093457 }, { "epoch": 1.2902299083118207, "grad_norm": 0.4361426532268524, "learning_rate": 2.7987655396852723e-06, "loss": 0.6116227626800537, "step": 19930, "token_acc": 0.8062666190419494 }, { "epoch": 1.2905536088564469, "grad_norm": 0.3543068468570709, "learning_rate": 2.7964832103517064e-06, "loss": 0.6226283073425293, "step": 19935, "token_acc": 0.8020034114212339 }, { "epoch": 1.290877309401073, "grad_norm": 0.41668501496315, "learning_rate": 2.794201450667776e-06, "loss": 0.6136879920959473, "step": 19940, "token_acc": 0.8042032084816484 }, { "epoch": 1.2912010099456992, "grad_norm": 0.32392311096191406, "learning_rate": 2.7919202612233596e-06, "loss": 0.6228927135467529, "step": 19945, "token_acc": 0.8011528076934745 }, { "epoch": 1.2915247104903254, "grad_norm": 0.3395463824272156, "learning_rate": 2.7896396426081844e-06, "loss": 0.5989672183990479, "step": 19950, "token_acc": 0.806853290304827 }, { "epoch": 1.2918484110349515, "grad_norm": 0.2847698926925659, "learning_rate": 2.7873595954118336e-06, "loss": 0.6402006626129151, "step": 19955, "token_acc": 0.7985489116837629 }, { "epoch": 1.2921721115795777, "grad_norm": 0.4302859306335449, "learning_rate": 2.78508012022374e-06, "loss": 0.6229188442230225, "step": 19960, "token_acc": 0.8026977007633387 }, { "epoch": 1.2924958121242038, "grad_norm": 0.405086874961853, "learning_rate": 2.7828012176331926e-06, "loss": 0.6148734092712402, "step": 19965, "token_acc": 0.8057677503404986 }, { "epoch": 1.29281951266883, "grad_norm": 0.37799254059791565, "learning_rate": 2.7805228882293277e-06, "loss": 0.610033369064331, "step": 19970, "token_acc": 0.8059691015717231 }, { "epoch": 1.2931432132134562, "grad_norm": 0.34888237714767456, "learning_rate": 2.778245132601136e-06, "loss": 0.6123259544372559, "step": 19975, "token_acc": 0.8059610240733664 }, { "epoch": 1.2934669137580823, "grad_norm": 0.32301679253578186, "learning_rate": 2.7759679513374593e-06, "loss": 0.613831615447998, "step": 19980, "token_acc": 0.8054693726517136 }, { "epoch": 1.2937906143027087, "grad_norm": 0.3470699191093445, "learning_rate": 2.7736913450269887e-06, "loss": 0.6284806251525878, "step": 19985, "token_acc": 0.8013647778846589 }, { "epoch": 1.2941143148473349, "grad_norm": 0.3296222388744354, "learning_rate": 2.7714153142582723e-06, "loss": 0.610337209701538, "step": 19990, "token_acc": 0.8068407687243314 }, { "epoch": 1.294438015391961, "grad_norm": 0.37767332792282104, "learning_rate": 2.769139859619705e-06, "loss": 0.5981666564941406, "step": 19995, "token_acc": 0.8094681927898466 }, { "epoch": 1.2947617159365872, "grad_norm": 0.4135221838951111, "learning_rate": 2.766864981699532e-06, "loss": 0.6063864707946778, "step": 20000, "token_acc": 0.8071444677081656 }, { "epoch": 1.2950854164812133, "grad_norm": 0.33008500933647156, "learning_rate": 2.764590681085851e-06, "loss": 0.6277981758117676, "step": 20005, "token_acc": 0.800869823325203 }, { "epoch": 1.2954091170258395, "grad_norm": 0.3405666947364807, "learning_rate": 2.7623169583666155e-06, "loss": 0.615336561203003, "step": 20010, "token_acc": 0.804272264491762 }, { "epoch": 1.2957328175704657, "grad_norm": 0.3321567475795746, "learning_rate": 2.7600438141296165e-06, "loss": 0.6158397674560547, "step": 20015, "token_acc": 0.8040754969099716 }, { "epoch": 1.2960565181150918, "grad_norm": 0.3791981339454651, "learning_rate": 2.75777124896251e-06, "loss": 0.6275372505187988, "step": 20020, "token_acc": 0.8022862728593345 }, { "epoch": 1.296380218659718, "grad_norm": 0.3902549147605896, "learning_rate": 2.7554992634527943e-06, "loss": 0.5980644702911377, "step": 20025, "token_acc": 0.8078895321226112 }, { "epoch": 1.2967039192043441, "grad_norm": 0.2764299213886261, "learning_rate": 2.753227858187819e-06, "loss": 0.6244902610778809, "step": 20030, "token_acc": 0.8036859413537956 }, { "epoch": 1.2970276197489703, "grad_norm": 0.3482162058353424, "learning_rate": 2.750957033754782e-06, "loss": 0.6258597373962402, "step": 20035, "token_acc": 0.8016144034861941 }, { "epoch": 1.2973513202935965, "grad_norm": 0.3028187155723572, "learning_rate": 2.7486867907407394e-06, "loss": 0.629415225982666, "step": 20040, "token_acc": 0.8007080084491616 }, { "epoch": 1.2976750208382226, "grad_norm": 0.33636024594306946, "learning_rate": 2.7464171297325826e-06, "loss": 0.5967544555664063, "step": 20045, "token_acc": 0.8083113425100444 }, { "epoch": 1.2979987213828488, "grad_norm": 0.33586785197257996, "learning_rate": 2.744148051317067e-06, "loss": 0.6075431823730468, "step": 20050, "token_acc": 0.8063903632877759 }, { "epoch": 1.298322421927475, "grad_norm": 0.3326430916786194, "learning_rate": 2.741879556080788e-06, "loss": 0.6123885154724121, "step": 20055, "token_acc": 0.8049561977901817 }, { "epoch": 1.298646122472101, "grad_norm": 0.33909720182418823, "learning_rate": 2.7396116446101973e-06, "loss": 0.6123732566833496, "step": 20060, "token_acc": 0.805954421464729 }, { "epoch": 1.2989698230167273, "grad_norm": 0.3819717466831207, "learning_rate": 2.7373443174915846e-06, "loss": 0.6249608993530273, "step": 20065, "token_acc": 0.802233725451713 }, { "epoch": 1.2992935235613534, "grad_norm": 0.41548407077789307, "learning_rate": 2.735077575311103e-06, "loss": 0.6119152545928955, "step": 20070, "token_acc": 0.8046896261659121 }, { "epoch": 1.2996172241059796, "grad_norm": 0.3132532835006714, "learning_rate": 2.732811418654744e-06, "loss": 0.5941080570220947, "step": 20075, "token_acc": 0.8095520812718517 }, { "epoch": 1.2999409246506057, "grad_norm": 0.3343132734298706, "learning_rate": 2.73054584810835e-06, "loss": 0.6315126895904541, "step": 20080, "token_acc": 0.800586164846738 }, { "epoch": 1.300264625195232, "grad_norm": 0.38393375277519226, "learning_rate": 2.7282808642576118e-06, "loss": 0.6064279556274415, "step": 20085, "token_acc": 0.8048585443257165 }, { "epoch": 1.300588325739858, "grad_norm": 0.35905933380126953, "learning_rate": 2.7260164676880753e-06, "loss": 0.6325490474700928, "step": 20090, "token_acc": 0.7994175735966698 }, { "epoch": 1.3009120262844842, "grad_norm": 0.2695278227329254, "learning_rate": 2.7237526589851193e-06, "loss": 0.6071886539459228, "step": 20095, "token_acc": 0.8069283604871089 }, { "epoch": 1.3012357268291104, "grad_norm": 0.38822633028030396, "learning_rate": 2.7214894387339885e-06, "loss": 0.6177011489868164, "step": 20100, "token_acc": 0.803242063364684 }, { "epoch": 1.3015594273737365, "grad_norm": 0.3589460551738739, "learning_rate": 2.7192268075197615e-06, "loss": 0.5898853302001953, "step": 20105, "token_acc": 0.810542325504919 }, { "epoch": 1.3018831279183627, "grad_norm": 0.31378987431526184, "learning_rate": 2.7169647659273757e-06, "loss": 0.6384511470794678, "step": 20110, "token_acc": 0.79980503493717 }, { "epoch": 1.3022068284629889, "grad_norm": 0.3196277618408203, "learning_rate": 2.714703314541603e-06, "loss": 0.6260396003723144, "step": 20115, "token_acc": 0.8027318081065 }, { "epoch": 1.302530529007615, "grad_norm": 0.6076635718345642, "learning_rate": 2.7124424539470762e-06, "loss": 0.6256596565246582, "step": 20120, "token_acc": 0.8023235428972139 }, { "epoch": 1.3028542295522412, "grad_norm": 0.4071848392486572, "learning_rate": 2.7101821847282676e-06, "loss": 0.6172112464904785, "step": 20125, "token_acc": 0.8052391951613549 }, { "epoch": 1.3031779300968673, "grad_norm": 0.8221994638442993, "learning_rate": 2.707922507469498e-06, "loss": 0.6009257316589356, "step": 20130, "token_acc": 0.808430909980149 }, { "epoch": 1.3035016306414935, "grad_norm": 0.3787896931171417, "learning_rate": 2.705663422754934e-06, "loss": 0.6175362586975097, "step": 20135, "token_acc": 0.8038719490208677 }, { "epoch": 1.3038253311861197, "grad_norm": 0.3020961582660675, "learning_rate": 2.703404931168594e-06, "loss": 0.6023732185363769, "step": 20140, "token_acc": 0.8082312024950292 }, { "epoch": 1.3041490317307458, "grad_norm": 0.3558862805366516, "learning_rate": 2.701147033294338e-06, "loss": 0.6207688808441162, "step": 20145, "token_acc": 0.8015876099089649 }, { "epoch": 1.304472732275372, "grad_norm": 0.2692457437515259, "learning_rate": 2.6988897297158746e-06, "loss": 0.590411376953125, "step": 20150, "token_acc": 0.8103553355109532 }, { "epoch": 1.3047964328199981, "grad_norm": 0.3428630828857422, "learning_rate": 2.6966330210167547e-06, "loss": 0.6214546203613281, "step": 20155, "token_acc": 0.8018360809978762 }, { "epoch": 1.3051201333646243, "grad_norm": 0.35377037525177, "learning_rate": 2.6943769077803865e-06, "loss": 0.6000072479248046, "step": 20160, "token_acc": 0.8092403687734427 }, { "epoch": 1.3054438339092505, "grad_norm": 0.4333164393901825, "learning_rate": 2.692121390590009e-06, "loss": 0.6030070304870605, "step": 20165, "token_acc": 0.808025977464828 }, { "epoch": 1.3057675344538766, "grad_norm": 0.320332407951355, "learning_rate": 2.689866470028719e-06, "loss": 0.6063490867614746, "step": 20170, "token_acc": 0.806371902214332 }, { "epoch": 1.3060912349985028, "grad_norm": 0.3405361771583557, "learning_rate": 2.6876121466794552e-06, "loss": 0.6111227035522461, "step": 20175, "token_acc": 0.8048294796731832 }, { "epoch": 1.306414935543129, "grad_norm": 0.26699650287628174, "learning_rate": 2.6853584211250005e-06, "loss": 0.598191499710083, "step": 20180, "token_acc": 0.809632717135356 }, { "epoch": 1.306738636087755, "grad_norm": 0.34075745940208435, "learning_rate": 2.683105293947983e-06, "loss": 0.6089489459991455, "step": 20185, "token_acc": 0.8063063063063063 }, { "epoch": 1.3070623366323812, "grad_norm": 0.3185068368911743, "learning_rate": 2.6808527657308803e-06, "loss": 0.5912919044494629, "step": 20190, "token_acc": 0.8111594561769665 }, { "epoch": 1.3073860371770076, "grad_norm": 0.30666273832321167, "learning_rate": 2.6786008370560118e-06, "loss": 0.5950634002685546, "step": 20195, "token_acc": 0.808094718803552 }, { "epoch": 1.3077097377216338, "grad_norm": 0.3823400139808655, "learning_rate": 2.676349508505541e-06, "loss": 0.5918362140655518, "step": 20200, "token_acc": 0.811479330372395 }, { "epoch": 1.30803343826626, "grad_norm": 0.2575695812702179, "learning_rate": 2.6740987806614804e-06, "loss": 0.6217640399932861, "step": 20205, "token_acc": 0.8016746062286859 }, { "epoch": 1.3083571388108861, "grad_norm": 0.3376823961734772, "learning_rate": 2.6718486541056823e-06, "loss": 0.5870573043823242, "step": 20210, "token_acc": 0.8112677318584524 }, { "epoch": 1.3086808393555123, "grad_norm": 0.24628986418247223, "learning_rate": 2.6695991294198433e-06, "loss": 0.6183928489685059, "step": 20215, "token_acc": 0.8039051747424205 }, { "epoch": 1.3090045399001384, "grad_norm": 0.35002225637435913, "learning_rate": 2.667350207185513e-06, "loss": 0.6059556484222413, "step": 20220, "token_acc": 0.8062382966464572 }, { "epoch": 1.3093282404447646, "grad_norm": 0.2959648072719574, "learning_rate": 2.6651018879840755e-06, "loss": 0.6362898826599122, "step": 20225, "token_acc": 0.7993998138251128 }, { "epoch": 1.3096519409893908, "grad_norm": 0.28434979915618896, "learning_rate": 2.662854172396764e-06, "loss": 0.6045337677001953, "step": 20230, "token_acc": 0.8066727998358605 }, { "epoch": 1.309975641534017, "grad_norm": 0.23935994505882263, "learning_rate": 2.660607061004653e-06, "loss": 0.5872687816619873, "step": 20235, "token_acc": 0.8107917593767431 }, { "epoch": 1.310299342078643, "grad_norm": 0.30616939067840576, "learning_rate": 2.6583605543886616e-06, "loss": 0.6050528526306153, "step": 20240, "token_acc": 0.8069637334654195 }, { "epoch": 1.3106230426232692, "grad_norm": 0.34297341108322144, "learning_rate": 2.656114653129558e-06, "loss": 0.6020625591278076, "step": 20245, "token_acc": 0.8074753937363248 }, { "epoch": 1.3109467431678954, "grad_norm": 0.22870828211307526, "learning_rate": 2.6538693578079418e-06, "loss": 0.6265586376190185, "step": 20250, "token_acc": 0.8020980292570368 }, { "epoch": 1.3112704437125215, "grad_norm": 0.3866533041000366, "learning_rate": 2.651624669004268e-06, "loss": 0.6023680686950683, "step": 20255, "token_acc": 0.8070720336609383 }, { "epoch": 1.3115941442571477, "grad_norm": 0.26070183515548706, "learning_rate": 2.6493805872988285e-06, "loss": 0.6361178398132324, "step": 20260, "token_acc": 0.7993592470488142 }, { "epoch": 1.3119178448017739, "grad_norm": 0.31589964032173157, "learning_rate": 2.6471371132717607e-06, "loss": 0.6143457412719726, "step": 20265, "token_acc": 0.8061761280736744 }, { "epoch": 1.3122415453464, "grad_norm": 0.3099479079246521, "learning_rate": 2.6448942475030404e-06, "loss": 0.6241928100585937, "step": 20270, "token_acc": 0.8027140838369278 }, { "epoch": 1.3125652458910262, "grad_norm": 0.30029746890068054, "learning_rate": 2.642651990572495e-06, "loss": 0.6251064300537109, "step": 20275, "token_acc": 0.8013026018290419 }, { "epoch": 1.3128889464356523, "grad_norm": 0.3057628571987152, "learning_rate": 2.6404103430597862e-06, "loss": 0.6194153785705566, "step": 20280, "token_acc": 0.8019029569822685 }, { "epoch": 1.3132126469802785, "grad_norm": 0.30282464623451233, "learning_rate": 2.6381693055444215e-06, "loss": 0.6108550071716309, "step": 20285, "token_acc": 0.8052510670429313 }, { "epoch": 1.3135363475249047, "grad_norm": 0.3699933886528015, "learning_rate": 2.635928878605748e-06, "loss": 0.6243587493896484, "step": 20290, "token_acc": 0.8019889461217431 }, { "epoch": 1.3138600480695308, "grad_norm": 0.4036909341812134, "learning_rate": 2.633689062822964e-06, "loss": 0.6309145927429199, "step": 20295, "token_acc": 0.8003270999614779 }, { "epoch": 1.314183748614157, "grad_norm": 0.2135104089975357, "learning_rate": 2.6314498587750946e-06, "loss": 0.5993346214294434, "step": 20300, "token_acc": 0.8080128436395122 }, { "epoch": 1.3145074491587831, "grad_norm": 0.38689279556274414, "learning_rate": 2.6292112670410206e-06, "loss": 0.6246518135070801, "step": 20305, "token_acc": 0.8038256877543213 }, { "epoch": 1.3148311497034093, "grad_norm": 0.3681826889514923, "learning_rate": 2.626973288199459e-06, "loss": 0.6002184391021729, "step": 20310, "token_acc": 0.8079102127602309 }, { "epoch": 1.3151548502480355, "grad_norm": 0.40434151887893677, "learning_rate": 2.624735922828967e-06, "loss": 0.6079056739807129, "step": 20315, "token_acc": 0.806328820415051 }, { "epoch": 1.3154785507926616, "grad_norm": 0.26994141936302185, "learning_rate": 2.6224991715079427e-06, "loss": 0.6232817649841309, "step": 20320, "token_acc": 0.8021093727238295 }, { "epoch": 1.315802251337288, "grad_norm": 0.3035297393798828, "learning_rate": 2.6202630348146323e-06, "loss": 0.601105785369873, "step": 20325, "token_acc": 0.8084507782919647 }, { "epoch": 1.3161259518819142, "grad_norm": 0.3274645209312439, "learning_rate": 2.618027513327116e-06, "loss": 0.6106992244720459, "step": 20330, "token_acc": 0.8055279634459732 }, { "epoch": 1.3164496524265403, "grad_norm": 0.3814002275466919, "learning_rate": 2.615792607623317e-06, "loss": 0.5918049812316895, "step": 20335, "token_acc": 0.8104042872560817 }, { "epoch": 1.3167733529711665, "grad_norm": 0.23444944620132446, "learning_rate": 2.6135583182809977e-06, "loss": 0.5917957305908204, "step": 20340, "token_acc": 0.809756539053308 }, { "epoch": 1.3170970535157926, "grad_norm": 0.26549196243286133, "learning_rate": 2.6113246458777686e-06, "loss": 0.6101328372955322, "step": 20345, "token_acc": 0.8046231977117506 }, { "epoch": 1.3174207540604188, "grad_norm": 0.3083811402320862, "learning_rate": 2.6090915909910674e-06, "loss": 0.6055974960327148, "step": 20350, "token_acc": 0.8069833658024876 }, { "epoch": 1.317744454605045, "grad_norm": 0.4239337146282196, "learning_rate": 2.6068591541981865e-06, "loss": 0.6197865962982178, "step": 20355, "token_acc": 0.8020688257256255 }, { "epoch": 1.3180681551496711, "grad_norm": 0.29155299067497253, "learning_rate": 2.604627336076247e-06, "loss": 0.6119935989379883, "step": 20360, "token_acc": 0.8050792911725233 }, { "epoch": 1.3183918556942973, "grad_norm": 0.29843536019325256, "learning_rate": 2.602396137202221e-06, "loss": 0.5890740394592285, "step": 20365, "token_acc": 0.8127407921097242 }, { "epoch": 1.3187155562389234, "grad_norm": 0.33892086148262024, "learning_rate": 2.600165558152907e-06, "loss": 0.6035958290100097, "step": 20370, "token_acc": 0.8076087934113656 }, { "epoch": 1.3190392567835496, "grad_norm": 0.37264692783355713, "learning_rate": 2.5979355995049572e-06, "loss": 0.5914902687072754, "step": 20375, "token_acc": 0.810127024985311 }, { "epoch": 1.3193629573281758, "grad_norm": 0.3836909234523773, "learning_rate": 2.595706261834854e-06, "loss": 0.6126152992248535, "step": 20380, "token_acc": 0.8057132180982999 }, { "epoch": 1.319686657872802, "grad_norm": 0.36104199290275574, "learning_rate": 2.593477545718922e-06, "loss": 0.6203949451446533, "step": 20385, "token_acc": 0.8020215877617581 }, { "epoch": 1.320010358417428, "grad_norm": 0.3617611229419708, "learning_rate": 2.5912494517333236e-06, "loss": 0.6163020610809327, "step": 20390, "token_acc": 0.804694563266628 }, { "epoch": 1.3203340589620542, "grad_norm": 0.3236984312534332, "learning_rate": 2.5890219804540683e-06, "loss": 0.5845859527587891, "step": 20395, "token_acc": 0.8110586688971203 }, { "epoch": 1.3206577595066804, "grad_norm": 0.33660808205604553, "learning_rate": 2.5867951324569904e-06, "loss": 0.6282458305358887, "step": 20400, "token_acc": 0.8011566792364354 }, { "epoch": 1.3209814600513066, "grad_norm": 0.24644295871257782, "learning_rate": 2.5845689083177776e-06, "loss": 0.5810025215148926, "step": 20405, "token_acc": 0.8123758918667233 }, { "epoch": 1.3213051605959327, "grad_norm": 0.2954145073890686, "learning_rate": 2.5823433086119472e-06, "loss": 0.5898115158081054, "step": 20410, "token_acc": 0.8098048204128278 }, { "epoch": 1.3216288611405589, "grad_norm": 0.3491242825984955, "learning_rate": 2.5801183339148574e-06, "loss": 0.609378719329834, "step": 20415, "token_acc": 0.8073255159059124 }, { "epoch": 1.321952561685185, "grad_norm": 0.3072139024734497, "learning_rate": 2.5778939848017032e-06, "loss": 0.5930171966552734, "step": 20420, "token_acc": 0.8116664837275671 }, { "epoch": 1.3222762622298112, "grad_norm": 0.4528675377368927, "learning_rate": 2.5756702618475244e-06, "loss": 0.6225132942199707, "step": 20425, "token_acc": 0.8021843511192264 }, { "epoch": 1.3225999627744374, "grad_norm": 0.3348761796951294, "learning_rate": 2.573447165627192e-06, "loss": 0.615131950378418, "step": 20430, "token_acc": 0.8050128705419541 }, { "epoch": 1.3229236633190635, "grad_norm": 0.3761042058467865, "learning_rate": 2.5712246967154166e-06, "loss": 0.6163182258605957, "step": 20435, "token_acc": 0.8040904693905754 }, { "epoch": 1.3232473638636897, "grad_norm": 0.37267547845840454, "learning_rate": 2.5690028556867487e-06, "loss": 0.6024033069610596, "step": 20440, "token_acc": 0.8074801913924634 }, { "epoch": 1.3235710644083158, "grad_norm": 0.31181439757347107, "learning_rate": 2.5667816431155736e-06, "loss": 0.6228703022003174, "step": 20445, "token_acc": 0.8041577330743431 }, { "epoch": 1.323894764952942, "grad_norm": 0.2570783793926239, "learning_rate": 2.5645610595761144e-06, "loss": 0.6087719917297363, "step": 20450, "token_acc": 0.8048646659738047 }, { "epoch": 1.3242184654975682, "grad_norm": 0.3782115876674652, "learning_rate": 2.5623411056424367e-06, "loss": 0.6059441089630127, "step": 20455, "token_acc": 0.8070829507193144 }, { "epoch": 1.3245421660421943, "grad_norm": 0.37007105350494385, "learning_rate": 2.5601217818884376e-06, "loss": 0.6267706871032714, "step": 20460, "token_acc": 0.8012340330379853 }, { "epoch": 1.3248658665868205, "grad_norm": 0.3847164809703827, "learning_rate": 2.557903088887853e-06, "loss": 0.6248229026794434, "step": 20465, "token_acc": 0.8019071483260249 }, { "epoch": 1.3251895671314466, "grad_norm": 0.4338604509830475, "learning_rate": 2.5556850272142565e-06, "loss": 0.6142656326293945, "step": 20470, "token_acc": 0.8063401643793625 }, { "epoch": 1.3255132676760728, "grad_norm": 0.35933080315589905, "learning_rate": 2.5534675974410537e-06, "loss": 0.5878487586975097, "step": 20475, "token_acc": 0.8105543191875784 }, { "epoch": 1.325836968220699, "grad_norm": 0.4219489097595215, "learning_rate": 2.551250800141498e-06, "loss": 0.5905946254730224, "step": 20480, "token_acc": 0.8097264760086446 }, { "epoch": 1.3261606687653251, "grad_norm": 0.4261353611946106, "learning_rate": 2.549034635888668e-06, "loss": 0.5950478076934814, "step": 20485, "token_acc": 0.8105576920683518 }, { "epoch": 1.3264843693099513, "grad_norm": 0.33719590306282043, "learning_rate": 2.5468191052554834e-06, "loss": 0.6165555953979492, "step": 20490, "token_acc": 0.8030785738413951 }, { "epoch": 1.3268080698545774, "grad_norm": 0.24472369253635406, "learning_rate": 2.544604208814699e-06, "loss": 0.604993486404419, "step": 20495, "token_acc": 0.807584721950357 }, { "epoch": 1.3271317703992036, "grad_norm": 0.32028090953826904, "learning_rate": 2.54238994713891e-06, "loss": 0.6356503963470459, "step": 20500, "token_acc": 0.798782041323598 }, { "epoch": 1.3274554709438298, "grad_norm": 0.3565361797809601, "learning_rate": 2.540176320800538e-06, "loss": 0.6152597904205322, "step": 20505, "token_acc": 0.805456751316624 }, { "epoch": 1.327779171488456, "grad_norm": 0.31028470396995544, "learning_rate": 2.537963330371851e-06, "loss": 0.6074260711669922, "step": 20510, "token_acc": 0.8065019079010354 }, { "epoch": 1.328102872033082, "grad_norm": 0.3777877688407898, "learning_rate": 2.5357509764249462e-06, "loss": 0.614719295501709, "step": 20515, "token_acc": 0.8047523299908962 }, { "epoch": 1.3284265725777082, "grad_norm": 0.3008211553096771, "learning_rate": 2.533539259531757e-06, "loss": 0.606049633026123, "step": 20520, "token_acc": 0.806851802471017 }, { "epoch": 1.3287502731223344, "grad_norm": 0.3374449610710144, "learning_rate": 2.5313281802640515e-06, "loss": 0.6050344467163086, "step": 20525, "token_acc": 0.8061901960548906 }, { "epoch": 1.3290739736669606, "grad_norm": 0.4039478600025177, "learning_rate": 2.529117739193441e-06, "loss": 0.6173422813415528, "step": 20530, "token_acc": 0.8034900294951947 }, { "epoch": 1.329397674211587, "grad_norm": 0.4124361276626587, "learning_rate": 2.526907936891355e-06, "loss": 0.6152377128601074, "step": 20535, "token_acc": 0.8048307356566486 }, { "epoch": 1.329721374756213, "grad_norm": 0.30098628997802734, "learning_rate": 2.5246987739290772e-06, "loss": 0.5875153541564941, "step": 20540, "token_acc": 0.8120434020757514 }, { "epoch": 1.3300450753008393, "grad_norm": 0.24751150608062744, "learning_rate": 2.5224902508777103e-06, "loss": 0.5799997329711915, "step": 20545, "token_acc": 0.8132370054957991 }, { "epoch": 1.3303687758454654, "grad_norm": 0.33524906635284424, "learning_rate": 2.5202823683082055e-06, "loss": 0.604480791091919, "step": 20550, "token_acc": 0.8062731621858366 }, { "epoch": 1.3306924763900916, "grad_norm": 0.30898958444595337, "learning_rate": 2.5180751267913328e-06, "loss": 0.602250051498413, "step": 20555, "token_acc": 0.8078626186588437 }, { "epoch": 1.3310161769347177, "grad_norm": 0.32487359642982483, "learning_rate": 2.51586852689771e-06, "loss": 0.6361273765563965, "step": 20560, "token_acc": 0.7995891225604153 }, { "epoch": 1.331339877479344, "grad_norm": 0.3335306644439697, "learning_rate": 2.5136625691977824e-06, "loss": 0.6056660175323486, "step": 20565, "token_acc": 0.806325251796201 }, { "epoch": 1.33166357802397, "grad_norm": 0.27236685156822205, "learning_rate": 2.5114572542618308e-06, "loss": 0.6045228004455566, "step": 20570, "token_acc": 0.8065903403963932 }, { "epoch": 1.3319872785685962, "grad_norm": 0.2413511425256729, "learning_rate": 2.509252582659968e-06, "loss": 0.6071479797363282, "step": 20575, "token_acc": 0.8062425945360371 }, { "epoch": 1.3323109791132224, "grad_norm": 0.3808964192867279, "learning_rate": 2.507048554962147e-06, "loss": 0.5857719421386719, "step": 20580, "token_acc": 0.8120557549668448 }, { "epoch": 1.3326346796578485, "grad_norm": 0.37466123700141907, "learning_rate": 2.504845171738143e-06, "loss": 0.6157328605651855, "step": 20585, "token_acc": 0.8034525790349417 }, { "epoch": 1.3329583802024747, "grad_norm": 0.28910329937934875, "learning_rate": 2.5026424335575756e-06, "loss": 0.5929395675659179, "step": 20590, "token_acc": 0.8089773515866507 }, { "epoch": 1.3332820807471009, "grad_norm": 0.3503934442996979, "learning_rate": 2.50044034098989e-06, "loss": 0.5870051383972168, "step": 20595, "token_acc": 0.8120458930972267 }, { "epoch": 1.333605781291727, "grad_norm": 0.31573712825775146, "learning_rate": 2.498238894604374e-06, "loss": 0.6270317554473877, "step": 20600, "token_acc": 0.802098795709473 }, { "epoch": 1.3339294818363532, "grad_norm": 0.4438617527484894, "learning_rate": 2.496038094970133e-06, "loss": 0.60833740234375, "step": 20605, "token_acc": 0.8053040749845115 }, { "epoch": 1.3342531823809793, "grad_norm": 0.2516520917415619, "learning_rate": 2.493837942656121e-06, "loss": 0.644194507598877, "step": 20610, "token_acc": 0.796296417556657 }, { "epoch": 1.3345768829256055, "grad_norm": 0.4039454460144043, "learning_rate": 2.4916384382311154e-06, "loss": 0.5835566997528077, "step": 20615, "token_acc": 0.8132714026183208 }, { "epoch": 1.3349005834702317, "grad_norm": 0.2940123975276947, "learning_rate": 2.4894395822637293e-06, "loss": 0.6072229385375977, "step": 20620, "token_acc": 0.8062990994756193 }, { "epoch": 1.3352242840148578, "grad_norm": 0.21831977367401123, "learning_rate": 2.487241375322404e-06, "loss": 0.6114068984985351, "step": 20625, "token_acc": 0.8067062203012162 }, { "epoch": 1.335547984559484, "grad_norm": 0.2803598940372467, "learning_rate": 2.4850438179754215e-06, "loss": 0.6042396545410156, "step": 20630, "token_acc": 0.8054801530099657 }, { "epoch": 1.3358716851041101, "grad_norm": 0.355085551738739, "learning_rate": 2.4828469107908894e-06, "loss": 0.6173673629760742, "step": 20635, "token_acc": 0.8059905310960095 }, { "epoch": 1.3361953856487363, "grad_norm": 0.30481353402137756, "learning_rate": 2.480650654336747e-06, "loss": 0.6066675186157227, "step": 20640, "token_acc": 0.8067378504882919 }, { "epoch": 1.3365190861933625, "grad_norm": 0.28894779086112976, "learning_rate": 2.478455049180766e-06, "loss": 0.6047684669494628, "step": 20645, "token_acc": 0.8074154184935924 }, { "epoch": 1.3368427867379886, "grad_norm": 0.3711511790752411, "learning_rate": 2.476260095890557e-06, "loss": 0.6163007259368897, "step": 20650, "token_acc": 0.8043608061309787 }, { "epoch": 1.3371664872826148, "grad_norm": 0.2908421754837036, "learning_rate": 2.4740657950335474e-06, "loss": 0.6369609832763672, "step": 20655, "token_acc": 0.8004187065608197 }, { "epoch": 1.337490187827241, "grad_norm": 0.2679577171802521, "learning_rate": 2.4718721471770103e-06, "loss": 0.6096551418304443, "step": 20660, "token_acc": 0.806175957783921 }, { "epoch": 1.3378138883718673, "grad_norm": 0.30308499932289124, "learning_rate": 2.4696791528880416e-06, "loss": 0.6167789459228515, "step": 20665, "token_acc": 0.8037217486353366 }, { "epoch": 1.3381375889164935, "grad_norm": 0.3010331094264984, "learning_rate": 2.4674868127335717e-06, "loss": 0.590080976486206, "step": 20670, "token_acc": 0.8121801301339917 }, { "epoch": 1.3384612894611196, "grad_norm": 0.3144301772117615, "learning_rate": 2.465295127280358e-06, "loss": 0.5905081272125244, "step": 20675, "token_acc": 0.8099049712166432 }, { "epoch": 1.3387849900057458, "grad_norm": 0.38577020168304443, "learning_rate": 2.463104097094996e-06, "loss": 0.6008964538574219, "step": 20680, "token_acc": 0.8077845732060948 }, { "epoch": 1.339108690550372, "grad_norm": 0.38207346200942993, "learning_rate": 2.460913722743905e-06, "loss": 0.6217141628265381, "step": 20685, "token_acc": 0.8032320153981876 }, { "epoch": 1.3394323910949981, "grad_norm": 0.2702699899673462, "learning_rate": 2.4587240047933375e-06, "loss": 0.5923429012298584, "step": 20690, "token_acc": 0.8094060328863147 }, { "epoch": 1.3397560916396243, "grad_norm": 0.31488245725631714, "learning_rate": 2.4565349438093755e-06, "loss": 0.6097066879272461, "step": 20695, "token_acc": 0.8062267325896425 }, { "epoch": 1.3400797921842504, "grad_norm": 0.41011908650398254, "learning_rate": 2.4543465403579318e-06, "loss": 0.6039000511169433, "step": 20700, "token_acc": 0.8057741213654442 }, { "epoch": 1.3404034927288766, "grad_norm": 0.3378327488899231, "learning_rate": 2.4521587950047486e-06, "loss": 0.611311674118042, "step": 20705, "token_acc": 0.8040324251354946 }, { "epoch": 1.3407271932735028, "grad_norm": 0.34201690554618835, "learning_rate": 2.4499717083153975e-06, "loss": 0.6410088062286377, "step": 20710, "token_acc": 0.7980702092712413 }, { "epoch": 1.341050893818129, "grad_norm": 0.293199360370636, "learning_rate": 2.4477852808552827e-06, "loss": 0.6189375877380371, "step": 20715, "token_acc": 0.8038571838256381 }, { "epoch": 1.341374594362755, "grad_norm": 0.245814248919487, "learning_rate": 2.4455995131896348e-06, "loss": 0.6105786800384522, "step": 20720, "token_acc": 0.8051942385959227 }, { "epoch": 1.3416982949073812, "grad_norm": 0.35867080092430115, "learning_rate": 2.4434144058835157e-06, "loss": 0.6144158363342285, "step": 20725, "token_acc": 0.8048841924961272 }, { "epoch": 1.3420219954520074, "grad_norm": 0.39122769236564636, "learning_rate": 2.4412299595018128e-06, "loss": 0.6178291320800782, "step": 20730, "token_acc": 0.8032147157384707 }, { "epoch": 1.3423456959966336, "grad_norm": 0.3425944447517395, "learning_rate": 2.4390461746092524e-06, "loss": 0.632993507385254, "step": 20735, "token_acc": 0.7996210357081337 }, { "epoch": 1.3426693965412597, "grad_norm": 0.2598259449005127, "learning_rate": 2.436863051770375e-06, "loss": 0.6064866065979004, "step": 20740, "token_acc": 0.8072086701733329 }, { "epoch": 1.3429930970858859, "grad_norm": 0.3566889762878418, "learning_rate": 2.434680591549564e-06, "loss": 0.6133054733276367, "step": 20745, "token_acc": 0.8039589933295291 }, { "epoch": 1.343316797630512, "grad_norm": 0.3214312493801117, "learning_rate": 2.4324987945110227e-06, "loss": 0.5979425430297851, "step": 20750, "token_acc": 0.8072008007712951 }, { "epoch": 1.3436404981751382, "grad_norm": 0.3131994605064392, "learning_rate": 2.430317661218787e-06, "loss": 0.5934410095214844, "step": 20755, "token_acc": 0.810012047428825 }, { "epoch": 1.3439641987197644, "grad_norm": 0.3988649249076843, "learning_rate": 2.4281371922367177e-06, "loss": 0.6394545555114746, "step": 20760, "token_acc": 0.7984023208683824 }, { "epoch": 1.3442878992643905, "grad_norm": 0.35971149802207947, "learning_rate": 2.425957388128509e-06, "loss": 0.595639419555664, "step": 20765, "token_acc": 0.8083355582482731 }, { "epoch": 1.3446115998090167, "grad_norm": 0.2879805564880371, "learning_rate": 2.42377824945768e-06, "loss": 0.5831378936767578, "step": 20770, "token_acc": 0.8126111758572042 }, { "epoch": 1.3449353003536428, "grad_norm": 0.3395923674106598, "learning_rate": 2.421599776787577e-06, "loss": 0.602627182006836, "step": 20775, "token_acc": 0.8079256410922602 }, { "epoch": 1.345259000898269, "grad_norm": 0.35642027854919434, "learning_rate": 2.4194219706813736e-06, "loss": 0.6164754390716553, "step": 20780, "token_acc": 0.8040339661504382 }, { "epoch": 1.3455827014428952, "grad_norm": 0.30713123083114624, "learning_rate": 2.417244831702079e-06, "loss": 0.5991246223449707, "step": 20785, "token_acc": 0.8075027415996155 }, { "epoch": 1.3459064019875213, "grad_norm": 0.34075021743774414, "learning_rate": 2.4150683604125156e-06, "loss": 0.5872828483581543, "step": 20790, "token_acc": 0.8121123899796886 }, { "epoch": 1.3462301025321475, "grad_norm": 0.3639211356639862, "learning_rate": 2.4128925573753476e-06, "loss": 0.6159225940704346, "step": 20795, "token_acc": 0.8059747417991117 }, { "epoch": 1.3465538030767736, "grad_norm": 0.4524071514606476, "learning_rate": 2.4107174231530574e-06, "loss": 0.6175346374511719, "step": 20800, "token_acc": 0.8041557716229596 }, { "epoch": 1.3468775036213998, "grad_norm": 0.33930546045303345, "learning_rate": 2.408542958307957e-06, "loss": 0.6081322193145752, "step": 20805, "token_acc": 0.8052434700159758 }, { "epoch": 1.347201204166026, "grad_norm": 0.4185369908809662, "learning_rate": 2.406369163402185e-06, "loss": 0.6300171375274658, "step": 20810, "token_acc": 0.7995846029815667 }, { "epoch": 1.3475249047106521, "grad_norm": 0.4143422544002533, "learning_rate": 2.40419603899771e-06, "loss": 0.6000718116760254, "step": 20815, "token_acc": 0.8082809539457585 }, { "epoch": 1.3478486052552783, "grad_norm": 0.36013951897621155, "learning_rate": 2.402023585656323e-06, "loss": 0.6392532825469971, "step": 20820, "token_acc": 0.7982507327739434 }, { "epoch": 1.3481723057999044, "grad_norm": 0.25455018877983093, "learning_rate": 2.3998518039396427e-06, "loss": 0.6085757732391357, "step": 20825, "token_acc": 0.8057252779498549 }, { "epoch": 1.3484960063445306, "grad_norm": 0.33292242884635925, "learning_rate": 2.3976806944091148e-06, "loss": 0.5910012722015381, "step": 20830, "token_acc": 0.8116960833311413 }, { "epoch": 1.3488197068891568, "grad_norm": 0.37138235569000244, "learning_rate": 2.395510257626014e-06, "loss": 0.5814853191375733, "step": 20835, "token_acc": 0.8123002019715635 }, { "epoch": 1.349143407433783, "grad_norm": 0.331071138381958, "learning_rate": 2.3933404941514327e-06, "loss": 0.613859748840332, "step": 20840, "token_acc": 0.8053793581304526 }, { "epoch": 1.349467107978409, "grad_norm": 0.45640829205513, "learning_rate": 2.391171404546299e-06, "loss": 0.6367541313171386, "step": 20845, "token_acc": 0.7997918180568376 }, { "epoch": 1.3497908085230352, "grad_norm": 0.3632934093475342, "learning_rate": 2.3890029893713613e-06, "loss": 0.6116308689117431, "step": 20850, "token_acc": 0.8058373048479869 }, { "epoch": 1.3501145090676614, "grad_norm": 0.3792321979999542, "learning_rate": 2.3868352491871947e-06, "loss": 0.612739086151123, "step": 20855, "token_acc": 0.805841722845925 }, { "epoch": 1.3504382096122876, "grad_norm": 0.2999248802661896, "learning_rate": 2.384668184554198e-06, "loss": 0.6106705665588379, "step": 20860, "token_acc": 0.8054787683329494 }, { "epoch": 1.3507619101569137, "grad_norm": 0.4728933870792389, "learning_rate": 2.382501796032601e-06, "loss": 0.60975022315979, "step": 20865, "token_acc": 0.804218063378623 }, { "epoch": 1.3510856107015399, "grad_norm": 0.3035792112350464, "learning_rate": 2.380336084182453e-06, "loss": 0.5915223121643066, "step": 20870, "token_acc": 0.8099751267887715 }, { "epoch": 1.351409311246166, "grad_norm": 0.3106413781642914, "learning_rate": 2.378171049563631e-06, "loss": 0.6132369995117187, "step": 20875, "token_acc": 0.8054918768065384 }, { "epoch": 1.3517330117907924, "grad_norm": 0.3343586325645447, "learning_rate": 2.376006692735833e-06, "loss": 0.603574562072754, "step": 20880, "token_acc": 0.8066769073220686 }, { "epoch": 1.3520567123354186, "grad_norm": 0.419514536857605, "learning_rate": 2.3738430142585924e-06, "loss": 0.6087109565734863, "step": 20885, "token_acc": 0.8064836979225378 }, { "epoch": 1.3523804128800447, "grad_norm": 0.3472267985343933, "learning_rate": 2.371680014691251e-06, "loss": 0.5871832847595215, "step": 20890, "token_acc": 0.8116633890647503 }, { "epoch": 1.352704113424671, "grad_norm": 0.32545194029808044, "learning_rate": 2.3695176945929904e-06, "loss": 0.6106641292572021, "step": 20895, "token_acc": 0.8049536922039672 }, { "epoch": 1.353027813969297, "grad_norm": 0.321864515542984, "learning_rate": 2.3673560545228082e-06, "loss": 0.6265786170959473, "step": 20900, "token_acc": 0.8032285860462611 }, { "epoch": 1.3533515145139232, "grad_norm": 0.2002936601638794, "learning_rate": 2.365195095039528e-06, "loss": 0.5855608940124511, "step": 20905, "token_acc": 0.8126512577987965 }, { "epoch": 1.3536752150585494, "grad_norm": 0.28097793459892273, "learning_rate": 2.3630348167017953e-06, "loss": 0.6041151523590088, "step": 20910, "token_acc": 0.8088958241272647 }, { "epoch": 1.3539989156031755, "grad_norm": 0.26329305768013, "learning_rate": 2.3608752200680862e-06, "loss": 0.6328288555145264, "step": 20915, "token_acc": 0.801995246225436 }, { "epoch": 1.3543226161478017, "grad_norm": 0.3449956178665161, "learning_rate": 2.3587163056966945e-06, "loss": 0.6180632591247559, "step": 20920, "token_acc": 0.8057224723144508 }, { "epoch": 1.3546463166924279, "grad_norm": 0.29878920316696167, "learning_rate": 2.356558074145738e-06, "loss": 0.5952261924743653, "step": 20925, "token_acc": 0.809493962958116 }, { "epoch": 1.354970017237054, "grad_norm": 0.37599408626556396, "learning_rate": 2.354400525973161e-06, "loss": 0.5966568946838379, "step": 20930, "token_acc": 0.8087383637228269 }, { "epoch": 1.3552937177816802, "grad_norm": 0.31987717747688293, "learning_rate": 2.3522436617367285e-06, "loss": 0.6084564685821533, "step": 20935, "token_acc": 0.8065968185095451 }, { "epoch": 1.3556174183263063, "grad_norm": 0.4010063111782074, "learning_rate": 2.3500874819940266e-06, "loss": 0.59304838180542, "step": 20940, "token_acc": 0.8094736702691249 }, { "epoch": 1.3559411188709325, "grad_norm": 0.34466904401779175, "learning_rate": 2.3479319873024734e-06, "loss": 0.5986930847167968, "step": 20945, "token_acc": 0.8105537244561635 }, { "epoch": 1.3562648194155587, "grad_norm": 0.3856388032436371, "learning_rate": 2.3457771782193007e-06, "loss": 0.6230667114257813, "step": 20950, "token_acc": 0.8027983836144392 }, { "epoch": 1.3565885199601848, "grad_norm": 0.34655606746673584, "learning_rate": 2.3436230553015664e-06, "loss": 0.5911431789398194, "step": 20955, "token_acc": 0.8110463617141973 }, { "epoch": 1.356912220504811, "grad_norm": 0.3967161178588867, "learning_rate": 2.3414696191061514e-06, "loss": 0.6147897720336915, "step": 20960, "token_acc": 0.8043887349358768 }, { "epoch": 1.3572359210494371, "grad_norm": 0.28135356307029724, "learning_rate": 2.3393168701897563e-06, "loss": 0.6158343315124511, "step": 20965, "token_acc": 0.8045663667746982 }, { "epoch": 1.3575596215940633, "grad_norm": 0.3359743356704712, "learning_rate": 2.3371648091089098e-06, "loss": 0.6385013580322265, "step": 20970, "token_acc": 0.7989618516482078 }, { "epoch": 1.3578833221386895, "grad_norm": 0.35605791211128235, "learning_rate": 2.3350134364199582e-06, "loss": 0.6224196434020997, "step": 20975, "token_acc": 0.8033830054312027 }, { "epoch": 1.3582070226833156, "grad_norm": 0.36066463589668274, "learning_rate": 2.332862752679071e-06, "loss": 0.6029472827911377, "step": 20980, "token_acc": 0.8080502340621534 }, { "epoch": 1.3585307232279418, "grad_norm": 0.38568881154060364, "learning_rate": 2.330712758442236e-06, "loss": 0.6167685985565186, "step": 20985, "token_acc": 0.8040179225472481 }, { "epoch": 1.358854423772568, "grad_norm": 0.37231892347335815, "learning_rate": 2.3285634542652736e-06, "loss": 0.6122508525848389, "step": 20990, "token_acc": 0.8061246583128095 }, { "epoch": 1.359178124317194, "grad_norm": 0.362911581993103, "learning_rate": 2.3264148407038106e-06, "loss": 0.6249132633209229, "step": 20995, "token_acc": 0.8027193021781316 }, { "epoch": 1.3595018248618203, "grad_norm": 0.4300540089607239, "learning_rate": 2.324266918313308e-06, "loss": 0.6053180694580078, "step": 21000, "token_acc": 0.8074108112067875 }, { "epoch": 1.3598255254064466, "grad_norm": 0.3978058397769928, "learning_rate": 2.3221196876490425e-06, "loss": 0.6182643890380859, "step": 21005, "token_acc": 0.8045215954810689 }, { "epoch": 1.3601492259510728, "grad_norm": 0.33118942379951477, "learning_rate": 2.3199731492661125e-06, "loss": 0.5956403732299804, "step": 21010, "token_acc": 0.808716309278611 }, { "epoch": 1.360472926495699, "grad_norm": 0.34755128622055054, "learning_rate": 2.3178273037194347e-06, "loss": 0.5961792469024658, "step": 21015, "token_acc": 0.8093800789412584 }, { "epoch": 1.3607966270403251, "grad_norm": 0.33426329493522644, "learning_rate": 2.3156821515637566e-06, "loss": 0.5659821510314942, "step": 21020, "token_acc": 0.8159631740213625 }, { "epoch": 1.3611203275849513, "grad_norm": 0.298376202583313, "learning_rate": 2.3135376933536314e-06, "loss": 0.6179848670959472, "step": 21025, "token_acc": 0.8046219682555736 }, { "epoch": 1.3614440281295774, "grad_norm": 0.3375217318534851, "learning_rate": 2.311393929643447e-06, "loss": 0.6197453022003174, "step": 21030, "token_acc": 0.8043057036593929 }, { "epoch": 1.3617677286742036, "grad_norm": 0.32758474349975586, "learning_rate": 2.309250860987401e-06, "loss": 0.6175555229187012, "step": 21035, "token_acc": 0.8046670823438888 }, { "epoch": 1.3620914292188298, "grad_norm": 0.3272964358329773, "learning_rate": 2.307108487939523e-06, "loss": 0.5936335563659668, "step": 21040, "token_acc": 0.8085758603142684 }, { "epoch": 1.362415129763456, "grad_norm": 0.3162420690059662, "learning_rate": 2.3049668110536476e-06, "loss": 0.6113729476928711, "step": 21045, "token_acc": 0.8038754025601472 }, { "epoch": 1.362738830308082, "grad_norm": 0.2882990539073944, "learning_rate": 2.302825830883444e-06, "loss": 0.5909668445587158, "step": 21050, "token_acc": 0.8107597831057686 }, { "epoch": 1.3630625308527082, "grad_norm": 0.34853431582450867, "learning_rate": 2.300685547982392e-06, "loss": 0.614354419708252, "step": 21055, "token_acc": 0.8046147462365738 }, { "epoch": 1.3633862313973344, "grad_norm": 0.323112428188324, "learning_rate": 2.298545962903795e-06, "loss": 0.6087687969207763, "step": 21060, "token_acc": 0.805331715726965 }, { "epoch": 1.3637099319419606, "grad_norm": 0.2768162190914154, "learning_rate": 2.296407076200773e-06, "loss": 0.6331075668334961, "step": 21065, "token_acc": 0.8001802017414809 }, { "epoch": 1.3640336324865867, "grad_norm": 0.37384307384490967, "learning_rate": 2.2942688884262727e-06, "loss": 0.62760910987854, "step": 21070, "token_acc": 0.8015850181780138 }, { "epoch": 1.3643573330312129, "grad_norm": 0.41738006472587585, "learning_rate": 2.292131400133048e-06, "loss": 0.6070219039916992, "step": 21075, "token_acc": 0.8058081150766725 }, { "epoch": 1.364681033575839, "grad_norm": 0.41609475016593933, "learning_rate": 2.289994611873685e-06, "loss": 0.5987778186798096, "step": 21080, "token_acc": 0.8093497656751698 }, { "epoch": 1.3650047341204652, "grad_norm": 0.24393044412136078, "learning_rate": 2.287858524200578e-06, "loss": 0.5907064914703369, "step": 21085, "token_acc": 0.8108768928270473 }, { "epoch": 1.3653284346650914, "grad_norm": 0.32732653617858887, "learning_rate": 2.2857231376659517e-06, "loss": 0.6219820022583008, "step": 21090, "token_acc": 0.8022731191447784 }, { "epoch": 1.3656521352097175, "grad_norm": 0.3183170258998871, "learning_rate": 2.2835884528218342e-06, "loss": 0.6116510391235351, "step": 21095, "token_acc": 0.8060141698457988 }, { "epoch": 1.3659758357543437, "grad_norm": 0.4181213676929474, "learning_rate": 2.2814544702200874e-06, "loss": 0.6142049312591553, "step": 21100, "token_acc": 0.8042195387046657 }, { "epoch": 1.3662995362989698, "grad_norm": 0.30461686849594116, "learning_rate": 2.2793211904123826e-06, "loss": 0.5930198192596435, "step": 21105, "token_acc": 0.8096453160594067 }, { "epoch": 1.366623236843596, "grad_norm": 0.3541666269302368, "learning_rate": 2.277188613950212e-06, "loss": 0.6222552299499512, "step": 21110, "token_acc": 0.8010060669692398 }, { "epoch": 1.3669469373882221, "grad_norm": 0.3354015350341797, "learning_rate": 2.275056741384884e-06, "loss": 0.6147989749908447, "step": 21115, "token_acc": 0.8055455623509347 }, { "epoch": 1.3672706379328483, "grad_norm": 0.2815946638584137, "learning_rate": 2.272925573267531e-06, "loss": 0.6303214073181153, "step": 21120, "token_acc": 0.7997346970163027 }, { "epoch": 1.3675943384774745, "grad_norm": 0.3086487948894501, "learning_rate": 2.2707951101490966e-06, "loss": 0.6087788105010986, "step": 21125, "token_acc": 0.806217113464289 }, { "epoch": 1.3679180390221006, "grad_norm": 0.2310701161623001, "learning_rate": 2.2686653525803455e-06, "loss": 0.6183690547943115, "step": 21130, "token_acc": 0.8044485166345455 }, { "epoch": 1.3682417395667268, "grad_norm": 0.3614632189273834, "learning_rate": 2.2665363011118584e-06, "loss": 0.6158724308013916, "step": 21135, "token_acc": 0.8048577618445826 }, { "epoch": 1.368565440111353, "grad_norm": 0.3060438930988312, "learning_rate": 2.2644079562940347e-06, "loss": 0.575397253036499, "step": 21140, "token_acc": 0.813333858081782 }, { "epoch": 1.368889140655979, "grad_norm": 0.3734787702560425, "learning_rate": 2.2622803186770892e-06, "loss": 0.5981419563293457, "step": 21145, "token_acc": 0.8099644721484731 }, { "epoch": 1.3692128412006053, "grad_norm": 0.4035857617855072, "learning_rate": 2.2601533888110585e-06, "loss": 0.6296905517578125, "step": 21150, "token_acc": 0.8002385344208133 }, { "epoch": 1.3695365417452314, "grad_norm": 0.30418431758880615, "learning_rate": 2.2580271672457914e-06, "loss": 0.6004048824310303, "step": 21155, "token_acc": 0.8057712723178382 }, { "epoch": 1.3698602422898576, "grad_norm": 0.36314576864242554, "learning_rate": 2.255901654530955e-06, "loss": 0.5995625972747802, "step": 21160, "token_acc": 0.80881600202086 }, { "epoch": 1.3701839428344837, "grad_norm": 0.3332996964454651, "learning_rate": 2.253776851216035e-06, "loss": 0.6055148601531982, "step": 21165, "token_acc": 0.8059450711011724 }, { "epoch": 1.37050764337911, "grad_norm": 0.2821986973285675, "learning_rate": 2.2516527578503283e-06, "loss": 0.600367259979248, "step": 21170, "token_acc": 0.8077591198610307 }, { "epoch": 1.370831343923736, "grad_norm": 0.331885427236557, "learning_rate": 2.2495293749829566e-06, "loss": 0.6253182411193847, "step": 21175, "token_acc": 0.8014723466413304 }, { "epoch": 1.3711550444683622, "grad_norm": 0.30055758357048035, "learning_rate": 2.247406703162852e-06, "loss": 0.5819596767425537, "step": 21180, "token_acc": 0.812564263322884 }, { "epoch": 1.3714787450129884, "grad_norm": 0.3524894714355469, "learning_rate": 2.2452847429387635e-06, "loss": 0.6021834373474121, "step": 21185, "token_acc": 0.8088968179691156 }, { "epoch": 1.3718024455576145, "grad_norm": 0.26283860206604004, "learning_rate": 2.2431634948592572e-06, "loss": 0.5789691925048828, "step": 21190, "token_acc": 0.8134168331790048 }, { "epoch": 1.3721261461022407, "grad_norm": 0.3213316798210144, "learning_rate": 2.241042959472715e-06, "loss": 0.6023395538330079, "step": 21195, "token_acc": 0.8072332730560579 }, { "epoch": 1.3724498466468669, "grad_norm": 0.32593849301338196, "learning_rate": 2.2389231373273323e-06, "loss": 0.6427409172058105, "step": 21200, "token_acc": 0.797666350878867 }, { "epoch": 1.372773547191493, "grad_norm": 0.37297526001930237, "learning_rate": 2.2368040289711255e-06, "loss": 0.6128757476806641, "step": 