diff --git "a/checkpoint-2747520/trainer_state.json" "b/checkpoint-2747520/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2747520/trainer_state.json" @@ -0,0 +1,32509 @@ +{ + "best_metric": 3.9711503982543945, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/npi-sim-ques/lstm/4/checkpoints/checkpoint-2747520", + "epoch": 0.025000606015738065, + "eval_steps": 10, + "global_step": 2747520, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 4.999998362119627e-05, + "loss": 10.8194, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 7.5486, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 7.0539, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 6.9878, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 6.9434, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 6.9114, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 6.7517, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994131474623009e-05, + "loss": 6.6461, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993292879871958e-05, + "loss": 6.549, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992454285120906e-05, + "loss": 6.4708, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.991615690369854e-05, + "loss": 6.4004, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990777095618801e-05, + "loss": 6.3455, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989938500867749e-05, + "loss": 6.2713, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 6.1949, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 6.1449, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 6.084, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 6.0493, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.9922, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.9462, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.9133, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.8722, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.982391148108281e-05, + "loss": 5.8431, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.981552553357229e-05, + "loss": 5.8165, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.980713958606178e-05, + "loss": 5.7852, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.979875363855125e-05, + "loss": 5.7557, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.979036769104073e-05, + "loss": 5.7299, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.978198174353021e-05, + "loss": 5.6998, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773612174823426e-05, + "loss": 5.6709, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.97652262273129e-05, + "loss": 5.6449, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.975684027980238e-05, + "loss": 5.6317, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.974845433229186e-05, + "loss": 5.609, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 5.587, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731731573682013e-05, + "loss": 5.5662, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.97233456261715e-05, + "loss": 5.5456, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 5.5391, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 5.5277, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 5.5037, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968980183612942e-05, + "loss": 5.4646, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.96814158886189e-05, + "loss": 5.4736, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967302994110837e-05, + "loss": 5.437, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966464399359785e-05, + "loss": 5.4315, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965625804608733e-05, + "loss": 5.4222, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964787209857681e-05, + "loss": 5.4133, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963948615106629e-05, + "loss": 5.3905, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 5.3859, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962273063484898e-05, + "loss": 5.3807, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.961434468733847e-05, + "loss": 5.3674, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960595873982795e-05, + "loss": 5.3574, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 5.3373, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.958920322361064e-05, + "loss": 5.3251, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958081727610012e-05, + "loss": 5.3296, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957244770739333e-05, + "loss": 5.3082, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956406175988281e-05, + "loss": 5.2976, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.955567581237229e-05, + "loss": 5.2782, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.954728986486177e-05, + "loss": 5.2829, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.953890391735125e-05, + "loss": 5.2636, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530517969840727e-05, + "loss": 5.2775, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522132022330207e-05, + "loss": 5.2492, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.9513746074819686e-05, + "loss": 5.2467, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.9505360127309166e-05, + "loss": 5.239, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.9496974179798646e-05, + "loss": 5.2178, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948860461109186e-05, + "loss": 5.2206, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.948021866358134e-05, + "loss": 5.2062, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947184909487455e-05, + "loss": 5.1948, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946346314736403e-05, + "loss": 5.1903, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945507719985351e-05, + "loss": 5.2079, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944669125234299e-05, + "loss": 5.1826, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943830530483247e-05, + "loss": 5.1684, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942991935732195e-05, + "loss": 5.1504, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942153340981143e-05, + "loss": 5.1494, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.9413147462300904e-05, + "loss": 5.1635, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404761514790384e-05, + "loss": 5.1584, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.939637556727987e-05, + "loss": 5.1325, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.938800599857309e-05, + "loss": 5.1492, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.937962005106256e-05, + "loss": 5.1404, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.937123410355204e-05, + "loss": 5.1257, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.936284815604152e-05, + "loss": 5.106, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.935447858733473e-05, + "loss": 5.109, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.934609263982421e-05, + "loss": 5.0932, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.933770669231369e-05, + "loss": 5.091, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.932932074480317e-05, + "loss": 5.0907, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932095117609638e-05, + "loss": 5.0813, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931256522858586e-05, + "loss": 5.0844, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930417928107534e-05, + "loss": 5.0787, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.9295793333564825e-05, + "loss": 5.0572, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.9287407386054305e-05, + "loss": 5.0601, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.9279021438543785e-05, + "loss": 5.0585, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.9270635491033264e-05, + "loss": 5.0515, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.9262249543522744e-05, + "loss": 5.0396, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.9253879974815954e-05, + "loss": 5.0377, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.9245494027305433e-05, + "loss": 5.0352, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.9237108079794913e-05, + "loss": 5.0227, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922872213228439e-05, + "loss": 5.0248, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.92203525635776e-05, + "loss": 5.0107, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921196661606708e-05, + "loss": 5.013, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920358066855656e-05, + "loss": 5.0082, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919519472104604e-05, + "loss": 4.9996, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918682515233926e-05, + "loss": 4.9799, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917843920482874e-05, + "loss": 4.9799, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917005325731822e-05, + "loss": 4.9794, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.91616673098077e-05, + "loss": 4.989, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915329774110091e-05, + "loss": 4.9758, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914491179359039e-05, + "loss": 4.9635, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.913652584607987e-05, + "loss": 4.9561, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.912813989856935e-05, + "loss": 4.9611, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.911975395105883e-05, + "loss": 4.9344, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.9111384382352036e-05, + "loss": 4.9379, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.9102998434841516e-05, + "loss": 4.9341, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.9094612487330996e-05, + "loss": 4.936, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.9086226539820476e-05, + "loss": 4.9265, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907785697111369e-05, + "loss": 4.9328, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906947102360317e-05, + "loss": 4.9106, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906110145489638e-05, + "loss": 4.9341, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905271550738586e-05, + "loss": 4.9127, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904432955987534e-05, + "loss": 4.9136, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903594361236482e-05, + "loss": 4.9159, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.90275576648543e-05, + "loss": 4.9144, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901917171734378e-05, + "loss": 4.8995, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901078576983326e-05, + "loss": 4.8896, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.900239982232274e-05, + "loss": 4.8967, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994013874812214e-05, + "loss": 4.8887, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.89856279273017e-05, + "loss": 4.889, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.897724197979118e-05, + "loss": 4.8842, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968872411084396e-05, + "loss": 4.8729, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.896048646357387e-05, + "loss": 4.8848, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.895210051606335e-05, + "loss": 4.8642, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.894371456855283e-05, + "loss": 4.8591, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.893532862104231e-05, + "loss": 4.8521, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.892695905233552e-05, + "loss": 4.8589, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918589483628734e-05, + "loss": 4.8433, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.8910219914921943e-05, + "loss": 4.8617, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.8901833967411423e-05, + "loss": 4.8539, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.88934480199009e-05, + "loss": 4.8408, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888506207239038e-05, + "loss": 4.8331, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887667612487986e-05, + "loss": 4.8357, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886829017736934e-05, + "loss": 4.8336, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885990422985882e-05, + "loss": 4.8344, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.88515182823483e-05, + "loss": 4.8335, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884313233483778e-05, + "loss": 4.8304, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883474638732726e-05, + "loss": 4.8228, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882636043981674e-05, + "loss": 4.8176, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881797449230622e-05, + "loss": 4.806, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.880960492359943e-05, + "loss": 4.8046, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880121897608891e-05, + "loss": 4.8088, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879283302857839e-05, + "loss": 4.7913, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878444708106787e-05, + "loss": 4.8045, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877606113355735e-05, + "loss": 4.8037, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876767518604683e-05, + "loss": 4.7927, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875930561734005e-05, + "loss": 4.7971, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875091966982953e-05, + "loss": 4.7918, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.747582912445068, + "eval_runtime": 297.2858, + "eval_samples_per_second": 1283.583, + "eval_steps_per_second": 40.113, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.874253372231901e-05, + "loss": 4.7713, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873414777480849e-05, + "loss": 4.777, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.872576182729797e-05, + "loss": 4.7895, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.871737587978745e-05, + "loss": 4.7703, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709006311080657e-05, + "loss": 4.7756, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.8700620363570137e-05, + "loss": 4.7651, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.8692234416059616e-05, + "loss": 4.7655, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683864847352826e-05, + "loss": 4.7543, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.8675478899842306e-05, + "loss": 4.7625, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.8667092952331785e-05, + "loss": 4.7512, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.865870700482127e-05, + "loss": 4.7718, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865032105731075e-05, + "loss": 4.7634, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.864195148860396e-05, + "loss": 4.7431, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.863356554109344e-05, + "loss": 4.7394, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862517959358292e-05, + "loss": 4.7379, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.86167936460724e-05, + "loss": 4.739, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.8608407698561874e-05, + "loss": 4.7325, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.8600021751051354e-05, + "loss": 4.73, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.8591635803540834e-05, + "loss": 4.7264, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.8583249856030314e-05, + "loss": 4.7376, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.8574863908519794e-05, + "loss": 4.729, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.8566477961009274e-05, + "loss": 4.7326, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558092013498754e-05, + "loss": 4.7273, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.854972244479197e-05, + "loss": 4.7351, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.854133649728145e-05, + "loss": 4.7113, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.853295054977093e-05, + "loss": 4.7112, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.852456460226041e-05, + "loss": 4.7045, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851621141235735e-05, + "loss": 4.7054, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.8507841843650564e-05, + "loss": 4.7048, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.8499455896140044e-05, + "loss": 4.7017, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.8491069948629524e-05, + "loss": 4.7022, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.8482684001119e-05, + "loss": 4.7004, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847429805360848e-05, + "loss": 4.6902, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.8465912106097964e-05, + "loss": 4.7041, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.8457526158587444e-05, + "loss": 4.7041, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.8449140211076924e-05, + "loss": 4.6896, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.8440754263566404e-05, + "loss": 4.6736, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.8432368316055884e-05, + "loss": 4.6864, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.8423982368545363e-05, + "loss": 4.6664, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.841561279983857e-05, + "loss": 4.6762, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840722685232805e-05, + "loss": 4.6751, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.839884090481753e-05, + "loss": 4.6796, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839045495730701e-05, + "loss": 4.6679, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.838206900979649e-05, + "loss": 4.6734, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.837368306228597e-05, + "loss": 4.6753, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836529711477545e-05, + "loss": 4.6691, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.835692754606866e-05, + "loss": 4.6698, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834854159855814e-05, + "loss": 4.6518, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834015565104763e-05, + "loss": 4.6561, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.833176970353711e-05, + "loss": 4.6631, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.832340013483032e-05, + "loss": 4.6524, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.83150141873198e-05, + "loss": 4.6533, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.830662823980928e-05, + "loss": 4.6361, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.829824229229876e-05, + "loss": 4.6471, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.828985634478824e-05, + "loss": 4.6368, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.828147039727771e-05, + "loss": 4.6536, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.827308444976719e-05, + "loss": 4.6383, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.826469850225667e-05, + "loss": 4.6425, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.8256328933549886e-05, + "loss": 4.6434, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.8247942986039366e-05, + "loss": 4.6207, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.8239557038528846e-05, + "loss": 4.6325, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823118746982206e-05, + "loss": 4.6322, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.8222801522311535e-05, + "loss": 4.6171, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.8214415574801015e-05, + "loss": 4.6204, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.8206029627290495e-05, + "loss": 4.6404, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.8197643679779975e-05, + "loss": 4.6244, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.8189257732269455e-05, + "loss": 4.612, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.8180871784758935e-05, + "loss": 4.606, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.8172502216052144e-05, + "loss": 4.6106, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.8164116268541624e-05, + "loss": 4.6273, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.8155730321031104e-05, + "loss": 4.6262, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.8147344373520584e-05, + "loss": 4.608, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.8138958426010064e-05, + "loss": 4.6256, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.813057247849955e-05, + "loss": 4.6237, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812218653098903e-05, + "loss": 4.6133, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.811380058347851e-05, + "loss": 4.5999, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810544739357545e-05, + "loss": 4.6131, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.809707782486866e-05, + "loss": 4.6006, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.808869187735814e-05, + "loss": 4.5959, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808030592984762e-05, + "loss": 4.6023, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.80719199823371e-05, + "loss": 4.5939, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806353403482658e-05, + "loss": 4.6105, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805514808731606e-05, + "loss": 4.5969, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804676213980554e-05, + "loss": 4.589, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803837619229502e-05, + "loss": 4.5945, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.8029990244784504e-05, + "loss": 4.5929, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.8021604297273984e-05, + "loss": 4.5909, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.8013218349763464e-05, + "loss": 4.5877, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.80048651598604e-05, + "loss": 4.581, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.799647921234988e-05, + "loss": 4.5919, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.798809326483936e-05, + "loss": 4.5779, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.797970731732884e-05, + "loss": 4.5838, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.797132136981832e-05, + "loss": 4.5717, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.79629354223078e-05, + "loss": 4.5856, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.795454947479728e-05, + "loss": 4.5815, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.794616352728676e-05, + "loss": 4.5732, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.793777757977624e-05, + "loss": 4.5596, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792939163226572e-05, + "loss": 4.5663, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.79210056847552e-05, + "loss": 4.5684, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.791261973724468e-05, + "loss": 4.5803, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.79042501685379e-05, + "loss": 4.5702, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.7895880599831107e-05, + "loss": 4.5603, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.7887494652320587e-05, + "loss": 4.5562, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.7879108704810067e-05, + "loss": 4.5658, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.7870722757299546e-05, + "loss": 4.5381, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.7862353188592756e-05, + "loss": 4.5526, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.7853967241082236e-05, + "loss": 4.5507, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.7845581293571715e-05, + "loss": 4.5526, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.7837195346061195e-05, + "loss": 4.5457, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.782882577735441e-05, + "loss": 4.5542, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782043982984389e-05, + "loss": 4.5421, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.781205388233337e-05, + "loss": 4.5616, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.7803667934822844e-05, + "loss": 4.5453, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.7795281987312324e-05, + "loss": 4.5417, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.7786896039801804e-05, + "loss": 4.5618, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777852647109502e-05, + "loss": 4.5566, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.777014052358449e-05, + "loss": 4.5428, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.776175457607397e-05, + "loss": 4.535, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775336862856345e-05, + "loss": 4.5493, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.774498268105293e-05, + "loss": 4.5381, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773659673354241e-05, + "loss": 4.5385, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772821078603189e-05, + "loss": 4.5455, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.771984121732511e-05, + "loss": 4.5293, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771145526981459e-05, + "loss": 4.5461, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770306932230407e-05, + "loss": 4.5282, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769468337479355e-05, + "loss": 4.5307, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768629742728303e-05, + "loss": 4.5189, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.767791147977251e-05, + "loss": 4.5327, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766952553226199e-05, + "loss": 4.5218, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766113958475147e-05, + "loss": 4.5364, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765277001604468e-05, + "loss": 4.5339, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764438406853416e-05, + "loss": 4.5249, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.763599812102364e-05, + "loss": 4.5101, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762762855231685e-05, + "loss": 4.5266, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761924260480633e-05, + "loss": 4.5204, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.7610856657295813e-05, + "loss": 4.5267, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.7602470709785293e-05, + "loss": 4.525, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.7594084762274773e-05, + "loss": 4.5207, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758571519356798e-05, + "loss": 4.5188, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.757732924605746e-05, + "loss": 4.5222, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.756894329854694e-05, + "loss": 4.5064, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.756055735103642e-05, + "loss": 4.5072, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.75521714035259e-05, + "loss": 4.5137, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.7543785456015375e-05, + "loss": 4.5018, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.7535399508504855e-05, + "loss": 4.5093, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.752702993979807e-05, + "loss": 4.5196, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.751866037109128e-05, + "loss": 4.5035, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.751027442358077e-05, + "loss": 4.5057, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.750188847607025e-05, + "loss": 4.5063, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.471279144287109, + "eval_runtime": 296.6309, + "eval_samples_per_second": 1286.417, + "eval_steps_per_second": 40.201, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.749350252855973e-05, + "loss": 4.4923, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748511658104921e-05, + "loss": 4.4952, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747673063353868e-05, + "loss": 4.5092, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746834468602816e-05, + "loss": 4.497, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.745995873851764e-05, + "loss": 4.5017, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.745157279100712e-05, + "loss": 4.4862, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.74431868434966e-05, + "loss": 4.5001, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.743480089598608e-05, + "loss": 4.4813, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.742641494847556e-05, + "loss": 4.4953, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.741802900096504e-05, + "loss": 4.4879, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740964305345452e-05, + "loss": 4.5023, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.7401257105944e-05, + "loss": 4.5026, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.7392887537237216e-05, + "loss": 4.4791, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.7384501589726696e-05, + "loss": 4.4833, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.7376115642216176e-05, + "loss": 4.4837, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.7367729694705656e-05, + "loss": 4.4772, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.7359343747195135e-05, + "loss": 4.4775, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.7350957799684615e-05, + "loss": 4.4765, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.7342571852174095e-05, + "loss": 4.4745, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733418590466357e-05, + "loss": 4.4942, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732579995715305e-05, + "loss": 4.4746, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731741400964253e-05, + "loss": 4.4869, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.730902806213201e-05, + "loss": 4.4828, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730064211462149e-05, + "loss": 4.4889, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.7292272545914704e-05, + "loss": 4.4638, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.7283886598404184e-05, + "loss": 4.4727, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.7275500650893664e-05, + "loss": 4.4627, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726713108218687e-05, + "loss": 4.4721, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725874513467635e-05, + "loss": 4.4636, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725035918716583e-05, + "loss": 4.4653, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.724197323965531e-05, + "loss": 4.4732, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723358729214479e-05, + "loss": 4.4668, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.722520134463427e-05, + "loss": 4.4568, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721681539712375e-05, + "loss": 4.474, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720842944961323e-05, + "loss": 4.4685, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720007625971017e-05, + "loss": 4.4615, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719169031219965e-05, + "loss": 4.4499, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.718330436468914e-05, + "loss": 4.4616, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.717491841717862e-05, + "loss": 4.4423, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.71665324696681e-05, + "loss": 4.4558, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.715816290096131e-05, + "loss": 4.4501, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.714977695345079e-05, + "loss": 4.458, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714139100594027e-05, + "loss": 4.4516, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.713300505842975e-05, + "loss": 4.4545, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712461911091923e-05, + "loss": 4.4571, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711623316340871e-05, + "loss": 4.4541, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710784721589819e-05, + "loss": 4.4563, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.7099461268387667e-05, + "loss": 4.439, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.7091091699680876e-05, + "loss": 4.439, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.7082705752170356e-05, + "loss": 4.4535, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.7074319804659836e-05, + "loss": 4.4411, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706593385714932e-05, + "loss": 4.4406, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705756428844253e-05, + "loss": 4.428, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704917834093201e-05, + "loss": 4.4416, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704079239342149e-05, + "loss": 4.4264, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703240644591097e-05, + "loss": 4.446, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.702403687720418e-05, + "loss": 4.4326, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.701565092969366e-05, + "loss": 4.4414, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.700726498218314e-05, + "loss": 4.4377, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.699887903467262e-05, + "loss": 4.423, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699050946596583e-05, + "loss": 4.4291, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.698212351845531e-05, + "loss": 4.4319, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.697373757094479e-05, + "loss": 4.4184, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.6965368002238005e-05, + "loss": 4.4276, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.6956982054727485e-05, + "loss": 4.4355, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.6948596107216965e-05, + "loss": 4.4313, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.6940210159706445e-05, + "loss": 4.4189, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.6931824212195925e-05, + "loss": 4.4098, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.69234382646854e-05, + "loss": 4.4164, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.6915068695978614e-05, + "loss": 4.4327, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.6906682748468094e-05, + "loss": 4.4365, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.6898296800957574e-05, + "loss": 4.4199, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.688992723225078e-05, + "loss": 4.4339, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688154128474026e-05, + "loss": 4.4342, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.687315533722974e-05, + "loss": 4.4287, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.686476938971923e-05, + "loss": 4.4065, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.68563834422087e-05, + "loss": 4.4279, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.684799749469818e-05, + "loss": 4.4213, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683961154718766e-05, + "loss": 4.409, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.683122559967714e-05, + "loss": 4.4214, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.682283965216662e-05, + "loss": 4.4123, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.68144537046561e-05, + "loss": 4.4239, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.680606775714558e-05, + "loss": 4.4177, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679769818843879e-05, + "loss": 4.4055, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678931224092827e-05, + "loss": 4.4139, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678092629341775e-05, + "loss": 4.4115, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.677255672471097e-05, + "loss": 4.4141, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676417077720045e-05, + "loss": 4.4103, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675578482968993e-05, + "loss": 4.4042, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674739888217941e-05, + "loss": 4.4139, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.673901293466889e-05, + "loss": 4.4034, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.6730643365962096e-05, + "loss": 4.4089, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.6722273797255305e-05, + "loss": 4.4, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.6713887849744785e-05, + "loss": 4.4139, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.6705501902234265e-05, + "loss": 4.4082, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.6697115954723745e-05, + "loss": 4.3989, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.6688730007213225e-05, + "loss": 4.3942, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.6680344059702705e-05, + "loss": 4.4001, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.6671958112192185e-05, + "loss": 4.3942, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.6663572164681665e-05, + "loss": 4.413, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.6655186217171145e-05, + "loss": 4.3983, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664680026966063e-05, + "loss": 4.394, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663841432215011e-05, + "loss": 4.3889, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663002837463959e-05, + "loss": 4.3956, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.66216588059328e-05, + "loss": 4.3777, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661327285842228e-05, + "loss": 4.3871, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660490328971549e-05, + "loss": 4.386, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659651734220497e-05, + "loss": 4.39, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.658813139469445e-05, + "loss": 4.3788, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657974544718393e-05, + "loss": 4.3946, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657135949967341e-05, + "loss": 4.3777, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.656297355216288e-05, + "loss": 4.4, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655458760465237e-05, + "loss": 4.3846, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.6546218035945586e-05, + "loss": 4.3816, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.6537832088435065e-05, + "loss": 4.4036, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.6529462519728275e-05, + "loss": 4.4017, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.6521076572217755e-05, + "loss": 4.3861, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.6512690624707234e-05, + "loss": 4.3775, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650430467719671e-05, + "loss": 4.3879, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649591872968619e-05, + "loss": 4.3843, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648753278217567e-05, + "loss": 4.3803, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.647914683466515e-05, + "loss": 4.3947, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.647076088715463e-05, + "loss": 4.3742, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.6462391318447837e-05, + "loss": 4.3907, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645400537093732e-05, + "loss": 4.3768, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644563580223053e-05, + "loss": 4.3804, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.643724985472001e-05, + "loss": 4.3657, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.642886390720949e-05, + "loss": 4.383, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642047795969897e-05, + "loss": 4.3671, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.641209201218845e-05, + "loss": 4.3868, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640370606467793e-05, + "loss": 4.3806, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.639532011716741e-05, + "loss": 4.3779, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.638693416965689e-05, + "loss": 4.3608, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637858097975383e-05, + "loss": 4.3783, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.637019503224331e-05, + "loss": 4.3762, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636180908473279e-05, + "loss": 4.3755, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.635342313722228e-05, + "loss": 4.3735, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.634503718971176e-05, + "loss": 4.3797, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633665124220124e-05, + "loss": 4.3732, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.6328281673494446e-05, + "loss": 4.3793, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.6319895725983926e-05, + "loss": 4.3601, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.6311509778473406e-05, + "loss": 4.3638, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.6303123830962886e-05, + "loss": 4.3689, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.6294737883452366e-05, + "loss": 4.3565, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.6286351935941846e-05, + "loss": 4.3667, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.6277965988431326e-05, + "loss": 4.3765, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.6269580040920806e-05, + "loss": 4.3618, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.6261210472214015e-05, + "loss": 4.3603, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.6252824524703495e-05, + "loss": 4.3693, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 4.337189197540283, + "eval_runtime": 311.5899, + "eval_samples_per_second": 1224.658, + "eval_steps_per_second": 38.271, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624445495599671e-05, + "loss": 4.3592, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.623606900848619e-05, + "loss": 4.3548, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.622768306097567e-05, + "loss": 4.3692, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.621929711346515e-05, + "loss": 4.3534, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621091116595463e-05, + "loss": 4.3654, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620252521844411e-05, + "loss": 4.3498, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.619413927093359e-05, + "loss": 4.3619, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.618575332342307e-05, + "loss": 4.3443, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.617738375471628e-05, + "loss": 4.3606, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.616899780720576e-05, + "loss": 4.3507, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.616061185969524e-05, + "loss": 4.3681, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.615222591218472e-05, + "loss": 4.365, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.614385634347793e-05, + "loss": 4.3461, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.6135470395967415e-05, + "loss": 4.3523, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.6127084448456895e-05, + "loss": 4.3489, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611869850094637e-05, + "loss": 4.3491, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.611031255343585e-05, + "loss": 4.3403, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.610192660592533e-05, + "loss": 4.3448, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.609354065841481e-05, + "loss": 4.3421, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.608515471090429e-05, + "loss": 4.3676, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.60767851421975e-05, + "loss": 4.3444, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.606839919468698e-05, + "loss": 4.3512, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.606001324717646e-05, + "loss": 4.3563, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.605162729966594e-05, + "loss": 4.3586, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.604325773095915e-05, + "loss": 4.3364, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.603488816225236e-05, + "loss": 4.3426, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.602650221474184e-05, + "loss": 4.3357, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.601811626723132e-05, + "loss": 4.3433, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.600974669852454e-05, + "loss": 4.3354, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.600136075101402e-05, + "loss": 4.3366, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.599297480350349e-05, + "loss": 4.3462, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598458885599297e-05, + "loss": 4.3421, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.597620290848245e-05, + "loss": 4.3374, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.596781696097193e-05, + "loss": 4.3453, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.595943101346141e-05, + "loss": 4.3451, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.595104506595089e-05, + "loss": 4.3369, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.594265911844037e-05, + "loss": 4.3239, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.593427317092985e-05, + "loss": 4.3394, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.592588722341933e-05, + "loss": 4.317, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.5917517654712546e-05, + "loss": 4.332, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.5909131707202026e-05, + "loss": 4.3269, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.5900745759691506e-05, + "loss": 4.3375, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.5892359812180986e-05, + "loss": 4.3354, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.5883973864670466e-05, + "loss": 4.3294, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.5875587917159946e-05, + "loss": 4.3358, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.5867201969649426e-05, + "loss": 4.3358, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.5858832400942635e-05, + "loss": 4.3368, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.5850446453432115e-05, + "loss": 4.3187, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.5842060505921595e-05, + "loss": 4.3186, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.5833674558411075e-05, + "loss": 4.3362, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.5825288610900555e-05, + "loss": 4.3204, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.5816902663390035e-05, + "loss": 4.319, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.580853309468325e-05, + "loss": 4.3144, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.580014714717273e-05, + "loss": 4.324, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.5791761199662204e-05, + "loss": 4.3123, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.5783375252151684e-05, + "loss": 4.3245, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.5774989304641164e-05, + "loss": 4.3174, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.5766603357130644e-05, + "loss": 4.3213, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.5758217409620124e-05, + "loss": 4.3234, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.5749831462109604e-05, + "loss": 4.3108, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.574146189340281e-05, + "loss": 4.3095, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.573309232469602e-05, + "loss": 4.321, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.572470637718551e-05, + "loss": 4.3024, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.571632042967499e-05, + "loss": 4.3124, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.570793448216447e-05, + "loss": 4.3208, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.569956491345768e-05, + "loss": 4.3228, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.569117896594716e-05, + "loss": 4.3047, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.568279301843664e-05, + "loss": 4.2986, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.567440707092612e-05, + "loss": 4.3029, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.56660211234156e-05, + "loss": 4.3158, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.565763517590508e-05, + "loss": 4.3243, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.564924922839456e-05, + "loss": 4.3104, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.564086328088404e-05, + "loss": 4.3219, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.5632493712177247e-05, + "loss": 4.3233, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.5624107764666726e-05, + "loss": 4.3187, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.561573819595994e-05, + "loss": 4.3004, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.560735224844942e-05, + "loss": 4.3152, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.559898267974263e-05, + "loss": 4.3116, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.559059673223211e-05, + "loss": 4.3012, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.558221078472159e-05, + "loss": 4.3113, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557382483721107e-05, + "loss": 4.3061, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.556543888970055e-05, + "loss": 4.3126, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.555705294219003e-05, + "loss": 4.3108, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.554866699467951e-05, + "loss": 4.3, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.554028104716899e-05, + "loss": 4.31, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553189509965847e-05, + "loss": 4.3031, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.552350915214795e-05, + "loss": 4.3062, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.551512320463743e-05, + "loss": 4.3045, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.550673725712691e-05, + "loss": 4.2972, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.549836768842013e-05, + "loss": 4.3086, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.548998174090961e-05, + "loss": 4.3024, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548159579339909e-05, + "loss": 4.2974, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.547320984588857e-05, + "loss": 4.2963, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.5464840277181776e-05, + "loss": 4.3117, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.5456470708474985e-05, + "loss": 4.3047, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.5448084760964465e-05, + "loss": 4.2953, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.5439698813453945e-05, + "loss": 4.2904, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.5431312865943425e-05, + "loss": 4.2967, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.5422926918432905e-05, + "loss": 4.2903, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.5414540970922385e-05, + "loss": 4.3121, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.5406155023411865e-05, + "loss": 4.2977, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.539778545470508e-05, + "loss": 4.2934, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.538939950719456e-05, + "loss": 4.2881, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.538101355968404e-05, + "loss": 4.2981, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.537264399097725e-05, + "loss": 4.2716, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.536427442227046e-05, + "loss": 4.2881, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.535588847475994e-05, + "loss": 4.286, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.534750252724942e-05, + "loss": 4.293, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.53391165797389e-05, + "loss": 4.2791, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.533073063222838e-05, + "loss": 4.2961, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.532234468471786e-05, + "loss": 4.2776, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.531395873720733e-05, + "loss": 4.2964, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.530557278969682e-05, + "loss": 4.2894, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.52971868421863e-05, + "loss": 4.2816, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.528880089467578e-05, + "loss": 4.3029, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.528041494716526e-05, + "loss": 4.3046, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.527204537845847e-05, + "loss": 4.2905, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.526365943094795e-05, + "loss": 4.2813, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.525527348343743e-05, + "loss": 4.2885, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.524688753592691e-05, + "loss": 4.2842, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.523850158841639e-05, + "loss": 4.2823, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.523011564090587e-05, + "loss": 4.2984, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.522172969339535e-05, + "loss": 4.2782, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.521334374588483e-05, + "loss": 4.291, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.5204974177178036e-05, + "loss": 4.2835, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.5196588229667516e-05, + "loss": 4.2879, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.5188202282157e-05, + "loss": 4.2647, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.517983271345021e-05, + "loss": 4.2914, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.517144676593969e-05, + "loss": 4.2722, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.516306081842917e-05, + "loss": 4.292, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515467487091865e-05, + "loss": 4.2838, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.514628892340813e-05, + "loss": 4.2879, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513790297589761e-05, + "loss": 4.2652, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.512951702838709e-05, + "loss": 4.29, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.51211474596803e-05, + "loss": 4.2798, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.511276151216978e-05, + "loss": 4.2831, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.510437556465926e-05, + "loss": 4.2799, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.509598961714874e-05, + "loss": 4.2899, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.508760366963822e-05, + "loss": 4.2836, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.5079234100931436e-05, + "loss": 4.2836, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.5070848153420916e-05, + "loss": 4.2698, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.5062462205910396e-05, + "loss": 4.2741, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.5054076258399876e-05, + "loss": 4.2743, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.504569031088935e-05, + "loss": 4.2683, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.503730436337883e-05, + "loss": 4.2769, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.502891841586831e-05, + "loss": 4.2828, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.502053246835779e-05, + "loss": 4.2733, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.5012162899651e-05, + "loss": 4.2701, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.500377695214048e-05, + "loss": 4.2798, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 4.255205154418945, + "eval_runtime": 311.0995, + "eval_samples_per_second": 1226.588, + "eval_steps_per_second": 38.332, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.499539100462996e-05, + "loss": 4.2624, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.498700505711944e-05, + "loss": 4.2648, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.4978619109608925e-05, + "loss": 4.2754, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.4970233162098405e-05, + "loss": 4.2667, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.4961847214587885e-05, + "loss": 4.2797, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.4953461267077365e-05, + "loss": 4.2607, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.4945075319566845e-05, + "loss": 4.2699, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.4936689372056325e-05, + "loss": 4.2572, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.4928303424545805e-05, + "loss": 4.275, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.4919917477035285e-05, + "loss": 4.2642, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.4911531529524765e-05, + "loss": 4.2741, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.490314558201424e-05, + "loss": 4.2798, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.4894776013307454e-05, + "loss": 4.2542, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.4886390065796934e-05, + "loss": 4.2697, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487800411828641e-05, + "loss": 4.2618, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.486961817077589e-05, + "loss": 4.2638, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.48612486020691e-05, + "loss": 4.2524, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485286265455859e-05, + "loss": 4.2604, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.484447670704806e-05, + "loss": 4.2566, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483609075953754e-05, + "loss": 4.2794, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482770481202702e-05, + "loss": 4.2576, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.48193188645165e-05, + "loss": 4.2669, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481093291700598e-05, + "loss": 4.2732, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480254696949546e-05, + "loss": 4.2754, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479416102198494e-05, + "loss": 4.25, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478579145327815e-05, + "loss": 4.2632, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477740550576763e-05, + "loss": 4.2499, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476901955825711e-05, + "loss": 4.2585, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476063361074659e-05, + "loss": 4.2491, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475224766323607e-05, + "loss": 4.2573, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474387809452929e-05, + "loss": 4.2614, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473549214701877e-05, + "loss": 4.2588, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472710619950825e-05, + "loss": 4.2522, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.471872025199773e-05, + "loss": 4.2645, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.471033430448721e-05, + "loss": 4.2561, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470194835697669e-05, + "loss": 4.2592, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469356240946617e-05, + "loss": 4.244, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468517646195565e-05, + "loss": 4.2549, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467679051444512e-05, + "loss": 4.2408, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.4668420945738336e-05, + "loss": 4.2483, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.4660034998227816e-05, + "loss": 4.2451, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.4651649050717296e-05, + "loss": 4.2575, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.4643263103206776e-05, + "loss": 4.2531, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463489353449999e-05, + "loss": 4.252, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462650758698947e-05, + "loss": 4.2552, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461812163947895e-05, + "loss": 4.2553, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.4609735691968425e-05, + "loss": 4.2534, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460136612326164e-05, + "loss": 4.2448, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.459298017575112e-05, + "loss": 4.2323, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.4584594228240594e-05, + "loss": 4.2574, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.4576208280730074e-05, + "loss": 4.2456, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.456783871202329e-05, + "loss": 4.2395, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.455945276451277e-05, + "loss": 4.2384, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.455108319580598e-05, + "loss": 4.2447, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.4542697248295465e-05, + "loss": 4.2339, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.4534311300784945e-05, + "loss": 4.2387, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.4525925353274425e-05, + "loss": 4.2403, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.4517555784567634e-05, + "loss": 4.2405, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.4509169837057114e-05, + "loss": 4.2513, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.4500783889546594e-05, + "loss": 4.2308, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.449239794203607e-05, + "loss": 4.2341, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448401199452555e-05, + "loss": 4.246, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.447562604701503e-05, + "loss": 4.2289, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446724009950451e-05, + "loss": 4.2367, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445885415199399e-05, + "loss": 4.2408, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.44504845832872e-05, + "loss": 4.2451, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444209863577668e-05, + "loss": 4.2296, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443371268826616e-05, + "loss": 4.2233, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442532674075564e-05, + "loss": 4.2224, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441694079324512e-05, + "loss": 4.2396, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440857122453833e-05, + "loss": 4.251, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440018527702781e-05, + "loss": 4.2331, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439179932951729e-05, + "loss": 4.2454, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438341338200677e-05, + "loss": 4.2475, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437504381329998e-05, + "loss": 4.2467, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436665786578946e-05, + "loss": 4.2248, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435827191827894e-05, + "loss": 4.2399, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.434988597076842e-05, + "loss": 4.2359, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.43415000232579e-05, + "loss": 4.2241, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.4333130454551117e-05, + "loss": 4.2398, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.4324744507040597e-05, + "loss": 4.2337, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.4316358559530076e-05, + "loss": 4.2338, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.4307972612019556e-05, + "loss": 4.2387, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.4299586664509036e-05, + "loss": 4.2312, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.4291217095802245e-05, + "loss": 4.2344, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.4282831148291725e-05, + "loss": 4.2279, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.4274445200781205e-05, + "loss": 4.2335, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.4266059253270685e-05, + "loss": 4.2259, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.4257673305760165e-05, + "loss": 4.2278, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.4249287358249645e-05, + "loss": 4.2325, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.4240901410739125e-05, + "loss": 4.2318, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.4232515463228605e-05, + "loss": 4.2244, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422414589452182e-05, + "loss": 4.2231, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.421577632581503e-05, + "loss": 4.2408, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420739037830451e-05, + "loss": 4.2344, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419900443079399e-05, + "loss": 4.2261, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.419061848328347e-05, + "loss": 4.2192, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.418223253577295e-05, + "loss": 4.2246, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.417384658826243e-05, + "loss": 4.2227, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.41654606407519e-05, + "loss": 4.2345, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415709107204512e-05, + "loss": 4.2327, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.41487051245346e-05, + "loss": 4.2224, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.414031917702408e-05, + "loss": 4.2173, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413193322951356e-05, + "loss": 4.2297, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412354728200304e-05, + "loss": 4.1981, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411516133449252e-05, + "loss": 4.2226, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.4106791765785735e-05, + "loss": 4.2098, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409840581827521e-05, + "loss": 4.2216, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409001987076469e-05, + "loss": 4.2111, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408163392325417e-05, + "loss": 4.2247, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407324797574365e-05, + "loss": 4.2158, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406486202823313e-05, + "loss": 4.2211, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405649245952634e-05, + "loss": 4.2243, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404810651201582e-05, + "loss": 4.2095, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.40397205645053e-05, + "loss": 4.2338, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.4031334616994777e-05, + "loss": 4.2369, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402296504828799e-05, + "loss": 4.2227, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401457910077747e-05, + "loss": 4.2092, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400619315326695e-05, + "loss": 4.2229, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399780720575643e-05, + "loss": 4.2179, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398942125824591e-05, + "loss": 4.2106, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398103531073539e-05, + "loss": 4.2314, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397264936322487e-05, + "loss": 4.2121, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396426341571435e-05, + "loss": 4.22, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.395587746820383e-05, + "loss": 4.2189, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394752427830077e-05, + "loss": 4.2186, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393913833079025e-05, + "loss": 4.2063, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.3930768762083466e-05, + "loss": 4.2155, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.3922382814572946e-05, + "loss": 4.2108, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.3913996867062426e-05, + "loss": 4.2267, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.3905610919551906e-05, + "loss": 4.2156, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.3897224972041386e-05, + "loss": 4.2185, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.3888839024530866e-05, + "loss": 4.2011, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.3880453077020346e-05, + "loss": 4.2227, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.3872067129509826e-05, + "loss": 4.2148, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.3863681181999306e-05, + "loss": 4.2183, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.3855295234488786e-05, + "loss": 4.2113, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.3846909286978266e-05, + "loss": 4.2244, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.3838539718271475e-05, + "loss": 4.2151, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.3830153770760955e-05, + "loss": 4.2217, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.3821767823250435e-05, + "loss": 4.2015, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.3813381875739915e-05, + "loss": 4.2114, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.3804995928229395e-05, + "loss": 4.2068, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.3796609980718875e-05, + "loss": 4.2038, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.3788224033208355e-05, + "loss": 4.2147, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.3779838085697835e-05, + "loss": 4.2139, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.3771468516991044e-05, + "loss": 4.212, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.376309894828426e-05, + "loss": 4.1993, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.375471300077374e-05, + "loss": 4.2162, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 4.199580669403076, + "eval_runtime": 287.876, + "eval_samples_per_second": 1325.539, + "eval_steps_per_second": 41.424, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.374632705326321e-05, + "loss": 4.2055, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.373794110575269e-05, + "loss": 4.1975, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.372957153704591e-05, + "loss": 4.2147, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.372118558953539e-05, + "loss": 4.206, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.371279964202487e-05, + "loss": 4.2083, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.370441369451435e-05, + "loss": 4.2026, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.369602774700383e-05, + "loss": 4.2025, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.368764179949331e-05, + "loss": 4.1958, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.367925585198279e-05, + "loss": 4.2081, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.367086990447227e-05, + "loss": 4.2033, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.366250033576548e-05, + "loss": 4.2088, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.365411438825496e-05, + "loss": 4.2145, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.3645744819548166e-05, + "loss": 4.1948, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.3637358872037646e-05, + "loss": 4.2064, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.3628972924527126e-05, + "loss": 4.2014, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.3620586977016606e-05, + "loss": 4.1984, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.3612201029506086e-05, + "loss": 4.1914, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.3603815081995566e-05, + "loss": 4.1983, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.359542913448505e-05, + "loss": 4.1925, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.358704318697453e-05, + "loss": 4.2135, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.357865723946401e-05, + "loss": 4.2031, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.357027129195349e-05, + "loss": 4.2029, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.35619017232467e-05, + "loss": 4.2121, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.355351577573618e-05, + "loss": 4.2117, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.354512982822566e-05, + "loss": 4.1873, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.353674388071514e-05, + "loss": 4.2017, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.352835793320462e-05, + "loss": 4.1912, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.35199719856941e-05, + "loss": 4.1967, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.3511586038183575e-05, + "loss": 4.1879, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.3503200090673055e-05, + "loss": 4.1952, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.349483052196627e-05, + "loss": 4.2021, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.348644457445575e-05, + "loss": 4.1971, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.3478075005748966e-05, + "loss": 4.1949, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.3469689058238446e-05, + "loss": 4.2002, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.3461319489531655e-05, + "loss": 4.1993, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.3452933542021135e-05, + "loss": 4.1976, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.3444547594510615e-05, + "loss": 4.1867, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.3436161647000095e-05, + "loss": 4.1871, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.3427775699489575e-05, + "loss": 4.1844, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.341938975197905e-05, + "loss": 4.1868, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.341100380446853e-05, + "loss": 4.1866, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.340261785695801e-05, + "loss": 4.1968, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.339423190944749e-05, + "loss": 4.1944, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.3385845961936975e-05, + "loss": 4.1934, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.3377460014426455e-05, + "loss": 4.2015, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.3369074066915935e-05, + "loss": 4.1893, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.3360704498209144e-05, + "loss": 4.1958, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.3352318550698624e-05, + "loss": 4.1853, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.3343932603188104e-05, + "loss": 4.1725, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.3335546655677584e-05, + "loss": 4.1998, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.332717708697079e-05, + "loss": 4.1837, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.331879113946027e-05, + "loss": 4.1845, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.331040519194975e-05, + "loss": 4.1798, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.330201924443923e-05, + "loss": 4.185, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.329364967573244e-05, + "loss": 4.1783, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.328528010702566e-05, + "loss": 4.18, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.327689415951514e-05, + "loss": 4.1834, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.326850821200462e-05, + "loss": 4.182, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.32601222644941e-05, + "loss": 4.1937, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.325173631698358e-05, + "loss": 4.1738, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.324335036947306e-05, + "loss": 4.1747, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.323496442196254e-05, + "loss": 4.1915, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.322657847445202e-05, + "loss": 4.1731, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.321820890574523e-05, + "loss": 4.1779, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.3209822958234707e-05, + "loss": 4.1806, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.3201437010724187e-05, + "loss": 4.1901, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.3193051063213666e-05, + "loss": 4.1732, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.3184681494506876e-05, + "loss": 4.1721, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.317629554699636e-05, + "loss": 4.1609, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.316790959948584e-05, + "loss": 4.184, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.315952365197532e-05, + "loss": 4.1932, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.31511377044648e-05, + "loss": 4.1792, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.314276813575801e-05, + "loss": 4.1859, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.313439856705122e-05, + "loss": 4.1892, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.31260126195407e-05, + "loss": 4.1954, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.311762667203018e-05, + "loss": 4.169, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.310924072451966e-05, + "loss": 4.1854, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.310085477700914e-05, + "loss": 4.1812, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.309246882949862e-05, + "loss": 4.1664, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.30840828819881e-05, + "loss": 4.184, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.307569693447758e-05, + "loss": 4.1812, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.306731098696706e-05, + "loss": 4.1784, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.305892503945654e-05, + "loss": 4.1846, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.3050555470749756e-05, + "loss": 4.1753, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.3042169523239236e-05, + "loss": 4.1734, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.303378357572871e-05, + "loss": 4.1778, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.3025414007021925e-05, + "loss": 4.1803, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.3017028059511405e-05, + "loss": 4.1669, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.3008642112000885e-05, + "loss": 4.1735, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.300025616449036e-05, + "loss": 4.181, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.299187021697984e-05, + "loss": 4.1784, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.298348426946932e-05, + "loss": 4.172, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.29750983219588e-05, + "loss": 4.1693, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.2966728753252014e-05, + "loss": 4.1875, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.2958342805741494e-05, + "loss": 4.1801, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.2949956858230974e-05, + "loss": 4.1759, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.2941570910720454e-05, + "loss": 4.1621, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.2933184963209934e-05, + "loss": 4.1706, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.2924799015699413e-05, + "loss": 4.1712, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.2916413068188893e-05, + "loss": 4.179, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.290802712067837e-05, + "loss": 4.1813, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.289965755197158e-05, + "loss": 4.1685, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.289127160446106e-05, + "loss": 4.1631, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.288288565695054e-05, + "loss": 4.176, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.287449970944002e-05, + "loss": 4.147, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.286613014073324e-05, + "loss": 4.1693, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.285774419322272e-05, + "loss": 4.1552, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.28493582457122e-05, + "loss": 4.1751, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.284097229820168e-05, + "loss": 4.1575, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.283260272949489e-05, + "loss": 4.1705, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.282421678198437e-05, + "loss": 4.1619, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.281583083447385e-05, + "loss": 4.1677, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.2807461265767056e-05, + "loss": 4.1719, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.2799075318256536e-05, + "loss": 4.165, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.2790689370746016e-05, + "loss": 4.1796, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.2782303423235496e-05, + "loss": 4.1823, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.2773917475724976e-05, + "loss": 4.1716, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.2765531528214456e-05, + "loss": 4.1601, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.2757145580703936e-05, + "loss": 4.1658, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.2748759633193416e-05, + "loss": 4.169, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.274039006448663e-05, + "loss": 4.1559, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.273200411697611e-05, + "loss": 4.1852, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.272361816946559e-05, + "loss": 4.1564, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.271523222195507e-05, + "loss": 4.1714, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.270686265324828e-05, + "loss": 4.1666, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.269847670573776e-05, + "loss": 4.1641, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.269010713703097e-05, + "loss": 4.1563, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.268172118952045e-05, + "loss": 4.1663, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.267333524200993e-05, + "loss": 4.1604, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.266494929449941e-05, + "loss": 4.176, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.265656334698889e-05, + "loss": 4.166, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.264817739947837e-05, + "loss": 4.1714, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.263979145196785e-05, + "loss": 4.1503, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.263140550445733e-05, + "loss": 4.173, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.2623035935750545e-05, + "loss": 4.1629, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.261464998824002e-05, + "loss": 4.1674, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.26062640407295e-05, + "loss": 4.1638, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.259787809321898e-05, + "loss": 4.1733, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.258950852451219e-05, + "loss": 4.1642, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.258112257700167e-05, + "loss": 4.1767, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.257273662949115e-05, + "loss": 4.151, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.256436706078436e-05, + "loss": 4.1617, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.255598111327384e-05, + "loss": 4.1587, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.254759516576332e-05, + "loss": 4.1579, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.25392092182528e-05, + "loss": 4.1592, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.253082327074228e-05, + "loss": 4.1636, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.252243732323176e-05, + "loss": 4.1649, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.251405137572124e-05, + "loss": 4.1492, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.250566542821072e-05, + "loss": 4.1702, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 4.157918930053711, + "eval_runtime": 288.5832, + "eval_samples_per_second": 1322.291, + "eval_steps_per_second": 41.323, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.249729585950393e-05, + "loss": 4.1588, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.248890991199341e-05, + "loss": 4.1452, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.248052396448289e-05, + "loss": 4.1661, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247213801697237e-05, + "loss": 4.156, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.246375206946185e-05, + "loss": 4.1602, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.245536612195133e-05, + "loss": 4.1534, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.244698017444081e-05, + "loss": 4.1515, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243859422693029e-05, + "loss": 4.1495, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243020827941978e-05, + "loss": 4.1582, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.242182233190926e-05, + "loss": 4.1539, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.241343638439873e-05, + "loss": 4.1638, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240505043688821e-05, + "loss": 4.1654, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239668086818143e-05, + "loss": 4.1505, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238829492067091e-05, + "loss": 4.1541, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.237990897316038e-05, + "loss": 4.1563, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.237152302564986e-05, + "loss": 4.1484, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.236313707813934e-05, + "loss": 4.1424, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.235475113062882e-05, + "loss": 4.1509, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.23463651831183e-05, + "loss": 4.1488, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233797923560778e-05, + "loss": 4.162, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.232959328809726e-05, + "loss": 4.158, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232120734058675e-05, + "loss": 4.1575, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.231282139307623e-05, + "loss": 4.1627, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230443544556571e-05, + "loss": 4.1643, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.2296065876858916e-05, + "loss": 4.144, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.2287679929348396e-05, + "loss": 4.157, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.2279293981837876e-05, + "loss": 4.1407, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.2270908034327356e-05, + "loss": 4.1483, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.2262538465620565e-05, + "loss": 4.1477, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.2254152518110045e-05, + "loss": 4.1447, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.2245766570599525e-05, + "loss": 4.1579, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.2237380623089005e-05, + "loss": 4.1496, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.2228994675578485e-05, + "loss": 4.1477, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.2220608728067965e-05, + "loss": 4.154, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221223915936118e-05, + "loss": 4.1509, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.220385321185066e-05, + "loss": 4.1543, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219546726434014e-05, + "loss": 4.1431, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.218708131682962e-05, + "loss": 4.1413, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.2178695369319094e-05, + "loss": 4.1367, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.2170309421808574e-05, + "loss": 4.1419, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.2161923474298054e-05, + "loss": 4.1416, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.215355390559126e-05, + "loss": 4.1504, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.214516795808074e-05, + "loss": 4.1475, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.213678201057022e-05, + "loss": 4.1471, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.21283960630597e-05, + "loss": 4.1562, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.212001011554918e-05, + "loss": 4.1466, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.2111656925646134e-05, + "loss": 4.1507, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.2103270978135614e-05, + "loss": 4.1377, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.2094885030625094e-05, + "loss": 4.128, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208649908311457e-05, + "loss": 4.1572, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207811313560405e-05, + "loss": 4.1405, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.206972718809353e-05, + "loss": 4.135, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.206134124058301e-05, + "loss": 4.1396, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.205295529307249e-05, + "loss": 4.1341, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.204460210316943e-05, + "loss": 4.138, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.203621615565891e-05, + "loss": 4.133, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.2027830208148385e-05, + "loss": 4.1382, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.20194606394416e-05, + "loss": 4.139, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.201107469193109e-05, + "loss": 4.1508, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200268874442057e-05, + "loss": 4.1289, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.199430279691004e-05, + "loss": 4.1285, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.198591684939952e-05, + "loss": 4.1506, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.1977530901889e-05, + "loss": 4.1224, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196914495437848e-05, + "loss": 4.1322, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.196075900686796e-05, + "loss": 4.1393, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195238943816117e-05, + "loss": 4.1494, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194400349065065e-05, + "loss": 4.1288, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193561754314013e-05, + "loss": 4.1273, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192723159562961e-05, + "loss": 4.118, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.191884564811909e-05, + "loss": 4.1373, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191045970060857e-05, + "loss": 4.1512, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.1902090131901786e-05, + "loss": 4.136, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.1893704184391266e-05, + "loss": 4.1379, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.1885318236880746e-05, + "loss": 4.1458, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.1876932289370226e-05, + "loss": 4.1516, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.1868562720663435e-05, + "loss": 4.1275, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.1860176773152915e-05, + "loss": 4.14, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.1851790825642395e-05, + "loss": 4.1401, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.1843421256935604e-05, + "loss": 4.1226, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.1835035309425084e-05, + "loss": 4.1376, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.1826649361914564e-05, + "loss": 4.1382, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.1818263414404044e-05, + "loss": 4.1371, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.1809877466893524e-05, + "loss": 4.1382, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180149151938301e-05, + "loss": 4.1361, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.179312195067622e-05, + "loss": 4.1296, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.17847360031657e-05, + "loss": 4.1374, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.177635005565518e-05, + "loss": 4.1357, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.176796410814466e-05, + "loss": 4.1277, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.175957816063414e-05, + "loss": 4.1331, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175119221312362e-05, + "loss": 4.1309, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.17428062656131e-05, + "loss": 4.1374, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.173442031810257e-05, + "loss": 4.1307, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.172603437059205e-05, + "loss": 4.125, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171764842308153e-05, + "loss": 4.1463, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170926247557101e-05, + "loss": 4.1375, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.170089290686423e-05, + "loss": 4.1328, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.169250695935371e-05, + "loss": 4.1202, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.168412101184319e-05, + "loss": 4.1326, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167573506433267e-05, + "loss": 4.124, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166736549562588e-05, + "loss": 4.1336, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.165897954811536e-05, + "loss": 4.1435, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.165059360060484e-05, + "loss": 4.1252, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.164220765309432e-05, + "loss": 4.1259, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.16338217055838e-05, + "loss": 4.1306, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.1625452136877006e-05, + "loss": 4.1066, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.161708256817022e-05, + "loss": 4.1301, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.16086966206597e-05, + "loss": 4.1113, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160031067314918e-05, + "loss": 4.1313, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159192472563866e-05, + "loss": 4.1173, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158353877812814e-05, + "loss": 4.1302, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.157515283061762e-05, + "loss": 4.122, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.15667668831071e-05, + "loss": 4.1257, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155838093559658e-05, + "loss": 4.1366, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.155002774569352e-05, + "loss": 4.1204, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.1541641798183e-05, + "loss": 4.1367, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153325585067248e-05, + "loss": 4.1408, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152486990316196e-05, + "loss": 4.1287, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151648395565144e-05, + "loss": 4.1262, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150809800814092e-05, + "loss": 4.1188, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.14997120606304e-05, + "loss": 4.1295, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149132611311988e-05, + "loss": 4.1209, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.1482956544413095e-05, + "loss": 