21205, "token_acc": 0.8057679298505367 }, { "epoch": 1.3730972477361192, "grad_norm": 0.35267603397369385, "learning_rate": 2.234685634951922e-06, "loss": 0.6100303173065186, "step": 21210, "token_acc": 0.805648865873547 }, { "epoch": 1.3734209482807453, "grad_norm": 0.32410991191864014, "learning_rate": 2.232567955817365e-06, "loss": 0.5959237575531006, "step": 21215, "token_acc": 0.8094106431971213 }, { "epoch": 1.3737446488253717, "grad_norm": 0.2682749629020691, "learning_rate": 2.2304509921149116e-06, "loss": 0.5986323833465577, "step": 21220, "token_acc": 0.808322584737699 }, { "epoch": 1.3740683493699979, "grad_norm": 0.3410983383655548, "learning_rate": 2.228334744391842e-06, "loss": 0.6074954032897949, "step": 21225, "token_acc": 0.8072495513384784 }, { "epoch": 1.374392049914624, "grad_norm": 0.2975408732891083, "learning_rate": 2.226219213195237e-06, "loss": 0.6014563560485839, "step": 21230, "token_acc": 0.8086726599682708 }, { "epoch": 1.3747157504592502, "grad_norm": 0.3655281960964203, "learning_rate": 2.2241043990720067e-06, "loss": 0.6065655708312988, "step": 21235, "token_acc": 0.8076998500768593 }, { "epoch": 1.3750394510038764, "grad_norm": 0.35759982466697693, "learning_rate": 2.221990302568867e-06, "loss": 0.6001896858215332, "step": 21240, "token_acc": 0.8081634106392575 }, { "epoch": 1.3753631515485025, "grad_norm": 0.3357022702693939, "learning_rate": 2.2198769242323507e-06, "loss": 0.6077526092529297, "step": 21245, "token_acc": 0.8066314893617021 }, { "epoch": 1.3756868520931287, "grad_norm": 0.31638455390930176, "learning_rate": 2.2177642646088042e-06, "loss": 0.6261239528656006, "step": 21250, "token_acc": 0.8024985839259865 }, { "epoch": 1.3760105526377548, "grad_norm": 0.3224806487560272, "learning_rate": 2.2156523242443915e-06, "loss": 0.6073157787322998, "step": 21255, "token_acc": 0.8064929312759616 }, { "epoch": 1.376334253182381, "grad_norm": 0.31904882192611694, "learning_rate": 2.2135411036850864e-06, "loss": 0.5981536865234375, "step": 21260, "token_acc": 0.8098151441524936 }, { "epoch": 1.3766579537270072, "grad_norm": 0.3281309902667999, "learning_rate": 2.2114306034766787e-06, "loss": 0.5902351379394531, "step": 21265, "token_acc": 0.8110760191978816 }, { "epoch": 1.3769816542716333, "grad_norm": 0.34341996908187866, "learning_rate": 2.209320824164769e-06, "loss": 0.591153907775879, "step": 21270, "token_acc": 0.8116189447145687 }, { "epoch": 1.3773053548162595, "grad_norm": 0.40429261326789856, "learning_rate": 2.2072117662947797e-06, "loss": 0.6026077270507812, "step": 21275, "token_acc": 0.8083493326169149 }, { "epoch": 1.3776290553608856, "grad_norm": 0.2866215705871582, "learning_rate": 2.2051034304119344e-06, "loss": 0.6091183662414551, "step": 21280, "token_acc": 0.8061942810163657 }, { "epoch": 1.3779527559055118, "grad_norm": 0.35159802436828613, "learning_rate": 2.2029958170612814e-06, "loss": 0.6111019134521485, "step": 21285, "token_acc": 0.8052503526549417 }, { "epoch": 1.378276456450138, "grad_norm": 0.3235801160335541, "learning_rate": 2.2008889267876765e-06, "loss": 0.5704746246337891, "step": 21290, "token_acc": 0.815354008627101 }, { "epoch": 1.3786001569947641, "grad_norm": 0.29279786348342896, "learning_rate": 2.1987827601357893e-06, "loss": 0.6167157649993896, "step": 21295, "token_acc": 0.8044587406858582 }, { "epoch": 1.3789238575393903, "grad_norm": 0.27307504415512085, "learning_rate": 2.1966773176501006e-06, "loss": 0.614600658416748, "step": 21300, "token_acc": 0.8037565499930089 }, { "epoch": 1.3792475580840164, "grad_norm": 0.2946801483631134, "learning_rate": 2.1945725998749096e-06, "loss": 0.6192754745483399, "step": 21305, "token_acc": 0.8029856768206577 }, { "epoch": 1.3795712586286426, "grad_norm": 0.3497871458530426, "learning_rate": 2.192468607354323e-06, "loss": 0.6061624526977539, "step": 21310, "token_acc": 0.806650397331502 }, { "epoch": 1.3798949591732688, "grad_norm": 0.3481796383857727, "learning_rate": 2.1903653406322617e-06, "loss": 0.6115283012390137, "step": 21315, "token_acc": 0.8060419765328045 }, { "epoch": 1.380218659717895, "grad_norm": 0.3977203667163849, "learning_rate": 2.1882628002524565e-06, "loss": 0.5933060646057129, "step": 21320, "token_acc": 0.8101904271744724 }, { "epoch": 1.380542360262521, "grad_norm": 0.26667100191116333, "learning_rate": 2.1861609867584588e-06, "loss": 0.6079401969909668, "step": 21325, "token_acc": 0.8061964321307554 }, { "epoch": 1.3808660608071472, "grad_norm": 0.31148889660835266, "learning_rate": 2.1840599006936185e-06, "loss": 0.5814791202545166, "step": 21330, "token_acc": 0.8139706240561212 }, { "epoch": 1.3811897613517734, "grad_norm": 0.3450070321559906, "learning_rate": 2.181959542601111e-06, "loss": 0.6255539894104004, "step": 21335, "token_acc": 0.8017808564746951 }, { "epoch": 1.3815134618963996, "grad_norm": 0.3709574341773987, "learning_rate": 2.1798599130239145e-06, "loss": 0.613282585144043, "step": 21340, "token_acc": 0.80661279619003 }, { "epoch": 1.381837162441026, "grad_norm": 0.3395098149776459, "learning_rate": 2.1777610125048233e-06, "loss": 0.6053675651550293, "step": 21345, "token_acc": 0.8063388121275621 }, { "epoch": 1.382160862985652, "grad_norm": 0.2528027296066284, "learning_rate": 2.1756628415864386e-06, "loss": 0.6177014827728271, "step": 21350, "token_acc": 0.8045352271129237 }, { "epoch": 1.3824845635302783, "grad_norm": 0.32121363282203674, "learning_rate": 2.1735654008111807e-06, "loss": 0.6113145351409912, "step": 21355, "token_acc": 0.8043862094600873 }, { "epoch": 1.3828082640749044, "grad_norm": 0.34142443537712097, "learning_rate": 2.1714686907212753e-06, "loss": 0.5939093589782715, "step": 21360, "token_acc": 0.8104391962273442 }, { "epoch": 1.3831319646195306, "grad_norm": 0.3695322573184967, "learning_rate": 2.1693727118587586e-06, "loss": 0.6081871032714844, "step": 21365, "token_acc": 0.8070178725317546 }, { "epoch": 1.3834556651641567, "grad_norm": 0.35031428933143616, "learning_rate": 2.1672774647654806e-06, "loss": 0.6079596042633056, "step": 21370, "token_acc": 0.8074367526663415 }, { "epoch": 1.383779365708783, "grad_norm": 0.5458864569664001, "learning_rate": 2.1651829499831045e-06, "loss": 0.5938146591186524, "step": 21375, "token_acc": 0.8104517726447591 }, { "epoch": 1.384103066253409, "grad_norm": 0.2776803970336914, "learning_rate": 2.163089168053094e-06, "loss": 0.5875552654266357, "step": 21380, "token_acc": 0.8111488413085178 }, { "epoch": 1.3844267667980352, "grad_norm": 0.47295820713043213, "learning_rate": 2.160996119516737e-06, "loss": 0.6019543647766114, "step": 21385, "token_acc": 0.8086693205403015 }, { "epoch": 1.3847504673426614, "grad_norm": 0.3476332724094391, "learning_rate": 2.1589038049151217e-06, "loss": 0.5817793846130371, "step": 21390, "token_acc": 0.8123917711435894 }, { "epoch": 1.3850741678872875, "grad_norm": 0.43043068051338196, "learning_rate": 2.1568122247891502e-06, "loss": 0.5927652359008789, "step": 21395, "token_acc": 0.809721674460533 }, { "epoch": 1.3853978684319137, "grad_norm": 0.25410187244415283, "learning_rate": 2.154721379679534e-06, "loss": 0.6051632404327393, "step": 21400, "token_acc": 0.8081559723876635 }, { "epoch": 1.3857215689765399, "grad_norm": 0.44373878836631775, "learning_rate": 2.152631270126797e-06, "loss": 0.6212539196014404, "step": 21405, "token_acc": 0.8047893639824574 }, { "epoch": 1.386045269521166, "grad_norm": 0.30131247639656067, "learning_rate": 2.1505418966712706e-06, "loss": 0.6101522445678711, "step": 21410, "token_acc": 0.8057570650448206 }, { "epoch": 1.3863689700657922, "grad_norm": 0.2524717152118683, "learning_rate": 2.1484532598530945e-06, "loss": 0.6079968452453614, "step": 21415, "token_acc": 0.8071537033912604 }, { "epoch": 1.3866926706104183, "grad_norm": 0.4189867675304413, "learning_rate": 2.1463653602122207e-06, "loss": 0.6076858520507813, "step": 21420, "token_acc": 0.8078315561369432 }, { "epoch": 1.3870163711550445, "grad_norm": 0.35400065779685974, "learning_rate": 2.1442781982884108e-06, "loss": 0.5868753433227539, "step": 21425, "token_acc": 0.8117218547529907 }, { "epoch": 1.3873400716996707, "grad_norm": 0.27275392413139343, "learning_rate": 2.142191774621233e-06, "loss": 0.6064041137695313, "step": 21430, "token_acc": 0.8078114870997019 }, { "epoch": 1.3876637722442968, "grad_norm": 0.3882024884223938, "learning_rate": 2.140106089750064e-06, "loss": 0.5994613647460938, "step": 21435, "token_acc": 0.8085358473739529 }, { "epoch": 1.387987472788923, "grad_norm": 0.37971121072769165, "learning_rate": 2.1380211442140975e-06, "loss": 0.5934159278869628, "step": 21440, "token_acc": 0.8100035796804321 }, { "epoch": 1.3883111733335491, "grad_norm": 0.32204321026802063, "learning_rate": 2.1359369385523266e-06, "loss": 0.6443913459777832, "step": 21445, "token_acc": 0.7986583808001579 }, { "epoch": 1.3886348738781753, "grad_norm": 0.29258713126182556, "learning_rate": 2.1338534733035577e-06, "loss": 0.6060538768768311, "step": 21450, "token_acc": 0.8064351412392393 }, { "epoch": 1.3889585744228015, "grad_norm": 0.2578437030315399, "learning_rate": 2.131770749006403e-06, "loss": 0.6427943229675293, "step": 21455, "token_acc": 0.7974760028013897 }, { "epoch": 1.3892822749674276, "grad_norm": 0.26868492364883423, "learning_rate": 2.1296887661992893e-06, "loss": 0.6223750591278077, "step": 21460, "token_acc": 0.8020428506536113 }, { "epoch": 1.3896059755120538, "grad_norm": 0.2916467785835266, "learning_rate": 2.127607525420442e-06, "loss": 0.5999565601348877, "step": 21465, "token_acc": 0.8095137851865983 }, { "epoch": 1.38992967605668, "grad_norm": 0.35467562079429626, "learning_rate": 2.1255270272079044e-06, "loss": 0.6123686313629151, "step": 21470, "token_acc": 0.8054329239351639 }, { "epoch": 1.390253376601306, "grad_norm": 0.23831874132156372, "learning_rate": 2.1234472720995224e-06, "loss": 0.6107475757598877, "step": 21475, "token_acc": 0.8061981102420444 }, { "epoch": 1.3905770771459323, "grad_norm": 0.29328837990760803, "learning_rate": 2.1213682606329506e-06, "loss": 0.5980595111846924, "step": 21480, "token_acc": 0.8096255974508763 }, { "epoch": 1.3909007776905584, "grad_norm": 0.2498471736907959, "learning_rate": 2.1192899933456502e-06, "loss": 0.5789847373962402, "step": 21485, "token_acc": 0.8132850865856811 }, { "epoch": 1.3912244782351846, "grad_norm": 0.36668986082077026, "learning_rate": 2.117212470774895e-06, "loss": 0.6195030212402344, "step": 21490, "token_acc": 0.8027396744045825 }, { "epoch": 1.3915481787798107, "grad_norm": 0.2704319357872009, "learning_rate": 2.1151356934577604e-06, "loss": 0.5931704044342041, "step": 21495, "token_acc": 0.8112363385896365 }, { "epoch": 1.391871879324437, "grad_norm": 0.31160593032836914, "learning_rate": 2.1130596619311326e-06, "loss": 0.5853563785552979, "step": 21500, "token_acc": 0.8112626724759578 }, { "epoch": 1.392195579869063, "grad_norm": 0.28751787543296814, "learning_rate": 2.1109843767317016e-06, "loss": 0.6057657241821289, "step": 21505, "token_acc": 0.8072125245929088 }, { "epoch": 1.3925192804136892, "grad_norm": 0.34795600175857544, "learning_rate": 2.108909838395973e-06, "loss": 0.6230082511901855, "step": 21510, "token_acc": 0.8025877581715145 }, { "epoch": 1.3928429809583154, "grad_norm": 0.3589794933795929, "learning_rate": 2.1068360474602446e-06, "loss": 0.6392251014709472, "step": 21515, "token_acc": 0.799320961202492 }, { "epoch": 1.3931666815029415, "grad_norm": 0.3302416503429413, "learning_rate": 2.104763004460635e-06, "loss": 0.5914234161376953, "step": 21520, "token_acc": 0.8109040123906223 }, { "epoch": 1.3934903820475677, "grad_norm": 0.39733606576919556, "learning_rate": 2.1026907099330613e-06, "loss": 0.5998664379119873, "step": 21525, "token_acc": 0.809418071450157 }, { "epoch": 1.3938140825921939, "grad_norm": 0.3503054082393646, "learning_rate": 2.100619164413255e-06, "loss": 0.5905999183654785, "step": 21530, "token_acc": 0.8100830003074085 }, { "epoch": 1.39413778313682, "grad_norm": 0.2693327069282532, "learning_rate": 2.0985483684367412e-06, "loss": 0.5903061389923095, "step": 21535, "token_acc": 0.8107063942848622 }, { "epoch": 1.3944614836814462, "grad_norm": 0.348051518201828, "learning_rate": 2.0964783225388642e-06, "loss": 0.5940690040588379, "step": 21540, "token_acc": 0.8104612560046276 }, { "epoch": 1.3947851842260723, "grad_norm": 0.2313263714313507, "learning_rate": 2.0944090272547672e-06, "loss": 0.6125397682189941, "step": 21545, "token_acc": 0.8064229754861619 }, { "epoch": 1.3951088847706985, "grad_norm": 0.2999633550643921, "learning_rate": 2.092340483119401e-06, "loss": 0.6099413871765137, "step": 21550, "token_acc": 0.8063842482100239 }, { "epoch": 1.3954325853153247, "grad_norm": 0.29732048511505127, "learning_rate": 2.0902726906675208e-06, "loss": 0.6158965587615967, "step": 21555, "token_acc": 0.8032686830326868 }, { "epoch": 1.395756285859951, "grad_norm": 0.21814700961112976, "learning_rate": 2.0882056504336946e-06, "loss": 0.5938830852508545, "step": 21560, "token_acc": 0.8103556944860033 }, { "epoch": 1.3960799864045772, "grad_norm": 0.30763888359069824, "learning_rate": 2.0861393629522824e-06, "loss": 0.6076069831848144, "step": 21565, "token_acc": 0.8060911112633854 }, { "epoch": 1.3964036869492034, "grad_norm": 0.33379390835762024, "learning_rate": 2.084073828757463e-06, "loss": 0.6052599906921386, "step": 21570, "token_acc": 0.8072859908460365 }, { "epoch": 1.3967273874938295, "grad_norm": 0.30205297470092773, "learning_rate": 2.0820090483832125e-06, "loss": 0.595198678970337, "step": 21575, "token_acc": 0.8109277686069989 }, { "epoch": 1.3970510880384557, "grad_norm": 0.33219170570373535, "learning_rate": 2.0799450223633185e-06, "loss": 0.6279903411865234, "step": 21580, "token_acc": 0.8000026580369068 }, { "epoch": 1.3973747885830818, "grad_norm": 0.3354595899581909, "learning_rate": 2.0778817512313633e-06, "loss": 0.6095685005187989, "step": 21585, "token_acc": 0.8062361833657652 }, { "epoch": 1.397698489127708, "grad_norm": 0.3936217427253723, "learning_rate": 2.0758192355207462e-06, "loss": 0.5968213558197022, "step": 21590, "token_acc": 0.8084434213812703 }, { "epoch": 1.3980221896723342, "grad_norm": 0.3569580912590027, "learning_rate": 2.0737574757646628e-06, "loss": 0.6117986679077149, "step": 21595, "token_acc": 0.8057949892428343 }, { "epoch": 1.3983458902169603, "grad_norm": 0.28101515769958496, "learning_rate": 2.071696472496117e-06, "loss": 0.6073368072509766, "step": 21600, "token_acc": 0.806874951963723 }, { "epoch": 1.3986695907615865, "grad_norm": 0.26882144808769226, "learning_rate": 2.069636226247913e-06, "loss": 0.624103307723999, "step": 21605, "token_acc": 0.8019088874826301 }, { "epoch": 1.3989932913062126, "grad_norm": 0.3471778333187103, "learning_rate": 2.0675767375526684e-06, "loss": 0.6051501750946044, "step": 21610, "token_acc": 0.8072132268799243 }, { "epoch": 1.3993169918508388, "grad_norm": 0.34374290704727173, "learning_rate": 2.065518006942792e-06, "loss": 0.6051115989685059, "step": 21615, "token_acc": 0.8051936702563895 }, { "epoch": 1.399640692395465, "grad_norm": 0.32168641686439514, "learning_rate": 2.063460034950509e-06, "loss": 0.6068493366241455, "step": 21620, "token_acc": 0.8069058575234405 }, { "epoch": 1.3999643929400911, "grad_norm": 0.2917729914188385, "learning_rate": 2.061402822107841e-06, "loss": 0.6050999641418457, "step": 21625, "token_acc": 0.8079405760510802 }, { "epoch": 1.4002880934847173, "grad_norm": 0.34030023217201233, "learning_rate": 2.0593463689466144e-06, "loss": 0.5985124588012696, "step": 21630, "token_acc": 0.8088756622408267 }, { "epoch": 1.4006117940293434, "grad_norm": 0.3972060978412628, "learning_rate": 2.05729067599846e-06, "loss": 0.6068375110626221, "step": 21635, "token_acc": 0.8077588414196232 }, { "epoch": 1.4009354945739696, "grad_norm": 0.2431924045085907, "learning_rate": 2.0552357437948146e-06, "loss": 0.5840141296386718, "step": 21640, "token_acc": 0.8132124435331433 }, { "epoch": 1.4012591951185958, "grad_norm": 0.34057173132896423, "learning_rate": 2.053181572866915e-06, "loss": 0.5988939285278321, "step": 21645, "token_acc": 0.8082798455559922 }, { "epoch": 1.401582895663222, "grad_norm": 0.29819804430007935, "learning_rate": 2.051128163745802e-06, "loss": 0.592226505279541, "step": 21650, "token_acc": 0.811588469551916 }, { "epoch": 1.401906596207848, "grad_norm": 0.33885031938552856, "learning_rate": 2.0490755169623193e-06, "loss": 0.6137294292449951, "step": 21655, "token_acc": 0.8057567670606176 }, { "epoch": 1.4022302967524742, "grad_norm": 0.34155595302581787, "learning_rate": 2.0470236330471125e-06, "loss": 0.6027752876281738, "step": 21660, "token_acc": 0.8077521896208665 }, { "epoch": 1.4025539972971004, "grad_norm": 0.3211902976036072, "learning_rate": 2.0449725125306345e-06, "loss": 0.5935115814208984, "step": 21665, "token_acc": 0.8105117113107898 }, { "epoch": 1.4028776978417266, "grad_norm": 0.373969167470932, "learning_rate": 2.042922155943137e-06, "loss": 0.626009750366211, "step": 21670, "token_acc": 0.8025571996567693 }, { "epoch": 1.4032013983863527, "grad_norm": 0.3005725145339966, "learning_rate": 2.0408725638146724e-06, "loss": 0.5951686382293702, "step": 21675, "token_acc": 0.8103767601167068 }, { "epoch": 1.4035250989309789, "grad_norm": 0.3088710606098175, "learning_rate": 2.0388237366751005e-06, "loss": 0.6274917602539063, "step": 21680, "token_acc": 0.8016261461933396 }, { "epoch": 1.403848799475605, "grad_norm": 0.31278786063194275, "learning_rate": 2.0367756750540806e-06, "loss": 0.6309249877929688, "step": 21685, "token_acc": 0.7985248791872249 }, { "epoch": 1.4041725000202314, "grad_norm": 0.39590001106262207, "learning_rate": 2.0347283794810714e-06, "loss": 0.6155230522155761, "step": 21690, "token_acc": 0.8056913064349852 }, { "epoch": 1.4044962005648576, "grad_norm": 0.28281375765800476, "learning_rate": 2.03268185048534e-06, "loss": 0.6162055492401123, "step": 21695, "token_acc": 0.803284299046001 }, { "epoch": 1.4048199011094837, "grad_norm": 0.32093438506126404, "learning_rate": 2.030636088595951e-06, "loss": 0.6171216011047364, "step": 21700, "token_acc": 0.8033141847105612 }, { "epoch": 1.40514360165411, "grad_norm": 0.3305385708808899, "learning_rate": 2.0285910943417706e-06, "loss": 0.6182077884674072, "step": 21705, "token_acc": 0.8054824221774818 }, { "epoch": 1.405467302198736, "grad_norm": 0.3381751775741577, "learning_rate": 2.0265468682514665e-06, "loss": 0.5987805843353271, "step": 21710, "token_acc": 0.8091774355799737 }, { "epoch": 1.4057910027433622, "grad_norm": 0.24360238015651703, "learning_rate": 2.0245034108535137e-06, "loss": 0.6081260681152344, "step": 21715, "token_acc": 0.8065074331148321 }, { "epoch": 1.4061147032879884, "grad_norm": 0.3062171936035156, "learning_rate": 2.022460722676177e-06, "loss": 0.606325626373291, "step": 21720, "token_acc": 0.8072538226299694 }, { "epoch": 1.4064384038326145, "grad_norm": 0.3436850309371948, "learning_rate": 2.0204188042475324e-06, "loss": 0.5892898082733155, "step": 21725, "token_acc": 0.8120498048207013 }, { "epoch": 1.4067621043772407, "grad_norm": 0.320779025554657, "learning_rate": 2.0183776560954533e-06, "loss": 0.6005910873413086, "step": 21730, "token_acc": 0.8088680664883696 }, { "epoch": 1.4070858049218669, "grad_norm": 0.346914678812027, "learning_rate": 2.0163372787476137e-06, "loss": 0.6130880832672119, "step": 21735, "token_acc": 0.8054248837975588 }, { "epoch": 1.407409505466493, "grad_norm": 0.33424803614616394, "learning_rate": 2.0142976727314866e-06, "loss": 0.6089773654937745, "step": 21740, "token_acc": 0.8051379243375011 }, { "epoch": 1.4077332060111192, "grad_norm": 0.309074729681015, "learning_rate": 2.012258838574352e-06, "loss": 0.6277301788330079, "step": 21745, "token_acc": 0.802003061841479 }, { "epoch": 1.4080569065557453, "grad_norm": 0.26831427216529846, "learning_rate": 2.0102207768032827e-06, "loss": 0.6027600288391113, "step": 21750, "token_acc": 0.8081861005185585 }, { "epoch": 1.4083806071003715, "grad_norm": 0.26809436082839966, "learning_rate": 2.0081834879451567e-06, "loss": 0.604628610610962, "step": 21755, "token_acc": 0.8081317124985248 }, { "epoch": 1.4087043076449977, "grad_norm": 0.35625359416007996, "learning_rate": 2.0061469725266485e-06, "loss": 0.5936473846435547, "step": 21760, "token_acc": 0.8103401746076725 }, { "epoch": 1.4090280081896238, "grad_norm": 0.36263853311538696, "learning_rate": 2.00411123107424e-06, "loss": 0.6089651107788085, "step": 21765, "token_acc": 0.8059682099701156 }, { "epoch": 1.40935170873425, "grad_norm": 0.39543795585632324, "learning_rate": 2.0020762641142005e-06, "loss": 0.5921533584594727, "step": 21770, "token_acc": 0.8098001744305356 }, { "epoch": 1.4096754092788761, "grad_norm": 0.2800646424293518, "learning_rate": 2.0000420721726122e-06, "loss": 0.6474410057067871, "step": 21775, "token_acc": 0.7973389072438362 }, { "epoch": 1.4099991098235023, "grad_norm": 0.31017300486564636, "learning_rate": 1.9980086557753493e-06, "loss": 0.5990583419799804, "step": 21780, "token_acc": 0.809826554293392 }, { "epoch": 1.4103228103681285, "grad_norm": 0.3293941915035248, "learning_rate": 1.9959760154480867e-06, "loss": 0.5989398956298828, "step": 21785, "token_acc": 0.8090888058498146 }, { "epoch": 1.4106465109127546, "grad_norm": 0.390351802110672, "learning_rate": 1.9939441517162983e-06, "loss": 0.6002597808837891, "step": 21790, "token_acc": 0.8081327277639824 }, { "epoch": 1.4109702114573808, "grad_norm": 0.34524598717689514, "learning_rate": 1.991913065105261e-06, "loss": 0.610637092590332, "step": 21795, "token_acc": 0.8060994922753811 }, { "epoch": 1.411293912002007, "grad_norm": 0.40353068709373474, "learning_rate": 1.9898827561400475e-06, "loss": 0.60623140335083, "step": 21800, "token_acc": 0.8071314687029997 }, { "epoch": 1.411617612546633, "grad_norm": 0.22534675896167755, "learning_rate": 1.987853225345529e-06, "loss": 0.6235541343688965, "step": 21805, "token_acc": 0.8023870295143257 }, { "epoch": 1.4119413130912593, "grad_norm": 0.29479509592056274, "learning_rate": 1.985824473246375e-06, "loss": 0.5837502956390381, "step": 21810, "token_acc": 0.8121226132840124 }, { "epoch": 1.4122650136358854, "grad_norm": 0.3569989800453186, "learning_rate": 1.9837965003670613e-06, "loss": 0.5979376792907715, "step": 21815, "token_acc": 0.8082570490475799 }, { "epoch": 1.4125887141805116, "grad_norm": 0.32105687260627747, "learning_rate": 1.9817693072318477e-06, "loss": 0.600281047821045, "step": 21820, "token_acc": 0.8070321567556497 }, { "epoch": 1.4129124147251377, "grad_norm": 0.3605409264564514, "learning_rate": 1.979742894364808e-06, "loss": 0.5922582149505615, "step": 21825, "token_acc": 0.809719729032089 }, { "epoch": 1.413236115269764, "grad_norm": 0.31482580304145813, "learning_rate": 1.9777172622898033e-06, "loss": 0.6083170413970947, "step": 21830, "token_acc": 0.8051066045102818 }, { "epoch": 1.41355981581439, "grad_norm": 0.2629224359989166, "learning_rate": 1.9756924115304985e-06, "loss": 0.5861042022705079, "step": 21835, "token_acc": 0.8122237599892852 }, { "epoch": 1.4138835163590162, "grad_norm": 0.32064297795295715, "learning_rate": 1.9736683426103533e-06, "loss": 0.5915960788726806, "step": 21840, "token_acc": 0.8101733051865148 }, { "epoch": 1.4142072169036424, "grad_norm": 0.41202512383461, "learning_rate": 1.9716450560526286e-06, "loss": 0.6071003913879395, "step": 21845, "token_acc": 0.8079842137219186 }, { "epoch": 1.4145309174482685, "grad_norm": 0.3566247522830963, "learning_rate": 1.9696225523803803e-06, "loss": 0.6197120666503906, "step": 21850, "token_acc": 0.8031625915577102 }, { "epoch": 1.4148546179928947, "grad_norm": 0.2764502167701721, "learning_rate": 1.967600832116463e-06, "loss": 0.6182141304016113, "step": 21855, "token_acc": 0.8039953945104682 }, { "epoch": 1.4151783185375209, "grad_norm": 0.44615110754966736, "learning_rate": 1.9655798957835265e-06, "loss": 0.5970151901245118, "step": 21860, "token_acc": 0.8087798036465638 }, { "epoch": 1.415502019082147, "grad_norm": 0.2921011745929718, "learning_rate": 1.9635597439040255e-06, "loss": 0.5999674320220947, "step": 21865, "token_acc": 0.8077193944644226 }, { "epoch": 1.4158257196267732, "grad_norm": 0.31634247303009033, "learning_rate": 1.9615403770001995e-06, "loss": 0.6313540935516357, "step": 21870, "token_acc": 0.80022346845821 }, { "epoch": 1.4161494201713993, "grad_norm": 0.32961365580558777, "learning_rate": 1.959521795594097e-06, "loss": 0.5933090686798096, "step": 21875, "token_acc": 0.8097974503332687 }, { "epoch": 1.4164731207160255, "grad_norm": 0.375340074300766, "learning_rate": 1.957504000207557e-06, "loss": 0.6310998916625976, "step": 21880, "token_acc": 0.7997718552317743 }, { "epoch": 1.4167968212606517, "grad_norm": 0.3414098024368286, "learning_rate": 1.9554869913622164e-06, "loss": 0.6148220062255859, "step": 21885, "token_acc": 0.8033105007285553 }, { "epoch": 1.4171205218052778, "grad_norm": 0.25904393196105957, "learning_rate": 1.953470769579509e-06, "loss": 0.6047789573669433, "step": 21890, "token_acc": 0.8056896234828012 }, { "epoch": 1.417444222349904, "grad_norm": 0.4264904856681824, "learning_rate": 1.9514553353806644e-06, "loss": 0.6014879226684571, "step": 21895, "token_acc": 0.8075696469566297 }, { "epoch": 1.4177679228945304, "grad_norm": 0.3792853355407715, "learning_rate": 1.9494406892867114e-06, "loss": 0.5909170150756836, "step": 21900, "token_acc": 0.8107562395487126 }, { "epoch": 1.4180916234391565, "grad_norm": 0.2781294584274292, "learning_rate": 1.9474268318184725e-06, "loss": 0.6008384704589844, "step": 21905, "token_acc": 0.8080081935864443 }, { "epoch": 1.4184153239837827, "grad_norm": 0.40128278732299805, "learning_rate": 1.945413763496567e-06, "loss": 0.5994678020477295, "step": 21910, "token_acc": 0.8084108712441617 }, { "epoch": 1.4187390245284088, "grad_norm": 0.40845638513565063, "learning_rate": 1.9434014848414097e-06, "loss": 0.6124649047851562, "step": 21915, "token_acc": 0.8052966675697643 }, { "epoch": 1.419062725073035, "grad_norm": 0.295032262802124, "learning_rate": 1.9413899963732106e-06, "loss": 0.6360205173492431, "step": 21920, "token_acc": 0.799986935362707 }, { "epoch": 1.4193864256176612, "grad_norm": 0.31309276819229126, "learning_rate": 1.9393792986119767e-06, "loss": 0.5897377014160157, "step": 21925, "token_acc": 0.8103784835342007 }, { "epoch": 1.4197101261622873, "grad_norm": 0.3310197591781616, "learning_rate": 1.9373693920775126e-06, "loss": 0.6061924934387207, "step": 21930, "token_acc": 0.8078365774533658 }, { "epoch": 1.4200338267069135, "grad_norm": 0.43649041652679443, "learning_rate": 1.9353602772894154e-06, "loss": 0.6049371719360351, "step": 21935, "token_acc": 0.8060144269155585 }, { "epoch": 1.4203575272515396, "grad_norm": 0.32269543409347534, "learning_rate": 1.9333519547670773e-06, "loss": 0.5857161521911621, "step": 21940, "token_acc": 0.811650727997002 }, { "epoch": 1.4206812277961658, "grad_norm": 0.2723448574542999, "learning_rate": 1.931344425029685e-06, "loss": 0.5849769592285157, "step": 21945, "token_acc": 0.8132619159734212 }, { "epoch": 1.421004928340792, "grad_norm": 0.2776789367198944, "learning_rate": 1.9293376885962267e-06, "loss": 0.5912519454956054, "step": 21950, "token_acc": 0.8098572373283541 }, { "epoch": 1.421328628885418, "grad_norm": 0.2950287163257599, "learning_rate": 1.927331745985475e-06, "loss": 0.5788369178771973, "step": 21955, "token_acc": 0.8146394415227115 }, { "epoch": 1.4216523294300443, "grad_norm": 0.507353663444519, "learning_rate": 1.9253265977160074e-06, "loss": 0.6070298194885254, "step": 21960, "token_acc": 0.8058683405548515 }, { "epoch": 1.4219760299746704, "grad_norm": 0.36118799448013306, "learning_rate": 1.92332224430619e-06, "loss": 0.6257360935211181, "step": 21965, "token_acc": 0.8025848099071042 }, { "epoch": 1.4222997305192966, "grad_norm": 0.2704084515571594, "learning_rate": 1.9213186862741845e-06, "loss": 0.6227851390838623, "step": 21970, "token_acc": 0.8022923703556527 }, { "epoch": 1.4226234310639227, "grad_norm": 0.4379176199436188, "learning_rate": 1.9193159241379467e-06, "loss": 0.5864459991455078, "step": 21975, "token_acc": 0.8130590086322981 }, { "epoch": 1.422947131608549, "grad_norm": 0.4521101713180542, "learning_rate": 1.9173139584152307e-06, "loss": 0.6288810729980469, "step": 21980, "token_acc": 0.8011901650549849 }, { "epoch": 1.423270832153175, "grad_norm": 0.3030271828174591, "learning_rate": 1.915312789623579e-06, "loss": 0.6192741870880127, "step": 21985, "token_acc": 0.8028936756570548 }, { "epoch": 1.4235945326978012, "grad_norm": 0.3535589575767517, "learning_rate": 1.9133124182803314e-06, "loss": 0.5790410995483398, "step": 21990, "token_acc": 0.8142448781789705 }, { "epoch": 1.4239182332424274, "grad_norm": 0.4128485321998596, "learning_rate": 1.9113128449026193e-06, "loss": 0.6019806385040283, "step": 21995, "token_acc": 0.8082650566851233 }, { "epoch": 1.4242419337870535, "grad_norm": 0.4160822033882141, "learning_rate": 1.909314070007373e-06, "loss": 0.6098884105682373, "step": 22000, "token_acc": 0.8054699512110703 }, { "epoch": 1.4245656343316797, "grad_norm": 0.395944207906723, "learning_rate": 1.9073160941113068e-06, "loss": 0.6081625938415527, "step": 22005, "token_acc": 0.8068166266469263 }, { "epoch": 1.4248893348763059, "grad_norm": 0.2655559778213501, "learning_rate": 1.905318917730939e-06, "loss": 0.5990860939025879, "step": 22010, "token_acc": 0.8081090945286837 }, { "epoch": 1.425213035420932, "grad_norm": 0.3676702380180359, "learning_rate": 1.9033225413825728e-06, "loss": 0.6243730068206788, "step": 22015, "token_acc": 0.8026738979630447 }, { "epoch": 1.4255367359655582, "grad_norm": 0.3344113826751709, "learning_rate": 1.9013269655823142e-06, "loss": 0.6004489898681641, "step": 22020, "token_acc": 0.8096816079205779 }, { "epoch": 1.4258604365101843, "grad_norm": 0.35497987270355225, "learning_rate": 1.8993321908460483e-06, "loss": 0.5853458404541015, "step": 22025, "token_acc": 0.8127209848504401 }, { "epoch": 1.4261841370548107, "grad_norm": 0.2918533980846405, "learning_rate": 1.8973382176894667e-06, "loss": 0.6052596569061279, "step": 22030, "token_acc": 0.8084071486089826 }, { "epoch": 1.426507837599437, "grad_norm": 0.26776623725891113, "learning_rate": 1.895345046628047e-06, "loss": 0.5963624477386474, "step": 22035, "token_acc": 0.8087881272982196 }, { "epoch": 1.426831538144063, "grad_norm": 0.4262397587299347, "learning_rate": 1.89335267817706e-06, "loss": 0.6068666458129883, "step": 22040, "token_acc": 0.8059297223499865 }, { "epoch": 1.4271552386886892, "grad_norm": 0.3485472798347473, "learning_rate": 1.891361112851568e-06, "loss": 0.5946514129638671, "step": 22045, "token_acc": 0.8094693279810665 }, { "epoch": 1.4274789392333154, "grad_norm": 0.26093101501464844, "learning_rate": 1.8893703511664324e-06, "loss": 0.6197484493255615, "step": 22050, "token_acc": 0.8027427678516356 }, { "epoch": 1.4278026397779415, "grad_norm": 0.30643430352211, "learning_rate": 1.887380393636295e-06, "loss": 0.5956783294677734, "step": 22055, "token_acc": 0.8105202510542316 }, { "epoch": 1.4281263403225677, "grad_norm": 0.34594765305519104, "learning_rate": 1.885391240775601e-06, "loss": 0.5907033443450928, "step": 22060, "token_acc": 0.8101176358656872 }, { "epoch": 1.4284500408671938, "grad_norm": 0.35843944549560547, "learning_rate": 1.8834028930985803e-06, "loss": 0.610577917098999, "step": 22065, "token_acc": 0.8060086310303465 }, { "epoch": 1.42877374141182, "grad_norm": 0.34512096643447876, "learning_rate": 1.8814153511192622e-06, "loss": 0.6081363201141358, "step": 22070, "token_acc": 0.8073357385648205 }, { "epoch": 1.4290974419564462, "grad_norm": 0.33416131138801575, "learning_rate": 1.8794286153514563e-06, "loss": 0.6073312759399414, "step": 22075, "token_acc": 0.8057037817000696 }, { "epoch": 1.4294211425010723, "grad_norm": 0.3469647467136383, "learning_rate": 1.8774426863087753e-06, "loss": 0.588625717163086, "step": 22080, "token_acc": 0.8125333833783257 }, { "epoch": 1.4297448430456985, "grad_norm": 0.2599055767059326, "learning_rate": 1.8754575645046164e-06, "loss": 0.6146186351776123, "step": 22085, "token_acc": 0.8047203457886533 }, { "epoch": 1.4300685435903246, "grad_norm": 0.33141693472862244, "learning_rate": 1.8734732504521708e-06, "loss": 0.611210823059082, "step": 22090, "token_acc": 0.8056833091637318 }, { "epoch": 1.4303922441349508, "grad_norm": 0.3198060393333435, "learning_rate": 1.8714897446644176e-06, "loss": 0.5939502239227294, "step": 22095, "token_acc": 0.8095847937449447 }, { "epoch": 1.430715944679577, "grad_norm": 0.2927035093307495, "learning_rate": 1.8695070476541348e-06, "loss": 0.5902384757995606, "step": 22100, "token_acc": 0.8113002283321632 }, { "epoch": 1.4310396452242031, "grad_norm": 0.31594738364219666, "learning_rate": 1.8675251599338805e-06, "loss": 0.6176301956176757, "step": 22105, "token_acc": 0.8031390535187778 }, { "epoch": 1.4313633457688293, "grad_norm": 0.32448050379753113, "learning_rate": 1.8655440820160125e-06, "loss": 0.6050626754760742, "step": 22110, "token_acc": 0.8072459310682476 }, { "epoch": 1.4316870463134554, "grad_norm": 0.38743510842323303, "learning_rate": 1.8635638144126756e-06, "loss": 0.6228161811828613, "step": 22115, "token_acc": 0.804687661902558 }, { "epoch": 1.4320107468580816, "grad_norm": 0.31861257553100586, "learning_rate": 1.8615843576358045e-06, "loss": 0.6137866497039794, "step": 22120, "token_acc": 0.8054261297120112 }, { "epoch": 1.4323344474027078, "grad_norm": 0.2905128002166748, "learning_rate": 1.859605712197124e-06, "loss": 0.6047208786010743, "step": 22125, "token_acc": 0.8063984770031527 }, { "epoch": 1.432658147947334, "grad_norm": 0.3357781171798706, "learning_rate": 1.8576278786081537e-06, "loss": 0.5914220333099365, "step": 22130, "token_acc": 0.8116667884448047 }, { "epoch": 1.43298184849196, "grad_norm": 0.28469404578208923, "learning_rate": 1.855650857380198e-06, "loss": 0.6102324008941651, "step": 22135, "token_acc": 0.806110513264399 }, { "epoch": 1.4333055490365862, "grad_norm": 0.28143349289894104, "learning_rate": 1.8536746490243528e-06, "loss": 0.6003706932067872, "step": 22140, "token_acc": 0.8086298627755683 }, { "epoch": 1.4336292495812124, "grad_norm": 0.37377557158470154, "learning_rate": 1.8516992540515056e-06, "loss": 0.6093939781188965, "step": 22145, "token_acc": 0.8060169894334012 }, { "epoch": 1.4339529501258386, "grad_norm": 0.3013562560081482, "learning_rate": 1.84972467297233e-06, "loss": 0.6053746223449707, "step": 22150, "token_acc": 0.8071959073439285 }, { "epoch": 1.4342766506704647, "grad_norm": 0.41152507066726685, "learning_rate": 1.8477509062972947e-06, "loss": 0.6134701251983643, "step": 22155, "token_acc": 0.8043770862495963 }, { "epoch": 1.4346003512150909, "grad_norm": 0.3921172618865967, "learning_rate": 1.8457779545366532e-06, "loss": 0.6131926059722901, "step": 22160, "token_acc": 0.8065997187922728 }, { "epoch": 1.434924051759717, "grad_norm": 0.3403335213661194, "learning_rate": 1.8438058182004503e-06, "loss": 0.6040429592132568, "step": 22165, "token_acc": 0.807378860351461 }, { "epoch": 1.4352477523043432, "grad_norm": 0.3141685128211975, "learning_rate": 1.8418344977985187e-06, "loss": 0.6162731170654296, "step": 22170, "token_acc": 0.8048834008258693 }, { "epoch": 1.4355714528489694, "grad_norm": 0.3952360153198242, "learning_rate": 1.8398639938404817e-06, "loss": 0.6040067195892334, "step": 22175, "token_acc": 0.80701394585726 }, { "epoch": 1.4358951533935955, "grad_norm": 0.25698161125183105, "learning_rate": 1.8378943068357485e-06, "loss": 0.6063200950622558, "step": 22180, "token_acc": 0.8057902230659706 }, { "epoch": 1.4362188539382217, "grad_norm": 0.42742446064949036, "learning_rate": 1.8359254372935248e-06, "loss": 0.6109306335449218, "step": 22185, "token_acc": 0.8073090988976908 }, { "epoch": 1.4365425544828478, "grad_norm": 0.3925442695617676, "learning_rate": 1.8339573857227932e-06, "loss": 0.6039934158325195, "step": 22190, "token_acc": 0.8080917677458199 }, { "epoch": 1.436866255027474, "grad_norm": 0.262929230928421, "learning_rate": 1.8319901526323358e-06, "loss": 0.6126141548156738, "step": 22195, "token_acc": 0.8063473446848318 }, { "epoch": 1.4371899555721002, "grad_norm": 0.3614024221897125, "learning_rate": 1.8300237385307157e-06, "loss": 0.61643967628479, "step": 22200, "token_acc": 0.8035816253386628 }, { "epoch": 1.4375136561167263, "grad_norm": 0.35937148332595825, "learning_rate": 1.8280581439262913e-06, "loss": 0.6107302665710449, "step": 22205, "token_acc": 0.8057152431520502 }, { "epoch": 1.4378373566613525, "grad_norm": 0.3173360228538513, "learning_rate": 1.8260933693271993e-06, "loss": 0.6025022029876709, "step": 22210, "token_acc": 0.807734999161063 }, { "epoch": 1.4381610572059786, "grad_norm": 0.28584539890289307, "learning_rate": 1.824129415241374e-06, "loss": 0.5846347808837891, "step": 22215, "token_acc": 0.811102417077256 }, { "epoch": 1.4384847577506048, "grad_norm": 0.3079756200313568, "learning_rate": 1.8221662821765335e-06, "loss": 0.6156644344329834, "step": 22220, "token_acc": 0.8054929233109668 }, { "epoch": 1.438808458295231, "grad_norm": 0.35522985458374023, "learning_rate": 1.8202039706401826e-06, "loss": 0.5863254547119141, "step": 22225, "token_acc": 0.811080126190665 }, { "epoch": 1.4391321588398571, "grad_norm": 0.29274705052375793, "learning_rate": 1.8182424811396131e-06, "loss": 0.6015525817871094, "step": 22230, "token_acc": 0.8085406345525455 }, { "epoch": 1.4394558593844833, "grad_norm": 0.3309204578399658, "learning_rate": 1.8162818141819122e-06, "loss": 0.5997155189514161, "step": 22235, "token_acc": 0.808756343487353 }, { "epoch": 1.4397795599291094, "grad_norm": 0.2832494080066681, "learning_rate": 1.8143219702739413e-06, "loss": 0.6388392448425293, "step": 22240, "token_acc": 0.7987682648545745 }, { "epoch": 1.4401032604737358, "grad_norm": 0.39421510696411133, "learning_rate": 1.8123629499223606e-06, "loss": 0.6078163146972656, "step": 22245, "token_acc": 0.8064587668203848 }, { "epoch": 1.440426961018362, "grad_norm": 0.3733595907688141, "learning_rate": 1.81040475363361e-06, "loss": 0.603285551071167, "step": 22250, "token_acc": 0.8081953687171995 }, { "epoch": 1.4407506615629881, "grad_norm": 0.2975884675979614, "learning_rate": 1.8084473819139241e-06, "loss": 0.6172417640686035, "step": 22255, "token_acc": 0.8055286580270331 }, { "epoch": 1.4410743621076143, "grad_norm": 0.21493013203144073, "learning_rate": 1.8064908352693134e-06, "loss": 0.6026329040527344, "step": 22260, "token_acc": 0.8085756467038963 }, { "epoch": 1.4413980626522405, "grad_norm": 0.3289962410926819, "learning_rate": 1.804535114205585e-06, "loss": 0.59806227684021, "step": 22265, "token_acc": 0.807714396872742 }, { "epoch": 1.4417217631968666, "grad_norm": 0.3756510019302368, "learning_rate": 1.8025802192283288e-06, "loss": 0.6152998447418213, "step": 22270, "token_acc": 0.8067331256766 }, { "epoch": 1.4420454637414928, "grad_norm": 0.3320239782333374, "learning_rate": 1.8006261508429195e-06, "loss": 0.6342500686645508, "step": 22275, "token_acc": 0.8004837468869388 }, { "epoch": 1.442369164286119, "grad_norm": 0.3071822226047516, "learning_rate": 1.7986729095545191e-06, "loss": 0.6111244201660156, "step": 22280, "token_acc": 0.8061619763474513 }, { "epoch": 1.442692864830745, "grad_norm": 0.33146247267723083, "learning_rate": 1.7967204958680796e-06, "loss": 0.6111873149871826, "step": 22285, "token_acc": 0.8051938952303302 }, { "epoch": 1.4430165653753713, "grad_norm": 0.2638182044029236, "learning_rate": 1.7947689102883337e-06, "loss": 0.600447702407837, "step": 22290, "token_acc": 0.8086292163327415 }, { "epoch": 1.4433402659199974, "grad_norm": 0.34303906559944153, "learning_rate": 1.7928181533198025e-06, "loss": 0.5991978645324707, "step": 22295, "token_acc": 0.807004100948306 }, { "epoch": 1.4436639664646236, "grad_norm": 0.3044310510158539, "learning_rate": 1.7908682254667913e-06, "loss": 0.5938996791839599, "step": 22300, "token_acc": 0.8098526467115059 }, { "epoch": 1.4439876670092497, "grad_norm": 0.3880491256713867, "learning_rate": 1.7889191272333967e-06, "loss": 0.6312888145446778, "step": 22305, "token_acc": 0.8027883122042836 }, { "epoch": 1.444311367553876, "grad_norm": 0.3405056595802307, "learning_rate": 1.7869708591234896e-06, "loss": 0.5900967121124268, "step": 22310, "token_acc": 0.8104751583065797 }, { "epoch": 1.444635068098502, "grad_norm": 0.33940649032592773, "learning_rate": 1.7850234216407391e-06, "loss": 0.5866680145263672, "step": 22315, "token_acc": 0.8125024782901781 }, { "epoch": 1.4449587686431282, "grad_norm": 0.329312801361084, "learning_rate": 1.7830768152885913e-06, "loss": 0.6061891555786133, "step": 22320, "token_acc": 0.8077783148058644 }, { "epoch": 1.4452824691877544, "grad_norm": 0.38588881492614746, "learning_rate": 1.7811310405702797e-06, "loss": 0.6036844253540039, "step": 22325, "token_acc": 0.8070762285496723 }, { "epoch": 1.4456061697323805, "grad_norm": 0.29737696051597595, "learning_rate": 1.779186097988822e-06, "loss": 0.6074584484100342, "step": 22330, "token_acc": 0.8057828527669876 }, { "epoch": 1.4459298702770067, "grad_norm": 0.2800498902797699, "learning_rate": 1.7772419880470238e-06, "loss": 0.5905674934387207, "step": 22335, "token_acc": 0.8108350272814807 }, { "epoch": 1.4462535708216329, "grad_norm": 0.32807284593582153, "learning_rate": 1.7752987112474724e-06, "loss": 0.6046620845794678, "step": 22340, "token_acc": 0.8055126631560887 }, { "epoch": 1.446577271366259, "grad_norm": 0.29322946071624756, "learning_rate": 1.7733562680925403e-06, "loss": 0.5911740779876709, "step": 22345, "token_acc": 0.8107171506497673 }, { "epoch": 1.4469009719108852, "grad_norm": 0.34101155400276184, "learning_rate": 1.771414659084385e-06, "loss": 0.6074857234954834, "step": 22350, "token_acc": 0.8082749921160517 }, { "epoch": 1.4472246724555113, "grad_norm": 0.3315340280532837, "learning_rate": 1.7694738847249483e-06, "loss": 0.6063518524169922, "step": 22355, "token_acc": 0.8055470115115541 }, { "epoch": 1.4475483730001375, "grad_norm": 0.23971009254455566, "learning_rate": 1.767533945515954e-06, "loss": 0.6027677059173584, "step": 22360, "token_acc": 0.8071855690030366 }, { "epoch": 1.4478720735447637, "grad_norm": 0.293367475271225, "learning_rate": 1.7655948419589153e-06, "loss": 0.6006639480590821, "step": 22365, "token_acc": 0.8078014861109455 }, { "epoch": 1.44819577408939, "grad_norm": 0.34127455949783325, "learning_rate": 1.7636565745551255e-06, "loss": 0.6118844032287598, "step": 22370, "token_acc": 0.8058359499575019 }, { "epoch": 1.4485194746340162, "grad_norm": 0.24034897983074188, "learning_rate": 1.7617191438056608e-06, "loss": 0.6416442394256592, "step": 22375, "token_acc": 0.7987390851246998 }, { "epoch": 1.4488431751786424, "grad_norm": 0.382911741733551, "learning_rate": 1.7597825502113842e-06, "loss": 0.6191469192504883, "step": 22380, "token_acc": 0.8039155366327861 }, { "epoch": 1.4491668757232685, "grad_norm": 0.3614951968193054, "learning_rate": 1.7578467942729382e-06, "loss": 0.591596269607544, "step": 22385, "token_acc": 0.8106562675361022 }, { "epoch": 1.4494905762678947, "grad_norm": 0.3416374623775482, "learning_rate": 1.755911876490755e-06, "loss": 0.5735852241516113, "step": 22390, "token_acc": 0.8146023613276899 }, { "epoch": 1.4498142768125208, "grad_norm": 0.30709901452064514, "learning_rate": 1.7539777973650446e-06, "loss": 0.5970231056213379, "step": 22395, "token_acc": 0.8084923664122138 }, { "epoch": 1.450137977357147, "grad_norm": 0.4415408968925476, "learning_rate": 1.7520445573958023e-06, "loss": 0.6125824928283692, "step": 22400, "token_acc": 0.8065205186838466 }, { "epoch": 1.4504616779017732, "grad_norm": 0.29454177618026733, "learning_rate": 1.750112157082806e-06, "loss": 0.6104018688201904, "step": 22405, "token_acc": 0.8063857956980307 }, { "epoch": 1.4507853784463993, "grad_norm": 0.316042423248291, "learning_rate": 1.7481805969256172e-06, "loss": 0.6043789386749268, "step": 22410, "token_acc": 0.80747791952895 }, { "epoch": 1.4511090789910255, "grad_norm": 0.29190793633461, "learning_rate": 1.7462498774235776e-06, "loss": 0.5902798652648926, "step": 22415, "token_acc": 0.8120455263989883 }, { "epoch": 1.4514327795356516, "grad_norm": 0.43761107325553894, "learning_rate": 1.7443199990758168e-06, "loss": 0.594058609008789, "step": 22420, "token_acc": 0.810971069251772 }, { "epoch": 1.4517564800802778, "grad_norm": 0.41984468698501587, "learning_rate": 1.7423909623812424e-06, "loss": 0.5966863632202148, "step": 22425, "token_acc": 0.8093019414602589 }, { "epoch": 1.452080180624904, "grad_norm": 0.2701086401939392, "learning_rate": 1.7404627678385466e-06, "loss": 0.5945908546447753, "step": 22430, "token_acc": 0.8104279511023963 }, { "epoch": 1.4524038811695301, "grad_norm": 0.4663260281085968, "learning_rate": 1.7385354159462004e-06, "loss": 0.6160743713378907, "step": 22435, "token_acc": 0.8052641666134287 }, { "epoch": 1.4527275817141563, "grad_norm": 0.3358099162578583, "learning_rate": 1.7366089072024655e-06, "loss": 0.6009190082550049, "step": 22440, "token_acc": 0.8079466330960462 }, { "epoch": 1.4530512822587824, "grad_norm": 0.3652559518814087, "learning_rate": 1.7346832421053727e-06, "loss": 0.5986167907714843, "step": 22445, "token_acc": 0.8090889799173028 }, { "epoch": 1.4533749828034086, "grad_norm": 0.31027570366859436, "learning_rate": 1.7327584211527476e-06, "loss": 0.6099766731262207, "step": 22450, "token_acc": 0.8058107690994227 }, { "epoch": 1.4536986833480348, "grad_norm": 0.2616700232028961, "learning_rate": 1.7308344448421894e-06, "loss": 0.6099893093109131, "step": 22455, "token_acc": 0.8050691338917005 }, { "epoch": 1.454022383892661, "grad_norm": 0.3295402228832245, "learning_rate": 1.7289113136710817e-06, "loss": 0.6047229766845703, "step": 22460, "token_acc": 0.8069171040424964 }, { "epoch": 1.454346084437287, "grad_norm": 0.2850024700164795, "learning_rate": 1.7269890281365876e-06, "loss": 0.6196771621704101, "step": 22465, "token_acc": 0.8035821087494774 }, { "epoch": 1.4546697849819132, "grad_norm": 0.3843737840652466, "learning_rate": 1.7250675887356561e-06, "loss": 0.5988304138183593, "step": 22470, "token_acc": 0.8090679623903578 }, { "epoch": 1.4549934855265394, "grad_norm": 0.2652477025985718, "learning_rate": 1.7231469959650142e-06, "loss": 0.590077018737793, "step": 22475, "token_acc": 0.8104703772120044 }, { "epoch": 1.4553171860711656, "grad_norm": 0.3581297993659973, "learning_rate": 1.7212272503211692e-06, "loss": 0.5920826911926269, "step": 22480, "token_acc": 0.8114463872723924 }, { "epoch": 1.4556408866157917, "grad_norm": 0.33032968640327454, "learning_rate": 1.71930835230041e-06, "loss": 0.611225700378418, "step": 22485, "token_acc": 0.804994498458925 }, { "epoch": 1.4559645871604179, "grad_norm": 0.3331901729106903, "learning_rate": 1.7173903023988109e-06, "loss": 0.6144105434417725, "step": 22490, "token_acc": 0.805291785100186 }, { "epoch": 1.456288287705044, "grad_norm": 0.37977659702301025, "learning_rate": 1.7154731011122178e-06, "loss": 0.5870308876037598, "step": 22495, "token_acc": 0.8113717128642501 }, { "epoch": 1.4566119882496702, "grad_norm": 0.3084089457988739, "learning_rate": 1.7135567489362664e-06, "loss": 0.6032567501068116, "step": 22500, "token_acc": 0.8085213202618814 }, { "epoch": 1.4569356887942964, "grad_norm": 0.4708234369754791, "learning_rate": 1.7116412463663663e-06, "loss": 0.6132768630981446, "step": 22505, "token_acc": 0.8039447565147612 }, { "epoch": 1.4572593893389225, "grad_norm": 0.27259016036987305, "learning_rate": 1.7097265938977149e-06, "loss": 0.5836855888366699, "step": 22510, "token_acc": 0.8120243829215126 }, { "epoch": 1.4575830898835487, "grad_norm": 0.39090266823768616, "learning_rate": 1.7078127920252784e-06, "loss": 0.5846968650817871, "step": 22515, "token_acc": 0.812916767023363 }, { "epoch": 1.4579067904281748, "grad_norm": 0.4021725654602051, "learning_rate": 1.7058998412438155e-06, "loss": 0.6168601036071777, "step": 22520, "token_acc": 0.8051311815072768 }, { "epoch": 1.458230490972801, "grad_norm": 0.23477059602737427, "learning_rate": 1.7039877420478562e-06, "loss": 0.6183853149414062, "step": 22525, "token_acc": 0.804289749938967 }, { "epoch": 1.4585541915174272, "grad_norm": 0.4343772232532501, "learning_rate": 1.7020764949317143e-06, "loss": 0.5933317184448242, "step": 22530, "token_acc": 0.8096442769373742 }, { "epoch": 1.4588778920620533, "grad_norm": 0.2834841012954712, "learning_rate": 1.7001661003894798e-06, "loss": 0.6025009632110596, "step": 22535, "token_acc": 0.8075668457698789 }, { "epoch": 1.4592015926066795, "grad_norm": 0.28530117869377136, "learning_rate": 1.6982565589150313e-06, "loss": 0.598045015335083, "step": 22540, "token_acc": 0.8090192557118627 }, { "epoch": 1.4595252931513056, "grad_norm": 0.38984331488609314, "learning_rate": 1.6963478710020126e-06, "loss": 0.6045328140258789, "step": 22545, "token_acc": 0.8083660898406999 }, { "epoch": 1.4598489936959318, "grad_norm": 0.31571123003959656, "learning_rate": 1.6944400371438595e-06, "loss": 0.6429012298583985, "step": 22550, "token_acc": 0.7967745524676095 }, { "epoch": 1.460172694240558, "grad_norm": 0.2950453460216522, "learning_rate": 1.6925330578337795e-06, "loss": 0.607561445236206, "step": 22555, "token_acc": 0.805785236175037 }, { "epoch": 1.4604963947851841, "grad_norm": 0.3254185914993286, "learning_rate": 1.6906269335647668e-06, "loss": 0.6298431396484375, "step": 22560, "token_acc": 0.801208248169517 }, { "epoch": 1.4608200953298103, "grad_norm": 0.2936904728412628, "learning_rate": 1.6887216648295824e-06, "loss": 0.5908546447753906, "step": 22565, "token_acc": 0.8107937015229923 }, { "epoch": 1.4611437958744364, "grad_norm": 0.425326943397522, "learning_rate": 1.6868172521207786e-06, "loss": 0.6246141910552978, "step": 22570, "token_acc": 0.8025198743743253 }, { "epoch": 1.4614674964190626, "grad_norm": 0.3750622272491455, "learning_rate": 1.68491369593068e-06, "loss": 0.6036381721496582, "step": 22575, "token_acc": 0.8088001772591307 }, { "epoch": 1.4617911969636888, "grad_norm": 0.2947201728820801, "learning_rate": 1.6830109967513903e-06, "loss": 0.6228940963745118, "step": 22580, "token_acc": 0.8037813073826997 }, { "epoch": 1.4621148975083151, "grad_norm": 0.4697037935256958, "learning_rate": 1.6811091550747904e-06, "loss": 0.5925629138946533, "step": 22585, "token_acc": 0.8115242617732905 }, { "epoch": 1.4624385980529413, "grad_norm": 0.33543655276298523, "learning_rate": 1.6792081713925467e-06, "loss": 0.6162841796875, "step": 22590, "token_acc": 0.8046788558993074 }, { "epoch": 1.4627622985975675, "grad_norm": 0.2623262107372284, "learning_rate": 1.6773080461960921e-06, "loss": 0.6177430152893066, "step": 22595, "token_acc": 0.8029152058174263 }, { "epoch": 1.4630859991421936, "grad_norm": 0.39055073261260986, "learning_rate": 1.6754087799766483e-06, "loss": 0.6083108425140381, "step": 22600, "token_acc": 0.8054016074805631 }, { "epoch": 1.4634096996868198, "grad_norm": 0.28417786955833435, "learning_rate": 1.6735103732252089e-06, "loss": 0.6037928104400635, "step": 22605, "token_acc": 0.8062539263323889 }, { "epoch": 1.463733400231446, "grad_norm": 0.28110697865486145, "learning_rate": 1.6716128264325477e-06, "loss": 0.6011906147003174, "step": 22610, "token_acc": 0.8076562003524076 }, { "epoch": 1.464057100776072, "grad_norm": 0.32530686259269714, "learning_rate": 1.669716140089213e-06, "loss": 0.6084872722625733, "step": 22615, "token_acc": 0.8048915523377848 }, { "epoch": 1.4643808013206983, "grad_norm": 0.42811545729637146, "learning_rate": 1.6678203146855372e-06, "loss": 0.5933531761169434, "step": 22620, "token_acc": 0.8098074236248145 }, { "epoch": 1.4647045018653244, "grad_norm": 0.2644801735877991, "learning_rate": 1.665925350711624e-06, "loss": 0.590269660949707, "step": 22625, "token_acc": 0.811696026342293 }, { "epoch": 1.4650282024099506, "grad_norm": 0.31866517663002014, "learning_rate": 1.6640312486573562e-06, "loss": 0.6184965133666992, "step": 22630, "token_acc": 0.8038209088991987 }, { "epoch": 1.4653519029545767, "grad_norm": 0.3095812499523163, "learning_rate": 1.6621380090123945e-06, "loss": 0.6200621604919434, "step": 22635, "token_acc": 0.8037714736213013 }, { "epoch": 1.465675603499203, "grad_norm": 0.3069746196269989, "learning_rate": 1.6602456322661741e-06, "loss": 0.5761318206787109, "step": 22640, "token_acc": 0.8149656401119878 }, { "epoch": 1.465999304043829, "grad_norm": 0.31603315472602844, "learning_rate": 1.6583541189079144e-06, "loss": 0.60689697265625, "step": 22645, "token_acc": 0.8072002877032547 }, { "epoch": 1.4663230045884552, "grad_norm": 0.28847795724868774, "learning_rate": 1.6564634694265995e-06, "loss": 0.5923643112182617, "step": 22650, "token_acc": 0.8109004642689633 }, { "epoch": 1.4666467051330814, "grad_norm": 0.2636339068412781, "learning_rate": 1.6545736843110028e-06, "loss": 0.5973324775695801, "step": 22655, "token_acc": 0.8087437734916568 }, { "epoch": 1.4669704056777075, "grad_norm": 0.3432855010032654, "learning_rate": 1.6526847640496663e-06, "loss": 0.6198443412780762, "step": 22660, "token_acc": 0.8022091638419558 }, { "epoch": 1.4672941062223337, "grad_norm": 0.3961753845214844, "learning_rate": 1.6507967091309102e-06, "loss": 0.5987567901611328, "step": 22665, "token_acc": 0.8097864358814044 }, { "epoch": 1.4676178067669599, "grad_norm": 0.30728068947792053, "learning_rate": 1.6489095200428307e-06, "loss": 0.6060595989227295, "step": 22670, "token_acc": 0.8074584209399827 }, { "epoch": 1.467941507311586, "grad_norm": 0.33169400691986084, "learning_rate": 1.6470231972733058e-06, "loss": 0.5975189685821534, "step": 22675, "token_acc": 0.8100810314029047 }, { "epoch": 1.4682652078562122, "grad_norm": 0.291488915681839, "learning_rate": 1.6451377413099774e-06, "loss": 0.5999453067779541, "step": 22680, "token_acc": 0.8077893161076063 }, { "epoch": 1.4685889084008383, "grad_norm": 0.2549120783805847, "learning_rate": 1.6432531526402757e-06, "loss": 0.6056122779846191, "step": 22685, "token_acc": 0.807070707070707 }, { "epoch": 1.4689126089454645, "grad_norm": 0.39531728625297546, "learning_rate": 1.6413694317513983e-06, "loss": 0.5963809967041016, "step": 22690, "token_acc": 0.8096703519369831 }, { "epoch": 1.4692363094900907, "grad_norm": 0.3010088801383972, "learning_rate": 1.639486579130327e-06, "loss": 0.5814424514770508, "step": 22695, "token_acc": 0.8137677034854521 }, { "epoch": 1.4695600100347168, "grad_norm": 0.35059094429016113, "learning_rate": 1.637604595263807e-06, "loss": 0.6006516456604004, "step": 22700, "token_acc": 0.8089230104710218 }, { "epoch": 1.469883710579343, "grad_norm": 0.36879459023475647, "learning_rate": 1.635723480638371e-06, "loss": 0.6158897399902343, "step": 22705, "token_acc": 0.804650632478416 }, { "epoch": 1.4702074111239694, "grad_norm": 0.29778626561164856, "learning_rate": 1.6338432357403195e-06, "loss": 0.5926938056945801, "step": 22710, "token_acc": 0.8114402451481103 }, { "epoch": 1.4705311116685955, "grad_norm": 0.36997532844543457, "learning_rate": 1.6319638610557304e-06, "loss": 0.6234292030334473, "step": 22715, "token_acc": 0.803535995362629 }, { "epoch": 1.4708548122132217, "grad_norm": 0.2669143080711365, "learning_rate": 1.6300853570704556e-06, "loss": 0.6187479019165039, "step": 22720, "token_acc": 0.8034517899996713 }, { "epoch": 1.4711785127578478, "grad_norm": 0.40949198603630066, "learning_rate": 1.6282077242701273e-06, "loss": 0.6002233028411865, "step": 22725, "token_acc": 0.8081605334276261 }, { "epoch": 1.471502213302474, "grad_norm": 0.2826702296733856, "learning_rate": 1.626330963140142e-06, "loss": 0.610401964187622, "step": 22730, "token_acc": 0.8067677343263407 }, { "epoch": 1.4718259138471002, "grad_norm": 0.32017892599105835, "learning_rate": 1.6244550741656817e-06, "loss": 0.6118975162506104, "step": 22735, "token_acc": 0.805798627893723 }, { "epoch": 1.4721496143917263, "grad_norm": 0.27043429017066956, "learning_rate": 1.6225800578316952e-06, "loss": 0.6271997451782226, "step": 22740, "token_acc": 0.8019758768449452 }, { "epoch": 1.4724733149363525, "grad_norm": 0.2746049463748932, "learning_rate": 1.6207059146229132e-06, "loss": 0.5967771530151367, "step": 22745, "token_acc": 0.808226349245918 }, { "epoch": 1.4727970154809786, "grad_norm": 0.36663389205932617, "learning_rate": 1.6188326450238296e-06, "loss": 0.5996570587158203, "step": 22750, "token_acc": 0.8093609360936094 }, { "epoch": 1.4731207160256048, "grad_norm": 0.3623381555080414, "learning_rate": 1.6169602495187247e-06, "loss": 0.584031057357788, "step": 22755, "token_acc": 0.8128955231670559 }, { "epoch": 1.473444416570231, "grad_norm": 0.3307233154773712, "learning_rate": 1.615088728591645e-06, "loss": 0.5875648975372314, "step": 22760, "token_acc": 0.8115745734457737 }, { "epoch": 1.4737681171148571, "grad_norm": 0.41072630882263184, "learning_rate": 1.6132180827264127e-06, "loss": 0.594256067276001, "step": 22765, "token_acc": 0.8113361470314586 }, { "epoch": 1.4740918176594833, "grad_norm": 0.24412649869918823, "learning_rate": 1.6113483124066237e-06, "loss": 0.6030219078063965, "step": 22770, "token_acc": 0.8063122037555612 }, { "epoch": 1.4744155182041094, "grad_norm": 0.255594402551651, "learning_rate": 1.6094794181156504e-06, "loss": 0.590544319152832, "step": 22775, "token_acc": 0.8110165298692072 }, { "epoch": 1.4747392187487356, "grad_norm": 0.33516910672187805, "learning_rate": 1.6076114003366345e-06, "loss": 0.5996019840240479, "step": 22780, "token_acc": 0.8090342165176362 }, { "epoch": 1.4750629192933618, "grad_norm": 0.28024327754974365, "learning_rate": 1.605744259552494e-06, "loss": 0.6041827201843262, "step": 22785, "token_acc": 0.8067869409797763 }, { "epoch": 1.475386619837988, "grad_norm": 0.3550144135951996, "learning_rate": 1.6038779962459168e-06, "loss": 0.6036459922790527, "step": 22790, "token_acc": 0.8081150739751803 }, { "epoch": 1.475710320382614, "grad_norm": 0.38126829266548157, "learning_rate": 1.6020126108993712e-06, "loss": 0.5860748767852784, "step": 22795, "token_acc": 0.8141133312729276 }, { "epoch": 1.4760340209272402, "grad_norm": 0.2076520174741745, "learning_rate": 1.6001481039950872e-06, "loss": 0.6071739196777344, "step": 22800, "token_acc": 0.8077660416563598 }, { "epoch": 1.4763577214718664, "grad_norm": 0.4846919775009155, "learning_rate": 1.5982844760150795e-06, "loss": 0.6154404163360596, "step": 22805, "token_acc": 0.8060564888010541 }, { "epoch": 1.4766814220164926, "grad_norm": 0.29928457736968994, "learning_rate": 1.5964217274411276e-06, "loss": 0.5950464248657227, "step": 22810, "token_acc": 0.8093021367579198 }, { "epoch": 1.4770051225611187, "grad_norm": 0.38623175024986267, "learning_rate": 1.5945598587547873e-06, "loss": 0.5904923915863037, "step": 22815, "token_acc": 0.8105253261884137 }, { "epoch": 1.4773288231057449, "grad_norm": 0.29586929082870483, "learning_rate": 1.5926988704373836e-06, "loss": 0.6083493709564209, "step": 22820, "token_acc": 0.8068981655387306 }, { "epoch": 1.477652523650371, "grad_norm": 0.30839377641677856, "learning_rate": 1.59083876297002e-06, "loss": 0.6062010288238525, "step": 22825, "token_acc": 0.8064280496712929 }, { "epoch": 1.4779762241949972, "grad_norm": 0.29767411947250366, "learning_rate": 1.5889795368335664e-06, "loss": 0.5786330699920654, "step": 22830, "token_acc": 0.8141693779965236 }, { "epoch": 1.4782999247396233, "grad_norm": 0.35284414887428284, "learning_rate": 1.5871211925086672e-06, "loss": 0.606883430480957, "step": 22835, "token_acc": 0.8061741789131078 }, { "epoch": 1.4786236252842495, "grad_norm": 0.35363614559173584, "learning_rate": 1.5852637304757384e-06, "loss": 0.6142573833465577, "step": 22840, "token_acc": 0.8053494256330459 }, { "epoch": 1.4789473258288757, "grad_norm": 0.28667861223220825, "learning_rate": 1.5834071512149684e-06, "loss": 0.6273666858673096, "step": 22845, "token_acc": 0.802096610566293 }, { "epoch": 1.4792710263735018, "grad_norm": 0.30638232827186584, "learning_rate": 1.581551455206316e-06, "loss": 0.6041758537292481, "step": 22850, "token_acc": 0.8083410906029326 }, { "epoch": 1.479594726918128, "grad_norm": 0.31923994421958923, "learning_rate": 1.5796966429295147e-06, "loss": 0.6052731513977051, "step": 22855, "token_acc": 0.8090049427499412 }, { "epoch": 1.4799184274627541, "grad_norm": 0.39835304021835327, "learning_rate": 1.5778427148640669e-06, "loss": 0.5977448463439942, "step": 22860, "token_acc": 0.8096013179571664 }, { "epoch": 1.4802421280073803, "grad_norm": 0.37261417508125305, "learning_rate": 1.5759896714892464e-06, "loss": 0.574111795425415, "step": 22865, "token_acc": 0.8143640322115259 }, { "epoch": 1.4805658285520065, "grad_norm": 0.40845435857772827, "learning_rate": 1.5741375132841003e-06, "loss": 0.6032320976257324, "step": 22870, "token_acc": 0.8081526949296974 }, { "epoch": 1.4808895290966326, "grad_norm": 0.34627407789230347, "learning_rate": 1.5722862407274425e-06, "loss": 0.5985132217407226, "step": 22875, "token_acc": 0.8090400098613572 }, { "epoch": 1.4812132296412588, "grad_norm": 0.37395167350769043, "learning_rate": 1.5704358542978654e-06, "loss": 0.5734530448913574, "step": 22880, "token_acc": 0.8150433568250463 }, { "epoch": 1.481536930185885, "grad_norm": 0.2690599262714386, "learning_rate": 1.5685863544737256e-06, "loss": 0.5723891258239746, "step": 22885, "token_acc": 0.8176874103590829 }, { "epoch": 1.481860630730511, "grad_norm": 0.266392320394516, "learning_rate": 1.5667377417331531e-06, "loss": 0.6201344966888428, "step": 22890, "token_acc": 0.8051937401763138 }, { "epoch": 1.4821843312751373, "grad_norm": 0.3527684509754181, "learning_rate": 1.564890016554048e-06, "loss": 0.6180258750915527, "step": 22895, "token_acc": 0.8043352919455043 }, { "epoch": 1.4825080318197634, "grad_norm": 0.3096027672290802, "learning_rate": 1.5630431794140815e-06, "loss": 0.6187921524047851, "step": 22900, "token_acc": 0.8041418756779856 }, { "epoch": 1.4828317323643896, "grad_norm": 0.3483850657939911, "learning_rate": 1.5611972307906937e-06, "loss": 0.5791762828826904, "step": 22905, "token_acc": 0.8124915990859806 }, { "epoch": 1.4831554329090157, "grad_norm": 0.3231044113636017, "learning_rate": 1.5593521711610992e-06, "loss": 0.6009858608245849, "step": 22910, "token_acc": 0.8081833129856107 }, { "epoch": 1.483479133453642, "grad_norm": 0.2502117156982422, "learning_rate": 1.5575080010022781e-06, "loss": 0.6076344966888427, "step": 22915, "token_acc": 0.8065069407367859 }, { "epoch": 1.483802833998268, "grad_norm": 0.2721686065196991, "learning_rate": 1.5556647207909826e-06, "loss": 0.5937073230743408, "step": 22920, "token_acc": 0.8103420597311326 }, { "epoch": 1.4841265345428944, "grad_norm": 0.2887909412384033, "learning_rate": 1.5538223310037332e-06, "loss": 0.6042622566223145, "step": 22925, "token_acc": 0.8067120667632908 }, { "epoch": 1.4844502350875206, "grad_norm": 0.23362457752227783, "learning_rate": 1.551980832116825e-06, "loss": 0.5803974151611329, "step": 22930, "token_acc": 0.8141533169846173 }, { "epoch": 1.4847739356321468, "grad_norm": 0.27420690655708313, "learning_rate": 1.5501402246063147e-06, "loss": 0.6119444370269775, "step": 22935, "token_acc": 0.8070197120435024 }, { "epoch": 1.485097636176773, "grad_norm": 0.38589346408843994, "learning_rate": 1.5483005089480374e-06, "loss": 0.5952499389648438, "step": 22940, "token_acc": 0.8078467019693013 }, { "epoch": 1.485421336721399, "grad_norm": 0.3654158115386963, "learning_rate": 1.5464616856175912e-06, "loss": 0.5790834426879883, "step": 22945, "token_acc": 0.8143123779829373 }, { "epoch": 1.4857450372660252, "grad_norm": 0.473335862159729, "learning_rate": 1.5446237550903465e-06, "loss": 0.599569034576416, "step": 22950, "token_acc": 0.809751056463185 }, { "epoch": 1.4860687378106514, "grad_norm": 0.3922523558139801, "learning_rate": 1.5427867178414403e-06, "loss": 0.6118449211120606, "step": 22955, "token_acc": 0.8043998488601537 }, { "epoch": 1.4863924383552776, "grad_norm": 0.2939489185810089, "learning_rate": 1.5409505743457836e-06, "loss": 0.5838317394256591, "step": 22960, "token_acc": 0.8139056555580948 }, { "epoch": 1.4867161388999037, "grad_norm": 0.32385706901550293, "learning_rate": 1.5391153250780522e-06, "loss": 0.6050832271575928, "step": 22965, "token_acc": 0.8075829858632909 }, { "epoch": 1.4870398394445299, "grad_norm": 0.4250566363334656, "learning_rate": 1.5372809705126911e-06, "loss": 0.6015281677246094, "step": 22970, "token_acc": 0.8070481799612086 }, { "epoch": 1.487363539989156, "grad_norm": 0.35540828108787537, "learning_rate": 1.5354475111239137e-06, "loss": 0.6018146514892578, "step": 22975, "token_acc": 0.8104397834912044 }, { "epoch": 1.4876872405337822, "grad_norm": 0.29153043031692505, "learning_rate": 1.5336149473857076e-06, "loss": 0.619541072845459, "step": 22980, "token_acc": 0.8034713034713035 }, { "epoch": 1.4880109410784084, "grad_norm": 0.38180962204933167, "learning_rate": 1.5317832797718174e-06, "loss": 0.5668795585632325, "step": 22985, "token_acc": 0.8178332038233863 }, { "epoch": 1.4883346416230345, "grad_norm": 0.30308231711387634, "learning_rate": 1.5299525087557682e-06, "loss": 0.5920558929443359, "step": 22990, "token_acc": 0.8124162602953079 }, { "epoch": 1.4886583421676607, "grad_norm": 0.36840468645095825, "learning_rate": 1.5281226348108464e-06, "loss": 0.5794614315032959, "step": 22995, "token_acc": 0.8133303766591694 }, { "epoch": 1.4889820427122868, "grad_norm": 0.44977933168411255, "learning_rate": 1.526293658410108e-06, "loss": 0.6100489616394043, "step": 23000, "token_acc": 0.8065973073026006 }, { "epoch": 1.489305743256913, "grad_norm": 0.31528279185295105, "learning_rate": 1.5244655800263752e-06, "loss": 0.5990635871887207, "step": 23005, "token_acc": 0.808659420768347 }, { "epoch": 1.4896294438015392, "grad_norm": 0.27781546115875244, "learning_rate": 1.5226384001322437e-06, "loss": 0.5988456726074218, "step": 23010, "token_acc": 0.8086155913978494 }, { "epoch": 1.4899531443461653, "grad_norm": 0.3503884971141815, "learning_rate": 1.5208121192000708e-06, "loss": 0.6149314880371094, "step": 23015, "token_acc": 0.8061887160531854 }, { "epoch": 1.4902768448907915, "grad_norm": 0.31879565119743347, "learning_rate": 1.5189867377019841e-06, "loss": 0.5925295352935791, "step": 23020, "token_acc": 0.8098508105779071 }, { "epoch": 1.4906005454354176, "grad_norm": 0.3602858781814575, "learning_rate": 1.5171622561098764e-06, "loss": 0.598461389541626, "step": 23025, "token_acc": 0.8075171904019479 }, { "epoch": 1.4909242459800438, "grad_norm": 0.3708169460296631, "learning_rate": 1.5153386748954153e-06, "loss": 0.5952506065368652, "step": 23030, "token_acc": 0.8094670026474434 }, { "epoch": 1.49124794652467, "grad_norm": 0.37511709332466125, "learning_rate": 1.5135159945300232e-06, "loss": 0.6144786834716797, "step": 23035, "token_acc": 0.8055821414609816 }, { "epoch": 1.4915716470692961, "grad_norm": 0.2821391820907593, "learning_rate": 1.5116942154849007e-06, "loss": 0.6051403045654297, "step": 23040, "token_acc": 0.8078391577345088 }, { "epoch": 1.4918953476139223, "grad_norm": 0.26773694157600403, "learning_rate": 1.5098733382310094e-06, "loss": 0.5879620552062989, "step": 23045, "token_acc": 0.811803127267929 }, { "epoch": 1.4922190481585484, "grad_norm": 0.3497713506221771, "learning_rate": 1.5080533632390832e-06, "loss": 0.6225480079650879, "step": 23050, "token_acc": 0.8033377743496248 }, { "epoch": 1.4925427487031748, "grad_norm": 0.41595780849456787, "learning_rate": 1.506234290979613e-06, "loss": 0.6024541854858398, "step": 23055, "token_acc": 0.8085794717142015 }, { "epoch": 1.492866449247801, "grad_norm": 0.38846102356910706, "learning_rate": 1.5044161219228675e-06, "loss": 0.5810710906982421, "step": 23060, "token_acc": 0.8136071484558708 }, { "epoch": 1.4931901497924271, "grad_norm": 0.3482680916786194, "learning_rate": 1.5025988565388755e-06, "loss": 0.5807567596435547, "step": 23065, "token_acc": 0.8120840060496608 }, { "epoch": 1.4935138503370533, "grad_norm": 0.3568812310695648, "learning_rate": 1.500782495297433e-06, "loss": 0.5980871200561524, "step": 23070, "token_acc": 0.8096916066129716 }, { "epoch": 1.4938375508816795, "grad_norm": 0.2777484059333801, "learning_rate": 1.4989670386681026e-06, "loss": 0.6076942443847656, "step": 23075, "token_acc": 0.805985942105661 }, { "epoch": 1.4941612514263056, "grad_norm": 0.2539638876914978, "learning_rate": 1.4971524871202143e-06, "loss": 0.5887938976287842, "step": 23080, "token_acc": 0.8103987571206629 }, { "epoch": 1.4944849519709318, "grad_norm": 0.443433940410614, "learning_rate": 1.4953388411228603e-06, "loss": 0.6075390815734864, "step": 23085, "token_acc": 0.8077001913091009 }, { "epoch": 1.494808652515558, "grad_norm": 0.28568562865257263, "learning_rate": 1.4935261011449054e-06, "loss": 0.6157797813415528, "step": 23090, "token_acc": 0.8048099734846723 }, { "epoch": 1.495132353060184, "grad_norm": 0.3150516748428345, "learning_rate": 1.4917142676549746e-06, "loss": 0.6016316413879395, "step": 23095, "token_acc": 0.8072899216769601 }, { "epoch": 1.4954560536048103, "grad_norm": 0.376413494348526, "learning_rate": 1.489903341121459e-06, "loss": 0.570214033126831, "step": 23100, "token_acc": 0.8157757723012843 }, { "epoch": 1.4957797541494364, "grad_norm": 0.2722102403640747, "learning_rate": 1.4880933220125188e-06, "loss": 0.5930957794189453, "step": 23105, "token_acc": 0.8112360555034067 }, { "epoch": 1.4961034546940626, "grad_norm": 0.3610982298851013, "learning_rate": 1.4862842107960735e-06, "loss": 0.5786555290222168, "step": 23110, "token_acc": 0.8133536354249715 }, { "epoch": 1.4964271552386887, "grad_norm": 0.2556774616241455, "learning_rate": 1.4844760079398157e-06, "loss": 0.5950203895568847, "step": 23115, "token_acc": 0.8090105881516925 }, { "epoch": 1.496750855783315, "grad_norm": 0.4092099368572235, "learning_rate": 1.4826687139111973e-06, "loss": 0.5884793758392334, "step": 23120, "token_acc": 0.8121561770851736 }, { "epoch": 1.497074556327941, "grad_norm": 0.36781951785087585, "learning_rate": 1.480862329177437e-06, "loss": 0.6135913372039795, "step": 23125, "token_acc": 0.804943699883031 }, { "epoch": 1.4973982568725672, "grad_norm": 0.3035937547683716, "learning_rate": 1.4790568542055196e-06, "loss": 0.5857363700866699, "step": 23130, "token_acc": 0.8126970344643334 }, { "epoch": 1.4977219574171934, "grad_norm": 0.35594844818115234, "learning_rate": 1.4772522894621916e-06, "loss": 0.6031308650970459, "step": 23135, "token_acc": 0.8074220766913067 }, { "epoch": 1.4980456579618195, "grad_norm": 0.2623201310634613, "learning_rate": 1.4754486354139664e-06, "loss": 0.6061822414398194, "step": 23140, "token_acc": 0.8067710396297609 }, { "epoch": 1.4983693585064457, "grad_norm": 0.3949176073074341, "learning_rate": 1.4736458925271236e-06, "loss": 0.5918424606323243, "step": 23145, "token_acc": 0.8103971845148316 }, { "epoch": 1.4986930590510719, "grad_norm": 0.3066674470901489, "learning_rate": 1.4718440612677049e-06, "loss": 0.6206615924835205, "step": 23150, "token_acc": 0.8027122511822281 }, { "epoch": 1.499016759595698, "grad_norm": 0.4563153088092804, "learning_rate": 1.470043142101516e-06, "loss": 0.5948781490325927, "step": 23155, "token_acc": 0.810276521133924 }, { "epoch": 1.4993404601403242, "grad_norm": 0.34085357189178467, "learning_rate": 1.4682431354941267e-06, "loss": 0.575091552734375, "step": 23160, "token_acc": 0.8147876819915786 }, { "epoch": 1.4996641606849503, "grad_norm": 0.3710900843143463, "learning_rate": 1.4664440419108766e-06, "loss": 0.559198522567749, "step": 23165, "token_acc": 0.8191691234889722 }, { "epoch": 1.4999878612295765, "grad_norm": 0.36047816276550293, "learning_rate": 1.4646458618168573e-06, "loss": 0.5854372978210449, "step": 23170, "token_acc": 0.8129863862132759 }, { "epoch": 1.5003115617742027, "grad_norm": 0.3626617193222046, "learning_rate": 1.4628485956769373e-06, "loss": 0.5899957180023193, "step": 23175, "token_acc": 0.8103337336993823 }, { "epoch": 1.5006352623188288, "grad_norm": 0.3254316449165344, "learning_rate": 1.461052243955739e-06, "loss": 0.5942634582519531, "step": 23180, "token_acc": 0.8107162440922265 }, { "epoch": 1.500958962863455, "grad_norm": 0.3873162269592285, "learning_rate": 1.4592568071176572e-06, "loss": 0.6166719913482666, "step": 23185, "token_acc": 0.8040455460611815 }, { "epoch": 1.5012826634080811, "grad_norm": 0.32899582386016846, "learning_rate": 1.4574622856268394e-06, "loss": 0.6024688720703125, "step": 23190, "token_acc": 0.8061501602453541 }, { "epoch": 1.5016063639527073, "grad_norm": 0.32091230154037476, "learning_rate": 1.455668679947207e-06, "loss": 0.6230904579162597, "step": 23195, "token_acc": 0.8032001179766997 }, { "epoch": 1.5019300644973335, "grad_norm": 0.26720941066741943, "learning_rate": 1.4538759905424383e-06, "loss": 0.6022717475891113, "step": 23200, "token_acc": 0.8070962846744428 }, { "epoch": 1.5022537650419596, "grad_norm": 0.32461321353912354, "learning_rate": 1.4520842178759763e-06, "loss": 0.6184596538543701, "step": 23205, "token_acc": 0.8035538068771447 }, { "epoch": 1.5025774655865858, "grad_norm": 0.34629708528518677, "learning_rate": 1.4502933624110271e-06, "loss": 0.5924974918365479, "step": 23210, "token_acc": 0.8101601669950643 }, { "epoch": 1.502901166131212, "grad_norm": 0.33559688925743103, "learning_rate": 1.4485034246105629e-06, "loss": 0.5756032943725586, "step": 23215, "token_acc": 0.8131593766325402 }, { "epoch": 1.503224866675838, "grad_norm": 0.3514809012413025, "learning_rate": 1.4467144049373095e-06, "loss": 0.6000430107116699, "step": 23220, "token_acc": 0.8079482816390621 }, { "epoch": 1.5035485672204643, "grad_norm": 0.3684837222099304, "learning_rate": 1.4449263038537664e-06, "loss": 0.5886465549468994, "step": 23225, "token_acc": 0.8102479040586308 }, { "epoch": 1.5038722677650904, "grad_norm": 0.2617456912994385, "learning_rate": 1.4431391218221875e-06, "loss": 0.5919118881225586, "step": 23230, "token_acc": 0.810814533234168 }, { "epoch": 1.5041959683097166, "grad_norm": 0.2990429699420929, "learning_rate": 1.4413528593045971e-06, "loss": 0.5874880313873291, "step": 23235, "token_acc": 0.811846544757779 }, { "epoch": 1.5045196688543427, "grad_norm": 0.38767191767692566, "learning_rate": 1.439567516762771e-06, "loss": 0.599497127532959, "step": 23240, "token_acc": 0.8078367144217068 }, { "epoch": 1.504843369398969, "grad_norm": 0.31342029571533203, "learning_rate": 1.4377830946582565e-06, "loss": 0.5892878532409668, "step": 23245, "token_acc": 0.8105013445117636 }, { "epoch": 1.505167069943595, "grad_norm": 0.23724746704101562, "learning_rate": 1.435999593452359e-06, "loss": 0.6172861099243164, "step": 23250, "token_acc": 0.8045556207258828 }, { "epoch": 1.5054907704882212, "grad_norm": 0.4015567898750305, "learning_rate": 1.4342170136061463e-06, "loss": 0.5942465782165527, "step": 23255, "token_acc": 0.8104105725031342 }, { "epoch": 1.5058144710328474, "grad_norm": 0.3236212134361267, "learning_rate": 1.4324353555804466e-06, "loss": 0.6015493869781494, "step": 23260, "token_acc": 0.807410034825229 }, { "epoch": 1.5061381715774735, "grad_norm": 0.31706351041793823, "learning_rate": 1.4306546198358533e-06, "loss": 0.6185480117797851, "step": 23265, "token_acc": 0.8028372121906286 }, { "epoch": 1.5064618721220997, "grad_norm": 0.3138197362422943, "learning_rate": 1.4288748068327197e-06, "loss": 0.5892140388488769, "step": 23270, "token_acc": 0.8105642209657742 }, { "epoch": 1.5067855726667259, "grad_norm": 0.37479159235954285, "learning_rate": 1.4270959170311587e-06, "loss": 0.6214252948760987, "step": 23275, "token_acc": 0.8043241026726368 }, { "epoch": 1.507109273211352, "grad_norm": 0.2896706163883209, "learning_rate": 1.4253179508910452e-06, "loss": 0.6167472839355469, "step": 23280, "token_acc": 0.8040147879923528 }, { "epoch": 1.5074329737559782, "grad_norm": 0.3332063853740692, "learning_rate": 1.4235409088720204e-06, "loss": 0.5916187286376953, "step": 23285, "token_acc": 0.8088890327592905 }, { "epoch": 1.5077566743006046, "grad_norm": 0.33096054196357727, "learning_rate": 1.4217647914334765e-06, "loss": 0.598295021057129, "step": 23290, "token_acc": 0.8091670279644483 }, { "epoch": 1.5080803748452307, "grad_norm": 0.31703582406044006, "learning_rate": 1.419989599034577e-06, "loss": 0.593410873413086, "step": 23295, "token_acc": 0.8092768287282438 }, { "epoch": 1.5084040753898569, "grad_norm": 0.3815608024597168, "learning_rate": 1.41821533213424e-06, "loss": 0.5962639331817627, "step": 23300, "token_acc": 0.8091804590875055 }, { "epoch": 1.508727775934483, "grad_norm": 0.3484819531440735, "learning_rate": 1.416441991191147e-06, "loss": 0.600352668762207, "step": 23305, "token_acc": 0.8082858189046398 }, { "epoch": 1.5090514764791092, "grad_norm": 0.30246880650520325, "learning_rate": 1.4146695766637369e-06, "loss": 0.5841845512390137, "step": 23310, "token_acc": 0.8139991089299845 }, { "epoch": 1.5093751770237354, "grad_norm": 0.2894844710826874, "learning_rate": 1.4128980890102146e-06, "loss": 0.590594482421875, "step": 23315, "token_acc": 0.8106780279041204 }, { "epoch": 1.5096988775683615, "grad_norm": 0.26525944471359253, "learning_rate": 1.4111275286885413e-06, "loss": 0.5937294006347656, "step": 23320, "token_acc": 0.8098862383347228 }, { "epoch": 1.5100225781129877, "grad_norm": 0.3646310567855835, "learning_rate": 1.409357896156439e-06, "loss": 0.6071089744567871, "step": 23325, "token_acc": 0.8056801503367488 }, { "epoch": 1.5103462786576138, "grad_norm": 0.28711801767349243, "learning_rate": 1.4075891918713902e-06, "loss": 0.6011370182037353, "step": 23330, "token_acc": 0.807468426796944 }, { "epoch": 1.51066997920224, "grad_norm": 0.29192614555358887, "learning_rate": 1.4058214162906375e-06, "loss": 0.6040204048156739, "step": 23335, "token_acc": 0.8074645823155838 }, { "epoch": 1.5109936797468662, "grad_norm": 0.3419972062110901, "learning_rate": 1.4040545698711828e-06, "loss": 0.6007554054260253, "step": 23340, "token_acc": 0.8089111765139682 }, { "epoch": 1.5113173802914923, "grad_norm": 0.2867151200771332, "learning_rate": 1.40228865306979e-06, "loss": 0.5831372261047363, "step": 23345, "token_acc": 0.8127065783550897 }, { "epoch": 1.5116410808361185, "grad_norm": 0.3389207720756531, "learning_rate": 1.40052366634298e-06, "loss": 0.5925567626953125, "step": 23350, "token_acc": 0.810923332039657 }, { "epoch": 1.5119647813807446, "grad_norm": 0.3316132426261902, "learning_rate": 1.3987596101470353e-06, "loss": 0.6300113201141357, "step": 23355, "token_acc": 0.7995749376199014 }, { "epoch": 1.5122884819253708, "grad_norm": 0.4198872148990631, "learning_rate": 1.3969964849379957e-06, "loss": 0.6094406127929688, "step": 23360, "token_acc": 0.8068512313347864 }, { "epoch": 1.512612182469997, "grad_norm": 0.3674508333206177, "learning_rate": 1.3952342911716605e-06, "loss": 0.5843388557434082, "step": 23365, "token_acc": 0.8131149591416977 }, { "epoch": 1.5129358830146231, "grad_norm": 0.3267726004123688, "learning_rate": 1.3934730293035935e-06, "loss": 0.6191632747650146, "step": 23370, "token_acc": 0.8040183362259702 }, { "epoch": 1.5132595835592495, "grad_norm": 0.3068889081478119, "learning_rate": 1.391712699789108e-06, "loss": 0.623860502243042, "step": 23375, "token_acc": 0.8024588469390392 }, { "epoch": 1.5135832841038757, "grad_norm": 0.28515517711639404, "learning_rate": 1.389953303083285e-06, "loss": 0.6067644596099854, "step": 23380, "token_acc": 0.8066406499088138 }, { "epoch": 1.5139069846485018, "grad_norm": 0.34080106019973755, "learning_rate": 1.3881948396409605e-06, "loss": 0.6067288398742676, "step": 23385, "token_acc": 0.8050430942374813 }, { "epoch": 1.514230685193128, "grad_norm": 0.44125667214393616, "learning_rate": 1.3864373099167295e-06, "loss": 0.5843630313873291, "step": 23390, "token_acc": 0.8137929356520258 }, { "epoch": 1.5145543857377541, "grad_norm": 0.3586481511592865, "learning_rate": 1.3846807143649433e-06, "loss": 0.6014153003692627, "step": 23395, "token_acc": 0.8086673846540116 }, { "epoch": 1.5148780862823803, "grad_norm": 0.26282262802124023, "learning_rate": 1.3829250534397175e-06, "loss": 0.6061799049377441, "step": 23400, "token_acc": 0.8075765466584602 }, { "epoch": 1.5152017868270065, "grad_norm": 0.29717305302619934, "learning_rate": 1.3811703275949223e-06, "loss": 0.6081892490386963, "step": 23405, "token_acc": 0.806203493668719 }, { "epoch": 1.5155254873716326, "grad_norm": 0.37624138593673706, "learning_rate": 1.3794165372841855e-06, "loss": 0.5928567886352539, "step": 23410, "token_acc": 0.8110375700318576 }, { "epoch": 1.5158491879162588, "grad_norm": 0.37507426738739014, "learning_rate": 1.377663682960893e-06, "loss": 0.5968840599060059, "step": 23415, "token_acc": 0.8093796159527327 }, { "epoch": 1.516172888460885, "grad_norm": 0.4318726360797882, "learning_rate": 1.3759117650781945e-06, "loss": 0.6220679759979248, "step": 23420, "token_acc": 0.8032819858372462 }, { "epoch": 1.516496589005511, "grad_norm": 0.3015983998775482, "learning_rate": 1.3741607840889871e-06, "loss": 0.6279092788696289, "step": 23425, "token_acc": 0.8014322193849228 }, { "epoch": 1.5168202895501373, "grad_norm": 0.4171047508716583, "learning_rate": 1.3724107404459357e-06, "loss": 0.5602330684661865, "step": 23430, "token_acc": 0.8179660645302755 }, { "epoch": 1.5171439900947634, "grad_norm": 0.3898422122001648, "learning_rate": 1.3706616346014578e-06, "loss": 0.5943058967590332, "step": 23435, "token_acc": 0.8102090177716843 }, { "epoch": 1.5174676906393896, "grad_norm": 0.43818244338035583, "learning_rate": 1.3689134670077287e-06, "loss": 0.6046676635742188, "step": 23440, "token_acc": 0.8068700287317707 }, { "epoch": 1.5177913911840157, "grad_norm": 0.36512237787246704, "learning_rate": 1.367166238116681e-06, "loss": 0.5865427494049072, "step": 23445, "token_acc": 0.8111298148331518 }, { "epoch": 1.518115091728642, "grad_norm": 0.39671561121940613, "learning_rate": 1.3654199483800084e-06, "loss": 0.621088695526123, "step": 23450, "token_acc": 0.8024879614767255 }, { "epoch": 1.518438792273268, "grad_norm": 0.3226565420627594, "learning_rate": 1.3636745982491578e-06, "loss": 0.6062163352966309, "step": 23455, "token_acc": 0.8067023931383766 }, { "epoch": 1.5187624928178942, "grad_norm": 0.345488041639328, "learning_rate": 1.3619301881753338e-06, "loss": 0.5949037551879883, "step": 23460, "token_acc": 0.8100421456647969 }, { "epoch": 1.5190861933625204, "grad_norm": 0.39454296231269836, "learning_rate": 1.360186718609497e-06, "loss": 0.5979668617248535, "step": 23465, "token_acc": 0.8081030649515643 }, { "epoch": 1.5194098939071465, "grad_norm": 0.4003968834877014, "learning_rate": 1.3584441900023708e-06, "loss": 0.591142225265503, "step": 23470, "token_acc": 0.8102779845767021 }, { "epoch": 1.5197335944517727, "grad_norm": 0.3238218426704407, "learning_rate": 1.3567026028044255e-06, "loss": 0.5756365776062011, "step": 23475, "token_acc": 0.8133176438014813 }, { "epoch": 1.5200572949963989, "grad_norm": 0.2522776126861572, "learning_rate": 1.3549619574658972e-06, "loss": 0.5965761184692383, "step": 23480, "token_acc": 0.8085714106748013 }, { "epoch": 1.520380995541025, "grad_norm": 0.4371185600757599, "learning_rate": 1.353222254436774e-06, "loss": 0.5950991630554199, "step": 23485, "token_acc": 0.8085483219815854 }, { "epoch": 1.5207046960856512, "grad_norm": 0.3990171253681183, "learning_rate": 1.3514834941668004e-06, "loss": 0.5753474712371827, "step": 23490, "token_acc": 0.8142208067135553 }, { "epoch": 1.5210283966302773, "grad_norm": 0.29830437898635864, "learning_rate": 1.3497456771054767e-06, "loss": 0.5714759349822998, "step": 23495, "token_acc": 0.8159609685680378 }, { "epoch": 1.5213520971749035, "grad_norm": 0.3312675654888153, "learning_rate": 1.3480088037020638e-06, "loss": 0.5818878650665283, "step": 23500, "token_acc": 0.8131081046389238 }, { "epoch": 1.5216757977195297, "grad_norm": 0.3881378471851349, "learning_rate": 1.3462728744055742e-06, "loss": 0.5975228309631347, "step": 23505, "token_acc": 0.80741982272361 }, { "epoch": 1.5219994982641558, "grad_norm": 0.3306126296520233, "learning_rate": 1.3445378896647766e-06, "loss": 0.5983952522277832, "step": 23510, "token_acc": 0.8086790567801929 }, { "epoch": 1.522323198808782, "grad_norm": 0.32697659730911255, "learning_rate": 1.3428038499281958e-06, "loss": 0.5992615222930908, "step": 23515, "token_acc": 0.809643779698313 }, { "epoch": 1.5226468993534081, "grad_norm": 0.31820380687713623, "learning_rate": 1.3410707556441172e-06, "loss": 0.5910326957702636, "step": 23520, "token_acc": 0.8109297682662467 }, { "epoch": 1.5229705998980343, "grad_norm": 0.27459588646888733, "learning_rate": 1.3393386072605713e-06, "loss": 0.5950813293457031, "step": 23525, "token_acc": 0.8083394662188088 }, { "epoch": 1.5232943004426605, "grad_norm": 0.33188506960868835, "learning_rate": 1.3376074052253552e-06, "loss": 0.6147159576416016, "step": 23530, "token_acc": 0.803227581147992 }, { "epoch": 1.5236180009872866, "grad_norm": 0.3436678946018219, "learning_rate": 1.3358771499860152e-06, "loss": 0.6018144607543945, "step": 23535, "token_acc": 0.8086737582511273 }, { "epoch": 1.5239417015319128, "grad_norm": 0.3264910578727722, "learning_rate": 1.3341478419898536e-06, "loss": 0.5927250862121582, "step": 23540, "token_acc": 0.8112737127371273 }, { "epoch": 1.524265402076539, "grad_norm": 0.4000045359134674, "learning_rate": 1.3324194816839264e-06, "loss": 0.6186488151550293, "step": 23545, "token_acc": 0.8039648641002464 }, { "epoch": 1.524589102621165, "grad_norm": 0.404902845621109, "learning_rate": 1.330692069515051e-06, "loss": 0.6017335414886474, "step": 23550, "token_acc": 0.808157995970555 }, { "epoch": 1.5249128031657913, "grad_norm": 0.32978835701942444, "learning_rate": 1.328965605929793e-06, "loss": 0.5870532512664794, "step": 23555, "token_acc": 0.8128578662407977 }, { "epoch": 1.5252365037104174, "grad_norm": 0.28328749537467957, "learning_rate": 1.3272400913744744e-06, "loss": 0.6010096549987793, "step": 23560, "token_acc": 0.8070869053622458 }, { "epoch": 1.5255602042550436, "grad_norm": 0.37314891815185547, "learning_rate": 1.325515526295173e-06, "loss": 0.6204755783081055, "step": 23565, "token_acc": 0.8046279408484339 }, { "epoch": 1.5258839047996697, "grad_norm": 0.31838420033454895, "learning_rate": 1.3237919111377207e-06, "loss": 0.6043296813964844, "step": 23570, "token_acc": 0.8069332229330677 }, { "epoch": 1.526207605344296, "grad_norm": 0.3950125575065613, "learning_rate": 1.3220692463477024e-06, "loss": 0.5735435485839844, "step": 23575, "token_acc": 0.8144997164114369 }, { "epoch": 1.526531305888922, "grad_norm": 0.3206150531768799, "learning_rate": 1.3203475323704612e-06, "loss": 0.617720651626587, "step": 23580, "token_acc": 0.8047303517939808 }, { "epoch": 1.5268550064335482, "grad_norm": 0.2615509629249573, "learning_rate": 1.31862676965109e-06, "loss": 0.5887337684631347, "step": 23585, "token_acc": 0.8105717298903838 }, { "epoch": 1.5271787069781744, "grad_norm": 0.3883870542049408, "learning_rate": 1.316906958634439e-06, "loss": 0.5899475574493408, "step": 23590, "token_acc": 0.8115823917252873 }, { "epoch": 1.5275024075228005, "grad_norm": 0.3248406648635864, "learning_rate": 1.3151880997651095e-06, "loss": 0.6049712181091309, "step": 23595, "token_acc": 0.8073465304963138 }, { "epoch": 1.5278261080674267, "grad_norm": 0.32007676362991333, "learning_rate": 1.3134701934874577e-06, "loss": 0.6093414306640625, "step": 23600, "token_acc": 0.8061272839385973 }, { "epoch": 1.5281498086120529, "grad_norm": 0.28118976950645447, "learning_rate": 1.3117532402455962e-06, "loss": 0.6003198623657227, "step": 23605, "token_acc": 0.8096801970482809 }, { "epoch": 1.528473509156679, "grad_norm": 0.27956125140190125, "learning_rate": 1.3100372404833877e-06, "loss": 0.5952267169952392, "step": 23610, "token_acc": 0.8091484639055643 }, { "epoch": 1.5287972097013052, "grad_norm": 0.4073447287082672, "learning_rate": 1.3083221946444503e-06, "loss": 0.6016127109527588, "step": 23615, "token_acc": 0.8079610486110206 }, { "epoch": 1.5291209102459313, "grad_norm": 0.31805041432380676, "learning_rate": 1.3066081031721545e-06, "loss": 0.5978311538696289, "step": 23620, "token_acc": 0.8095710616137092 }, { "epoch": 1.5294446107905575, "grad_norm": 0.3262706398963928, "learning_rate": 1.3048949665096245e-06, "loss": 0.5900527000427246, "step": 23625, "token_acc": 0.8113843530723326 }, { "epoch": 1.5297683113351839, "grad_norm": 0.3103025257587433, "learning_rate": 1.3031827850997358e-06, "loss": 0.5900993347167969, "step": 23630, "token_acc": 0.8104393083286356 }, { "epoch": 1.53009201187981, "grad_norm": 0.38264238834381104, "learning_rate": 1.3014715593851224e-06, "loss": 0.6047293186187744, "step": 23635, "token_acc": 0.8068761916477029 }, { "epoch": 1.5304157124244362, "grad_norm": 0.30755719542503357, "learning_rate": 1.2997612898081653e-06, "loss": 0.6006240844726562, "step": 23640, "token_acc": 0.8076496534341525 }, { "epoch": 1.5307394129690624, "grad_norm": 0.35721880197525024, "learning_rate": 1.2980519768110016e-06, "loss": 0.585969877243042, "step": 23645, "token_acc": 0.8126827777858608 }, { "epoch": 1.5310631135136885, "grad_norm": 0.3283511698246002, "learning_rate": 1.2963436208355184e-06, "loss": 0.6049962043762207, "step": 23650, "token_acc": 0.8075178766990917 }, { "epoch": 1.5313868140583147, "grad_norm": 0.33931684494018555, "learning_rate": 1.2946362223233616e-06, "loss": 0.5894518852233886, "step": 23655, "token_acc": 0.810233831814442 }, { "epoch": 1.5317105146029408, "grad_norm": 0.34568750858306885, "learning_rate": 1.2929297817159187e-06, "loss": 0.5793607711791993, "step": 23660, "token_acc": 0.8138780443752865 }, { "epoch": 1.532034215147567, "grad_norm": 0.3248903155326843, "learning_rate": 1.291224299454341e-06, "loss": 0.6050247192382813, "step": 23665, "token_acc": 0.8066815711264023 }, { "epoch": 1.5323579156921932, "grad_norm": 0.2851080596446991, "learning_rate": 1.2895197759795237e-06, "loss": 0.6076528549194335, "step": 23670, "token_acc": 0.8069274234974683 }, { "epoch": 1.5326816162368193, "grad_norm": 0.43354904651641846, "learning_rate": 1.2878162117321224e-06, "loss": 0.6119383811950684, "step": 23675, "token_acc": 0.805134103367267 }, { "epoch": 1.5330053167814455, "grad_norm": 0.2980201244354248, "learning_rate": 1.2861136071525337e-06, "loss": 0.5940888404846192, "step": 23680, "token_acc": 0.8100165325128781 }, { "epoch": 1.5333290173260716, "grad_norm": 0.3472643196582794, "learning_rate": 1.2844119626809166e-06, "loss": 0.5878699779510498, "step": 23685, "token_acc": 0.8102239457599261 }, { "epoch": 1.5336527178706978, "grad_norm": 0.35182324051856995, "learning_rate": 1.2827112787571755e-06, "loss": 0.5912360668182373, "step": 23690, "token_acc": 0.8098252373744323 }, { "epoch": 1.533976418415324, "grad_norm": 0.32178375124931335, "learning_rate": 1.2810115558209695e-06, "loss": 0.5985129833221435, "step": 23695, "token_acc": 0.8091910394143762 }, { "epoch": 1.53430011895995, "grad_norm": 0.32788705825805664, "learning_rate": 1.2793127943117062e-06, "loss": 0.6009908199310303, "step": 23700, "token_acc": 0.8074869238984582 }, { "epoch": 1.5346238195045763, "grad_norm": 0.4740966856479645, "learning_rate": 1.2776149946685513e-06, "loss": 0.5841952800750733, "step": 23705, "token_acc": 0.8143307851735229 }, { "epoch": 1.5349475200492024, "grad_norm": 0.42699870467185974, "learning_rate": 1.2759181573304109e-06, "loss": 0.6085145950317383, "step": 23710, "token_acc": 0.8078040680780407 }, { "epoch": 1.5352712205938288, "grad_norm": 0.34891459345817566, "learning_rate": 1.2742222827359534e-06, "loss": 0.6085374832153321, "step": 23715, "token_acc": 0.8049458618056508 }, { "epoch": 1.535594921138455, "grad_norm": 0.3789644241333008, "learning_rate": 1.2725273713235913e-06, "loss": 0.598017692565918, "step": 23720, "token_acc": 0.8092961109076358 }, { "epoch": 1.5359186216830811, "grad_norm": 0.3918962776660919, "learning_rate": 1.2708334235314939e-06, "loss": 0.5835404396057129, "step": 23725, "token_acc": 0.8132798730435149 }, { "epoch": 1.5362423222277073, "grad_norm": 0.3677109479904175, "learning_rate": 1.269140439797572e-06, "loss": 0.5917834281921387, "step": 23730, "token_acc": 0.8105611734344551 }, { "epoch": 1.5365660227723335, "grad_norm": 0.4436217248439789, "learning_rate": 1.2674484205594983e-06, "loss": 0.6059063911437989, "step": 23735, "token_acc": 0.8061980152193741 }, { "epoch": 1.5368897233169596, "grad_norm": 0.25977399945259094, "learning_rate": 1.2657573662546886e-06, "loss": 0.5786881446838379, "step": 23740, "token_acc": 0.813609541745135 }, { "epoch": 1.5372134238615858, "grad_norm": 0.36608028411865234, "learning_rate": 1.2640672773203117e-06, "loss": 0.5766257286071778, "step": 23745, "token_acc": 0.8134892147813899 }, { "epoch": 1.537537124406212, "grad_norm": 0.38083985447883606, "learning_rate": 1.262378154193285e-06, "loss": 0.6100115299224853, "step": 23750, "token_acc": 0.8067226890756303 }, { "epoch": 1.537860824950838, "grad_norm": 0.3589264452457428, "learning_rate": 1.260689997310283e-06, "loss": 0.5999322891235351, "step": 23755, "token_acc": 0.8096662549534249 }, { "epoch": 1.5381845254954642, "grad_norm": 0.46151086688041687, "learning_rate": 