4.1419, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.1474570596902575e-05, + "loss": 4.1131, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.1466184649392055e-05, + "loss": 4.1308, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.1457798701881535e-05, + "loss": 4.129, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.1449429133174744e-05, + "loss": 4.1258, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.1441043185664224e-05, + "loss": 4.1133, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.1432657238153704e-05, + "loss": 4.1275, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.142428766944691e-05, + "loss": 4.116, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.141590172193639e-05, + "loss": 4.1394, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140751577442587e-05, + "loss": 4.1219, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.139912982691535e-05, + "loss": 4.1295, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139074387940483e-05, + "loss": 4.11, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138235793189432e-05, + "loss": 4.1345, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.13739719843838e-05, + "loss": 4.1258, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136558603687328e-05, + "loss": 4.1283, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.135721646816649e-05, + "loss": 4.1236, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.134883052065597e-05, + "loss": 4.1263, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.134044457314545e-05, + "loss": 4.1258, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.133205862563493e-05, + "loss": 4.1402, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132368905692814e-05, + "loss": 4.1082, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.131530310941762e-05, + "loss": 4.1244, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.13069171619071e-05, + "loss": 4.1193, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.129853121439658e-05, + "loss": 4.121, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.129016164568979e-05, + "loss": 4.118, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.1281775698179273e-05, + "loss": 4.1238, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.1273389750668753e-05, + "loss": 4.1258, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.126500380315823e-05, + "loss": 4.1138, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.1256617855647707e-05, + "loss": 4.1299, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 4.1273651123046875, + "eval_runtime": 317.6105, + "eval_samples_per_second": 1201.443, + "eval_steps_per_second": 37.546, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.1248231908137186e-05, + "loss": 4.1171, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.12398623394304e-05, + "loss": 4.1101, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.123147639191988e-05, + "loss": 4.1278, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.1223090444409356e-05, + "loss": 4.1148, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.1214704496898835e-05, + "loss": 4.1213, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.1206318549388315e-05, + "loss": 4.1154, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.1197932601877795e-05, + "loss": 4.116, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.118956303317101e-05, + "loss": 4.1096, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.118117708566049e-05, + "loss": 4.1217, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.117279113814997e-05, + "loss": 4.1144, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.116440519063945e-05, + "loss": 4.1244, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.115601924312893e-05, + "loss": 4.1257, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.114764967442214e-05, + "loss": 4.1172, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.113926372691162e-05, + "loss": 4.1163, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.11308777794011e-05, + "loss": 4.1151, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.112249183189058e-05, + "loss": 4.1089, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.111410588438006e-05, + "loss": 4.1082, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.110571993686954e-05, + "loss": 4.1112, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.109733398935902e-05, + "loss": 4.1142, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.10889480418485e-05, + "loss": 4.1192, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.108056209433798e-05, + "loss": 4.126, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.1072192525631196e-05, + "loss": 4.119, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.1063822956924405e-05, + "loss": 4.1227, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.1055437009413885e-05, + "loss": 4.1268, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.1047051061903365e-05, + "loss": 4.1032, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.1038665114392845e-05, + "loss": 4.1215, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.1030279166882325e-05, + "loss": 4.1086, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.1021893219371805e-05, + "loss": 4.1104, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.1013507271861285e-05, + "loss": 4.1073, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.1005121324350764e-05, + "loss": 4.1127, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.0996751755643974e-05, + "loss": 4.1143, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.0988365808133454e-05, + "loss": 4.1161, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.0979979860622933e-05, + "loss": 4.1127, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.0971593913112413e-05, + "loss": 4.1179, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.096322434440563e-05, + "loss": 4.1081, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.095483839689511e-05, + "loss": 4.1179, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.094646882818832e-05, + "loss": 4.1138, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.09380828806778e-05, + "loss": 4.0976, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.092969693316728e-05, + "loss": 4.1015, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.092131098565676e-05, + "loss": 4.1042, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.091292503814624e-05, + "loss": 4.1088, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.090453909063572e-05, + "loss": 4.1128, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.089615314312519e-05, + "loss": 4.1106, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.088776719561467e-05, + "loss": 4.107, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.087939762690789e-05, + "loss": 4.1214, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.087101167939737e-05, + "loss": 4.1097, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086262573188685e-05, + "loss": 4.1149, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.085423978437633e-05, + "loss": 4.1042, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.084585383686581e-05, + "loss": 4.085, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.0837484268159016e-05, + "loss": 4.1226, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.0829098320648496e-05, + "loss": 4.1069, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.0820712373137976e-05, + "loss": 4.1052, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.0812326425627456e-05, + "loss": 4.1019, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.0803956856920665e-05, + "loss": 4.0987, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.0795570909410145e-05, + "loss": 4.1016, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.078720134070336e-05, + "loss": 4.096, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.0778815393192834e-05, + "loss": 4.1033, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.077042944568232e-05, + "loss": 4.0999, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.076205987697554e-05, + "loss": 4.1167, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.0753673929465017e-05, + "loss": 4.0947, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.074528798195449e-05, + "loss": 4.0926, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.073690203444397e-05, + "loss": 4.1156, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.072851608693345e-05, + "loss": 4.0879, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.072013013942293e-05, + "loss": 4.0943, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.071174419191241e-05, + "loss": 4.1072, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.070335824440189e-05, + "loss": 4.113, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.069497229689137e-05, + "loss": 4.0942, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.068658634938085e-05, + "loss": 4.0929, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.067821678067406e-05, + "loss": 4.085, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.066983083316354e-05, + "loss": 4.1024, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.066144488565302e-05, + "loss": 4.1154, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.0653058938142505e-05, + "loss": 4.1019, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.0644672990631985e-05, + "loss": 4.1031, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.0636287043121465e-05, + "loss": 4.1134, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.0627901095610945e-05, + "loss": 4.1178, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.0619531526904154e-05, + "loss": 4.0903, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.0611145579393634e-05, + "loss": 4.1086, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.0602759631883114e-05, + "loss": 4.0985, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.0594373684372594e-05, + "loss": 4.0941, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.0585987736862074e-05, + "loss": 4.0991, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.0577601789351554e-05, + "loss": 4.1084, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.056921584184103e-05, + "loss": 4.1029, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.056084627313424e-05, + "loss": 4.1091, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.055246032562372e-05, + "loss": 4.0994, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.05440743781132e-05, + "loss": 4.0931, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.053568843060268e-05, + "loss": 4.1027, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.052730248309216e-05, + "loss": 4.1009, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.051893291438538e-05, + "loss": 4.0936, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.051054696687485e-05, + "loss": 4.0984, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.050216101936433e-05, + "loss": 4.0994, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049377507185381e-05, + "loss": 4.1045, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.048538912434329e-05, + "loss": 4.0971, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.047700317683277e-05, + "loss": 4.0879, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.046861722932225e-05, + "loss": 4.1093, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.046023128181173e-05, + "loss": 4.1051, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.045186171310494e-05, + "loss": 4.0983, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.044347576559443e-05, + "loss": 4.0898, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.043508981808391e-05, + "loss": 4.0964, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.042670387057339e-05, + "loss": 4.0905, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.0418334301866596e-05, + "loss": 4.1006, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.0409948354356076e-05, + "loss": 4.1086, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.0401562406845556e-05, + "loss": 4.0955, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.0393176459335036e-05, + "loss": 4.0931, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.0384806890628245e-05, + "loss": 4.0925, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.0376420943117725e-05, + "loss": 4.0793, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.0368034995607205e-05, + "loss": 4.092, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.0359665426900414e-05, + "loss": 4.0793, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.0351279479389894e-05, + "loss": 4.0993, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.0342893531879374e-05, + "loss": 4.0857, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.033450758436886e-05, + "loss": 4.0959, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.032612163685834e-05, + "loss": 4.0865, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.031775206815155e-05, + "loss": 4.0955, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.030936612064103e-05, + "loss": 4.0986, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.030098017313051e-05, + "loss": 4.0891, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.029259422561999e-05, + "loss": 4.1069, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.028420827810947e-05, + "loss": 4.1051, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.027582233059895e-05, + "loss": 4.0945, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.026743638308843e-05, + "loss": 4.0968, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.025905043557791e-05, + "loss": 4.0847, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.025066448806738e-05, + "loss": 4.0961, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.02422949193606e-05, + "loss": 4.0927, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.023390897185008e-05, + "loss": 4.1027, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.022552302433956e-05, + "loss": 4.0828, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.021713707682904e-05, + "loss": 4.0998, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.0208767508122255e-05, + "loss": 4.0993, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.0200381560611735e-05, + "loss": 4.0933, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.0191995613101214e-05, + "loss": 4.078, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.018360966559069e-05, + "loss": 4.0968, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.0175240096883904e-05, + "loss": 4.0862, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.016687052817711e-05, + "loss": 4.1025, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.015848458066659e-05, + "loss": 4.0944, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.015009863315607e-05, + "loss": 4.0955, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.014171268564555e-05, + "loss": 4.0753, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.013332673813503e-05, + "loss": 4.1065, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.012494079062451e-05, + "loss": 4.0899, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011657122191773e-05, + "loss": 4.097, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.010818527440721e-05, + "loss": 4.093, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.009979932689669e-05, + "loss": 4.0928, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.009141337938616e-05, + "loss": 4.0967, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.008302743187564e-05, + "loss": 4.1064, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.007464148436512e-05, + "loss": 4.0776, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.00662555368546e-05, + "loss": 4.0937, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.005786958934408e-05, + "loss": 4.0865, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.004948364183356e-05, + "loss": 4.0862, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.004111407312677e-05, + "loss": 4.087, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.0032744504419986e-05, + "loss": 4.0944, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.0024358556909466e-05, + "loss": 4.0949, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.0015972609398946e-05, + "loss": 4.0812, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.0007586661888426e-05, + "loss": 4.0979, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 4.103210926055908, + "eval_runtime": 316.9009, + "eval_samples_per_second": 1204.134, + "eval_steps_per_second": 37.63, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.9999200714377906e-05, + "loss": 4.0836, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.9990814766867386e-05, + "loss": 4.0808, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.9982428819356866e-05, + "loss": 4.0925, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.9974042871846346e-05, + "loss": 4.0817, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.9965656924335826e-05, + "loss": 4.0925, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.9957270976825306e-05, + "loss": 4.079, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.9948885029314786e-05, + "loss": 4.0918, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.9940499081804266e-05, + "loss": 4.0771, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.9932113134293746e-05, + "loss": 4.0891, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.992372718678322e-05, + "loss": 4.084, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.9915341239272706e-05, + "loss": 4.0906, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.9906955291762185e-05, + "loss": 4.096, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.98985857230554e-05, + "loss": 4.0838, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.9890199775544875e-05, + "loss": 4.0863, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.9881813828034354e-05, + "loss": 4.0849, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.9873427880523834e-05, + "loss": 4.0755, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.9865041933013314e-05, + "loss": 4.0759, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.9856655985502794e-05, + "loss": 4.0816, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.9848270037992274e-05, + "loss": 4.082, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.9839884090481754e-05, + "loss": 4.0841, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.9831498142971234e-05, + "loss": 4.0957, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.9823112195460714e-05, + "loss": 4.0884, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.9814726247950194e-05, + "loss": 4.0926, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.9806340300439674e-05, + "loss": 4.0925, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.9797954352929154e-05, + "loss": 4.0772, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.978958478422237e-05, + "loss": 4.0874, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978121521551558e-05, + "loss": 4.0767, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.977282926800506e-05, + "loss": 4.0809, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.976444332049454e-05, + "loss": 4.0814, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.975605737298402e-05, + "loss": 4.078, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.974768780427723e-05, + "loss": 4.0839, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.973930185676671e-05, + "loss": 4.0847, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973091590925619e-05, + "loss": 4.082, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.972252996174567e-05, + "loss": 4.088, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.971414401423515e-05, + "loss": 4.077, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.970575806672463e-05, + "loss": 4.0885, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.969740487682157e-05, + "loss": 4.0827, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.968901892931105e-05, + "loss": 4.0685, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968063298180053e-05, + "loss": 4.0747, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967224703429001e-05, + "loss": 4.0695, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966386108677949e-05, + "loss": 4.0794, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.965547513926897e-05, + "loss": 4.0833, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964708919175845e-05, + "loss": 4.08, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963870324424793e-05, + "loss": 4.0791, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.9630317296737406e-05, + "loss": 4.0886, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.9621931349226886e-05, + "loss": 4.0812, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.96135617805201e-05, + "loss": 4.0868, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.960517583300958e-05, + "loss": 4.0755, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.959678988549906e-05, + "loss": 4.0479, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958840393798854e-05, + "loss": 4.0981, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.958001799047802e-05, + "loss": 4.0726, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.95716320429675e-05, + "loss": 4.0795, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956324609545698e-05, + "loss": 4.0711, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.955486014794646e-05, + "loss": 4.0702, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.954649057923967e-05, + "loss": 4.0684, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953810463172915e-05, + "loss": 4.0672, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.952971868421863e-05, + "loss": 4.0738, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.952133273670811e-05, + "loss": 4.0684, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.951294678919759e-05, + "loss": 4.0886, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.950456084168707e-05, + "loss": 4.0686, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949619127298028e-05, + "loss": 4.0643, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.948780532546976e-05, + "loss": 4.0838, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.9479419377959246e-05, + "loss": 4.0609, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.9471033430448726e-05, + "loss": 4.0637, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.9462647482938206e-05, + "loss": 4.0786, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.9454277914231415e-05, + "loss": 4.0802, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.9445891966720895e-05, + "loss": 4.0654, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.9437506019210375e-05, + "loss": 4.0653, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.9429120071699855e-05, + "loss": 4.056, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.9420734124189335e-05, + "loss": 4.072, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.9412364555482544e-05, + "loss": 4.0879, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.9403978607972024e-05, + "loss": 4.0709, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.9395592660461504e-05, + "loss": 4.0776, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.9387206712950984e-05, + "loss": 4.0803, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.93788371442442e-05, + "loss": 4.088, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.937046757553741e-05, + "loss": 4.0641, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936208162802689e-05, + "loss": 4.0786, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.935369568051637e-05, + "loss": 4.0687, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.934530973300585e-05, + "loss": 4.0696, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.933694016429906e-05, + "loss": 4.0686, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.932855421678854e-05, + "loss": 4.0772, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.932016826927802e-05, + "loss": 4.0727, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.93117823217675e-05, + "loss": 4.0827, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.9303412753060706e-05, + "loss": 4.0649, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.9295026805550186e-05, + "loss": 4.0662, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.9286640858039666e-05, + "loss": 4.0779, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927825491052915e-05, + "loss": 4.0698, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.926986896301863e-05, + "loss": 4.0621, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926149939431184e-05, + "loss": 4.072, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925311344680132e-05, + "loss": 4.0714, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.92447274992908e-05, + "loss": 4.0774, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923634155178028e-05, + "loss": 4.068, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922795560426976e-05, + "loss": 4.0595, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.921956965675924e-05, + "loss": 4.0806, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.921120008805245e-05, + "loss": 4.0752, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.920281414054193e-05, + "loss": 4.0684, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.919442819303141e-05, + "loss": 4.0649, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918604224552089e-05, + "loss": 4.0649, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.917765629801037e-05, + "loss": 4.0624, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.916927035049985e-05, + "loss": 4.0739, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.916088440298933e-05, + "loss": 4.0797, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.915251483428254e-05, + "loss": 4.0695, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.914412888677202e-05, + "loss": 4.0645, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.91357429392615e-05, + "loss": 4.0588, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912735699175098e-05, + "loss": 4.0581, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.911897104424046e-05, + "loss": 4.0607, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.911060147553367e-05, + "loss": 4.0537, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.910221552802315e-05, + "loss": 4.0708, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.909382958051263e-05, + "loss": 4.0585, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.908544363300211e-05, + "loss": 4.0655, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907705768549159e-05, + "loss": 4.0558, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.906867173798107e-05, + "loss": 4.0696, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.9060285790470555e-05, + "loss": 4.0716, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.9051916221763764e-05, + "loss": 4.0594, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.9043530274253244e-05, + "loss": 4.0806, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.9035144326742724e-05, + "loss": 4.0796, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.9026758379232204e-05, + "loss": 4.0662, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.901838881052541e-05, + "loss": 4.0693, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.901000286301489e-05, + "loss": 4.0586, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.900161691550437e-05, + "loss": 4.0628, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.899323096799385e-05, + "loss": 4.0721, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.898484502048333e-05, + "loss": 4.0709, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.897645907297281e-05, + "loss": 4.0562, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896807312546229e-05, + "loss": 4.0728, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.895970355675551e-05, + "loss": 4.0726, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.895131760924499e-05, + "loss": 4.0671, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.894293166173447e-05, + "loss": 4.0541, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.893454571422395e-05, + "loss": 4.0659, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.892615976671343e-05, + "loss": 4.0565, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.891779019800664e-05, + "loss": 4.077, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.890940425049612e-05, + "loss": 4.0649, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.89010183029856e-05, + "loss": 4.0713, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889263235547508e-05, + "loss": 4.0482, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.888424640796455e-05, + "loss": 4.0778, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887586046045403e-05, + "loss": 4.0606, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886747451294351e-05, + "loss": 4.0714, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.885908856543299e-05, + "loss": 4.0668, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.885070261792248e-05, + "loss": 4.0629, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.884231667041196e-05, + "loss": 4.0688, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.8833947101705167e-05, + "loss": 4.0779, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.8825561154194647e-05, + "loss": 4.0503, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.8817175206684127e-05, + "loss": 4.0697, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.8808789259173606e-05, + "loss": 4.0585, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.8800419690466816e-05, + "loss": 4.0592, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.8792033742956296e-05, + "loss": 4.061, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.8783647795445775e-05, + "loss": 4.0668, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.8775261847935255e-05, + "loss": 4.0656, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.8766875900424735e-05, + "loss": 4.0598, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.8758506331717944e-05, + "loss": 4.0699, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 4.0840983390808105, + "eval_runtime": 319.7445, + "eval_samples_per_second": 1193.425, + "eval_steps_per_second": 37.295, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.875012038420743e-05, + "loss": 4.0558, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.874173443669691e-05, + "loss": 4.0545, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.873334848918639e-05, + "loss": 4.0642, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.87249789204796e-05, + "loss": 4.0569, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.871659297296908e-05, + "loss": 4.064, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.870820702545856e-05, + "loss": 4.0534, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.869982107794804e-05, + "loss": 4.0659, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.869143513043752e-05, + "loss": 4.0516, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.8683049182927e-05, + "loss": 4.059, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.867466323541648e-05, + "loss": 4.0604, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.866627728790596e-05, + "loss": 4.0612, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.86579240980029e-05, + "loss": 4.0668, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.8649554529296114e-05, + "loss": 4.0702, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.8641168581785594e-05, + "loss": 4.0514, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.8632782634275074e-05, + "loss": 4.0568, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.8624396686764554e-05, + "loss": 4.0512, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.8616010739254034e-05, + "loss": 4.0477, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.860764117054724e-05, + "loss": 4.0579, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.859925522303672e-05, + "loss": 4.0516, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.85908692755262e-05, + "loss": 4.0578, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.858248332801568e-05, + "loss": 4.0704, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.857409738050516e-05, + "loss": 4.0655, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.856571143299464e-05, + "loss": 4.0653, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.855732548548412e-05, + "loss": 4.065, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.85489395379736e-05, + "loss": 4.0499, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.854055359046308e-05, + "loss": 4.0598, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.853216764295256e-05, + "loss": 4.051, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.852378169544204e-05, + "loss": 4.0576, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.851539574793152e-05, + "loss": 4.0509, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.850704255802847e-05, + "loss": 4.0534, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.849865661051795e-05, + "loss": 4.0552, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.849027066300743e-05, + "loss": 4.058, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.848188471549691e-05, + "loss": 4.0561, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.847349876798639e-05, + "loss": 4.0572, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.846511282047586e-05, + "loss": 4.0539, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.845672687296534e-05, + "loss": 4.0601, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.8448357304258556e-05, + "loss": 4.0602, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.8439971356748036e-05, + "loss": 4.0442, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.8431585409237516e-05, + "loss": 4.0481, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.8423199461726996e-05, + "loss": 4.0455, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.8414813514216476e-05, + "loss": 4.0476, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.8406427566705956e-05, + "loss": 4.055, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.8398041619195436e-05, + "loss": 4.0572, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.8389672050488645e-05, + "loss": 4.055, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.8381286102978125e-05, + "loss": 4.0592, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.8372900155467605e-05, + "loss": 4.0572, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.8364514207957085e-05, + "loss": 4.0597, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.8356128260446565e-05, + "loss": 4.0501, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.8347758691739774e-05, + "loss": 4.0277, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.8339372744229254e-05, + "loss": 4.0694, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.833098679671874e-05, + "loss": 4.0464, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.832260084920822e-05, + "loss": 4.0524, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.83142149016977e-05, + "loss": 4.0485, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.830582895418718e-05, + "loss": 4.0421, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.829744300667666e-05, + "loss": 4.044, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.828905705916614e-05, + "loss": 4.0413, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.828067111165562e-05, + "loss": 4.0504, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.827230154294883e-05, + "loss": 4.0419, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.826391559543831e-05, + "loss": 4.0617, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.825552964792779e-05, + "loss": 4.0445, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.824714370041727e-05, + "loss": 4.0318, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.823875775290675e-05, + "loss": 4.0606, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.823038818419996e-05, + "loss": 4.0378, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.822200223668944e-05, + "loss": 4.0371, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.8213616289178925e-05, + "loss": 4.0534, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.8205246720472134e-05, + "loss": 4.0582, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.8196860772961614e-05, + "loss": 4.0398, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.8188474825451094e-05, + "loss": 4.0391, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.8180088877940574e-05, + "loss": 4.0329, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.817170293043005e-05, + "loss": 4.0466, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.816333336172326e-05, + "loss": 4.0608, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.815494741421274e-05, + "loss": 4.0483, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.814656146670222e-05, + "loss": 4.0517, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.8138175519191696e-05, + "loss": 4.0519, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.812980595048491e-05, + "loss": 4.0619, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.812143638177813e-05, + "loss": 4.0418, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.811305043426761e-05, + "loss": 4.0578, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810466448675709e-05, + "loss": 4.0387, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.809627853924657e-05, + "loss": 4.0459, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808789259173605e-05, + "loss": 4.0432, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.807950664422552e-05, + "loss": 4.0503, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.8071120696715e-05, + "loss": 4.0511, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.806273474920448e-05, + "loss": 4.0583, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.805434880169396e-05, + "loss": 4.039, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.804597923298717e-05, + "loss": 4.0425, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.803759328547665e-05, + "loss": 4.0503, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.802920733796613e-05, + "loss": 4.0492, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.802082139045561e-05, + "loss": 4.0374, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.801246820055256e-05, + "loss": 4.0444, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.800408225304204e-05, + "loss": 4.0487, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.799569630553152e-05, + "loss": 4.0495, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.7987310358020995e-05, + "loss": 4.0446, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.7978924410510475e-05, + "loss": 4.033, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.797055484180369e-05, + "loss": 4.0562, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.7962168894293164e-05, + "loss": 4.051, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.7953782946782644e-05, + "loss": 4.0435, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.7945396999272124e-05, + "loss": 4.0388, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.7937011051761604e-05, + "loss": 4.0417, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.7928625104251084e-05, + "loss": 4.0356, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.7920239156740564e-05, + "loss": 4.0516, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.791186958803378e-05, + "loss": 4.0541, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.790348364052326e-05, + "loss": 4.0412, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.789509769301274e-05, + "loss": 4.0465, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.788671174550222e-05, + "loss": 4.0354, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.787834217679543e-05, + "loss": 4.0364, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.786995622928491e-05, + "loss": 4.0326, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.786157028177439e-05, + "loss": 4.033, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.785318433426387e-05, + "loss": 4.0431, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.784479838675335e-05, + "loss": 4.0368, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.783641243924283e-05, + "loss": 4.039, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.782802649173231e-05, + "loss": 4.0359, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.781964054422179e-05, + "loss": 4.0397, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.7811270975515004e-05, + "loss": 4.049, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.780290140680821e-05, + "loss": 4.0361, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.779451545929769e-05, + "loss": 4.0537, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.778612951178717e-05, + "loss": 4.0557, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.777774356427665e-05, + "loss": 4.0453, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.776935761676613e-05, + "loss": 4.0403, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.776097166925561e-05, + "loss": 4.0358, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.775258572174509e-05, + "loss": 4.0407, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.77442161530383e-05, + "loss": 4.0478, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.773583020552778e-05, + "loss": 4.045, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.772744425801726e-05, + "loss": 4.0347, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.771905831050674e-05, + "loss": 4.0503, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.771067236299622e-05, + "loss": 4.0514, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.77022864154857e-05, + "loss": 4.0364, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.769390046797518e-05, + "loss": 4.0316, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.768551452046466e-05, + "loss": 4.0453, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.767714495175788e-05, + "loss": 4.0318, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.7668775383051087e-05, + "loss": 4.0557, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.7660389435540566e-05, + "loss": 4.038, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.7652003488030046e-05, + "loss": 4.0489, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.7643617540519526e-05, + "loss": 4.0264, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.7635231593009e-05, + "loss": 4.0499, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.762684564549848e-05, + "loss": 4.0468, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.761845969798796e-05, + "loss": 4.0426, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.761007375047744e-05, + "loss": 4.0439, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.7601704181770655e-05, + "loss": 4.0376, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.7593318234260135e-05, + "loss": 4.0448, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.7584932286749615e-05, + "loss": 4.0622, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.7576546339239095e-05, + "loss": 4.0242, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.7568176770532304e-05, + "loss": 4.0465, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.7559790823021784e-05, + "loss": 4.0373, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.7551404875511264e-05, + "loss": 4.0326, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.7543018928000744e-05, + "loss": 4.0398, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.753464935929395e-05, + "loss": 4.0415, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.752626341178343e-05, + "loss": 4.0422, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.751787746427291e-05, + "loss": 4.0396, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.750949151676239e-05, + "loss": 4.0453, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 4.068212509155273, + "eval_runtime": 318.7899, + "eval_samples_per_second": 1196.998, + "eval_steps_per_second": 37.407, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.750110556925188e-05, + "loss": 4.0247, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.749271962174136e-05, + "loss": 4.0333, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.748433367423084e-05, + "loss": 4.0392, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.747594772672032e-05, + "loss": 4.0353, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.74675617792098e-05, + "loss": 4.0434, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.745917583169928e-05, + "loss": 4.031, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.745078988418876e-05, + "loss": 4.0413, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744240393667824e-05, + "loss": 4.0287, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.743401798916771e-05, + "loss": 4.0381, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.742563204165719e-05, + "loss": 4.0374, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.741724609414667e-05, + "loss": 4.0349, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.740886014663615e-05, + "loss": 4.0471, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.740049057792936e-05, + "loss": 4.0485, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.739210463041884e-05, + "loss": 4.0291, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.738371868290833e-05, + "loss": 4.0365, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.737533273539781e-05, + "loss": 4.0267, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.736694678788729e-05, + "loss": 4.0271, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.735856084037677e-05, + "loss": 4.0347, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.735017489286625e-05, + "loss": 4.0267, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.734178894535573e-05, + "loss": 4.0362, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.733340299784521e-05, + "loss": 4.0488, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.732501705033469e-05, + "loss": 4.0424, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.731663110282417e-05, + "loss": 4.0449, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.730824515531365e-05, + "loss": 4.0411, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.729985920780313e-05, + "loss": 4.0326, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.729148963909634e-05, + "loss": 4.0375, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.728310369158582e-05, + "loss": 4.0282, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.7274734122879026e-05, + "loss": 4.0387, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.726634817536851e-05, + "loss": 4.0275, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.725796222785799e-05, + "loss": 