1.2590028071077198e-06, "loss": 0.606703519821167, "step": 23760, "token_acc": 0.8059426732484251 }, { "epoch": 1.5385082260400904, "grad_norm": 0.32542508840560913, "learning_rate": 1.2573165840217684e-06, "loss": 0.5942884922027588, "step": 23765, "token_acc": 0.8099078631831377 }, { "epoch": 1.5388319265847166, "grad_norm": 0.3914918005466461, "learning_rate": 1.2556313284883454e-06, "loss": 0.5825592994689941, "step": 23770, "token_acc": 0.8130290931335469 }, { "epoch": 1.5391556271293427, "grad_norm": 0.32745561003685, "learning_rate": 1.253947040943126e-06, "loss": 0.5853156089782715, "step": 23775, "token_acc": 0.8121174041827484 }, { "epoch": 1.539479327673969, "grad_norm": 0.39517343044281006, "learning_rate": 1.2522637218215227e-06, "loss": 0.6103170871734619, "step": 23780, "token_acc": 0.804351083088832 }, { "epoch": 1.539803028218595, "grad_norm": 0.3118666410446167, "learning_rate": 1.2505813715587095e-06, "loss": 0.6043131351470947, "step": 23785, "token_acc": 0.8073083443209644 }, { "epoch": 1.5401267287632212, "grad_norm": 0.3216411769390106, "learning_rate": 1.2488999905896027e-06, "loss": 0.5974723339080811, "step": 23790, "token_acc": 0.808581280437951 }, { "epoch": 1.5404504293078474, "grad_norm": 0.4166313707828522, "learning_rate": 1.2472195793488711e-06, "loss": 0.5947760581970215, "step": 23795, "token_acc": 0.8101298553868858 }, { "epoch": 1.5407741298524735, "grad_norm": 0.4019356071949005, "learning_rate": 1.2455401382709297e-06, "loss": 0.6080838203430176, "step": 23800, "token_acc": 0.8072295263741486 }, { "epoch": 1.5410978303970997, "grad_norm": 0.3222793936729431, "learning_rate": 1.2438616677899478e-06, "loss": 0.5930906295776367, "step": 23805, "token_acc": 0.8109979496487513 }, { "epoch": 1.5414215309417258, "grad_norm": 0.3772710859775543, "learning_rate": 1.2421841683398405e-06, "loss": 0.6083483219146728, "step": 23810, "token_acc": 0.8063999356520923 }, { "epoch": 1.541745231486352, "grad_norm": 0.32354333996772766, "learning_rate": 1.2405076403542709e-06, "loss": 0.6048157691955567, "step": 23815, "token_acc": 0.8075200499947922 }, { "epoch": 1.5420689320309782, "grad_norm": 0.4792010188102722, "learning_rate": 1.2388320842666534e-06, "loss": 0.5673504829406738, "step": 23820, "token_acc": 0.8183978028523212 }, { "epoch": 1.5423926325756043, "grad_norm": 0.34212401509284973, "learning_rate": 1.23715750051015e-06, "loss": 0.5763498306274414, "step": 23825, "token_acc": 0.8143117453066253 }, { "epoch": 1.5427163331202305, "grad_norm": 0.3090091943740845, "learning_rate": 1.2354838895176707e-06, "loss": 0.5950101852416992, "step": 23830, "token_acc": 0.809293439323121 }, { "epoch": 1.5430400336648566, "grad_norm": 0.26483064889907837, "learning_rate": 1.2338112517218737e-06, "loss": 0.6011191844940186, "step": 23835, "token_acc": 0.8074127226780644 }, { "epoch": 1.5433637342094828, "grad_norm": 0.32016992568969727, "learning_rate": 1.2321395875551689e-06, "loss": 0.6128260612487793, "step": 23840, "token_acc": 0.8060965063429415 }, { "epoch": 1.543687434754109, "grad_norm": 0.3806251585483551, "learning_rate": 1.2304688974497125e-06, "loss": 0.5800630569458007, "step": 23845, "token_acc": 0.8133209026844718 }, { "epoch": 1.5440111352987351, "grad_norm": 0.30609187483787537, "learning_rate": 1.2287991818374067e-06, "loss": 0.6062675476074219, "step": 23850, "token_acc": 0.8076348104644955 }, { "epoch": 1.5443348358433613, "grad_norm": 0.31908664107322693, "learning_rate": 1.2271304411499035e-06, "loss": 0.5920530319213867, "step": 23855, "token_acc": 0.8106003603404596 }, { "epoch": 1.5446585363879874, "grad_norm": 0.31232213973999023, "learning_rate": 1.2254626758186071e-06, "loss": 0.5941596984863281, "step": 23860, "token_acc": 0.8095150564246654 }, { "epoch": 1.5449822369326136, "grad_norm": 0.35002151131629944, "learning_rate": 1.2237958862746597e-06, "loss": 0.5919837951660156, "step": 23865, "token_acc": 0.8101174550767538 }, { "epoch": 1.5453059374772398, "grad_norm": 0.24659214913845062, "learning_rate": 1.222130072948961e-06, "loss": 0.5892264366149902, "step": 23870, "token_acc": 0.8101604614050739 }, { "epoch": 1.545629638021866, "grad_norm": 0.3978927433490753, "learning_rate": 1.2204652362721537e-06, "loss": 0.5788814067840576, "step": 23875, "token_acc": 0.8135520949202818 }, { "epoch": 1.545953338566492, "grad_norm": 0.3116265833377838, "learning_rate": 1.218801376674628e-06, "loss": 0.5948805332183837, "step": 23880, "token_acc": 0.8090906036886485 }, { "epoch": 1.5462770391111182, "grad_norm": 0.273237407207489, "learning_rate": 1.217138494586521e-06, "loss": 0.6033329486846923, "step": 23885, "token_acc": 0.8086961395467595 }, { "epoch": 1.5466007396557444, "grad_norm": 0.38454967737197876, "learning_rate": 1.215476590437723e-06, "loss": 0.5734662055969239, "step": 23890, "token_acc": 0.8156428878191363 }, { "epoch": 1.5469244402003706, "grad_norm": 0.36042964458465576, "learning_rate": 1.2138156646578615e-06, "loss": 0.5862568855285645, "step": 23895, "token_acc": 0.8124983832164938 }, { "epoch": 1.5472481407449967, "grad_norm": 0.2715114951133728, "learning_rate": 1.2121557176763187e-06, "loss": 0.586149263381958, "step": 23900, "token_acc": 0.81189142002529 }, { "epoch": 1.5475718412896229, "grad_norm": 0.4319576323032379, "learning_rate": 1.210496749922221e-06, "loss": 0.6161426067352295, "step": 23905, "token_acc": 0.8071745743155834 }, { "epoch": 1.547895541834249, "grad_norm": 0.3067244589328766, "learning_rate": 1.2088387618244446e-06, "loss": 0.5980366706848145, "step": 23910, "token_acc": 0.8101906201153191 }, { "epoch": 1.5482192423788752, "grad_norm": 0.3194601237773895, "learning_rate": 1.2071817538116048e-06, "loss": 0.5865428447723389, "step": 23915, "token_acc": 0.8117145170740699 }, { "epoch": 1.5485429429235014, "grad_norm": 0.2874203622341156, "learning_rate": 1.2055257263120735e-06, "loss": 0.6010730266571045, "step": 23920, "token_acc": 0.8083131251894513 }, { "epoch": 1.5488666434681275, "grad_norm": 0.4287340044975281, "learning_rate": 1.2038706797539617e-06, "loss": 0.5894576072692871, "step": 23925, "token_acc": 0.8107863624251433 }, { "epoch": 1.5491903440127537, "grad_norm": 0.22831574082374573, "learning_rate": 1.2022166145651305e-06, "loss": 0.5840960025787354, "step": 23930, "token_acc": 0.8133311200870543 }, { "epoch": 1.5495140445573798, "grad_norm": 0.27776047587394714, "learning_rate": 1.2005635311731845e-06, "loss": 0.6141258239746094, "step": 23935, "token_acc": 0.805070095439393 }, { "epoch": 1.549837745102006, "grad_norm": 0.3437739312648773, "learning_rate": 1.1989114300054782e-06, "loss": 0.5937165737152099, "step": 23940, "token_acc": 0.8089993422664724 }, { "epoch": 1.5501614456466322, "grad_norm": 0.33096641302108765, "learning_rate": 1.1972603114891095e-06, "loss": 0.6056174278259278, "step": 23945, "token_acc": 0.8086405116288523 }, { "epoch": 1.5504851461912583, "grad_norm": 0.344972163438797, "learning_rate": 1.195610176050923e-06, "loss": 0.5928673267364502, "step": 23950, "token_acc": 0.809804841189192 }, { "epoch": 1.5508088467358845, "grad_norm": 0.27996209263801575, "learning_rate": 1.1939610241175076e-06, "loss": 0.6172910690307617, "step": 23955, "token_acc": 0.8042029241274452 }, { "epoch": 1.5511325472805106, "grad_norm": 0.37417423725128174, "learning_rate": 1.1923128561152037e-06, "loss": 0.5729294300079346, "step": 23960, "token_acc": 0.8154786015471961 }, { "epoch": 1.5514562478251368, "grad_norm": 0.27169883251190186, "learning_rate": 1.1906656724700866e-06, "loss": 0.6067827224731446, "step": 23965, "token_acc": 0.807326553642489 }, { "epoch": 1.5517799483697632, "grad_norm": 0.3231510818004608, "learning_rate": 1.1890194736079886e-06, "loss": 0.5935104370117188, "step": 23970, "token_acc": 0.8091108024046323 }, { "epoch": 1.5521036489143893, "grad_norm": 0.34509289264678955, "learning_rate": 1.1873742599544807e-06, "loss": 0.5765653610229492, "step": 23975, "token_acc": 0.8145781602078399 }, { "epoch": 1.5524273494590155, "grad_norm": 0.3193449079990387, "learning_rate": 1.1857300319348814e-06, "loss": 0.5762745857238769, "step": 23980, "token_acc": 0.8128740498412393 }, { "epoch": 1.5527510500036417, "grad_norm": 0.33122360706329346, "learning_rate": 1.184086789974252e-06, "loss": 0.5830844879150391, "step": 23985, "token_acc": 0.812978312272762 }, { "epoch": 1.5530747505482678, "grad_norm": 0.4102756679058075, "learning_rate": 1.1824445344974035e-06, "loss": 0.6062613487243652, "step": 23990, "token_acc": 0.8078057810601824 }, { "epoch": 1.553398451092894, "grad_norm": 0.3994075059890747, "learning_rate": 1.1808032659288875e-06, "loss": 0.6233758449554443, "step": 23995, "token_acc": 0.8020527762142834 }, { "epoch": 1.5537221516375201, "grad_norm": 0.42218852043151855, "learning_rate": 1.179162984693003e-06, "loss": 0.6235945701599122, "step": 24000, "token_acc": 0.801900692974385 }, { "epoch": 1.5540458521821463, "grad_norm": 0.20464666187763214, "learning_rate": 1.1775236912137916e-06, "loss": 0.6009771347045898, "step": 24005, "token_acc": 0.8090091566204319 }, { "epoch": 1.5543695527267725, "grad_norm": 0.3257799744606018, "learning_rate": 1.1758853859150438e-06, "loss": 0.6005872249603271, "step": 24010, "token_acc": 0.808419974958668 }, { "epoch": 1.5546932532713986, "grad_norm": 0.3838268518447876, "learning_rate": 1.1742480692202867e-06, "loss": 0.620258378982544, "step": 24015, "token_acc": 0.8020106405030056 }, { "epoch": 1.5550169538160248, "grad_norm": 0.23681874573230743, "learning_rate": 1.1726117415528016e-06, "loss": 0.6038740634918213, "step": 24020, "token_acc": 0.8058708460718511 }, { "epoch": 1.555340654360651, "grad_norm": 0.4276295304298401, "learning_rate": 1.1709764033356069e-06, "loss": 0.5874143123626709, "step": 24025, "token_acc": 0.8108430300360225 }, { "epoch": 1.555664354905277, "grad_norm": 0.256788045167923, "learning_rate": 1.1693420549914686e-06, "loss": 0.581900691986084, "step": 24030, "token_acc": 0.8145068379891297 }, { "epoch": 1.5559880554499033, "grad_norm": 0.272173672914505, "learning_rate": 1.167708696942893e-06, "loss": 0.5956933975219727, "step": 24035, "token_acc": 0.8093996399081145 }, { "epoch": 1.5563117559945294, "grad_norm": 0.2940874993801117, "learning_rate": 1.1660763296121375e-06, "loss": 0.6027836799621582, "step": 24040, "token_acc": 0.8066681732980604 }, { "epoch": 1.5566354565391556, "grad_norm": 0.2063339501619339, "learning_rate": 1.164444953421197e-06, "loss": 0.6168605804443359, "step": 24045, "token_acc": 0.8045202670795201 }, { "epoch": 1.5569591570837817, "grad_norm": 0.2975543439388275, "learning_rate": 1.1628145687918123e-06, "loss": 0.6093913078308105, "step": 24050, "token_acc": 0.8064431421526244 }, { "epoch": 1.5572828576284081, "grad_norm": 0.3164381980895996, "learning_rate": 1.161185176145468e-06, "loss": 0.5958076000213623, "step": 24055, "token_acc": 0.8102905960779238 }, { "epoch": 1.5576065581730343, "grad_norm": 0.32520002126693726, "learning_rate": 1.159556775903392e-06, "loss": 0.5831997871398926, "step": 24060, "token_acc": 0.8131715042351998 }, { "epoch": 1.5579302587176604, "grad_norm": 0.3504476249217987, "learning_rate": 1.1579293684865545e-06, "loss": 0.5837512493133545, "step": 24065, "token_acc": 0.8119018731306001 }, { "epoch": 1.5582539592622866, "grad_norm": 0.3604826331138611, "learning_rate": 1.1563029543156722e-06, "loss": 0.5926136016845703, "step": 24070, "token_acc": 0.8099903629938966 }, { "epoch": 1.5585776598069128, "grad_norm": 0.38753747940063477, "learning_rate": 1.1546775338112027e-06, "loss": 0.5952015399932862, "step": 24075, "token_acc": 0.8086097434568541 }, { "epoch": 1.558901360351539, "grad_norm": 0.3704439699649811, "learning_rate": 1.1530531073933471e-06, "loss": 0.6007763862609863, "step": 24080, "token_acc": 0.8087564204201003 }, { "epoch": 1.559225060896165, "grad_norm": 0.31486231088638306, "learning_rate": 1.1514296754820486e-06, "loss": 0.5959040641784668, "step": 24085, "token_acc": 0.8094309362980279 }, { "epoch": 1.5595487614407912, "grad_norm": 0.3686031699180603, "learning_rate": 1.1498072384969938e-06, "loss": 0.6002017974853515, "step": 24090, "token_acc": 0.8080598387776742 }, { "epoch": 1.5598724619854174, "grad_norm": 0.2967207729816437, "learning_rate": 1.1481857968576143e-06, "loss": 0.5876909255981445, "step": 24095, "token_acc": 0.8118680149015434 }, { "epoch": 1.5601961625300436, "grad_norm": 0.42556291818618774, "learning_rate": 1.1465653509830826e-06, "loss": 0.5639089107513428, "step": 24100, "token_acc": 0.8167708791023085 }, { "epoch": 1.5605198630746697, "grad_norm": 0.3883719742298126, "learning_rate": 1.1449459012923126e-06, "loss": 0.641604232788086, "step": 24105, "token_acc": 0.7981585060318752 }, { "epoch": 1.5608435636192959, "grad_norm": 0.4131147861480713, "learning_rate": 1.143327448203962e-06, "loss": 0.5903783321380616, "step": 24110, "token_acc": 0.8110617759394972 }, { "epoch": 1.561167264163922, "grad_norm": 0.3508374094963074, "learning_rate": 1.141709992136431e-06, "loss": 0.5996078968048095, "step": 24115, "token_acc": 0.8079836471722157 }, { "epoch": 1.5614909647085482, "grad_norm": 0.48395806550979614, "learning_rate": 1.1400935335078605e-06, "loss": 0.582412576675415, "step": 24120, "token_acc": 0.8117123903837574 }, { "epoch": 1.5618146652531744, "grad_norm": 0.43241220712661743, "learning_rate": 1.1384780727361378e-06, "loss": 0.5867739677429199, "step": 24125, "token_acc": 0.8103563406786863 }, { "epoch": 1.5621383657978005, "grad_norm": 0.2811703085899353, "learning_rate": 1.136863610238887e-06, "loss": 0.6054916381835938, "step": 24130, "token_acc": 0.807725021923607 }, { "epoch": 1.5624620663424267, "grad_norm": 0.27551013231277466, "learning_rate": 1.1352501464334765e-06, "loss": 0.5943435668945313, "step": 24135, "token_acc": 0.8105156336488922 }, { "epoch": 1.5627857668870528, "grad_norm": 0.4067167639732361, "learning_rate": 1.1336376817370155e-06, "loss": 0.5828618049621582, "step": 24140, "token_acc": 0.8151041014205898 }, { "epoch": 1.563109467431679, "grad_norm": 0.4469960033893585, "learning_rate": 1.1320262165663598e-06, "loss": 0.5792229652404786, "step": 24145, "token_acc": 0.8128929726428581 }, { "epoch": 1.5634331679763052, "grad_norm": 0.3794800341129303, "learning_rate": 1.130415751338097e-06, "loss": 0.5976645469665527, "step": 24150, "token_acc": 0.8087246472663139 }, { "epoch": 1.5637568685209313, "grad_norm": 0.334473192691803, "learning_rate": 1.1288062864685668e-06, "loss": 0.5807289123535156, "step": 24155, "token_acc": 0.8137645476038088 }, { "epoch": 1.5640805690655575, "grad_norm": 0.37562495470046997, "learning_rate": 1.1271978223738417e-06, "loss": 0.6068698406219483, "step": 24160, "token_acc": 0.8072585562790436 }, { "epoch": 1.5644042696101836, "grad_norm": 0.4117979407310486, "learning_rate": 1.1255903594697443e-06, "loss": 0.6072152137756348, "step": 24165, "token_acc": 0.8072322789838734 }, { "epoch": 1.5647279701548098, "grad_norm": 0.349081814289093, "learning_rate": 1.1239838981718276e-06, "loss": 0.6078972816467285, "step": 24170, "token_acc": 0.8081519037677701 }, { "epoch": 1.565051670699436, "grad_norm": 0.4156150817871094, "learning_rate": 1.1223784388953951e-06, "loss": 0.5868157386779785, "step": 24175, "token_acc": 0.8123136999674585 }, { "epoch": 1.5653753712440621, "grad_norm": 0.2839871644973755, "learning_rate": 1.1207739820554864e-06, "loss": 0.6017395973205566, "step": 24180, "token_acc": 0.8079553018536821 }, { "epoch": 1.5656990717886883, "grad_norm": 0.2839588224887848, "learning_rate": 1.1191705280668835e-06, "loss": 0.6142794132232666, "step": 24185, "token_acc": 0.8049251937713403 }, { "epoch": 1.5660227723333144, "grad_norm": 0.30431634187698364, "learning_rate": 1.1175680773441072e-06, "loss": 0.6037611961364746, "step": 24190, "token_acc": 0.806872262845397 }, { "epoch": 1.5663464728779406, "grad_norm": 0.22595088183879852, "learning_rate": 1.1159666303014244e-06, "loss": 0.6027230262756348, "step": 24195, "token_acc": 0.808448167618951 }, { "epoch": 1.5666701734225668, "grad_norm": 0.38763585686683655, "learning_rate": 1.1143661873528334e-06, "loss": 0.6108691692352295, "step": 24200, "token_acc": 0.8048977090286521 }, { "epoch": 1.566993873967193, "grad_norm": 0.35849031805992126, "learning_rate": 1.112766748912082e-06, "loss": 0.6014337062835693, "step": 24205, "token_acc": 0.8069939389279719 }, { "epoch": 1.567317574511819, "grad_norm": 0.37504690885543823, "learning_rate": 1.1111683153926516e-06, "loss": 0.6041045188903809, "step": 24210, "token_acc": 0.8077768116134428 }, { "epoch": 1.5676412750564452, "grad_norm": 0.37531664967536926, "learning_rate": 1.1095708872077716e-06, "loss": 0.5926700592041015, "step": 24215, "token_acc": 0.8108930868901904 }, { "epoch": 1.5679649756010714, "grad_norm": 0.3584319055080414, "learning_rate": 1.1079744647704e-06, "loss": 0.6051863670349121, "step": 24220, "token_acc": 0.8071456290245138 }, { "epoch": 1.5682886761456976, "grad_norm": 0.3684729039669037, "learning_rate": 1.1063790484932463e-06, "loss": 0.588780689239502, "step": 24225, "token_acc": 0.8108356731449127 }, { "epoch": 1.5686123766903237, "grad_norm": 0.26645517349243164, "learning_rate": 1.1047846387887534e-06, "loss": 0.5943243026733398, "step": 24230, "token_acc": 0.8101799329868348 }, { "epoch": 1.5689360772349499, "grad_norm": 0.2995162904262543, "learning_rate": 1.103191236069105e-06, "loss": 0.597218370437622, "step": 24235, "token_acc": 0.8102698826679866 }, { "epoch": 1.569259777779576, "grad_norm": 0.41623473167419434, "learning_rate": 1.1015988407462248e-06, "loss": 0.6114730358123779, "step": 24240, "token_acc": 0.8054358121822505 }, { "epoch": 1.5695834783242022, "grad_norm": 0.35904020071029663, "learning_rate": 1.1000074532317794e-06, "loss": 0.6074697494506835, "step": 24245, "token_acc": 0.8058863873171632 }, { "epoch": 1.5699071788688284, "grad_norm": 0.32596156001091003, "learning_rate": 1.0984170739371663e-06, "loss": 0.5976059913635254, "step": 24250, "token_acc": 0.8092942432890664 }, { "epoch": 1.5702308794134545, "grad_norm": 0.44009995460510254, "learning_rate": 1.096827703273533e-06, "loss": 0.6047541618347168, "step": 24255, "token_acc": 0.8078067184212435 }, { "epoch": 1.5705545799580807, "grad_norm": 0.30427178740501404, "learning_rate": 1.0952393416517582e-06, "loss": 0.5701379776000977, "step": 24260, "token_acc": 0.8153353752106077 }, { "epoch": 1.5708782805027068, "grad_norm": 0.34667694568634033, "learning_rate": 1.0936519894824638e-06, "loss": 0.596796703338623, "step": 24265, "token_acc": 0.8105240710134883 }, { "epoch": 1.571201981047333, "grad_norm": 0.3165658712387085, "learning_rate": 1.0920656471760072e-06, "loss": 0.6023131847381592, "step": 24270, "token_acc": 0.8088693837068345 }, { "epoch": 1.5715256815919592, "grad_norm": 0.35077911615371704, "learning_rate": 1.0904803151424909e-06, "loss": 0.5947998523712158, "step": 24275, "token_acc": 0.8104512740048436 }, { "epoch": 1.5718493821365853, "grad_norm": 0.28460925817489624, "learning_rate": 1.08889599379175e-06, "loss": 0.600013256072998, "step": 24280, "token_acc": 0.8079220860041073 }, { "epoch": 1.5721730826812115, "grad_norm": 0.31290772557258606, "learning_rate": 1.0873126835333613e-06, "loss": 0.605602502822876, "step": 24285, "token_acc": 0.8072359206110098 }, { "epoch": 1.5724967832258376, "grad_norm": 0.24569125473499298, "learning_rate": 1.0857303847766394e-06, "loss": 0.5766562461853028, "step": 24290, "token_acc": 0.8160298862285618 }, { "epoch": 1.5728204837704638, "grad_norm": 0.41692522168159485, "learning_rate": 1.0841490979306368e-06, "loss": 0.5867120265960694, "step": 24295, "token_acc": 0.8113398369187332 }, { "epoch": 1.57314418431509, "grad_norm": 0.2981976270675659, "learning_rate": 1.082568823404147e-06, "loss": 0.6130822181701661, "step": 24300, "token_acc": 0.8036975345181229 }, { "epoch": 1.5734678848597161, "grad_norm": 0.3487156629562378, "learning_rate": 1.0809895616056993e-06, "loss": 0.5993835926055908, "step": 24305, "token_acc": 0.8092257937095739 }, { "epoch": 1.5737915854043425, "grad_norm": 0.3595937490463257, "learning_rate": 1.0794113129435625e-06, "loss": 0.6050358772277832, "step": 24310, "token_acc": 0.807510273814471 }, { "epoch": 1.5741152859489687, "grad_norm": 0.2985328435897827, "learning_rate": 1.0778340778257419e-06, "loss": 0.6033134937286377, "step": 24315, "token_acc": 0.8070470027712933 }, { "epoch": 1.5744389864935948, "grad_norm": 0.35755234956741333, "learning_rate": 1.0762578566599818e-06, "loss": 0.5722482681274415, "step": 24320, "token_acc": 0.8180284209884324 }, { "epoch": 1.574762687038221, "grad_norm": 0.3229163587093353, "learning_rate": 1.0746826498537638e-06, "loss": 0.6135590553283692, "step": 24325, "token_acc": 0.804077599903868 }, { "epoch": 1.5750863875828471, "grad_norm": 0.2570040822029114, "learning_rate": 1.0731084578143098e-06, "loss": 0.5689505577087403, "step": 24330, "token_acc": 0.816519346982953 }, { "epoch": 1.5754100881274733, "grad_norm": 0.3692682385444641, "learning_rate": 1.0715352809485768e-06, "loss": 0.6243135929107666, "step": 24335, "token_acc": 0.8018637705405349 }, { "epoch": 1.5757337886720995, "grad_norm": 0.3661454916000366, "learning_rate": 1.0699631196632593e-06, "loss": 0.6022729873657227, "step": 24340, "token_acc": 0.807702307442314 }, { "epoch": 1.5760574892167256, "grad_norm": 0.3429076373577118, "learning_rate": 1.068391974364789e-06, "loss": 0.5825037479400634, "step": 24345, "token_acc": 0.8124661595977827 }, { "epoch": 1.5763811897613518, "grad_norm": 0.2866780161857605, "learning_rate": 1.0668218454593399e-06, "loss": 0.5904873371124267, "step": 24350, "token_acc": 0.8102929099370381 }, { "epoch": 1.576704890305978, "grad_norm": 0.2956089377403259, "learning_rate": 1.065252733352814e-06, "loss": 0.6018953323364258, "step": 24355, "token_acc": 0.8078432109907742 }, { "epoch": 1.577028590850604, "grad_norm": 0.32765695452690125, "learning_rate": 1.0636846384508587e-06, "loss": 0.5953081130981446, "step": 24360, "token_acc": 0.8110370011551217 }, { "epoch": 1.5773522913952303, "grad_norm": 0.3435005247592926, "learning_rate": 1.0621175611588551e-06, "loss": 0.5874766349792481, "step": 24365, "token_acc": 0.8116552881642543 }, { "epoch": 1.5776759919398564, "grad_norm": 0.2950029969215393, "learning_rate": 1.0605515018819207e-06, "loss": 0.5877567291259765, "step": 24370, "token_acc": 0.8123067845882476 }, { "epoch": 1.5779996924844826, "grad_norm": 0.3261282742023468, "learning_rate": 1.05898646102491e-06, "loss": 0.585355567932129, "step": 24375, "token_acc": 0.8114996997888838 }, { "epoch": 1.5783233930291087, "grad_norm": 0.36554887890815735, "learning_rate": 1.0574224389924193e-06, "loss": 0.6002898693084717, "step": 24380, "token_acc": 0.8081498196202972 }, { "epoch": 1.578647093573735, "grad_norm": 0.3007564842700958, "learning_rate": 1.0558594361887703e-06, "loss": 0.6001829624176025, "step": 24385, "token_acc": 0.8097180507075791 }, { "epoch": 1.578970794118361, "grad_norm": 0.3692658245563507, "learning_rate": 1.0542974530180327e-06, "loss": 0.6009154319763184, "step": 24390, "token_acc": 0.8098733935006538 }, { "epoch": 1.5792944946629874, "grad_norm": 0.345842570066452, "learning_rate": 1.0527364898840053e-06, "loss": 0.5750503540039062, "step": 24395, "token_acc": 0.8160061115355233 }, { "epoch": 1.5796181952076136, "grad_norm": 0.29695582389831543, "learning_rate": 1.0511765471902302e-06, "loss": 0.5961845397949219, "step": 24400, "token_acc": 0.809992568069725 }, { "epoch": 1.5799418957522398, "grad_norm": 0.2651531994342804, "learning_rate": 1.0496176253399748e-06, "loss": 0.601564884185791, "step": 24405, "token_acc": 0.8088265741867026 }, { "epoch": 1.580265596296866, "grad_norm": 0.3690587878227234, "learning_rate": 1.048059724736254e-06, "loss": 0.5769845962524414, "step": 24410, "token_acc": 0.8140933700301068 }, { "epoch": 1.580589296841492, "grad_norm": 0.3364418148994446, "learning_rate": 1.0465028457818128e-06, "loss": 0.5861063957214355, "step": 24415, "token_acc": 0.8117100868861565 }, { "epoch": 1.5809129973861182, "grad_norm": 0.31743890047073364, "learning_rate": 1.044946988879132e-06, "loss": 0.5967514991760254, "step": 24420, "token_acc": 0.8101193860147812 }, { "epoch": 1.5812366979307444, "grad_norm": 0.3790135979652405, "learning_rate": 1.0433921544304282e-06, "loss": 0.5897417068481445, "step": 24425, "token_acc": 0.8119045256053989 }, { "epoch": 1.5815603984753706, "grad_norm": 0.27658188343048096, "learning_rate": 1.0418383428376577e-06, "loss": 0.6207013130187988, "step": 24430, "token_acc": 0.8050431612890304 }, { "epoch": 1.5818840990199967, "grad_norm": 0.3699573576450348, "learning_rate": 1.0402855545025081e-06, "loss": 0.5928030967712402, "step": 24435, "token_acc": 0.8108583233008646 }, { "epoch": 1.5822077995646229, "grad_norm": 0.3319416642189026, "learning_rate": 1.0387337898264038e-06, "loss": 0.5864690780639649, "step": 24440, "token_acc": 0.8110006810786268 }, { "epoch": 1.582531500109249, "grad_norm": 0.2978593409061432, "learning_rate": 1.0371830492105023e-06, "loss": 0.5806516170501709, "step": 24445, "token_acc": 0.8133687925844321 }, { "epoch": 1.5828552006538752, "grad_norm": 0.3040585517883301, "learning_rate": 1.0356333330557038e-06, "loss": 0.5947978496551514, "step": 24450, "token_acc": 0.8111161827183034 }, { "epoch": 1.5831789011985014, "grad_norm": 0.2687186896800995, "learning_rate": 1.034084641762632e-06, "loss": 0.5738263130187988, "step": 24455, "token_acc": 0.8156587862416256 }, { "epoch": 1.5835026017431275, "grad_norm": 0.34610819816589355, "learning_rate": 1.0325369757316572e-06, "loss": 0.6059700012207031, "step": 24460, "token_acc": 0.8069105288521842 }, { "epoch": 1.5838263022877537, "grad_norm": 0.28000763058662415, "learning_rate": 1.0309903353628775e-06, "loss": 0.6003864288330079, "step": 24465, "token_acc": 0.8088982943135311 }, { "epoch": 1.5841500028323798, "grad_norm": 0.360948383808136, "learning_rate": 1.0294447210561282e-06, "loss": 0.6033974170684815, "step": 24470, "token_acc": 0.8087432393509777 }, { "epoch": 1.584473703377006, "grad_norm": 0.2935105264186859, "learning_rate": 1.0279001332109778e-06, "loss": 0.5826151847839356, "step": 24475, "token_acc": 0.8142578977187624 }, { "epoch": 1.5847974039216322, "grad_norm": 0.32927051186561584, "learning_rate": 1.0263565722267328e-06, "loss": 0.5899640083312988, "step": 24480, "token_acc": 0.8114414125200642 }, { "epoch": 1.5851211044662583, "grad_norm": 0.2959578037261963, "learning_rate": 1.0248140385024307e-06, "loss": 0.5766490936279297, "step": 24485, "token_acc": 0.8148618097734723 }, { "epoch": 1.5854448050108845, "grad_norm": 0.3414475917816162, "learning_rate": 1.023272532436846e-06, "loss": 0.6030645370483398, "step": 24490, "token_acc": 0.8088170681277783 }, { "epoch": 1.5857685055555106, "grad_norm": 0.3957618474960327, "learning_rate": 1.0217320544284836e-06, "loss": 0.6001055717468262, "step": 24495, "token_acc": 0.8084008794670692 }, { "epoch": 1.5860922061001368, "grad_norm": 0.2906537353992462, "learning_rate": 1.0201926048755905e-06, "loss": 0.6090543746948243, "step": 24500, "token_acc": 0.8077002940526348 }, { "epoch": 1.586415906644763, "grad_norm": 0.3562072515487671, "learning_rate": 1.0186541841761366e-06, "loss": 0.5965821266174316, "step": 24505, "token_acc": 0.8109445392820013 }, { "epoch": 1.5867396071893891, "grad_norm": 0.2750691771507263, "learning_rate": 1.0171167927278369e-06, "loss": 0.6083815574645997, "step": 24510, "token_acc": 0.807430749134785 }, { "epoch": 1.5870633077340153, "grad_norm": 0.31106141209602356, "learning_rate": 1.0155804309281336e-06, "loss": 0.589762020111084, "step": 24515, "token_acc": 0.8113245968404112 }, { "epoch": 1.5873870082786414, "grad_norm": 0.33520418405532837, "learning_rate": 1.014045099174204e-06, "loss": 0.604371976852417, "step": 24520, "token_acc": 0.80654351212998 }, { "epoch": 1.5877107088232676, "grad_norm": 0.4379861056804657, "learning_rate": 1.012510797862959e-06, "loss": 0.587368106842041, "step": 24525, "token_acc": 0.8116226368236427 }, { "epoch": 1.5880344093678938, "grad_norm": 0.2997688353061676, "learning_rate": 1.0109775273910455e-06, "loss": 0.5842586517333984, "step": 24530, "token_acc": 0.8134970605628413 }, { "epoch": 1.58835810991252, "grad_norm": 0.3294426500797272, "learning_rate": 1.0094452881548416e-06, "loss": 0.59449462890625, "step": 24535, "token_acc": 0.810306777058888 }, { "epoch": 1.588681810457146, "grad_norm": 0.4459681212902069, "learning_rate": 1.0079140805504596e-06, "loss": 0.5959283828735351, "step": 24540, "token_acc": 0.8086862253540212 }, { "epoch": 1.5890055110017722, "grad_norm": 0.3355756998062134, "learning_rate": 1.0063839049737439e-06, "loss": 0.605148458480835, "step": 24545, "token_acc": 0.8085199714246325 }, { "epoch": 1.5893292115463984, "grad_norm": 0.3760126531124115, "learning_rate": 1.0048547618202737e-06, "loss": 0.6173823356628418, "step": 24550, "token_acc": 0.8032733134785104 }, { "epoch": 1.5896529120910246, "grad_norm": 0.30556899309158325, "learning_rate": 1.00332665148536e-06, "loss": 0.5607346057891845, "step": 24555, "token_acc": 0.8181895247535083 }, { "epoch": 1.5899766126356507, "grad_norm": 0.2622094750404358, "learning_rate": 1.0017995743640474e-06, "loss": 0.5934197425842285, "step": 24560, "token_acc": 0.8091601186290397 }, { "epoch": 1.5903003131802769, "grad_norm": 0.41324615478515625, "learning_rate": 1.0002735308511147e-06, "loss": 0.5919451236724853, "step": 24565, "token_acc": 0.8109533441025154 }, { "epoch": 1.590624013724903, "grad_norm": 0.321902871131897, "learning_rate": 9.987485213410714e-07, "loss": 0.6163719177246094, "step": 24570, "token_acc": 0.8045019941364465 }, { "epoch": 1.5909477142695292, "grad_norm": 0.32224634289741516, "learning_rate": 9.972245462281605e-07, "loss": 0.5983548641204834, "step": 24575, "token_acc": 0.8090772791835447 }, { "epoch": 1.5912714148141553, "grad_norm": 0.28193148970603943, "learning_rate": 9.957016059063569e-07, "loss": 0.5860691070556641, "step": 24580, "token_acc": 0.8126856589502336 }, { "epoch": 1.5915951153587815, "grad_norm": 0.29916852712631226, "learning_rate": 9.941797007693715e-07, "loss": 0.5877694129943848, "step": 24585, "token_acc": 0.8126585062440291 }, { "epoch": 1.5919188159034077, "grad_norm": 0.2316613793373108, "learning_rate": 9.9265883121064e-07, "loss": 0.5942611694335938, "step": 24590, "token_acc": 0.8103989967772819 }, { "epoch": 1.5922425164480338, "grad_norm": 0.2818564474582672, "learning_rate": 9.911389976233394e-07, "loss": 0.5842258930206299, "step": 24595, "token_acc": 0.813028250122557 }, { "epoch": 1.59256621699266, "grad_norm": 0.345721036195755, "learning_rate": 9.896202004003734e-07, "loss": 0.609492301940918, "step": 24600, "token_acc": 0.8066120679272553 }, { "epoch": 1.5928899175372861, "grad_norm": 0.3283131718635559, "learning_rate": 9.881024399343785e-07, "loss": 0.5878755569458007, "step": 24605, "token_acc": 0.8140343552038413 }, { "epoch": 1.5932136180819123, "grad_norm": 0.3591528832912445, "learning_rate": 9.865857166177228e-07, "loss": 0.5930631160736084, "step": 24610, "token_acc": 0.8103914312484413 }, { "epoch": 1.5935373186265385, "grad_norm": 0.3392149806022644, "learning_rate": 9.850700308425098e-07, "loss": 0.6072890281677246, "step": 24615, "token_acc": 0.8055229521094788 }, { "epoch": 1.5938610191711646, "grad_norm": 0.3191194534301758, "learning_rate": 9.835553830005707e-07, "loss": 0.5897979259490966, "step": 24620, "token_acc": 0.8111702302577493 }, { "epoch": 1.5941847197157908, "grad_norm": 0.4079498052597046, "learning_rate": 9.820417734834698e-07, "loss": 0.5730199813842773, "step": 24625, "token_acc": 0.8146340823527869 }, { "epoch": 1.594508420260417, "grad_norm": 0.3275347054004669, "learning_rate": 9.80529202682502e-07, "loss": 0.5677448272705078, "step": 24630, "token_acc": 0.8158221235470811 }, { "epoch": 1.594832120805043, "grad_norm": 0.39543238282203674, "learning_rate": 9.790176709886984e-07, "loss": 0.5949745178222656, "step": 24635, "token_acc": 0.8104797388548431 }, { "epoch": 1.5951558213496693, "grad_norm": 0.3728965222835541, "learning_rate": 9.77507178792812e-07, "loss": 0.6074966430664063, "step": 24640, "token_acc": 0.806244410645395 }, { "epoch": 1.5954795218942954, "grad_norm": 0.31501057744026184, "learning_rate": 9.759977264853377e-07, "loss": 0.6090653419494629, "step": 24645, "token_acc": 0.8065408457079629 }, { "epoch": 1.5958032224389216, "grad_norm": 0.2166827768087387, "learning_rate": 9.74489314456493e-07, "loss": 0.5807843208312988, "step": 24650, "token_acc": 0.8136561218753 }, { "epoch": 1.596126922983548, "grad_norm": 0.29461872577667236, "learning_rate": 9.729819430962355e-07, "loss": 0.6031328201293945, "step": 24655, "token_acc": 0.8090075758061722 }, { "epoch": 1.5964506235281741, "grad_norm": 0.3172648847103119, "learning_rate": 9.714756127942427e-07, "loss": 0.592646312713623, "step": 24660, "token_acc": 0.8091535316620436 }, { "epoch": 1.5967743240728003, "grad_norm": 0.3884281516075134, "learning_rate": 9.699703239399316e-07, "loss": 0.6228704452514648, "step": 24665, "token_acc": 0.8016545886882183 }, { "epoch": 1.5970980246174264, "grad_norm": 0.3088853657245636, "learning_rate": 9.68466076922447e-07, "loss": 0.6217836856842041, "step": 24670, "token_acc": 0.8030487804878049 }, { "epoch": 1.5974217251620526, "grad_norm": 0.3726350665092468, "learning_rate": 9.669628721306633e-07, "loss": 0.6141092777252197, "step": 24675, "token_acc": 0.8051107369849784 }, { "epoch": 1.5977454257066788, "grad_norm": 0.3611472249031067, "learning_rate": 9.654607099531865e-07, "loss": 0.5990478515625, "step": 24680, "token_acc": 0.8100815958975205 }, { "epoch": 1.598069126251305, "grad_norm": 0.2714172899723053, "learning_rate": 9.639595907783567e-07, "loss": 0.5940711498260498, "step": 24685, "token_acc": 0.8103163158660651 }, { "epoch": 1.598392826795931, "grad_norm": 0.3264223635196686, "learning_rate": 9.62459514994235e-07, "loss": 0.5728429794311524, "step": 24690, "token_acc": 0.8166341682915854 }, { "epoch": 1.5987165273405572, "grad_norm": 0.28535065054893494, "learning_rate": 9.609604829886232e-07, "loss": 0.5933992862701416, "step": 24695, "token_acc": 0.8092588556556968 }, { "epoch": 1.5990402278851834, "grad_norm": 0.3038357198238373, "learning_rate": 9.594624951490455e-07, "loss": 0.5916357040405273, "step": 24700, "token_acc": 0.8113309340235333 }, { "epoch": 1.5993639284298096, "grad_norm": 0.3516353964805603, "learning_rate": 9.579655518627635e-07, "loss": 0.5728622436523437, "step": 24705, "token_acc": 0.8150553102502115 }, { "epoch": 1.5996876289744357, "grad_norm": 0.37946221232414246, "learning_rate": 9.564696535167596e-07, "loss": 0.599240779876709, "step": 24710, "token_acc": 0.8082808523850988 }, { "epoch": 1.6000113295190619, "grad_norm": 0.29347923398017883, "learning_rate": 9.54974800497755e-07, "loss": 0.5959394454956055, "step": 24715, "token_acc": 0.8096718249733191 }, { "epoch": 1.600335030063688, "grad_norm": 0.395040899515152, "learning_rate": 9.534809931921946e-07, "loss": 0.58457932472229, "step": 24720, "token_acc": 0.8126379018501076 }, { "epoch": 1.6006587306083142, "grad_norm": 0.2954128086566925, "learning_rate": 9.519882319862561e-07, "loss": 0.5710666179656982, "step": 24725, "token_acc": 0.8164135447553899 }, { "epoch": 1.6009824311529404, "grad_norm": 0.32250338792800903, "learning_rate": 9.504965172658437e-07, "loss": 0.6089597225189209, "step": 24730, "token_acc": 0.8082435597189696 }, { "epoch": 1.6013061316975665, "grad_norm": 0.27427613735198975, "learning_rate": 9.490058494165971e-07, "loss": 0.5836678981781006, "step": 24735, "token_acc": 0.8122134210133014 }, { "epoch": 1.601629832242193, "grad_norm": 0.34380900859832764, "learning_rate": 9.475162288238765e-07, "loss": 0.6117689132690429, "step": 24740, "token_acc": 0.8065120473511069 }, { "epoch": 1.601953532786819, "grad_norm": 0.3552458882331848, "learning_rate": 9.460276558727805e-07, "loss": 0.5793700695037842, "step": 24745, "token_acc": 0.8143871835789606 }, { "epoch": 1.6022772333314452, "grad_norm": 0.3190498948097229, "learning_rate": 9.4454013094813e-07, "loss": 0.5774411678314209, "step": 24750, "token_acc": 0.8135831313550378 }, { "epoch": 1.6026009338760714, "grad_norm": 0.39435842633247375, "learning_rate": 9.430536544344787e-07, "loss": 0.6175008773803711, "step": 24755, "token_acc": 0.8063031432729872 }, { "epoch": 1.6029246344206975, "grad_norm": 0.3049851059913635, "learning_rate": 9.415682267161064e-07, "loss": 0.579935359954834, "step": 24760, "token_acc": 0.8134782311530312 }, { "epoch": 1.6032483349653237, "grad_norm": 0.2947145402431488, "learning_rate": 9.400838481770264e-07, "loss": 0.5863023281097413, "step": 24765, "token_acc": 0.8131597235881096 }, { "epoch": 1.6035720355099499, "grad_norm": 0.3508933484554291, "learning_rate": 9.386005192009761e-07, "loss": 0.6213090896606446, "step": 24770, "token_acc": 0.8036759976982704 }, { "epoch": 1.603895736054576, "grad_norm": 0.33214160799980164, "learning_rate": 9.371182401714235e-07, "loss": 0.5888391494750976, "step": 24775, "token_acc": 0.8107817083692839 }, { "epoch": 1.6042194365992022, "grad_norm": 0.25506895780563354, "learning_rate": 9.356370114715651e-07, "loss": 0.5893509864807129, "step": 24780, "token_acc": 0.8111354232701444 }, { "epoch": 1.6045431371438283, "grad_norm": 0.45382633805274963, "learning_rate": 9.341568334843249e-07, "loss": 0.604922866821289, "step": 24785, "token_acc": 0.8069400495411005 }, { "epoch": 1.6048668376884545, "grad_norm": 0.3825998604297638, "learning_rate": 9.326777065923576e-07, "loss": 0.5900701522827149, "step": 24790, "token_acc": 0.811022312087687 }, { "epoch": 1.6051905382330807, "grad_norm": 0.2862212657928467, "learning_rate": 9.311996311780446e-07, "loss": 0.5767958641052247, "step": 24795, "token_acc": 0.8144691411307725 }, { "epoch": 1.6055142387777068, "grad_norm": 0.39187154173851013, "learning_rate": 9.297226076234949e-07, "loss": 0.590813684463501, "step": 24800, "token_acc": 0.8086101582992461 }, { "epoch": 1.605837939322333, "grad_norm": 0.26413848996162415, "learning_rate": 9.282466363105464e-07, "loss": 0.5823151588439941, "step": 24805, "token_acc": 0.813628888295405 }, { "epoch": 1.6061616398669591, "grad_norm": 0.37530750036239624, "learning_rate": 9.267717176207647e-07, "loss": 0.6025464057922363, "step": 24810, "token_acc": 0.8065556671559917 }, { "epoch": 1.6064853404115853, "grad_norm": 0.39710289239883423, "learning_rate": 9.252978519354427e-07, "loss": 0.6048964500427246, "step": 24815, "token_acc": 0.8065698877979455 }, { "epoch": 1.6068090409562115, "grad_norm": 0.3097006678581238, "learning_rate": 9.238250396356041e-07, "loss": 0.5990718841552735, "step": 24820, "token_acc": 0.8112522686025408 }, { "epoch": 1.6071327415008376, "grad_norm": 0.40602803230285645, "learning_rate": 9.223532811019964e-07, "loss": 0.5908004760742187, "step": 24825, "token_acc": 0.8104743819753489 }, { "epoch": 1.6074564420454638, "grad_norm": 0.3105126619338989, "learning_rate": 9.208825767150964e-07, "loss": 0.5895084381103516, "step": 24830, "token_acc": 0.8121384141554442 }, { "epoch": 1.60778014259009, "grad_norm": 0.3791414797306061, "learning_rate": 9.194129268551072e-07, "loss": 0.6031680107116699, "step": 24835, "token_acc": 0.8085875340507592 }, { "epoch": 1.608103843134716, "grad_norm": 0.3492751121520996, "learning_rate": 9.179443319019638e-07, "loss": 0.6062288761138916, "step": 24840, "token_acc": 0.8056399834541301 }, { "epoch": 1.6084275436793423, "grad_norm": 0.3563256859779358, "learning_rate": 9.164767922353207e-07, "loss": 0.5845636367797852, "step": 24845, "token_acc": 0.813815308617083 }, { "epoch": 1.6087512442239684, "grad_norm": 0.32791924476623535, "learning_rate": 9.150103082345662e-07, "loss": 0.6127992630004883, "step": 24850, "token_acc": 0.8058134051869317 }, { "epoch": 1.6090749447685946, "grad_norm": 0.4029567241668701, "learning_rate": 9.135448802788138e-07, "loss": 0.5969727516174317, "step": 24855, "token_acc": 0.8086481865114596 }, { "epoch": 1.6093986453132207, "grad_norm": 0.32337135076522827, "learning_rate": 9.120805087469026e-07, "loss": 0.5961473464965821, "step": 24860, "token_acc": 0.8092636009525743 }, { "epoch": 1.609722345857847, "grad_norm": 0.4095057547092438, "learning_rate": 9.106171940173986e-07, "loss": 0.6323802947998047, "step": 24865, "token_acc": 0.8017946002118348 }, { "epoch": 1.610046046402473, "grad_norm": 0.424343466758728, "learning_rate": 9.091549364685997e-07, "loss": 0.6035764217376709, "step": 24870, "token_acc": 0.8059625573068742 }, { "epoch": 1.6103697469470992, "grad_norm": 0.3667786121368408, "learning_rate": 9.076937364785204e-07, "loss": 0.5872853755950928, "step": 24875, "token_acc": 0.8135662280408791 }, { "epoch": 1.6106934474917254, "grad_norm": 0.33662521839141846, "learning_rate": 9.062335944249129e-07, "loss": 0.5860065460205078, "step": 24880, "token_acc": 0.8133092637566721 }, { "epoch": 1.6110171480363515, "grad_norm": 0.3673347532749176, "learning_rate": 9.047745106852468e-07, "loss": 0.5940380096435547, "step": 24885, "token_acc": 0.8095036641783916 }, { "epoch": 1.6113408485809777, "grad_norm": 0.280407190322876, "learning_rate": 9.033164856367271e-07, "loss": 0.5835587501525878, "step": 24890, "token_acc": 0.8123713580751972 }, { "epoch": 1.6116645491256039, "grad_norm": 0.23448731005191803, "learning_rate": 9.01859519656274e-07, "loss": 0.6061376571655274, "step": 24895, "token_acc": 0.8069291953965032 }, { "epoch": 1.61198824967023, "grad_norm": 0.33419498801231384, "learning_rate": 9.004036131205451e-07, "loss": 0.576718807220459, "step": 24900, "token_acc": 0.8159216300579366 }, { "epoch": 1.6123119502148562, "grad_norm": 0.3054639399051666, "learning_rate": 8.989487664059166e-07, "loss": 0.5814727783203125, "step": 24905, "token_acc": 0.8136420799064786 }, { "epoch": 1.6126356507594823, "grad_norm": 0.3803694546222687, "learning_rate": 8.974949798884935e-07, "loss": 0.5847614288330079, "step": 24910, "token_acc": 0.8134895377516111 }, { "epoch": 1.6129593513041085, "grad_norm": 0.38627734780311584, "learning_rate": 8.960422539441055e-07, "loss": 0.5809233665466309, "step": 24915, "token_acc": 0.8142509005392579 }, { "epoch": 1.6132830518487347, "grad_norm": 0.29949721693992615, "learning_rate": 8.945905889483108e-07, "loss": 0.5837748050689697, "step": 24920, "token_acc": 0.8122012914378686 }, { "epoch": 1.6136067523933608, "grad_norm": 0.3796670436859131, "learning_rate": 8.931399852763912e-07, "loss": 0.6006078720092773, "step": 24925, "token_acc": 0.8089909180225732 }, { "epoch": 1.613930452937987, "grad_norm": 0.3224579691886902, "learning_rate": 8.916904433033536e-07, "loss": 0.5701506614685059, "step": 24930, "token_acc": 0.8159696671115158 }, { "epoch": 1.6142541534826131, "grad_norm": 0.3427554965019226, "learning_rate": 8.9024196340393e-07, "loss": 0.5959551811218262, "step": 24935, "token_acc": 0.8098438439629138 }, { "epoch": 1.6145778540272393, "grad_norm": 0.28628799319267273, "learning_rate": 8.887945459525832e-07, "loss": 0.6055591583251954, "step": 24940, "token_acc": 0.8078690291720003 }, { "epoch": 1.6149015545718655, "grad_norm": 0.33248308300971985, "learning_rate": 8.873481913234928e-07, "loss": 0.5975377082824707, "step": 24945, "token_acc": 0.8097174154094284 }, { "epoch": 1.6152252551164916, "grad_norm": 0.2914814054965973, "learning_rate": 8.859028998905705e-07, "loss": 0.5758330345153808, "step": 24950, "token_acc": 0.8155734306327225 }, { "epoch": 1.6155489556611178, "grad_norm": 0.3087061643600464, "learning_rate": 8.844586720274506e-07, "loss": 0.6273255825042725, "step": 24955, "token_acc": 0.8018467220683287 }, { "epoch": 1.615872656205744, "grad_norm": 0.48077550530433655, "learning_rate": 8.830155081074921e-07, "loss": 0.598937702178955, "step": 24960, "token_acc": 0.8087777819422061 }, { "epoch": 1.61619635675037, "grad_norm": 0.3702889084815979, "learning_rate": 8.815734085037786e-07, "loss": 0.6059652805328369, "step": 24965, "token_acc": 0.8067384624304267 }, { "epoch": 1.6165200572949963, "grad_norm": 0.404598206281662, "learning_rate": 8.80132373589121e-07, "loss": 0.6139896392822266, "step": 24970, "token_acc": 0.8048960732879722 }, { "epoch": 1.6168437578396224, "grad_norm": 0.36091262102127075, "learning_rate": 8.786924037360533e-07, "loss": 0.6257696151733398, "step": 24975, "token_acc": 0.8024953865997484 }, { "epoch": 1.6171674583842486, "grad_norm": 0.3448483645915985, "learning_rate": 8.77253499316833e-07, "loss": 0.599729061126709, "step": 24980, "token_acc": 0.8096634220710683 }, { "epoch": 1.6174911589288747, "grad_norm": 0.353017657995224, "learning_rate": 8.75815660703443e-07, "loss": 0.5864225387573242, "step": 24985, "token_acc": 0.81254031824535 }, { "epoch": 1.617814859473501, "grad_norm": 0.2788691818714142, "learning_rate": 8.743788882675947e-07, "loss": 0.5919306755065918, "step": 24990, "token_acc": 0.8107732371251475 }, { "epoch": 1.6181385600181273, "grad_norm": 0.29396137595176697, "learning_rate": 8.729431823807144e-07, "loss": 0.5878116130828858, "step": 24995, "token_acc": 0.8111365252657274 }, { "epoch": 1.6184622605627534, "grad_norm": 0.3666927218437195, "learning_rate": 8.715085434139631e-07, "loss": 0.5988548278808594, "step": 25000, "token_acc": 0.8079124632364568 }, { "epoch": 1.6187859611073796, "grad_norm": 0.3073021471500397, "learning_rate": 8.700749717382195e-07, "loss": 0.5860789775848388, "step": 25005, "token_acc": 0.8116780030718 }, { "epoch": 1.6191096616520058, "grad_norm": 0.3634035587310791, "learning_rate": 8.68642467724089e-07, "loss": 0.588822603225708, "step": 25010, "token_acc": 0.8117477937431911 }, { "epoch": 1.619433362196632, "grad_norm": 0.32943400740623474, "learning_rate": 8.672110317418997e-07, "loss": 0.5740571975708008, "step": 25015, "token_acc": 0.8157057754442649 }, { "epoch": 1.619757062741258, "grad_norm": 0.25719118118286133, "learning_rate": 8.657806641617033e-07, "loss": 0.5861683845520019, "step": 25020, "token_acc": 0.8129462993747603 }, { "epoch": 1.6200807632858842, "grad_norm": 0.22008779644966125, "learning_rate": 8.643513653532781e-07, "loss": 0.596334171295166, "step": 25025, "token_acc": 0.8108561149118264 }, { "epoch": 1.6204044638305104, "grad_norm": 0.3477831184864044, "learning_rate": 8.629231356861228e-07, "loss": 0.5832921504974365, "step": 25030, "token_acc": 0.8135292175635523 }, { "epoch": 1.6207281643751366, "grad_norm": 0.3860042691230774, "learning_rate": 8.614959755294622e-07, "loss": 0.5849611282348632, "step": 25035, "token_acc": 0.8125875550801049 }, { "epoch": 1.6210518649197627, "grad_norm": 0.42641180753707886, "learning_rate": 