4.0299, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.724957628034747e-05, + "loss": 4.0328, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.724119033283695e-05, + "loss": 4.0367, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.723280438532643e-05, + "loss": 4.0395, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.7224418437815906e-05, + "loss": 4.0328, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.7216032490305386e-05, + "loss": 4.0338, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.72076629215986e-05, + "loss": 4.0335, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.7199276974088075e-05, + "loss": 4.041, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.7190891026577555e-05, + "loss": 4.0231, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.7182505079067035e-05, + "loss": 4.0241, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.7174119131556515e-05, + "loss": 4.0256, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.7165733184045995e-05, + "loss": 4.0254, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.715736361533921e-05, + "loss": 4.0313, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.714897766782869e-05, + "loss": 4.0363, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.714059172031817e-05, + "loss": 4.0332, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.713220577280765e-05, + "loss": 4.0372, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.712381982529713e-05, + "loss": 4.0344, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.711545025659034e-05, + "loss": 4.0379, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.710706430907982e-05, + "loss": 4.0302, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.70986783615693e-05, + "loss": 4.005, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.709029241405878e-05, + "loss": 4.0447, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.708192284535199e-05, + "loss": 4.0251, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.707353689784147e-05, + "loss": 4.0314, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.706515095033095e-05, + "loss": 4.0282, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.7056765002820435e-05, + "loss": 4.0173, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.7048395434113644e-05, + "loss": 4.0275, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.7040009486603124e-05, + "loss": 4.0186, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.7031623539092604e-05, + "loss": 4.0314, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.7023237591582084e-05, + "loss": 4.0183, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.7014851644071564e-05, + "loss": 4.0398, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.7006465696561044e-05, + "loss": 4.0229, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.6998079749050524e-05, + "loss": 4.0082, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.6989693801540004e-05, + "loss": 4.0424, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.6981307854029484e-05, + "loss": 4.016, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.697293828532269e-05, + "loss": 4.0145, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.696455233781217e-05, + "loss": 4.0322, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.695618276910538e-05, + "loss": 4.0364, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.694779682159487e-05, + "loss": 4.0186, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.693941087408435e-05, + "loss": 4.0194, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.693102492657383e-05, + "loss": 4.0118, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.692263897906331e-05, + "loss": 4.0202, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.691425303155279e-05, + "loss": 4.0353, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.6905883462846e-05, + "loss": 4.0297, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.689749751533548e-05, + "loss": 4.0299, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.688911156782496e-05, + "loss": 4.0304, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.688072562031444e-05, + "loss": 4.0392, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.6872356051607646e-05, + "loss": 4.0247, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.6863970104097126e-05, + "loss": 4.0334, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.6855584156586606e-05, + "loss": 4.0164, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.6847198209076086e-05, + "loss": 4.0236, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.6838812261565566e-05, + "loss": 4.0212, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.6830426314055046e-05, + "loss": 4.0278, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.6822040366544526e-05, + "loss": 4.0314, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.6813654419034006e-05, + "loss": 4.0353, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.6805284850327215e-05, + "loss": 4.0214, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.6796898902816695e-05, + "loss": 4.0198, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.678852933410991e-05, + "loss": 4.0266, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.6780143386599384e-05, + "loss": 4.0292, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.6771757439088864e-05, + "loss": 4.0167, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.6763371491578344e-05, + "loss": 4.0238, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.6754985544067824e-05, + "loss": 4.0339, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.6746599596557304e-05, + "loss": 4.0244, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.673821364904679e-05, + "loss": 4.023, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.672982770153627e-05, + "loss": 4.0139, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.672145813282948e-05, + "loss": 4.0306, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.671307218531896e-05, + "loss": 4.0334, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.670468623780844e-05, + "loss": 4.0241, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669630029029792e-05, + "loss": 4.0187, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.668793072159113e-05, + "loss": 4.0194, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.667954477408061e-05, + "loss": 4.0164, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.667115882657009e-05, + "loss": 4.0294, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.666277287905957e-05, + "loss": 4.0341, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.665440331035278e-05, + "loss": 4.0189, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.664601736284226e-05, + "loss": 4.0228, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.6637631415331745e-05, + "loss": 4.0188, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.6629261846624954e-05, + "loss": 4.0111, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.6620875899114434e-05, + "loss": 4.0146, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.6612489951603914e-05, + "loss": 4.0121, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.6604104004093393e-05, + "loss": 4.0171, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.6595718056582873e-05, + "loss": 4.0183, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.658733210907235e-05, + "loss": 4.0145, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.657894616156183e-05, + "loss": 4.0176, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.657056021405131e-05, + "loss": 4.0162, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.656219064534452e-05, + "loss": 4.0278, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.6553804697834e-05, + "loss": 4.0132, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.654541875032348e-05, + "loss": 4.0342, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.653703280281296e-05, + "loss": 4.0326, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.652866323410618e-05, + "loss": 4.0273, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.652027728659566e-05, + "loss": 4.0191, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.651189133908514e-05, + "loss": 4.0155, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.650350539157462e-05, + "loss": 4.0191, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.64951194440641e-05, + "loss": 4.0293, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.648674987535731e-05, + "loss": 4.024, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.6478380306650516e-05, + "loss": 4.0152, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.6469994359139996e-05, + "loss": 4.0243, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.6461608411629476e-05, + "loss": 4.033, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.6453222464118956e-05, + "loss": 4.0164, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.6444836516608436e-05, + "loss": 4.012, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.6436450569097916e-05, + "loss": 4.0229, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.642808100039113e-05, + "loss": 4.0085, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.641969505288061e-05, + "loss": 4.0377, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.641130910537009e-05, + "loss": 4.0159, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.640292315785957e-05, + "loss": 4.028, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.6394537210349045e-05, + "loss": 4.007, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.6386151262838525e-05, + "loss": 4.0255, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.6377765315328005e-05, + "loss": 4.0238, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.6369379367817485e-05, + "loss": 4.0244, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636102617791443e-05, + "loss": 4.0219, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.635264023040391e-05, + "loss": 4.0185, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.634425428289339e-05, + "loss": 4.023, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.633586833538287e-05, + "loss": 4.04, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.632748238787235e-05, + "loss": 4.0065, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.631909644036183e-05, + "loss": 4.0219, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.631071049285131e-05, + "loss": 4.0196, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.630234092414452e-05, + "loss": 4.0135, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.6293954976634e-05, + "loss": 4.0193, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.628556902912348e-05, + "loss": 4.0215, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.627718308161296e-05, + "loss": 4.0199, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.626879713410244e-05, + "loss": 4.0177, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.626041118659192e-05, + "loss": 4.0227, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 4.054370403289795, + "eval_runtime": 298.866, + "eval_samples_per_second": 1276.796, + "eval_steps_per_second": 39.901, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.62520252390814e-05, + "loss": 4.0123, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.624365567037461e-05, + "loss": 4.0126, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.623528610166782e-05, + "loss": 4.0201, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.62269001541573e-05, + "loss": 4.0149, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.621851420664678e-05, + "loss": 4.0235, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.621012825913626e-05, + "loss": 4.0133, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.620174231162574e-05, + "loss": 4.0189, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.619335636411522e-05, + "loss": 4.0131, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.61849704166047e-05, + "loss": 4.0182, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.617658446909418e-05, + "loss": 4.0121, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.616819852158366e-05, + "loss": 4.0169, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.615982895287687e-05, + "loss": 4.0315, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.615145938417008e-05, + "loss": 4.0227, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.614307343665956e-05, + "loss": 4.0091, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.613468748914904e-05, + "loss": 4.017, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.612630154163852e-05, + "loss": 4.0053, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.611791559412801e-05, + "loss": 4.0098, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.610954602542122e-05, + "loss": 4.0177, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.61011600779107e-05, + "loss": 4.0056, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.609277413040018e-05, + "loss": 4.0165, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.608438818288966e-05, + "loss": 4.0242, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.607600223537914e-05, + "loss": 4.0229, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.6067616287868617e-05, + "loss": 4.025, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.6059230340358097e-05, + "loss": 4.0216, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.6050844392847576e-05, + "loss": 4.0104, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.6042474824140786e-05, + "loss": 4.0157, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.6034088876630266e-05, + "loss": 4.0084, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.6025702929119745e-05, + "loss": 4.0159, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.6017316981609225e-05, + "loss": 4.0099, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.6008931034098705e-05, + "loss": 4.0142, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.600056146539192e-05, + "loss": 4.0129, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.59921755178814e-05, + "loss": 4.0127, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.598378957037088e-05, + "loss": 4.0161, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.5975403622860354e-05, + "loss": 4.0151, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.5967017675349834e-05, + "loss": 4.012, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.595864810664305e-05, + "loss": 4.0169, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.595026215913253e-05, + "loss": 4.0239, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.5941876211622e-05, + "loss": 4.0026, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.593349026411148e-05, + "loss": 4.0037, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.592510431660096e-05, + "loss": 4.0065, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.591671836909044e-05, + "loss": 4.0028, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.590833242157993e-05, + "loss": 4.0137, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.589994647406941e-05, + "loss": 4.0137, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.5891593284166355e-05, + "loss": 4.0185, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.588320733665583e-05, + "loss": 4.016, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.587482138914531e-05, + "loss": 4.0156, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.5866451820438524e-05, + "loss": 4.0173, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.5858065872928004e-05, + "loss": 4.0122, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.584967992541748e-05, + "loss": 3.9889, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.584129397790696e-05, + "loss": 4.0237, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.583290803039644e-05, + "loss": 4.0053, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.582452208288592e-05, + "loss": 4.0132, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.58161361353754e-05, + "loss": 4.0027, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.5807750187864884e-05, + "loss": 4.0009, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.5799364240354364e-05, + "loss": 4.0088, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.5790978292843844e-05, + "loss": 4.0025, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.5782592345333323e-05, + "loss": 4.0113, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.577422277662653e-05, + "loss": 3.996, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.576583682911601e-05, + "loss": 4.0224, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.575745088160549e-05, + "loss": 4.0088, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.574906493409497e-05, + "loss": 3.9846, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.574067898658445e-05, + "loss": 4.021, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.573229303907393e-05, + "loss": 3.9973, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.572390709156341e-05, + "loss": 3.9976, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.5715521144052885e-05, + "loss": 4.0103, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.57071515753461e-05, + "loss": 4.017, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.569876562783558e-05, + "loss": 3.9987, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.569037968032506e-05, + "loss": 4.0047, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.568199373281454e-05, + "loss": 3.9884, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.567360778530402e-05, + "loss": 4.0011, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.566523821659724e-05, + "loss": 4.0208, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.565685226908672e-05, + "loss": 4.0101, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.564846632157619e-05, + "loss": 4.012, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.5640096752869406e-05, + "loss": 4.0114, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.5631710805358886e-05, + "loss": 4.0213, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.562332485784836e-05, + "loss": 4.0081, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.561493891033784e-05, + "loss": 4.0142, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.560655296282732e-05, + "loss": 3.9991, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.55981670153168e-05, + "loss": 4.0059, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.5589781067806286e-05, + "loss": 4.0025, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.5581411499099495e-05, + "loss": 4.0077, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.5573025551588975e-05, + "loss": 4.0108, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.5564639604078455e-05, + "loss": 4.016, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.5556253656567935e-05, + "loss": 4.0106, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.5547867709057415e-05, + "loss": 3.998, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.5539481761546895e-05, + "loss": 4.0083, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.5531095814036375e-05, + "loss": 4.0108, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.5522726245329584e-05, + "loss": 3.9959, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.5514340297819064e-05, + "loss": 4.0053, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.5505954350308544e-05, + "loss": 4.0132, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.5497568402798024e-05, + "loss": 4.0034, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.548919883409124e-05, + "loss": 4.0097, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.548081288658072e-05, + "loss": 3.9949, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.54724269390702e-05, + "loss": 4.0135, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.546404099155968e-05, + "loss": 4.0109, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.545567142285289e-05, + "loss": 4.0108, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.544728547534237e-05, + "loss": 3.9926, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.543889952783185e-05, + "loss": 4.0054, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.543051358032133e-05, + "loss": 3.9954, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.542214401161454e-05, + "loss": 4.012, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.541375806410402e-05, + "loss": 4.0185, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.54053721165935e-05, + "loss": 3.9971, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.539698616908298e-05, + "loss": 4.0066, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.538860022157246e-05, + "loss": 3.9972, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.538021427406194e-05, + "loss": 3.9941, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.5371828326551424e-05, + "loss": 3.9976, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.5363442379040904e-05, + "loss": 3.9959, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.535505643153038e-05, + "loss": 4.0008, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.534668686282359e-05, + "loss": 4.0005, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.533830091531307e-05, + "loss": 3.999, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.532991496780255e-05, + "loss": 3.9944, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.5321529020292026e-05, + "loss": 3.9992, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.531315945158524e-05, + "loss": 4.0145, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.530478988287845e-05, + "loss": 3.9972, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.529642031417166e-05, + "loss": 4.0115, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.528803436666115e-05, + "loss": 4.0108, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.527964841915063e-05, + "loss": 4.0166, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.527126247164011e-05, + "loss": 4.0, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.526287652412959e-05, + "loss": 3.9982, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.5254490576619067e-05, + "loss": 4.0032, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.5246104629108547e-05, + "loss": 4.0092, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.5237718681598027e-05, + "loss": 4.0103, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.52293327340875e-05, + "loss": 4.0009, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.522094678657698e-05, + "loss": 4.0013, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.5212577217870196e-05, + "loss": 4.0151, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.520419127035967e-05, + "loss": 4.0054, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.519580532284915e-05, + "loss": 3.992, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.518741937533863e-05, + "loss": 4.0033, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.517903342782811e-05, + "loss": 3.9945, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.5170647480317595e-05, + "loss": 4.0192, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.5162277911610804e-05, + "loss": 3.9995, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.5153891964100284e-05, + "loss": 4.0098, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.5145506016589764e-05, + "loss": 3.9901, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.5137120069079244e-05, + "loss": 4.0092, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.5128734121568724e-05, + "loss": 4.0061, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.5120348174058204e-05, + "loss": 4.0043, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.5111962226547684e-05, + "loss": 4.0078, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.5103576279037164e-05, + "loss": 3.9991, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.509520671033037e-05, + "loss": 4.0094, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.508682076281985e-05, + "loss": 4.0225, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.507843481530933e-05, + "loss": 3.9905, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.507004886779881e-05, + "loss": 4.0023, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.506167929909203e-05, + "loss": 4.004, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.505329335158151e-05, + "loss": 3.9974, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.504490740407099e-05, + "loss": 3.9997, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.503652145656047e-05, + "loss": 4.0069, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.502813550904995e-05, + "loss": 4.0, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.501974956153943e-05, + "loss": 4.0006, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.501137999283264e-05, + "loss": 4.0083, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 4.04392671585083, + "eval_runtime": 305.8145, + "eval_samples_per_second": 1247.786, + "eval_steps_per_second": 38.994, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.500299404532212e-05, + "loss": 3.9899, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.49946080978116e-05, + "loss": 3.9918, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.498622215030108e-05, + "loss": 4.0036, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.497783620279056e-05, + "loss": 4.0001, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.496945025528003e-05, + "loss": 4.0013, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.496106430776952e-05, + "loss": 3.9937, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.4952678360259e-05, + "loss": 4.0076, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.494429241274848e-05, + "loss": 3.9919, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.493590646523796e-05, + "loss": 4.0009, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.492752051772744e-05, + "loss": 3.9949, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.491913457021692e-05, + "loss": 4.0007, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.49107486227064e-05, + "loss": 4.0101, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.4902379053999606e-05, + "loss": 4.01, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.4893993106489086e-05, + "loss": 3.9886, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.4885607158978566e-05, + "loss": 4.0014, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.4877221211468046e-05, + "loss": 3.986, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.4868835263957526e-05, + "loss": 3.9964, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.4860449316447006e-05, + "loss": 3.9975, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.4852063368936486e-05, + "loss": 3.9891, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.4843677421425966e-05, + "loss": 4.0002, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.4835291473915446e-05, + "loss": 4.0065, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.4826905526404926e-05, + "loss": 4.0029, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.4818519578894406e-05, + "loss": 4.0089, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.4810133631383886e-05, + "loss": 4.0089, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.48017640626771e-05, + "loss": 3.9911, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.4793378115166575e-05, + "loss": 4.0019, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.4784992167656055e-05, + "loss": 3.9923, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.477662259894927e-05, + "loss": 3.9976, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.4768236651438744e-05, + "loss": 3.9927, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.4759850703928224e-05, + "loss": 3.9947, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.4751464756417704e-05, + "loss": 4.0005, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.4743078808907184e-05, + "loss": 3.9954, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.47347092402004e-05, + "loss": 3.9965, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.472632329268988e-05, + "loss": 4.0028, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.471793734517936e-05, + "loss": 3.9952, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.4709567776472575e-05, + "loss": 3.9983, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.470118182896205e-05, + "loss": 4.0065, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469279588145153e-05, + "loss": 3.9831, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468440993394101e-05, + "loss": 3.9934, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467602398643049e-05, + "loss": 3.991, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466763803891997e-05, + "loss": 3.9839, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.465925209140945e-05, + "loss": 3.9962, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465086614389893e-05, + "loss": 3.996, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464248019638841e-05, + "loss": 4.0, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.463409424887789e-05, + "loss": 3.9991, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.462570830136737e-05, + "loss": 3.9991, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.4617338732660584e-05, + "loss": 4.0024, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.4608952785150064e-05, + "loss": 3.9958, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.4600566837639544e-05, + "loss": 3.976, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.4592180890129024e-05, + "loss": 4.0018, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.4583794942618504e-05, + "loss": 3.9905, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.457542537391171e-05, + "loss": 3.9952, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.456703942640119e-05, + "loss": 3.9887, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.455865347889067e-05, + "loss": 3.9822, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.455026753138015e-05, + "loss": 3.9925, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.454189796267336e-05, + "loss": 3.9832, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.453351201516284e-05, + "loss": 3.9953, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.452512606765232e-05, + "loss": 3.9763, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.45167401201418e-05, + "loss": 4.006, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.450835417263129e-05, + "loss": 3.9925, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.44999846039245e-05, + "loss": 3.9708, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449159865641398e-05, + "loss": 4.0024, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.448321270890346e-05, + "loss": 3.9794, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.447482676139293e-05, + "loss": 3.9854, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.446644081388241e-05, + "loss": 3.9891, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.4458071245175627e-05, + "loss": 4.0018, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.4449685297665107e-05, + "loss": 3.985, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.444129935015458e-05, + "loss": 3.9871, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.443291340264406e-05, + "loss": 3.9693, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.442452745513354e-05, + "loss": 3.9909, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.4416141507623026e-05, + "loss": 4.0008, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.4407771938916235e-05, + "loss": 3.9963, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.4399385991405715e-05, + "loss": 3.9921, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.4391000043895195e-05, + "loss": 3.9959, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.4382614096384675e-05, + "loss": 4.0067, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.4374244527677884e-05, + "loss": 3.9886, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.43658749589711e-05, + "loss": 3.9949, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.435748901146058e-05, + "loss": 3.986, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.4349103063950053e-05, + "loss": 3.9923, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.4340717116439533e-05, + "loss": 3.9852, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433233116892901e-05, + "loss": 3.9885, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.432394522141849e-05, + "loss": 3.9989, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.431555927390798e-05, + "loss": 3.997, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.430717332639746e-05, + "loss": 4.0003, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.429880375769067e-05, + "loss": 3.9787, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.429041781018015e-05, + "loss": 3.994, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.428203186266963e-05, + "loss": 3.9943, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.427364591515911e-05, + "loss": 3.982, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.4265292725256054e-05, + "loss": 3.9843, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.425690677774553e-05, + "loss": 3.9956, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.424852083023501e-05, + "loss": 3.9913, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.424013488272449e-05, + "loss": 3.9888, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.423174893521397e-05, + "loss": 3.9839, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.422336298770345e-05, + "loss": 3.9946, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.4214977040192934e-05, + "loss": 3.9988, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.4206591092682414e-05, + "loss": 3.9917, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.419822152397562e-05, + "loss": 3.9785, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.41898355764651e-05, + "loss": 3.9893, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.418144962895458e-05, + "loss": 3.9814, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.417306368144406e-05, + "loss": 3.9934, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.416469411273727e-05, + "loss": 4.0024, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.415630816522675e-05, + "loss": 3.9829, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.414792221771623e-05, + "loss": 3.9878, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.413953627020571e-05, + "loss": 3.9845, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.413116670149892e-05, + "loss": 3.9801, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.41227807539884e-05, + "loss": 3.976, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.411439480647789e-05, + "loss": 3.9837, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.4106025237771096e-05, + "loss": 3.9831, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.4097639290260576e-05, + "loss": 3.9851, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.4089253342750056e-05, + "loss": 3.981, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.4080867395239536e-05, + "loss": 3.9791, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.4072481447729016e-05, + "loss": 3.9818, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.4064095500218496e-05, + "loss": 3.9994, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.4055709552707976e-05, + "loss": 3.9826, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.4047323605197456e-05, + "loss": 3.9976, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.4038954036490665e-05, + "loss": 3.9926, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.4030584467783874e-05, + "loss": 4.0016, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.4022198520273354e-05, + "loss": 3.9887, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.4013812572762834e-05, + "loss": 3.9813, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.400542662525232e-05, + "loss": 3.9884, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.39970406777418e-05, + "loss": 3.9909, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398865473023128e-05, + "loss": 3.9889, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.398026878272076e-05, + "loss": 3.9897, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.397189921401397e-05, + "loss": 3.9839, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.396351326650345e-05, + "loss": 3.9991, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.395512731899293e-05, + "loss": 3.9848, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.394674137148241e-05, + "loss": 3.9792, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.393837180277562e-05, + "loss": 3.9862, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.39299858552651e-05, + "loss": 3.981, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.392159990775458e-05, + "loss": 3.9999, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.391321396024406e-05, + "loss": 3.983, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.390482801273354e-05, + "loss": 3.9931, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.389644206522302e-05, + "loss": 3.9792, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.3888072496516235e-05, + "loss": 3.9921, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.3879686549005715e-05, + "loss": 3.9921, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.387130060149519e-05, + "loss": 3.9892, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.386291465398467e-05, + "loss": 3.985, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.385452870647415e-05, + "loss": 3.9907, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.384614275896363e-05, + "loss": 3.9948, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.383775681145311e-05, + "loss": 4.0041, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.382937086394259e-05, + "loss": 3.9775, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.3821001295235797e-05, + "loss": 3.9844, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.3812615347725277e-05, + "loss": 3.9881, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.380424577901849e-05, + "loss": 3.9828, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379585983150797e-05, + "loss": 3.983, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.378747388399745e-05, + "loss": 3.9933, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.377908793648693e-05, + "loss": 3.9815, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.377071836778014e-05, + "loss": 3.9927, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.376233242026962e-05, + "loss": 3.9855, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 4.03481912612915, + "eval_runtime": 316.2016, + "eval_samples_per_second": 1206.796, + "eval_steps_per_second": 37.713, + "step": 992160 + }, + { + "epoch": 1.0, + "learning_rate": 3.37539464727591e-05, + "loss": 3.9868, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.374556052524858e-05, + "loss": 3.9729, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.373717457773806e-05, + "loss": 3.9885, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.372880500903127e-05, + "loss": 3.9864, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.372041906152075e-05, + "loss": 3.9852, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.371203311401023e-05, + "loss": 3.9834, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.370364716649971e-05, + "loss": 3.9864, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.36952612189892e-05, + "loss": 3.9815, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.368687527147868e-05, + "loss": 3.981, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.367848932396816e-05, + "loss": 3.9857, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.367010337645764e-05, + "loss": 3.9828, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.366171742894712e-05, + "loss": 3.9925, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.3653364239044055e-05, + "loss": 3.9998, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.3644978291533535e-05, + "loss": 3.975, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.3636592344023015e-05, + "loss": 3.9803, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.3628206396512495e-05, + "loss": 3.9758, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.3619820449001975e-05, + "loss": 3.981, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.3611434501491455e-05, + "loss": 3.9832, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.3603048553980935e-05, + "loss": 3.9726, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.3594662606470415e-05, + "loss": 3.98, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.358629303776363e-05, + "loss": 3.9972, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.357792346905684e-05, + "loss": 3.9847, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.356953752154632e-05, + "loss": 3.9927, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.35611515740358e-05, + "loss": 3.994, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.355276562652528e-05, + "loss": 3.9804, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.354439605781849e-05, + "loss": 3.9888, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.353601011030797e-05, + "loss": 3.9743, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.352762416279745e-05, + "loss": 3.9829, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.351923821528693e-05, + "loss": 3.9803, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.351085226777641e-05, + "loss": 3.9769, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.350248269906962e-05, + "loss": 3.9874, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.3494096751559104e-05, + "loss": 3.9794, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.3485710804048584e-05, + "loss": 3.9865, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.3477324856538064e-05, + "loss": 3.9817, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.3468938909027544e-05, + "loss": 3.9812, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.346056934032075e-05, + "loss": 3.9888, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.345218339281023e-05, + "loss": 3.9925, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.344379744529971e-05, + "loss": 3.9632, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.343541149778919e-05, + "loss": 3.981, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.342702555027867e-05, + "loss": 3.9779, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.3418639602768146e-05, + "loss": 3.968, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.3410253655257626e-05, + "loss": 3.9803, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.3401867707747106e-05, + "loss": 3.9879, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.339349813904032e-05, + "loss": 3.9841, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.33851121915298e-05, + "loss": 3.9853, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.337672624401928e-05, + "loss": 3.9847, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.336834029650876e-05, + "loss": 3.9847, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.335997072780197e-05, + "loss": 3.9805, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.335158478029145e-05, + "loss": 3.9622, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.334319883278093e-05, + "loss": 3.9855, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.333481288527041e-05, + "loss": 3.9781, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.332642693775989e-05, + "loss": 3.9819, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.33180573690531e-05, + "loss": 3.9718, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.330967142154258e-05, + "loss": 3.9703, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.330128547403206e-05, + "loss": 3.9754, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.329289952652154e-05, + "loss": 3.9673, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.328451357901102e-05, + "loss": 3.9857, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.3276144010304236e-05, + "loss": 3.9663, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.3267758062793716e-05, + "loss": 3.9861, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.3259372115283195e-05, + "loss": 3.9812, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.3250986167772675e-05, + "loss": 3.9599, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.3242600220262155e-05, + "loss": 3.9836, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.3234230651555364e-05, + "loss": 3.9675, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.3225844704044844e-05, + "loss": 3.9713, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.3217458756534324e-05, + "loss": 3.9708, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.3209072809023804e-05, + "loss": 3.9887, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.3200686861513284e-05, + "loss": 3.9723, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.3192300914002764e-05, + "loss": 3.9716, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.3183914966492244e-05, + "loss": 3.954, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.3175529018981724e-05, + "loss": 3.9704, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.3167143071471204e-05, + "loss": 3.9882, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.315877350276442e-05, + "loss": 3.9855, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.31503875552539e-05, + "loss": 3.9743, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.314200160774338e-05, + "loss": 3.984, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.313361566023286e-05, + "loss": 3.9908, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.31252624703298e-05, + "loss": 3.9726, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.311687652281928e-05, + "loss": 3.9778, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.310849057530876e-05, + "loss": 3.9761, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.310010462779824e-05, + "loss": 3.9746, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.309173505909145e-05, + "loss": 3.9684, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.308334911158093e-05, + "loss": 3.9749, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.3074963164070414e-05, + "loss": 3.9838, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.3066577216559894e-05, + "loss": 3.9835, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.3058191269049374e-05, + "loss": 3.9842, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.3049805321538854e-05, + "loss": 3.9634, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.3041419374028334e-05, + "loss": 3.9799, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.303303342651781e-05, + "loss": 3.9783, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.302464747900729e-05, + "loss": 3.9712, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.30162779103005e-05, + "loss": 3.9721, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.300790834159371e-05, + "loss": 3.98, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.299952239408319e-05, + "loss": 3.9739, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.299113644657267e-05, + "loss": 3.978, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.298275049906215e-05, + "loss": 3.9701, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.297436455155163e-05, + "loss": 3.983, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.296599498284485e-05, + "loss": 3.9822, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.295760903533433e-05, + "loss": 3.9795, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.294922308782381e-05, + "loss": 3.9615, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.294083714031328e-05, + "loss": 3.9758, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.293245119280276e-05, + "loss": 3.9696, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.292406524529224e-05, + "loss": 3.9763, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.291567929778172e-05, + "loss": 3.9898, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.290730972907493e-05, + "loss": 3.9675, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.289892378156441e-05, + "loss": 3.9735, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.289053783405389e-05, + "loss": 3.967, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.288215188654337e-05, + "loss": 3.9735, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.287376593903285e-05, + "loss": 3.9616, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.28654127491298e-05, + "loss": 3.968, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.285702680161928e-05, + "loss": 3.9705, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.2848640854108754e-05, + "loss": 3.9728, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.2840254906598234e-05, + "loss": 3.9662, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.2831868959087714e-05, + "loss": 3.9667, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.2823483011577194e-05, + "loss": 3.9654, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.2815097064066674e-05, + "loss": 3.9834, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.2806711116556154e-05, + "loss": 3.9695, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.279834154784936e-05, + "loss": 3.9799, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.278995560033884e-05, + "loss": 3.9805, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.278156965282832e-05, + "loss": 3.9898, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.27731837053178e-05, + "loss": 3.9722, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.276479775780728e-05, + "loss": 3.9694, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.275641181029677e-05, + "loss": 3.9744, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.274802586278625e-05, + "loss": 3.976, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.273963991527573e-05, + "loss": 3.9743, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.273127034656894e-05, + "loss": 3.9778, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.272290077786215e-05, + "loss": 3.9694, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.271451483035163e-05, + "loss": 3.982, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.270614526164484e-05, + "loss": 3.974, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.269775931413432e-05, + "loss": 3.9679, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.26893733666238e-05, + "loss": 3.971, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.268098741911328e-05, + "loss": 3.9695, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.2672601471602757e-05, + "loss": 3.9808, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.2664215524092237e-05, + "loss": 3.9751, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.265582957658172e-05, + "loss": 3.9772, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.26474436290712e-05, + "loss": 3.9697, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.263905768156068e-05, + "loss": 3.9757, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.263067173405016e-05, + "loss": 3.9802, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.2622285786539636e-05, + "loss": 3.9743, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.2613899839029116e-05, + "loss": 3.9734, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.260553027032233e-05, + "loss": 3.9745, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.259714432281181e-05, + "loss": 3.9785, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.2588758375301285e-05, + "loss": 3.9911, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.25803888065945e-05, + "loss": 3.9684, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.257200285908398e-05, + "loss": 3.9671, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.256361691157346e-05, + "loss": 3.9711, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.255523096406294e-05, + "loss": 3.9722, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.254686139535616e-05, + "loss": 3.9654, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.253847544784564e-05, + "loss": 3.98, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.253008950033511e-05, + "loss": 3.9705, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.252170355282459e-05, + "loss": 3.9796, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.251331760531407e-05, + "loss": 3.9686, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 4.026948928833008, + "eval_runtime": 316.4767, + "eval_samples_per_second": 1205.747, + "eval_steps_per_second": 37.68, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.250493165780355e-05, + "loss": 3.9537, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.249654571029303e-05, + "loss": 3.9624, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.248815976278251e-05, + "loss": 3.9723, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.247977381527199e-05, + "loss": 3.9739, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.247138786776147e-05, + "loss": 3.9733, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.246300192025095e-05, + "loss": 3.9664, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.245461597274043e-05, + "loss": 3.97, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.244623002522991e-05, + "loss": 3.9663, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.243784407771939e-05, + "loss": 3.9674, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.2429458130208876e-05, + "loss": 3.9712, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.2421072182698356e-05, + "loss": 3.9706, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.241268623518783e-05, + "loss": 3.9816, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.2404316666481045e-05, + "loss": 3.9838, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.2395930718970525e-05, + "loss": 3.9599, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.238754477146e-05, + "loss": 3.9698, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.237915882394948e-05, + "loss": 3.9595, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.237077287643896e-05, + "loss": 3.9666, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.236238692892844e-05, + "loss": 3.9672, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.235400098141792e-05, + "loss": 3.9651, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.23456150339074e-05, + "loss": 3.9621, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.233722908639688e-05, + "loss": 3.9839, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.232884313888636e-05, + "loss": 3.9733, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.232045719137584e-05, + "loss": 3.9786, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.2312087622669054e-05, + "loss": 3.9777, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.2303701675158534e-05, + "loss": 3.9718, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.2295315727648014e-05, + "loss": 3.9713, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.2286929780137494e-05, + "loss": 3.9615, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.2278543832626974e-05, + "loss": 3.9691, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.2270157885116454e-05, + "loss": 3.966, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.2261771937605934e-05, + "loss": 3.9635, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.225340236889914e-05, + "loss": 3.9724, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.224501642138862e-05, + "loss": 3.963, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.22366304738781e-05, + "loss": 3.9751, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.222824452636758e-05, + "loss": 3.967, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.221985857885706e-05, + "loss": 3.9665, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.221148901015028e-05, + "loss": 3.9766, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.220310306263976e-05, + "loss": 3.975, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.219471711512924e-05, + "loss": 3.9506, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.218633116761871e-05, + "loss": 3.9688, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.217796159891193e-05, + "loss": 3.9639, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.216957565140141e-05, + "loss": 3.9526, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.216118970389089e-05, + "loss": 3.9687, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.215280375638036e-05, + "loss": 3.9779, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.214441780886984e-05, + "loss": 3.9648, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.213603186135932e-05, + "loss": 3.9724, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.2127662292652536e-05, + "loss": 3.9725, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.2119276345142016e-05, + "loss": 3.9695, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.2110890397631496e-05, + "loss": 3.966, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.2102504450120976e-05, + "loss": 3.9522, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.2094118502610456e-05, + "loss": 3.969, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.2085732555099936e-05, + "loss": 3.9672, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.2077346607589416e-05, + "loss": 3.969, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.2068960660078896e-05, + "loss": 3.9576, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.2060591091372105e-05, + "loss": 3.9577, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.2052205143861585e-05, + "loss": 3.9553, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.2043835575154794e-05, + "loss": 3.9586, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.2035449627644274e-05, + "loss": 3.9752, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.2027063680133754e-05, + "loss": 3.9495, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.2018677732623234e-05, + "loss": 3.9717, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.2010291785112714e-05, + "loss": 3.9652, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.20019058376022e-05, + "loss": 3.9517, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.199353626889541e-05, + "loss": 3.9651, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.198515032138489e-05, + "loss": 3.9582, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.197676437387437e-05, + "loss": 3.9605, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.196837842636385e-05, + "loss": 3.9534, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.195999247885333e-05, + "loss": 3.9769, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.195160653134281e-05, + "loss": 3.9628, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.194322058383229e-05, + "loss": 3.9523, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.19348510151255e-05, + "loss": 3.9457, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.192646506761498e-05, + "loss": 3.9584, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.191807912010446e-05, + "loss": 3.9705, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.190969317259394e-05, + "loss": 3.9774, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.190130722508342e-05, + "loss": 3.9586, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.18929212775729e-05, + "loss": 3.9749, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.188453533006238e-05, + "loss": 3.9742, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.187614938255186e-05, + "loss": 3.9636, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.1867779813845074e-05, + "loss": 3.9611, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.185941024513828e-05, + "loss": 3.9638, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.185102429762776e-05, + "loss": 3.9629, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.184263835011724e-05, + "loss": 3.9547, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.183425240260672e-05, + "loss": 3.9622, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.1825866455096196e-05, + "loss": 3.9701, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.1817480507585676e-05, + "loss": 3.9738, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.1809094560075156e-05, + "loss": 3.967, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.180072499136837e-05, + "loss": 3.9506, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.179233904385785e-05, + "loss": 3.9673, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.178395309634733e-05, + "loss": 3.9648, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.177558352764055e-05, + "loss": 3.9619, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.176719758013002e-05, + "loss": 3.9593, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.17588116326195e-05, + "loss": 3.9649, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.175042568510898e-05, + "loss": 3.9651, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.174203973759846e-05, + "loss": 3.9587, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.173365379008794e-05, + "loss": 3.9601, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.172526784257742e-05, + "loss": 3.9658, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.17168818950669e-05, + "loss": 3.9665, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.170849594755638e-05, + "loss": 3.972, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.170012637884959e-05, + "loss": 3.9495, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.169174043133907e-05, + "loss": 3.9621, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.1683354483828557e-05, + "loss": 3.9619, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.1674968536318036e-05, + "loss": 3.9575, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.1666598967611246e-05, + "loss": 3.9781, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.1658213020100726e-05, + "loss": 3.9572, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.1649827072590205e-05, + "loss": 3.9545, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.1641457503883415e-05, + "loss": 3.958, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.1633071556372895e-05, + "loss": 3.9602, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.1624685608862375e-05, + "loss": 3.947, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.1616299661351854e-05, + "loss": 3.9561, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.1607913713841334e-05, + "loss": 3.9595, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.1599527766330814e-05, + "loss": 3.9569, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.1591141818820294e-05, + "loss": 3.9532, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.1582755871309774e-05, + "loss": 3.96, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.157438630260299e-05, + "loss": 3.9489, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.156600035509247e-05, + "loss": 3.9702, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.155761440758195e-05, + "loss": 3.9578, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.154922846007143e-05, + "loss": 3.9637, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.154085889136464e-05, + "loss": 3.9685, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.153247294385412e-05, + "loss": 3.9802, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.152410337514733e-05, + "loss": 3.9611, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.151571742763681e-05, + "loss": 3.954, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.150733148012629e-05, + "loss": 3.9655, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.149894553261577e-05, + "loss": 3.9596, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.149055958510525e-05, + "loss": 3.9616, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.148217363759473e-05, + "loss": 3.9668, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.147378769008421e-05, + "loss": 3.9605, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.146540174257369e-05, + "loss": 3.9681, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.145701579506317e-05, + "loss": 3.9594, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.1448646226356384e-05, + "loss": 3.9544, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.144026027884586e-05, + "loss": 3.9583, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.143189071013907e-05, + "loss": 3.965, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.142350476262855e-05, + "loss": 3.9619, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.141511881511803e-05, + "loss": 3.9634, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.1406732867607506e-05, + "loss": 3.9634, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.1398346920096986e-05, + "loss": 3.9557, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.1389960972586466e-05, + "loss": 3.9622, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.1381575025075946e-05, + "loss": 3.9655, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.137318907756543e-05, + "loss": 3.9661, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.136480313005491e-05, + "loss": 3.9593, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.135641718254439e-05, + "loss": 3.9628, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.134803123503387e-05, + "loss": 3.969, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.133964528752335e-05, + "loss": 3.9717, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.133127571881656e-05, + "loss": 3.9585, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.132290615010977e-05, + "loss": 3.9589, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.131452020259925e-05, + "loss": 3.9546, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.130613425508873e-05, + "loss": 3.961, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.129774830757821e-05, + "loss": 3.9526, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.128936236006769e-05, + "loss": 3.9691, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.12809927913609e-05, + "loss": 3.9582, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.1272606843850386e-05, + "loss": 3.9634, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.1264220896339866e-05, + "loss": 3.9569, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 4.020151138305664, + "eval_runtime": 293.1354, + "eval_samples_per_second": 1301.757, + "eval_steps_per_second": 40.681, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.1255834948829346e-05, + "loss": 3.9599, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.1247465380122555e-05, + "loss": 3.9527, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.1239079432612035e-05, + "loss": 3.9594, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.1230693485101515e-05, + "loss": 3.96, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.1222307537590995e-05, + "loss": 3.9598, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.1213921590080475e-05, + "loss": 3.9607, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.1205535642569955e-05, + "loss": 3.9556, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.1197149695059435e-05, + "loss": 3.9545, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.1188763747548915e-05, + "loss": 3.9585, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.1180377800038395e-05, + "loss": 3.9577, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.1172008231331604e-05, + "loss": 3.9577, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.1163622283821084e-05, + "loss": 3.9701, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.11552527151143e-05, + "loss": 3.971, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.114686676760378e-05, + "loss": 3.9479, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.113848082009326e-05, + "loss": 3.9568, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.113009487258274e-05, + "loss": 3.9483, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.112170892507222e-05, + "loss": 3.9585, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.111332297756169e-05, + "loss": 3.9486, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.110493703005117e-05, + "loss": 3.9534, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.109655108254065e-05, + "loss": 3.9547, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.108816513503013e-05, + "loss": 3.9681, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.107977918751961e-05, + "loss": 3.9622, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.107139324000909e-05, + "loss": 3.9629, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.106300729249857e-05, + "loss": 3.9668, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.105462134498805e-05, + "loss": 3.9621, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.104625177628127e-05, + "loss": 3.9577, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.103786582877075e-05, + "loss": 3.9492, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.102949626006396e-05, + "loss": 3.9572, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.102111031255344e-05, + "loss": 3.951, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.101272436504292e-05, + "loss": 3.9509, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.10043384175324e-05, + "loss": 3.9607, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.099595247002188e-05, + "loss": 3.9531, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.0987582901315086e-05, + "loss": 3.961, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.0979196953804566e-05, + "loss": 3.9546, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.0970811006294046e-05, + "loss": 3.9574, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.0962441437587255e-05, + "loss": 3.9659, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.095405549007674e-05, + "loss": 3.961, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.094566954256622e-05, + "loss": 3.9357, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.09372835950557e-05, + "loss": 3.963, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.092889764754518e-05, + "loss": 3.9474, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.092051170003466e-05, + "loss": 3.9396, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.091212575252414e-05, + "loss": 3.9597, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.090373980501362e-05, + "loss": 3.9661, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.08953538575031e-05, + "loss": 3.952, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.088696790999258e-05, + "loss": 3.9574, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.0878581962482055e-05, + "loss": 3.9643, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.0870196014971535e-05, + "loss": 3.9592, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.086182644626475e-05, + "loss": 3.9572, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.0853440498754224e-05, + "loss": 3.9375, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.084505455124371e-05, + "loss": 3.9555, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.083666860373319e-05, + "loss": 3.9592, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.0828299035026406e-05, + "loss": 3.9533, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.0819929466319615e-05, + "loss": 3.9454, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.0811543518809095e-05, + "loss": 3.9433, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.0803157571298575e-05, + "loss": 3.9488, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.0794771623788055e-05, + "loss": 3.9429, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.078638567627753e-05, + "loss": 3.9645, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.077799972876701e-05, + "loss": 3.9394, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.076961378125649e-05, + "loss": 3.959, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.076122783374597e-05, + "loss": 3.9553, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.075284188623545e-05, + "loss": 3.9397, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.074445593872493e-05, + "loss": 3.9526, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.0736086370018144e-05, + "loss": 3.9482, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.0727700422507624e-05, + "loss": 3.9436, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.0719314474997104e-05, + "loss": 3.94, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.0710928527486584e-05, + "loss": 3.9677, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.070255895877979e-05, + "loss": 3.9476, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.069417301126927e-05, + "loss": 3.9418, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.068578706375875e-05, + "loss": 3.9307, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.067740111624823e-05, + "loss": 3.946, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.066903154754144e-05, + "loss": 3.9605, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.066066197883465e-05, + "loss": 3.9637, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.065227603132413e-05, + "loss": 3.9473, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.064389008381362e-05, + "loss": 3.9623, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.06355041363031e-05, + "loss": 3.9627, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.062711818879258e-05, + "loss": 3.9514, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.061876499888952e-05, + "loss": 3.9482, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.0610379051379e-05, + "loss": 3.9542, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.0601993103868476e-05, + "loss": 3.9518, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.0593607156357956e-05, + "loss": 3.9465, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.0585221208847436e-05, + "loss": 3.9488, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.0576835261336916e-05, + "loss": 3.9597, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.0568449313826396e-05, + "loss": 3.9585, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.0560063366315876e-05, + "loss": 3.9573, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.0551677418805356e-05, + "loss": 3.9401, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.0543291471294836e-05, + "loss": 3.9542, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.0534905523784316e-05, + "loss": 3.9555, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.052653595507753e-05, + "loss": 3.9517, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.051815000756701e-05, + "loss": 3.9469, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.0509764060056488e-05, + "loss": 3.9511, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.050137811254597e-05, + "loss": 3.9572, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.049299216503545e-05, + "loss": 3.9442, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.048460621752493e-05, + "loss": 3.949, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.047622027001441e-05, + "loss": 3.9534, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.046783432250389e-05, + "loss": 3.9519, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.04594647537971e-05, + "loss": 3.9595, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.045107880628658e-05, + "loss": 3.9434, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.044269285877606e-05, + "loss": 3.9466, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.0434306911265537e-05, + "loss": 3.9479, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.0425937342558753e-05, + "loss": 3.9512, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.0417551395048233e-05, + "loss": 3.9616, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.0409165447537712e-05, + "loss": 3.9504, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.040077950002719e-05, + "loss": 3.9427, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.039239355251667e-05, + "loss": 3.9438, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.038400760500615e-05, + "loss": 3.9561, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.0375638036299358e-05, + "loss": 3.9261, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.0367252088788838e-05, + "loss": 3.9459, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.0358866141278318e-05, + "loss": 3.95, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.0350480193767798e-05, + "loss": 3.9426, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.034209424625728e-05, + "loss": 3.9398, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.033370829874676e-05, + "loss": 3.9496, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.032532235123624e-05, + "loss": 3.9363, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.031693640372572e-05, + "loss": 3.9601, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.030856683501893e-05, + "loss": 3.9454, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.030018088750841e-05, + "loss": 3.9527, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.029179493999789e-05, + "loss": 3.9565, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.0283425371291103e-05, + "loss": 3.9667, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.0275039423780583e-05, + "loss": 3.9511, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.0266653476270063e-05, + "loss": 3.9398, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.0258267528759542e-05, + "loss": 3.9521, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.024989796005275e-05, + "loss": 3.947, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.0241512012542235e-05, + "loss": 3.9503, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.0233126065031715e-05, + "loss": 3.9533, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.0224740117521195e-05, + "loss": 3.9487, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.0216354170010675e-05, + "loss": 3.9591, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.0207968222500155e-05, + "loss": 3.9488, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.0199582274989635e-05, + "loss": 3.9435, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.0191196327479115e-05, + "loss": 3.9467, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.0182826758772327e-05, + "loss": 3.9489, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.0174440811261807e-05, + "loss": 3.9469, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.0166054863751287e-05, + "loss": 3.9549, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.0157668916240767e-05, + "loss": 3.9556, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.0149282968730247e-05, + "loss": 3.9485, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.014089702121972e-05, + "loss": 3.9416, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.0132511073709203e-05, + "loss": 3.9537, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.0124125126198683e-05, + "loss": 3.9537, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.01157555574919e-05, + "loss": 3.9496, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.0107369609981372e-05, + "loss": 3.9505, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.0098983662470852e-05, + "loss": 3.9582, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.0090597714960332e-05, + "loss": 3.9569, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.0082211767449812e-05, + "loss": 3.9478, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.0073842198743025e-05, + "loss": 3.9448, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.0065456251232505e-05, + "loss": 3.9468, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.005708668252572e-05, + "loss": 3.9504, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.0048700735015194e-05, + "loss": 3.9378, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.0040314787504674e-05, + "loss": 3.9555, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.0031928839994157e-05, + "loss": 3.9515, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.0023542892483637e-05, + "loss": 3.9478, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.0015156944973117e-05, + "loss": 3.9448, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.0006787376266326e-05, + "loss": 3.9536, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 4.014498233795166, + "eval_runtime": 292.6716, + "eval_samples_per_second": 1303.82, + "eval_steps_per_second": 40.745, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.9998401428755806e-05, + "loss": 3.9383, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.9990015481245286e-05, + "loss": 3.9453, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.9981629533734766e-05, + "loss": 3.952, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.997324358622425e-05, + "loss": 3.9498, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.996485763871373e-05, + "loss": 3.9519, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.995647169120321e-05, + "loss": 3.9426, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.994808574369269e-05, + "loss": 3.9442, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.993969979618217e-05, + "loss": 3.9404, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.993131384867165e-05, + "loss": 3.9532, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.992292790116113e-05, + "loss": 3.9389, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.991454195365061e-05, + "loss": 3.9626, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.990617238494382e-05, + "loss": 3.9614, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.98977864374333e-05, + "loss": 3.9367, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.988940048992278e-05, + "loss": 3.9433, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.988101454241226e-05, + "loss": 3.9357, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.9872628594901735e-05, + "loss": 3.9462, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.9864242647391218e-05, + "loss": 3.9431, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.9855856699880698e-05, + "loss": 3.942, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.9847470752370178e-05, + "loss": 3.9424, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.9839084804859658e-05, + "loss": 3.9544, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.9830698857349138e-05, + "loss": 3.9489, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.9822312909838618e-05, + "loss": 3.9521, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.9813926962328098e-05, + "loss": 3.9556, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.9805557393621307e-05, + "loss": 3.9546, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.979718782491452e-05, + "loss": 3.9454, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.9788801877404e-05, + "loss": 3.9364, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.978041592989348e-05, + "loss": 3.9455, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.977202998238296e-05, + "loss": 3.9387, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.976364403487244e-05, + "loss": 3.9405, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.975525808736192e-05, + "loss": 3.943, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.97468721398514e-05, + "loss": 3.9463, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.973850257114461e-05, + "loss": 3.9512, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.973011662363409e-05, + "loss": 3.9406, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.972173067612357e-05, + "loss": 3.9477, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.971336110741678e-05, + "loss": 3.9559, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.970497515990626e-05, + "loss": 3.9494, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.9696589212395744e-05, + "loss": 3.9283, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.9688203264885224e-05, + "loss": 3.9509, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.9679817317374704e-05, + "loss": 3.9324, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.9671431369864184e-05, + "loss": 3.9355, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.9663045422353664e-05, + "loss": 3.9455, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.9654659474843144e-05, + "loss": 3.952, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.9646273527332624e-05, + "loss": 3.9427, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.96378875798221e-05, + "loss": 3.9483, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.962950163231158e-05, + "loss": 3.9513, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.962111568480106e-05, + "loss": 3.9478, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.961272973729054e-05, + "loss": 3.9461, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.9604376547387485e-05, + "loss": 3.9278, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.9595990599876965e-05, + "loss": 3.9412, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.9587604652366445e-05, + "loss": 3.9513, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.9579235083659657e-05, + "loss": 3.9431, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.9570849136149137e-05, + "loss": 3.935, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.9562463188638617e-05, + "loss": 3.9307, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.9554077241128097e-05, + "loss": 3.9409, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.9545691293617574e-05, + "loss": 3.9276, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.9537305346107054e-05, + "loss": 3.9493, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.9528919398596534e-05, + "loss": 3.9319, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.9520533451086014e-05, + "loss": 3.9484, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.9512147503575494e-05, + "loss": 3.9437, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.9503761556064974e-05, + "loss": 3.927, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.9495391987358183e-05, + "loss": 3.9437, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.9487006039847666e-05, + "loss": 3.9369, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.9478620092337146e-05, + "loss": 3.9316, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.9470234144826626e-05, + "loss": 3.9308, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.9461848197316106e-05, + "loss": 3.9534, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.9453478628609315e-05, + "loss": 3.9391, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.9445092681098795e-05, + "loss": 3.931, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.9436706733588275e-05, + "loss": 3.9224, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.9428320786077758e-05, + "loss": 3.9331, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.9419934838567238e-05, + "loss": 3.9477, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.9411548891056718e-05, + "loss": 3.9547, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.9403179322349927e-05, + "loss": 3.9372, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.9394793374839407e-05, + "loss": 3.9521, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.9386407427328887e-05, + "loss": 3.9523, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.9378021479818367e-05, + "loss": 3.9424, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.9369635532307847e-05, + "loss": 3.9342, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.936124958479733e-05, + "loss": 3.9444, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.935286363728681e-05, + "loss": 3.9404, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.9344477689776284e-05, + "loss": 3.9352, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.93361081210695e-05, + "loss": 3.9391, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.932773855236271e-05, + "loss": 3.9428, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.9319352604852192e-05, + "loss": 3.9502, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.9310966657341672e-05, + "loss": 3.9452, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.9302580709831152e-05, + "loss": 3.9335, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.9294194762320632e-05, + "loss": 3.9407, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.9285808814810105e-05, + "loss": 3.9452, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.9277422867299585e-05, + "loss": 3.9401, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.9269036919789068e-05, + "loss": 3.9383, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.9260667351082284e-05, + "loss": 3.9378, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.9252281403571757e-05, + "loss": 3.9467, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.9243895456061237e-05, + "loss": 3.9364, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.9235509508550717e-05, + "loss": 3.9387, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.9227123561040197e-05, + "loss": 3.9384, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.921875399233341e-05, + "loss": 3.9465, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.921036804482289e-05, + "loss": 3.9433, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.920198209731237e-05, + "loss": 3.9418, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.919359614980185e-05, + "loss": 3.9309, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.918522658109506e-05, + "loss": 3.9402, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.917684063358454e-05, + "loss": 3.9414, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.9168454686074022e-05, + "loss": 3.9502, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.9160068738563502e-05, + "loss": 3.9403, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.9151682791052982e-05, + "loss": 3.9334, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.9143296843542462e-05, + "loss": 3.9332, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.913491089603194e-05, + "loss": 3.9446, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.912654132732515e-05, + "loss": 3.9185, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.9118171758618363e-05, + "loss": 3.931, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9109785811107843e-05, + "loss": 3.9375, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9101399863597323e-05, + "loss": 3.9378, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.9093013916086803e-05, + "loss": 3.9269, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.9084627968576283e-05, + "loss": 3.9403, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.9076242021065763e-05, + "loss": 3.9256, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.9067856073555243e-05, + "loss": 3.952, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.9059470126044723e-05, + "loss": 3.9322, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.9051084178534206e-05, + "loss": 3.9413, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.9042698231023686e-05, + "loss": 3.9448, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.9034328662316895e-05, + "loss": 3.9602, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.9025959093610104e-05, + "loss": 3.9363, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.9017573146099584e-05, + "loss": 3.9344, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.9009187198589068e-05, + "loss": 3.942, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.9000801251078548e-05, + "loss": 3.9321, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.8992415303568028e-05, + "loss": 3.9429, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.8984029356057508e-05, + "loss": 3.9432, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.8975643408546988e-05, + "loss": 3.9343, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.8967257461036468e-05, + "loss": 3.9525, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.8958871513525944e-05, + "loss": 3.9363, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.895050194481916e-05, + "loss": 3.9351, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.894211599730864e-05, + "loss": 3.9332, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.893373004979812e-05, + "loss": 3.9401, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.8925344102287593e-05, + "loss": 3.9335, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.891697453358081e-05, + "loss": 3.9494, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.890858858607029e-05, + "loss": 3.9477, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.8900202638559765e-05, + "loss": 3.935, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.8891816691049245e-05, + "loss": 3.9315, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.8883430743538725e-05, + "loss": 3.943, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.8875044796028205e-05, + "loss": 3.9424, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.8866658848517685e-05, + "loss": 3.9452, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.8858272901007165e-05, + "loss": 3.9401, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.8849903332300378e-05, + "loss": 3.9493, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.8841517384789858e-05, + "loss": 3.9428, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.8833131437279338e-05, + "loss": 3.9393, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.8824761868572547e-05, + "loss": 3.9366, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.8816375921062027e-05, + "loss": 3.9354, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.8807989973551507e-05, + "loss": 3.9415, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.879962040484472e-05, + "loss": 3.926, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.87912344573342e-05, + "loss": 