8.600698852522421e-07, "loss": 0.5658823490142822, "step": 25040, "token_acc": 0.8172869802317655 }, { "epoch": 1.6213755654643889, "grad_norm": 0.3046068251132965, "learning_rate": 8.586448652231338e-07, "loss": 0.5957204341888428, "step": 25045, "token_acc": 0.8115990287894554 }, { "epoch": 1.621699266009015, "grad_norm": 0.2670336365699768, "learning_rate": 8.572209158105299e-07, "loss": 0.5967247009277343, "step": 25050, "token_acc": 0.8093200645214206 }, { "epoch": 1.6220229665536412, "grad_norm": 0.3490104675292969, "learning_rate": 8.557980373825497e-07, "loss": 0.5996834754943847, "step": 25055, "token_acc": 0.8091096075403229 }, { "epoch": 1.6223466670982674, "grad_norm": 0.2808069884777069, "learning_rate": 8.543762303070324e-07, "loss": 0.6019379615783691, "step": 25060, "token_acc": 0.8086561981657534 }, { "epoch": 1.6226703676428935, "grad_norm": 0.3808339536190033, "learning_rate": 8.529554949515417e-07, "loss": 0.5922805309295655, "step": 25065, "token_acc": 0.8119130721106355 }, { "epoch": 1.6229940681875197, "grad_norm": 0.34119170904159546, "learning_rate": 8.515358316833616e-07, "loss": 0.5961444854736329, "step": 25070, "token_acc": 0.8095093205499186 }, { "epoch": 1.6233177687321458, "grad_norm": 0.3497075140476227, "learning_rate": 8.501172408695063e-07, "loss": 0.5895150184631348, "step": 25075, "token_acc": 0.8127383625901957 }, { "epoch": 1.6236414692767722, "grad_norm": 0.2097425013780594, "learning_rate": 8.486997228767013e-07, "loss": 0.5998837947845459, "step": 25080, "token_acc": 0.8078813280205622 }, { "epoch": 1.6239651698213984, "grad_norm": 0.42827025055885315, "learning_rate": 8.472832780714058e-07, "loss": 0.5888548374176026, "step": 25085, "token_acc": 0.8116137484586929 }, { "epoch": 1.6242888703660245, "grad_norm": 0.4367963671684265, "learning_rate": 8.458679068197944e-07, "loss": 0.6131134033203125, "step": 25090, "token_acc": 0.806296821508888 }, { "epoch": 1.6246125709106507, "grad_norm": 0.28613200783729553, "learning_rate": 8.444536094877681e-07, "loss": 0.5861770153045655, "step": 25095, "token_acc": 0.8128474924941621 }, { "epoch": 1.6249362714552769, "grad_norm": 0.3971405327320099, "learning_rate": 8.430403864409465e-07, "loss": 0.5938613414764404, "step": 25100, "token_acc": 0.811844566983408 }, { "epoch": 1.625259971999903, "grad_norm": 0.3899421691894531, "learning_rate": 8.416282380446772e-07, "loss": 0.5907140254974366, "step": 25105, "token_acc": 0.8110802589719261 }, { "epoch": 1.6255836725445292, "grad_norm": 0.28330954909324646, "learning_rate": 8.402171646640239e-07, "loss": 0.5985447406768799, "step": 25110, "token_acc": 0.8088820301783265 }, { "epoch": 1.6259073730891553, "grad_norm": 0.20352135598659515, "learning_rate": 8.388071666637765e-07, "loss": 0.5777809619903564, "step": 25115, "token_acc": 0.8145732847721232 }, { "epoch": 1.6262310736337815, "grad_norm": 0.31774643063545227, "learning_rate": 8.373982444084428e-07, "loss": 0.5963313579559326, "step": 25120, "token_acc": 0.8096224441664445 }, { "epoch": 1.6265547741784077, "grad_norm": 0.38353291153907776, "learning_rate": 8.359903982622603e-07, "loss": 0.6045207977294922, "step": 25125, "token_acc": 0.8073054638693318 }, { "epoch": 1.6268784747230338, "grad_norm": 0.31613653898239136, "learning_rate": 8.345836285891768e-07, "loss": 0.5781006813049316, "step": 25130, "token_acc": 0.814490771511836 }, { "epoch": 1.62720217526766, "grad_norm": 0.3700692355632782, "learning_rate": 8.331779357528725e-07, "loss": 0.5914454460144043, "step": 25135, "token_acc": 0.8106805475226528 }, { "epoch": 1.6275258758122861, "grad_norm": 0.3136039972305298, "learning_rate": 8.317733201167438e-07, "loss": 0.6044976234436035, "step": 25140, "token_acc": 0.8077846625174226 }, { "epoch": 1.6278495763569123, "grad_norm": 0.318671852350235, "learning_rate": 8.3036978204391e-07, "loss": 0.6031053543090821, "step": 25145, "token_acc": 0.8079404682648814 }, { "epoch": 1.6281732769015385, "grad_norm": 0.34539559483528137, "learning_rate": 8.289673218972094e-07, "loss": 0.5982361793518066, "step": 25150, "token_acc": 0.8095152947186921 }, { "epoch": 1.6284969774461646, "grad_norm": 0.28705349564552307, "learning_rate": 8.275659400392061e-07, "loss": 0.6107872009277344, "step": 25155, "token_acc": 0.8047402426160337 }, { "epoch": 1.6288206779907908, "grad_norm": 0.3467339277267456, "learning_rate": 8.26165636832183e-07, "loss": 0.5740239143371582, "step": 25160, "token_acc": 0.8146889611779901 }, { "epoch": 1.629144378535417, "grad_norm": 0.37563109397888184, "learning_rate": 8.247664126381439e-07, "loss": 0.5927310943603515, "step": 25165, "token_acc": 0.8102523880876569 }, { "epoch": 1.629468079080043, "grad_norm": 0.3056710362434387, "learning_rate": 8.233682678188115e-07, "loss": 0.6220186233520508, "step": 25170, "token_acc": 0.8036163489680793 }, { "epoch": 1.6297917796246693, "grad_norm": 0.40017521381378174, "learning_rate": 8.219712027356375e-07, "loss": 0.6097563743591309, "step": 25175, "token_acc": 0.8062664718588995 }, { "epoch": 1.6301154801692954, "grad_norm": 0.3853064775466919, "learning_rate": 8.205752177497828e-07, "loss": 0.587377405166626, "step": 25180, "token_acc": 0.8109298905049844 }, { "epoch": 1.6304391807139216, "grad_norm": 0.288860559463501, "learning_rate": 8.191803132221393e-07, "loss": 0.6193977355957031, "step": 25185, "token_acc": 0.8035935064236951 }, { "epoch": 1.6307628812585477, "grad_norm": 0.34295690059661865, "learning_rate": 8.177864895133131e-07, "loss": 0.5859251022338867, "step": 25190, "token_acc": 0.8129397871977795 }, { "epoch": 1.631086581803174, "grad_norm": 0.38944002985954285, "learning_rate": 8.163937469836364e-07, "loss": 0.5983115196228027, "step": 25195, "token_acc": 0.810189050171007 }, { "epoch": 1.6314102823478, "grad_norm": 0.46169328689575195, "learning_rate": 8.150020859931551e-07, "loss": 0.5949231147766113, "step": 25200, "token_acc": 0.8085300076661921 }, { "epoch": 1.6317339828924262, "grad_norm": 0.44065576791763306, "learning_rate": 8.136115069016414e-07, "loss": 0.6239044189453125, "step": 25205, "token_acc": 0.801684128616291 }, { "epoch": 1.6320576834370524, "grad_norm": 0.24304339289665222, "learning_rate": 8.122220100685851e-07, "loss": 0.6003787994384766, "step": 25210, "token_acc": 0.8094145544268914 }, { "epoch": 1.6323813839816785, "grad_norm": 0.20107731223106384, "learning_rate": 8.108335958531965e-07, "loss": 0.5842286109924316, "step": 25215, "token_acc": 0.8110965556481813 }, { "epoch": 1.6327050845263047, "grad_norm": 0.35711342096328735, "learning_rate": 8.094462646144058e-07, "loss": 0.6074748992919922, "step": 25220, "token_acc": 0.8061755193162774 }, { "epoch": 1.6330287850709309, "grad_norm": 0.3244762420654297, "learning_rate": 8.08060016710866e-07, "loss": 0.5987215995788574, "step": 25225, "token_acc": 0.8098682927813149 }, { "epoch": 1.633352485615557, "grad_norm": 0.3147645890712738, "learning_rate": 8.066748525009438e-07, "loss": 0.6029754638671875, "step": 25230, "token_acc": 0.8080965974949826 }, { "epoch": 1.6336761861601832, "grad_norm": 0.269853413105011, "learning_rate": 8.052907723427322e-07, "loss": 0.5930551052093506, "step": 25235, "token_acc": 0.8099706468306829 }, { "epoch": 1.6339998867048093, "grad_norm": 0.2921529710292816, "learning_rate": 8.039077765940418e-07, "loss": 0.5830825805664063, "step": 25240, "token_acc": 0.8125567773944973 }, { "epoch": 1.6343235872494355, "grad_norm": 0.3321157991886139, "learning_rate": 8.025258656124008e-07, "loss": 0.5914920806884766, "step": 25245, "token_acc": 0.8089106520914514 }, { "epoch": 1.6346472877940617, "grad_norm": 0.2698540687561035, "learning_rate": 8.011450397550586e-07, "loss": 0.5854960918426514, "step": 25250, "token_acc": 0.8139959162468133 }, { "epoch": 1.6349709883386878, "grad_norm": 0.3374672830104828, "learning_rate": 7.997652993789862e-07, "loss": 0.5968760967254638, "step": 25255, "token_acc": 0.8107239977047627 }, { "epoch": 1.635294688883314, "grad_norm": 0.37998777627944946, "learning_rate": 7.9838664484087e-07, "loss": 0.5786191940307617, "step": 25260, "token_acc": 0.8140145945651582 }, { "epoch": 1.6356183894279401, "grad_norm": 0.4071350395679474, "learning_rate": 7.970090764971189e-07, "loss": 0.6058961391448975, "step": 25265, "token_acc": 0.807216370749323 }, { "epoch": 1.6359420899725663, "grad_norm": 0.36504751443862915, "learning_rate": 7.956325947038585e-07, "loss": 0.5878802299499511, "step": 25270, "token_acc": 0.812272366868864 }, { "epoch": 1.6362657905171925, "grad_norm": 0.31851503252983093, "learning_rate": 7.942571998169346e-07, "loss": 0.5951934337615967, "step": 25275, "token_acc": 0.810557151919991 }, { "epoch": 1.6365894910618186, "grad_norm": 0.22910597920417786, "learning_rate": 7.928828921919119e-07, "loss": 0.5997650146484375, "step": 25280, "token_acc": 0.8092243186582809 }, { "epoch": 1.6369131916064448, "grad_norm": 0.29493647813796997, "learning_rate": 7.915096721840754e-07, "loss": 0.5881243705749511, "step": 25285, "token_acc": 0.8131810171510834 }, { "epoch": 1.637236892151071, "grad_norm": 0.3057910203933716, "learning_rate": 7.901375401484279e-07, "loss": 0.5945725440979004, "step": 25290, "token_acc": 0.8101987831742369 }, { "epoch": 1.637560592695697, "grad_norm": 0.2639720141887665, "learning_rate": 7.887664964396896e-07, "loss": 0.606867790222168, "step": 25295, "token_acc": 0.8069666979877238 }, { "epoch": 1.6378842932403233, "grad_norm": 0.3759029507637024, "learning_rate": 7.873965414123008e-07, "loss": 0.575113582611084, "step": 25300, "token_acc": 0.8157160390155674 }, { "epoch": 1.6382079937849494, "grad_norm": 0.3886915147304535, "learning_rate": 7.860276754204194e-07, "loss": 0.6009090423583985, "step": 25305, "token_acc": 0.8082515712833703 }, { "epoch": 1.6385316943295756, "grad_norm": 0.5123876333236694, "learning_rate": 7.846598988179255e-07, "loss": 0.5989577770233154, "step": 25310, "token_acc": 0.8086544651890003 }, { "epoch": 1.6388553948742017, "grad_norm": 0.2878485918045044, "learning_rate": 7.832932119584103e-07, "loss": 0.591809892654419, "step": 25315, "token_acc": 0.8095903381514563 }, { "epoch": 1.639179095418828, "grad_norm": 0.2672504186630249, "learning_rate": 7.819276151951905e-07, "loss": 0.6033707141876221, "step": 25320, "token_acc": 0.8081080088620145 }, { "epoch": 1.639502795963454, "grad_norm": 0.3608129918575287, "learning_rate": 7.80563108881296e-07, "loss": 0.5853167057037354, "step": 25325, "token_acc": 0.8118472423155433 }, { "epoch": 1.6398264965080802, "grad_norm": 0.3083909749984741, "learning_rate": 7.7919969336948e-07, "loss": 0.5968828201293945, "step": 25330, "token_acc": 0.8083165195888615 }, { "epoch": 1.6401501970527066, "grad_norm": 0.2576487064361572, "learning_rate": 7.77837369012206e-07, "loss": 0.6129422664642334, "step": 25335, "token_acc": 0.8060210076780954 }, { "epoch": 1.6404738975973328, "grad_norm": 0.44217467308044434, "learning_rate": 7.76476136161663e-07, "loss": 0.5852829933166503, "step": 25340, "token_acc": 0.8135122235081044 }, { "epoch": 1.640797598141959, "grad_norm": 0.32893896102905273, "learning_rate": 7.751159951697545e-07, "loss": 0.5705222129821778, "step": 25345, "token_acc": 0.8159661775677692 }, { "epoch": 1.641121298686585, "grad_norm": 0.22243042290210724, "learning_rate": 7.737569463881012e-07, "loss": 0.6106114387512207, "step": 25350, "token_acc": 0.8054194733619106 }, { "epoch": 1.6414449992312112, "grad_norm": 0.3492306172847748, "learning_rate": 7.723989901680412e-07, "loss": 0.6054920196533203, "step": 25355, "token_acc": 0.8065573770491803 }, { "epoch": 1.6417686997758374, "grad_norm": 0.2687298655509949, "learning_rate": 7.71042126860635e-07, "loss": 0.5851747035980225, "step": 25360, "token_acc": 0.81175165868221 }, { "epoch": 1.6420924003204636, "grad_norm": 0.30756545066833496, "learning_rate": 7.696863568166519e-07, "loss": 0.6112255096435547, "step": 25365, "token_acc": 0.805054282705784 }, { "epoch": 1.6424161008650897, "grad_norm": 0.338437020778656, "learning_rate": 7.683316803865864e-07, "loss": 0.5777788639068604, "step": 25370, "token_acc": 0.8140609219742629 }, { "epoch": 1.6427398014097159, "grad_norm": 0.3366914689540863, "learning_rate": 7.669780979206454e-07, "loss": 0.6022114753723145, "step": 25375, "token_acc": 0.8081308840094005 }, { "epoch": 1.643063501954342, "grad_norm": 0.34164029359817505, "learning_rate": 7.656256097687587e-07, "loss": 0.612185287475586, "step": 25380, "token_acc": 0.8045129762181084 }, { "epoch": 1.6433872024989682, "grad_norm": 0.3505224287509918, "learning_rate": 7.642742162805644e-07, "loss": 0.5872992515563965, "step": 25385, "token_acc": 0.8121434570282123 }, { "epoch": 1.6437109030435944, "grad_norm": 0.2541707158088684, "learning_rate": 7.629239178054254e-07, "loss": 0.5636166095733642, "step": 25390, "token_acc": 0.8179101491678857 }, { "epoch": 1.6440346035882205, "grad_norm": 0.3502848446369171, "learning_rate": 7.615747146924191e-07, "loss": 0.5749737739562988, "step": 25395, "token_acc": 0.8141865282916465 }, { "epoch": 1.6443583041328467, "grad_norm": 0.32398200035095215, "learning_rate": 7.602266072903375e-07, "loss": 0.5916618824005127, "step": 25400, "token_acc": 0.8104009099798447 }, { "epoch": 1.6446820046774728, "grad_norm": 0.36630842089653015, "learning_rate": 7.588795959476913e-07, "loss": 0.5952952861785888, "step": 25405, "token_acc": 0.8100107338568443 }, { "epoch": 1.645005705222099, "grad_norm": 0.2881837785243988, "learning_rate": 7.575336810127099e-07, "loss": 0.5803236961364746, "step": 25410, "token_acc": 0.8129161448272446 }, { "epoch": 1.6453294057667252, "grad_norm": 0.34403491020202637, "learning_rate": 7.561888628333353e-07, "loss": 0.5950477600097657, "step": 25415, "token_acc": 0.8114442056972302 }, { "epoch": 1.6456531063113515, "grad_norm": 0.24075505137443542, "learning_rate": 7.548451417572283e-07, "loss": 0.5801521301269531, "step": 25420, "token_acc": 0.8129881841208376 }, { "epoch": 1.6459768068559777, "grad_norm": 0.27656763792037964, "learning_rate": 7.53502518131764e-07, "loss": 0.6052735328674317, "step": 25425, "token_acc": 0.8082990376958195 }, { "epoch": 1.6463005074006039, "grad_norm": 0.4529590606689453, "learning_rate": 7.52160992304039e-07, "loss": 0.6031914234161377, "step": 25430, "token_acc": 0.8079383812659171 }, { "epoch": 1.64662420794523, "grad_norm": 0.3026237189769745, "learning_rate": 7.508205646208577e-07, "loss": 0.5844563484191895, "step": 25435, "token_acc": 0.8118996908278941 }, { "epoch": 1.6469479084898562, "grad_norm": 0.40679487586021423, "learning_rate": 7.494812354287489e-07, "loss": 0.5955617904663086, "step": 25440, "token_acc": 0.8093150909388825 }, { "epoch": 1.6472716090344823, "grad_norm": 0.41985490918159485, "learning_rate": 7.48143005073953e-07, "loss": 0.5812784194946289, "step": 25445, "token_acc": 0.8127691623018726 }, { "epoch": 1.6475953095791085, "grad_norm": 0.3949822783470154, "learning_rate": 7.468058739024264e-07, "loss": 0.6198108673095704, "step": 25450, "token_acc": 0.8047892226376177 }, { "epoch": 1.6479190101237347, "grad_norm": 0.271759033203125, "learning_rate": 7.454698422598416e-07, "loss": 0.5628041744232177, "step": 25455, "token_acc": 0.8170428005522652 }, { "epoch": 1.6482427106683608, "grad_norm": 0.41000059247016907, "learning_rate": 7.44134910491589e-07, "loss": 0.6145094871520996, "step": 25460, "token_acc": 0.8053290410120655 }, { "epoch": 1.648566411212987, "grad_norm": 0.38570934534072876, "learning_rate": 7.428010789427726e-07, "loss": 0.5984353065490723, "step": 25465, "token_acc": 0.8088222984849753 }, { "epoch": 1.6488901117576131, "grad_norm": 0.28238844871520996, "learning_rate": 7.414683479582119e-07, "loss": 0.5934662818908691, "step": 25470, "token_acc": 0.8095156835605443 }, { "epoch": 1.6492138123022393, "grad_norm": 0.4052921235561371, "learning_rate": 7.401367178824425e-07, "loss": 0.5970856666564941, "step": 25475, "token_acc": 0.8085682202427515 }, { "epoch": 1.6495375128468655, "grad_norm": 0.2668794095516205, "learning_rate": 7.38806189059716e-07, "loss": 0.5830056190490722, "step": 25480, "token_acc": 0.8133828622339737 }, { "epoch": 1.6498612133914916, "grad_norm": 0.41627830266952515, "learning_rate": 7.374767618339962e-07, "loss": 0.581572151184082, "step": 25485, "token_acc": 0.8125591937243222 }, { "epoch": 1.6501849139361178, "grad_norm": 0.26864343881607056, "learning_rate": 7.361484365489674e-07, "loss": 0.5873490810394287, "step": 25490, "token_acc": 0.8131098323742807 }, { "epoch": 1.650508614480744, "grad_norm": 0.3894071877002716, "learning_rate": 7.348212135480248e-07, "loss": 0.6145315647125245, "step": 25495, "token_acc": 0.8067725200440182 }, { "epoch": 1.65083231502537, "grad_norm": 0.2762914001941681, "learning_rate": 7.334950931742807e-07, "loss": 0.5807331562042236, "step": 25500, "token_acc": 0.813839201779011 }, { "epoch": 1.6511560155699962, "grad_norm": 0.27130451798439026, "learning_rate": 7.321700757705607e-07, "loss": 0.5624841213226318, "step": 25505, "token_acc": 0.8187832852808239 }, { "epoch": 1.6514797161146224, "grad_norm": 0.28499776124954224, "learning_rate": 7.308461616794055e-07, "loss": 0.5816281318664551, "step": 25510, "token_acc": 0.8136332783865025 }, { "epoch": 1.6518034166592486, "grad_norm": 0.2831125557422638, "learning_rate": 7.295233512430733e-07, "loss": 0.5739923000335694, "step": 25515, "token_acc": 0.8157831508131212 }, { "epoch": 1.6521271172038747, "grad_norm": 0.33321070671081543, "learning_rate": 7.28201644803534e-07, "loss": 0.5761471748352051, "step": 25520, "token_acc": 0.8156080885120668 }, { "epoch": 1.6524508177485009, "grad_norm": 0.31648337841033936, "learning_rate": 7.268810427024725e-07, "loss": 0.5865737438201905, "step": 25525, "token_acc": 0.8134971211179925 }, { "epoch": 1.652774518293127, "grad_norm": 0.26904022693634033, "learning_rate": 7.255615452812897e-07, "loss": 0.589069938659668, "step": 25530, "token_acc": 0.8106767722023098 }, { "epoch": 1.6530982188377532, "grad_norm": 0.32292068004608154, "learning_rate": 7.242431528810995e-07, "loss": 0.5906251907348633, "step": 25535, "token_acc": 0.8123515280928867 }, { "epoch": 1.6534219193823794, "grad_norm": 0.30348822474479675, "learning_rate": 7.229258658427291e-07, "loss": 0.5876081943511963, "step": 25540, "token_acc": 0.8125107059831151 }, { "epoch": 1.6537456199270055, "grad_norm": 0.3661108613014221, "learning_rate": 7.216096845067244e-07, "loss": 0.5932699203491211, "step": 25545, "token_acc": 0.8100862340795986 }, { "epoch": 1.6540693204716317, "grad_norm": 0.26556724309921265, "learning_rate": 7.202946092133406e-07, "loss": 0.6061305046081543, "step": 25550, "token_acc": 0.8069374308355699 }, { "epoch": 1.6543930210162578, "grad_norm": 0.29537221789360046, "learning_rate": 7.189806403025496e-07, "loss": 0.609046459197998, "step": 25555, "token_acc": 0.805089485458613 }, { "epoch": 1.654716721560884, "grad_norm": 0.43925273418426514, "learning_rate": 7.176677781140351e-07, "loss": 0.5805350303649902, "step": 25560, "token_acc": 0.8138791113129707 }, { "epoch": 1.6550404221055102, "grad_norm": 0.3405936360359192, "learning_rate": 7.163560229871991e-07, "loss": 0.5924218654632568, "step": 25565, "token_acc": 0.8099185164372015 }, { "epoch": 1.6553641226501363, "grad_norm": 0.2182314693927765, "learning_rate": 7.150453752611502e-07, "loss": 0.581563663482666, "step": 25570, "token_acc": 0.8126799479892264 }, { "epoch": 1.6556878231947625, "grad_norm": 0.29100704193115234, "learning_rate": 7.137358352747186e-07, "loss": 0.5702010154724121, "step": 25575, "token_acc": 0.8150228525052325 }, { "epoch": 1.6560115237393886, "grad_norm": 0.33148249983787537, "learning_rate": 7.124274033664435e-07, "loss": 0.5944080829620362, "step": 25580, "token_acc": 0.8096056125626987 }, { "epoch": 1.6563352242840148, "grad_norm": 0.33053314685821533, "learning_rate": 7.111200798745782e-07, "loss": 0.5768553256988526, "step": 25585, "token_acc": 0.8151270678799929 }, { "epoch": 1.656658924828641, "grad_norm": 0.34195026755332947, "learning_rate": 7.09813865137089e-07, "loss": 0.586984920501709, "step": 25590, "token_acc": 0.8109462258282808 }, { "epoch": 1.6569826253732671, "grad_norm": 0.32264184951782227, "learning_rate": 7.085087594916578e-07, "loss": 0.6178982257843018, "step": 25595, "token_acc": 0.8049425947954396 }, { "epoch": 1.6573063259178933, "grad_norm": 0.34488818049430847, "learning_rate": 7.07204763275679e-07, "loss": 0.5797182559967041, "step": 25600, "token_acc": 0.8152230316007961 }, { "epoch": 1.6576300264625194, "grad_norm": 0.42209720611572266, "learning_rate": 7.059018768262582e-07, "loss": 0.6067178249359131, "step": 25605, "token_acc": 0.809135039717564 }, { "epoch": 1.6579537270071456, "grad_norm": 0.30906155705451965, "learning_rate": 7.04600100480215e-07, "loss": 0.5934983253479004, "step": 25610, "token_acc": 0.8101651567589576 }, { "epoch": 1.6582774275517718, "grad_norm": 0.3600173890590668, "learning_rate": 7.032994345740856e-07, "loss": 0.570137882232666, "step": 25615, "token_acc": 0.8167078433726566 }, { "epoch": 1.658601128096398, "grad_norm": 0.39053869247436523, "learning_rate": 7.019998794441119e-07, "loss": 0.6303149223327636, "step": 25620, "token_acc": 0.8004528896327656 }, { "epoch": 1.658924828641024, "grad_norm": 0.3323134183883667, "learning_rate": 7.007014354262565e-07, "loss": 0.5866384029388427, "step": 25625, "token_acc": 0.8125452402126031 }, { "epoch": 1.6592485291856502, "grad_norm": 0.3226790726184845, "learning_rate": 6.994041028561887e-07, "loss": 0.6089580059051514, "step": 25630, "token_acc": 0.8072246065808297 }, { "epoch": 1.6595722297302764, "grad_norm": 0.6157347559928894, "learning_rate": 6.981078820692943e-07, "loss": 0.5823562145233154, "step": 25635, "token_acc": 0.8118952813920677 }, { "epoch": 1.6598959302749026, "grad_norm": 0.2669318616390228, "learning_rate": 6.96812773400668e-07, "loss": 0.5849905014038086, "step": 25640, "token_acc": 0.8137668705454177 }, { "epoch": 1.6602196308195287, "grad_norm": 0.38761106133461, "learning_rate": 6.955187771851219e-07, "loss": 0.5929407119750977, "step": 25645, "token_acc": 0.8108441873000062 }, { "epoch": 1.6605433313641549, "grad_norm": 0.3243757486343384, "learning_rate": 6.942258937571772e-07, "loss": 0.5832089424133301, "step": 25650, "token_acc": 0.8126334383895892 }, { "epoch": 1.660867031908781, "grad_norm": 0.3479658365249634, "learning_rate": 6.929341234510673e-07, "loss": 0.576871109008789, "step": 25655, "token_acc": 0.8149171074585537 }, { "epoch": 1.6611907324534072, "grad_norm": 0.3583187758922577, "learning_rate": 6.916434666007377e-07, "loss": 0.588419246673584, "step": 25660, "token_acc": 0.8119866158471389 }, { "epoch": 1.6615144329980334, "grad_norm": 0.4261946976184845, "learning_rate": 6.903539235398499e-07, "loss": 0.5826686382293701, "step": 25665, "token_acc": 0.8126164626995604 }, { "epoch": 1.6618381335426595, "grad_norm": 0.3120292127132416, "learning_rate": 6.89065494601771e-07, "loss": 0.5743355751037598, "step": 25670, "token_acc": 0.8143395390070922 }, { "epoch": 1.662161834087286, "grad_norm": 0.3701743185520172, "learning_rate": 6.877781801195865e-07, "loss": 0.6020750522613525, "step": 25675, "token_acc": 0.8095198119543318 }, { "epoch": 1.662485534631912, "grad_norm": 0.30821049213409424, "learning_rate": 6.864919804260883e-07, "loss": 0.6008131504058838, "step": 25680, "token_acc": 0.8081551102745138 }, { "epoch": 1.6628092351765382, "grad_norm": 0.2970879077911377, "learning_rate": 6.852068958537866e-07, "loss": 0.5906544685363769, "step": 25685, "token_acc": 0.811723026551389 }, { "epoch": 1.6631329357211644, "grad_norm": 0.2942582368850708, "learning_rate": 6.83922926734894e-07, "loss": 0.5815858840942383, "step": 25690, "token_acc": 0.8134566759173605 }, { "epoch": 1.6634566362657905, "grad_norm": 0.35814884305000305, "learning_rate": 6.82640073401345e-07, "loss": 0.5970410823822021, "step": 25695, "token_acc": 0.8104923870333989 }, { "epoch": 1.6637803368104167, "grad_norm": 0.32133492827415466, "learning_rate": 6.813583361847781e-07, "loss": 0.6049193859100341, "step": 25700, "token_acc": 0.8082382832159988 }, { "epoch": 1.6641040373550429, "grad_norm": 0.4167601764202118, "learning_rate": 6.800777154165472e-07, "loss": 0.6213728904724121, "step": 25705, "token_acc": 0.8035928061315757 }, { "epoch": 1.664427737899669, "grad_norm": 0.38177743554115295, "learning_rate": 6.787982114277142e-07, "loss": 0.5889069557189941, "step": 25710, "token_acc": 0.8092771277448308 }, { "epoch": 1.6647514384442952, "grad_norm": 0.2687879204750061, "learning_rate": 6.775198245490588e-07, "loss": 0.5919972896575928, "step": 25715, "token_acc": 0.810129212388806 }, { "epoch": 1.6650751389889213, "grad_norm": 0.33420854806900024, "learning_rate": 6.762425551110624e-07, "loss": 0.5795973777770996, "step": 25720, "token_acc": 0.813353414282054 }, { "epoch": 1.6653988395335475, "grad_norm": 0.28289082646369934, "learning_rate": 6.749664034439257e-07, "loss": 0.5915867328643799, "step": 25725, "token_acc": 0.8098060084175899 }, { "epoch": 1.6657225400781737, "grad_norm": 0.28232619166374207, "learning_rate": 6.736913698775571e-07, "loss": 0.5712188720703125, "step": 25730, "token_acc": 0.8151539876030541 }, { "epoch": 1.6660462406227998, "grad_norm": 0.2924419641494751, "learning_rate": 6.724174547415757e-07, "loss": 0.5683441162109375, "step": 25735, "token_acc": 0.8161670691859639 }, { "epoch": 1.666369941167426, "grad_norm": 0.3305882215499878, "learning_rate": 6.711446583653108e-07, "loss": 0.5752309799194336, "step": 25740, "token_acc": 0.8148357834464567 }, { "epoch": 1.6666936417120521, "grad_norm": 0.307903528213501, "learning_rate": 6.698729810778065e-07, "loss": 0.5978945732116699, "step": 25745, "token_acc": 0.8091956700377222 }, { "epoch": 1.6670173422566783, "grad_norm": 0.26715344190597534, "learning_rate": 6.686024232078137e-07, "loss": 0.5967209815979004, "step": 25750, "token_acc": 0.8100849926419798 }, { "epoch": 1.6673410428013045, "grad_norm": 0.32101577520370483, "learning_rate": 6.67332985083794e-07, "loss": 0.5951004981994629, "step": 25755, "token_acc": 0.8104974101356099 }, { "epoch": 1.6676647433459308, "grad_norm": 0.31222131848335266, "learning_rate": 6.66064667033921e-07, "loss": 0.6010738849639893, "step": 25760, "token_acc": 0.8074727291263125 }, { "epoch": 1.667988443890557, "grad_norm": 0.28426116704940796, "learning_rate": 6.647974693860787e-07, "loss": 0.5905827522277832, "step": 25765, "token_acc": 0.8104037472421161 }, { "epoch": 1.6683121444351832, "grad_norm": 0.4159650206565857, "learning_rate": 6.635313924678605e-07, "loss": 0.5808542251586915, "step": 25770, "token_acc": 0.8152766263946836 }, { "epoch": 1.6686358449798093, "grad_norm": 0.3586675226688385, "learning_rate": 6.622664366065695e-07, "loss": 0.5965620040893554, "step": 25775, "token_acc": 0.8091854892995914 }, { "epoch": 1.6689595455244355, "grad_norm": 0.41541075706481934, "learning_rate": 6.610026021292226e-07, "loss": 0.5895281791687011, "step": 25780, "token_acc": 0.8124293716660389 }, { "epoch": 1.6692832460690616, "grad_norm": 0.36461183428764343, "learning_rate": 6.597398893625429e-07, "loss": 0.5797596931457519, "step": 25785, "token_acc": 0.8140476455389485 }, { "epoch": 1.6696069466136878, "grad_norm": 0.41360533237457275, "learning_rate": 6.584782986329652e-07, "loss": 0.5895915031433105, "step": 25790, "token_acc": 0.8122832409404954 }, { "epoch": 1.669930647158314, "grad_norm": 0.34012332558631897, "learning_rate": 6.572178302666327e-07, "loss": 0.568700122833252, "step": 25795, "token_acc": 0.8177183264744368 }, { "epoch": 1.6702543477029401, "grad_norm": 0.31458693742752075, "learning_rate": 6.559584845894024e-07, "loss": 0.5840260028839112, "step": 25800, "token_acc": 0.8128755666444109 }, { "epoch": 1.6705780482475663, "grad_norm": 0.3001744747161865, "learning_rate": 6.547002619268344e-07, "loss": 0.570408821105957, "step": 25805, "token_acc": 0.815071271892126 }, { "epoch": 1.6709017487921924, "grad_norm": 0.3652527630329132, "learning_rate": 6.534431626042059e-07, "loss": 0.5894405841827393, "step": 25810, "token_acc": 0.8117334410234031 }, { "epoch": 1.6712254493368186, "grad_norm": 0.3355942368507385, "learning_rate": 6.52187186946498e-07, "loss": 0.5827497959136962, "step": 25815, "token_acc": 0.8133789107610683 }, { "epoch": 1.6715491498814448, "grad_norm": 0.36380329728126526, "learning_rate": 6.509323352784064e-07, "loss": 0.5758859634399414, "step": 25820, "token_acc": 0.8145993038109569 }, { "epoch": 1.671872850426071, "grad_norm": 0.4212072789669037, "learning_rate": 6.496786079243289e-07, "loss": 0.5926262855529785, "step": 25825, "token_acc": 0.8119427351500691 }, { "epoch": 1.672196550970697, "grad_norm": 0.32555994391441345, "learning_rate": 6.484260052083807e-07, "loss": 0.5953402519226074, "step": 25830, "token_acc": 0.8096611985821449 }, { "epoch": 1.6725202515153232, "grad_norm": 0.316803902387619, "learning_rate": 6.471745274543817e-07, "loss": 0.5847869873046875, "step": 25835, "token_acc": 0.8145048535932569 }, { "epoch": 1.6728439520599494, "grad_norm": 0.29933464527130127, "learning_rate": 6.459241749858619e-07, "loss": 0.5694800853729248, "step": 25840, "token_acc": 0.8164741770812579 }, { "epoch": 1.6731676526045756, "grad_norm": 0.40698668360710144, "learning_rate": 6.44674948126059e-07, "loss": 0.5783508777618408, "step": 25845, "token_acc": 0.814166323560217 }, { "epoch": 1.6734913531492017, "grad_norm": 0.40419092774391174, "learning_rate": 6.434268471979243e-07, "loss": 0.6015665531158447, "step": 25850, "token_acc": 0.8090142652229962 }, { "epoch": 1.6738150536938279, "grad_norm": 0.23844140768051147, "learning_rate": 6.421798725241113e-07, "loss": 0.5683472633361817, "step": 25855, "token_acc": 0.81753525365156 }, { "epoch": 1.674138754238454, "grad_norm": 0.3767624497413635, "learning_rate": 6.409340244269885e-07, "loss": 0.5712543964385987, "step": 25860, "token_acc": 0.816639362649464 }, { "epoch": 1.6744624547830802, "grad_norm": 0.3542318642139435, "learning_rate": 6.396893032286283e-07, "loss": 0.5680499076843262, "step": 25865, "token_acc": 0.8160452110591594 }, { "epoch": 1.6747861553277064, "grad_norm": 0.20153935253620148, "learning_rate": 6.384457092508173e-07, "loss": 0.6302687644958496, "step": 25870, "token_acc": 0.8023148463688016 }, { "epoch": 1.6751098558723325, "grad_norm": 0.3430289030075073, "learning_rate": 6.372032428150432e-07, "loss": 0.5906713008880615, "step": 25875, "token_acc": 0.8108500801962449 }, { "epoch": 1.6754335564169587, "grad_norm": 0.3073093295097351, "learning_rate": 6.359619042425102e-07, "loss": 0.6082602977752686, "step": 25880, "token_acc": 0.8067601508251059 }, { "epoch": 1.6757572569615848, "grad_norm": 0.21501301229000092, "learning_rate": 6.347216938541256e-07, "loss": 0.6028924942016601, "step": 25885, "token_acc": 0.8072898956344328 }, { "epoch": 1.676080957506211, "grad_norm": 0.3224959075450897, "learning_rate": 6.334826119705067e-07, "loss": 0.5679169654846191, "step": 25890, "token_acc": 0.81827817377249 }, { "epoch": 1.6764046580508372, "grad_norm": 0.5128288269042969, "learning_rate": 6.322446589119774e-07, "loss": 0.61693115234375, "step": 25895, "token_acc": 0.8040079060836047 }, { "epoch": 1.6767283585954633, "grad_norm": 0.3147132694721222, "learning_rate": 6.310078349985754e-07, "loss": 0.5765877723693847, "step": 25900, "token_acc": 0.8146250981893552 }, { "epoch": 1.6770520591400895, "grad_norm": 0.22939971089363098, "learning_rate": 6.297721405500379e-07, "loss": 0.5952846527099609, "step": 25905, "token_acc": 0.8111755786413364 }, { "epoch": 1.6773757596847156, "grad_norm": 0.3326975703239441, "learning_rate": 6.285375758858176e-07, "loss": 0.5814358711242675, "step": 25910, "token_acc": 0.8133775121543368 }, { "epoch": 1.6776994602293418, "grad_norm": 0.31551724672317505, "learning_rate": 6.273041413250702e-07, "loss": 0.5849785804748535, "step": 25915, "token_acc": 0.8124350286203039 }, { "epoch": 1.678023160773968, "grad_norm": 0.3276600241661072, "learning_rate": 6.260718371866642e-07, "loss": 0.5904737949371338, "step": 25920, "token_acc": 0.8120428321001387 }, { "epoch": 1.6783468613185941, "grad_norm": 0.3842160999774933, "learning_rate": 6.248406637891691e-07, "loss": 0.5825568675994873, "step": 25925, "token_acc": 0.8132992489195705 }, { "epoch": 1.6786705618632203, "grad_norm": 0.3314618766307831, "learning_rate": 6.236106214508686e-07, "loss": 0.5748493194580078, "step": 25930, "token_acc": 0.8168914818222753 }, { "epoch": 1.6789942624078464, "grad_norm": 0.35817912220954895, "learning_rate": 6.2238171048975e-07, "loss": 0.579779052734375, "step": 25935, "token_acc": 0.8124088417659556 }, { "epoch": 1.6793179629524726, "grad_norm": 0.24183310568332672, "learning_rate": 6.211539312235104e-07, "loss": 0.5850948333740235, "step": 25940, "token_acc": 0.8128491224090509 }, { "epoch": 1.6796416634970988, "grad_norm": 0.30391162633895874, "learning_rate": 6.199272839695519e-07, "loss": 0.5760149478912353, "step": 25945, "token_acc": 0.8156486197164823 }, { "epoch": 1.679965364041725, "grad_norm": 0.28278905153274536, "learning_rate": 6.187017690449865e-07, "loss": 0.5973602294921875, "step": 25950, "token_acc": 0.8103222044029742 }, { "epoch": 1.680289064586351, "grad_norm": 0.34497758746147156, "learning_rate": 6.174773867666328e-07, "loss": 0.6314712524414062, "step": 25955, "token_acc": 0.801667247773305 }, { "epoch": 1.6806127651309772, "grad_norm": 0.2826799750328064, "learning_rate": 6.162541374510151e-07, "loss": 0.5971429824829102, "step": 25960, "token_acc": 0.8105248447824959 }, { "epoch": 1.6809364656756034, "grad_norm": 0.37528565526008606, "learning_rate": 6.150320214143662e-07, "loss": 0.5943683624267578, "step": 25965, "token_acc": 0.8106007388906233 }, { "epoch": 1.6812601662202296, "grad_norm": 0.3202539384365082, "learning_rate": 6.13811038972626e-07, "loss": 0.5774868965148926, "step": 25970, "token_acc": 0.8151034769777912 }, { "epoch": 1.6815838667648557, "grad_norm": 0.2661460340023041, "learning_rate": 6.125911904414389e-07, "loss": 0.5827987670898438, "step": 25975, "token_acc": 0.811175128467262 }, { "epoch": 1.6819075673094819, "grad_norm": 0.30818331241607666, "learning_rate": 6.113724761361612e-07, "loss": 0.6054079055786132, "step": 25980, "token_acc": 0.8074438614216342 }, { "epoch": 1.682231267854108, "grad_norm": 0.31025007367134094, "learning_rate": 6.101548963718512e-07, "loss": 0.6198466777801513, "step": 25985, "token_acc": 0.8035179050323394 }, { "epoch": 1.6825549683987342, "grad_norm": 0.35452213883399963, "learning_rate": 6.089384514632768e-07, "loss": 0.5905486106872558, "step": 25990, "token_acc": 0.8096244599534729 }, { "epoch": 1.6828786689433604, "grad_norm": 0.3522798717021942, "learning_rate": 6.077231417249096e-07, "loss": 0.6078499794006348, "step": 25995, "token_acc": 0.8055839543705776 }, { "epoch": 1.6832023694879865, "grad_norm": 0.3925829529762268, "learning_rate": 6.065089674709302e-07, "loss": 0.59164400100708, "step": 26000, "token_acc": 0.8106136691388546 }, { "epoch": 1.6835260700326127, "grad_norm": 0.22651587426662445, "learning_rate": 6.052959290152266e-07, "loss": 0.5848927974700928, "step": 26005, "token_acc": 0.8122720473568632 }, { "epoch": 1.6838497705772388, "grad_norm": 0.297159343957901, "learning_rate": 6.040840266713899e-07, "loss": 0.5869335651397705, "step": 26010, "token_acc": 0.8122817720434574 }, { "epoch": 1.6841734711218652, "grad_norm": 0.37914249300956726, "learning_rate": 6.028732607527194e-07, "loss": 0.5779970169067383, "step": 26015, "token_acc": 0.8147092169082871 }, { "epoch": 1.6844971716664914, "grad_norm": 0.4330170452594757, "learning_rate": 6.016636315722207e-07, "loss": 0.6152782440185547, "step": 26020, "token_acc": 0.8031980574353456 }, { "epoch": 1.6848208722111175, "grad_norm": 0.30823376774787903, "learning_rate": 6.004551394426055e-07, "loss": 0.5870462417602539, "step": 26025, "token_acc": 0.8117852197548592 }, { "epoch": 1.6851445727557437, "grad_norm": 0.3366018831729889, "learning_rate": 5.992477846762896e-07, "loss": 0.5750427722930909, "step": 26030, "token_acc": 0.8162485306042909 }, { "epoch": 1.6854682733003699, "grad_norm": 0.3686620593070984, "learning_rate": 5.980415675853979e-07, "loss": 0.5857184410095215, "step": 26035, "token_acc": 0.8109899897137409 }, { "epoch": 1.685791973844996, "grad_norm": 0.42851242423057556, "learning_rate": 5.968364884817601e-07, "loss": 0.6250300884246827, "step": 26040, "token_acc": 0.8026260030807105 }, { "epoch": 1.6861156743896222, "grad_norm": 0.26339617371559143, "learning_rate": 5.956325476769104e-07, "loss": 0.5870411396026611, "step": 26045, "token_acc": 0.8132924284885372 }, { "epoch": 1.6864393749342483, "grad_norm": 0.3093779683113098, "learning_rate": 5.944297454820891e-07, "loss": 0.5912964820861817, "step": 26050, "token_acc": 0.8103957591453544 }, { "epoch": 1.6867630754788745, "grad_norm": 0.2884688079357147, "learning_rate": 5.932280822082454e-07, "loss": 0.5863903522491455, "step": 26055, "token_acc": 0.8134948788064554 }, { "epoch": 1.6870867760235007, "grad_norm": 0.4219135642051697, "learning_rate": 5.920275581660279e-07, "loss": 0.6101415634155274, "step": 26060, "token_acc": 0.8060823602054594 }, { "epoch": 1.6874104765681268, "grad_norm": 0.367963582277298, "learning_rate": 5.908281736657961e-07, "loss": 0.5947577476501464, "step": 26065, "token_acc": 0.8107644087760276 }, { "epoch": 1.687734177112753, "grad_norm": 0.3121729791164398, "learning_rate": 5.896299290176128e-07, "loss": 0.5741025924682617, "step": 26070, "token_acc": 0.8148366004131158 }, { "epoch": 1.6880578776573791, "grad_norm": 0.31585946679115295, "learning_rate": 5.884328245312459e-07, "loss": 0.5873438835144043, "step": 26075, "token_acc": 0.8117849417528863 }, { "epoch": 1.6883815782020053, "grad_norm": 0.34761810302734375, "learning_rate": 5.872368605161683e-07, "loss": 0.6227782249450684, "step": 26080, "token_acc": 0.8034607961793857 }, { "epoch": 1.6887052787466315, "grad_norm": 0.306565523147583, "learning_rate": 5.860420372815606e-07, "loss": 0.5839948177337646, "step": 26085, "token_acc": 0.8123470682909595 }, { "epoch": 1.6890289792912576, "grad_norm": 0.3611340820789337, "learning_rate": 5.848483551363055e-07, "loss": 0.586191463470459, "step": 26090, "token_acc": 0.8114625908451722 }, { "epoch": 1.6893526798358838, "grad_norm": 0.32434508204460144, "learning_rate": 5.83655814388992e-07, "loss": 0.5929579257965087, "step": 26095, "token_acc": 0.8111176531707824 }, { "epoch": 1.6896763803805102, "grad_norm": 0.30031412839889526, "learning_rate": 5.82464415347912e-07, "loss": 0.5862227439880371, "step": 26100, "token_acc": 0.8136589457384348 }, { "epoch": 1.6900000809251363, "grad_norm": 0.4104633629322052, "learning_rate": 5.812741583210685e-07, "loss": 0.5857406616210937, "step": 26105, "token_acc": 0.8130508300881328 }, { "epoch": 1.6903237814697625, "grad_norm": 0.3693426847457886, "learning_rate": 5.800850436161592e-07, "loss": 0.6035534858703613, "step": 26110, "token_acc": 0.8070049623819433 }, { "epoch": 1.6906474820143886, "grad_norm": 0.3056334853172302, "learning_rate": 5.788970715405967e-07, "loss": 0.6070996761322022, "step": 26115, "token_acc": 0.8072180219695658 }, { "epoch": 1.6909711825590148, "grad_norm": 0.3575038015842438, "learning_rate": 5.777102424014913e-07, "loss": 0.5782311439514161, "step": 26120, "token_acc": 0.8154609425154105 }, { "epoch": 1.691294883103641, "grad_norm": 0.2801712453365326, "learning_rate": 5.765245565056616e-07, "loss": 0.6049066543579101, "step": 26125, "token_acc": 0.8072942687888088 }, { "epoch": 1.6916185836482671, "grad_norm": 0.3117503523826599, "learning_rate": 5.753400141596265e-07, "loss": 0.588124418258667, "step": 26130, "token_acc": 0.8129093323000108 }, { "epoch": 1.6919422841928933, "grad_norm": 0.3853572607040405, "learning_rate": 5.741566156696154e-07, "loss": 0.5849231719970703, "step": 26135, "token_acc": 0.8121632123520383 }, { "epoch": 1.6922659847375194, "grad_norm": 0.34836697578430176, "learning_rate": 5.729743613415573e-07, "loss": 0.5767227649688721, "step": 26140, "token_acc": 0.8155766285397725 }, { "epoch": 1.6925896852821456, "grad_norm": 0.33091166615486145, "learning_rate": 5.717932514810864e-07, "loss": 0.6002103805541992, "step": 26145, "token_acc": 0.808795266985718 }, { "epoch": 1.6929133858267718, "grad_norm": 0.32685691118240356, "learning_rate": 5.706132863935404e-07, "loss": 0.5857059478759765, "step": 26150, "token_acc": 0.8131740876262522 }, { "epoch": 1.693237086371398, "grad_norm": 0.3869569003582001, "learning_rate": 5.694344663839646e-07, "loss": 0.6021197319030762, "step": 26155, "token_acc": 0.8080444032805809 }, { "epoch": 1.693560786916024, "grad_norm": 0.28792604804039, "learning_rate": 5.682567917571025e-07, "loss": 0.594820213317871, "step": 26160, "token_acc": 0.8101698683160937 }, { "epoch": 1.6938844874606502, "grad_norm": 0.338572233915329, "learning_rate": 5.670802628174071e-07, "loss": 0.5890113830566406, "step": 26165, "token_acc": 0.811749151764936 }, { "epoch": 1.6942081880052764, "grad_norm": 0.2851116359233856, "learning_rate": 5.659048798690309e-07, "loss": 0.5922494888305664, "step": 26170, "token_acc": 0.8101685819742939 }, { "epoch": 1.6945318885499026, "grad_norm": 0.2636878490447998, "learning_rate": 5.647306432158351e-07, "loss": 0.5917437553405762, "step": 26175, "token_acc": 0.8114460711470622 }, { "epoch": 1.6948555890945287, "grad_norm": 0.29410484433174133, "learning_rate": 5.635575531613774e-07, "loss": 0.5622054100036621, "step": 26180, "token_acc": 0.8178799260716628 }, { "epoch": 1.6951792896391549, "grad_norm": 0.2649955451488495, "learning_rate": 5.623856100089265e-07, "loss": 0.5887691497802734, "step": 26185, "token_acc": 0.8124338244837456 }, { "epoch": 1.695502990183781, "grad_norm": 0.2868882715702057, "learning_rate": 5.612148140614492e-07, "loss": 0.5558265209197998, "step": 26190, "token_acc": 0.8201289262078398 }, { "epoch": 1.6958266907284072, "grad_norm": 0.44211268424987793, "learning_rate": 5.600451656216193e-07, "loss": 0.556718397140503, "step": 26195, "token_acc": 0.8196869909165245 }, { "epoch": 1.6961503912730334, "grad_norm": 0.3663857877254486, "learning_rate": 5.588766649918115e-07, "loss": 0.5900873661041259, "step": 26200, "token_acc": 0.8122633225399265 }, { "epoch": 1.6964740918176595, "grad_norm": 0.238418847322464, "learning_rate": 5.577093124741045e-07, "loss": 0.593217420578003, "step": 26205, "token_acc": 0.8091849935316947 }, { "epoch": 1.6967977923622857, "grad_norm": 0.3059323728084564, "learning_rate": 5.565431083702804e-07, "loss": 0.5931234359741211, "step": 26210, "token_acc": 0.8102058602960551 }, { "epoch": 1.6971214929069118, "grad_norm": 0.2824782133102417, "learning_rate": 5.553780529818253e-07, "loss": 0.5853814125061035, "step": 26215, "token_acc": 0.812539116183938 }, { "epoch": 1.697445193451538, "grad_norm": 0.31067168712615967, "learning_rate": 5.542141466099271e-07, "loss": 0.58781418800354, "step": 26220, "token_acc": 0.8131590982459916 }, { "epoch": 1.6977688939961642, "grad_norm": 0.33321186900138855, "learning_rate": 5.530513895554773e-07, "loss": 0.6037957191467285, "step": 26225, "token_acc": 0.8074300656858869 }, { "epoch": 1.6980925945407903, "grad_norm": 0.4063720107078552, "learning_rate": 5.518897821190694e-07, "loss": 0.5929387092590332, "step": 26230, "token_acc": 0.8113433455602463 }, { "epoch": 1.6984162950854165, "grad_norm": 0.2943022847175598, "learning_rate": 5.507293246009992e-07, "loss": 0.5807674407958985, "step": 26235, "token_acc": 0.8145936981757878 }, { "epoch": 1.6987399956300426, "grad_norm": 0.30299586057662964, "learning_rate": 5.495700173012686e-07, "loss": 0.6068077087402344, "step": 26240, "token_acc": 0.8073950510736414 }, { "epoch": 1.6990636961746688, "grad_norm": 0.26577919721603394, "learning_rate": 5.484118605195793e-07, "loss": 0.590302848815918, "step": 26245, "token_acc": 0.8103410953397038 }, { "epoch": 1.699387396719295, "grad_norm": 0.35257965326309204, "learning_rate": 5.472548545553358e-07, "loss": 0.5880874156951904, "step": 26250, "token_acc": 0.811020914521501 }, { "epoch": 1.6997110972639211, "grad_norm": 0.28780776262283325, "learning_rate": 5.460989997076449e-07, "loss": 0.5883055686950683, "step": 26255, "token_acc": 0.8119588631783754 }, { "epoch": 1.7000347978085473, "grad_norm": 0.3505170941352844, "learning_rate": 5.449442962753171e-07, "loss": 0.5942781448364258, "step": 26260, "token_acc": 0.8102736297655794 }, { "epoch": 1.7003584983531734, "grad_norm": 0.3599714934825897, "learning_rate": 5.437907445568629e-07, "loss": 0.5968554496765137, "step": 26265, "token_acc": 0.8098611174118455 }, { "epoch": 1.7006821988977996, "grad_norm": 0.3457060754299164, "learning_rate": 5.426383448504991e-07, "loss": 0.5797337532043457, "step": 26270, "token_acc": 0.812813188707354 }, { "epoch": 1.7010058994424258, "grad_norm": 0.31229519844055176, "learning_rate": 5.414870974541409e-07, "loss": 0.5933858394622803, "step": 26275, "token_acc": 0.8105903711672943 }, { "epoch": 1.701329599987052, "grad_norm": 0.34883615374565125, "learning_rate": 5.40337002665407e-07, "loss": 0.6004210948944092, "step": 26280, "token_acc": 0.8082875791360861 }, { "epoch": 1.701653300531678, "grad_norm": 0.34604281187057495, "learning_rate": 5.391880607816175e-07, "loss": 0.5951682090759277, "step": 26285, "token_acc": 0.8092902306767099 }, { "epoch": 1.7019770010763042, "grad_norm": 0.31449222564697266, "learning_rate": 5.380402720997979e-07, "loss": 0.5503500461578369, "step": 26290, "token_acc": 0.8209226578610938 }, { "epoch": 1.7023007016209304, "grad_norm": 0.2975345253944397, "learning_rate": 5.368936369166677e-07, "loss": 0.6081855297088623, "step": 26295, "token_acc": 0.8073360789309947 }, { "epoch": 1.7026244021655565, "grad_norm": 0.4247555434703827, "learning_rate": 5.357481555286575e-07, "loss": 0.5717340469360351, "step": 26300, "token_acc": 0.8161457682621304 }, { "epoch": 1.7029481027101827, "grad_norm": 0.2969509959220886, "learning_rate": 5.346038282318927e-07, "loss": 0.5818387508392334, "step": 26305, "token_acc": 0.814758827282057 }, { "epoch": 1.7032718032548089, "grad_norm": 0.2923595905303955, "learning_rate": 5.33460655322206e-07, "loss": 0.6095078468322754, "step": 26310, "token_acc": 0.8061549501460369 }, { "epoch": 1.703595503799435, "grad_norm": 0.32764166593551636, "learning_rate": 5.32318637095125e-07, "loss": 0.5849687099456787, "step": 26315, "token_acc": 0.8119899203924897 }, { "epoch": 1.7039192043440612, "grad_norm": 0.33757176995277405, "learning_rate": 5.311777738458845e-07, "loss": 0.5927643299102783, "step": 26320, "token_acc": 