3.9456, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.878284850982368e-05, + "loss": 3.9427, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.877446256231316e-05, + "loss": 3.9377, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.8766092993606368e-05, + "loss": 3.9334, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.875770704609585e-05, + "loss": 3.9419, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 4.009147644042969, + "eval_runtime": 296.8693, + "eval_samples_per_second": 1285.384, + "eval_steps_per_second": 40.169, + "step": 1297440 + }, + { + "epoch": 1.0, + "learning_rate": 2.874932109858533e-05, + "loss": 3.9268, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.874093515107481e-05, + "loss": 3.9342, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.873254920356429e-05, + "loss": 3.9437, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.872416325605377e-05, + "loss": 3.9338, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.871577730854325e-05, + "loss": 3.9399, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.870739136103273e-05, + "loss": 3.9355, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.869900541352221e-05, + "loss": 3.9332, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.869061946601169e-05, + "loss": 3.931, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.8682249897304904e-05, + "loss": 3.9398, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.8673863949794384e-05, + "loss": 3.9296, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.8665478002283863e-05, + "loss": 3.9519, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.8657092054773343e-05, + "loss": 3.9473, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.8648722486066553e-05, + "loss": 3.9326, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.8640336538556032e-05, + "loss": 3.9312, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.8631950591045516e-05, + "loss": 3.9312, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.8623564643534996e-05, + "loss": 3.9322, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.8615178696024476e-05, + "loss": 3.9313, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.860679274851395e-05, + "loss": 3.9321, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.859840680100343e-05, + "loss": 3.9286, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.859002085349291e-05, + "loss": 3.9478, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.8581634905982392e-05, + "loss": 3.9381, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.8573248958471872e-05, + "loss": 3.9428, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.8564863010961352e-05, + "loss": 3.9432, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.855649344225456e-05, + "loss": 3.9512, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.854810749474404e-05, + "loss": 3.9284, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.8539737926037254e-05, + "loss": 3.934, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.8531351978526734e-05, + "loss": 3.9307, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.8522966031016214e-05, + "loss": 3.9327, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.8514580083505693e-05, + "loss": 3.9304, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.8506194135995173e-05, + "loss": 3.9324, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.8497808188484653e-05, + "loss": 3.9388, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.8489422240974133e-05, + "loss": 3.9387, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.8481052672267346e-05, + "loss": 3.9284, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.8472666724756826e-05, + "loss": 3.9407, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.8464297156050035e-05, + "loss": 3.946, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.8455911208539515e-05, + "loss": 3.9354, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.8447525261028995e-05, + "loss": 3.9198, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.8439139313518475e-05, + "loss": 3.9389, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.8430753366007955e-05, + "loss": 3.9206, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.8422367418497438e-05, + "loss": 3.9301, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.8413981470986918e-05, + "loss": 3.9322, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.8405595523476398e-05, + "loss": 3.9442, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.8397209575965878e-05, + "loss": 3.9293, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.8388823628455358e-05, + "loss": 3.935, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.8380437680944838e-05, + "loss": 3.943, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.8372051733434314e-05, + "loss": 3.9352, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.836368216472753e-05, + "loss": 3.9379, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.835529621721701e-05, + "loss": 3.9174, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.834691026970649e-05, + "loss": 3.9317, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.8338524322195963e-05, + "loss": 3.9388, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.8330138374685443e-05, + "loss": 3.9311, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.832176880597866e-05, + "loss": 3.9284, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.831338285846814e-05, + "loss": 3.9163, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.8304996910957616e-05, + "loss": 3.9322, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.8296610963447096e-05, + "loss": 3.9191, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.828824139474031e-05, + "loss": 3.9374, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.8279855447229785e-05, + "loss": 3.9239, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.8271469499719268e-05, + "loss": 3.9371, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.8263083552208748e-05, + "loss": 3.9375, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.8254697604698228e-05, + "loss": 3.9156, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.8246328035991437e-05, + "loss": 3.929, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.8237942088480917e-05, + "loss": 3.9323, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.8229556140970397e-05, + "loss": 3.9206, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.8221170193459877e-05, + "loss": 3.9224, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.8212784245949357e-05, + "loss": 3.9404, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.820439829843884e-05, + "loss": 3.9319, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.819601235092832e-05, + "loss": 3.9207, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.81876264034178e-05, + "loss": 3.9112, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.817925683471101e-05, + "loss": 3.9247, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.817088726600422e-05, + "loss": 3.9357, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.81625013184937e-05, + "loss": 3.9415, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.815411537098318e-05, + "loss": 3.9286, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.814572942347266e-05, + "loss": 3.9418, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.813734347596214e-05, + "loss": 3.9393, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.812895752845162e-05, + "loss": 3.9344, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.812058795974483e-05, + "loss": 3.9223, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.811220201223431e-05, + "loss": 3.9371, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.8103816064723794e-05, + "loss": 3.9305, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.8095430117213274e-05, + "loss": 3.9257, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.8087060548506483e-05, + "loss": 3.9298, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.8078674600995963e-05, + "loss": 3.9277, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.8070288653485443e-05, + "loss": 3.9448, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.8061902705974923e-05, + "loss": 3.9315, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.8053516758464403e-05, + "loss": 3.9259, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.8045147189757615e-05, + "loss": 3.9308, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.8036761242247095e-05, + "loss": 3.9347, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.8028375294736575e-05, + "loss": 3.9308, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.8019989347226055e-05, + "loss": 3.9299, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.8011619778519264e-05, + "loss": 3.925, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.8003233831008748e-05, + "loss": 3.938, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.7994847883498228e-05, + "loss": 3.9243, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.7986461935987707e-05, + "loss": 3.9279, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.7978075988477187e-05, + "loss": 3.9245, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.7969690040966667e-05, + "loss": 3.937, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.7961304093456147e-05, + "loss": 3.935, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.7952918145945624e-05, + "loss": 3.9311, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.794454857723884e-05, + "loss": 3.9197, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.793616262972832e-05, + "loss": 3.9303, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.79277766822178e-05, + "loss": 3.9313, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.7919390734707273e-05, + "loss": 3.9385, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.791102116600049e-05, + "loss": 3.9315, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.79026515972937e-05, + "loss": 3.9258, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.789426564978318e-05, + "loss": 3.9208, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.788587970227266e-05, + "loss": 3.9343, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.787749375476214e-05, + "loss": 3.9068, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.786912418605535e-05, + "loss": 3.9228, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.786073823854483e-05, + "loss": 3.9292, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.785235229103431e-05, + "loss": 3.9272, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.7843966343523793e-05, + "loss": 3.916, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.7835580396013273e-05, + "loss": 3.9283, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.7827194448502747e-05, + "loss": 3.9192, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.7818808500992227e-05, + "loss": 3.9391, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.7810422553481706e-05, + "loss": 3.9229, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.780205298477492e-05, + "loss": 3.9276, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.7793683416068135e-05, + "loss": 3.9403, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.7785297468557615e-05, + "loss": 3.9471, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.7776911521047095e-05, + "loss": 3.9251, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.7768525573536568e-05, + "loss": 3.9236, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.7760156004829784e-05, + "loss": 3.9348, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.7751770057319264e-05, + "loss": 3.923, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.7743384109808747e-05, + "loss": 3.9291, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.773499816229822e-05, + "loss": 3.9354, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.77266122147877e-05, + "loss": 3.9237, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.7718242646080916e-05, + "loss": 3.9416, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.7709856698570393e-05, + "loss": 3.9256, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.7701470751059873e-05, + "loss": 3.9262, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.7693084803549353e-05, + "loss": 3.9206, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.768471523484257e-05, + "loss": 3.9309, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.767632928733204e-05, + "loss": 3.9251, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.766794333982152e-05, + "loss": 3.9395, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.7659557392311e-05, + "loss": 3.9385, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.7651171444800485e-05, + "loss": 3.9288, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.7642801876093694e-05, + "loss": 3.9153, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.7634415928583174e-05, + "loss": 3.9379, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.7626029981072654e-05, + "loss": 3.9282, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.7617644033562134e-05, + "loss": 3.9373, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.7609258086051614e-05, + "loss": 3.9312, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.7600872138541094e-05, + "loss": 3.935, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.7592502569834306e-05, + "loss": 3.9309, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.7584116622323786e-05, + "loss": 3.9358, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.7575730674813266e-05, + "loss": 3.9243, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.7567344727302746e-05, + "loss": 3.9242, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.7558958779792226e-05, + "loss": 3.9327, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.7550572832281706e-05, + "loss": 3.9187, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.7542186884771186e-05, + "loss": 3.9321, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.7533800937260666e-05, + "loss": 3.9412, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.752543136855388e-05, + "loss": 3.9262, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.751704542104336e-05, + "loss": 3.9233, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.7508675852336567e-05, + "loss": 3.9296, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 4.004470348358154, + "eval_runtime": 296.7086, + "eval_samples_per_second": 1286.08, + "eval_steps_per_second": 40.191, + "step": 1373760 + }, + { + "epoch": 0.0, + "learning_rate": 2.7500289904826047e-05, + "loss": 3.917, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.7491903957315527e-05, + "loss": 3.9249, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.748351800980501e-05, + "loss": 3.9344, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.747513206229449e-05, + "loss": 3.9263, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.746674611478397e-05, + "loss": 3.9317, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.745836016727345e-05, + "loss": 3.9195, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.744997421976293e-05, + "loss": 3.9294, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.7441588272252404e-05, + "loss": 3.9154, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.7433202324741887e-05, + "loss": 3.9285, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.7424816377231367e-05, + "loss": 3.9232, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.7416430429720847e-05, + "loss": 3.936, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.7408044482210327e-05, + "loss": 3.9383, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.7399674913503536e-05, + "loss": 3.9201, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.7391288965993016e-05, + "loss": 3.923, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.7382903018482496e-05, + "loss": 3.9247, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.737451707097198e-05, + "loss": 3.9207, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.736613112346146e-05, + "loss": 3.9191, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.735774517595094e-05, + "loss": 3.9228, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.734935922844042e-05, + "loss": 3.9184, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.73409732809299e-05, + "loss": 3.9428, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.7332603712223108e-05, + "loss": 3.924, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.7324217764712588e-05, + "loss": 3.9369, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.731583181720207e-05, + "loss": 3.933, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.730744586969155e-05, + "loss": 3.9412, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.729905992218103e-05, + "loss": 3.915, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.729067397467051e-05, + "loss": 3.9268, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.728228802715999e-05, + "loss": 3.9188, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.7273902079649465e-05, + "loss": 3.9267, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.7265548889746413e-05, + "loss": 3.9197, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.7257162942235893e-05, + "loss": 3.9227, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.7248793373529102e-05, + "loss": 3.9316, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.7240407426018582e-05, + "loss": 3.9289, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.7232021478508062e-05, + "loss": 3.9161, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.7223635530997542e-05, + "loss": 3.9326, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.7215265962290754e-05, + "loss": 3.9288, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.7206880014780234e-05, + "loss": 3.9254, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.7198494067269714e-05, + "loss": 3.9139, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.7190108119759194e-05, + "loss": 3.9294, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.7181722172248674e-05, + "loss": 3.9108, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.7173336224738154e-05, + "loss": 3.9231, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.7164950277227634e-05, + "loss": 3.92, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.7156580708520847e-05, + "loss": 3.9321, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.7148194761010327e-05, + "loss": 3.9236, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.7139808813499806e-05, + "loss": 3.9258, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.7131422865989286e-05, + "loss": 3.9327, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.7123036918478766e-05, + "loss": 3.927, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.7114650970968243e-05, + "loss": 3.9308, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.7106265023457723e-05, + "loss": 3.909, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.7097879075947203e-05, + "loss": 3.918, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.7089509507240412e-05, + "loss": 3.9313, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.7081123559729892e-05, + "loss": 3.923, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.7072737612219372e-05, + "loss": 3.9193, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.7064351664708855e-05, + "loss": 3.9092, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.7055965717198335e-05, + "loss": 3.9222, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.7047596148491544e-05, + "loss": 3.907, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.7039210200981024e-05, + "loss": 3.9257, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.703084063227424e-05, + "loss": 3.9152, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.7022454684763717e-05, + "loss": 3.9292, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.7014068737253197e-05, + "loss": 3.9233, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.7005682789742677e-05, + "loss": 3.9097, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.6997296842232157e-05, + "loss": 3.9169, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.6988910894721636e-05, + "loss": 3.9225, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.6980524947211116e-05, + "loss": 3.9093, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.6972138999700596e-05, + "loss": 3.9198, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.6963753052190076e-05, + "loss": 3.9257, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.695538348348329e-05, + "loss": 3.9248, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.694699753597277e-05, + "loss": 3.9139, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.693861158846225e-05, + "loss": 3.9032, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.693022564095173e-05, + "loss": 3.9129, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.692183969344121e-05, + "loss": 3.9265, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.6913470124734418e-05, + "loss": 3.9326, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.6905084177223898e-05, + "loss": 3.9209, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.689669822971338e-05, + "loss": 3.931, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.688831228220286e-05, + "loss": 3.9309, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.687992633469234e-05, + "loss": 3.9279, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.687155676598555e-05, + "loss": 3.9059, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.686317081847503e-05, + "loss": 3.9282, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.685478487096451e-05, + "loss": 3.9243, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.684639892345399e-05, + "loss": 3.9137, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.6838012975943473e-05, + "loss": 3.9258, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.6829627028432953e-05, + "loss": 3.919, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.6821241080922426e-05, + "loss": 3.9324, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.6812871512215642e-05, + "loss": 3.9228, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.6804485564705122e-05, + "loss": 3.9147, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.67960996171946e-05, + "loss": 3.9241, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.6787730048487815e-05, + "loss": 3.9232, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.6779344100977295e-05, + "loss": 3.9237, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.6770958153466775e-05, + "loss": 3.92, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.6762572205956248e-05, + "loss": 3.9163, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.6754186258445728e-05, + "loss": 3.9259, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.674580031093521e-05, + "loss": 3.9161, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.673741436342469e-05, + "loss": 3.9214, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.672902841591417e-05, + "loss": 3.9141, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.672064246840365e-05, + "loss": 3.9299, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.671225652089313e-05, + "loss": 3.9266, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.670387057338261e-05, + "loss": 3.9209, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.669548462587209e-05, + "loss": 3.9142, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.6687131435969032e-05, + "loss": 3.9248, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.6678745488458512e-05, + "loss": 3.916, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.6670359540947992e-05, + "loss": 3.9343, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.6661973593437472e-05, + "loss": 3.9223, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.6653587645926952e-05, + "loss": 3.918, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.6645201698416432e-05, + "loss": 3.9113, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.6636815750905912e-05, + "loss": 3.9213, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.6628429803395395e-05, + "loss": 3.9015, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.6620060234688605e-05, + "loss": 3.9142, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.6611674287178085e-05, + "loss": 3.9178, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.6603288339667565e-05, + "loss": 3.9186, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.6594902392157044e-05, + "loss": 3.9061, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.6586532823450257e-05, + "loss": 3.9235, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.6578146875939737e-05, + "loss": 3.9086, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.6569760928429217e-05, + "loss": 3.9315, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.6561374980918697e-05, + "loss": 3.9168, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.6553005412211906e-05, + "loss": 3.917, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.6544619464701386e-05, + "loss": 3.9327, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.65362498959946e-05, + "loss": 3.9408, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.6527863948484078e-05, + "loss": 3.9188, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.6519478000973558e-05, + "loss": 3.9138, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.6511092053463038e-05, + "loss": 3.9237, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.6502722484756247e-05, + "loss": 3.9163, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.6494336537245727e-05, + "loss": 3.9171, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.648595058973521e-05, + "loss": 3.9312, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.647756464222469e-05, + "loss": 3.914, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.646917869471417e-05, + "loss": 3.9314, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.646080912600738e-05, + "loss": 3.9196, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.645242317849686e-05, + "loss": 3.9195, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.644403723098634e-05, + "loss": 3.9101, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.643565128347582e-05, + "loss": 3.9242, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.64272653359653e-05, + "loss": 3.9125, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.6418879388454783e-05, + "loss": 3.932, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.6410493440944263e-05, + "loss": 3.9251, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.6402107493433736e-05, + "loss": 3.9224, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.6393737924726952e-05, + "loss": 3.9056, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.638536835602016e-05, + "loss": 3.9296, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.6376982408509644e-05, + "loss": 3.9249, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.6368596460999124e-05, + "loss": 3.9215, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.6360210513488604e-05, + "loss": 3.9208, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.6351824565978084e-05, + "loss": 3.9296, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.6343438618467557e-05, + "loss": 3.9259, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.6335069049760773e-05, + "loss": 3.9302, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.6326683102250253e-05, + "loss": 3.9114, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.6318297154739736e-05, + "loss": 3.9165, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.630991120722921e-05, + "loss": 3.9226, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.630152525971869e-05, + "loss": 3.908, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.629313931220817e-05, + "loss": 3.9225, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.628475336469765e-05, + "loss": 3.9307, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.627636741718713e-05, + "loss": 3.9184, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.6267997848480342e-05, + "loss": 3.9133, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.6259628279773558e-05, + "loss": 3.9249, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 4.0006632804870605, + "eval_runtime": 291.6235, + "eval_samples_per_second": 1308.506, + "eval_steps_per_second": 40.892, + "step": 1450080 + }, + { + "epoch": 1.0, + "learning_rate": 2.625124233226303e-05, + "loss": 3.9156, + "step": 1450496 + }, + { + "epoch": 1.0, + "learning_rate": 2.624285638475251e-05, + "loss": 3.9159, + "step": 1451008 + }, + { + "epoch": 1.0, + "learning_rate": 2.623447043724199e-05, + "loss": 3.9269, + "step": 1451520 + }, + { + "epoch": 1.0, + "learning_rate": 2.6226084489731474e-05, + "loss": 3.9134, + "step": 1452032 + }, + { + "epoch": 1.0, + "learning_rate": 2.6217698542220954e-05, + "loss": 3.9282, + "step": 1452544 + }, + { + "epoch": 1.0, + "learning_rate": 2.6209312594710434e-05, + "loss": 3.9113, + "step": 1453056 + }, + { + "epoch": 1.0, + "learning_rate": 2.6200943026003643e-05, + "loss": 3.9228, + "step": 1453568 + }, + { + "epoch": 1.0, + "learning_rate": 2.6192557078493123e-05, + "loss": 3.9069, + "step": 1454080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6184171130982603e-05, + "loss": 3.9226, + "step": 1454592 + }, + { + "epoch": 1.0, + "learning_rate": 2.6175785183472083e-05, + "loss": 3.9151, + "step": 1455104 + }, + { + "epoch": 1.0, + "learning_rate": 2.6167399235961566e-05, + "loss": 3.9264, + "step": 1455616 + }, + { + "epoch": 1.0, + "learning_rate": 2.6159029667254776e-05, + "loss": 3.9284, + "step": 1456128 + }, + { + "epoch": 1.0, + "learning_rate": 2.6150660098547985e-05, + "loss": 3.912, + "step": 1456640 + }, + { + "epoch": 1.0, + "learning_rate": 2.6142274151037465e-05, + "loss": 3.9166, + "step": 1457152 + }, + { + "epoch": 1.0, + "learning_rate": 2.6133888203526945e-05, + "loss": 3.9157, + "step": 1457664 + }, + { + "epoch": 1.0, + "learning_rate": 2.6125502256016428e-05, + "loss": 3.9147, + "step": 1458176 + }, + { + "epoch": 1.0, + "learning_rate": 2.6117116308505908e-05, + "loss": 3.9076, + "step": 1458688 + }, + { + "epoch": 1.0, + "learning_rate": 2.6108730360995388e-05, + "loss": 3.9133, + "step": 1459200 + }, + { + "epoch": 1.0, + "learning_rate": 2.6100344413484868e-05, + "loss": 3.9118, + "step": 1459712 + }, + { + "epoch": 1.0, + "learning_rate": 2.6091958465974348e-05, + "loss": 3.9384, + "step": 1460224 + }, + { + "epoch": 1.0, + "learning_rate": 2.6083572518463828e-05, + "loss": 3.9155, + "step": 1460736 + }, + { + "epoch": 1.0, + "learning_rate": 2.6075186570953308e-05, + "loss": 3.9236, + "step": 1461248 + }, + { + "epoch": 1.0, + "learning_rate": 2.606681700224652e-05, + "loss": 3.9302, + "step": 1461760 + }, + { + "epoch": 1.0, + "learning_rate": 2.6058431054736e-05, + "loss": 3.928, + "step": 1462272 + }, + { + "epoch": 1.0, + "learning_rate": 2.605004510722548e-05, + "loss": 3.9089, + "step": 1462784 + }, + { + "epoch": 1.0, + "learning_rate": 2.604165915971496e-05, + "loss": 3.9181, + "step": 1463296 + }, + { + "epoch": 1.0, + "learning_rate": 2.603327321220444e-05, + "loss": 3.911, + "step": 1463808 + }, + { + "epoch": 1.0, + "learning_rate": 2.602488726469392e-05, + "loss": 3.9194, + "step": 1464320 + }, + { + "epoch": 1.0, + "learning_rate": 2.6016501317183396e-05, + "loss": 3.9094, + "step": 1464832 + }, + { + "epoch": 1.01, + "learning_rate": 2.6008115369672876e-05, + "loss": 3.9119, + "step": 1465344 + }, + { + "epoch": 1.01, + "learning_rate": 2.599976217976982e-05, + "loss": 3.9217, + "step": 1465856 + }, + { + "epoch": 1.01, + "learning_rate": 2.59913762322593e-05, + "loss": 3.9212, + "step": 1466368 + }, + { + "epoch": 1.01, + "learning_rate": 2.598299028474878e-05, + "loss": 3.9139, + "step": 1466880 + }, + { + "epoch": 1.01, + "learning_rate": 2.597462071604199e-05, + "loss": 3.9227, + "step": 1467392 + }, + { + "epoch": 1.01, + "learning_rate": 2.5966234768531474e-05, + "loss": 3.9234, + "step": 1467904 + }, + { + "epoch": 1.01, + "learning_rate": 2.5957848821020954e-05, + "loss": 3.9152, + "step": 1468416 + }, + { + "epoch": 1.01, + "learning_rate": 2.5949462873510434e-05, + "loss": 3.9034, + "step": 1468928 + }, + { + "epoch": 1.01, + "learning_rate": 2.5941076925999914e-05, + "loss": 3.9232, + "step": 1469440 + }, + { + "epoch": 1.01, + "learning_rate": 2.5932690978489394e-05, + "loss": 3.9001, + "step": 1469952 + }, + { + "epoch": 1.01, + "learning_rate": 2.5924305030978867e-05, + "loss": 3.916, + "step": 1470464 + }, + { + "epoch": 1.01, + "learning_rate": 2.591591908346835e-05, + "loss": 3.9113, + "step": 1470976 + }, + { + "epoch": 1.01, + "learning_rate": 2.590753313595783e-05, + "loss": 3.9231, + "step": 1471488 + }, + { + "epoch": 1.01, + "learning_rate": 2.589914718844731e-05, + "loss": 3.9196, + "step": 1472000 + }, + { + "epoch": 1.01, + "learning_rate": 2.589076124093679e-05, + "loss": 3.9124, + "step": 1472512 + }, + { + "epoch": 1.01, + "learning_rate": 2.588237529342627e-05, + "loss": 3.9235, + "step": 1473024 + }, + { + "epoch": 1.01, + "learning_rate": 2.587400572471948e-05, + "loss": 3.9204, + "step": 1473536 + }, + { + "epoch": 1.01, + "learning_rate": 2.586563615601269e-05, + "loss": 3.9215, + "step": 1474048 + }, + { + "epoch": 1.01, + "learning_rate": 2.585725020850217e-05, + "loss": 3.9033, + "step": 1474560 + }, + { + "epoch": 1.01, + "learning_rate": 2.584886426099165e-05, + "loss": 3.9087, + "step": 1475072 + }, + { + "epoch": 1.01, + "learning_rate": 2.584047831348113e-05, + "loss": 3.927, + "step": 1475584 + }, + { + "epoch": 1.01, + "learning_rate": 2.583209236597061e-05, + "loss": 3.9103, + "step": 1476096 + }, + { + "epoch": 1.01, + "learning_rate": 2.582370641846009e-05, + "loss": 3.9087, + "step": 1476608 + }, + { + "epoch": 1.01, + "learning_rate": 2.5815336849753304e-05, + "loss": 3.9036, + "step": 1477120 + }, + { + "epoch": 1.01, + "learning_rate": 2.5806950902242784e-05, + "loss": 3.9134, + "step": 1477632 + }, + { + "epoch": 1.01, + "learning_rate": 2.5798564954732264e-05, + "loss": 3.9023, + "step": 1478144 + }, + { + "epoch": 1.01, + "learning_rate": 2.5790179007221744e-05, + "loss": 3.9134, + "step": 1478656 + }, + { + "epoch": 1.01, + "learning_rate": 2.5781793059711224e-05, + "loss": 3.9126, + "step": 1479168 + }, + { + "epoch": 1.01, + "learning_rate": 2.5773407112200704e-05, + "loss": 3.9164, + "step": 1479680 + }, + { + "epoch": 1.01, + "learning_rate": 2.5765037543493913e-05, + "loss": 3.9159, + "step": 1480192 + }, + { + "epoch": 1.01, + "learning_rate": 2.5756651595983393e-05, + "loss": 3.9041, + "step": 1480704 + }, + { + "epoch": 1.01, + "learning_rate": 2.5748265648472876e-05, + "loss": 3.9048, + "step": 1481216 + }, + { + "epoch": 1.01, + "learning_rate": 2.5739879700962356e-05, + "loss": 3.9186, + "step": 1481728 + }, + { + "epoch": 1.01, + "learning_rate": 2.5731493753451836e-05, + "loss": 3.9004, + "step": 1482240 + }, + { + "epoch": 1.01, + "learning_rate": 2.5723124184745045e-05, + "loss": 3.9086, + "step": 1482752 + }, + { + "epoch": 1.01, + "learning_rate": 2.5714738237234525e-05, + "loss": 3.9172, + "step": 1483264 + }, + { + "epoch": 1.01, + "learning_rate": 2.5706352289724005e-05, + "loss": 3.9215, + "step": 1483776 + }, + { + "epoch": 1.01, + "learning_rate": 2.5697966342213485e-05, + "loss": 3.9045, + "step": 1484288 + }, + { + "epoch": 1.01, + "learning_rate": 2.5689580394702968e-05, + "loss": 3.8964, + "step": 1484800 + }, + { + "epoch": 1.01, + "learning_rate": 2.5681210825996177e-05, + "loss": 3.9044, + "step": 1485312 + }, + { + "epoch": 1.01, + "learning_rate": 2.5672824878485657e-05, + "loss": 3.9153, + "step": 1485824 + }, + { + "epoch": 1.01, + "learning_rate": 2.5664438930975137e-05, + "loss": 3.9236, + "step": 1486336 + }, + { + "epoch": 1.01, + "learning_rate": 2.5656052983464617e-05, + "loss": 3.9109, + "step": 1486848 + }, + { + "epoch": 1.01, + "learning_rate": 2.5647667035954097e-05, + "loss": 3.9211, + "step": 1487360 + }, + { + "epoch": 1.01, + "learning_rate": 2.5639281088443577e-05, + "loss": 3.923, + "step": 1487872 + }, + { + "epoch": 1.01, + "learning_rate": 2.5630895140933054e-05, + "loss": 3.9216, + "step": 1488384 + }, + { + "epoch": 1.01, + "learning_rate": 2.5622509193422534e-05, + "loss": 3.9014, + "step": 1488896 + }, + { + "epoch": 1.01, + "learning_rate": 2.561413962471575e-05, + "loss": 3.9205, + "step": 1489408 + }, + { + "epoch": 1.01, + "learning_rate": 2.5605753677205223e-05, + "loss": 3.9168, + "step": 1489920 + }, + { + "epoch": 1.01, + "learning_rate": 2.5597367729694706e-05, + "loss": 3.9081, + "step": 1490432 + }, + { + "epoch": 1.01, + "learning_rate": 2.5588981782184186e-05, + "loss": 3.9139, + "step": 1490944 + }, + { + "epoch": 1.01, + "learning_rate": 2.5580595834673666e-05, + "loss": 3.9144, + "step": 1491456 + }, + { + "epoch": 1.01, + "learning_rate": 2.557224264477061e-05, + "loss": 3.9198, + "step": 1491968 + }, + { + "epoch": 1.01, + "learning_rate": 2.556385669726009e-05, + "loss": 3.917, + "step": 1492480 + }, + { + "epoch": 1.01, + "learning_rate": 2.555547074974957e-05, + "loss": 3.9073, + "step": 1492992 + }, + { + "epoch": 1.01, + "learning_rate": 2.554708480223905e-05, + "loss": 3.9161, + "step": 1493504 + }, + { + "epoch": 1.01, + "learning_rate": 2.5538698854728527e-05, + "loss": 3.9138, + "step": 1494016 + }, + { + "epoch": 1.01, + "learning_rate": 2.5530312907218007e-05, + "loss": 3.9153, + "step": 1494528 + }, + { + "epoch": 1.01, + "learning_rate": 2.5521926959707487e-05, + "loss": 3.9129, + "step": 1495040 + }, + { + "epoch": 1.01, + "learning_rate": 2.5513541012196967e-05, + "loss": 3.9068, + "step": 1495552 + }, + { + "epoch": 1.02, + "learning_rate": 2.5505155064686447e-05, + "loss": 3.92, + "step": 1496064 + }, + { + "epoch": 1.02, + "learning_rate": 2.549678549597966e-05, + "loss": 3.9122, + "step": 1496576 + }, + { + "epoch": 1.02, + "learning_rate": 2.548839954846914e-05, + "loss": 3.9096, + "step": 1497088 + }, + { + "epoch": 1.02, + "learning_rate": 2.548001360095862e-05, + "loss": 3.9054, + "step": 1497600 + }, + { + "epoch": 1.02, + "learning_rate": 2.54716276534481e-05, + "loss": 3.9244, + "step": 1498112 + }, + { + "epoch": 1.02, + "learning_rate": 2.546324170593758e-05, + "loss": 3.9185, + "step": 1498624 + }, + { + "epoch": 1.02, + "learning_rate": 2.545487213723079e-05, + "loss": 3.9114, + "step": 1499136 + }, + { + "epoch": 1.02, + "learning_rate": 2.5446502568524e-05, + "loss": 3.9027, + "step": 1499648 + }, + { + "epoch": 1.02, + "learning_rate": 2.5438132999817217e-05, + "loss": 3.9151, + "step": 1500160 + }, + { + "epoch": 1.02, + "learning_rate": 2.5429747052306697e-05, + "loss": 3.9039, + "step": 1500672 + }, + { + "epoch": 1.02, + "learning_rate": 2.542136110479617e-05, + "loss": 3.9291, + "step": 1501184 + }, + { + "epoch": 1.02, + "learning_rate": 2.541297515728565e-05, + "loss": 3.9148, + "step": 1501696 + }, + { + "epoch": 1.02, + "learning_rate": 2.540458920977513e-05, + "loss": 3.9109, + "step": 1502208 + }, + { + "epoch": 1.02, + "learning_rate": 2.5396203262264613e-05, + "loss": 3.9066, + "step": 1502720 + }, + { + "epoch": 1.02, + "learning_rate": 2.5387817314754093e-05, + "loss": 3.9166, + "step": 1503232 + }, + { + "epoch": 1.02, + "learning_rate": 2.5379431367243573e-05, + "loss": 3.89, + "step": 1503744 + }, + { + "epoch": 1.02, + "learning_rate": 2.5371045419733053e-05, + "loss": 3.906, + "step": 1504256 + }, + { + "epoch": 1.02, + "learning_rate": 2.5362659472222533e-05, + "loss": 3.9073, + "step": 1504768 + }, + { + "epoch": 1.02, + "learning_rate": 2.5354273524712013e-05, + "loss": 3.9126, + "step": 1505280 + }, + { + "epoch": 1.02, + "learning_rate": 2.5345887577201493e-05, + "loss": 3.8971, + "step": 1505792 + }, + { + "epoch": 1.02, + "learning_rate": 2.5337518008494706e-05, + "loss": 3.9169, + "step": 1506304 + }, + { + "epoch": 1.02, + "learning_rate": 2.5329132060984185e-05, + "loss": 3.9007, + "step": 1506816 + }, + { + "epoch": 1.02, + "learning_rate": 2.5320746113473665e-05, + "loss": 3.9193, + "step": 1507328 + }, + { + "epoch": 1.02, + "learning_rate": 2.5312376544766875e-05, + "loss": 3.9104, + "step": 1507840 + }, + { + "epoch": 1.02, + "learning_rate": 2.5303990597256355e-05, + "loss": 3.9073, + "step": 1508352 + }, + { + "epoch": 1.02, + "learning_rate": 2.5295604649745834e-05, + "loss": 3.9249, + "step": 1508864 + }, + { + "epoch": 1.02, + "learning_rate": 2.5287218702235314e-05, + "loss": 3.9299, + "step": 1509376 + }, + { + "epoch": 1.02, + "learning_rate": 2.5278832754724794e-05, + "loss": 3.9134, + "step": 1509888 + }, + { + "epoch": 1.02, + "learning_rate": 2.5270446807214278e-05, + "loss": 3.9062, + "step": 1510400 + }, + { + "epoch": 1.02, + "learning_rate": 2.5262060859703758e-05, + "loss": 3.9144, + "step": 1510912 + }, + { + "epoch": 1.02, + "learning_rate": 2.5253691290996967e-05, + "loss": 3.9064, + "step": 1511424 + }, + { + "epoch": 1.02, + "learning_rate": 2.5245305343486447e-05, + "loss": 3.9088, + "step": 1511936 + }, + { + "epoch": 1.02, + "learning_rate": 2.5236919395975927e-05, + "loss": 3.9239, + "step": 1512448 + }, + { + "epoch": 1.02, + "learning_rate": 2.5228533448465407e-05, + "loss": 3.9066, + "step": 1512960 + }, + { + "epoch": 1.02, + "learning_rate": 2.522016387975862e-05, + "loss": 3.9216, + "step": 1513472 + }, + { + "epoch": 1.02, + "learning_rate": 2.52117779322481e-05, + "loss": 3.9135, + "step": 1513984 + }, + { + "epoch": 1.02, + "learning_rate": 2.520339198473758e-05, + "loss": 3.9145, + "step": 1514496 + }, + { + "epoch": 1.02, + "learning_rate": 2.519500603722706e-05, + "loss": 3.8954, + "step": 1515008 + }, + { + "epoch": 1.02, + "learning_rate": 2.5186636468520268e-05, + "loss": 3.9181, + "step": 1515520 + }, + { + "epoch": 1.02, + "learning_rate": 2.5178250521009748e-05, + "loss": 3.9047, + "step": 1516032 + }, + { + "epoch": 1.02, + "learning_rate": 2.516986457349923e-05, + "loss": 3.9216, + "step": 1516544 + }, + { + "epoch": 1.02, + "learning_rate": 2.516147862598871e-05, + "loss": 3.9142, + "step": 1517056 + }, + { + "epoch": 1.02, + "learning_rate": 2.5153092678478185e-05, + "loss": 3.9194, + "step": 1517568 + }, + { + "epoch": 1.02, + "learning_rate": 2.5144706730967664e-05, + "loss": 3.9004, + "step": 1518080 + }, + { + "epoch": 1.02, + "learning_rate": 2.5136320783457144e-05, + "loss": 3.9236, + "step": 1518592 + }, + { + "epoch": 1.02, + "learning_rate": 2.5127934835946624e-05, + "loss": 3.9118, + "step": 1519104 + }, + { + "epoch": 1.02, + "learning_rate": 2.5119548888436108e-05, + "loss": 3.9151, + "step": 1519616 + }, + { + "epoch": 1.02, + "learning_rate": 2.5111179319729317e-05, + "loss": 3.9148, + "step": 1520128 + }, + { + "epoch": 1.02, + "learning_rate": 2.5102809751022533e-05, + "loss": 3.922, + "step": 1520640 + }, + { + "epoch": 1.02, + "learning_rate": 2.5094423803512006e-05, + "loss": 3.9181, + "step": 1521152 + }, + { + "epoch": 1.02, + "learning_rate": 2.5086054234805222e-05, + "loss": 3.9197, + "step": 1521664 + }, + { + "epoch": 1.02, + "learning_rate": 2.5077668287294702e-05, + "loss": 3.9033, + "step": 1522176 + }, + { + "epoch": 1.02, + "learning_rate": 2.5069282339784185e-05, + "loss": 3.9112, + "step": 1522688 + }, + { + "epoch": 1.02, + "learning_rate": 2.5060896392273658e-05, + "loss": 3.9122, + "step": 1523200 + }, + { + "epoch": 1.02, + "learning_rate": 2.5052510444763138e-05, + "loss": 3.9044, + "step": 1523712 + }, + { + "epoch": 1.02, + "learning_rate": 2.5044124497252618e-05, + "loss": 3.9151, + "step": 1524224 + }, + { + "epoch": 1.02, + "learning_rate": 2.5035738549742098e-05, + "loss": 3.9215, + "step": 1524736 + }, + { + "epoch": 1.02, + "learning_rate": 2.5027352602231578e-05, + "loss": 3.9103, + "step": 1525248 + }, + { + "epoch": 1.02, + "learning_rate": 2.501896665472106e-05, + "loss": 3.9066, + "step": 1525760 + }, + { + "epoch": 1.02, + "learning_rate": 2.501058070721054e-05, + "loss": 3.9165, + "step": 1526272 + }, + { + "epoch": 1.03, + "eval_loss": 3.997234582901001, + "eval_runtime": 296.5796, + "eval_samples_per_second": 1286.639, + "eval_steps_per_second": 40.208, + "step": 1526400 + }, + { + "epoch": 0.0, + "learning_rate": 2.500221113850375e-05, + "loss": 3.9004, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.499382519099323e-05, + "loss": 3.9091, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.498543924348271e-05, + "loss": 3.9157, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.497705329597219e-05, + "loss": 3.9102, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.496866734846167e-05, + "loss": 3.9208, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.4960281400951154e-05, + "loss": 3.9042, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.495189545344063e-05, + "loss": 3.9116, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.494350950593011e-05, + "loss": 3.9002, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.493512355841959e-05, + "loss": 3.9181, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.492673761090907e-05, + "loss": 3.9071, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.491835166339855e-05, + "loss": 3.9139, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.490996571588803e-05, + "loss": 3.9212, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.4901596147181242e-05, + "loss": 3.9021, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.4893210199670722e-05, + "loss": 3.9127, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.4884824252160202e-05, + "loss": 3.9051, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.4876438304649682e-05, + "loss": 3.9098, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.4868052357139162e-05, + "loss": 3.8982, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.485966640962864e-05, + "loss": 3.9077, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.4851280462118122e-05, + "loss": 3.9056, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.4842894514607602e-05, + "loss": 3.9268, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.483452494590081e-05, + "loss": 3.9074, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.482613899839029e-05, + "loss": 3.9151, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.481775305087977e-05, + "loss": 3.9226, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.480936710336925e-05, + "loss": 3.9213, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.480098115585873e-05, + "loss": 3.9002, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.479259520834821e-05, + "loss": 3.9138, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.4784209260837694e-05, + "loss": 3.9009, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.4775839692130903e-05, + "loss": 3.9113, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.4767453744620383e-05, + "loss": 3.8982, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.4759067797109863e-05, + "loss": 3.9086, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.4750681849599343e-05, + "loss": 