0.8112253497387494 }, { "epoch": 1.7042429048886873, "grad_norm": 0.3566299378871918, "learning_rate": 5.300380658694188e-07, "loss": 0.598874568939209, "step": 26325, "token_acc": 0.809561008093433 }, { "epoch": 1.7045666054333135, "grad_norm": 0.4306016266345978, "learning_rate": 5.288995134603625e-07, "loss": 0.5942813396453858, "step": 26330, "token_acc": 0.8085773624091381 }, { "epoch": 1.7048903059779397, "grad_norm": 0.3339928388595581, "learning_rate": 5.277621169130515e-07, "loss": 0.5727072715759277, "step": 26335, "token_acc": 0.8160416752235046 }, { "epoch": 1.7052140065225658, "grad_norm": 0.3063465356826782, "learning_rate": 5.266258765215271e-07, "loss": 0.5916549682617187, "step": 26340, "token_acc": 0.8097124206660367 }, { "epoch": 1.705537707067192, "grad_norm": 0.396269291639328, "learning_rate": 5.254907925795244e-07, "loss": 0.5849263191223144, "step": 26345, "token_acc": 0.811929131615427 }, { "epoch": 1.7058614076118181, "grad_norm": 0.41033411026000977, "learning_rate": 5.24356865380486e-07, "loss": 0.6005241394042968, "step": 26350, "token_acc": 0.8085885026301584 }, { "epoch": 1.7061851081564443, "grad_norm": 0.3905329704284668, "learning_rate": 5.232240952175511e-07, "loss": 0.5882457256317138, "step": 26355, "token_acc": 0.8120582585830707 }, { "epoch": 1.7065088087010707, "grad_norm": 0.37664732336997986, "learning_rate": 5.220924823835649e-07, "loss": 0.583552360534668, "step": 26360, "token_acc": 0.8138848944921914 }, { "epoch": 1.7068325092456968, "grad_norm": 0.2975994944572449, "learning_rate": 5.209620271710658e-07, "loss": 0.577974271774292, "step": 26365, "token_acc": 0.813910877531592 }, { "epoch": 1.707156209790323, "grad_norm": 0.3810698091983795, "learning_rate": 5.198327298723005e-07, "loss": 0.5766805648803711, "step": 26370, "token_acc": 0.8138253907551104 }, { "epoch": 1.7074799103349492, "grad_norm": 0.4163629710674286, "learning_rate": 5.187045907792121e-07, "loss": 0.5812359809875488, "step": 26375, "token_acc": 0.8142677320870975 }, { "epoch": 1.7078036108795753, "grad_norm": 0.30234524607658386, "learning_rate": 5.175776101834451e-07, "loss": 0.5875478267669678, "step": 26380, "token_acc": 0.813101251994518 }, { "epoch": 1.7081273114242015, "grad_norm": 0.41532421112060547, "learning_rate": 5.164517883763442e-07, "loss": 0.5704213142395019, "step": 26385, "token_acc": 0.8160823100713477 }, { "epoch": 1.7084510119688276, "grad_norm": 0.2681915760040283, "learning_rate": 5.153271256489578e-07, "loss": 0.5764833927154541, "step": 26390, "token_acc": 0.8145249897792314 }, { "epoch": 1.7087747125134538, "grad_norm": 0.3457813262939453, "learning_rate": 5.142036222920277e-07, "loss": 0.6021921157836914, "step": 26395, "token_acc": 0.8073973215460309 }, { "epoch": 1.70909841305808, "grad_norm": 0.3058505952358246, "learning_rate": 5.130812785960032e-07, "loss": 0.5847784042358398, "step": 26400, "token_acc": 0.8122008554776012 }, { "epoch": 1.7094221136027061, "grad_norm": 0.3512451648712158, "learning_rate": 5.119600948510289e-07, "loss": 0.6078359603881835, "step": 26405, "token_acc": 0.8069258036174145 }, { "epoch": 1.7097458141473323, "grad_norm": 0.28287655115127563, "learning_rate": 5.108400713469547e-07, "loss": 0.5951324462890625, "step": 26410, "token_acc": 0.8089700662287206 }, { "epoch": 1.7100695146919584, "grad_norm": 0.4037237763404846, "learning_rate": 5.097212083733232e-07, "loss": 0.5875383377075195, "step": 26415, "token_acc": 0.8133758318651834 }, { "epoch": 1.7103932152365846, "grad_norm": 0.37608325481414795, "learning_rate": 5.08603506219384e-07, "loss": 0.604975700378418, "step": 26420, "token_acc": 0.8063135581850868 }, { "epoch": 1.7107169157812108, "grad_norm": 0.28585565090179443, "learning_rate": 5.074869651740822e-07, "loss": 0.5918137550354003, "step": 26425, "token_acc": 0.810520936471941 }, { "epoch": 1.711040616325837, "grad_norm": 0.2995033264160156, "learning_rate": 5.063715855260648e-07, "loss": 0.5826369762420655, "step": 26430, "token_acc": 0.8134694343065694 }, { "epoch": 1.711364316870463, "grad_norm": 0.33279871940612793, "learning_rate": 5.052573675636768e-07, "loss": 0.5751862525939941, "step": 26435, "token_acc": 0.8158316202865646 }, { "epoch": 1.7116880174150892, "grad_norm": 0.36960744857788086, "learning_rate": 5.041443115749655e-07, "loss": 0.580727481842041, "step": 26440, "token_acc": 0.8148663643535652 }, { "epoch": 1.7120117179597156, "grad_norm": 0.3772326409816742, "learning_rate": 5.030324178476764e-07, "loss": 0.5898763179779053, "step": 26445, "token_acc": 0.8110306134266706 }, { "epoch": 1.7123354185043418, "grad_norm": 0.2918410897254944, "learning_rate": 5.019216866692539e-07, "loss": 0.5603340148925782, "step": 26450, "token_acc": 0.8188752787292933 }, { "epoch": 1.712659119048968, "grad_norm": 0.31844162940979004, "learning_rate": 5.008121183268428e-07, "loss": 0.6189053535461426, "step": 26455, "token_acc": 0.8037600917850933 }, { "epoch": 1.712982819593594, "grad_norm": 0.33439305424690247, "learning_rate": 4.997037131072862e-07, "loss": 0.5937745571136475, "step": 26460, "token_acc": 0.8100743855109961 }, { "epoch": 1.7133065201382203, "grad_norm": 0.35881340503692627, "learning_rate": 4.98596471297127e-07, "loss": 0.5547676086425781, "step": 26465, "token_acc": 0.8204359249728138 }, { "epoch": 1.7136302206828464, "grad_norm": 0.4682762324810028, "learning_rate": 4.974903931826092e-07, "loss": 0.5763650417327881, "step": 26470, "token_acc": 0.8148900238617794 }, { "epoch": 1.7139539212274726, "grad_norm": 0.26613306999206543, "learning_rate": 4.963854790496731e-07, "loss": 0.5957179546356202, "step": 26475, "token_acc": 0.810004331982774 }, { "epoch": 1.7142776217720987, "grad_norm": 0.2839241921901703, "learning_rate": 4.952817291839595e-07, "loss": 0.5979688167572021, "step": 26480, "token_acc": 0.809330429835403 }, { "epoch": 1.714601322316725, "grad_norm": 0.3053862452507019, "learning_rate": 4.941791438708087e-07, "loss": 0.6087169647216797, "step": 26485, "token_acc": 0.8069279234878052 }, { "epoch": 1.714925022861351, "grad_norm": 0.3096465468406677, "learning_rate": 4.930777233952577e-07, "loss": 0.5856787681579589, "step": 26490, "token_acc": 0.8132073519330514 }, { "epoch": 1.7152487234059772, "grad_norm": 0.4073527157306671, "learning_rate": 4.919774680420469e-07, "loss": 0.5744293689727783, "step": 26495, "token_acc": 0.8136860539889723 }, { "epoch": 1.7155724239506034, "grad_norm": 0.33995112776756287, "learning_rate": 4.908783780956089e-07, "loss": 0.5990978717803955, "step": 26500, "token_acc": 0.8088873034525208 }, { "epoch": 1.7158961244952295, "grad_norm": 0.2922038435935974, "learning_rate": 4.897804538400813e-07, "loss": 0.5843185901641845, "step": 26505, "token_acc": 0.8145757609617268 }, { "epoch": 1.7162198250398557, "grad_norm": 0.30019843578338623, "learning_rate": 4.886836955592966e-07, "loss": 0.5857113361358642, "step": 26510, "token_acc": 0.8125837936397275 }, { "epoch": 1.7165435255844819, "grad_norm": 0.28843122720718384, "learning_rate": 4.87588103536788e-07, "loss": 0.5717208862304688, "step": 26515, "token_acc": 0.8154968009660483 }, { "epoch": 1.716867226129108, "grad_norm": 0.4371696710586548, "learning_rate": 4.864936780557839e-07, "loss": 0.5915140151977539, "step": 26520, "token_acc": 0.8114804445795051 }, { "epoch": 1.7171909266737342, "grad_norm": 0.2517262399196625, "learning_rate": 4.854004193992173e-07, "loss": 0.5808851718902588, "step": 26525, "token_acc": 0.8136562007516063 }, { "epoch": 1.7175146272183603, "grad_norm": 0.3835810422897339, "learning_rate": 4.843083278497113e-07, "loss": 0.5892891407012939, "step": 26530, "token_acc": 0.8116671247260453 }, { "epoch": 1.7178383277629865, "grad_norm": 0.2834964394569397, "learning_rate": 4.832174036895948e-07, "loss": 0.5932900905609131, "step": 26535, "token_acc": 0.8114511532747156 }, { "epoch": 1.7181620283076127, "grad_norm": 0.26055532693862915, "learning_rate": 4.821276472008896e-07, "loss": 0.5864656448364258, "step": 26540, "token_acc": 0.8117205770887724 }, { "epoch": 1.7184857288522388, "grad_norm": 0.3086312413215637, "learning_rate": 4.810390586653207e-07, "loss": 0.5723962306976318, "step": 26545, "token_acc": 0.8145533094754489 }, { "epoch": 1.718809429396865, "grad_norm": 0.3041117787361145, "learning_rate": 4.799516383643049e-07, "loss": 0.5959522724151611, "step": 26550, "token_acc": 0.8104550296758484 }, { "epoch": 1.7191331299414911, "grad_norm": 0.4283868074417114, "learning_rate": 4.788653865789633e-07, "loss": 0.5990625381469726, "step": 26555, "token_acc": 0.809215216948462 }, { "epoch": 1.7194568304861173, "grad_norm": 0.2862222492694855, "learning_rate": 4.777803035901102e-07, "loss": 0.6126433372497558, "step": 26560, "token_acc": 0.8057951088029296 }, { "epoch": 1.7197805310307435, "grad_norm": 0.3406398594379425, "learning_rate": 4.7669638967825947e-07, "loss": 0.5653433322906494, "step": 26565, "token_acc": 0.8173338885253703 }, { "epoch": 1.7201042315753696, "grad_norm": 0.29418161511421204, "learning_rate": 4.756136451236232e-07, "loss": 0.6158867359161377, "step": 26570, "token_acc": 0.805808217287812 }, { "epoch": 1.7204279321199958, "grad_norm": 0.3858615756034851, "learning_rate": 4.7453207020611127e-07, "loss": 0.6064098358154297, "step": 26575, "token_acc": 0.8073651780071625 }, { "epoch": 1.720751632664622, "grad_norm": 0.32602083683013916, "learning_rate": 4.734516652053306e-07, "loss": 0.5843301773071289, "step": 26580, "token_acc": 0.8121640282093012 }, { "epoch": 1.721075333209248, "grad_norm": 0.37054479122161865, "learning_rate": 4.72372430400585e-07, "loss": 0.5898407459259033, "step": 26585, "token_acc": 0.8107955051604118 }, { "epoch": 1.7213990337538743, "grad_norm": 0.33901914954185486, "learning_rate": 4.712943660708763e-07, "loss": 0.6071171760559082, "step": 26590, "token_acc": 0.8076661374461329 }, { "epoch": 1.7217227342985004, "grad_norm": 0.3263348639011383, "learning_rate": 4.7021747249490655e-07, "loss": 0.5985137939453125, "step": 26595, "token_acc": 0.8089540018130246 }, { "epoch": 1.7220464348431266, "grad_norm": 0.2975483536720276, "learning_rate": 4.6914174995106863e-07, "loss": 0.5693036079406738, "step": 26600, "token_acc": 0.8176736448758173 }, { "epoch": 1.7223701353877527, "grad_norm": 0.39752280712127686, "learning_rate": 4.6806719871745955e-07, "loss": 0.6062446117401123, "step": 26605, "token_acc": 0.8074048643937993 }, { "epoch": 1.722693835932379, "grad_norm": 0.2880259156227112, "learning_rate": 4.669938190718698e-07, "loss": 0.5869193553924561, "step": 26610, "token_acc": 0.812155924665611 }, { "epoch": 1.723017536477005, "grad_norm": 0.30083727836608887, "learning_rate": 4.6592161129178803e-07, "loss": 0.5864467620849609, "step": 26615, "token_acc": 0.8116564187162567 }, { "epoch": 1.7233412370216312, "grad_norm": 0.3197925090789795, "learning_rate": 4.648505756543975e-07, "loss": 0.6047249794006347, "step": 26620, "token_acc": 0.8059578530282919 }, { "epoch": 1.7236649375662574, "grad_norm": 0.3687504529953003, "learning_rate": 4.6378071243658395e-07, "loss": 0.6115413188934327, "step": 26625, "token_acc": 0.8044481108727932 }, { "epoch": 1.7239886381108835, "grad_norm": 0.29924067854881287, "learning_rate": 4.6271202191492504e-07, "loss": 0.5801466464996338, "step": 26630, "token_acc": 0.8131535811059445 }, { "epoch": 1.7243123386555097, "grad_norm": 0.2846754193305969, "learning_rate": 4.61644504365697e-07, "loss": 0.6058863639831543, "step": 26635, "token_acc": 0.8069112247349096 }, { "epoch": 1.7246360392001359, "grad_norm": 0.3164573907852173, "learning_rate": 4.6057816006487177e-07, "loss": 0.6124056339263916, "step": 26640, "token_acc": 0.8059950456225959 }, { "epoch": 1.724959739744762, "grad_norm": 0.3848240077495575, "learning_rate": 4.595129892881217e-07, "loss": 0.5705453872680664, "step": 26645, "token_acc": 0.8166731048154924 }, { "epoch": 1.7252834402893882, "grad_norm": 0.36336106061935425, "learning_rate": 4.584489923108099e-07, "loss": 0.5862920761108399, "step": 26650, "token_acc": 0.8110063343356448 }, { "epoch": 1.7256071408340143, "grad_norm": 0.3086474537849426, "learning_rate": 4.573861694080012e-07, "loss": 0.588480281829834, "step": 26655, "token_acc": 0.8121390923857195 }, { "epoch": 1.7259308413786405, "grad_norm": 0.2791953682899475, "learning_rate": 4.563245208544548e-07, "loss": 0.6078633785247802, "step": 26660, "token_acc": 0.8061412137022623 }, { "epoch": 1.7262545419232667, "grad_norm": 0.3129325807094574, "learning_rate": 4.5526404692462553e-07, "loss": 0.5696497440338135, "step": 26665, "token_acc": 0.8153939821193963 }, { "epoch": 1.7265782424678928, "grad_norm": 0.46650126576423645, "learning_rate": 4.542047478926648e-07, "loss": 0.5938384056091308, "step": 26670, "token_acc": 0.8099940174438742 }, { "epoch": 1.726901943012519, "grad_norm": 0.367349237203598, "learning_rate": 4.531466240324228e-07, "loss": 0.5507253170013428, "step": 26675, "token_acc": 0.822342783879545 }, { "epoch": 1.7272256435571451, "grad_norm": 0.2430969923734665, "learning_rate": 4.520896756174431e-07, "loss": 0.5903034210205078, "step": 26680, "token_acc": 0.8103425913916733 }, { "epoch": 1.7275493441017713, "grad_norm": 0.4312872886657715, "learning_rate": 4.510339029209665e-07, "loss": 0.5992761611938476, "step": 26685, "token_acc": 0.8087688368644992 }, { "epoch": 1.7278730446463975, "grad_norm": 0.3374977707862854, "learning_rate": 4.499793062159291e-07, "loss": 0.5674622535705567, "step": 26690, "token_acc": 0.8169198977444743 }, { "epoch": 1.7281967451910236, "grad_norm": 0.3454602062702179, "learning_rate": 4.48925885774964e-07, "loss": 0.6071202278137207, "step": 26695, "token_acc": 0.807983959414088 }, { "epoch": 1.72852044573565, "grad_norm": 0.3895387053489685, "learning_rate": 4.4787364187039885e-07, "loss": 0.5865323543548584, "step": 26700, "token_acc": 0.8120449541408329 }, { "epoch": 1.7288441462802762, "grad_norm": 0.3272707760334015, "learning_rate": 4.4682257477425995e-07, "loss": 0.5967840671539306, "step": 26705, "token_acc": 0.8113142282816549 }, { "epoch": 1.7291678468249023, "grad_norm": 0.33173668384552, "learning_rate": 4.4577268475826664e-07, "loss": 0.5702534675598144, "step": 26710, "token_acc": 0.8168366046393066 }, { "epoch": 1.7294915473695285, "grad_norm": 0.46480247378349304, "learning_rate": 4.44723972093834e-07, "loss": 0.5943528652191162, "step": 26715, "token_acc": 0.8094416344341961 }, { "epoch": 1.7298152479141546, "grad_norm": 0.31051990389823914, "learning_rate": 4.4367643705207464e-07, "loss": 0.6013420581817627, "step": 26720, "token_acc": 0.8093429040510098 }, { "epoch": 1.7301389484587808, "grad_norm": 0.37315237522125244, "learning_rate": 4.426300799037941e-07, "loss": 0.5827752113342285, "step": 26725, "token_acc": 0.8142937036228721 }, { "epoch": 1.730462649003407, "grad_norm": 0.4302106499671936, "learning_rate": 4.4158490091949667e-07, "loss": 0.5894743442535401, "step": 26730, "token_acc": 0.8114904298713523 }, { "epoch": 1.7307863495480331, "grad_norm": 0.34525930881500244, "learning_rate": 4.4054090036938004e-07, "loss": 0.5910903930664062, "step": 26735, "token_acc": 0.8105311942959001 }, { "epoch": 1.7311100500926593, "grad_norm": 0.29770219326019287, "learning_rate": 4.3949807852333714e-07, "loss": 0.5822895050048829, "step": 26740, "token_acc": 0.8122200209471652 }, { "epoch": 1.7314337506372854, "grad_norm": 0.359533429145813, "learning_rate": 4.384564356509563e-07, "loss": 0.5763926029205322, "step": 26745, "token_acc": 0.814364118780213 }, { "epoch": 1.7317574511819116, "grad_norm": 0.34353145956993103, "learning_rate": 4.374159720215221e-07, "loss": 0.5976805686950684, "step": 26750, "token_acc": 0.8087123325892858 }, { "epoch": 1.7320811517265378, "grad_norm": 0.32696568965911865, "learning_rate": 4.363766879040127e-07, "loss": 0.6005486011505127, "step": 26755, "token_acc": 0.8103724690760832 }, { "epoch": 1.732404852271164, "grad_norm": 0.3271806538105011, "learning_rate": 4.3533858356710314e-07, "loss": 0.5775916099548339, "step": 26760, "token_acc": 0.8141065964736562 }, { "epoch": 1.73272855281579, "grad_norm": 0.23836749792099, "learning_rate": 4.3430165927916157e-07, "loss": 0.5937222480773926, "step": 26765, "token_acc": 0.8098610893109403 }, { "epoch": 1.7330522533604162, "grad_norm": 0.43946829438209534, "learning_rate": 4.33265915308253e-07, "loss": 0.5865724086761475, "step": 26770, "token_acc": 0.813247927245994 }, { "epoch": 1.7333759539050424, "grad_norm": 0.27646440267562866, "learning_rate": 4.322313519221344e-07, "loss": 0.5792046070098877, "step": 26775, "token_acc": 0.8127514003232961 }, { "epoch": 1.7336996544496686, "grad_norm": 0.333003968000412, "learning_rate": 4.3119796938826284e-07, "loss": 0.6006495475769043, "step": 26780, "token_acc": 0.8075726596082083 }, { "epoch": 1.734023354994295, "grad_norm": 0.23536382615566254, "learning_rate": 4.3016576797378305e-07, "loss": 0.5597051620483399, "step": 26785, "token_acc": 0.8173303296633563 }, { "epoch": 1.734347055538921, "grad_norm": 0.31830593943595886, "learning_rate": 4.2913474794554044e-07, "loss": 0.5882625579833984, "step": 26790, "token_acc": 0.8129004569742982 }, { "epoch": 1.7346707560835473, "grad_norm": 0.3822577893733978, "learning_rate": 4.281049095700718e-07, "loss": 0.5822860717773437, "step": 26795, "token_acc": 0.8140160533511844 }, { "epoch": 1.7349944566281734, "grad_norm": 0.3117934763431549, "learning_rate": 4.2707625311360967e-07, "loss": 0.5898955345153809, "step": 26800, "token_acc": 0.8117923533861627 }, { "epoch": 1.7353181571727996, "grad_norm": 0.2882404029369354, "learning_rate": 4.260487788420792e-07, "loss": 0.5708210945129395, "step": 26805, "token_acc": 0.8151110241885351 }, { "epoch": 1.7356418577174257, "grad_norm": 0.3085901141166687, "learning_rate": 4.250224870211034e-07, "loss": 0.5726735591888428, "step": 26810, "token_acc": 0.8160595126615021 }, { "epoch": 1.735965558262052, "grad_norm": 0.35520848631858826, "learning_rate": 4.2399737791599726e-07, "loss": 0.5901047706604003, "step": 26815, "token_acc": 0.8107732406602954 }, { "epoch": 1.736289258806678, "grad_norm": 0.24191240966320038, "learning_rate": 4.2297345179177e-07, "loss": 0.5796380043029785, "step": 26820, "token_acc": 0.8144862323707186 }, { "epoch": 1.7366129593513042, "grad_norm": 0.384895920753479, "learning_rate": 4.219507089131236e-07, "loss": 0.5756957054138183, "step": 26825, "token_acc": 0.81418990469467 }, { "epoch": 1.7369366598959304, "grad_norm": 0.27853935956954956, "learning_rate": 4.2092914954446005e-07, "loss": 0.5744770050048829, "step": 26830, "token_acc": 0.8168292879606484 }, { "epoch": 1.7372603604405565, "grad_norm": 0.3297410309314728, "learning_rate": 4.199087739498664e-07, "loss": 0.6015499114990235, "step": 26835, "token_acc": 0.8079732001899603 }, { "epoch": 1.7375840609851827, "grad_norm": 0.39967191219329834, "learning_rate": 4.1888958239313216e-07, "loss": 0.6007414817810058, "step": 26840, "token_acc": 0.8073932641773124 }, { "epoch": 1.7379077615298089, "grad_norm": 0.31301331520080566, "learning_rate": 4.1787157513773493e-07, "loss": 0.5951060771942138, "step": 26845, "token_acc": 0.8081291688272942 }, { "epoch": 1.738231462074435, "grad_norm": 0.2948305308818817, "learning_rate": 4.168547524468508e-07, "loss": 0.5984262466430664, "step": 26850, "token_acc": 0.8096940938367497 }, { "epoch": 1.7385551626190612, "grad_norm": 0.39740103483200073, "learning_rate": 4.1583911458334403e-07, "loss": 0.5788794040679932, "step": 26855, "token_acc": 0.8125559824041083 }, { "epoch": 1.7388788631636873, "grad_norm": 0.39075344800949097, "learning_rate": 4.1482466180977787e-07, "loss": 0.5850120067596436, "step": 26860, "token_acc": 0.812569287548589 }, { "epoch": 1.7392025637083135, "grad_norm": 0.46673956513404846, "learning_rate": 4.1381139438840643e-07, "loss": 0.575562572479248, "step": 26865, "token_acc": 0.8154421399124349 }, { "epoch": 1.7395262642529397, "grad_norm": 0.3680770993232727, "learning_rate": 4.12799312581178e-07, "loss": 0.5745129585266113, "step": 26870, "token_acc": 0.8140209128503795 }, { "epoch": 1.7398499647975658, "grad_norm": 0.35913124680519104, "learning_rate": 4.1178841664973323e-07, "loss": 0.5905661582946777, "step": 26875, "token_acc": 0.8104980559155712 }, { "epoch": 1.740173665342192, "grad_norm": 0.3202543556690216, "learning_rate": 4.107787068554103e-07, "loss": 0.5703462600708008, "step": 26880, "token_acc": 0.8149016811768238 }, { "epoch": 1.7404973658868181, "grad_norm": 0.38632577657699585, "learning_rate": 4.097701834592338e-07, "loss": 0.5773104667663574, "step": 26885, "token_acc": 0.8151528678121481 }, { "epoch": 1.7408210664314443, "grad_norm": 0.43193933367729187, "learning_rate": 4.08762846721929e-07, "loss": 0.5818793773651123, "step": 26890, "token_acc": 0.8132615471805044 }, { "epoch": 1.7411447669760705, "grad_norm": 0.38464269042015076, "learning_rate": 4.0775669690390816e-07, "loss": 0.5987610816955566, "step": 26895, "token_acc": 0.8085771345575267 }, { "epoch": 1.7414684675206966, "grad_norm": 0.3928433060646057, "learning_rate": 4.0675173426528326e-07, "loss": 0.5806583404541016, "step": 26900, "token_acc": 0.8140655302643667 }, { "epoch": 1.7417921680653228, "grad_norm": 0.4904243052005768, "learning_rate": 4.057479590658514e-07, "loss": 0.6182785987854004, "step": 26905, "token_acc": 0.8058865471456926 }, { "epoch": 1.742115868609949, "grad_norm": 0.30637118220329285, "learning_rate": 4.0474537156510953e-07, "loss": 0.5993210315704346, "step": 26910, "token_acc": 0.8091224307417337 }, { "epoch": 1.742439569154575, "grad_norm": 0.37373533844947815, "learning_rate": 4.0374397202224467e-07, "loss": 0.5764901161193847, "step": 26915, "token_acc": 0.8133489238466872 }, { "epoch": 1.7427632696992013, "grad_norm": 0.4160601496696472, "learning_rate": 4.027437606961365e-07, "loss": 0.5939919471740722, "step": 26920, "token_acc": 0.8109680309862412 }, { "epoch": 1.7430869702438274, "grad_norm": 0.34814852476119995, "learning_rate": 4.0174473784535707e-07, "loss": 0.5948063850402832, "step": 26925, "token_acc": 0.8089493231100995 }, { "epoch": 1.7434106707884536, "grad_norm": 0.3700987696647644, "learning_rate": 4.007469037281747e-07, "loss": 0.5656116485595704, "step": 26930, "token_acc": 0.8171185212528882 }, { "epoch": 1.7437343713330797, "grad_norm": 0.3412301242351532, "learning_rate": 3.9975025860254647e-07, "loss": 0.610438871383667, "step": 26935, "token_acc": 0.8059203411303031 }, { "epoch": 1.744058071877706, "grad_norm": 0.3565872609615326, "learning_rate": 3.9875480272612285e-07, "loss": 0.573479413986206, "step": 26940, "token_acc": 0.8152857020643727 }, { "epoch": 1.744381772422332, "grad_norm": 0.47770699858665466, "learning_rate": 3.977605363562487e-07, "loss": 0.6037470817565918, "step": 26945, "token_acc": 0.8067738883632923 }, { "epoch": 1.7447054729669582, "grad_norm": 0.33201202750205994, "learning_rate": 3.9676745974995987e-07, "loss": 0.5937537670135498, "step": 26950, "token_acc": 0.8106158224890613 }, { "epoch": 1.7450291735115844, "grad_norm": 0.2898240387439728, "learning_rate": 3.95775573163984e-07, "loss": 0.5788678169250489, "step": 26955, "token_acc": 0.8135236001316369 }, { "epoch": 1.7453528740562105, "grad_norm": 0.3362790644168854, "learning_rate": 3.9478487685474243e-07, "loss": 0.5781646728515625, "step": 26960, "token_acc": 0.8139212155245306 }, { "epoch": 1.7456765746008367, "grad_norm": 0.37121549248695374, "learning_rate": 3.937953710783493e-07, "loss": 0.5941207885742188, "step": 26965, "token_acc": 0.8107435124367395 }, { "epoch": 1.7460002751454629, "grad_norm": 0.26569658517837524, "learning_rate": 3.9280705609060944e-07, "loss": 0.5754789352416992, "step": 26970, "token_acc": 0.8140007400679516 }, { "epoch": 1.746323975690089, "grad_norm": 0.3643776774406433, "learning_rate": 3.918199321470206e-07, "loss": 0.583510160446167, "step": 26975, "token_acc": 0.8135043509905446 }, { "epoch": 1.7466476762347152, "grad_norm": 0.3161778748035431, "learning_rate": 3.9083399950277156e-07, "loss": 0.5849276542663574, "step": 26980, "token_acc": 0.8118307378309615 }, { "epoch": 1.7469713767793413, "grad_norm": 0.4053409695625305, "learning_rate": 3.898492584127461e-07, "loss": 0.5644471168518066, "step": 26985, "token_acc": 0.817630330493947 }, { "epoch": 1.7472950773239675, "grad_norm": 0.3018203377723694, "learning_rate": 3.888657091315151e-07, "loss": 0.5986415863037109, "step": 26990, "token_acc": 0.8079567051719257 }, { "epoch": 1.7476187778685937, "grad_norm": 0.46899130940437317, "learning_rate": 3.878833519133468e-07, "loss": 0.5784369468688965, "step": 26995, "token_acc": 0.8138321177289245 }, { "epoch": 1.7479424784132198, "grad_norm": 0.2970041334629059, "learning_rate": 3.869021870121975e-07, "loss": 0.5668084621429443, "step": 27000, "token_acc": 0.8173084907287349 }, { "epoch": 1.748266178957846, "grad_norm": 0.31986668705940247, "learning_rate": 3.85922214681716e-07, "loss": 0.5921407222747803, "step": 27005, "token_acc": 0.8106120764579725 }, { "epoch": 1.7485898795024721, "grad_norm": 0.3441462218761444, "learning_rate": 3.849434351752429e-07, "loss": 0.5832444667816162, "step": 27010, "token_acc": 0.8129185485126927 }, { "epoch": 1.7489135800470983, "grad_norm": 0.2718288004398346, "learning_rate": 3.839658487458131e-07, "loss": 0.5832558631896972, "step": 27015, "token_acc": 0.8127003786632606 }, { "epoch": 1.7492372805917245, "grad_norm": 0.3154279291629791, "learning_rate": 3.8298945564614775e-07, "loss": 0.5959957599639892, "step": 27020, "token_acc": 0.8094715600958506 }, { "epoch": 1.7495609811363506, "grad_norm": 0.32353052496910095, "learning_rate": 3.820142561286638e-07, "loss": 0.5907924175262451, "step": 27025, "token_acc": 0.8108679294664181 }, { "epoch": 1.7498846816809768, "grad_norm": 0.25050055980682373, "learning_rate": 3.810402504454674e-07, "loss": 0.5631738662719726, "step": 27030, "token_acc": 0.8186225208190852 }, { "epoch": 1.750208382225603, "grad_norm": 0.3693006932735443, "learning_rate": 3.800674388483594e-07, "loss": 0.5964280605316162, "step": 27035, "token_acc": 0.8091377133050546 }, { "epoch": 1.7505320827702293, "grad_norm": 0.3904133439064026, "learning_rate": 3.790958215888263e-07, "loss": 0.5799398422241211, "step": 27040, "token_acc": 0.8140404859333406 }, { "epoch": 1.7508557833148555, "grad_norm": 0.3424662947654724, "learning_rate": 3.781253989180511e-07, "loss": 0.5932320117950439, "step": 27045, "token_acc": 0.8113998158137087 }, { "epoch": 1.7511794838594816, "grad_norm": 0.3047880530357361, "learning_rate": 3.7715617108690537e-07, "loss": 0.5862281322479248, "step": 27050, "token_acc": 0.8128415719516907 }, { "epoch": 1.7515031844041078, "grad_norm": 0.3484901785850525, "learning_rate": 3.7618813834595256e-07, "loss": 0.5986660957336426, "step": 27055, "token_acc": 0.8084522239539623 }, { "epoch": 1.751826884948734, "grad_norm": 0.32743242383003235, "learning_rate": 3.752213009454453e-07, "loss": 0.5687274932861328, "step": 27060, "token_acc": 0.8168718084223852 }, { "epoch": 1.7521505854933601, "grad_norm": 0.27393993735313416, "learning_rate": 3.7425565913533135e-07, "loss": 0.583389139175415, "step": 27065, "token_acc": 0.8127631143659633 }, { "epoch": 1.7524742860379863, "grad_norm": 0.31239286065101624, "learning_rate": 3.732912131652455e-07, "loss": 0.5988585948944092, "step": 27070, "token_acc": 0.8083626119710062 }, { "epoch": 1.7527979865826124, "grad_norm": 0.2721938490867615, "learning_rate": 3.723279632845156e-07, "loss": 0.5854920387268067, "step": 27075, "token_acc": 0.8124800553132645 }, { "epoch": 1.7531216871272386, "grad_norm": 0.2604294419288635, "learning_rate": 3.7136590974215736e-07, "loss": 0.6043637752532959, "step": 27080, "token_acc": 0.8076290776702086 }, { "epoch": 1.7534453876718648, "grad_norm": 0.3077108561992645, "learning_rate": 3.70405052786883e-07, "loss": 0.5844528198242187, "step": 27085, "token_acc": 0.8126260744884978 }, { "epoch": 1.753769088216491, "grad_norm": 0.3067146837711334, "learning_rate": 3.6944539266708766e-07, "loss": 0.5711519241333007, "step": 27090, "token_acc": 0.8161951182118423 }, { "epoch": 1.754092788761117, "grad_norm": 0.33491232991218567, "learning_rate": 3.6848692963086407e-07, "loss": 0.5781194686889648, "step": 27095, "token_acc": 0.8156820227996094 }, { "epoch": 1.7544164893057432, "grad_norm": 0.3832436203956604, "learning_rate": 3.675296639259912e-07, "loss": 0.5818233489990234, "step": 27100, "token_acc": 0.8131122586232916 }, { "epoch": 1.7547401898503694, "grad_norm": 0.3189758062362671, "learning_rate": 3.6657359579994056e-07, "loss": 0.5954449653625489, "step": 27105, "token_acc": 0.8102671190094184 }, { "epoch": 1.7550638903949956, "grad_norm": 0.3058355450630188, "learning_rate": 3.656187254998722e-07, "loss": 0.6344422340393067, "step": 27110, "token_acc": 0.800858907865614 }, { "epoch": 1.7553875909396217, "grad_norm": 0.35364922881126404, "learning_rate": 3.6466505327263926e-07, "loss": 0.580682897567749, "step": 27115, "token_acc": 0.8135501463688495 }, { "epoch": 1.7557112914842479, "grad_norm": 0.28949296474456787, "learning_rate": 3.637125793647828e-07, "loss": 0.58676176071167, "step": 27120, "token_acc": 0.8124972257274935 }, { "epoch": 1.7560349920288743, "grad_norm": 0.24746781587600708, "learning_rate": 3.6276130402253475e-07, "loss": 0.5873853683471679, "step": 27125, "token_acc": 0.8116779781486071 }, { "epoch": 1.7563586925735004, "grad_norm": 0.4096037447452545, "learning_rate": 3.6181122749181617e-07, "loss": 0.5937515258789062, "step": 27130, "token_acc": 0.8105059933052766 }, { "epoch": 1.7566823931181266, "grad_norm": 0.2740054726600647, "learning_rate": 3.608623500182423e-07, "loss": 0.5828095436096191, "step": 27135, "token_acc": 0.8133251841774939 }, { "epoch": 1.7570060936627527, "grad_norm": 0.3957638442516327, "learning_rate": 3.5991467184711246e-07, "loss": 0.6146990776062011, "step": 27140, "token_acc": 0.8038336723342352 }, { "epoch": 1.757329794207379, "grad_norm": 0.3161128759384155, "learning_rate": 3.5896819322342013e-07, "loss": 0.5921982765197754, "step": 27145, "token_acc": 0.8096348096348096 }, { "epoch": 1.757653494752005, "grad_norm": 0.36207887530326843, "learning_rate": 3.580229143918479e-07, "loss": 0.5826342582702637, "step": 27150, "token_acc": 0.8121561350392291 }, { "epoch": 1.7579771952966312, "grad_norm": 0.31879347562789917, "learning_rate": 3.570788355967669e-07, "loss": 0.5943296432495118, "step": 27155, "token_acc": 0.8107128078161274 }, { "epoch": 1.7583008958412574, "grad_norm": 0.2982327938079834, "learning_rate": 3.561359570822387e-07, "loss": 0.5884320259094238, "step": 27160, "token_acc": 0.8110609437318964 }, { "epoch": 1.7586245963858835, "grad_norm": 0.4550664722919464, "learning_rate": 3.55194279092016e-07, "loss": 0.5865602493286133, "step": 27165, "token_acc": 0.8120710389411929 }, { "epoch": 1.7589482969305097, "grad_norm": 0.38229191303253174, "learning_rate": 3.5425380186953905e-07, "loss": 0.6095870018005372, "step": 27170, "token_acc": 0.8070474294682847 }, { "epoch": 1.7592719974751359, "grad_norm": 0.3261159360408783, "learning_rate": 3.5331452565793844e-07, "loss": 0.5889203548431396, "step": 27175, "token_acc": 0.8110968648675305 }, { "epoch": 1.759595698019762, "grad_norm": 0.3044169843196869, "learning_rate": 3.523764507000349e-07, "loss": 0.606352710723877, "step": 27180, "token_acc": 0.8080701729424402 }, { "epoch": 1.7599193985643882, "grad_norm": 0.3078401982784271, "learning_rate": 3.514395772383372e-07, "loss": 0.573097038269043, "step": 27185, "token_acc": 0.8156259925046052 }, { "epoch": 1.7602430991090143, "grad_norm": 0.4138924181461334, "learning_rate": 3.505039055150444e-07, "loss": 0.5644870281219483, "step": 27190, "token_acc": 0.8179901986615377 }, { "epoch": 1.7605667996536405, "grad_norm": 0.40699365735054016, "learning_rate": 3.495694357720464e-07, "loss": 0.5987428665161133, "step": 27195, "token_acc": 0.8093192573716782 }, { "epoch": 1.7608905001982667, "grad_norm": 0.36131757497787476, "learning_rate": 3.4863616825091927e-07, "loss": 0.5819900035858154, "step": 27200, "token_acc": 0.8130862164352894 }, { "epoch": 1.7612142007428928, "grad_norm": 0.35532429814338684, "learning_rate": 3.4770410319293015e-07, "loss": 0.5851555824279785, "step": 27205, "token_acc": 0.8118061871597124 }, { "epoch": 1.761537901287519, "grad_norm": 0.36606934666633606, "learning_rate": 3.467732408390356e-07, "loss": 0.5786441802978516, "step": 27210, "token_acc": 0.8135104548394051 }, { "epoch": 1.7618616018321451, "grad_norm": 0.35779696702957153, "learning_rate": 3.4584358142987885e-07, "loss": 0.5750261783599854, "step": 27215, "token_acc": 0.8163886572143453 }, { "epoch": 1.7621853023767713, "grad_norm": 0.26165738701820374, "learning_rate": 3.449151252057964e-07, "loss": 0.6045761108398438, "step": 27220, "token_acc": 0.8071630970311183 }, { "epoch": 1.7625090029213974, "grad_norm": 0.3302924335002899, "learning_rate": 3.4398787240681077e-07, "loss": 0.5757181644439697, "step": 27225, "token_acc": 0.8137540617688068 }, { "epoch": 1.7628327034660236, "grad_norm": 0.34933847188949585, "learning_rate": 3.430618232726324e-07, "loss": 0.5812204360961915, "step": 27230, "token_acc": 0.8148456464547615 }, { "epoch": 1.7631564040106498, "grad_norm": 0.32460954785346985, "learning_rate": 3.4213697804266363e-07, "loss": 0.5935491561889649, "step": 27235, "token_acc": 0.8102495047453808 }, { "epoch": 1.763480104555276, "grad_norm": 0.37592363357543945, "learning_rate": 3.412133369559928e-07, "loss": 0.6084652900695801, "step": 27240, "token_acc": 0.8049982269172623 }, { "epoch": 1.763803805099902, "grad_norm": 0.35423409938812256, "learning_rate": 3.4029090025139765e-07, "loss": 0.6145220279693604, "step": 27245, "token_acc": 0.8046681478076559 }, { "epoch": 1.7641275056445282, "grad_norm": 0.28568366169929504, "learning_rate": 3.393696681673475e-07, "loss": 0.5954877853393554, "step": 27250, "token_acc": 0.8105854207538699 }, { "epoch": 1.7644512061891544, "grad_norm": 0.3296334445476532, "learning_rate": 3.3844964094199575e-07, "loss": 0.5996424198150635, "step": 27255, "token_acc": 0.8083000070160667 }, { "epoch": 1.7647749067337806, "grad_norm": 0.3752017319202423, "learning_rate": 3.375308188131871e-07, "loss": 0.5711554527282715, "step": 27260, "token_acc": 0.8165753564936894 }, { "epoch": 1.7650986072784067, "grad_norm": 0.22929295897483826, "learning_rate": 3.3661320201845316e-07, "loss": 0.5719847679138184, "step": 27265, "token_acc": 0.8158494136730763 }, { "epoch": 1.7654223078230329, "grad_norm": 0.49293434619903564, "learning_rate": 3.3569679079501647e-07, "loss": 0.5875855922698975, "step": 27270, "token_acc": 0.811321789816561 }, { "epoch": 1.765746008367659, "grad_norm": 0.485601007938385, "learning_rate": 3.3478158537978365e-07, "loss": 0.587206506729126, "step": 27275, "token_acc": 0.8132060482839408 }, { "epoch": 1.7660697089122852, "grad_norm": 0.38108059763908386, "learning_rate": 3.338675860093543e-07, "loss": 0.6055339813232422, "step": 27280, "token_acc": 0.806835366468394 }, { "epoch": 1.7663934094569114, "grad_norm": 0.24160970747470856, "learning_rate": 3.329547929200139e-07, "loss": 0.5751542091369629, "step": 27285, "token_acc": 0.8156454834444539 }, { "epoch": 1.7667171100015375, "grad_norm": 0.25542303919792175, "learning_rate": 3.320432063477352e-07, "loss": 0.5806589126586914, "step": 27290, "token_acc": 0.8142359767891683 }, { "epoch": 1.7670408105461637, "grad_norm": 0.3421727120876312, "learning_rate": 3.311328265281799e-07, "loss": 0.5974699974060058, "step": 27295, "token_acc": 0.808865677345392 }, { "epoch": 1.7673645110907898, "grad_norm": 0.37764421105384827, "learning_rate": 3.302236536966996e-07, "loss": 0.5850855827331543, "step": 27300, "token_acc": 0.8133090034307896 }, { "epoch": 1.767688211635416, "grad_norm": 0.28881171345710754, "learning_rate": 3.2931568808833136e-07, "loss": 0.5907952308654785, "step": 27305, "token_acc": 0.8127026761439943 }, { "epoch": 1.7680119121800422, "grad_norm": 0.2993928790092468, "learning_rate": 3.2840892993780073e-07, "loss": 0.6083899021148682, "step": 27310, "token_acc": 0.8068327042529795 }, { "epoch": 1.7683356127246683, "grad_norm": 0.31048598885536194, "learning_rate": 3.275033794795207e-07, "loss": 0.5926627159118653, "step": 27315, "token_acc": 0.8102245281331067 }, { "epoch": 1.7686593132692945, "grad_norm": 0.3716188371181488, "learning_rate": 3.2659903694759574e-07, "loss": 0.586342716217041, "step": 27320, "token_acc": 0.8133095468422177 }, { "epoch": 1.7689830138139206, "grad_norm": 0.34494397044181824, "learning_rate": 3.2569590257581053e-07, "loss": 0.5999391555786133, "step": 27325, "token_acc": 0.809001878772369 }, { "epoch": 1.7693067143585468, "grad_norm": 0.3413146734237671, "learning_rate": 3.2479397659764544e-07, "loss": 0.5648810386657714, "step": 27330, "token_acc": 0.8177452127332061 }, { "epoch": 1.769630414903173, "grad_norm": 0.32469406723976135, "learning_rate": 3.238932592462629e-07, "loss": 0.5908962249755859, "step": 27335, "token_acc": 0.8104898657019673 }, { "epoch": 1.7699541154477991, "grad_norm": 0.37386244535446167, "learning_rate": 3.229937507545172e-07, "loss": 0.5913266181945801, "step": 27340, "token_acc": 0.8119469850212829 }, { "epoch": 1.7702778159924253, "grad_norm": 0.3579709231853485, "learning_rate": 3.2209545135494515e-07, "loss": 0.5721112728118897, "step": 27345, "token_acc": 0.816211289651483 }, { "epoch": 1.7706015165370514, "grad_norm": 0.2233559489250183, "learning_rate": 3.2119836127977533e-07, "loss": 0.5655905246734619, "step": 27350, "token_acc": 0.8180918103851968 }, { "epoch": 1.7709252170816776, "grad_norm": 0.4024774134159088, "learning_rate": 3.2030248076092175e-07, "loss": 0.5623735427856446, "step": 27355, "token_acc": 0.8188954358033844 }, { "epoch": 1.7712489176263038, "grad_norm": 0.28778064250946045, "learning_rate": 3.194078100299863e-07, "loss": 0.6012577056884766, "step": 27360, "token_acc": 0.8083691661030051 }, { "epoch": 1.77157261817093, "grad_norm": 0.3519861102104187, "learning_rate": 3.1851434931825634e-07, "loss": 0.5794395923614502, "step": 27365, "token_acc": 0.8142954523322622 }, { "epoch": 1.771896318715556, "grad_norm": 0.38644370436668396, "learning_rate": 3.1762209885671024e-07, "loss": 0.5944041252136231, "step": 27370, "token_acc": 0.8101791622365893 }, { "epoch": 1.7722200192601822, "grad_norm": 0.35439029335975647, "learning_rate": 3.1673105887600865e-07, "loss": 0.5877679824829102, "step": 27375, "token_acc": 0.8123323879531554 }, { "epoch": 1.7725437198048086, "grad_norm": 0.31255683302879333, "learning_rate": 3.1584122960650387e-07, "loss": 0.5816058158874512, "step": 27380, "token_acc": 0.8121586579553521 }, { "epoch": 1.7728674203494348, "grad_norm": 0.2733062505722046, "learning_rate": 3.1495261127823253e-07, "loss": 0.595708179473877, "step": 27385, "token_acc": 0.8104521918374652 }, { "epoch": 1.773191120894061, "grad_norm": 0.35099413990974426, "learning_rate": 3.14065204120918e-07, "loss": 0.6066841125488281, "step": 27390, "token_acc": 0.8079469302105192 }, { "epoch": 1.773514821438687, "grad_norm": 0.3120277225971222, "learning_rate": 3.1317900836397186e-07, "loss": 0.5634661674499511, "step": 27395, "token_acc": 0.8179759927120733 }, { "epoch": 1.7738385219833133, "grad_norm": 0.32190269231796265, "learning_rate": 3.122940242364925e-07, "loss": 0.6058499813079834, "step": 27400, "token_acc": 0.8089399359278254 }, { "epoch": 1.7741622225279394, "grad_norm": 0.3292146325111389, "learning_rate": 3.1141025196726405e-07, "loss": 0.5827508926391601, "step": 27405, "token_acc": 0.8131591507947405 }, { "epoch": 1.7744859230725656, "grad_norm": 0.31385791301727295, "learning_rate": 3.105276917847588e-07, "loss": 0.6029545783996582, "step": 27410, "token_acc": 0.8075797983972517 }, { "epoch": 1.7748096236171917, "grad_norm": 0.4271527826786041, "learning_rate": 3.0964634391713376e-07, "loss": 0.571938419342041, "step": 27415, "token_acc": 0.815622829049324 }, { "epoch": 1.775133324161818, "grad_norm": 0.31220075488090515, "learning_rate": 3.0876620859223383e-07, "loss": 0.5803673267364502, "step": 27420, "token_acc": 0.8148017983369362 }, { "epoch": 1.775457024706444, "grad_norm": 0.44138261675834656, "learning_rate": 3.078872860375892e-07, "loss": 0.6184544563293457, "step": 27425, "token_acc": 0.8033360594936949 }, { "epoch": 1.7757807252510702, "grad_norm": 0.3249646723270416, "learning_rate": 3.070095764804198e-07, "loss": 0.5845355987548828, "step": 27430, "token_acc": 0.812824743602187 }, { "epoch": 1.7761044257956964, "grad_norm": 0.23496872186660767, "learning_rate": 3.061330801476281e-07, "loss": 0.5847995758056641, "step": 27435, "token_acc": 0.8122790162670169 }, { "epoch": 1.7764281263403225, "grad_norm": 0.4837476313114166, "learning_rate": 3.0525779726580495e-07, "loss": 0.5800567150115967, "step": 27440, "token_acc": 0.8141732497586577 }, { "epoch": 1.7767518268849487, "grad_norm": 0.33295339345932007, "learning_rate": 3.043837280612272e-07, "loss": 0.5951687812805175, "step": 27445, "token_acc": 0.8102434565644339 }, { "epoch": 1.7770755274295749, "grad_norm": 0.41335195302963257, "learning_rate": 3.0351087275985736e-07, "loss": 0.5915603637695312, "step": 27450, "token_acc": 0.8114043601362794 }, { "epoch": 1.777399227974201, "grad_norm": 0.37022408843040466, "learning_rate": 3.0263923158734496e-07, "loss": 0.5933212280273438, "step": 27455, "token_acc": 0.8109724789484494 }, { "epoch": 1.7777229285188272, "grad_norm": 0.27873754501342773, "learning_rate": 3.017688047690254e-07, "loss": 0.6020809173583984, "step": 27460, "token_acc": 0.8079905551530763 }, { "epoch": 1.7780466290634536, "grad_norm": 0.29073795676231384, "learning_rate": 3.0089959252991964e-07, "loss": 0.6044716835021973, "step": 27465, "token_acc": 0.8068489743556178 }, { "epoch": 1.7783703296080797, "grad_norm": 0.33266186714172363, "learning_rate": 3.000315950947352e-07, "loss": 0.5810756683349609, "step": 27470, "token_acc": 0.813347991634043 }, { "epoch": 1.7786940301527059, "grad_norm": 0.3745174705982208, "learning_rate": 2.99164812687866e-07, "loss": 0.583245849609375, "step": 27475, "token_acc": 0.8126205777510892 }, { "epoch": 1.779017730697332, "grad_norm": 0.37659457325935364, "learning_rate": 2.9829924553338997e-07, "loss": 0.5837265491485596, "step": 27480, "token_acc": 0.8130215295963277 }, { "epoch": 1.7793414312419582, "grad_norm": 0.30949804186820984, "learning_rate": 2.974348938550731e-07, "loss": 0.5861087799072265, "step": 27485, "token_acc": 0.8122322200954982 }, { "epoch": 1.7796651317865844, "grad_norm": 0.39890822768211365, "learning_rate": 2.9657175787636605e-07, "loss": 0.5866697311401368, "step": 27490, "token_acc": 0.8144923333454163 }, { "epoch": 1.7799888323312105, "grad_norm": 0.3613791763782501, "learning_rate": 2.957098378204054e-07, "loss": 0.5987870216369628, "step": 27495, "token_acc": 0.8078630185627207 }, { "epoch": 1.7803125328758367, "grad_norm": 0.3421333134174347, "learning_rate": 2.9484913391001234e-07, "loss": 0.6021543502807617, "step": 27500, "token_acc": 0.8087635054021609 }, { "epoch": 1.7806362334204628, "grad_norm": 0.30329984426498413, "learning_rate": 2.9398964636769667e-07, "loss": 0.5750802516937256, "step": 27505, "token_acc": 0.8164509297819889 }, { "epoch": 1.780959933965089, "grad_norm": 0.24794766306877136, "learning_rate": 2.931313754156495e-07, "loss": 0.578611946105957, "step": 27510, "token_acc": 0.8139891610940323 }, { "epoch": 1.7812836345097152, "grad_norm": 0.31897908449172974, "learning_rate": 2.9227432127575175e-07, "loss": 0.5731524467468262, "step": 27515, "token_acc": 0.8169944286610339 }, { "epoch": 1.7816073350543413, "grad_norm": 0.2726776599884033, "learning_rate": 2.914184841695655e-07, "loss": 0.5886312961578369, "step": 27520, "token_acc": 0.8100349082030848 }, { "epoch": 1.7819310355989675, "grad_norm": 0.2906186878681183, "learning_rate": 2.905638643183434e-07, "loss": 0.5875823020935058, "step": 27525, "token_acc": 0.8121195014145406 }, { "epoch": 1.7822547361435936, "grad_norm": 0.3496454954147339, "learning_rate": 2.8971046194301686e-07, "loss": 0.5802260875701905, "step": 27530, "token_acc": 0.8136286041983409 }, { "epoch": 1.7825784366882198, "grad_norm": 0.35042211413383484, "learning_rate": 2.888582772642085e-07, "loss": 0.5756482124328614, "step": 27535, "token_acc": 0.8151911927561722 }, { "epoch": 1.782902137232846, "grad_norm": 0.40973398089408875, "learning_rate": 2.8800731050222297e-07, "loss": 0.5833860397338867, "step": 27540, "token_acc": 0.8126463223468577 }, { "epoch": 1.7832258377774721, "grad_norm": 0.2707161009311676, "learning_rate": 2.8715756187705114e-07, "loss": 0.5727653503417969, "step": 27545, "token_acc": 0.8149717426116432 }, { "epoch": 1.7835495383220983, "grad_norm": 0.32278507947921753, "learning_rate": 2.8630903160836776e-07, "loss": 0.5970273494720459, "step": 27550, "token_acc": 0.8091696549471635 }, { "epoch": 1.7838732388667244, "grad_norm": 0.28194326162338257, "learning_rate": 2.8546171991553574e-07, "loss": 0.5730408668518067, "step": 27555, "token_acc": 0.8157448842160142 }, { "epoch": 1.7841969394113506, "grad_norm": 0.26151973009109497, "learning_rate": 2.846156270175976e-07, "loss": 0.572089147567749, "step": 27560, "token_acc": 0.8154499924115951 }, { "epoch": 1.7845206399559768, "grad_norm": 0.3435782492160797, "learning_rate": 2.837707531332862e-07, "loss": 0.5961718082427978, "step": 27565, "token_acc": 0.8083278339815093 }, { "epoch": 1.784844340500603, "grad_norm": 0.3285648822784424, "learning_rate": 2.829270984810156e-07, "loss": 0.5922811985015869, "step": 27570, "token_acc": 0.8104866150646509 }, { "epoch": 1.785168041045229, "grad_norm": 0.31485843658447266, "learning_rate": 2.8208466327888816e-07, "loss": 0.5687605381011963, "step": 27575, "token_acc": 0.8160888519825618 }, { "epoch": 1.7854917415898552, "grad_norm": 0.3721502125263214, "learning_rate": 2.812434477446863e-07, "loss": 0.5728319644927978, "step": 27580, "token_acc": 0.8168526982490879 }, { "epoch": 1.7858154421344814, "grad_norm": 0.2873498201370239, "learning_rate": 2.804034520958815e-07, "loss": 0.6000038623809815, "step": 27585, "token_acc": 0.8083540842409791 }, { "epoch": 1.7861391426791076, "grad_norm": 0.3739844858646393, "learning_rate": 2.7956467654962736e-07, "loss": 0.6080126285552978, "step": 27590, "token_acc": 0.8063179460066748 }, { "epoch": 1.7864628432237337, "grad_norm": 0.28882113099098206, "learning_rate": 2.787271213227633e-07, "loss": 0.6010209083557129, "step": 27595, "token_acc": 0.8080347247875878 }, { "epoch": 1.7867865437683599, "grad_norm": 0.4588044285774231, "learning_rate": 2.7789078663181146e-07, "loss": 0.5964925765991211, "step": 