3.9138, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.4742295902088823e-05, + "loss": 3.9118, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.4733909954578303e-05, + "loss": 3.9062, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.4725524007067783e-05, + "loss": 3.9192, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.4717154438360992e-05, + "loss": 3.91, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.4708768490850472e-05, + "loss": 3.9128, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.4700382543339952e-05, + "loss": 3.8959, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.4691996595829432e-05, + "loss": 3.9133, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.4683610648318915e-05, + "loss": 3.8979, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.4675224700808395e-05, + "loss": 3.9037, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.4666838753297875e-05, + "loss": 3.9036, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.4658452805787352e-05, + "loss": 3.9165, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.4650066858276832e-05, + "loss": 3.9129, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.4641680910766312e-05, + "loss": 3.9086, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.4633311342059524e-05, + "loss": 3.9139, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.4624925394549004e-05, + "loss": 3.913, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.4616539447038484e-05, + "loss": 3.9105, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.4608153499527964e-05, + "loss": 3.9017, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.4599783930821173e-05, + "loss": 3.8942, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.4591397983310653e-05, + "loss": 3.9177, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.4583012035800133e-05, + "loss": 3.9071, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.457464246709335e-05, + "loss": 3.9014, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.4566256519582826e-05, + "loss": 3.8991, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.4557870572072306e-05, + "loss": 3.907, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.4549484624561786e-05, + "loss": 3.8968, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.4541115055854998e-05, + "loss": 3.8992, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.4532729108344478e-05, + "loss": 3.9048, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.4524343160833958e-05, + "loss": 3.9044, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.4515957213323438e-05, + "loss": 3.915, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.4507571265812918e-05, + "loss": 3.8965, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.4499185318302398e-05, + "loss": 3.8967, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.4490799370791878e-05, + "loss": 3.9142, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.4482413423281354e-05, + "loss": 3.8954, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.447404385457457e-05, + "loss": 3.9014, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.446567428586778e-05, + "loss": 3.9079, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.445728833835726e-05, + "loss": 3.9137, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.444890239084674e-05, + "loss": 3.899, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.444051644333622e-05, + "loss": 3.8896, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.44321304958257e-05, + "loss": 3.8933, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.442376092711891e-05, + "loss": 3.9067, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.441537497960839e-05, + "loss": 3.9171, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.440698903209787e-05, + "loss": 3.9038, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.439860308458735e-05, + "loss": 3.9144, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.4390217137076828e-05, + "loss": 3.9144, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.4381831189566308e-05, + "loss": 3.9185, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.4373445242055788e-05, + "loss": 3.8944, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.4365075673349004e-05, + "loss": 3.9092, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.435668972583848e-05, + "loss": 3.9078, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.434830377832796e-05, + "loss": 3.8973, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.433991783081744e-05, + "loss": 3.9115, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.433153188330692e-05, + "loss": 3.9077, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.43231459357964e-05, + "loss": 3.9092, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.4314776367089613e-05, + "loss": 3.909, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.4306390419579093e-05, + "loss": 3.9037, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.4298004472068573e-05, + "loss": 3.9096, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.4289634903361782e-05, + "loss": 3.9043, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.4281248955851262e-05, + "loss": 3.9081, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.427286300834074e-05, + "loss": 3.9029, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.4264477060830225e-05, + "loss": 3.9029, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4256091113319705e-05, + "loss": 3.9095, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.4247705165809185e-05, + "loss": 3.9068, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.423931921829866e-05, + "loss": 3.9, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.423093327078814e-05, + "loss": 3.8987, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.422254732327762e-05, + "loss": 3.9185, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.4214177754570834e-05, + "loss": 3.9121, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.4205791807060314e-05, + "loss": 3.9069, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.4197405859549794e-05, + "loss": 3.8976, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.4189019912039274e-05, + "loss": 3.9045, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.4180633964528754e-05, + "loss": 3.9012, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.4172248017018234e-05, + "loss": 3.9151, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.4163862069507714e-05, + "loss": 3.9122, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.4155476121997194e-05, + "loss": 3.9023, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.4147090174486674e-05, + "loss": 3.898, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.4138720605779886e-05, + "loss": 3.9106, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.4130334658269366e-05, + "loss": 3.8806, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.4121948710758843e-05, + "loss": 3.9024, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.4113579142052055e-05, + "loss": 3.8952, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.4105193194541535e-05, + "loss": 3.9047, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.4096807247031015e-05, + "loss": 3.8913, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.4088421299520495e-05, + "loss": 3.9076, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.4080035352009975e-05, + "loss": 3.8978, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.4071649404499455e-05, + "loss": 3.9056, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.4063263456988935e-05, + "loss": 3.9074, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.4054877509478415e-05, + "loss": 3.8983, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.4046507940771627e-05, + "loss": 3.9185, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.4038121993261107e-05, + "loss": 3.9253, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.4029752424554316e-05, + "loss": 3.9062, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.4021366477043796e-05, + "loss": 3.8956, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.4012980529533276e-05, + "loss": 3.9078, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.4004594582022756e-05, + "loss": 3.9036, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.399622501331597e-05, + "loss": 3.8977, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.398783906580545e-05, + "loss": 3.9173, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.397945311829493e-05, + "loss": 3.8993, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.397106717078441e-05, + "loss": 3.9112, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.396268122327389e-05, + "loss": 3.9073, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.395429527576337e-05, + "loss": 3.9068, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.394590932825285e-05, + "loss": 3.8971, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.393753975954606e-05, + "loss": 3.9042, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.392915381203554e-05, + "loss": 3.9022, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.392076786452502e-05, + "loss": 3.9154, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.3912381917014497e-05, + "loss": 3.9076, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.3903995969503977e-05, + "loss": 3.9113, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.3895610021993457e-05, + "loss": 3.893, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.388722407448294e-05, + "loss": 3.9159, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.387883812697242e-05, + "loss": 3.9067, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.387046855826563e-05, + "loss": 3.9101, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.386208261075511e-05, + "loss": 3.9034, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.385369666324459e-05, + "loss": 3.9155, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.3845327094537802e-05, + "loss": 3.9083, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.3836941147027282e-05, + "loss": 3.9161, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.3828555199516762e-05, + "loss": 3.8929, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.3820169252006242e-05, + "loss": 3.9063, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.3811783304495722e-05, + "loss": 3.9007, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.38033973569852e-05, + "loss": 3.8973, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.379501140947468e-05, + "loss": 3.911, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.3786641840767894e-05, + "loss": 3.9101, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.3778255893257374e-05, + "loss": 3.9089, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.376986994574685e-05, + "loss": 3.8931, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.376148399823633e-05, + "loss": 3.91, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.9940273761749268, + "eval_runtime": 309.2776, + "eval_samples_per_second": 1233.814, + "eval_steps_per_second": 38.558, + "step": 1602720 + }, + { + "epoch": 1.0, + "learning_rate": 2.375309805072581e-05, + "loss": 3.9011, + "step": 1603072 + }, + { + "epoch": 1.0, + "learning_rate": 2.374471210321529e-05, + "loss": 3.8968, + "step": 1603584 + }, + { + "epoch": 1.0, + "learning_rate": 2.373632615570477e-05, + "loss": 3.9102, + "step": 1604096 + }, + { + "epoch": 1.0, + "learning_rate": 2.372794020819425e-05, + "loss": 3.903, + "step": 1604608 + }, + { + "epoch": 1.0, + "learning_rate": 2.3719570639487463e-05, + "loss": 3.9069, + "step": 1605120 + }, + { + "epoch": 1.0, + "learning_rate": 2.3711184691976943e-05, + "loss": 3.9, + "step": 1605632 + }, + { + "epoch": 1.0, + "learning_rate": 2.3702815123270152e-05, + "loss": 3.9033, + "step": 1606144 + }, + { + "epoch": 1.0, + "learning_rate": 2.3694429175759632e-05, + "loss": 3.8937, + "step": 1606656 + }, + { + "epoch": 1.0, + "learning_rate": 2.3686043228249112e-05, + "loss": 3.9058, + "step": 1607168 + }, + { + "epoch": 1.0, + "learning_rate": 2.3677657280738595e-05, + "loss": 3.9038, + "step": 1607680 + }, + { + "epoch": 1.0, + "learning_rate": 2.3669287712031804e-05, + "loss": 3.9062, + "step": 1608192 + }, + { + "epoch": 1.0, + "learning_rate": 2.3660901764521284e-05, + "loss": 3.913, + "step": 1608704 + }, + { + "epoch": 1.0, + "learning_rate": 2.3652532195814497e-05, + "loss": 3.8954, + "step": 1609216 + }, + { + "epoch": 1.0, + "learning_rate": 2.3644146248303973e-05, + "loss": 3.906, + "step": 1609728 + }, + { + "epoch": 1.0, + "learning_rate": 2.3635760300793457e-05, + "loss": 3.9019, + "step": 1610240 + }, + { + "epoch": 1.0, + "learning_rate": 2.3627374353282937e-05, + "loss": 3.8986, + "step": 1610752 + }, + { + "epoch": 1.0, + "learning_rate": 2.3618988405772417e-05, + "loss": 3.8921, + "step": 1611264 + }, + { + "epoch": 1.0, + "learning_rate": 2.3610602458261897e-05, + "loss": 3.9001, + "step": 1611776 + }, + { + "epoch": 1.0, + "learning_rate": 2.3602216510751377e-05, + "loss": 3.8962, + "step": 1612288 + }, + { + "epoch": 1.0, + "learning_rate": 2.3593830563240853e-05, + "loss": 3.9163, + "step": 1612800 + }, + { + "epoch": 1.0, + "learning_rate": 2.3585444615730333e-05, + "loss": 3.9069, + "step": 1613312 + }, + { + "epoch": 1.0, + "learning_rate": 2.3577058668219813e-05, + "loss": 3.9062, + "step": 1613824 + }, + { + "epoch": 1.0, + "learning_rate": 2.356868909951303e-05, + "loss": 3.9157, + "step": 1614336 + }, + { + "epoch": 1.0, + "learning_rate": 2.3560303152002505e-05, + "loss": 3.9129, + "step": 1614848 + }, + { + "epoch": 1.0, + "learning_rate": 2.3551917204491985e-05, + "loss": 3.8924, + "step": 1615360 + }, + { + "epoch": 1.0, + "learning_rate": 2.3543531256981465e-05, + "loss": 3.9057, + "step": 1615872 + }, + { + "epoch": 1.0, + "learning_rate": 2.3535145309470945e-05, + "loss": 3.8964, + "step": 1616384 + }, + { + "epoch": 1.0, + "learning_rate": 2.3526759361960425e-05, + "loss": 3.9023, + "step": 1616896 + }, + { + "epoch": 1.0, + "learning_rate": 2.3518389793253638e-05, + "loss": 3.8938, + "step": 1617408 + }, + { + "epoch": 1.0, + "learning_rate": 2.3510003845743118e-05, + "loss": 3.8964, + "step": 1617920 + }, + { + "epoch": 1.01, + "learning_rate": 2.3501617898232598e-05, + "loss": 3.9078, + "step": 1618432 + }, + { + "epoch": 1.01, + "learning_rate": 2.3493231950722078e-05, + "loss": 3.9038, + "step": 1618944 + }, + { + "epoch": 1.01, + "learning_rate": 2.3484846003211558e-05, + "loss": 3.9004, + "step": 1619456 + }, + { + "epoch": 1.01, + "learning_rate": 2.3476460055701034e-05, + "loss": 3.907, + "step": 1619968 + }, + { + "epoch": 1.01, + "learning_rate": 2.346809048699425e-05, + "loss": 3.9052, + "step": 1620480 + }, + { + "epoch": 1.01, + "learning_rate": 2.345970453948373e-05, + "loss": 3.9049, + "step": 1620992 + }, + { + "epoch": 1.01, + "learning_rate": 2.345131859197321e-05, + "loss": 3.8934, + "step": 1621504 + }, + { + "epoch": 1.01, + "learning_rate": 2.3442932644462687e-05, + "loss": 3.8976, + "step": 1622016 + }, + { + "epoch": 1.01, + "learning_rate": 2.3434546696952166e-05, + "loss": 3.8952, + "step": 1622528 + }, + { + "epoch": 1.01, + "learning_rate": 2.3426160749441646e-05, + "loss": 3.8962, + "step": 1623040 + }, + { + "epoch": 1.01, + "learning_rate": 2.341779118073486e-05, + "loss": 3.8961, + "step": 1623552 + }, + { + "epoch": 1.01, + "learning_rate": 2.340940523322434e-05, + "loss": 3.9089, + "step": 1624064 + }, + { + "epoch": 1.01, + "learning_rate": 2.340101928571382e-05, + "loss": 3.9055, + "step": 1624576 + }, + { + "epoch": 1.01, + "learning_rate": 2.33926333382033e-05, + "loss": 3.9011, + "step": 1625088 + }, + { + "epoch": 1.01, + "learning_rate": 2.338424739069278e-05, + "loss": 3.9112, + "step": 1625600 + }, + { + "epoch": 1.01, + "learning_rate": 2.337586144318226e-05, + "loss": 3.9013, + "step": 1626112 + }, + { + "epoch": 1.01, + "learning_rate": 2.336747549567174e-05, + "loss": 3.9064, + "step": 1626624 + }, + { + "epoch": 1.01, + "learning_rate": 2.335908954816122e-05, + "loss": 3.8936, + "step": 1627136 + }, + { + "epoch": 1.01, + "learning_rate": 2.335071997945443e-05, + "loss": 3.8847, + "step": 1627648 + }, + { + "epoch": 1.01, + "learning_rate": 2.334233403194391e-05, + "loss": 3.9119, + "step": 1628160 + }, + { + "epoch": 1.01, + "learning_rate": 2.333396446323712e-05, + "loss": 3.8958, + "step": 1628672 + }, + { + "epoch": 1.01, + "learning_rate": 2.33255785157266e-05, + "loss": 3.8987, + "step": 1629184 + }, + { + "epoch": 1.01, + "learning_rate": 2.331719256821608e-05, + "loss": 3.8929, + "step": 1629696 + }, + { + "epoch": 1.01, + "learning_rate": 2.330880662070556e-05, + "loss": 3.8965, + "step": 1630208 + }, + { + "epoch": 1.01, + "learning_rate": 2.330042067319504e-05, + "loss": 3.8896, + "step": 1630720 + }, + { + "epoch": 1.01, + "learning_rate": 2.3292051104488252e-05, + "loss": 3.8927, + "step": 1631232 + }, + { + "epoch": 1.01, + "learning_rate": 2.3283665156977732e-05, + "loss": 3.8971, + "step": 1631744 + }, + { + "epoch": 1.01, + "learning_rate": 2.327529558827094e-05, + "loss": 3.8968, + "step": 1632256 + }, + { + "epoch": 1.01, + "learning_rate": 2.326690964076042e-05, + "loss": 3.9062, + "step": 1632768 + }, + { + "epoch": 1.01, + "learning_rate": 2.3258523693249905e-05, + "loss": 3.8879, + "step": 1633280 + }, + { + "epoch": 1.01, + "learning_rate": 2.3250137745739385e-05, + "loss": 3.8917, + "step": 1633792 + }, + { + "epoch": 1.01, + "learning_rate": 2.3241751798228865e-05, + "loss": 3.9067, + "step": 1634304 + }, + { + "epoch": 1.01, + "learning_rate": 2.323336585071834e-05, + "loss": 3.8874, + "step": 1634816 + }, + { + "epoch": 1.01, + "learning_rate": 2.322497990320782e-05, + "loss": 3.8925, + "step": 1635328 + }, + { + "epoch": 1.01, + "learning_rate": 2.32165939556973e-05, + "loss": 3.897, + "step": 1635840 + }, + { + "epoch": 1.01, + "learning_rate": 2.320820800818678e-05, + "loss": 3.9049, + "step": 1636352 + }, + { + "epoch": 1.01, + "learning_rate": 2.3199822060676265e-05, + "loss": 3.8899, + "step": 1636864 + }, + { + "epoch": 1.01, + "learning_rate": 2.3191436113165744e-05, + "loss": 3.8877, + "step": 1637376 + }, + { + "epoch": 1.01, + "learning_rate": 2.3183066544458954e-05, + "loss": 3.8788, + "step": 1637888 + }, + { + "epoch": 1.01, + "learning_rate": 2.3174680596948434e-05, + "loss": 3.9017, + "step": 1638400 + }, + { + "epoch": 1.01, + "learning_rate": 2.3166311028241643e-05, + "loss": 3.9098, + "step": 1638912 + }, + { + "epoch": 1.01, + "learning_rate": 2.3157925080731126e-05, + "loss": 3.8974, + "step": 1639424 + }, + { + "epoch": 1.01, + "learning_rate": 2.3149539133220606e-05, + "loss": 3.9026, + "step": 1639936 + }, + { + "epoch": 1.01, + "learning_rate": 2.3141169564513815e-05, + "loss": 3.9068, + "step": 1640448 + }, + { + "epoch": 1.01, + "learning_rate": 2.3132783617003295e-05, + "loss": 3.915, + "step": 1640960 + }, + { + "epoch": 1.01, + "learning_rate": 2.3124397669492775e-05, + "loss": 3.886, + "step": 1641472 + }, + { + "epoch": 1.01, + "learning_rate": 2.3116011721982255e-05, + "loss": 3.9036, + "step": 1641984 + }, + { + "epoch": 1.01, + "learning_rate": 2.3107625774471735e-05, + "loss": 3.8997, + "step": 1642496 + }, + { + "epoch": 1.01, + "learning_rate": 2.3099239826961215e-05, + "loss": 3.8879, + "step": 1643008 + }, + { + "epoch": 1.01, + "learning_rate": 2.3090853879450695e-05, + "loss": 3.9035, + "step": 1643520 + }, + { + "epoch": 1.01, + "learning_rate": 2.3082467931940175e-05, + "loss": 3.9028, + "step": 1644032 + }, + { + "epoch": 1.01, + "learning_rate": 2.3074081984429655e-05, + "loss": 3.9007, + "step": 1644544 + }, + { + "epoch": 1.01, + "learning_rate": 2.3065712415722867e-05, + "loss": 3.9031, + "step": 1645056 + }, + { + "epoch": 1.01, + "learning_rate": 2.3057326468212344e-05, + "loss": 3.8966, + "step": 1645568 + }, + { + "epoch": 1.01, + "learning_rate": 2.3048940520701827e-05, + "loss": 3.8936, + "step": 1646080 + }, + { + "epoch": 1.01, + "learning_rate": 2.3040554573191307e-05, + "loss": 3.8988, + "step": 1646592 + }, + { + "epoch": 1.01, + "learning_rate": 2.3032168625680787e-05, + "loss": 3.9023, + "step": 1647104 + }, + { + "epoch": 1.01, + "learning_rate": 2.3023782678170267e-05, + "loss": 3.8904, + "step": 1647616 + }, + { + "epoch": 1.01, + "learning_rate": 2.301542948826721e-05, + "loss": 3.8964, + "step": 1648128 + }, + { + "epoch": 1.02, + "learning_rate": 2.300704354075669e-05, + "loss": 3.9028, + "step": 1648640 + }, + { + "epoch": 1.02, + "learning_rate": 2.299865759324617e-05, + "loss": 3.8975, + "step": 1649152 + }, + { + "epoch": 1.02, + "learning_rate": 2.299027164573565e-05, + "loss": 3.8923, + "step": 1649664 + }, + { + "epoch": 1.02, + "learning_rate": 2.298188569822513e-05, + "loss": 3.8921, + "step": 1650176 + }, + { + "epoch": 1.02, + "learning_rate": 2.297349975071461e-05, + "loss": 3.9097, + "step": 1650688 + }, + { + "epoch": 1.02, + "learning_rate": 2.2965113803204088e-05, + "loss": 3.9038, + "step": 1651200 + }, + { + "epoch": 1.02, + "learning_rate": 2.2956727855693568e-05, + "loss": 3.9007, + "step": 1651712 + }, + { + "epoch": 1.02, + "learning_rate": 2.2948341908183048e-05, + "loss": 3.8853, + "step": 1652224 + }, + { + "epoch": 1.02, + "learning_rate": 2.2939955960672528e-05, + "loss": 3.8974, + "step": 1652736 + }, + { + "epoch": 1.02, + "learning_rate": 2.293158639196574e-05, + "loss": 3.8941, + "step": 1653248 + }, + { + "epoch": 1.02, + "learning_rate": 2.292320044445522e-05, + "loss": 3.9042, + "step": 1653760 + }, + { + "epoch": 1.02, + "learning_rate": 2.29148144969447e-05, + "loss": 3.907, + "step": 1654272 + }, + { + "epoch": 1.02, + "learning_rate": 2.2906428549434177e-05, + "loss": 3.8934, + "step": 1654784 + }, + { + "epoch": 1.02, + "learning_rate": 2.2898042601923657e-05, + "loss": 3.8906, + "step": 1655296 + }, + { + "epoch": 1.02, + "learning_rate": 2.2889656654413137e-05, + "loss": 3.9026, + "step": 1655808 + }, + { + "epoch": 1.02, + "learning_rate": 2.288127070690262e-05, + "loss": 3.8757, + "step": 1656320 + }, + { + "epoch": 1.02, + "learning_rate": 2.28728847593921e-05, + "loss": 3.8935, + "step": 1656832 + }, + { + "epoch": 1.02, + "learning_rate": 2.286451519068531e-05, + "loss": 3.8846, + "step": 1657344 + }, + { + "epoch": 1.02, + "learning_rate": 2.285612924317479e-05, + "loss": 3.9017, + "step": 1657856 + }, + { + "epoch": 1.02, + "learning_rate": 2.284774329566427e-05, + "loss": 3.884, + "step": 1658368 + }, + { + "epoch": 1.02, + "learning_rate": 2.283935734815375e-05, + "loss": 3.9009, + "step": 1658880 + }, + { + "epoch": 1.02, + "learning_rate": 2.2830987779446962e-05, + "loss": 3.8891, + "step": 1659392 + }, + { + "epoch": 1.02, + "learning_rate": 2.2822601831936442e-05, + "loss": 3.8981, + "step": 1659904 + }, + { + "epoch": 1.02, + "learning_rate": 2.281421588442592e-05, + "loss": 3.8996, + "step": 1660416 + }, + { + "epoch": 1.02, + "learning_rate": 2.28058299369154e-05, + "loss": 3.8953, + "step": 1660928 + }, + { + "epoch": 1.02, + "learning_rate": 2.279746036820861e-05, + "loss": 3.907, + "step": 1661440 + }, + { + "epoch": 1.02, + "learning_rate": 2.278907442069809e-05, + "loss": 3.9158, + "step": 1661952 + }, + { + "epoch": 1.02, + "learning_rate": 2.2780688473187574e-05, + "loss": 3.8989, + "step": 1662464 + }, + { + "epoch": 1.02, + "learning_rate": 2.2772302525677054e-05, + "loss": 3.8924, + "step": 1662976 + }, + { + "epoch": 1.02, + "learning_rate": 2.276391657816653e-05, + "loss": 3.8979, + "step": 1663488 + }, + { + "epoch": 1.02, + "learning_rate": 2.2755547009459743e-05, + "loss": 3.8979, + "step": 1664000 + }, + { + "epoch": 1.02, + "learning_rate": 2.2747161061949223e-05, + "loss": 3.8864, + "step": 1664512 + }, + { + "epoch": 1.02, + "learning_rate": 2.2738775114438703e-05, + "loss": 3.9146, + "step": 1665024 + }, + { + "epoch": 1.02, + "learning_rate": 2.2730389166928183e-05, + "loss": 3.8882, + "step": 1665536 + }, + { + "epoch": 1.02, + "learning_rate": 2.2722003219417663e-05, + "loss": 3.9058, + "step": 1666048 + }, + { + "epoch": 1.02, + "learning_rate": 2.2713633650710875e-05, + "loss": 3.9001, + "step": 1666560 + }, + { + "epoch": 1.02, + "learning_rate": 2.2705247703200352e-05, + "loss": 3.8992, + "step": 1667072 + }, + { + "epoch": 1.02, + "learning_rate": 2.2696861755689832e-05, + "loss": 3.8888, + "step": 1667584 + }, + { + "epoch": 1.02, + "learning_rate": 2.2688492186983044e-05, + "loss": 3.8989, + "step": 1668096 + }, + { + "epoch": 1.02, + "learning_rate": 2.2680106239472528e-05, + "loss": 3.8929, + "step": 1668608 + }, + { + "epoch": 1.02, + "learning_rate": 2.2671720291962004e-05, + "loss": 3.9082, + "step": 1669120 + }, + { + "epoch": 1.02, + "learning_rate": 2.2663334344451484e-05, + "loss": 3.8987, + "step": 1669632 + }, + { + "epoch": 1.02, + "learning_rate": 2.2654948396940964e-05, + "loss": 3.9031, + "step": 1670144 + }, + { + "epoch": 1.02, + "learning_rate": 2.2646578828234177e-05, + "loss": 3.8861, + "step": 1670656 + }, + { + "epoch": 1.02, + "learning_rate": 2.2638192880723653e-05, + "loss": 3.909, + "step": 1671168 + }, + { + "epoch": 1.02, + "learning_rate": 2.2629806933213137e-05, + "loss": 3.8964, + "step": 1671680 + }, + { + "epoch": 1.02, + "learning_rate": 2.2621420985702617e-05, + "loss": 3.9011, + "step": 1672192 + }, + { + "epoch": 1.02, + "learning_rate": 2.2613035038192096e-05, + "loss": 3.8981, + "step": 1672704 + }, + { + "epoch": 1.02, + "learning_rate": 2.2604649090681576e-05, + "loss": 3.9055, + "step": 1673216 + }, + { + "epoch": 1.02, + "learning_rate": 2.2596263143171056e-05, + "loss": 3.8995, + "step": 1673728 + }, + { + "epoch": 1.02, + "learning_rate": 2.2587877195660533e-05, + "loss": 3.9126, + "step": 1674240 + }, + { + "epoch": 1.02, + "learning_rate": 2.2579507626953745e-05, + "loss": 3.8863, + "step": 1674752 + }, + { + "epoch": 1.02, + "learning_rate": 2.257112167944323e-05, + "loss": 3.8951, + "step": 1675264 + }, + { + "epoch": 1.02, + "learning_rate": 2.256273573193271e-05, + "loss": 3.8951, + "step": 1675776 + }, + { + "epoch": 1.02, + "learning_rate": 2.2554349784422185e-05, + "loss": 3.894, + "step": 1676288 + }, + { + "epoch": 1.02, + "learning_rate": 2.2545980215715398e-05, + "loss": 3.8958, + "step": 1676800 + }, + { + "epoch": 1.02, + "learning_rate": 2.2537610647008607e-05, + "loss": 3.9034, + "step": 1677312 + }, + { + "epoch": 1.02, + "learning_rate": 2.252922469949809e-05, + "loss": 3.9033, + "step": 1677824 + }, + { + "epoch": 1.02, + "learning_rate": 2.252083875198757e-05, + "loss": 3.8842, + "step": 1678336 + }, + { + "epoch": 1.02, + "learning_rate": 2.251245280447705e-05, + "loss": 3.9061, + "step": 1678848 + }, + { + "epoch": 1.03, + "eval_loss": 3.991403102874756, + "eval_runtime": 312.043, + "eval_samples_per_second": 1222.88, + "eval_steps_per_second": 38.216, + "step": 1679040 + }, + { + "epoch": 0.0, + "learning_rate": 2.250406685696653e-05, + "loss": 3.8959, + "step": 1679360 + }, + { + "epoch": 0.0, + "learning_rate": 2.2495680909456007e-05, + "loss": 3.8852, + "step": 1679872 + }, + { + "epoch": 0.0, + "learning_rate": 2.2487294961945487e-05, + "loss": 3.9032, + "step": 1680384 + }, + { + "epoch": 0.0, + "learning_rate": 2.2478909014434967e-05, + "loss": 3.8968, + "step": 1680896 + }, + { + "epoch": 0.0, + "learning_rate": 2.2470523066924447e-05, + "loss": 3.8986, + "step": 1681408 + }, + { + "epoch": 0.0, + "learning_rate": 2.246213711941393e-05, + "loss": 3.8918, + "step": 1681920 + }, + { + "epoch": 0.0, + "learning_rate": 2.245375117190341e-05, + "loss": 3.892, + "step": 1682432 + }, + { + "epoch": 0.0, + "learning_rate": 2.244536522439289e-05, + "loss": 3.8896, + "step": 1682944 + }, + { + "epoch": 0.0, + "learning_rate": 2.2436979276882366e-05, + "loss": 3.8989, + "step": 1683456 + }, + { + "epoch": 0.0, + "learning_rate": 2.2428593329371846e-05, + "loss": 3.8945, + "step": 1683968 + }, + { + "epoch": 0.0, + "learning_rate": 2.2420207381861326e-05, + "loss": 3.9016, + "step": 1684480 + }, + { + "epoch": 0.0, + "learning_rate": 2.2411821434350806e-05, + "loss": 3.9054, + "step": 1684992 + }, + { + "epoch": 0.0, + "learning_rate": 2.240345186564402e-05, + "loss": 3.8927, + "step": 1685504 + }, + { + "epoch": 0.0, + "learning_rate": 2.23950659181335e-05, + "loss": 3.8959, + "step": 1686016 + }, + { + "epoch": 0.0, + "learning_rate": 2.238667997062298e-05, + "loss": 3.8988, + "step": 1686528 + }, + { + "epoch": 0.0, + "learning_rate": 2.237829402311246e-05, + "loss": 3.8906, + "step": 1687040 + }, + { + "epoch": 0.0, + "learning_rate": 2.236990807560194e-05, + "loss": 3.883, + "step": 1687552 + }, + { + "epoch": 0.0, + "learning_rate": 2.236152212809142e-05, + "loss": 3.8917, + "step": 1688064 + }, + { + "epoch": 0.0, + "learning_rate": 2.23531361805809e-05, + "loss": 3.8924, + "step": 1688576 + }, + { + "epoch": 0.0, + "learning_rate": 2.234475023307038e-05, + "loss": 3.9056, + "step": 1689088 + }, + { + "epoch": 0.0, + "learning_rate": 2.233636428555986e-05, + "loss": 3.8994, + "step": 1689600 + }, + { + "epoch": 0.0, + "learning_rate": 2.232797833804934e-05, + "loss": 3.9017, + "step": 1690112 + }, + { + "epoch": 0.0, + "learning_rate": 2.2319592390538818e-05, + "loss": 3.907, + "step": 1690624 + }, + { + "epoch": 0.0, + "learning_rate": 2.2311222821832027e-05, + "loss": 3.9056, + "step": 1691136 + }, + { + "epoch": 0.0, + "learning_rate": 2.2302836874321507e-05, + "loss": 3.888, + "step": 1691648 + }, + { + "epoch": 0.0, + "learning_rate": 2.229445092681099e-05, + "loss": 3.9014, + "step": 1692160 + }, + { + "epoch": 0.0, + "learning_rate": 2.228606497930047e-05, + "loss": 3.8848, + "step": 1692672 + }, + { + "epoch": 0.0, + "learning_rate": 2.227767903178995e-05, + "loss": 3.8943, + "step": 1693184 + }, + { + "epoch": 0.0, + "learning_rate": 2.226929308427943e-05, + "loss": 3.8922, + "step": 1693696 + }, + { + "epoch": 0.0, + "learning_rate": 2.226092351557264e-05, + "loss": 3.8895, + "step": 1694208 + }, + { + "epoch": 0.01, + "learning_rate": 2.225253756806212e-05, + "loss": 3.8996, + "step": 1694720 + }, + { + "epoch": 0.01, + "learning_rate": 2.22441516205516e-05, + "loss": 3.8973, + "step": 1695232 + }, + { + "epoch": 0.01, + "learning_rate": 2.223576567304108e-05, + "loss": 3.8941, + "step": 1695744 + }, + { + "epoch": 0.01, + "learning_rate": 2.222737972553056e-05, + "loss": 3.8995, + "step": 1696256 + }, + { + "epoch": 0.01, + "learning_rate": 2.22190265356275e-05, + "loss": 3.8966, + "step": 1696768 + }, + { + "epoch": 0.01, + "learning_rate": 2.221064058811698e-05, + "loss": 3.899, + "step": 1697280 + }, + { + "epoch": 0.01, + "learning_rate": 2.220225464060646e-05, + "loss": 3.8881, + "step": 1697792 + }, + { + "epoch": 0.01, + "learning_rate": 2.2193868693095944e-05, + "loss": 3.8901, + "step": 1698304 + }, + { + "epoch": 0.01, + "learning_rate": 2.2185482745585424e-05, + "loss": 3.8848, + "step": 1698816 + }, + { + "epoch": 0.01, + "learning_rate": 2.2177096798074904e-05, + "loss": 3.8882, + "step": 1699328 + }, + { + "epoch": 0.01, + "learning_rate": 2.216871085056438e-05, + "loss": 3.8897, + "step": 1699840 + }, + { + "epoch": 0.01, + "learning_rate": 2.216032490305386e-05, + "loss": 3.9018, + "step": 1700352 + }, + { + "epoch": 0.01, + "learning_rate": 2.215193895554334e-05, + "loss": 3.8977, + "step": 1700864 + }, + { + "epoch": 0.01, + "learning_rate": 2.214355300803282e-05, + "loss": 3.894, + "step": 1701376 + }, + { + "epoch": 0.01, + "learning_rate": 2.2135183439326033e-05, + "loss": 3.9051, + "step": 1701888 + }, + { + "epoch": 0.01, + "learning_rate": 2.2126813870619246e-05, + "loss": 3.8976, + "step": 1702400 + }, + { + "epoch": 0.01, + "learning_rate": 2.2118427923108726e-05, + "loss": 3.9003, + "step": 1702912 + }, + { + "epoch": 0.01, + "learning_rate": 2.2110041975598202e-05, + "loss": 3.8864, + "step": 1703424 + }, + { + "epoch": 0.01, + "learning_rate": 2.2101656028087682e-05, + "loss": 3.8768, + "step": 1703936 + }, + { + "epoch": 0.01, + "learning_rate": 2.2093270080577162e-05, + "loss": 3.9068, + "step": 1704448 + }, + { + "epoch": 0.01, + "learning_rate": 2.2084884133066645e-05, + "loss": 3.8905, + "step": 1704960 + }, + { + "epoch": 0.01, + "learning_rate": 2.2076498185556125e-05, + "loss": 3.8874, + "step": 1705472 + }, + { + "epoch": 0.01, + "learning_rate": 2.2068112238045605e-05, + "loss": 3.8899, + "step": 1705984 + }, + { + "epoch": 0.01, + "learning_rate": 2.2059742669338814e-05, + "loss": 3.8857, + "step": 1706496 + }, + { + "epoch": 0.01, + "learning_rate": 2.2051356721828294e-05, + "loss": 3.8873, + "step": 1707008 + }, + { + "epoch": 0.01, + "learning_rate": 2.2042970774317774e-05, + "loss": 3.8814, + "step": 1707520 + }, + { + "epoch": 0.01, + "learning_rate": 2.2034584826807254e-05, + "loss": 3.8926, + "step": 1708032 + }, + { + "epoch": 0.01, + "learning_rate": 2.2026198879296734e-05, + "loss": 3.8913, + "step": 1708544 + }, + { + "epoch": 0.01, + "learning_rate": 2.2017812931786214e-05, + "loss": 3.9021, + "step": 1709056 + }, + { + "epoch": 0.01, + "learning_rate": 2.2009443363079427e-05, + "loss": 3.882, + "step": 1709568 + }, + { + "epoch": 0.01, + "learning_rate": 2.2001057415568907e-05, + "loss": 3.8796, + "step": 1710080 + }, + { + "epoch": 0.01, + "learning_rate": 2.1992671468058383e-05, + "loss": 3.9035, + "step": 1710592 + }, + { + "epoch": 0.01, + "learning_rate": 2.1984285520547863e-05, + "loss": 3.8773, + "step": 1711104 + }, + { + "epoch": 0.01, + "learning_rate": 2.1975899573037347e-05, + "loss": 3.884, + "step": 1711616 + }, + { + "epoch": 0.01, + "learning_rate": 2.1967513625526826e-05, + "loss": 3.8942, + "step": 1712128 + }, + { + "epoch": 0.01, + "learning_rate": 2.1959127678016306e-05, + "loss": 3.9022, + "step": 1712640 + }, + { + "epoch": 0.01, + "learning_rate": 2.1950741730505786e-05, + "loss": 3.8837, + "step": 1713152 + }, + { + "epoch": 0.01, + "learning_rate": 2.1942355782995263e-05, + "loss": 3.8789, + "step": 1713664 + }, + { + "epoch": 0.01, + "learning_rate": 2.1933986214288475e-05, + "loss": 3.8732, + "step": 1714176 + }, + { + "epoch": 0.01, + "learning_rate": 2.1925600266777955e-05, + "loss": 3.8923, + "step": 1714688 + }, + { + "epoch": 0.01, + "learning_rate": 2.191721431926744e-05, + "loss": 3.9059, + "step": 1715200 + }, + { + "epoch": 0.01, + "learning_rate": 2.1908828371756915e-05, + "loss": 3.892, + "step": 1715712 + }, + { + "epoch": 0.01, + "learning_rate": 2.1900475181853857e-05, + "loss": 3.8907, + "step": 1716224 + }, + { + "epoch": 0.01, + "learning_rate": 2.1892089234343337e-05, + "loss": 3.9006, + "step": 1716736 + }, + { + "epoch": 0.01, + "learning_rate": 2.1883703286832817e-05, + "loss": 3.9085, + "step": 1717248 + }, + { + "epoch": 0.01, + "learning_rate": 2.18753173393223e-05, + "loss": 3.8825, + "step": 1717760 + }, + { + "epoch": 0.01, + "learning_rate": 2.186693139181178e-05, + "loss": 3.8965, + "step": 1718272 + }, + { + "epoch": 0.01, + "learning_rate": 2.185854544430126e-05, + "loss": 3.8956, + "step": 1718784 + }, + { + "epoch": 0.01, + "learning_rate": 2.1850159496790737e-05, + "loss": 3.8807, + "step": 1719296 + }, + { + "epoch": 0.01, + "learning_rate": 2.184178992808395e-05, + "loss": 3.8957, + "step": 1719808 + }, + { + "epoch": 0.01, + "learning_rate": 2.183340398057343e-05, + "loss": 3.8965, + "step": 1720320 + }, + { + "epoch": 0.01, + "learning_rate": 2.182501803306291e-05, + "loss": 3.8973, + "step": 1720832 + }, + { + "epoch": 0.01, + "learning_rate": 2.181663208555239e-05, + "loss": 3.895, + "step": 1721344 + }, + { + "epoch": 0.01, + "learning_rate": 2.180824613804187e-05, + "loss": 3.8934, + "step": 1721856 + }, + { + "epoch": 0.01, + "learning_rate": 2.179986019053135e-05, + "loss": 3.8866, + "step": 1722368 + }, + { + "epoch": 0.01, + "learning_rate": 2.179149062182456e-05, + "loss": 3.8956, + "step": 1722880 + }, + { + "epoch": 0.01, + "learning_rate": 2.1783104674314038e-05, + "loss": 3.8933, + "step": 1723392 + }, + { + "epoch": 0.01, + "learning_rate": 2.177471872680352e-05, + "loss": 3.8883, + "step": 1723904 + }, + { + "epoch": 0.01, + "learning_rate": 2.1766332779293e-05, + "loss": 3.8907, + "step": 1724416 + }, + { + "epoch": 0.02, + "learning_rate": 2.175794683178248e-05, + "loss": 3.8891, + "step": 1724928 + }, + { + "epoch": 0.02, + "learning_rate": 2.174956088427196e-05, + "loss": 3.8964, + "step": 1725440 + }, + { + "epoch": 0.02, + "learning_rate": 2.174119131556517e-05, + "loss": 3.8886, + "step": 1725952 + }, + { + "epoch": 0.02, + "learning_rate": 2.173280536805465e-05, + "loss": 3.8836, + "step": 1726464 + }, + { + "epoch": 0.02, + "learning_rate": 2.172441942054413e-05, + "loss": 3.9044, + "step": 1726976 + }, + { + "epoch": 0.02, + "learning_rate": 2.171603347303361e-05, + "loss": 3.8939, + "step": 1727488 + }, + { + "epoch": 0.02, + "learning_rate": 2.1707647525523093e-05, + "loss": 3.8929, + "step": 1728000 + }, + { + "epoch": 0.02, + "learning_rate": 2.1699277956816303e-05, + "loss": 3.8801, + "step": 1728512 + }, + { + "epoch": 0.02, + "learning_rate": 2.1690892009305783e-05, + "loss": 3.8935, + "step": 1729024 + }, + { + "epoch": 0.02, + "learning_rate": 2.1682506061795263e-05, + "loss": 3.8858, + "step": 1729536 + }, + { + "epoch": 0.02, + "learning_rate": 2.1674120114284742e-05, + "loss": 3.8972, + "step": 1730048 + }, + { + "epoch": 0.02, + "learning_rate": 2.1665750545577955e-05, + "loss": 3.9034, + "step": 1730560 + }, + { + "epoch": 0.02, + "learning_rate": 2.1657364598067435e-05, + "loss": 3.8854, + "step": 1731072 + }, + { + "epoch": 0.02, + "learning_rate": 2.1648978650556915e-05, + "loss": 3.8858, + "step": 1731584 + }, + { + "epoch": 0.02, + "learning_rate": 2.164059270304639e-05, + "loss": 3.8924, + "step": 1732096 + }, + { + "epoch": 0.02, + "learning_rate": 2.1632223134339604e-05, + "loss": 3.8691, + "step": 1732608 + }, + { + "epoch": 0.02, + "learning_rate": 2.1623837186829084e-05, + "loss": 3.8913, + "step": 1733120 + }, + { + "epoch": 0.02, + "learning_rate": 2.1615451239318564e-05, + "loss": 3.8754, + "step": 1733632 + }, + { + "epoch": 0.02, + "learning_rate": 2.1607065291808044e-05, + "loss": 3.8936, + "step": 1734144 + }, + { + "epoch": 0.02, + "learning_rate": 2.1598679344297524e-05, + "loss": 3.8799, + "step": 1734656 + }, + { + "epoch": 0.02, + "learning_rate": 2.1590293396787004e-05, + "loss": 3.8929, + "step": 1735168 + }, + { + "epoch": 0.02, + "learning_rate": 2.1581923828080216e-05, + "loss": 3.8844, + "step": 1735680 + }, + { + "epoch": 0.02, + "learning_rate": 2.1573537880569693e-05, + "loss": 3.8887, + "step": 1736192 + }, + { + "epoch": 0.02, + "learning_rate": 2.1565151933059176e-05, + "loss": 3.8975, + "step": 1736704 + }, + { + "epoch": 0.02, + "learning_rate": 2.1556765985548656e-05, + "loss": 3.885, + "step": 1737216 + }, + { + "epoch": 0.02, + "learning_rate": 2.1548380038038136e-05, + "loss": 3.901, + "step": 1737728 + }, + { + "epoch": 0.02, + "learning_rate": 2.1539994090527616e-05, + "loss": 3.9076, + "step": 1738240 + }, + { + "epoch": 0.02, + "learning_rate": 2.1531624521820825e-05, + "loss": 3.8912, + "step": 1738752 + }, + { + "epoch": 0.02, + "learning_rate": 2.1523238574310305e-05, + "loss": 3.8905, + "step": 1739264 + }, + { + "epoch": 0.02, + "learning_rate": 2.1514852626799785e-05, + "loss": 3.8844, + "step": 1739776 + }, + { + "epoch": 0.02, + "learning_rate": 2.1506466679289268e-05, + "loss": 3.8939, + "step": 1740288 + }, + { + "epoch": 0.02, + "learning_rate": 2.1498080731778748e-05, + "loss": 3.8865, + "step": 1740800 + }, + { + "epoch": 0.02, + "learning_rate": 2.1489711163071957e-05, + "loss": 3.9052, + "step": 1741312 + }, + { + "epoch": 0.02, + "learning_rate": 2.1481325215561437e-05, + "loss": 3.8791, + "step": 1741824 + }, + { + "epoch": 0.02, + "learning_rate": 2.1472939268050917e-05, + "loss": 3.8996, + "step": 1742336 + }, + { + "epoch": 0.02, + "learning_rate": 2.1464553320540394e-05, + "loss": 3.8961, + "step": 1742848 + }, + { + "epoch": 0.02, + "learning_rate": 2.145618375183361e-05, + "loss": 3.8923, + "step": 1743360 + }, + { + "epoch": 0.02, + "learning_rate": 2.144779780432309e-05, + "loss": 3.8815, + "step": 1743872 + }, + { + "epoch": 0.02, + "learning_rate": 2.14394282356163e-05, + "loss": 3.8935, + "step": 1744384 + }, + { + "epoch": 0.02, + "learning_rate": 2.143104228810578e-05, + "loss": 3.8835, + "step": 1744896 + }, + { + "epoch": 0.02, + "learning_rate": 2.142265634059526e-05, + "loss": 3.9058, + "step": 1745408 + }, + { + "epoch": 0.02, + "learning_rate": 2.141427039308474e-05, + "loss": 3.8892, + "step": 1745920 + }, + { + "epoch": 0.02, + "learning_rate": 2.140588444557422e-05, + "loss": 3.8992, + "step": 1746432 + }, + { + "epoch": 0.02, + "learning_rate": 2.13974984980637e-05, + "loss": 3.8789, + "step": 1746944 + }, + { + "epoch": 0.02, + "learning_rate": 2.138911255055318e-05, + "loss": 3.9045, + "step": 1747456 + }, + { + "epoch": 0.02, + "learning_rate": 2.138072660304266e-05, + "loss": 3.8937, + "step": 1747968 + }, + { + "epoch": 0.02, + "learning_rate": 2.137234065553214e-05, + "loss": 3.8974, + "step": 1748480 + }, + { + "epoch": 0.02, + "learning_rate": 2.136395470802162e-05, + "loss": 3.8925, + "step": 1748992 + }, + { + "epoch": 0.02, + "learning_rate": 2.13555687605111e-05, + "loss": 3.8942, + "step": 1749504 + }, + { + "epoch": 0.02, + "learning_rate": 2.1347182813000578e-05, + "loss": 3.8967, + "step": 1750016 + }, + { + "epoch": 0.02, + "learning_rate": 2.133882962309752e-05, + "loss": 3.909, + "step": 1750528 + }, + { + "epoch": 0.02, + "learning_rate": 2.1330443675587e-05, + "loss": 3.8767, + "step": 1751040 + }, + { + "epoch": 0.02, + "learning_rate": 2.132205772807648e-05, + "loss": 3.8915, + "step": 1751552 + }, + { + "epoch": 0.02, + "learning_rate": 2.131367178056596e-05, + "loss": 3.8882, + "step": 1752064 + }, + { + "epoch": 0.02, + "learning_rate": 2.130528583305544e-05, + "loss": 3.8912, + "step": 1752576 + }, + { + "epoch": 0.02, + "learning_rate": 2.1296916264348652e-05, + "loss": 3.8874, + "step": 1753088 + }, + { + "epoch": 0.02, + "learning_rate": 2.1288530316838132e-05, + "loss": 3.8954, + "step": 1753600 + }, + { + "epoch": 0.02, + "learning_rate": 2.1280144369327612e-05, + "loss": 3.8946, + "step": 1754112 + }, + { + "epoch": 0.02, + "learning_rate": 2.1271758421817092e-05, + "loss": 3.8825, + "step": 1754624 + }, + { + "epoch": 0.02, + "learning_rate": 2.1263372474306572e-05, + "loss": 3.9003, + "step": 1755136 + }, + { + "epoch": 0.03, + "eval_loss": 3.989001989364624, + "eval_runtime": 306.2095, + "eval_samples_per_second": 1246.176, + "eval_steps_per_second": 38.944, + "step": 1755360 + }, + { + "epoch": 1.0, + "learning_rate": 2.125498652679605e-05, + "loss": 3.8886, + "step": 1755648 + }, + { + "epoch": 1.0, + "learning_rate": 2.1246600579285532e-05, + "loss": 3.8818, + "step": 1756160 + }, + { + "epoch": 1.0, + "learning_rate": 2.1238231010578744e-05, + "loss": 3.8974, + "step": 1756672 + }, + { + "epoch": 1.0, + "learning_rate": 2.1229861441871954e-05, + "loss": 3.8865, + "step": 1757184 + }, + { + "epoch": 1.0, + "learning_rate": 2.1221475494361433e-05, + "loss": 3.8919, + "step": 1757696 + }, + { + "epoch": 1.0, + "learning_rate": 2.1213089546850913e-05, + "loss": 3.8884, + "step": 1758208 + }, + { + "epoch": 1.0, + "learning_rate": 2.1204703599340393e-05, + "loss": 3.8898, + "step": 1758720 + }, + { + "epoch": 1.0, + "learning_rate": 2.1196317651829877e-05, + "loss": 3.8816, + "step": 1759232 + }, + { + "epoch": 1.0, + "learning_rate": 2.1187948083123086e-05, + "loss": 3.8922, + "step": 1759744 + }, + { + "epoch": 1.0, + "learning_rate": 2.1179562135612566e-05, + "loss": 3.8848, + "step": 1760256 + }, + { + "epoch": 1.0, + "learning_rate": 2.1171176188102046e-05, + "loss": 3.895, + "step": 1760768 + }, + { + "epoch": 1.0, + "learning_rate": 2.1162790240591522e-05, + "loss": 3.896, + "step": 1761280 + }, + { + "epoch": 1.0, + "learning_rate": 2.1154420671884738e-05, + "loss": 3.8903, + "step": 1761792 + }, + { + "epoch": 1.0, + "learning_rate": 2.1146034724374218e-05, + "loss": 3.888, + "step": 1762304 + }, + { + "epoch": 1.0, + "learning_rate": 2.1137648776863698e-05, + "loss": 3.8882, + "step": 1762816 + }, + { + "epoch": 1.0, + "learning_rate": 2.1129262829353175e-05, + "loss": 3.882, + "step": 1763328 + }, + { + "epoch": 1.0, + "learning_rate": 2.1120876881842655e-05, + "loss": 3.8784, + "step": 1763840 + }, + { + "epoch": 1.0, + "learning_rate": 2.1112490934332135e-05, + "loss": 3.8861, + "step": 1764352 + }, + { + "epoch": 1.0, + "learning_rate": 2.1104121365625347e-05, + "loss": 3.888, + "step": 1764864 + }, + { + "epoch": 1.0, + "learning_rate": 2.1095735418114827e-05, + "loss": 3.8954, + "step": 1765376 + }, + { + "epoch": 1.0, + "learning_rate": 2.1087349470604307e-05, + "loss": 3.8983, + "step": 1765888 + }, + { + "epoch": 1.0, + "learning_rate": 2.1078963523093787e-05, + "loss": 3.8942, + "step": 1766400 + }, + { + "epoch": 1.0, + "learning_rate": 2.1070593954386996e-05, + "loss": 3.8986, + "step": 1766912 + }, + { + "epoch": 1.0, + "learning_rate": 2.1062208006876476e-05, + "loss": 3.8989, + "step": 1767424 + }, + { + "epoch": 1.0, + "learning_rate": 2.1053822059365956e-05, + "loss": 3.8809, + "step": 1767936 + }, + { + "epoch": 1.0, + "learning_rate": 2.104543611185544e-05, + "loss": 3.8972, + "step": 1768448 + }, + { + "epoch": 1.0, + "learning_rate": 2.103705016434492e-05, + "loss": 3.8826, + "step": 1768960 + }, + { + "epoch": 1.0, + "learning_rate": 2.10286642168344e-05, + "loss": 3.8865, + "step": 1769472 + }, + { + "epoch": 1.0, + "learning_rate": 2.102027826932388e-05, + "loss": 3.8837, + "step": 1769984 + }, + { + "epoch": 1.0, + "learning_rate": 2.1011892321813356e-05, + "loss": 3.8861, + "step": 1770496 + }, + { + "epoch": 1.01, + "learning_rate": 2.1003522753106568e-05, + "loss": 3.8907, + "step": 1771008 + }, + { + "epoch": 1.01, + "learning_rate": 2.099515318439978e-05, + "loss": 3.8951, + "step": 1771520 + }, + { + "epoch": 1.01, + "learning_rate": 2.0986783615692993e-05, + "loss": 3.8888, + "step": 1772032 + }, + { + "epoch": 1.01, + "learning_rate": 2.097839766818247e-05, + "loss": 3.8947, + "step": 1772544 + }, + { + "epoch": 1.01, + "learning_rate": 2.0970028099475682e-05, + "loss": 3.8835, + "step": 1773056 + }, + { + "epoch": 1.01, + "learning_rate": 2.0961642151965162e-05, + "loss": 3.8941, + "step": 1773568 + }, + { + "epoch": 1.01, + "learning_rate": 2.0953256204454642e-05, + "loss": 3.8902, + "step": 1774080 + }, + { + "epoch": 1.01, + "learning_rate": 2.0944870256944122e-05, + "loss": 3.8765, + "step": 1774592 + }, + { + "epoch": 1.01, + "learning_rate": 2.0936484309433602e-05, + "loss": 3.8798, + "step": 1775104 + }, + { + "epoch": 1.01, + "learning_rate": 2.0928098361923082e-05, + "loss": 3.8818, + "step": 1775616 + }, + { + "epoch": 1.01, + "learning_rate": 2.0919712414412562e-05, + "loss": 3.8881, + "step": 1776128 + }, + { + "epoch": 1.01, + "learning_rate": 2.0911326466902042e-05, + "loss": 3.8926, + "step": 1776640 + }, + { + "epoch": 1.01, + "learning_rate": 2.0902940519391522e-05, + "loss": 3.8909, + "step": 1777152 + }, + { + "epoch": 1.01, + "learning_rate": 2.0894554571881002e-05, + "loss": 3.8839, + "step": 1777664 + }, + { + "epoch": 