27600, "token_acc": 0.8097059542023992 }, { "epoch": 1.787110244312986, "grad_norm": 0.3765964210033417, "learning_rate": 2.7705567269298126e-07, "loss": 0.5980074405670166, "step": 27605, "token_acc": 0.8091216905315547 }, { "epoch": 1.7874339448576122, "grad_norm": 0.354209303855896, "learning_rate": 2.762217797221645e-07, "loss": 0.5535361289978027, "step": 27610, "token_acc": 0.819576073240798 }, { "epoch": 1.7877576454022384, "grad_norm": 0.342307448387146, "learning_rate": 2.75389107934938e-07, "loss": 0.5976544380187988, "step": 27615, "token_acc": 0.8095280183843027 }, { "epoch": 1.7880813459468645, "grad_norm": 0.3624352216720581, "learning_rate": 2.7455765754656137e-07, "loss": 0.5847282409667969, "step": 27620, "token_acc": 0.8127103570035245 }, { "epoch": 1.7884050464914907, "grad_norm": 0.3803417384624481, "learning_rate": 2.7372742877198264e-07, "loss": 0.5794491767883301, "step": 27625, "token_acc": 0.8145173610353331 }, { "epoch": 1.7887287470361168, "grad_norm": 0.26160678267478943, "learning_rate": 2.728984218258285e-07, "loss": 0.5896779060363769, "step": 27630, "token_acc": 0.811186682898428 }, { "epoch": 1.789052447580743, "grad_norm": 0.2614302933216095, "learning_rate": 2.7207063692241407e-07, "loss": 0.5807828903198242, "step": 27635, "token_acc": 0.8140588072195303 }, { "epoch": 1.7893761481253692, "grad_norm": 0.32407650351524353, "learning_rate": 2.7124407427573606e-07, "loss": 0.6030203819274902, "step": 27640, "token_acc": 0.8080243742831611 }, { "epoch": 1.7896998486699953, "grad_norm": 0.4187397360801697, "learning_rate": 2.7041873409947737e-07, "loss": 0.5788754940032959, "step": 27645, "token_acc": 0.8151030531086975 }, { "epoch": 1.7900235492146215, "grad_norm": 0.3527413010597229, "learning_rate": 2.6959461660700126e-07, "loss": 0.595462417602539, "step": 27650, "token_acc": 0.8114626657910542 }, { "epoch": 1.7903472497592476, "grad_norm": 0.2665305733680725, "learning_rate": 2.6877172201136e-07, "loss": 0.6203504085540772, "step": 27655, "token_acc": 0.8028996814251349 }, { "epoch": 1.7906709503038738, "grad_norm": 0.30718716979026794, "learning_rate": 2.6795005052528577e-07, "loss": 0.5807876110076904, "step": 27660, "token_acc": 0.8137094784335381 }, { "epoch": 1.7909946508485, "grad_norm": 0.3075360357761383, "learning_rate": 2.671296023611958e-07, "loss": 0.6051148414611817, "step": 27665, "token_acc": 0.8083040759057218 }, { "epoch": 1.7913183513931261, "grad_norm": 0.3371681571006775, "learning_rate": 2.6631037773119097e-07, "loss": 0.5941081047058105, "step": 27670, "token_acc": 0.8092576384468492 }, { "epoch": 1.7916420519377523, "grad_norm": 0.30617406964302063, "learning_rate": 2.654923768470563e-07, "loss": 0.5809928894042968, "step": 27675, "token_acc": 0.814455996835325 }, { "epoch": 1.7919657524823784, "grad_norm": 0.33352744579315186, "learning_rate": 2.6467559992025935e-07, "loss": 0.5914144039154052, "step": 27680, "token_acc": 0.810358029870225 }, { "epoch": 1.7922894530270046, "grad_norm": 0.3318106234073639, "learning_rate": 2.638600471619518e-07, "loss": 0.6134165287017822, "step": 27685, "token_acc": 0.806497807213819 }, { "epoch": 1.7926131535716308, "grad_norm": 0.3927594721317291, "learning_rate": 2.6304571878296993e-07, "loss": 0.5664835929870605, "step": 27690, "token_acc": 0.8171100055840398 }, { "epoch": 1.792936854116257, "grad_norm": 0.29526442289352417, "learning_rate": 2.622326149938331e-07, "loss": 0.5909520626068115, "step": 27695, "token_acc": 0.8125117972225967 }, { "epoch": 1.793260554660883, "grad_norm": 0.3806879222393036, "learning_rate": 2.6142073600474216e-07, "loss": 0.5954401016235351, "step": 27700, "token_acc": 0.8100275482093664 }, { "epoch": 1.7935842552055092, "grad_norm": 0.3622387647628784, "learning_rate": 2.60610082025583e-07, "loss": 0.5861949920654297, "step": 27705, "token_acc": 0.8118240945012047 }, { "epoch": 1.7939079557501354, "grad_norm": 0.45105814933776855, "learning_rate": 2.598006532659264e-07, "loss": 0.5810764312744141, "step": 27710, "token_acc": 0.8126529518592396 }, { "epoch": 1.7942316562947616, "grad_norm": 0.38309359550476074, "learning_rate": 2.5899244993502157e-07, "loss": 0.58274245262146, "step": 27715, "token_acc": 0.812291209938407 }, { "epoch": 1.7945553568393877, "grad_norm": 0.37565040588378906, "learning_rate": 2.5818547224180646e-07, "loss": 0.5761528015136719, "step": 27720, "token_acc": 0.8144877593509944 }, { "epoch": 1.794879057384014, "grad_norm": 0.3987029492855072, "learning_rate": 2.5737972039489913e-07, "loss": 0.5854181289672852, "step": 27725, "token_acc": 0.811481488646843 }, { "epoch": 1.7952027579286403, "grad_norm": 0.4125126600265503, "learning_rate": 2.565751946026007e-07, "loss": 0.5806376457214355, "step": 27730, "token_acc": 0.8135477762110096 }, { "epoch": 1.7955264584732664, "grad_norm": 0.44588637351989746, "learning_rate": 2.557718950728949e-07, "loss": 0.5777948379516602, "step": 27735, "token_acc": 0.813299736210087 }, { "epoch": 1.7958501590178926, "grad_norm": 0.33639460802078247, "learning_rate": 2.549698220134517e-07, "loss": 0.593541955947876, "step": 27740, "token_acc": 0.8102028199349859 }, { "epoch": 1.7961738595625187, "grad_norm": 0.26723238825798035, "learning_rate": 2.541689756316207e-07, "loss": 0.5827701568603516, "step": 27745, "token_acc": 0.8127755625972802 }, { "epoch": 1.796497560107145, "grad_norm": 0.32029467821121216, "learning_rate": 2.5336935613443524e-07, "loss": 0.5657354354858398, "step": 27750, "token_acc": 0.8172568889370581 }, { "epoch": 1.796821260651771, "grad_norm": 0.3080611824989319, "learning_rate": 2.525709637286111e-07, "loss": 0.5786918640136719, "step": 27755, "token_acc": 0.8140480427609705 }, { "epoch": 1.7971449611963972, "grad_norm": 0.3009866178035736, "learning_rate": 2.5177379862054983e-07, "loss": 0.5893653869628906, "step": 27760, "token_acc": 0.8115236804998756 }, { "epoch": 1.7974686617410234, "grad_norm": 0.32761725783348083, "learning_rate": 2.509778610163299e-07, "loss": 0.5605625629425048, "step": 27765, "token_acc": 0.8189150246074964 }, { "epoch": 1.7977923622856495, "grad_norm": 0.47165563702583313, "learning_rate": 2.5018315112171845e-07, "loss": 0.5775324821472168, "step": 27770, "token_acc": 0.8138377834386892 }, { "epoch": 1.7981160628302757, "grad_norm": 0.2891939878463745, "learning_rate": 2.4938966914216157e-07, "loss": 0.5882877349853516, "step": 27775, "token_acc": 0.8138782192557144 }, { "epoch": 1.7984397633749019, "grad_norm": 0.35786524415016174, "learning_rate": 2.4859741528278913e-07, "loss": 0.5815564155578613, "step": 27780, "token_acc": 0.8141647421093149 }, { "epoch": 1.798763463919528, "grad_norm": 0.3590810000896454, "learning_rate": 2.478063897484123e-07, "loss": 0.5989810466766358, "step": 27785, "token_acc": 0.8094752602309996 }, { "epoch": 1.7990871644641542, "grad_norm": 0.4321127235889435, "learning_rate": 2.470165927435275e-07, "loss": 0.5961930274963378, "step": 27790, "token_acc": 0.8092688209356173 }, { "epoch": 1.7994108650087803, "grad_norm": 0.24065932631492615, "learning_rate": 2.4622802447231085e-07, "loss": 0.5831407070159912, "step": 27795, "token_acc": 0.8141974223048514 }, { "epoch": 1.7997345655534065, "grad_norm": 0.32525870203971863, "learning_rate": 2.454406851386221e-07, "loss": 0.5674458503723144, "step": 27800, "token_acc": 0.8173836698858647 }, { "epoch": 1.8000582660980327, "grad_norm": 0.3552042841911316, "learning_rate": 2.446545749460022e-07, "loss": 0.5851253032684326, "step": 27805, "token_acc": 0.8111499473530089 }, { "epoch": 1.800381966642659, "grad_norm": 0.2739790380001068, "learning_rate": 2.438696940976765e-07, "loss": 0.5718461036682129, "step": 27810, "token_acc": 0.8152022315202232 }, { "epoch": 1.8007056671872852, "grad_norm": 0.36725884675979614, "learning_rate": 2.4308604279654923e-07, "loss": 0.572062873840332, "step": 27815, "token_acc": 0.8153662700533018 }, { "epoch": 1.8010293677319114, "grad_norm": 0.31217074394226074, "learning_rate": 2.423036212452107e-07, "loss": 0.5853707313537597, "step": 27820, "token_acc": 0.8117110553819858 }, { "epoch": 1.8013530682765375, "grad_norm": 0.3003024756908417, "learning_rate": 2.41522429645929e-07, "loss": 0.5739645957946777, "step": 27825, "token_acc": 0.8173107590899426 }, { "epoch": 1.8016767688211637, "grad_norm": 0.38276976346969604, "learning_rate": 2.407424682006598e-07, "loss": 0.5701052188873291, "step": 27830, "token_acc": 0.8162644692956641 }, { "epoch": 1.8020004693657898, "grad_norm": 0.3433385193347931, "learning_rate": 2.399637371110336e-07, "loss": 0.6040802001953125, "step": 27835, "token_acc": 0.8091664025356576 }, { "epoch": 1.802324169910416, "grad_norm": 0.2602675259113312, "learning_rate": 2.3918623657836984e-07, "loss": 0.5788061618804932, "step": 27840, "token_acc": 0.8151966820037587 }, { "epoch": 1.8026478704550422, "grad_norm": 0.3857860863208771, "learning_rate": 2.3840996680366545e-07, "loss": 0.5995131492614746, "step": 27845, "token_acc": 0.8092609519030294 }, { "epoch": 1.8029715709996683, "grad_norm": 0.3339509665966034, "learning_rate": 2.3763492798760002e-07, "loss": 0.6038222312927246, "step": 27850, "token_acc": 0.808544983532291 }, { "epoch": 1.8032952715442945, "grad_norm": 0.34000274538993835, "learning_rate": 2.3686112033053542e-07, "loss": 0.5824145793914794, "step": 27855, "token_acc": 0.8128863915100243 }, { "epoch": 1.8036189720889206, "grad_norm": 0.2645990550518036, "learning_rate": 2.3608854403251725e-07, "loss": 0.5580187320709229, "step": 27860, "token_acc": 0.8190256040491439 }, { "epoch": 1.8039426726335468, "grad_norm": 0.23727893829345703, "learning_rate": 2.3531719929326734e-07, "loss": 0.5890618801116944, "step": 27865, "token_acc": 0.8111691442346324 }, { "epoch": 1.804266373178173, "grad_norm": 0.42187467217445374, "learning_rate": 2.3454708631219513e-07, "loss": 0.5809251308441162, "step": 27870, "token_acc": 0.8127823005977335 }, { "epoch": 1.8045900737227991, "grad_norm": 0.375846803188324, "learning_rate": 2.3377820528838745e-07, "loss": 0.5975522994995117, "step": 27875, "token_acc": 0.8096380909857618 }, { "epoch": 1.8049137742674253, "grad_norm": 0.25795063376426697, "learning_rate": 2.3301055642061533e-07, "loss": 0.5774406433105469, "step": 27880, "token_acc": 0.8153576152868911 }, { "epoch": 1.8052374748120514, "grad_norm": 0.3311763405799866, "learning_rate": 2.3224413990732885e-07, "loss": 0.5774648666381836, "step": 27885, "token_acc": 0.8160943289667617 }, { "epoch": 1.8055611753566776, "grad_norm": 0.2525579631328583, "learning_rate": 2.3147895594666237e-07, "loss": 0.6004843711853027, "step": 27890, "token_acc": 0.808126856969689 }, { "epoch": 1.8058848759013038, "grad_norm": 0.384790301322937, "learning_rate": 2.307150047364287e-07, "loss": 0.5961179733276367, "step": 27895, "token_acc": 0.8086213933628458 }, { "epoch": 1.80620857644593, "grad_norm": 0.37868887186050415, "learning_rate": 2.299522864741244e-07, "loss": 0.5671015739440918, "step": 27900, "token_acc": 0.8179380363200958 }, { "epoch": 1.806532276990556, "grad_norm": 0.34889110922813416, "learning_rate": 2.2919080135692496e-07, "loss": 0.5820887565612793, "step": 27905, "token_acc": 0.8140663414382988 }, { "epoch": 1.8068559775351822, "grad_norm": 0.31308963894844055, "learning_rate": 2.284305495816891e-07, "loss": 0.6030869007110595, "step": 27910, "token_acc": 0.8074943535692287 }, { "epoch": 1.8071796780798084, "grad_norm": 0.3498806655406952, "learning_rate": 2.2767153134495512e-07, "loss": 0.59188871383667, "step": 27915, "token_acc": 0.8109210661992163 }, { "epoch": 1.8075033786244346, "grad_norm": 0.30599144101142883, "learning_rate": 2.2691374684294386e-07, "loss": 0.590766716003418, "step": 27920, "token_acc": 0.8096997018832255 }, { "epoch": 1.8078270791690607, "grad_norm": 0.37060174345970154, "learning_rate": 2.2615719627155696e-07, "loss": 0.6084624767303467, "step": 27925, "token_acc": 0.8065544480545307 }, { "epoch": 1.8081507797136869, "grad_norm": 0.30912670493125916, "learning_rate": 2.2540187982637628e-07, "loss": 0.6124053001403809, "step": 27930, "token_acc": 0.8056878879745921 }, { "epoch": 1.808474480258313, "grad_norm": 0.38763779401779175, "learning_rate": 2.2464779770266454e-07, "loss": 0.5848542213439941, "step": 27935, "token_acc": 0.812989868418374 }, { "epoch": 1.8087981808029392, "grad_norm": 0.3357309401035309, "learning_rate": 2.2389495009536578e-07, "loss": 0.5637359619140625, "step": 27940, "token_acc": 0.8195176208874839 }, { "epoch": 1.8091218813475654, "grad_norm": 0.3744279444217682, "learning_rate": 2.2314333719910598e-07, "loss": 0.5915754318237305, "step": 27945, "token_acc": 0.8117245035389862 }, { "epoch": 1.8094455818921915, "grad_norm": 0.31982874870300293, "learning_rate": 2.2239295920819025e-07, "loss": 0.6080604076385498, "step": 27950, "token_acc": 0.8076341088066554 }, { "epoch": 1.8097692824368177, "grad_norm": 0.4098273813724518, "learning_rate": 2.2164381631660513e-07, "loss": 0.5757701873779297, "step": 27955, "token_acc": 0.8149687728120691 }, { "epoch": 1.8100929829814438, "grad_norm": 0.4538932144641876, "learning_rate": 2.2089590871801737e-07, "loss": 0.5733930110931397, "step": 27960, "token_acc": 0.8153570460301401 }, { "epoch": 1.81041668352607, "grad_norm": 0.34123262763023376, "learning_rate": 2.2014923660577613e-07, "loss": 0.5876915931701661, "step": 27965, "token_acc": 0.8130335033708441 }, { "epoch": 1.8107403840706962, "grad_norm": 0.3414938151836395, "learning_rate": 2.1940380017290818e-07, "loss": 0.5873911857604981, "step": 27970, "token_acc": 0.8124565659214581 }, { "epoch": 1.8110640846153223, "grad_norm": 0.23526529967784882, "learning_rate": 2.1865959961212435e-07, "loss": 0.5981061935424805, "step": 27975, "token_acc": 0.809636718313837 }, { "epoch": 1.8113877851599485, "grad_norm": 0.43883419036865234, "learning_rate": 2.1791663511581297e-07, "loss": 0.586398983001709, "step": 27980, "token_acc": 0.8130369204538003 }, { "epoch": 1.8117114857045746, "grad_norm": 0.37917038798332214, "learning_rate": 2.1717490687604482e-07, "loss": 0.5984127998352051, "step": 27985, "token_acc": 0.8091383197066048 }, { "epoch": 1.8120351862492008, "grad_norm": 0.337551474571228, "learning_rate": 2.1643441508456874e-07, "loss": 0.5683386325836182, "step": 27990, "token_acc": 0.8171509663468036 }, { "epoch": 1.812358886793827, "grad_norm": 0.5136353373527527, "learning_rate": 2.1569515993281777e-07, "loss": 0.5996238708496093, "step": 27995, "token_acc": 0.808539604786343 }, { "epoch": 1.812682587338453, "grad_norm": 0.41944071650505066, "learning_rate": 2.1495714161190117e-07, "loss": 0.5698789596557617, "step": 28000, "token_acc": 0.8171773040830278 }, { "epoch": 1.8130062878830793, "grad_norm": 0.37259581685066223, "learning_rate": 2.1422036031261085e-07, "loss": 0.5703476905822754, "step": 28005, "token_acc": 0.8150826649851223 }, { "epoch": 1.8133299884277054, "grad_norm": 0.3065275549888611, "learning_rate": 2.1348481622541773e-07, "loss": 0.5831892967224122, "step": 28010, "token_acc": 0.813349000885914 }, { "epoch": 1.8136536889723316, "grad_norm": 0.3779553472995758, "learning_rate": 2.1275050954047583e-07, "loss": 0.588901138305664, "step": 28015, "token_acc": 0.8118528166720937 }, { "epoch": 1.8139773895169578, "grad_norm": 0.37024691700935364, "learning_rate": 2.1201744044761387e-07, "loss": 0.5777019023895263, "step": 28020, "token_acc": 0.8157559045986934 }, { "epoch": 1.814301090061584, "grad_norm": 0.24376943707466125, "learning_rate": 2.1128560913634577e-07, "loss": 0.5756284713745117, "step": 28025, "token_acc": 0.8152104004220293 }, { "epoch": 1.81462479060621, "grad_norm": 0.451524555683136, "learning_rate": 2.1055501579586247e-07, "loss": 0.5896323680877685, "step": 28030, "token_acc": 0.8118131868131868 }, { "epoch": 1.8149484911508362, "grad_norm": 0.291548490524292, "learning_rate": 2.0982566061503563e-07, "loss": 0.5785144329071045, "step": 28035, "token_acc": 0.8139583265611287 }, { "epoch": 1.8152721916954624, "grad_norm": 0.27580758929252625, "learning_rate": 2.090975437824172e-07, "loss": 0.5842741966247559, "step": 28040, "token_acc": 0.8136210743664035 }, { "epoch": 1.8155958922400885, "grad_norm": 0.36379528045654297, "learning_rate": 2.0837066548624052e-07, "loss": 0.5503035545349121, "step": 28045, "token_acc": 0.822340631660531 }, { "epoch": 1.8159195927847147, "grad_norm": 0.38571083545684814, "learning_rate": 2.076450259144136e-07, "loss": 0.564844799041748, "step": 28050, "token_acc": 0.8176065187257912 }, { "epoch": 1.8162432933293409, "grad_norm": 0.30316972732543945, "learning_rate": 2.0692062525453027e-07, "loss": 0.5621135711669922, "step": 28055, "token_acc": 0.8184473260339565 }, { "epoch": 1.816566993873967, "grad_norm": 0.33806440234184265, "learning_rate": 2.0619746369385963e-07, "loss": 0.5817000389099121, "step": 28060, "token_acc": 0.8139038351810837 }, { "epoch": 1.8168906944185934, "grad_norm": 0.35241976380348206, "learning_rate": 2.0547554141935488e-07, "loss": 0.565097427368164, "step": 28065, "token_acc": 0.8166253447010904 }, { "epoch": 1.8172143949632196, "grad_norm": 0.3343571424484253, "learning_rate": 2.0475485861764343e-07, "loss": 0.5740338325500488, "step": 28070, "token_acc": 0.8138307254264621 }, { "epoch": 1.8175380955078457, "grad_norm": 0.406302273273468, "learning_rate": 2.0403541547503626e-07, "loss": 0.6129008293151855, "step": 28075, "token_acc": 0.8061095140788972 }, { "epoch": 1.817861796052472, "grad_norm": 0.29465922713279724, "learning_rate": 2.0331721217752288e-07, "loss": 0.6137235164642334, "step": 28080, "token_acc": 0.8054970035131226 }, { "epoch": 1.818185496597098, "grad_norm": 0.4199775755405426, "learning_rate": 2.0260024891077202e-07, "loss": 0.5961042404174804, "step": 28085, "token_acc": 0.8102641595326311 }, { "epoch": 1.8185091971417242, "grad_norm": 0.4023956060409546, "learning_rate": 2.0188452586013097e-07, "loss": 0.6109575748443603, "step": 28090, "token_acc": 0.8069131441880703 }, { "epoch": 1.8188328976863504, "grad_norm": 0.3009651303291321, "learning_rate": 2.0117004321062784e-07, "loss": 0.6119848251342773, "step": 28095, "token_acc": 0.8074914108544454 }, { "epoch": 1.8191565982309765, "grad_norm": 0.3584894835948944, "learning_rate": 2.004568011469704e-07, "loss": 0.5764208316802979, "step": 28100, "token_acc": 0.814903470559927 }, { "epoch": 1.8194802987756027, "grad_norm": 0.33377981185913086, "learning_rate": 1.9974479985354402e-07, "loss": 0.5750246047973633, "step": 28105, "token_acc": 0.8153891639323354 }, { "epoch": 1.8198039993202288, "grad_norm": 0.35098743438720703, "learning_rate": 1.9903403951441303e-07, "loss": 0.5636520385742188, "step": 28110, "token_acc": 0.8176672997010322 }, { "epoch": 1.820127699864855, "grad_norm": 0.3160334527492523, "learning_rate": 1.9832452031332495e-07, "loss": 0.5668888092041016, "step": 28115, "token_acc": 0.816490557176881 }, { "epoch": 1.8204514004094812, "grad_norm": 0.40512850880622864, "learning_rate": 1.9761624243370026e-07, "loss": 0.5882149696350097, "step": 28120, "token_acc": 0.8132916117996823 }, { "epoch": 1.8207751009541073, "grad_norm": 0.2464430332183838, "learning_rate": 1.9690920605864415e-07, "loss": 0.5825413703918457, "step": 28125, "token_acc": 0.812913388071616 }, { "epoch": 1.8210988014987335, "grad_norm": 0.37255746126174927, "learning_rate": 1.9620341137093824e-07, "loss": 0.6047531604766846, "step": 28130, "token_acc": 0.8095099761931753 }, { "epoch": 1.8214225020433596, "grad_norm": 0.34302186965942383, "learning_rate": 1.9549885855304262e-07, "loss": 0.6130841255187989, "step": 28135, "token_acc": 0.8059553519537793 }, { "epoch": 1.8217462025879858, "grad_norm": 0.3975629210472107, "learning_rate": 1.947955477870972e-07, "loss": 0.5913331985473633, "step": 28140, "token_acc": 0.8114634445534838 }, { "epoch": 1.822069903132612, "grad_norm": 0.43360018730163574, "learning_rate": 1.9409347925492095e-07, "loss": 0.5796351432800293, "step": 28145, "token_acc": 0.8145756895511052 }, { "epoch": 1.8223936036772383, "grad_norm": 0.34970900416374207, "learning_rate": 1.9339265313801203e-07, "loss": 0.5715503692626953, "step": 28150, "token_acc": 0.8150870432713734 }, { "epoch": 1.8227173042218645, "grad_norm": 0.34536001086235046, "learning_rate": 1.9269306961754663e-07, "loss": 0.5975099563598633, "step": 28155, "token_acc": 0.8099016228490621 }, { "epoch": 1.8230410047664907, "grad_norm": 0.3658890724182129, "learning_rate": 1.9199472887437952e-07, "loss": 0.5968454837799072, "step": 28160, "token_acc": 0.8089815315716311 }, { "epoch": 1.8233647053111168, "grad_norm": 0.31945177912712097, "learning_rate": 1.912976310890452e-07, "loss": 0.5979910373687745, "step": 28165, "token_acc": 0.8077132981626342 }, { "epoch": 1.823688405855743, "grad_norm": 0.23123346269130707, "learning_rate": 1.906017764417556e-07, "loss": 0.5788061141967773, "step": 28170, "token_acc": 0.8147638145036424 }, { "epoch": 1.8240121064003691, "grad_norm": 0.41261687874794006, "learning_rate": 1.8990716511240238e-07, "loss": 0.5701908111572266, "step": 28175, "token_acc": 0.8163233865836096 }, { "epoch": 1.8243358069449953, "grad_norm": 0.35907208919525146, "learning_rate": 1.8921379728055523e-07, "loss": 0.5838214874267578, "step": 28180, "token_acc": 0.8134301062158886 }, { "epoch": 1.8246595074896215, "grad_norm": 0.40402525663375854, "learning_rate": 1.88521673125463e-07, "loss": 0.573861026763916, "step": 28185, "token_acc": 0.815209827728606 }, { "epoch": 1.8249832080342476, "grad_norm": 0.2676875591278076, "learning_rate": 1.8783079282605255e-07, "loss": 0.5883191108703614, "step": 28190, "token_acc": 0.812060711716199 }, { "epoch": 1.8253069085788738, "grad_norm": 0.5194862484931946, "learning_rate": 1.8714115656092714e-07, "loss": 0.5785234451293946, "step": 28195, "token_acc": 0.8135520862751795 }, { "epoch": 1.8256306091235, "grad_norm": 0.3642778694629669, "learning_rate": 1.8645276450837414e-07, "loss": 0.6060747146606446, "step": 28200, "token_acc": 0.8069616681922483 }, { "epoch": 1.825954309668126, "grad_norm": 0.3093012571334839, "learning_rate": 1.8576561684635175e-07, "loss": 0.5912766456604004, "step": 28205, "token_acc": 0.8114924265268725 }, { "epoch": 1.8262780102127523, "grad_norm": 0.42284858226776123, "learning_rate": 1.8507971375250233e-07, "loss": 0.5982771396636963, "step": 28210, "token_acc": 0.8094161834475487 }, { "epoch": 1.8266017107573784, "grad_norm": 0.4210812449455261, "learning_rate": 1.8439505540414458e-07, "loss": 0.5986227035522461, "step": 28215, "token_acc": 0.8101949385316942 }, { "epoch": 1.8269254113020046, "grad_norm": 0.25851523876190186, "learning_rate": 1.8371164197827418e-07, "loss": 0.593076515197754, "step": 28220, "token_acc": 0.8090050141121453 }, { "epoch": 1.8272491118466307, "grad_norm": 0.29594093561172485, "learning_rate": 1.8302947365156642e-07, "loss": 0.5977873802185059, "step": 28225, "token_acc": 0.8089273919008181 }, { "epoch": 1.827572812391257, "grad_norm": 0.3432173430919647, "learning_rate": 1.8234855060037525e-07, "loss": 0.5713578224182129, "step": 28230, "token_acc": 0.8159630227851657 }, { "epoch": 1.827896512935883, "grad_norm": 0.303902804851532, "learning_rate": 1.8166887300073154e-07, "loss": 0.5986263275146484, "step": 28235, "token_acc": 0.8103676843295512 }, { "epoch": 1.8282202134805092, "grad_norm": 0.21835379302501678, "learning_rate": 1.8099044102834362e-07, "loss": 0.5725471019744873, "step": 28240, "token_acc": 0.8165861605921174 }, { "epoch": 1.8285439140251354, "grad_norm": 0.34795862436294556, "learning_rate": 1.8031325485859842e-07, "loss": 0.5802090644836426, "step": 28245, "token_acc": 0.8122904151495938 }, { "epoch": 1.8288676145697615, "grad_norm": 0.2759946286678314, "learning_rate": 1.7963731466656309e-07, "loss": 0.5798514366149903, "step": 28250, "token_acc": 0.8131085873263628 }, { "epoch": 1.8291913151143877, "grad_norm": 0.25882551074028015, "learning_rate": 1.7896262062697846e-07, "loss": 0.590430736541748, "step": 28255, "token_acc": 0.8125587272786184 }, { "epoch": 1.8295150156590139, "grad_norm": 0.36457082629203796, "learning_rate": 1.7828917291426606e-07, "loss": 0.5985527992248535, "step": 28260, "token_acc": 0.808535129079516 }, { "epoch": 1.82983871620364, "grad_norm": 0.3585638105869293, "learning_rate": 1.7761697170252502e-07, "loss": 0.6035002708435059, "step": 28265, "token_acc": 0.8080655537872888 }, { "epoch": 1.8301624167482662, "grad_norm": 0.45149603486061096, "learning_rate": 1.769460171655313e-07, "loss": 0.5831531047821045, "step": 28270, "token_acc": 0.8134175357757527 }, { "epoch": 1.8304861172928923, "grad_norm": 0.4100467264652252, "learning_rate": 1.7627630947673835e-07, "loss": 0.5694278717041016, "step": 28275, "token_acc": 0.8175794235453515 }, { "epoch": 1.8308098178375185, "grad_norm": 0.35682493448257446, "learning_rate": 1.7560784880927883e-07, "loss": 0.5988203048706054, "step": 28280, "token_acc": 0.8092554790920536 }, { "epoch": 1.8311335183821447, "grad_norm": 0.35542798042297363, "learning_rate": 1.7494063533596173e-07, "loss": 0.5818205356597901, "step": 28285, "token_acc": 0.8131161383386694 }, { "epoch": 1.8314572189267708, "grad_norm": 0.3101004958152771, "learning_rate": 1.742746692292746e-07, "loss": 0.5796947956085206, "step": 28290, "token_acc": 0.8130155454212576 }, { "epoch": 1.831780919471397, "grad_norm": 0.33965426683425903, "learning_rate": 1.7360995066138086e-07, "loss": 0.5797388076782226, "step": 28295, "token_acc": 0.812131340286539 }, { "epoch": 1.8321046200160231, "grad_norm": 0.3403896987438202, "learning_rate": 1.7294647980412415e-07, "loss": 0.5748054504394531, "step": 28300, "token_acc": 0.8157371412442426 }, { "epoch": 1.8324283205606493, "grad_norm": 0.24666699767112732, "learning_rate": 1.7228425682902173e-07, "loss": 0.5636676788330078, "step": 28305, "token_acc": 0.8180026962563518 }, { "epoch": 1.8327520211052755, "grad_norm": 0.30149057507514954, "learning_rate": 1.7162328190727217e-07, "loss": 0.5734023094177246, "step": 28310, "token_acc": 0.8156215393133998 }, { "epoch": 1.8330757216499016, "grad_norm": 0.319145530462265, "learning_rate": 1.7096355520974883e-07, "loss": 0.5790453910827636, "step": 28315, "token_acc": 0.8156029325473638 }, { "epoch": 1.8333994221945278, "grad_norm": 0.32407423853874207, "learning_rate": 1.703050769070036e-07, "loss": 0.5872117519378662, "step": 28320, "token_acc": 0.8114416232162002 }, { "epoch": 1.833723122739154, "grad_norm": 0.2805934548377991, "learning_rate": 1.696478471692642e-07, "loss": 0.585767412185669, "step": 28325, "token_acc": 0.8122298733855869 }, { "epoch": 1.83404682328378, "grad_norm": 0.41341501474380493, "learning_rate": 1.6899186616643803e-07, "loss": 0.5563737869262695, "step": 28330, "token_acc": 0.8196496143835287 }, { "epoch": 1.8343705238284063, "grad_norm": 0.3597338795661926, "learning_rate": 1.6833713406810782e-07, "loss": 0.5915238380432128, "step": 28335, "token_acc": 0.810206338673492 }, { "epoch": 1.8346942243730324, "grad_norm": 0.4792593717575073, "learning_rate": 1.6768365104353367e-07, "loss": 0.604317569732666, "step": 28340, "token_acc": 0.8067531328967047 }, { "epoch": 1.8350179249176586, "grad_norm": 0.4262389838695526, "learning_rate": 1.6703141726165217e-07, "loss": 0.605742359161377, "step": 28345, "token_acc": 0.8077656177023769 }, { "epoch": 1.8353416254622847, "grad_norm": 0.3105766773223877, "learning_rate": 1.6638043289108008e-07, "loss": 0.6000059127807618, "step": 28350, "token_acc": 0.8078277245558012 }, { "epoch": 1.835665326006911, "grad_norm": 0.3008670210838318, "learning_rate": 1.6573069810010612e-07, "loss": 0.5841016292572021, "step": 28355, "token_acc": 0.8150198533903482 }, { "epoch": 1.835989026551537, "grad_norm": 0.3061349391937256, "learning_rate": 1.6508221305670036e-07, "loss": 0.5816014289855957, "step": 28360, "token_acc": 0.8126918803784029 }, { "epoch": 1.8363127270961632, "grad_norm": 0.3286285996437073, "learning_rate": 1.6443497792850815e-07, "loss": 0.5926127433776855, "step": 28365, "token_acc": 0.8097777253080954 }, { "epoch": 1.8366364276407894, "grad_norm": 0.38673344254493713, "learning_rate": 1.6378899288285067e-07, "loss": 0.595226240158081, "step": 28370, "token_acc": 0.810503249582908 }, { "epoch": 1.8369601281854155, "grad_norm": 0.4073368310928345, "learning_rate": 1.6314425808672707e-07, "loss": 0.6100571155548096, "step": 28375, "token_acc": 0.8064010485990527 }, { "epoch": 1.8372838287300417, "grad_norm": 0.24947327375411987, "learning_rate": 1.6250077370681406e-07, "loss": 0.5892942428588868, "step": 28380, "token_acc": 0.8103843167701863 }, { "epoch": 1.8376075292746679, "grad_norm": 0.3984755277633667, "learning_rate": 1.6185853990946355e-07, "loss": 0.6045118808746338, "step": 28385, "token_acc": 0.8083665526754217 }, { "epoch": 1.837931229819294, "grad_norm": 0.3676779866218567, "learning_rate": 1.6121755686070494e-07, "loss": 0.5914732933044433, "step": 28390, "token_acc": 0.8093314821826749 }, { "epoch": 1.8382549303639202, "grad_norm": 0.3428005576133728, "learning_rate": 1.6057782472624461e-07, "loss": 0.5771743774414062, "step": 28395, "token_acc": 0.8144374551496305 }, { "epoch": 1.8385786309085463, "grad_norm": 0.40632033348083496, "learning_rate": 1.5993934367146413e-07, "loss": 0.5776586532592773, "step": 28400, "token_acc": 0.8155085403726708 }, { "epoch": 1.8389023314531727, "grad_norm": 0.3592054843902588, "learning_rate": 1.5930211386142257e-07, "loss": 0.5831953048706054, "step": 28405, "token_acc": 0.8133732877889195 }, { "epoch": 1.8392260319977989, "grad_norm": 0.4187608063220978, "learning_rate": 1.5866613546085653e-07, "loss": 0.5879387855529785, "step": 28410, "token_acc": 0.8125397794432826 }, { "epoch": 1.839549732542425, "grad_norm": 0.31659168004989624, "learning_rate": 1.5803140863417832e-07, "loss": 0.5806797981262207, "step": 28415, "token_acc": 0.814226588211828 }, { "epoch": 1.8398734330870512, "grad_norm": 0.42466670274734497, "learning_rate": 1.5739793354547507e-07, "loss": 0.5887734413146972, "step": 28420, "token_acc": 0.8110371410927204 }, { "epoch": 1.8401971336316774, "grad_norm": 0.4883805513381958, "learning_rate": 1.5676571035851296e-07, "loss": 0.5976511478424072, "step": 28425, "token_acc": 0.8105707937683497 }, { "epoch": 1.8405208341763035, "grad_norm": 0.3438090682029724, "learning_rate": 1.561347392367324e-07, "loss": 0.6131591320037841, "step": 28430, "token_acc": 0.8054118257403033 }, { "epoch": 1.8408445347209297, "grad_norm": 0.262708842754364, "learning_rate": 1.5550502034325233e-07, "loss": 0.5954771995544433, "step": 28435, "token_acc": 0.8106185697955036 }, { "epoch": 1.8411682352655558, "grad_norm": 0.3228038549423218, "learning_rate": 1.5487655384086476e-07, "loss": 0.587981128692627, "step": 28440, "token_acc": 0.8123506179782461 }, { "epoch": 1.841491935810182, "grad_norm": 0.3475252091884613, "learning_rate": 1.5424933989204193e-07, "loss": 0.5959904193878174, "step": 28445, "token_acc": 0.8086324598106144 }, { "epoch": 1.8418156363548082, "grad_norm": 0.4033214747905731, "learning_rate": 1.5362337865892807e-07, "loss": 0.5774631500244141, "step": 28450, "token_acc": 0.8145362080839116 }, { "epoch": 1.8421393368994343, "grad_norm": 0.35298991203308105, "learning_rate": 1.5299867030334815e-07, "loss": 0.5999075412750244, "step": 28455, "token_acc": 0.8088677421952595 }, { "epoch": 1.8424630374440605, "grad_norm": 0.3195127546787262, "learning_rate": 1.5237521498679851e-07, "loss": 0.6115934371948242, "step": 28460, "token_acc": 0.8055815443768023 }, { "epoch": 1.8427867379886866, "grad_norm": 0.3559489846229553, "learning_rate": 1.517530128704553e-07, "loss": 0.5802792549133301, "step": 28465, "token_acc": 0.8150326424180133 }, { "epoch": 1.8431104385333128, "grad_norm": 0.29205477237701416, "learning_rate": 1.511320641151687e-07, "loss": 0.6036479949951172, "step": 28470, "token_acc": 0.8068936850922328 }, { "epoch": 1.843434139077939, "grad_norm": 0.37151333689689636, "learning_rate": 1.5051236888146526e-07, "loss": 0.5918941974639893, "step": 28475, "token_acc": 0.8112460451281662 }, { "epoch": 1.8437578396225651, "grad_norm": 0.329267293214798, "learning_rate": 1.4989392732954688e-07, "loss": 0.5908680915832519, "step": 28480, "token_acc": 0.8112382300978647 }, { "epoch": 1.8440815401671913, "grad_norm": 0.3313192129135132, "learning_rate": 1.4927673961929456e-07, "loss": 0.5812126636505127, "step": 28485, "token_acc": 0.813190027908283 }, { "epoch": 1.8444052407118177, "grad_norm": 0.3812672197818756, "learning_rate": 1.4866080591025955e-07, "loss": 0.5789908409118653, "step": 28490, "token_acc": 0.8127849163814812 }, { "epoch": 1.8447289412564438, "grad_norm": 0.3338225483894348, "learning_rate": 1.4804612636167392e-07, "loss": 0.5740067481994628, "step": 28495, "token_acc": 0.8138075173665771 }, { "epoch": 1.84505264180107, "grad_norm": 0.29145506024360657, "learning_rate": 1.4743270113244278e-07, "loss": 0.5836912155151367, "step": 28500, "token_acc": 0.8124379462767766 }, { "epoch": 1.8453763423456961, "grad_norm": 0.3095857799053192, "learning_rate": 1.4682053038114985e-07, "loss": 0.5857921600341797, "step": 28505, "token_acc": 0.8132121469076262 }, { "epoch": 1.8457000428903223, "grad_norm": 0.3775104284286499, "learning_rate": 1.4620961426604962e-07, "loss": 0.6011552810668945, "step": 28510, "token_acc": 0.809171288061107 }, { "epoch": 1.8460237434349485, "grad_norm": 0.30443820357322693, "learning_rate": 1.455999529450769e-07, "loss": 0.5836809635162353, "step": 28515, "token_acc": 0.8115867158671587 }, { "epoch": 1.8463474439795746, "grad_norm": 0.3900969922542572, "learning_rate": 1.4499154657584002e-07, "loss": 0.6153765201568604, "step": 28520, "token_acc": 0.805411358614993 }, { "epoch": 1.8466711445242008, "grad_norm": 0.3595648407936096, "learning_rate": 1.443843953156232e-07, "loss": 0.5738586902618408, "step": 28525, "token_acc": 0.8149989898134088 }, { "epoch": 1.846994845068827, "grad_norm": 0.399332195520401, "learning_rate": 1.4377849932138533e-07, "loss": 0.5745117664337158, "step": 28530, "token_acc": 0.8146517507113983 }, { "epoch": 1.847318545613453, "grad_norm": 0.41888850927352905, "learning_rate": 1.4317385874976386e-07, "loss": 0.5935904502868652, "step": 28535, "token_acc": 0.8103236512354148 }, { "epoch": 1.8476422461580793, "grad_norm": 0.36425715684890747, "learning_rate": 1.4257047375706712e-07, "loss": 0.5855271339416503, "step": 28540, "token_acc": 0.8130882372032039 }, { "epoch": 1.8479659467027054, "grad_norm": 0.2705388367176056, "learning_rate": 1.419683444992831e-07, "loss": 0.5597472190856934, "step": 28545, "token_acc": 0.8187020889860647 }, { "epoch": 1.8482896472473316, "grad_norm": 0.32277825474739075, "learning_rate": 1.4136747113207172e-07, "loss": 0.5931585311889649, "step": 28550, "token_acc": 0.8122525360538713 }, { "epoch": 1.8486133477919577, "grad_norm": 0.33798444271087646, "learning_rate": 1.4076785381077152e-07, "loss": 0.5897981643676757, "step": 28555, "token_acc": 0.810885240667323 }, { "epoch": 1.848937048336584, "grad_norm": 0.2785498797893524, "learning_rate": 1.4016949269039236e-07, "loss": 0.6071082592010498, "step": 28560, "token_acc": 0.8095682836176499 }, { "epoch": 1.84926074888121, "grad_norm": 0.2952532470226288, "learning_rate": 1.395723879256239e-07, "loss": 0.576163387298584, "step": 28565, "token_acc": 0.8163043549411203 }, { "epoch": 1.8495844494258362, "grad_norm": 0.3900469243526459, "learning_rate": 1.3897653967082758e-07, "loss": 0.5850375175476075, "step": 28570, "token_acc": 0.8121359345184292 }, { "epoch": 1.8499081499704624, "grad_norm": 0.3082848787307739, "learning_rate": 1.3838194808004136e-07, "loss": 0.5913514137268067, "step": 28575, "token_acc": 0.8117168581185967 }, { "epoch": 1.8502318505150885, "grad_norm": 0.3454076945781708, "learning_rate": 1.3778861330697725e-07, "loss": 0.5689266681671142, "step": 28580, "token_acc": 0.8165014386429029 }, { "epoch": 1.8505555510597147, "grad_norm": 0.3468858003616333, "learning_rate": 1.3719653550502422e-07, "loss": 0.5990514755249023, "step": 28585, "token_acc": 0.8101957184103035 }, { "epoch": 1.8508792516043409, "grad_norm": 0.38639330863952637, "learning_rate": 1.3660571482724538e-07, "loss": 0.5800633430480957, "step": 28590, "token_acc": 0.8130081826708496 }, { "epoch": 1.851202952148967, "grad_norm": 0.3226420283317566, "learning_rate": 1.3601615142637858e-07, "loss": 0.5942270278930664, "step": 28595, "token_acc": 0.808961882682769 }, { "epoch": 1.8515266526935932, "grad_norm": 0.37354326248168945, "learning_rate": 1.3542784545483634e-07, "loss": 0.5947279453277587, "step": 28600, "token_acc": 0.8094603187626921 }, { "epoch": 1.8518503532382193, "grad_norm": 0.4016250967979431, "learning_rate": 1.3484079706470642e-07, "loss": 0.5607942581176758, "step": 28605, "token_acc": 0.817020879940343 }, { "epoch": 1.8521740537828455, "grad_norm": 0.41122716665267944, "learning_rate": 1.3425500640775245e-07, "loss": 0.5991900444030762, "step": 28610, "token_acc": 0.8093036208091288 }, { "epoch": 1.8524977543274717, "grad_norm": 0.44889578223228455, "learning_rate": 1.3367047363541164e-07, "loss": 0.611264705657959, "step": 28615, "token_acc": 0.8056484509940832 }, { "epoch": 1.8528214548720978, "grad_norm": 0.2912823259830475, "learning_rate": 1.330871988987964e-07, "loss": 0.5630593299865723, "step": 28620, "token_acc": 0.8175220494468443 }, { "epoch": 1.853145155416724, "grad_norm": 0.33788418769836426, "learning_rate": 1.3250518234869446e-07, "loss": 0.587399959564209, "step": 28625, "token_acc": 0.8124312201373508 }, { "epoch": 1.8534688559613501, "grad_norm": 0.25951525568962097, "learning_rate": 1.3192442413556716e-07, "loss": 0.5824138164520264, "step": 28630, "token_acc": 0.8133614472637427 }, { "epoch": 1.8537925565059763, "grad_norm": 0.32175973057746887, "learning_rate": 1.3134492440955105e-07, "loss": 0.5825742721557617, "step": 28635, "token_acc": 0.8115791993685014 }, { "epoch": 1.8541162570506025, "grad_norm": 0.37325048446655273, "learning_rate": 1.3076668332045904e-07, "loss": 0.5653495788574219, "step": 28640, "token_acc": 0.8175128912033491 }, { "epoch": 1.8544399575952286, "grad_norm": 0.37350329756736755, "learning_rate": 1.3018970101777494e-07, "loss": 0.5868482112884521, "step": 28645, "token_acc": 0.8117857142857143 }, { "epoch": 1.8547636581398548, "grad_norm": 0.3108110725879669, "learning_rate": 1.2961397765066107e-07, "loss": 0.5728143215179443, "step": 28650, "token_acc": 0.8166675658178679 }, { "epoch": 1.855087358684481, "grad_norm": 0.30936840176582336, "learning_rate": 1.2903951336795117e-07, "loss": 0.6064917087554932, "step": 28655, "token_acc": 0.807889177019877 }, { "epoch": 1.855411059229107, "grad_norm": 0.2966541051864624, "learning_rate": 1.2846630831815588e-07, "loss": 0.5886490821838379, "step": 28660, "token_acc": 0.8122442408060859 }, { "epoch": 1.8557347597737333, "grad_norm": 0.34616798162460327, "learning_rate": 1.2789436264945831e-07, "loss": 0.5983979225158691, "step": 28665, "token_acc": 0.8091205382269402 }, { "epoch": 1.8560584603183594, "grad_norm": 0.33042657375335693, "learning_rate": 1.2732367650971745e-07, "loss": 0.5946360111236573, "step": 28670, "token_acc": 0.8104441768981657 }, { "epoch": 1.8563821608629856, "grad_norm": 0.3727301061153412, "learning_rate": 1.2675425004646635e-07, "loss": 0.5807968139648437, "step": 28675, "token_acc": 0.8134064997742693 }, { "epoch": 1.8567058614076117, "grad_norm": 0.39862072467803955, "learning_rate": 1.261860834069123e-07, "loss": 0.5954802513122559, "step": 28680, "token_acc": 0.8094893303095713 }, { "epoch": 1.857029561952238, "grad_norm": 0.3126380145549774, "learning_rate": 1.2561917673793556e-07, "loss": 0.564904260635376, "step": 28685, "token_acc": 0.8165526392763125 }, { "epoch": 1.857353262496864, "grad_norm": 0.35134539008140564, "learning_rate": 1.2505353018609445e-07, "loss": 0.5861207962036132, "step": 28690, "token_acc": 0.812018367993244 }, { "epoch": 1.8576769630414902, "grad_norm": 0.36830246448516846, "learning_rate": 1.2448914389761592e-07, "loss": 0.5973448753356934, "step": 28695, "token_acc": 0.8107112926534733 }, { "epoch": 1.8580006635861164, "grad_norm": 0.35415738821029663, "learning_rate": 1.2392601801840654e-07, "loss": 0.5790829181671142, "step": 28700, "token_acc": 0.8129862012270105 }, { "epoch": 1.8583243641307425, "grad_norm": 0.3646937906742096, "learning_rate": 1.2336415269404433e-07, "loss": 0.5804753303527832, "step": 28705, "token_acc": 0.8144798759168222 }, { "epoch": 1.8586480646753687, "grad_norm": 0.33079347014427185, "learning_rate": 1.228035480697809e-07, "loss": 0.5937491893768311, "step": 28710, "token_acc": 0.8101706268723369 }, { "epoch": 1.8589717652199949, "grad_norm": 0.44130876660346985, "learning_rate": 1.2224420429054307e-07, "loss": 0.5794403553009033, "step": 28715, "token_acc": 0.814558661592257 }, { "epoch": 1.859295465764621, "grad_norm": 0.27764517068862915, "learning_rate": 1.2168612150093238e-07, "loss": 0.548492431640625, "step": 28720, "token_acc": 0.8225776141937908 }, { "epoch": 1.8596191663092472, "grad_norm": 0.31312012672424316, "learning_rate": 1.2112929984522236e-07, "loss": 0.5852845191955567, "step": 28725, "token_acc": 0.8121630165303934 }, { "epoch": 1.8599428668538733, "grad_norm": 0.2705683708190918, "learning_rate": 1.2057373946736283e-07, "loss": 0.5963920593261719, "step": 28730, "token_acc": 0.8102061045219947 }, { "epoch": 1.8602665673984995, "grad_norm": 0.28771230578422546, "learning_rate": 1.2001944051097503e-07, "loss": 0.6018524646759034, "step": 28735, "token_acc": 0.8086959364477426 }, { "epoch": 1.8605902679431257, "grad_norm": 0.33360788226127625, "learning_rate": 1.1946640311935763e-07, "loss": 0.576365852355957, "step": 28740, "token_acc": 0.8149445684986674 }, { "epoch": 1.860913968487752, "grad_norm": 0.25579240918159485, "learning_rate": 1.18914627435478e-07, "loss": 0.5636270046234131, "step": 28745, "token_acc": 0.8182439947330069 }, { "epoch": 1.8612376690323782, "grad_norm": 0.34786805510520935, "learning_rate": 1.1836411360198252e-07, "loss": 0.5780919551849365, "step": 28750, "token_acc": 0.8130738003539086 }, { "epoch": 1.8615613695770044, "grad_norm": 0.2506873905658722, "learning_rate": 1.178148617611885e-07, "loss": 0.5918601989746094, "step": 28755, "token_acc": 0.8113424169443436 }, { "epoch": 1.8618850701216305, "grad_norm": 0.3799079656600952, "learning_rate": 1.1726687205508736e-07, "loss": 0.5818385601043701, "step": 28760, "token_acc": 0.8130043481350829 }, { "epoch": 1.8622087706662567, "grad_norm": 0.3220536410808563, "learning_rate": 1.1672014462534465e-07, "loss": 0.6313385009765625, "step": 28765, "token_acc": 0.8025383540790949 }, { "epoch": 1.8625324712108828, "grad_norm": 0.31296801567077637, "learning_rate": 1.1617467961329953e-07, "loss": 0.5861471652984619, "step": 28770, "token_acc": 0.8125445058715383 }, { "epoch": 1.862856171755509, "grad_norm": 0.3125946819782257, "learning_rate": 1.1563047715996534e-07, "loss": 0.5779627799987793, "step": 28775, "token_acc": 0.8140889758995477 }, { "epoch": 1.8631798723001352, "grad_norm": 0.3756372034549713, "learning_rate": 1.150875374060273e-07, "loss": 0.573953914642334, "step": 28780, "token_acc": 0.8160254770208583 }, { "epoch": 1.8635035728447613, "grad_norm": 0.3804457485675812, "learning_rate": 1.145458604918459e-07, "loss": 0.6182926177978516, "step": 28785, "token_acc": 0.8050717857718986 }, { "epoch": 1.8638272733893875, "grad_norm": 0.33124735951423645, "learning_rate": 1.1400544655745582e-07, "loss": 0.6017640590667724, "step": 28790, "token_acc": 0.8072046386029361 }, { "epoch": 1.8641509739340136, "grad_norm": 0.40294286608695984, "learning_rate": 1.134662957425614e-07, "loss": 0.5751821041107178, "step": 28795, "token_acc": 0.8136522631039108 }, { "epoch": 1.8644746744786398, "grad_norm": 0.39487937092781067, "learning_rate": 1.1292840818654449e-07, "loss": 0.5775926589965821, "step": 28800, "token_acc": 0.8142621676255637 }, { "epoch": 1.864798375023266, "grad_norm": 0.2731483280658722, "learning_rate": 1.1239178402845941e-07, "loss": 0.5863497257232666, "step": 28805, "token_acc": 0.8118870647907084 }, { "epoch": 1.8651220755678921, "grad_norm": 0.32711830735206604, "learning_rate": 1.1185642340703295e-07, "loss": 0.5847933769226075, "step": 28810, "token_acc": 0.8132060398386384 }, { "epoch": 1.8654457761125183, "grad_norm": 0.34270504117012024, "learning_rate": 1.1132232646066498e-07, "loss": 0.5923723697662353, "step": 28815, "token_acc": 0.809971758306893 }, { "epoch": 1.8657694766571444, "grad_norm": 0.306826651096344, "learning_rate": 1.1078949332743005e-07, "loss": 0.5975201606750489, "step": 28820, "token_acc": 0.8094277074552204 }, { "epoch": 1.8660931772017706, "grad_norm": 0.38727831840515137, "learning_rate": 1.1025792414507575e-07, "loss": 0.5831534385681152, "step": 28825, "token_acc": 0.8121406672225809 }, { "epoch": 1.866416877746397, "grad_norm": 0.4221629202365875, "learning_rate": 1.0972761905102158e-07, "loss": 0.5712116718292236, "step": 28830, "token_acc": 0.815842176446109 }, { "epoch": 1.8667405782910231, "grad_norm": 0.3294749855995178, "learning_rate": 1.0919857818236179e-07, "loss": 0.5750903129577637, "step": 28835, "token_acc": 0.8158562171349657 }, { "epoch": 1.8670642788356493, "grad_norm": 0.3052281141281128, "learning_rate": 1.0867080167586307e-07, "loss": 0.5997267723083496, "step": 28840, "token_acc": 0.8086334874286817 }, { "epoch": 1.8673879793802755, "grad_norm": 0.27559858560562134, "learning_rate": 1.0814428966796464e-07, "loss": 0.5717778205871582, "step": 28845, "token_acc": 0.8155753910377328 }, { "epoch": 1.8677116799249016, "grad_norm": 0.3231881260871887, "learning_rate": 1.0761904229478092e-07, "loss": 0.5830865383148194, "step": 28850, "token_acc": 0.8135658649266231 }, { "epoch": 1.8680353804695278, "grad_norm": 0.3191392421722412, "learning_rate": 1.0709505969209721e-07, "loss": 0.5828176975250244, "step": 28855, "token_acc": 0.8121477770820288 }, { "epoch": 1.868359081014154, "grad_norm": 0.39345964789390564, "learning_rate": 1.0657234199537236e-07, "loss": 0.5894408226013184, "step": 28860, "token_acc": 0.8120751646851954 }, { "epoch": 1.86868278155878, "grad_norm": 0.30350783467292786, "learning_rate": 1.0605088933973884e-07, "loss": 0.5874760627746582, "step": 28865, "token_acc": 0.8109296864543917 }, { "epoch": 1.8690064821034063, "grad_norm": 0.30290156602859497, "learning_rate": 1.0553070186000159e-07, "loss": 0.5672390937805176, "step": 28870, "token_acc": 0.8190599553475536 }, { "epoch": 1.8693301826480324, "grad_norm": 0.3019731044769287, "learning_rate": 1.0501177969063913e-07, "loss": 0.5677722930908203, "step": 28875, "token_acc": 0.8159135946970136 }, { "epoch": 1.8696538831926586, "grad_norm": 0.34143078327178955, "learning_rate": 1.0449412296580252e-07, "loss": 0.5707415580749512, "step": 28880, "token_acc": 0.816341601969324 }, { "epoch": 1.8699775837372847, "grad_norm": 0.3497663140296936, "learning_rate": 1.039777318193147e-07, "loss": 0.5763197898864746, "step": 28885, "token_acc": 0.8142363033551976 }, { "epoch": 1.870301284281911, "grad_norm": 0.3292216658592224, "learning_rate": 1.0346260638467277e-07, "loss": 0.5828659534454346, "step": 28890, "token_acc": 0.813481788964397 }, { "epoch": 1.870624984826537, "grad_norm": 0.2940293550491333, "learning_rate": 1.0294874679504574e-07, "loss": 0.6094152927398682, "step": 28895, "token_acc": 0.8062354564911556 }, { "epoch": 1.8709486853711632, "grad_norm": 0.38484448194503784, "learning_rate": 1.0243615318327627e-07, "loss": 0.6172927379608154, "step": 28900, "token_acc": 0.8044182451458958 }, { "epoch": 1.8712723859157894, "grad_norm": 0.3700612485408783, "learning_rate": 1.019248256818789e-07, "loss": 0.58718900680542, "step": 28905, "token_acc": 0.814052529143299 }, { "epoch": 1.8715960864604155, "grad_norm": 0.3551168143749237, "learning_rate": 1.0141476442304177e-07, "loss": 0.5844422340393066, "step": 28910, "token_acc": 0.8123706494133931 }, { "epoch": 1.8719197870050417, "grad_norm": 0.37488630414009094, "learning_rate": 1.0090596953862497e-07, "loss": 0.5899063587188721, "step": 28915, "token_acc": 0.8115265479803511 }, { "epoch": 1.8722434875496679, "grad_norm": 0.383512020111084, "learning_rate": 1.0039844116015995e-07, "loss": 0.5785984516143798, "step": 28920, "token_acc": 0.813630379487966 }, { "epoch": 1.872567188094294, "grad_norm": 0.2898206412792206, "learning_rate": 9.989217941885454e-08, "loss": 0.588868522644043, "step": 28925, "token_acc": 0.8105223198774948 }, { "epoch": 1.8728908886389202, "grad_norm": 0.30796733498573303, "learning_rate": 9.938718444558405e-08, "loss": 0.5632638931274414, "step": 28930, "token_acc": 0.8175156747938255 }, { "epoch": 1.8732145891835463, "grad_norm": 0.3695075511932373, "learning_rate": 9.888345637090125e-08, "loss": 0.5719148635864257, "step": 28935, "token_acc": 0.8160887486226551 }, { "epoch": 1.8735382897281725, "grad_norm": 0.503964900970459, "learning_rate": 9.83809953250281e-08, "loss": 0.612525463104248, "step": 28940, "token_acc": 0.8072953724597318 }, { "epoch": 1.8738619902727986, "grad_norm": 0.3120588958263397, "learning_rate": 9.787980143786014e-08, "loss": 0.5859006404876709, "step": 28945, "token_acc": 0.811314393312892 }, { "epoch": 1.8741856908174248, "grad_norm": 0.40320920944213867, "learning_rate": 9.737987483896482e-08, "loss": 0.593478775024414, "step": 28950, "token_acc": 0.8113671215825169 }, { "epoch": 1.874509391362051, "grad_norm": 0.3161034882068634, "learning_rate": 9.688121565758323e-08, "loss": 0.5949908256530761, "step": 28955, "token_acc": 0.8107870521345829 }, { "epoch": 1.8748330919066771, "grad_norm": 0.3422195017337799, "learning_rate": 9.638382402262725e-08, "loss": 0.5911094665527343, "step": 28960, "token_acc": 0.8115805188011177 }, { "epoch": 1.8751567924513033, "grad_norm": 0.33957329392433167, "learning_rate": 9.588770006268233e-08, "loss": 0.5935993194580078, "step": 28965, "token_acc": 0.8110582884119375 }, { "epoch": 1.8754804929959294, "grad_norm": 0.41082993149757385, "learning_rate": 9.539284390600478e-08, "loss": 0.5967353820800781, "step": 28970, "token_acc": 0.808374791033052 }, { "epoch": 1.8758041935405556, "grad_norm": 0.33551549911499023, "learning_rate": 9.489925568052504e-08, "loss": 0.5827733516693115, "step": 28975, "token_acc": 0.812074360390208 }, { "epoch": 1.8761278940851818, "grad_norm": 0.487936407327652, "learning_rate": 9.440693551384384e-08, "loss": 0.5909733772277832, "step": 28980, "token_acc": 0.8112489427685368 }, { "epoch": 1.876451594629808, "grad_norm": 0.3452223539352417, "learning_rate": 9.391588353323544e-08, "loss": 0.5998981952667236, "step": 28985, "token_acc": 0.8083850290184372 }, { "epoch": 1.876775295174434, "grad_norm": 0.38916274905204773, "learning_rate": 9.342609986564555e-08, "loss": 0.56199631690979, "step": 28990, "token_acc": 0.8196965677543234 }, { "epoch": 1.8770989957190602, "grad_norm": 0.31268933415412903, "learning_rate": 9.293758463769342e-08, "loss": 0.5743255615234375, "step": 28995, "token_acc": 0.8164336505101164 }, { "epoch": 1.8774226962636864, "grad_norm": 0.3413991630077362, "learning_rate": 9.245033797566749e-08, "loss": 0.5808323383331299, "step": 29000, "token_acc": 0.8136983479055873 }, { "epoch": 1.8777463968083126, "grad_norm": 0.3514113426208496, "learning_rate": 9.196436000553144e-08, "loss": 0.5867229461669922, "step": 29005, "token_acc": 0.8127029710942323 }, { "epoch": 1.8780700973529387, "grad_norm": 0.3806316554546356, "learning_rate": 9.14796508529181e-08, "loss": 0.5836231231689453, "step": 29010, "token_acc": 0.812427219669342 }, { "epoch": 1.8783937978975649, "grad_norm": 0.37567171454429626, "learning_rate": 9.099621064313501e-08, "loss": 0.584116792678833, "step": 29015, "token_acc": 0.811717783907921 }, { "epoch": 1.878717498442191, "grad_norm": 0.32778218388557434, "learning_rate": 9.051403950115944e-08, "loss": 0.5824841499328614, "step": 29020, "token_acc": 0.8137711116880696 }, { "epoch": 1.8790411989868172, "grad_norm": 0.30027931928634644, "learning_rate": 9.003313755164278e-08, "loss": 0.6053277969360351, "step": 29025, "token_acc": 0.8064055641499704 }, { "epoch": 1.8793648995314434, "grad_norm": 0.33193376660346985, "learning_rate": 8.955350491890503e-08, "loss": 0.5770270347595214, "step": 29030, "token_acc": 0.8137750531138813 }, { "epoch": 1.8796886000760695, "grad_norm": 0.3220821022987366, "learning_rate": 8.907514172694198e-08, "loss": 0.584411907196045, "step": 29035, "token_acc": 0.8133555285229528 }, { "epoch": 1.8800123006206957, "grad_norm": 0.3084849417209625, "learning_rate": 8.859804809941753e-08, "loss": 0.5863637924194336, "step": 29040, "token_acc": 0.8110638951107018 }, { "epoch": 1.8803360011653218, "grad_norm": 0.3107534348964691, "learning_rate": 8.812222415967131e-08, "loss": 0.6046392917633057, "step": 29045, "token_acc": 0.805985798903646 }, { "epoch": 1.880659701709948, "grad_norm": 0.3929542005062103, "learning_rate": 8.76476700307105e-08, "loss": 0.5876918792724609, "step": 29050, "token_acc": 0.8113779403934632 }, { "epoch": 1.8809834022545742, "grad_norm": 0.25697338581085205, "learning_rate": 8.717438583521753e-08, "loss": 0.568729305267334, "step": 29055, "token_acc": 0.8169745445312004 }, { "epoch": 1.8813071027992003, "grad_norm": 0.36212238669395447, "learning_rate": 8.670237169554452e-08, "loss": 0.6140256881713867, "step": 29060, "token_acc": 0.8052335411960447 }, { "epoch": 1.8816308033438265, "grad_norm": 0.2895280718803406, "learning_rate": 8.623162773371551e-08, "loss": 0.5760573863983154, "step": 29065, "token_acc": 0.8147460199340221 }, { "epoch": 1.8819545038884526, "grad_norm": 0.4066506326198578, "learning_rate": 8.576215407142652e-08, "loss": 0.6100759506225586, "step": 29070, "token_acc": 0.8070013955283708 }, { "epoch": 1.8822782044330788, "grad_norm": 0.27221429347991943, "learning_rate": 8.529395083004599e-08, "loss": 0.57790207862854, "step": 29075, "token_acc": 0.8144217475123167 }, { "epoch": 1.882601904977705, "grad_norm": 0.24112772941589355, "learning_rate": 8.482701813061212e-08, "loss": 0.609343433380127, "step": 29080, "token_acc": 0.8062637214928984 }, { "epoch": 1.8829256055223311, "grad_norm": 0.4271285831928253, "learning_rate": 8.436135609383611e-08, "loss": 0.5968101024627686, "step": 29085, "token_acc": 0.8107657633340531 }, { "epoch": 1.8832493060669575, "grad_norm": 0.33086055517196655, "learning_rate": 8.389696484010001e-08, "loss": 0.5621286392211914, "step": 29090, "token_acc": 0.8175872335040595 }, { "epoch": 1.8835730066115837, "grad_norm": 0.2974946200847626, "learning_rate": 8.343384448945724e-08, "loss": 0.5811017036437989, "step": 29095, "token_acc": 0.8133868646518447 }, { "epoch": 1.8838967071562098, "grad_norm": 0.28641265630722046, "learning_rate": 8.297199516163312e-08, "loss": 0.577714204788208, "step": 29100, "token_acc": 0.8142544014706922 }, { "epoch": 1.884220407700836, "grad_norm": 0.36888688802719116, "learning_rate": 8.251141697602438e-08, "loss": 0.6031044960021973, "step": 29105, "token_acc": 0.8084861729634265 }, { "epoch": 1.8845441082454621, "grad_norm": 0.4360865652561188, "learning_rate": 8.205211005169911e-08, "loss": 0.5856315135955811, "step": 29110, "token_acc": 0.8107661800167206 }, { "epoch": 1.8848678087900883, "grad_norm": 0.3482767939567566, "learning_rate": 8.15940745073962e-08, "loss": 0.5858936309814453, "step": 29115, "token_acc": 0.8117352961599889 }, { "epoch": 1.8851915093347145, "grad_norm": 0.39541095495224, "learning_rate": 8.113731046152651e-08, "loss": 0.5786465644836426, "step": 29120, "token_acc": 0.8147829343776488 }, { "epoch": 1.8855152098793406, "grad_norm": 0.3928070068359375, "learning_rate": 8.068181803217113e-08, "loss": 0.5946337699890136, "step": 29125, "token_acc": 0.8113349270421026 }, { "epoch": 1.8858389104239668, "grad_norm": 0.298565149307251, "learning_rate": 8.022759733708474e-08, "loss": 0.5773486137390137, "step": 29130, "token_acc": 0.8141423940272116 }, { "epoch": 1.886162610968593, "grad_norm": 0.3402121663093567, "learning_rate": 7.977464849369066e-08, "loss": 0.5906056880950927, "step": 29135, "token_acc": 0.811751780572814 }, { "epoch": 1.886486311513219, "grad_norm": 0.40087366104125977, "learning_rate": 7.93229716190852e-08, "loss": 0.5795812606811523, "step": 29140, "token_acc": 0.8136129947957735 }, { "epoch": 1.8868100120578453, "grad_norm": 0.3277084231376648, "learning_rate": 7.887256683003442e-08, "loss": 0.5981580734252929, "step": 29145, "token_acc": 0.8088149830938293 }, { "epoch": 1.8871337126024714, "grad_norm": 0.4251009225845337, "learning_rate": 7.842343424297627e-08, "loss": 0.5996896743774414, "step": 29150, "token_acc": 0.8085621391601621 }, { "epoch": 1.8874574131470976, "grad_norm": 0.4198228120803833, "learning_rate": 7.797557397402011e-08, "loss": 0.5485268592834472, "step": 29155, "token_acc": 0.8216946057008675 }, { "epoch": 1.8877811136917237, "grad_norm": 0.3482833802700043, "learning_rate": 7.75289861389461e-08, "loss": 0.5779337882995605, "step": 29160, "token_acc": 0.8147169167803547 }, { "epoch": 1.88810481423635, "grad_norm": 0.3478686213493347, "learning_rate": 7.708367085320578e-08, "loss": 0.5821466445922852, "step": 29165, "token_acc": 0.8140072938316144 }, { "epoch": 1.888428514780976, "grad_norm": 0.3765518367290497, "learning_rate": 7.663962823192039e-08, "loss": 0.597576379776001, "step": 29170, "token_acc": 0.808646026931607 }, { "epoch": 1.8887522153256024, "grad_norm": 0.3307449221611023, "learning_rate": 7.619685838988366e-08, "loss": 0.5794121265411377, "step": 29175, "token_acc": 0.8146423375528573 }, { "epoch": 1.8890759158702286, "grad_norm": 0.2851371765136719, "learning_rate": 7.57553614415607e-08, "loss": 0.5698373317718506, "step": 29180, "token_acc": 0.8175764870321478 }, { "epoch": 1.8893996164148548, "grad_norm": 0.2258061319589615, "learning_rate": 7.53151375010841e-08, "loss": 0.5961649894714356, "step": 29185, "token_acc": 0.8101639232448163 }, { "epoch": 1.889723316959481, "grad_norm": 0.2342943251132965, "learning_rate": 7.487618668226226e-08, "loss": 0.5990504264831543, "step": 29190, "token_acc": 0.8088938053097345 }, { "epoch": 1.890047017504107, "grad_norm": 0.3288692235946655, "learning_rate": 7.443850909857109e-08, "loss": 0.5968211174011231, "step": 29195, "token_acc": 0.8105452646622328 }, { "epoch": 1.8903707180487332, "grad_norm": 0.26572898030281067, "learning_rate": 7.40021048631584e-08, "loss": 0.5636476516723633, "step": 29200, "token_acc": 0.8180538118458198 }, { "epoch": 1.8906944185933594, "grad_norm": 0.30647096037864685, "learning_rate": 7.356697408884172e-08, "loss": 0.5809598445892334, "step": 29205, "token_acc": 0.8141422025447621 }, { "epoch": 1.8910181191379856, "grad_norm": 0.24982139468193054, "learning_rate": 7.31331168881122e-08, "loss": 0.5823041915893554, "step": 29210, "token_acc": 0.8125962475250637 }, { "epoch": 1.8913418196826117, "grad_norm": 0.3749590814113617, "learning_rate": 7.2700533373129e-08, "loss": 0.5870339393615722, "step": 29215, "token_acc": 0.812952938241976 }, { "epoch": 1.8916655202272379, "grad_norm": 0.3947635293006897, "learning_rate": 7.22692236557232e-08, "loss": 0.5909783363342285, "step": 29220, "token_acc": 0.8111546871203971 }, { "epoch": 1.891989220771864, "grad_norm": 0.4099123775959015, "learning_rate": 7.183918784739507e-08, "loss": 0.6095870494842529, "step": 29225, "token_acc": 0.8066338504995119 }, { "epoch": 1.8923129213164902, "grad_norm": 0.22962923347949982, "learning_rate": 7.141042605931903e-08, "loss": 0.5871486663818359, "step": 29230, "token_acc": 0.8128049387633177 }, { "epoch": 1.8926366218611164, "grad_norm": 0.28506553173065186, "learning_rate": 7.098293840233527e-08, "loss": 0.5823151588439941, "step": 29235, "token_acc": 0.8124293124293124 }, { "epoch": 1.8929603224057425, "grad_norm": 0.3625204265117645, "learning_rate": 7.055672498695932e-08, "loss": 0.5994904041290283, "step": 29240, "token_acc": 0.808551393877202 }, { "epoch": 1.8932840229503687, "grad_norm": 0.42812448740005493, "learning_rate": 7.013178592337466e-08, "loss": 0.5805496215820313, "step": 29245, "token_acc": 0.8141291385087172 }, { "epoch": 1.8936077234949948, "grad_norm": 0.36467137932777405, "learning_rate": 6.970812132143511e-08, "loss": 0.6059844970703125, "step": 29250, "token_acc": 0.8074544841314455 }, { "epoch": 1.893931424039621, "grad_norm": 0.3615747392177582, "learning_rate": 6.928573129066585e-08, "loss": 0.5923479080200196, "step": 29255, "token_acc": 0.8108307836813061 }, { "epoch": 1.8942551245842472, "grad_norm": 0.3605741262435913, "learning_rate": 6.886461594026394e-08, "loss": 0.6001727104187011, "step": 29260, "token_acc": 0.8080527712364187 }, { "epoch": 1.8945788251288733, "grad_norm": 0.34332308173179626, "learning_rate": 6.8444775379094e-08, "loss": 0.5840620040893555, "step": 29265, "token_acc": 0.8133582901999733 }, { "epoch": 1.8949025256734995, "grad_norm": 0.28457555174827576, "learning_rate": 6.802620971569252e-08, "loss": 0.5955625057220459, "step": 29270, "token_acc": 0.8105489479126011 }, { "epoch": 1.8952262262181256, "grad_norm": 0.33149009943008423, "learning_rate": 6.760891905826683e-08, "loss": 0.5866666793823242, "step": 29275, "token_acc": 0.812111352587214 }, { "epoch": 1.8955499267627518, "grad_norm": 0.3062267005443573, "learning_rate": 6.71929035146951e-08, "loss": 0.5859328269958496, "step": 29280, "token_acc": 0.8126805054151625 }, { "epoch": 1.895873627307378, "grad_norm": 0.3653869032859802, "learning_rate": 6.677816319252351e-08, "loss": 0.5811365127563477, "step": 29285, "token_acc": 0.8141349054017001 }, { "epoch": 1.8961973278520041, "grad_norm": 0.2672649323940277, "learning_rate": 6.636469819897128e-08, "loss": 0.58297119140625, "step": 29290, "token_acc": 0.8111850422516468 }, { "epoch": 1.8965210283966303, "grad_norm": 0.3264363408088684, "learning_rate": 6.595250864092573e-08, "loss": 0.5959244251251221, "step": 29295, "token_acc": 0.8104052939435724 }, { "epoch": 1.8968447289412564, "grad_norm": 0.2678895592689514, "learning_rate": 6.554159462494602e-08, "loss": 0.5869588851928711, "step": 29300, "token_acc": 0.8117723846641437 }, { "epoch": 1.8971684294858826, "grad_norm": 0.3471051752567291, "learning_rate": 6.513195625726055e-08, "loss": 0.579188060760498, "step": 29305, "token_acc": 0.8151378981793835 }, { "epoch": 1.8974921300305088, "grad_norm": 0.45325466990470886, "learning_rate": 6.4723593643769e-08, "loss": 0.5852316379547119, "step": 29310, "token_acc": 0.811504397083216 }, { "epoch": 1.897815830575135, "grad_norm": 0.3431326746940613, "learning_rate": 6.431650689004032e-08, "loss": 0.5824343681335449, "step": 29315, "token_acc": 0.8134086197349953 }, { "epoch": 1.898139531119761, "grad_norm": 0.3160485029220581, "learning_rate": 6.391069610131362e-08, "loss": 0.5598427295684815, "step": 29320, "token_acc": 0.8171732090726911 }, { "epoch": 1.8984632316643872, "grad_norm": 0.3448595404624939, "learning_rate": 6.350616138249888e-08, "loss": 0.5911309242248535, "step": 29325, "token_acc": 0.8125063220716164 }, { "epoch": 1.8987869322090134, "grad_norm": 0.4120725691318512, "learning_rate": 6.310290283817577e-08, "loss": 0.591297721862793, "step": 29330, "token_acc": 0.8110017930514295 }, { "epoch": 1.8991106327536396, "grad_norm": 0.34276339411735535, "learning_rate": 6.270092057259314e-08, "loss": 0.5906764507293701, "step": 29335, "token_acc": 0.8110601560974295 }, { "epoch": 1.8994343332982657, "grad_norm": 0.3260226249694824, "learning_rate": 6.23002146896723e-08, "loss": 0.5797289848327637, "step": 29340, "token_acc": 0.813442258642895 }, { "epoch": 1.8997580338428919, "grad_norm": 0.3484223484992981, "learning_rate": 6.190078529300259e-08, "loss": 0.5767003536224365, "step": 29345, "token_acc": 0.8155498988816373 }, { "epoch": 1.900081734387518, "grad_norm": 0.33410966396331787, "learning_rate": 6.15026324858431e-08, "loss": 0.5868629932403564, "step": 29350, "token_acc": 0.8116187928751555 }, { "epoch": 1.9004054349321442, "grad_norm": 0.41270336508750916, "learning_rate": 6.110575637112426e-08, "loss": 0.5806546211242676, "step": 29355, "token_acc": 0.8140446032606962 }, { "epoch": 1.9007291354767704, "grad_norm": 0.30005332827568054, "learning_rate": 6.071015705144568e-08, "loss": 0.5673135280609131, "step": 29360, "token_acc": 0.8161301808859137 }, { "epoch": 1.9010528360213965, "grad_norm": 0.2621200382709503, "learning_rate": 6.03158346290772e-08, "loss": 0.5989467620849609, "step": 29365, "token_acc": 0.8090755839955964 }, { "epoch": 1.9013765365660227, "grad_norm": 0.30228933691978455, "learning_rate": 5.992278920595839e-08, "loss": 0.5572944641113281, "step": 29370, "token_acc": 0.8196850138009417 }, { "epoch": 1.9017002371106488, "grad_norm": 0.38103634119033813, "learning_rate": 5.953102088369911e-08, "loss": 0.5655049800872802, "step": 29375, "token_acc": 0.8175660448228371 }, { "epoch": 1.902023937655275, "grad_norm": 0.3189229369163513, "learning_rate": 5.914052976357776e-08, "loss": 0.5731976985931396, "step": 29380, "token_acc": 0.815417826211345 }, { "epoch": 1.9023476381999012, "grad_norm": 0.22813540697097778, "learning_rate": 5.875131594654415e-08, "loss": 0.5688034057617187, "step": 29385, "token_acc": 0.817062165562998 }, { "epoch": 1.9026713387445273, "grad_norm": 0.3882611393928528, "learning_rate": 5.836337953321669e-08, "loss": 0.5802187442779541, "step": 29390, "token_acc": 0.8131463211696185 }, { "epoch": 1.9029950392891535, "grad_norm": 0.36592745780944824, "learning_rate": 5.79767206238846e-08, "loss": 0.5893004417419434, "step": 29395, "token_acc": 0.8099656540376474 }, { "epoch": 1.9033187398337796, "grad_norm": 0.3796146810054779, "learning_rate": 5.75913393185068e-08, "loss": 0.607360553741455, "step": 29400, "token_acc": 0.8073155251393564 }, { "epoch": 1.9036424403784058, "grad_norm": 0.4786016047000885, "learning_rate": 5.7207235716710274e-08, "loss": 0.5693157196044922, "step": 29405, "token_acc": 0.816586983343615 }, { "epoch": 1.903966140923032, "grad_norm": 0.3705671727657318, "learning_rate": 5.6824409917793366e-08, "loss": 0.5770243644714356, "step": 29410, "token_acc": 0.813775978724811 }, { "epoch": 1.9042898414676581, "grad_norm": 0.3437530994415283, "learning_rate": 5.644286202072413e-08, "loss": 0.5785627841949463, "step": 29415, "token_acc": 0.8144060689234522 }, { "epoch": 1.9046135420122843, "grad_norm": 0.2628321647644043, "learning_rate": 5.606259212413867e-08, "loss": 0.5660230636596679, "step": 29420, "token_acc": 0.8174359042944457 }, { "epoch": 1.9049372425569104, "grad_norm": 0.3037952184677124, "learning_rate": 5.568360032634445e-08, "loss": 0.5649650573730469, "step": 29425, "token_acc": 0.8187260407509075 }, { "epoch": 1.9052609431015368, "grad_norm": 0.3472951650619507, "learning_rate": 5.530588672531756e-08, "loss": 0.5534515857696534, "step": 29430, "token_acc": 0.8218037891795932 }, { "epoch": 1.905584643646163, "grad_norm": 0.43946537375450134, "learning_rate": 5.492945141870432e-08, "loss": 0.5868183612823487, "step": 29435, "token_acc": 0.8114173998044966 }, { "epoch": 1.9059083441907891, "grad_norm": 0.3363897502422333, "learning_rate": 5.455429450381966e-08, "loss": 0.5847843647003174, "step": 29440, "token_acc": 0.812235570645077 }, { "epoch": 1.9062320447354153, "grad_norm": 0.3230562210083008, "learning_rate": 5.418041607764934e-08, "loss": 0.5683218479156494, "step": 29445, "token_acc": 0.8157691163344243 }, { "epoch": 1.9065557452800415, "grad_norm": 0.36541619896888733, "learning_rate": 5.3807816236846614e-08, "loss": 0.6015649795532226, "step": 29450, "token_acc": 0.8076415206454424 }, { "epoch": 1.9068794458246676, "grad_norm": 0.3753396272659302, "learning_rate": 5.3436495077736626e-08, "loss": 0.6121631145477295, "step": 29455, "token_acc": 0.8060905496520504 }, { "epoch": 1.9072031463692938, "grad_norm": 0.30351781845092773, "learning_rate": 5.30664526963115e-08, "loss": 0.6062748908996582, "step": 29460, "token_acc": 0.8066308499989786 }, { "epoch": 1.90752684691392, "grad_norm": 0.24021326005458832, "learning_rate": 5.2697689188235255e-08, "loss": 0.5890585899353027, "step": 29465, "token_acc": 0.8110279855915766 }, { "epoch": 1.907850547458546, "grad_norm": 0.2979341149330139, "learning_rate": 5.233020464883887e-08, "loss": 0.5772913455963135, "step": 29470, "token_acc": 0.8141188586028444 }, { "epoch": 1.9081742480031723, "grad_norm": 0.2845975160598755, "learning_rate": 5.196399917312467e-08, "loss": 0.5901806354522705, "step": 29475, "token_acc": 0.8124920767729013 }, { "epoch": 1.9084979485477984, "grad_norm": 0.42189908027648926, "learning_rate": 5.1599072855763045e-08, "loss": 0.6181430816650391, "step": 29480, "token_acc": 0.8051208448274727 }, { "epoch": 1.9088216490924246, "grad_norm": 0.3846147954463959, "learning_rate": 5.123542579109464e-08, "loss": 0.581566047668457, "step": 29485, "token_acc": 0.8127833212854932 }, { "epoch": 1.9091453496370507, "grad_norm": 0.1941436380147934, "learning_rate": 5.08730580731287e-08, "loss": 0.5873302459716797, "step": 29490, "token_acc": 0.8120235701258008 }, { "epoch": 1.909469050181677, "grad_norm": 0.2512357532978058, "learning_rate": 5.0511969795543624e-08, "loss": 0.5722295761108398, "step": 29495, "token_acc": 0.8167640031855588 }, { "epoch": 1.909792750726303, "grad_norm": 0.35651251673698425, "learning_rate": 5.0152161051688074e-08, "loss": 0.5892555713653564, "step": 29500, "token_acc": 0.8122730573710966 }, { "epoch": 1.9101164512709292, "grad_norm": 0.36156123876571655, "learning_rate": 4.9793631934578204e-08, "loss": 0.5628208637237548, "step": 29505, "token_acc": 0.8183789644890214 }, { "epoch": 1.9104401518155554, "grad_norm": 0.3177362084388733, "learning_rate": 4.943638253690153e-08, "loss": 0.5983798980712891, "step": 29510, "token_acc": 0.8091037402964009 }, { "epoch": 1.9107638523601818, "grad_norm": 0.28626859188079834, "learning_rate": 4.908041295101307e-08, "loss": 0.5790454387664795, "step": 29515, "token_acc": 0.8143377222632242 }, { "epoch": 1.911087552904808, "grad_norm": 0.3224135637283325, "learning_rate": 4.872572326893699e-08, "loss": 0.5817524909973144, "step": 29520, "token_acc": 0.8149138157599534 }, { "epoch": 1.911411253449434, "grad_norm": 0.38414764404296875, "learning_rate": 4.837231358236827e-08, "loss": 0.5927958011627197, "step": 29525, "token_acc": 0.8102052420665006 }, { "epoch": 1.9117349539940602, "grad_norm": 0.29655399918556213, "learning_rate": 4.802018398266828e-08, "loss": 0.587675952911377, "step": 29530, "token_acc": 0.8113209935136846 }, { "epoch": 1.9120586545386864, "grad_norm": 0.2606968283653259, "learning_rate": 4.766933456087086e-08, "loss": 0.5955822944641114, "step": 29535, "token_acc": 0.8107972809190073 }, { "epoch": 1.9123823550833126, "grad_norm": 0.32543179392814636, "learning_rate": 4.7319765407675135e-08, "loss": 0.5920497894287109, "step": 29540, "token_acc": 0.8101100469627166 }, { "epoch": 1.9127060556279387, "grad_norm": 0.3880055844783783, "learning_rate": 4.697147661345269e-08, "loss": 0.5697394371032715, "step": 29545, "token_acc": 0.8161497052037939 }, { "epoch": 1.9130297561725649, "grad_norm": 0.26334860920906067, "learning_rate": 4.662446826824207e-08, "loss": 0.5709447860717773, "step": 29550, "token_acc": 0.8155975613313498 }, { "epoch": 1.913353456717191, "grad_norm": 0.3765723407268524, "learning_rate": 4.627874046175096e-08, "loss": 0.5897690296173096, "step": 29555, "token_acc": 0.8122889891836119 }, { "epoch": 1.9136771572618172, "grad_norm": 0.28274261951446533, "learning_rate": 4.593429328335619e-08, "loss": 0.5780274391174316, "step": 29560, "token_acc": 0.8142360185530735 }, { "epoch": 1.9140008578064434, "grad_norm": 0.39581912755966187, "learning_rate": 4.5591126822105424e-08, "loss": 0.5975417137145996, "step": 29565, "token_acc": 0.8103827627901445 }, { "epoch": 1.9143245583510695, "grad_norm": 0.38197898864746094, "learning_rate": 4.524924116671103e-08, "loss": 0.5861856460571289, "step": 29570, "token_acc": 0.8125549411597902 }, { "epoch": 1.9146482588956957, "grad_norm": 0.4618681073188782, "learning_rate": 4.490863640555843e-08, "loss": 0.5782647132873535, "step": 29575, "token_acc": 0.8142743304576794 }, { "epoch": 1.9149719594403218, "grad_norm": 0.4331124722957611, "learning_rate": 4.456931262669939e-08, "loss": 0.6020595073699951, "step": 29580, "token_acc": 0.8081391872770393 }, { "epoch": 1.915295659984948, "grad_norm": 0.29374295473098755, "learning_rate": 4.4231269917855976e-08, "loss": 0.5986007690429688, "step": 29585, "token_acc": 0.8097026123957076 }, { "epoch": 1.9156193605295742, "grad_norm": 0.33562496304512024, "learning_rate": 4.389450836641773e-08, "loss": 0.5878048419952393, "step": 29590, "token_acc": 0.8126307171775963 }, { "epoch": 1.9159430610742003, "grad_norm": 0.28501471877098083, "learning_rate": 4.355902805944445e-08, "loss": 0.577731990814209, "step": 29595, "token_acc": 0.8150723796202214 }, { "epoch": 1.9162667616188265, "grad_norm": 0.4856882095336914, "learning_rate": 4.3224829083663985e-08, "loss": 0.5728161811828614, "step": 29600, "token_acc": 0.8146786422145431 }, { "epoch": 1.9165904621634526, "grad_norm": 0.3182126581668854, "learning_rate": 4.289191152547223e-08, "loss": 0.5959715366363525, "step": 29605, "token_acc": 0.8095017576357169 }, { "epoch": 1.9169141627080788, "grad_norm": 0.3696821630001068, "learning_rate": 4.256027547093478e-08, "loss": 0.5939080238342285, "step": 29610, "token_acc": 0.8099524444153139 }, { "epoch": 1.917237863252705, "grad_norm": 0.3030305802822113, "learning_rate": 4.2229921005785824e-08, "loss": 0.5939681053161621, "step": 29615, "token_acc": 0.8098012121073122 }, { "epoch": 1.9175615637973311, "grad_norm": 0.3884377181529999, "learning_rate": 4.190084821542817e-08, "loss": 0.5938408851623536, "step": 29620, "token_acc": 0.8101491364675842 }, { "epoch": 1.9178852643419573, "grad_norm": 0.2981163561344147, "learning_rate": 4.157305718493265e-08, "loss": 0.5740984439849853, "step": 29625, "token_acc": 0.8163584132210064 }, { "epoch": 1.9182089648865834, "grad_norm": 0.35665005445480347, "learning_rate": 4.124654799903982e-08, "loss": 0.5683915138244628, "step": 29630, "token_acc": 0.8190391756286217 }, { "epoch": 1.9185326654312096, "grad_norm": 0.38060590624809265, "learning_rate": 4.092132074215827e-08, "loss": 0.6051250457763672, "step": 29635, "token_acc": 0.8068652489777555 }, { "epoch": 1.9188563659758358, "grad_norm": 0.3993053436279297, "learning_rate": 4.0597375498365175e-08, "loss": 0.5610968112945557, "step": 29640, "token_acc": 0.8176795965000279 }, { "epoch": 1.919180066520462, "grad_norm": 0.34189069271087646, "learning_rate": 4.027471235140579e-08, "loss": 0.5848625183105469, "step": 29645, "token_acc": 0.812280792576391 }, { "epoch": 1.919503767065088, "grad_norm": 0.29242831468582153, "learning_rate": 3.995333138469504e-08, "loss": 0.5694612026214599, "step": 29650, "token_acc": 0.8168887916356102 }, { "epoch": 1.9198274676097142, "grad_norm": 0.31786879897117615, "learning_rate": 3.963323268131592e-08, "loss": 0.5627144336700439, "step": 29655, "token_acc": 0.8181782772119112 }, { "epoch": 1.9201511681543404, "grad_norm": 0.31318166851997375, "learning_rate": 3.931441632401944e-08, "loss": 0.600270938873291, "step": 29660, "token_acc": 0.8097123623011016 }, { "epoch": 1.9204748686989666, "grad_norm": 0.4397692382335663, "learning_rate": 3.899688239522525e-08, "loss": 0.582939624786377, "step": 29665, "token_acc": 0.8139541002585067 }, { "epoch": 1.9207985692435927, "grad_norm": 0.379002183675766, "learning_rate": 3.868063097702324e-08, "loss": 0.5929255008697509, "step": 29670, "token_acc": 0.8128483697122013 }, { "epoch": 1.9211222697882189, "grad_norm": 0.2784947454929352, "learning_rate": 3.836566215116799e-08, "loss": 0.6057531833648682, "step": 29675, "token_acc": 0.8072390572390572 }, { "epoch": 1.921445970332845, "grad_norm": 0.29556626081466675, "learning_rate": 3.805197599908661e-08, "loss": 0.56791672706604, "step": 29680, "token_acc": 0.8174746529196936 }, { "epoch": 1.9217696708774712, "grad_norm": 0.39968496561050415, "learning_rate": 3.7739572601872e-08, "loss": 0.5873870849609375, "step": 29685, "token_acc": 0.8121404250322883 }, { "epoch": 1.9220933714220974, "grad_norm": 0.312712162733078, "learning_rate": 3.742845204028567e-08, "loss": 0.5761700630187988, "step": 29690, "token_acc": 0.8148818767147671 }, { "epoch": 1.9224170719667235, "grad_norm": 0.3053032457828522, "learning_rate": 3.711861439475884e-08, "loss": 0.5718563079833985, "step": 29695, "token_acc": 0.8165888584168987 }, { "epoch": 1.9227407725113497, "grad_norm": 0.25799113512039185, "learning_rate": 3.6810059745390204e-08, "loss": 0.5996273994445801, "step": 29700, "token_acc": 0.8110097265352467 }, { "epoch": 1.9230644730559758, "grad_norm": 0.35283318161964417, "learning_rate": 3.6502788171945966e-08, "loss": 0.5816853523254395, "step": 29705, "token_acc": 0.8142688170718184 }, { "epoch": 1.923388173600602, "grad_norm": 0.35322779417037964, "learning_rate": 3.619679975386203e-08, "loss": 0.582574462890625, "step": 29710, "token_acc": 0.813491257898343 }, { "epoch": 1.9237118741452282, "grad_norm": 0.38089719414711, "learning_rate": 3.5892094570242345e-08, "loss": 0.5643949031829834, "step": 29715, "token_acc": 0.8184201834738708 }, { "epoch": 1.9240355746898543, "grad_norm": 0.2816852927207947, "learning_rate": 3.5588672699858885e-08, "loss": 0.5787210464477539, "step": 29720, "token_acc": 0.814140585967025 }, { "epoch": 1.9243592752344805, "grad_norm": 0.3354380428791046, "learning_rate": 3.528653422115058e-08, "loss": 0.5868836879730225, "step": 29725, "token_acc": 0.8122400070806582 }, { "epoch": 1.9246829757791066, "grad_norm": 0.3240512013435364, "learning_rate": 3.4985679212227175e-08, "loss": 0.5949860572814941, "step": 29730, "token_acc": 0.8120319967287689 }, { "epoch": 1.9250066763237328, "grad_norm": 0.4051561951637268, "learning_rate": 3.4686107750864785e-08, "loss": 0.5981053829193115, "step": 29735, "token_acc": 0.8071833083165392 }, { "epoch": 1.925330376868359, "grad_norm": 0.3941391110420227, "learning_rate": 3.438781991450812e-08, "loss": 0.5977519512176513, "step": 29740, "token_acc": 0.809658264342582 }, { "epoch": 1.925654077412985, "grad_norm": 0.2726207375526428, "learning_rate": 3.40908157802694e-08, "loss": 0.5786013603210449, "step": 29745, "token_acc": 0.8144822999795376 }, { "epoch": 1.9259777779576113, "grad_norm": 0.4006578028202057, "learning_rate": 3.3795095424930535e-08, "loss": 0.5989896774291992, "step": 29750, "token_acc": 0.8102030280958072 }, { "epoch": 1.9263014785022374, "grad_norm": 0.39611122012138367, "learning_rate": 3.350065892494092e-08, "loss": 0.5679657936096192, "step": 29755, "token_acc": 0.8179873988320869 }, { "epoch": 1.9266251790468636, "grad_norm": 0.37244534492492676, "learning_rate": 3.3207506356416896e-08, "loss": 0.5923634529113769, "step": 29760, "token_acc": 0.8126623079575764 }, { "epoch": 1.9269488795914897, "grad_norm": 0.3798404335975647, "learning_rate": 3.291563779514395e-08, "loss": 0.5706295490264892, "step": 29765, "token_acc": 0.8163966428429238 }, { "epoch": 1.9272725801361161, "grad_norm": 0.30146172642707825, "learning_rate": 3.262505331657617e-08, "loss": 0.5918014526367188, "step": 29770, "token_acc": 0.8113511862046425 }, { "epoch": 1.9275962806807423, "grad_norm": 0.371146023273468, "learning_rate": 3.2335752995834024e-08, "loss": 0.5812792778015137, "step": 29775, "token_acc": 0.8132822591421317 }, { "epoch": 1.9279199812253685, "grad_norm": 0.29849594831466675, "learning_rate": 3.204773690770768e-08, "loss": 0.5997792243957519, "step": 29780, "token_acc": 0.8086516463562528 }, { "epoch": 1.9282436817699946, "grad_norm": 0.4181983470916748, "learning_rate": 3.1761005126654256e-08, "loss": 0.5835773944854736, "step": 29785, "token_acc": 0.8131632634529351 }, { "epoch": 1.9285673823146208, "grad_norm": 0.40042978525161743, "learning_rate": 3.1475557726799444e-08, "loss": 0.5732242584228515, "step": 29790, "token_acc": 0.8147178477690289 }, { "epoch": 1.928891082859247, "grad_norm": 0.3329901099205017, "learning_rate": 3.1191394781936445e-08, "loss": 0.5739415168762207, "step": 29795, "token_acc": 0.8145586824432364 }, { "epoch": 1.929214783403873, "grad_norm": 0.38579753041267395, "learning_rate": 3.090851636552705e-08, "loss": 0.5881896018981934, "step": 29800, "token_acc": 0.8123150136382102 }, { "epoch": 1.9295384839484993, "grad_norm": 0.2775738537311554, "learning_rate": 3.062692255069999e-08, "loss": 0.5729144096374512, "step": 29805, "token_acc": 0.8154690684373151 }, { "epoch": 1.9298621844931254, "grad_norm": 0.2845875322818756, "learning_rate": 3.034661341025258e-08, "loss": 0.5770316600799561, "step": 29810, "token_acc": 0.8143054504991655 }, { "epoch": 1.9301858850377516, "grad_norm": 0.3775562047958374, "learning_rate": 3.006758901665019e-08, "loss": 0.5759816646575928, "step": 29815, "token_acc": 0.8142602545571912 }, { "epoch": 1.9305095855823777, "grad_norm": 0.3031672239303589, "learning_rate": 2.9789849442025122e-08, "loss": 0.5757213115692139, "step": 29820, "token_acc": 0.8137664906372609 }, { "epoch": 1.930833286127004, "grad_norm": 0.28719034790992737, "learning_rate": 2.9513394758178825e-08, "loss": 0.5891547203063965, "step": 29825, "token_acc": 0.8117675462636703 }, { "epoch": 1.93115698667163, "grad_norm": 0.3812742233276367, "learning_rate": 2.9238225036579693e-08, "loss": 0.5690175533294678, "step": 29830, "token_acc": 0.8151567005951691 }, { "epoch": 1.9314806872162562, "grad_norm": 0.28933268785476685, "learning_rate": 2.896434034836415e-08, "loss": 0.5900057315826416, "step": 29835, "token_acc": 0.811492094342596 }, { "epoch": 1.9318043877608824, "grad_norm": 0.4068340063095093, "learning_rate": 2.8691740764336118e-08, "loss": 0.6064192771911621, "step": 29840, "token_acc": 0.8090093645953361 }, { "epoch": 1.9321280883055085, "grad_norm": 0.305351585149765, "learning_rate": 2.842042635496811e-08, "loss": 0.5869458675384521, "step": 29845, "token_acc": 0.8132349920402608 }, { "epoch": 1.9324517888501347, "grad_norm": 0.30226555466651917, "learning_rate": 2.815039719039958e-08, "loss": 0.5939374923706054, "step": 29850, "token_acc": 0.8109746774011262 }, { "epoch": 1.932775489394761, "grad_norm": 0.2547888457775116, "learning_rate": 2.7881653340438575e-08, "loss": 0.5939952850341796, "step": 29855, "token_acc": 0.8116988049539163 }, { "epoch": 1.9330991899393872, "grad_norm": 0.3480433225631714, "learning_rate": 2.761419487455952e-08, "loss": 0.5789199829101562, "step": 29860, "token_acc": 0.8153829493116914 }, { "epoch": 1.9334228904840134, "grad_norm": 0.3343488276004791, "learning_rate": 2.7348021861905437e-08, "loss": 0.5886806964874267, "step": 29865, "token_acc": 0.8128347123591113 }, { "epoch": 1.9337465910286395, "grad_norm": 0.3671160340309143, "learning_rate": 2.7083134371287957e-08, "loss": 0.5950784683227539, "step": 29870, "token_acc": 0.810580204778157 }, { "epoch": 1.9340702915732657, "grad_norm": 0.2726690471172333, "learning_rate": 2.6819532471183962e-08, "loss": 0.6083380699157714, "step": 29875, "token_acc": 0.8068046147265193 }, { "epoch": 1.9343939921178919, "grad_norm": 0.30664384365081787, "learning_rate": 2.6557216229740058e-08, "loss": 0.5960630893707275, "step": 29880, "token_acc": 0.8098331522163318 }, { "epoch": 1.934717692662518, "grad_norm": 0.34150123596191406, "learning_rate": 2.629618571477033e-08, "loss": 0.5819798469543457, "step": 29885, "token_acc": 0.8132353831560677 }, { "epoch": 1.9350413932071442, "grad_norm": 0.26293784379959106, "learning_rate": 2.603644099375524e-08, "loss": 0.5939103126525879, "step": 29890, "token_acc": 0.8084296077377754 }, { "epoch": 1.9353650937517703, "grad_norm": 0.33054912090301514, "learning_rate": 2.577798213384386e-08, "loss": 0.5865084648132324, "step": 29895, "token_acc": 0.8116371649095468 }, { "epoch": 1.9356887942963965, "grad_norm": 0.3409588932991028, "learning_rate": 2.5520809201852183e-08, "loss": 0.579673957824707, "step": 29900, "token_acc": 0.8140272620646487 }, { "epoch": 1.9360124948410227, "grad_norm": 0.351272314786911, "learning_rate": 2.5264922264265356e-08, "loss": 0.5750021457672119, "step": 29905, "token_acc": 0.8140888841465042 }, { "epoch": 1.9363361953856488, "grad_norm": 0.343021422624588, "learning_rate": 2.5010321387233248e-08, "loss": 0.5728131771087647, "step": 29910, "token_acc": 0.8148632557049993 }, { "epoch": 1.936659895930275, "grad_norm": 0.3238738179206848, "learning_rate": 2.4757006636575432e-08, "loss": 0.5866805076599121, "step": 29915, "token_acc": 0.8123354980148235 }, { "epoch": 1.9369835964749011, "grad_norm": 0.3903043568134308, "learning_rate": 2.4504978077778962e-08, "loss": 0.5727003574371338, "step": 29920, "token_acc": 0.8165389688945998 }, { "epoch": 1.9373072970195273, "grad_norm": 0.4167115390300751, "learning_rate": 2.4254235775997835e-08, "loss": 0.5788278579711914, "step": 29925, "token_acc": 0.8137919372294372 }, { "epoch": 1.9376309975641535, "grad_norm": 0.36617669463157654, "learning_rate": 2.4004779796052424e-08, "loss": 0.5895508766174317, "step": 29930, "token_acc": 0.8118435723429736 }, { "epoch": 1.9379546981087796, "grad_norm": 0.36031606793403625, "learning_rate": 2.3756610202432805e-08, "loss": 0.597810935974121, "step": 29935, "token_acc": 0.809253475411844 }, { "epoch": 1.9382783986534058, "grad_norm": 0.37520015239715576, "learning_rate": 2.350972705929544e-08, "loss": 0.569661283493042, "step": 29940, "token_acc": 0.8169005999024083 }, { "epoch": 1.938602099198032, "grad_norm": 0.31964388489723206, "learning_rate": 2.326413043046316e-08, "loss": 0.5849875450134278, "step": 29945, "token_acc": 0.812853800519782 }, { "epoch": 1.938925799742658, "grad_norm": 0.33997228741645813, "learning_rate": 2.3019820379427958e-08, "loss": 0.581880521774292, "step": 29950, "token_acc": 0.8125355242081331 }, { "epoch": 1.9392495002872843, "grad_norm": 0.3831128180027008, "learning_rate": 2.2776796969348757e-08, "loss": 0.5895407199859619, "step": 29955, "token_acc": 0.8109242393200599 }, { "epoch": 1.9395732008319104, "grad_norm": 0.31415438652038574, "learning_rate": 2.2535060263050855e-08, "loss": 0.5852593421936035, "step": 29960, "token_acc": 0.8131080813816247 }, { "epoch": 1.9398969013765366, "grad_norm": 0.3134956359863281, "learning_rate": 2.2294610323028154e-08, "loss": 0.567507266998291, "step": 29965, "token_acc": 0.8171364912669303 }, { "epoch": 1.9402206019211627, "grad_norm": 0.2503584325313568, "learning_rate": 2.205544721144093e-08, "loss": 0.5944766044616699, "step": 29970, "token_acc": 0.8113025288458976 }, { "epoch": 1.940544302465789, "grad_norm": 0.4152255654335022, "learning_rate": 2.1817570990118053e-08, "loss": 0.6024272441864014, "step": 29975, "token_acc": 0.8080950877722725 }, { "epoch": 1.940868003010415, "grad_norm": 0.4365973472595215, "learning_rate": 2.1580981720553674e-08, "loss": 0.5825493335723877, "step": 29980, "token_acc": 0.8128181741734749 }, { "epoch": 1.9411917035550412, "grad_norm": 0.2532629370689392, "learning_rate": 2.134567946391164e-08, "loss": 0.5826168537139893, "step": 29985, "token_acc": 0.8130085534623948 }, { "epoch": 1.9415154040996674, "grad_norm": 0.3942984342575073, "learning_rate": 2.111166428102107e-08, "loss": 0.5865542411804199, "step": 29990, "token_acc": 0.8125735665041197 }, { "epoch": 1.9418391046442935, "grad_norm": 0.3169024586677551, "learning_rate": 2.0878936232380244e-08, "loss": 0.5773403644561768, "step": 29995, "token_acc": 0.8128863414866864 }, { "epoch": 1.9421628051889197, "grad_norm": 0.3719084560871124, "learning_rate": 2.0647495378152137e-08, "loss": 0.5803543090820312, "step": 30000, "token_acc": 0.8118341213300182 }, { "epoch": 1.9424865057335459, "grad_norm": 0.2988846004009247, "learning_rate": 2.041734177817001e-08, "loss": 0.5657333374023438, "step": 30005, "token_acc": 0.8176010587868492 }, { "epoch": 1.942810206278172, "grad_norm": 0.3362090587615967, "learning_rate": 2.018847549193126e-08, "loss": 0.5987734794616699, "step": 30010, "token_acc": 0.8096168444107069 }, { "epoch": 1.9431339068227982, "grad_norm": 0.2811208963394165, "learning_rate": 1.996089657860356e-08, "loss": 0.5933868885040283, "step": 30015, "token_acc": 0.8103743137581101 }, { "epoch": 1.9434576073674243, "grad_norm": 0.2922621965408325, "learning_rate": 1.97346050970193e-08, "loss": 0.6171135902404785, "step": 30020, "token_acc": 0.8060110663983904 }, { "epoch": 1.9437813079120505, "grad_norm": 0.3285737931728363, "learning_rate": 1.9509601105679453e-08, "loss": 0.5941544532775879, "step": 30025, "token_acc": 0.8107005943345255 }, { "epoch": 1.9441050084566767, "grad_norm": 0.30913883447647095, "learning_rate": 1.9285884662750832e-08, "loss": 0.5732960224151611, "step": 30030, "token_acc": 0.8157170998772002 }, { "epoch": 1.9444287090013028, "grad_norm": 0.32811444997787476, "learning_rate": 1.9063455826069388e-08, "loss": 0.6141761302947998, "step": 30035, "token_acc": 0.8052300798984913 }, { "epoch": 1.944752409545929, "grad_norm": 0.22800233960151672, "learning_rate": 1.8842314653136907e-08, "loss": 0.5629295349121094, "step": 30040, "token_acc": 0.8191321458585279 }, { "epoch": 1.9450761100905551, "grad_norm": 0.2737078368663788, "learning_rate": 1.8622461201121545e-08, "loss": 0.5717148780822754, "step": 30045, "token_acc": 0.816240712505143 }, { "epoch": 1.9453998106351813, "grad_norm": 0.33838382363319397, "learning_rate": 1.8403895526860062e-08, "loss": 0.5864665508270264, "step": 30050, "token_acc": 0.8126072553321222 }, { "epoch": 1.9457235111798075, "grad_norm": 0.3310241103172302, "learning_rate": 1.8186617686856145e-08, "loss": 0.5880932807922363, "step": 30055, "token_acc": 0.8122113904566445 }, { "epoch": 1.9460472117244336, "grad_norm": 0.33206361532211304, "learning_rate": 1.797062773727931e-08, "loss": 0.5940081119537354, "step": 30060, "token_acc": 0.8125 }, { "epoch": 1.9463709122690598, "grad_norm": 0.3693242371082306, "learning_rate": 1.7755925733967118e-08, "loss": 0.5845967292785644, "step": 30065, "token_acc": 0.8138539959949026 }, { "epoch": 1.946694612813686, "grad_norm": 0.25274932384490967, "learning_rate": 1.7542511732424605e-08, "loss": 0.5521420955657959, "step": 30070, "token_acc": 0.8219061811584812 }, { "epoch": 1.947018313358312, "grad_norm": 0.286105751991272, "learning_rate": 1.7330385787822645e-08, "loss": 0.5778824806213378, "step": 30075, "token_acc": 0.8162766955466034 }, { "epoch": 1.9473420139029383, "grad_norm": 0.41855865716934204, "learning_rate": 1.7119547954999593e-08, "loss": 0.5904989242553711, "step": 30080, "token_acc": 0.812501689600173 }, { "epoch": 1.9476657144475644, "grad_norm": 0.3495219647884369, "learning_rate": 1.6909998288461292e-08, "loss": 0.605185604095459, "step": 30085, "token_acc": 0.8091172521026221 }, { "epoch": 1.9479894149921906, "grad_norm": 0.3874102234840393, "learning_rate": 1.670173684237997e-08, "loss": 0.5874824047088623, "step": 30090, "token_acc": 0.8118101241432465 }, { "epoch": 1.9483131155368167, "grad_norm": 0.3685978651046753, "learning_rate": 1.649476367059477e-08, "loss": 0.6013567924499512, "step": 30095, "token_acc": 0.8102811151740282 }, { "epoch": 1.948636816081443, "grad_norm": 0.30182909965515137, "learning_rate": 1.62890788266129e-08, "loss": 0.5765318393707275, "step": 30100, "token_acc": 0.8155622719664768 }, { "epoch": 1.948960516626069, "grad_norm": 0.41279563307762146, "learning_rate": 1.608468236360683e-08, "loss": 0.5744367122650147, "step": 30105, "token_acc": 0.8150430341729186 }, { "epoch": 1.9492842171706954, "grad_norm": 0.2783951163291931, "learning_rate": 1.5881574334417617e-08, "loss": 0.5870861053466797, "step": 30110, "token_acc": 0.8113673758046358 }, { "epoch": 1.9496079177153216, "grad_norm": 0.3144550621509552, "learning_rate": 1.5679754791551594e-08, "loss": 0.6016420364379883, "step": 30115, "token_acc": 0.8083893764960675 }, { "epoch": 1.9499316182599478, "grad_norm": 0.3980986773967743, "learning_rate": 1.547922378718314e-08, "loss": 0.5863885879516602, "step": 30120, "token_acc": 0.8138243808749412 }, { "epoch": 1.950255318804574, "grad_norm": 0.2687034606933594, "learning_rate": 1.527998137315356e-08, "loss": 0.5913163185119629, "step": 30125, "token_acc": 0.8122907145715309 }, { "epoch": 1.9505790193492, "grad_norm": 0.42929887771606445, "learning_rate": 1.5082027600969996e-08, "loss": 0.6066089630126953, "step": 30130, "token_acc": 0.8081294819382079 }, { "epoch": 1.9509027198938262, "grad_norm": 0.2726595997810364, "learning_rate": 1.4885362521807611e-08, "loss": 0.5897239685058594, "step": 30135, "token_acc": 0.8118739196882029 }, { "epoch": 1.9512264204384524, "grad_norm": 0.3591351807117462, "learning_rate": 1.4689986186507965e-08, "loss": 0.5996665000915528, "step": 30140, "token_acc": 0.8091679932425847 }, { "epoch": 1.9515501209830786, "grad_norm": 0.39523276686668396, "learning_rate": 1.4495898645579543e-08, "loss": 0.6153468608856201, "step": 30145, "token_acc": 0.8049594532969393 }, { "epoch": 1.9518738215277047, "grad_norm": 0.35662582516670227, "learning_rate": 1.4303099949196652e-08, "loss": 0.581098985671997, "step": 30150, "token_acc": 0.8145211150237897 } ], "logging_steps": 5, "max_steps": 30894, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 50, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 2.2061873783482876e+19, "train_batch_size": 1, "trial_name": null, "trial_params": null }