1.01, + "learning_rate": 2.0886168624370482e-05, + "loss": 3.9004, + "step": 1778176 + }, + { + "epoch": 1.01, + "learning_rate": 2.0877782676859962e-05, + "loss": 3.8887, + "step": 1778688 + }, + { + "epoch": 1.01, + "learning_rate": 2.086939672934944e-05, + "loss": 3.896, + "step": 1779200 + }, + { + "epoch": 1.01, + "learning_rate": 2.086101078183892e-05, + "loss": 3.8812, + "step": 1779712 + }, + { + "epoch": 1.01, + "learning_rate": 2.08526248343284e-05, + "loss": 3.8641, + "step": 1780224 + }, + { + "epoch": 1.01, + "learning_rate": 2.084423888681788e-05, + "loss": 3.9022, + "step": 1780736 + }, + { + "epoch": 1.01, + "learning_rate": 2.083585293930736e-05, + "loss": 3.8867, + "step": 1781248 + }, + { + "epoch": 1.01, + "learning_rate": 2.0827483370600574e-05, + "loss": 3.8871, + "step": 1781760 + }, + { + "epoch": 1.01, + "learning_rate": 2.0819097423090054e-05, + "loss": 3.8806, + "step": 1782272 + }, + { + "epoch": 1.01, + "learning_rate": 2.0810711475579534e-05, + "loss": 3.8798, + "step": 1782784 + }, + { + "epoch": 1.01, + "learning_rate": 2.080232552806901e-05, + "loss": 3.8818, + "step": 1783296 + }, + { + "epoch": 1.01, + "learning_rate": 2.0793955959362223e-05, + "loss": 3.8738, + "step": 1783808 + }, + { + "epoch": 1.01, + "learning_rate": 2.0785570011851703e-05, + "loss": 3.8854, + "step": 1784320 + }, + { + "epoch": 1.01, + "learning_rate": 2.0777184064341183e-05, + "loss": 3.8827, + "step": 1784832 + }, + { + "epoch": 1.01, + "learning_rate": 2.0768814495634395e-05, + "loss": 3.8982, + "step": 1785344 + }, + { + "epoch": 1.01, + "learning_rate": 2.0760428548123875e-05, + "loss": 3.8761, + "step": 1785856 + }, + { + "epoch": 1.01, + "learning_rate": 2.0752042600613355e-05, + "loss": 3.8754, + "step": 1786368 + }, + { + "epoch": 1.01, + "learning_rate": 2.0743656653102832e-05, + "loss": 3.8976, + "step": 1786880 + }, + { + "epoch": 1.01, + "learning_rate": 2.0735270705592312e-05, + "loss": 3.8705, + "step": 1787392 + }, + { + "epoch": 1.01, + "learning_rate": 2.0726901136885528e-05, + "loss": 3.8765, + "step": 1787904 + }, + { + "epoch": 1.01, + "learning_rate": 2.0718515189375008e-05, + "loss": 3.8889, + "step": 1788416 + }, + { + "epoch": 1.01, + "learning_rate": 2.0710129241864484e-05, + "loss": 3.8944, + "step": 1788928 + }, + { + "epoch": 1.01, + "learning_rate": 2.0701743294353964e-05, + "loss": 3.8791, + "step": 1789440 + }, + { + "epoch": 1.01, + "learning_rate": 2.0693357346843444e-05, + "loss": 3.874, + "step": 1789952 + }, + { + "epoch": 1.01, + "learning_rate": 2.0684971399332924e-05, + "loss": 3.8703, + "step": 1790464 + }, + { + "epoch": 1.01, + "learning_rate": 2.0676585451822404e-05, + "loss": 3.8842, + "step": 1790976 + }, + { + "epoch": 1.01, + "learning_rate": 2.0668199504311887e-05, + "loss": 3.901, + "step": 1791488 + }, + { + "epoch": 1.01, + "learning_rate": 2.0659829935605096e-05, + "loss": 3.8861, + "step": 1792000 + }, + { + "epoch": 1.01, + "learning_rate": 2.0651460366898306e-05, + "loss": 3.8851, + "step": 1792512 + }, + { + "epoch": 1.01, + "learning_rate": 2.0643074419387785e-05, + "loss": 3.8966, + "step": 1793024 + }, + { + "epoch": 1.01, + "learning_rate": 2.0634688471877265e-05, + "loss": 3.9007, + "step": 1793536 + }, + { + "epoch": 1.01, + "learning_rate": 2.062631890317048e-05, + "loss": 3.8749, + "step": 1794048 + }, + { + "epoch": 1.01, + "learning_rate": 2.0617932955659958e-05, + "loss": 3.894, + "step": 1794560 + }, + { + "epoch": 1.01, + "learning_rate": 2.0609547008149438e-05, + "loss": 3.8836, + "step": 1795072 + }, + { + "epoch": 1.01, + "learning_rate": 2.0601161060638918e-05, + "loss": 3.8806, + "step": 1795584 + }, + { + "epoch": 1.01, + "learning_rate": 2.0592775113128398e-05, + "loss": 3.8843, + "step": 1796096 + }, + { + "epoch": 1.01, + "learning_rate": 2.0584389165617878e-05, + "loss": 3.8936, + "step": 1796608 + }, + { + "epoch": 1.01, + "learning_rate": 2.0576003218107358e-05, + "loss": 3.8871, + "step": 1797120 + }, + { + "epoch": 1.01, + "learning_rate": 2.0567617270596838e-05, + "loss": 3.8942, + "step": 1797632 + }, + { + "epoch": 1.01, + "learning_rate": 2.0559231323086318e-05, + "loss": 3.8842, + "step": 1798144 + }, + { + "epoch": 1.01, + "learning_rate": 2.0550845375575798e-05, + "loss": 3.8788, + "step": 1798656 + }, + { + "epoch": 1.01, + "learning_rate": 2.054247580686901e-05, + "loss": 3.8897, + "step": 1799168 + }, + { + "epoch": 1.01, + "learning_rate": 2.0534089859358487e-05, + "loss": 3.8875, + "step": 1799680 + }, + { + "epoch": 1.01, + "learning_rate": 2.0525720290651702e-05, + "loss": 3.8828, + "step": 1800192 + }, + { + "epoch": 1.01, + "learning_rate": 2.051735072194491e-05, + "loss": 3.8819, + "step": 1800704 + }, + { + "epoch": 1.02, + "learning_rate": 2.050896477443439e-05, + "loss": 3.8845, + "step": 1801216 + }, + { + "epoch": 1.02, + "learning_rate": 2.050057882692387e-05, + "loss": 3.8909, + "step": 1801728 + }, + { + "epoch": 1.02, + "learning_rate": 2.049219287941335e-05, + "loss": 3.8844, + "step": 1802240 + }, + { + "epoch": 1.02, + "learning_rate": 2.048380693190283e-05, + "loss": 3.8748, + "step": 1802752 + }, + { + "epoch": 1.02, + "learning_rate": 2.047542098439231e-05, + "loss": 3.8956, + "step": 1803264 + }, + { + "epoch": 1.02, + "learning_rate": 2.046703503688179e-05, + "loss": 3.8914, + "step": 1803776 + }, + { + "epoch": 1.02, + "learning_rate": 2.045864908937127e-05, + "loss": 3.888, + "step": 1804288 + }, + { + "epoch": 1.02, + "learning_rate": 2.045026314186075e-05, + "loss": 3.8767, + "step": 1804800 + }, + { + "epoch": 1.02, + "learning_rate": 2.044187719435023e-05, + "loss": 3.8841, + "step": 1805312 + }, + { + "epoch": 1.02, + "learning_rate": 2.043349124683971e-05, + "loss": 3.8782, + "step": 1805824 + }, + { + "epoch": 1.02, + "learning_rate": 2.042510529932919e-05, + "loss": 3.8889, + "step": 1806336 + }, + { + "epoch": 1.02, + "learning_rate": 2.041671935181867e-05, + "loss": 3.896, + "step": 1806848 + }, + { + "epoch": 1.02, + "learning_rate": 2.040833340430815e-05, + "loss": 3.8841, + "step": 1807360 + }, + { + "epoch": 1.02, + "learning_rate": 2.039994745679763e-05, + "loss": 3.8826, + "step": 1807872 + }, + { + "epoch": 1.02, + "learning_rate": 2.039156150928711e-05, + "loss": 3.8811, + "step": 1808384 + }, + { + "epoch": 1.02, + "learning_rate": 2.038319194058032e-05, + "loss": 3.8685, + "step": 1808896 + }, + { + "epoch": 1.02, + "learning_rate": 2.03748059930698e-05, + "loss": 3.8814, + "step": 1809408 + }, + { + "epoch": 1.02, + "learning_rate": 2.036642004555928e-05, + "loss": 3.8712, + "step": 1809920 + }, + { + "epoch": 1.02, + "learning_rate": 2.0358034098048763e-05, + "loss": 3.8892, + "step": 1810432 + }, + { + "epoch": 1.02, + "learning_rate": 2.0349664529341972e-05, + "loss": 3.8736, + "step": 1810944 + }, + { + "epoch": 1.02, + "learning_rate": 2.0341278581831452e-05, + "loss": 3.885, + "step": 1811456 + }, + { + "epoch": 1.02, + "learning_rate": 2.0332909013124665e-05, + "loss": 3.8787, + "step": 1811968 + }, + { + "epoch": 1.02, + "learning_rate": 2.032452306561414e-05, + "loss": 3.8878, + "step": 1812480 + }, + { + "epoch": 1.02, + "learning_rate": 2.0316137118103625e-05, + "loss": 3.8877, + "step": 1812992 + }, + { + "epoch": 1.02, + "learning_rate": 2.0307751170593105e-05, + "loss": 3.8804, + "step": 1813504 + }, + { + "epoch": 1.02, + "learning_rate": 2.0299365223082585e-05, + "loss": 3.8963, + "step": 1814016 + }, + { + "epoch": 1.02, + "learning_rate": 2.0290979275572065e-05, + "loss": 3.8985, + "step": 1814528 + }, + { + "epoch": 1.02, + "learning_rate": 2.0282593328061545e-05, + "loss": 3.8837, + "step": 1815040 + }, + { + "epoch": 1.02, + "learning_rate": 2.027420738055102e-05, + "loss": 3.8883, + "step": 1815552 + }, + { + "epoch": 1.02, + "learning_rate": 2.0265837811844234e-05, + "loss": 3.8772, + "step": 1816064 + }, + { + "epoch": 1.02, + "learning_rate": 2.0257468243137446e-05, + "loss": 3.8873, + "step": 1816576 + }, + { + "epoch": 1.02, + "learning_rate": 2.0249082295626926e-05, + "loss": 3.8842, + "step": 1817088 + }, + { + "epoch": 1.02, + "learning_rate": 2.0240696348116406e-05, + "loss": 3.8922, + "step": 1817600 + }, + { + "epoch": 1.02, + "learning_rate": 2.0232310400605886e-05, + "loss": 3.8763, + "step": 1818112 + }, + { + "epoch": 1.02, + "learning_rate": 2.0223924453095366e-05, + "loss": 3.8937, + "step": 1818624 + }, + { + "epoch": 1.02, + "learning_rate": 2.021555488438858e-05, + "loss": 3.8914, + "step": 1819136 + }, + { + "epoch": 1.02, + "learning_rate": 2.0207185315681787e-05, + "loss": 3.8847, + "step": 1819648 + }, + { + "epoch": 1.02, + "learning_rate": 2.0198799368171267e-05, + "loss": 3.8724, + "step": 1820160 + }, + { + "epoch": 1.02, + "learning_rate": 2.0190413420660747e-05, + "loss": 3.888, + "step": 1820672 + }, + { + "epoch": 1.02, + "learning_rate": 2.0182027473150227e-05, + "loss": 3.8792, + "step": 1821184 + }, + { + "epoch": 1.02, + "learning_rate": 2.0173641525639707e-05, + "loss": 3.8961, + "step": 1821696 + }, + { + "epoch": 1.02, + "learning_rate": 2.0165255578129187e-05, + "loss": 3.8874, + "step": 1822208 + }, + { + "epoch": 1.02, + "learning_rate": 2.0156869630618667e-05, + "loss": 3.8907, + "step": 1822720 + }, + { + "epoch": 1.02, + "learning_rate": 2.0148483683108147e-05, + "loss": 3.8713, + "step": 1823232 + }, + { + "epoch": 1.02, + "learning_rate": 2.014011411440136e-05, + "loss": 3.9023, + "step": 1823744 + }, + { + "epoch": 1.02, + "learning_rate": 2.013172816689084e-05, + "loss": 3.8828, + "step": 1824256 + }, + { + "epoch": 1.02, + "learning_rate": 2.012334221938032e-05, + "loss": 3.8903, + "step": 1824768 + }, + { + "epoch": 1.02, + "learning_rate": 2.0114956271869796e-05, + "loss": 3.887, + "step": 1825280 + }, + { + "epoch": 1.02, + "learning_rate": 2.010657032435928e-05, + "loss": 3.8855, + "step": 1825792 + }, + { + "epoch": 1.02, + "learning_rate": 2.0098200755652492e-05, + "loss": 3.8916, + "step": 1826304 + }, + { + "epoch": 1.02, + "learning_rate": 2.008981480814197e-05, + "loss": 3.9007, + "step": 1826816 + }, + { + "epoch": 1.02, + "learning_rate": 2.008142886063145e-05, + "loss": 3.8731, + "step": 1827328 + }, + { + "epoch": 1.02, + "learning_rate": 2.007304291312093e-05, + "loss": 3.8867, + "step": 1827840 + }, + { + "epoch": 1.02, + "learning_rate": 2.006465696561041e-05, + "loss": 3.8818, + "step": 1828352 + }, + { + "epoch": 1.02, + "learning_rate": 2.005627101809989e-05, + "loss": 3.8832, + "step": 1828864 + }, + { + "epoch": 1.02, + "learning_rate": 2.004788507058937e-05, + "loss": 3.8807, + "step": 1829376 + }, + { + "epoch": 1.02, + "learning_rate": 2.003949912307885e-05, + "loss": 3.8903, + "step": 1829888 + }, + { + "epoch": 1.02, + "learning_rate": 2.0031145933175793e-05, + "loss": 3.8893, + "step": 1830400 + }, + { + "epoch": 1.02, + "learning_rate": 2.002275998566527e-05, + "loss": 3.8761, + "step": 1830912 + }, + { + "epoch": 1.02, + "learning_rate": 2.001437403815475e-05, + "loss": 3.8927, + "step": 1831424 + }, + { + "epoch": 1.03, + "eval_loss": 3.9870405197143555, + "eval_runtime": 321.7049, + "eval_samples_per_second": 1186.152, + "eval_steps_per_second": 37.068, + "step": 1831680 + }, + { + "epoch": 0.0, + "learning_rate": 2.0005988090644233e-05, + "loss": 3.8804, + "step": 1831936 + }, + { + "epoch": 0.0, + "learning_rate": 1.9997602143133713e-05, + "loss": 3.8793, + "step": 1832448 + }, + { + "epoch": 0.0, + "learning_rate": 1.9989216195623193e-05, + "loss": 3.8868, + "step": 1832960 + }, + { + "epoch": 0.0, + "learning_rate": 1.9980830248112673e-05, + "loss": 3.8804, + "step": 1833472 + }, + { + "epoch": 0.0, + "learning_rate": 1.997244430060215e-05, + "loss": 3.8899, + "step": 1833984 + }, + { + "epoch": 0.0, + "learning_rate": 1.996405835309163e-05, + "loss": 3.8761, + "step": 1834496 + }, + { + "epoch": 0.0, + "learning_rate": 1.995567240558111e-05, + "loss": 3.8911, + "step": 1835008 + }, + { + "epoch": 0.0, + "learning_rate": 1.994728645807059e-05, + "loss": 3.8757, + "step": 1835520 + }, + { + "epoch": 0.0, + "learning_rate": 1.9938900510560073e-05, + "loss": 3.8864, + "step": 1836032 + }, + { + "epoch": 0.0, + "learning_rate": 1.9930514563049553e-05, + "loss": 3.8805, + "step": 1836544 + }, + { + "epoch": 0.0, + "learning_rate": 1.9922128615539033e-05, + "loss": 3.886, + "step": 1837056 + }, + { + "epoch": 0.0, + "learning_rate": 1.991374266802851e-05, + "loss": 3.8935, + "step": 1837568 + }, + { + "epoch": 0.0, + "learning_rate": 1.9905373099321722e-05, + "loss": 3.8815, + "step": 1838080 + }, + { + "epoch": 0.0, + "learning_rate": 1.98969871518112e-05, + "loss": 3.8842, + "step": 1838592 + }, + { + "epoch": 0.0, + "learning_rate": 1.988860120430068e-05, + "loss": 3.884, + "step": 1839104 + }, + { + "epoch": 0.0, + "learning_rate": 1.988021525679016e-05, + "loss": 3.8748, + "step": 1839616 + }, + { + "epoch": 0.0, + "learning_rate": 1.987182930927964e-05, + "loss": 3.8738, + "step": 1840128 + }, + { + "epoch": 0.0, + "learning_rate": 1.986344336176912e-05, + "loss": 3.8811, + "step": 1840640 + }, + { + "epoch": 0.0, + "learning_rate": 1.98550574142586e-05, + "loss": 3.8821, + "step": 1841152 + }, + { + "epoch": 0.0, + "learning_rate": 1.984667146674808e-05, + "loss": 3.8846, + "step": 1841664 + }, + { + "epoch": 0.0, + "learning_rate": 1.983828551923756e-05, + "loss": 3.8931, + "step": 1842176 + }, + { + "epoch": 0.0, + "learning_rate": 1.982989957172704e-05, + "loss": 3.8904, + "step": 1842688 + }, + { + "epoch": 0.0, + "learning_rate": 1.982151362421652e-05, + "loss": 3.892, + "step": 1843200 + }, + { + "epoch": 0.0, + "learning_rate": 1.9813127676706e-05, + "loss": 3.8926, + "step": 1843712 + }, + { + "epoch": 0.0, + "learning_rate": 1.980474172919548e-05, + "loss": 3.8768, + "step": 1844224 + }, + { + "epoch": 0.0, + "learning_rate": 1.979637216048869e-05, + "loss": 3.8893, + "step": 1844736 + }, + { + "epoch": 0.0, + "learning_rate": 1.978798621297817e-05, + "loss": 3.8758, + "step": 1845248 + }, + { + "epoch": 0.0, + "learning_rate": 1.9779616644271383e-05, + "loss": 3.8823, + "step": 1845760 + }, + { + "epoch": 0.0, + "learning_rate": 1.9771230696760866e-05, + "loss": 3.8821, + "step": 1846272 + }, + { + "epoch": 0.0, + "learning_rate": 1.9762844749250343e-05, + "loss": 3.8775, + "step": 1846784 + }, + { + "epoch": 0.01, + "learning_rate": 1.9754458801739823e-05, + "loss": 3.883, + "step": 1847296 + }, + { + "epoch": 0.01, + "learning_rate": 1.9746089233033035e-05, + "loss": 3.8861, + "step": 1847808 + }, + { + "epoch": 0.01, + "learning_rate": 1.973770328552251e-05, + "loss": 3.8834, + "step": 1848320 + }, + { + "epoch": 0.01, + "learning_rate": 1.9729317338011995e-05, + "loss": 3.8871, + "step": 1848832 + }, + { + "epoch": 0.01, + "learning_rate": 1.9720947769305207e-05, + "loss": 3.8784, + "step": 1849344 + }, + { + "epoch": 0.01, + "learning_rate": 1.9712561821794687e-05, + "loss": 3.8878, + "step": 1849856 + }, + { + "epoch": 0.01, + "learning_rate": 1.9704175874284164e-05, + "loss": 3.885, + "step": 1850368 + }, + { + "epoch": 0.01, + "learning_rate": 1.9695789926773644e-05, + "loss": 3.8721, + "step": 1850880 + }, + { + "epoch": 0.01, + "learning_rate": 1.9687403979263124e-05, + "loss": 3.8769, + "step": 1851392 + }, + { + "epoch": 0.01, + "learning_rate": 1.9679018031752604e-05, + "loss": 3.8715, + "step": 1851904 + }, + { + "epoch": 0.01, + "learning_rate": 1.9670632084242084e-05, + "loss": 3.8824, + "step": 1852416 + }, + { + "epoch": 0.01, + "learning_rate": 1.9662246136731567e-05, + "loss": 3.8872, + "step": 1852928 + }, + { + "epoch": 0.01, + "learning_rate": 1.9653860189221044e-05, + "loss": 3.8853, + "step": 1853440 + }, + { + "epoch": 0.01, + "learning_rate": 1.9645474241710524e-05, + "loss": 3.8807, + "step": 1853952 + }, + { + "epoch": 0.01, + "learning_rate": 1.9637088294200004e-05, + "loss": 3.8922, + "step": 1854464 + }, + { + "epoch": 0.01, + "learning_rate": 1.9628702346689484e-05, + "loss": 3.8832, + "step": 1854976 + }, + { + "epoch": 0.01, + "learning_rate": 1.9620332777982696e-05, + "loss": 3.89, + "step": 1855488 + }, + { + "epoch": 0.01, + "learning_rate": 1.961196320927591e-05, + "loss": 3.8785, + "step": 1856000 + }, + { + "epoch": 0.01, + "learning_rate": 1.960357726176539e-05, + "loss": 3.8524, + "step": 1856512 + }, + { + "epoch": 0.01, + "learning_rate": 1.959519131425487e-05, + "loss": 3.901, + "step": 1857024 + }, + { + "epoch": 0.01, + "learning_rate": 1.9586805366744345e-05, + "loss": 3.8762, + "step": 1857536 + }, + { + "epoch": 0.01, + "learning_rate": 1.9578419419233825e-05, + "loss": 3.884, + "step": 1858048 + }, + { + "epoch": 0.01, + "learning_rate": 1.9570033471723305e-05, + "loss": 3.8752, + "step": 1858560 + }, + { + "epoch": 0.01, + "learning_rate": 1.9561663903016517e-05, + "loss": 3.8749, + "step": 1859072 + }, + { + "epoch": 0.01, + "learning_rate": 1.9553277955505997e-05, + "loss": 3.8713, + "step": 1859584 + }, + { + "epoch": 0.01, + "learning_rate": 1.954490838679921e-05, + "loss": 3.8676, + "step": 1860096 + }, + { + "epoch": 0.01, + "learning_rate": 1.953652243928869e-05, + "loss": 3.8808, + "step": 1860608 + }, + { + "epoch": 0.01, + "learning_rate": 1.9528136491778166e-05, + "loss": 3.8752, + "step": 1861120 + }, + { + "epoch": 0.01, + "learning_rate": 1.951975054426765e-05, + "loss": 3.8937, + "step": 1861632 + }, + { + "epoch": 0.01, + "learning_rate": 1.951136459675713e-05, + "loss": 3.8732, + "step": 1862144 + }, + { + "epoch": 0.01, + "learning_rate": 1.950297864924661e-05, + "loss": 3.8685, + "step": 1862656 + }, + { + "epoch": 0.01, + "learning_rate": 1.949459270173609e-05, + "loss": 3.8899, + "step": 1863168 + }, + { + "epoch": 0.01, + "learning_rate": 1.948620675422557e-05, + "loss": 3.8674, + "step": 1863680 + }, + { + "epoch": 0.01, + "learning_rate": 1.947782080671505e-05, + "loss": 3.8707, + "step": 1864192 + }, + { + "epoch": 0.01, + "learning_rate": 1.9469434859204526e-05, + "loss": 3.886, + "step": 1864704 + }, + { + "epoch": 0.01, + "learning_rate": 1.9461065290497742e-05, + "loss": 3.8869, + "step": 1865216 + }, + { + "epoch": 0.01, + "learning_rate": 1.9452679342987222e-05, + "loss": 3.8745, + "step": 1865728 + }, + { + "epoch": 0.01, + "learning_rate": 1.94442933954767e-05, + "loss": 3.8691, + "step": 1866240 + }, + { + "epoch": 0.01, + "learning_rate": 1.943590744796618e-05, + "loss": 3.8628, + "step": 1866752 + }, + { + "epoch": 0.01, + "learning_rate": 1.942753787925939e-05, + "loss": 3.8779, + "step": 1867264 + }, + { + "epoch": 0.01, + "learning_rate": 1.941915193174887e-05, + "loss": 3.8941, + "step": 1867776 + }, + { + "epoch": 0.01, + "learning_rate": 1.941076598423835e-05, + "loss": 3.8781, + "step": 1868288 + }, + { + "epoch": 0.01, + "learning_rate": 1.940238003672783e-05, + "loss": 3.8817, + "step": 1868800 + }, + { + "epoch": 0.01, + "learning_rate": 1.939399408921731e-05, + "loss": 3.8865, + "step": 1869312 + }, + { + "epoch": 0.01, + "learning_rate": 1.9385624520510523e-05, + "loss": 3.8949, + "step": 1869824 + }, + { + "epoch": 0.01, + "learning_rate": 1.9377238573e-05, + "loss": 3.8709, + "step": 1870336 + }, + { + "epoch": 0.01, + "learning_rate": 1.936885262548948e-05, + "loss": 3.886, + "step": 1870848 + }, + { + "epoch": 0.01, + "learning_rate": 1.936046667797896e-05, + "loss": 3.8744, + "step": 1871360 + }, + { + "epoch": 0.01, + "learning_rate": 1.9352080730468443e-05, + "loss": 3.8771, + "step": 1871872 + }, + { + "epoch": 0.01, + "learning_rate": 1.9343694782957923e-05, + "loss": 3.8758, + "step": 1872384 + }, + { + "epoch": 0.01, + "learning_rate": 1.9335325214251132e-05, + "loss": 3.8869, + "step": 1872896 + }, + { + "epoch": 0.01, + "learning_rate": 1.9326939266740612e-05, + "loss": 3.8826, + "step": 1873408 + }, + { + "epoch": 0.01, + "learning_rate": 1.9318553319230092e-05, + "loss": 3.8912, + "step": 1873920 + }, + { + "epoch": 0.01, + "learning_rate": 1.9310167371719572e-05, + "loss": 3.873, + "step": 1874432 + }, + { + "epoch": 0.01, + "learning_rate": 1.9301781424209052e-05, + "loss": 3.8766, + "step": 1874944 + }, + { + "epoch": 0.01, + "learning_rate": 1.9293395476698532e-05, + "loss": 3.8847, + "step": 1875456 + }, + { + "epoch": 0.01, + "learning_rate": 1.9285009529188012e-05, + "loss": 3.88, + "step": 1875968 + }, + { + "epoch": 0.01, + "learning_rate": 1.9276623581677492e-05, + "loss": 3.872, + "step": 1876480 + }, + { + "epoch": 0.01, + "learning_rate": 1.9268254012970704e-05, + "loss": 3.8821, + "step": 1876992 + }, + { + "epoch": 0.02, + "learning_rate": 1.925986806546018e-05, + "loss": 3.8808, + "step": 1877504 + }, + { + "epoch": 0.02, + "learning_rate": 1.925148211794966e-05, + "loss": 3.8864, + "step": 1878016 + }, + { + "epoch": 0.02, + "learning_rate": 1.9243096170439144e-05, + "loss": 3.8776, + "step": 1878528 + }, + { + "epoch": 0.02, + "learning_rate": 1.9234710222928624e-05, + "loss": 3.8687, + "step": 1879040 + }, + { + "epoch": 0.02, + "learning_rate": 1.9226340654221833e-05, + "loss": 3.8897, + "step": 1879552 + }, + { + "epoch": 0.02, + "learning_rate": 1.9217954706711313e-05, + "loss": 3.8856, + "step": 1880064 + }, + { + "epoch": 0.02, + "learning_rate": 1.9209568759200793e-05, + "loss": 3.8806, + "step": 1880576 + }, + { + "epoch": 0.02, + "learning_rate": 1.9201182811690273e-05, + "loss": 3.8736, + "step": 1881088 + }, + { + "epoch": 0.02, + "learning_rate": 1.9192796864179753e-05, + "loss": 3.8758, + "step": 1881600 + }, + { + "epoch": 0.02, + "learning_rate": 1.9184443674276698e-05, + "loss": 3.8723, + "step": 1882112 + }, + { + "epoch": 0.02, + "learning_rate": 1.9176057726766178e-05, + "loss": 3.8843, + "step": 1882624 + }, + { + "epoch": 0.02, + "learning_rate": 1.9167671779255655e-05, + "loss": 3.8909, + "step": 1883136 + }, + { + "epoch": 0.02, + "learning_rate": 1.9159285831745135e-05, + "loss": 3.88, + "step": 1883648 + }, + { + "epoch": 0.02, + "learning_rate": 1.9150899884234614e-05, + "loss": 3.8754, + "step": 1884160 + }, + { + "epoch": 0.02, + "learning_rate": 1.9142530315527827e-05, + "loss": 3.8708, + "step": 1884672 + }, + { + "epoch": 0.02, + "learning_rate": 1.9134144368017307e-05, + "loss": 3.8708, + "step": 1885184 + }, + { + "epoch": 0.02, + "learning_rate": 1.9125758420506787e-05, + "loss": 3.8721, + "step": 1885696 + }, + { + "epoch": 0.02, + "learning_rate": 1.9117372472996267e-05, + "loss": 3.8668, + "step": 1886208 + }, + { + "epoch": 0.02, + "learning_rate": 1.9108986525485747e-05, + "loss": 3.8825, + "step": 1886720 + }, + { + "epoch": 0.02, + "learning_rate": 1.910061695677896e-05, + "loss": 3.87, + "step": 1887232 + }, + { + "epoch": 0.02, + "learning_rate": 1.909223100926844e-05, + "loss": 3.8752, + "step": 1887744 + }, + { + "epoch": 0.02, + "learning_rate": 1.908384506175792e-05, + "loss": 3.8686, + "step": 1888256 + }, + { + "epoch": 0.02, + "learning_rate": 1.90754591142474e-05, + "loss": 3.884, + "step": 1888768 + }, + { + "epoch": 0.02, + "learning_rate": 1.9067089545540608e-05, + "loss": 3.8847, + "step": 1889280 + }, + { + "epoch": 0.02, + "learning_rate": 1.9058703598030088e-05, + "loss": 3.8714, + "step": 1889792 + }, + { + "epoch": 0.02, + "learning_rate": 1.9050317650519568e-05, + "loss": 3.8916, + "step": 1890304 + }, + { + "epoch": 0.02, + "learning_rate": 1.904193170300905e-05, + "loss": 3.8948, + "step": 1890816 + }, + { + "epoch": 0.02, + "learning_rate": 1.903354575549853e-05, + "loss": 3.8799, + "step": 1891328 + }, + { + "epoch": 0.02, + "learning_rate": 1.9025159807988008e-05, + "loss": 3.8804, + "step": 1891840 + }, + { + "epoch": 0.02, + "learning_rate": 1.9016773860477488e-05, + "loss": 3.8717, + "step": 1892352 + }, + { + "epoch": 0.02, + "learning_rate": 1.9008387912966968e-05, + "loss": 3.8758, + "step": 1892864 + }, + { + "epoch": 0.02, + "learning_rate": 1.900001834426018e-05, + "loss": 3.8847, + "step": 1893376 + }, + { + "epoch": 0.02, + "learning_rate": 1.899163239674966e-05, + "loss": 3.884, + "step": 1893888 + }, + { + "epoch": 0.02, + "learning_rate": 1.898324644923914e-05, + "loss": 3.8708, + "step": 1894400 + }, + { + "epoch": 0.02, + "learning_rate": 1.897486050172862e-05, + "loss": 3.8875, + "step": 1894912 + }, + { + "epoch": 0.02, + "learning_rate": 1.8966507311825562e-05, + "loss": 3.8879, + "step": 1895424 + }, + { + "epoch": 0.02, + "learning_rate": 1.8958121364315042e-05, + "loss": 3.8814, + "step": 1895936 + }, + { + "epoch": 0.02, + "learning_rate": 1.8949735416804522e-05, + "loss": 3.8683, + "step": 1896448 + }, + { + "epoch": 0.02, + "learning_rate": 1.8941349469294005e-05, + "loss": 3.8794, + "step": 1896960 + }, + { + "epoch": 0.02, + "learning_rate": 1.8932963521783482e-05, + "loss": 3.8718, + "step": 1897472 + }, + { + "epoch": 0.02, + "learning_rate": 1.892457757427296e-05, + "loss": 3.8903, + "step": 1897984 + }, + { + "epoch": 0.02, + "learning_rate": 1.891619162676244e-05, + "loss": 3.8796, + "step": 1898496 + }, + { + "epoch": 0.02, + "learning_rate": 1.890780567925192e-05, + "loss": 3.887, + "step": 1899008 + }, + { + "epoch": 0.02, + "learning_rate": 1.889943611054513e-05, + "loss": 3.8652, + "step": 1899520 + }, + { + "epoch": 0.02, + "learning_rate": 1.8891050163034614e-05, + "loss": 3.8954, + "step": 1900032 + }, + { + "epoch": 0.02, + "learning_rate": 1.8882664215524094e-05, + "loss": 3.875, + "step": 1900544 + }, + { + "epoch": 0.02, + "learning_rate": 1.8874294646817303e-05, + "loss": 3.8872, + "step": 1901056 + }, + { + "epoch": 0.02, + "learning_rate": 1.8865908699306783e-05, + "loss": 3.8829, + "step": 1901568 + }, + { + "epoch": 0.02, + "learning_rate": 1.8857539130599996e-05, + "loss": 3.8775, + "step": 1902080 + }, + { + "epoch": 0.02, + "learning_rate": 1.8849153183089475e-05, + "loss": 3.8866, + "step": 1902592 + }, + { + "epoch": 0.02, + "learning_rate": 1.8840767235578955e-05, + "loss": 3.8951, + "step": 1903104 + }, + { + "epoch": 0.02, + "learning_rate": 1.8832381288068435e-05, + "loss": 3.8659, + "step": 1903616 + }, + { + "epoch": 0.02, + "learning_rate": 1.8823995340557915e-05, + "loss": 3.8847, + "step": 1904128 + }, + { + "epoch": 0.02, + "learning_rate": 1.8815609393047395e-05, + "loss": 3.8758, + "step": 1904640 + }, + { + "epoch": 0.02, + "learning_rate": 1.8807223445536875e-05, + "loss": 3.8748, + "step": 1905152 + }, + { + "epoch": 0.02, + "learning_rate": 1.8798837498026355e-05, + "loss": 3.8775, + "step": 1905664 + }, + { + "epoch": 0.02, + "learning_rate": 1.8790451550515835e-05, + "loss": 3.8836, + "step": 1906176 + }, + { + "epoch": 0.02, + "learning_rate": 1.8782081981809048e-05, + "loss": 3.8825, + "step": 1906688 + }, + { + "epoch": 0.02, + "learning_rate": 1.8773696034298528e-05, + "loss": 3.8757, + "step": 1907200 + }, + { + "epoch": 0.02, + "learning_rate": 1.8765310086788008e-05, + "loss": 3.8857, + "step": 1907712 + }, + { + "epoch": 0.03, + "eval_loss": 3.9841580390930176, + "eval_runtime": 283.4654, + "eval_samples_per_second": 1346.164, + "eval_steps_per_second": 42.069, + "step": 1908000 + }, + { + "epoch": 1.0, + "learning_rate": 1.8756924139277484e-05, + "loss": 3.8737, + "step": 1908224 + }, + { + "epoch": 1.0, + "learning_rate": 1.8748538191766964e-05, + "loss": 3.8726, + "step": 1908736 + }, + { + "epoch": 1.0, + "learning_rate": 1.8740168623060177e-05, + "loss": 3.8823, + "step": 1909248 + }, + { + "epoch": 1.0, + "learning_rate": 1.873178267554966e-05, + "loss": 3.8757, + "step": 1909760 + }, + { + "epoch": 1.0, + "learning_rate": 1.8723396728039136e-05, + "loss": 3.8817, + "step": 1910272 + }, + { + "epoch": 1.0, + "learning_rate": 1.8715010780528616e-05, + "loss": 3.8717, + "step": 1910784 + }, + { + "epoch": 1.0, + "learning_rate": 1.8706624833018096e-05, + "loss": 3.8829, + "step": 1911296 + }, + { + "epoch": 1.0, + "learning_rate": 1.8698238885507576e-05, + "loss": 3.8714, + "step": 1911808 + }, + { + "epoch": 1.0, + "learning_rate": 1.8689852937997056e-05, + "loss": 3.8753, + "step": 1912320 + }, + { + "epoch": 1.0, + "learning_rate": 1.868148336929027e-05, + "loss": 3.8791, + "step": 1912832 + }, + { + "epoch": 1.0, + "learning_rate": 1.867309742177975e-05, + "loss": 3.8789, + "step": 1913344 + }, + { + "epoch": 1.0, + "learning_rate": 1.866471147426923e-05, + "loss": 3.8861, + "step": 1913856 + }, + { + "epoch": 1.0, + "learning_rate": 1.8656341905562438e-05, + "loss": 3.8879, + "step": 1914368 + }, + { + "epoch": 1.0, + "learning_rate": 1.8647955958051918e-05, + "loss": 3.8709, + "step": 1914880 + }, + { + "epoch": 1.0, + "learning_rate": 1.8639570010541398e-05, + "loss": 3.8774, + "step": 1915392 + }, + { + "epoch": 1.0, + "learning_rate": 1.8631184063030878e-05, + "loss": 3.871, + "step": 1915904 + }, + { + "epoch": 1.0, + "learning_rate": 1.862279811552036e-05, + "loss": 3.8664, + "step": 1916416 + }, + { + "epoch": 1.0, + "learning_rate": 1.861441216800984e-05, + "loss": 3.8762, + "step": 1916928 + }, + { + "epoch": 1.0, + "learning_rate": 1.8606026220499318e-05, + "loss": 3.8718, + "step": 1917440 + }, + { + "epoch": 1.0, + "learning_rate": 1.8597640272988797e-05, + "loss": 3.878, + "step": 1917952 + }, + { + "epoch": 1.0, + "learning_rate": 1.8589254325478277e-05, + "loss": 3.8888, + "step": 1918464 + }, + { + "epoch": 1.0, + "learning_rate": 1.8580868377967757e-05, + "loss": 3.888, + "step": 1918976 + }, + { + "epoch": 1.0, + "learning_rate": 1.8572482430457237e-05, + "loss": 3.8869, + "step": 1919488 + }, + { + "epoch": 1.0, + "learning_rate": 1.856411286175045e-05, + "loss": 3.8851, + "step": 1920000 + }, + { + "epoch": 1.0, + "learning_rate": 1.855572691423993e-05, + "loss": 3.8716, + "step": 1920512 + }, + { + "epoch": 1.0, + "learning_rate": 1.854735734553314e-05, + "loss": 3.8819, + "step": 1921024 + }, + { + "epoch": 1.0, + "learning_rate": 1.853897139802262e-05, + "loss": 3.8701, + "step": 1921536 + }, + { + "epoch": 1.0, + "learning_rate": 1.85305854505121e-05, + "loss": 3.8796, + "step": 1922048 + }, + { + "epoch": 1.0, + "learning_rate": 1.8522199503001582e-05, + "loss": 3.8736, + "step": 1922560 + }, + { + "epoch": 1.0, + "learning_rate": 1.8513813555491062e-05, + "loss": 3.8732, + "step": 1923072 + }, + { + "epoch": 1.01, + "learning_rate": 1.8505427607980542e-05, + "loss": 3.8767, + "step": 1923584 + }, + { + "epoch": 1.01, + "learning_rate": 1.8497041660470022e-05, + "loss": 3.8786, + "step": 1924096 + }, + { + "epoch": 1.01, + "learning_rate": 1.84886557129595e-05, + "loss": 3.8786, + "step": 1924608 + }, + { + "epoch": 1.01, + "learning_rate": 1.848028614425271e-05, + "loss": 3.8771, + "step": 1925120 + }, + { + "epoch": 1.01, + "learning_rate": 1.847190019674219e-05, + "loss": 3.8747, + "step": 1925632 + }, + { + "epoch": 1.01, + "learning_rate": 1.8463530628035403e-05, + "loss": 3.8815, + "step": 1926144 + }, + { + "epoch": 1.01, + "learning_rate": 1.8455144680524883e-05, + "loss": 3.8816, + "step": 1926656 + }, + { + "epoch": 1.01, + "learning_rate": 1.8446758733014363e-05, + "loss": 3.866, + "step": 1927168 + }, + { + "epoch": 1.01, + "learning_rate": 1.8438372785503843e-05, + "loss": 3.8725, + "step": 1927680 + }, + { + "epoch": 1.01, + "learning_rate": 1.842998683799332e-05, + "loss": 3.8672, + "step": 1928192 + }, + { + "epoch": 1.01, + "learning_rate": 1.84216008904828e-05, + "loss": 3.8711, + "step": 1928704 + }, + { + "epoch": 1.01, + "learning_rate": 1.8413214942972283e-05, + "loss": 3.8804, + "step": 1929216 + }, + { + "epoch": 1.01, + "learning_rate": 1.8404845374265496e-05, + "loss": 3.8819, + "step": 1929728 + }, + { + "epoch": 1.01, + "learning_rate": 1.8396459426754972e-05, + "loss": 3.8775, + "step": 1930240 + }, + { + "epoch": 1.01, + "learning_rate": 1.8388073479244452e-05, + "loss": 3.8831, + "step": 1930752 + }, + { + "epoch": 1.01, + "learning_rate": 1.8379687531733932e-05, + "loss": 3.8811, + "step": 1931264 + }, + { + "epoch": 1.01, + "learning_rate": 1.8371301584223412e-05, + "loss": 3.882, + "step": 1931776 + }, + { + "epoch": 1.01, + "learning_rate": 1.8362915636712892e-05, + "loss": 3.8733, + "step": 1932288 + }, + { + "epoch": 1.01, + "learning_rate": 1.8354529689202375e-05, + "loss": 3.8516, + "step": 1932800 + }, + { + "epoch": 1.01, + "learning_rate": 1.8346143741691852e-05, + "loss": 3.8921, + "step": 1933312 + }, + { + "epoch": 1.01, + "learning_rate": 1.8337774172985064e-05, + "loss": 3.8706, + "step": 1933824 + }, + { + "epoch": 1.01, + "learning_rate": 1.8329388225474544e-05, + "loss": 3.8767, + "step": 1934336 + }, + { + "epoch": 1.01, + "learning_rate": 1.8321002277964024e-05, + "loss": 3.874, + "step": 1934848 + }, + { + "epoch": 1.01, + "learning_rate": 1.83126163304535e-05, + "loss": 3.8675, + "step": 1935360 + }, + { + "epoch": 1.01, + "learning_rate": 1.8304246761746717e-05, + "loss": 3.8679, + "step": 1935872 + }, + { + "epoch": 1.01, + "learning_rate": 1.8295860814236197e-05, + "loss": 3.8643, + "step": 1936384 + }, + { + "epoch": 1.01, + "learning_rate": 1.8287474866725677e-05, + "loss": 3.8768, + "step": 1936896 + }, + { + "epoch": 1.01, + "learning_rate": 1.8279105298018886e-05, + "loss": 3.8676, + "step": 1937408 + }, + { + "epoch": 1.01, + "learning_rate": 1.8270719350508366e-05, + "loss": 3.8873, + "step": 1937920 + }, + { + "epoch": 1.01, + "learning_rate": 1.8262333402997846e-05, + "loss": 3.8702, + "step": 1938432 + }, + { + "epoch": 1.01, + "learning_rate": 1.8253947455487326e-05, + "loss": 3.8584, + "step": 1938944 + }, + { + "epoch": 1.01, + "learning_rate": 1.8245561507976806e-05, + "loss": 3.8848, + "step": 1939456 + }, + { + "epoch": 1.01, + "learning_rate": 1.8237175560466286e-05, + "loss": 3.8676, + "step": 1939968 + }, + { + "epoch": 1.01, + "learning_rate": 1.8228789612955766e-05, + "loss": 3.862, + "step": 1940480 + }, + { + "epoch": 1.01, + "learning_rate": 1.8220403665445246e-05, + "loss": 3.8789, + "step": 1940992 + }, + { + "epoch": 1.01, + "learning_rate": 1.8212017717934725e-05, + "loss": 3.8822, + "step": 1941504 + }, + { + "epoch": 1.01, + "learning_rate": 1.8203631770424205e-05, + "loss": 3.8669, + "step": 1942016 + }, + { + "epoch": 1.01, + "learning_rate": 1.8195245822913685e-05, + "loss": 3.8649, + "step": 1942528 + }, + { + "epoch": 1.01, + "learning_rate": 1.8186859875403165e-05, + "loss": 3.8583, + "step": 1943040 + }, + { + "epoch": 1.01, + "learning_rate": 1.8178506685500107e-05, + "loss": 3.8714, + "step": 1943552 + }, + { + "epoch": 1.01, + "learning_rate": 1.8170120737989587e-05, + "loss": 3.8852, + "step": 1944064 + }, + { + "epoch": 1.01, + "learning_rate": 1.8161734790479067e-05, + "loss": 3.8747, + "step": 1944576 + }, + { + "epoch": 1.01, + "learning_rate": 1.8153348842968547e-05, + "loss": 3.8773, + "step": 1945088 + }, + { + "epoch": 1.01, + "learning_rate": 1.814496289545803e-05, + "loss": 3.8783, + "step": 1945600 + }, + { + "epoch": 1.01, + "learning_rate": 1.8136576947947507e-05, + "loss": 3.8887, + "step": 1946112 + }, + { + "epoch": 1.01, + "learning_rate": 1.812820737924072e-05, + "loss": 3.8682, + "step": 1946624 + }, + { + "epoch": 1.01, + "learning_rate": 1.81198214317302e-05, + "loss": 3.8848, + "step": 1947136 + }, + { + "epoch": 1.01, + "learning_rate": 1.811143548421968e-05, + "loss": 3.8652, + "step": 1947648 + }, + { + "epoch": 1.01, + "learning_rate": 1.8103049536709156e-05, + "loss": 3.8734, + "step": 1948160 + }, + { + "epoch": 1.01, + "learning_rate": 1.809467996800237e-05, + "loss": 3.8717, + "step": 1948672 + }, + { + "epoch": 1.01, + "learning_rate": 1.808629402049185e-05, + "loss": 3.8787, + "step": 1949184 + }, + { + "epoch": 1.01, + "learning_rate": 1.807790807298133e-05, + "loss": 3.88, + "step": 1949696 + }, + { + "epoch": 1.01, + "learning_rate": 1.8069522125470808e-05, + "loss": 3.8847, + "step": 1950208 + }, + { + "epoch": 1.01, + "learning_rate": 1.8061136177960288e-05, + "loss": 3.8678, + "step": 1950720 + }, + { + "epoch": 1.01, + "learning_rate": 1.8052750230449768e-05, + "loss": 3.8713, + "step": 1951232 + }, + { + "epoch": 1.01, + "learning_rate": 1.804438066174298e-05, + "loss": 3.8786, + "step": 1951744 + }, + { + "epoch": 1.01, + "learning_rate": 1.803599471423246e-05, + "loss": 3.8795, + "step": 1952256 + }, + { + "epoch": 1.01, + "learning_rate": 1.802760876672194e-05, + "loss": 3.8662, + "step": 1952768 + }, + { + "epoch": 1.01, + "learning_rate": 1.801922281921142e-05, + "loss": 3.8736, + "step": 1953280 + }, + { + "epoch": 1.02, + "learning_rate": 1.80108368717009e-05, + "loss": 3.8782, + "step": 1953792 + }, + { + "epoch": 1.02, + "learning_rate": 1.800246730299411e-05, + "loss": 3.8784, + "step": 1954304 + }, + { + "epoch": 1.02, + "learning_rate": 1.7994081355483593e-05, + "loss": 3.8737, + "step": 1954816 + }, + { + "epoch": 1.02, + "learning_rate": 1.7985695407973073e-05, + "loss": 3.8627, + "step": 1955328 + }, + { + "epoch": 1.02, + "learning_rate": 1.7977309460462553e-05, + "loss": 3.8823, + "step": 1955840 + }, + { + "epoch": 1.02, + "learning_rate": 1.7968923512952033e-05, + "loss": 3.8822, + "step": 1956352 + }, + { + "epoch": 1.02, + "learning_rate": 1.7960553944245242e-05, + "loss": 3.8755, + "step": 1956864 + }, + { + "epoch": 1.02, + "learning_rate": 1.7952184375538454e-05, + "loss": 3.8663, + "step": 1957376 + }, + { + "epoch": 1.02, + "learning_rate": 1.7943798428027934e-05, + "loss": 3.8734, + "step": 1957888 + }, + { + "epoch": 1.02, + "learning_rate": 1.7935412480517414e-05, + "loss": 3.8671, + "step": 1958400 + }, + { + "epoch": 1.02, + "learning_rate": 1.7927026533006894e-05, + "loss": 3.8824, + "step": 1958912 + }, + { + "epoch": 1.02, + "learning_rate": 1.7918640585496374e-05, + "loss": 3.8841, + "step": 1959424 + }, + { + "epoch": 1.02, + "learning_rate": 1.7910254637985854e-05, + "loss": 3.8727, + "step": 1959936 + }, + { + "epoch": 1.02, + "learning_rate": 1.7901868690475334e-05, + "loss": 3.8764, + "step": 1960448 + }, + { + "epoch": 1.02, + "learning_rate": 1.7893482742964814e-05, + "loss": 3.8646, + "step": 1960960 + }, + { + "epoch": 1.02, + "learning_rate": 1.7885096795454294e-05, + "loss": 3.866, + "step": 1961472 + }, + { + "epoch": 1.02, + "learning_rate": 1.7876710847943774e-05, + "loss": 3.8634, + "step": 1961984 + }, + { + "epoch": 1.02, + "learning_rate": 1.7868324900433254e-05, + "loss": 3.8638, + "step": 1962496 + }, + { + "epoch": 1.02, + "learning_rate": 1.7859938952922734e-05, + "loss": 3.8751, + "step": 1963008 + }, + { + "epoch": 1.02, + "learning_rate": 1.7851569384215943e-05, + "loss": 3.8663, + "step": 1963520 + }, + { + "epoch": 1.02, + "learning_rate": 1.7843183436705423e-05, + "loss": 3.87, + "step": 1964032 + }, + { + "epoch": 1.02, + "learning_rate": 1.7834797489194903e-05, + "loss": 3.868, + "step": 1964544 + }, + { + "epoch": 1.02, + "learning_rate": 1.7826411541684386e-05, + "loss": 3.8713, + "step": 1965056 + }, + { + "epoch": 1.02, + "learning_rate": 1.7818041972977595e-05, + "loss": 3.8807, + "step": 1965568 + }, + { + "epoch": 1.02, + "learning_rate": 1.7809656025467075e-05, + "loss": 3.8683, + "step": 1966080 + }, + { + "epoch": 1.02, + "learning_rate": 1.7801270077956555e-05, + "loss": 3.8854, + "step": 1966592 + }, + { + "epoch": 1.02, + "learning_rate": 1.7792884130446035e-05, + "loss": 3.8884, + "step": 1967104 + }, + { + "epoch": 1.02, + "learning_rate": 1.7784498182935515e-05, + "loss": 3.8761, + "step": 1967616 + }, + { + "epoch": 1.02, + "learning_rate": 1.7776128614228727e-05, + "loss": 3.8714, + "step": 1968128 + }, + { + "epoch": 1.02, + "learning_rate": 1.7767742666718207e-05, + "loss": 3.8707, + "step": 1968640 + }, + { + "epoch": 1.02, + "learning_rate": 1.7759373098011417e-05, + "loss": 3.8736, + "step": 1969152 + }, + { + "epoch": 1.02, + "learning_rate": 1.7750987150500896e-05, + "loss": 3.8794, + "step": 1969664 + }, + { + "epoch": 1.02, + "learning_rate": 1.7742601202990376e-05, + "loss": 3.8765, + "step": 1970176 + }, + { + "epoch": 1.02, + "learning_rate": 1.7734215255479856e-05, + "loss": 3.866, + "step": 1970688 + }, + { + "epoch": 1.02, + "learning_rate": 1.772584568677307e-05, + "loss": 3.8851, + "step": 1971200 + }, + { + "epoch": 1.02, + "learning_rate": 1.771745973926255e-05, + "loss": 3.8854, + "step": 1971712 + }, + { + "epoch": 1.02, + "learning_rate": 1.770907379175203e-05, + "loss": 3.8697, + "step": 1972224 + }, + { + "epoch": 1.02, + "learning_rate": 1.770068784424151e-05, + "loss": 3.8643, + "step": 1972736 + }, + { + "epoch": 1.02, + "learning_rate": 1.769230189673099e-05, + "loss": 3.8777, + "step": 1973248 + }, + { + "epoch": 1.02, + "learning_rate": 1.768391594922047e-05, + "loss": 3.864, + "step": 1973760 + }, + { + "epoch": 1.02, + "learning_rate": 1.767553000170995e-05, + "loss": 3.889, + "step": 1974272 + }, + { + "epoch": 1.02, + "learning_rate": 1.766716043300316e-05, + "loss": 3.8728, + "step": 1974784 + }, + { + "epoch": 1.02, + "learning_rate": 1.7658774485492638e-05, + "loss": 3.8823, + "step": 1975296 + }, + { + "epoch": 1.02, + "learning_rate": 1.7650388537982118e-05, + "loss": 3.8604, + "step": 1975808 + }, + { + "epoch": 1.02, + "learning_rate": 1.7642002590471598e-05, + "loss": 3.8853, + "step": 1976320 + }, + { + "epoch": 1.02, + "learning_rate": 1.7633616642961078e-05, + "loss": 3.8787, + "step": 1976832 + }, + { + "epoch": 1.02, + "learning_rate": 1.7625230695450557e-05, + "loss": 3.8761, + "step": 1977344 + }, + { + "epoch": 1.02, + "learning_rate": 1.761684474794004e-05, + "loss": 3.8775, + "step": 1977856 + }, + { + "epoch": 1.02, + "learning_rate": 1.760845880042952e-05, + "loss": 3.8702, + "step": 1978368 + }, + { + "epoch": 1.02, + "learning_rate": 1.760008923172273e-05, + "loss": 3.8784, + "step": 1978880 + }, + { + "epoch": 1.02, + "learning_rate": 1.759170328421221e-05, + "loss": 3.896, + "step": 1979392 + }, + { + "epoch": 1.02, + "learning_rate": 1.7583333715505422e-05, + "loss": 3.8587, + "step": 1979904 + }, + { + "epoch": 1.02, + "learning_rate": 1.7574947767994902e-05, + "loss": 3.8794, + "step": 1980416 + }, + { + "epoch": 1.02, + "learning_rate": 1.7566561820484382e-05, + "loss": 3.8721, + "step": 1980928 + }, + { + "epoch": 1.02, + "learning_rate": 1.7558175872973862e-05, + "loss": 3.8684, + "step": 1981440 + }, + { + "epoch": 1.02, + "learning_rate": 1.7549789925463342e-05, + "loss": 3.8735, + "step": 1981952 + }, + { + "epoch": 1.02, + "learning_rate": 1.754142035675655e-05, + "loss": 3.8766, + "step": 1982464 + }, + { + "epoch": 1.02, + "learning_rate": 1.753303440924603e-05, + "loss": 3.8761, + "step": 1982976 + }, + { + "epoch": 1.02, + "learning_rate": 1.752464846173551e-05, + "loss": 3.8725, + "step": 1983488 + }, + { + "epoch": 1.02, + "learning_rate": 1.7516262514224994e-05, + "loss": 3.8796, + "step": 1984000 + }, + { + "epoch": 1.03, + "eval_loss": 3.982668399810791, + "eval_runtime": 286.0614, + "eval_samples_per_second": 1333.948, + "eval_steps_per_second": 41.687, + "step": 1984320 + }, + { + "epoch": 0.0, + "learning_rate": 1.7507892945518204e-05, + "loss": 3.8577, + "step": 1984512 + }, + { + "epoch": 0.0, + "learning_rate": 1.7499506998007684e-05, + "loss": 3.8703, + "step": 1985024 + }, + { + "epoch": 0.0, + "learning_rate": 1.7491121050497163e-05, + "loss": 3.876, + "step": 1985536 + }, + { + "epoch": 0.0, + "learning_rate": 1.7482735102986643e-05, + "loss": 3.8716, + "step": 1986048 + }, + { + "epoch": 0.0, + "learning_rate": 1.7474349155476123e-05, + "loss": 3.8792, + "step": 1986560 + }, + { + "epoch": 0.0, + "learning_rate": 1.7465963207965603e-05, + "loss": 3.8674, + "step": 1987072 + }, + { + "epoch": 0.0, + "learning_rate": 1.7457577260455083e-05, + "loss": 3.8776, + "step": 1987584 + }, + { + "epoch": 0.0, + "learning_rate": 1.7449191312944563e-05, + "loss": 3.8653, + "step": 1988096 + }, + { + "epoch": 0.0, + "learning_rate": 1.7440805365434043e-05, + "loss": 3.875, + "step": 1988608 + }, + { + "epoch": 0.0, + "learning_rate": 1.7432419417923523e-05, + "loss": 3.8739, + "step": 1989120 + }, + { + "epoch": 0.0, + "learning_rate": 1.7424033470413e-05, + "loss": 3.8712, + "step": 1989632 + }, + { + "epoch": 0.0, + "learning_rate": 1.741564752290248e-05, + "loss": 3.8825, + "step": 1990144 + }, + { + "epoch": 0.0, + "learning_rate": 1.7407277954195696e-05, + "loss": 3.8857, + "step": 1990656 + }, + { + "epoch": 0.0, + "learning_rate": 1.7398892006685176e-05, + "loss": 3.8647, + "step": 1991168 + }, + { + "epoch": 0.0, + "learning_rate": 1.7390506059174652e-05, + "loss": 3.8733, + "step": 1991680 + }, + { + "epoch": 0.0, + "learning_rate": 1.7382120111664132e-05, + "loss": 3.8626, + "step": 1992192 + }, + { + "epoch": 0.0, + "learning_rate": 1.7373734164153612e-05, + "loss": 3.863, + "step": 1992704 + }, + { + "epoch": 0.0, + "learning_rate": 1.7365364595446824e-05, + "loss": 3.8706, + "step": 1993216 + }, + { + "epoch": 0.0, + "learning_rate": 1.7356978647936304e-05, + "loss": 3.8671, + "step": 1993728 + }, + { + "epoch": 0.0, + "learning_rate": 1.7348592700425784e-05, + "loss": 3.8738, + "step": 1994240 + }, + { + "epoch": 0.0, + "learning_rate": 1.7340206752915264e-05, + "loss": 3.8823, + "step": 1994752 + }, + { + "epoch": 0.0, + "learning_rate": 1.7331820805404744e-05, + "loss": 3.8792, + "step": 1995264 + }, + { + "epoch": 0.0, + "learning_rate": 1.7323434857894224e-05, + "loss": 3.8811, + "step": 1995776 + }, + { + "epoch": 0.0, + "learning_rate": 1.7315048910383704e-05, + "loss": 3.8772, + "step": 1996288 + }, + { + "epoch": 0.0, + "learning_rate": 1.730666296287318e-05, + "loss": 3.8721, + "step": 1996800 + }, + { + "epoch": 0.0, + "learning_rate": 1.7298277015362664e-05, + "loss": 3.8753, + "step": 1997312 + }, + { + "epoch": 0.0, + "learning_rate": 1.7289891067852144e-05, + "loss": 3.8675, + "step": 1997824 + }, + { + "epoch": 0.0, + "learning_rate": 1.7281505120341624e-05, + "loss": 3.876, + "step": 1998336 + }, + { + "epoch": 0.0, + "learning_rate": 1.7273119172831104e-05, + "loss": 3.866, + "step": 1998848 + }, + { + "epoch": 0.0, + "learning_rate": 1.7264749604124313e-05, + "loss": 3.8691, + "step": 1999360 + }, + { + "epoch": 0.01, + "learning_rate": 1.7256380035417526e-05, + "loss": 3.871, + "step": 1999872 + }, + { + "epoch": 0.01, + "learning_rate": 1.7247994087907006e-05, + "loss": 3.8767, + "step": 2000384 + }, + { + "epoch": 0.01, + "learning_rate": 1.7239608140396485e-05, + "loss": 3.8782, + "step": 2000896 + }, + { + "epoch": 0.01, + "learning_rate": 1.7231222192885965e-05, + "loss": 3.8707, + "step": 2001408 + }, + { + "epoch": 0.01, + "learning_rate": 1.7222836245375445e-05, + "loss": 3.8738, + "step": 2001920 + }, + { + "epoch": 0.01, + "learning_rate": 1.7214466676668655e-05, + "loss": 3.8734, + "step": 2002432 + }, + { + "epoch": 0.01, + "learning_rate": 1.720609710796187e-05, + "loss": 3.8789, + "step": 2002944 + }, + { + "epoch": 0.01, + "learning_rate": 1.719771116045135e-05, + "loss": 3.8623, + "step": 2003456 + }, + { + "epoch": 0.01, + "learning_rate": 1.718932521294083e-05, + "loss": 3.8652, + "step": 2003968 + }, + { + "epoch": 0.01, + "learning_rate": 1.7180939265430307e-05, + "loss": 3.8649, + "step": 2004480 + }, + { + "epoch": 0.01, + "learning_rate": 1.7172553317919787e-05, + "loss": 3.8661, + "step": 2004992 + }, + { + "epoch": 0.01, + "learning_rate": 1.7164167370409267e-05, + "loss": 3.8727, + "step": 2005504 + }, + { + "epoch": 0.01, + "learning_rate": 1.7155781422898747e-05, + "loss": 3.878, + "step": 2006016 + }, + { + "epoch": 0.01, + "learning_rate": 1.7147395475388227e-05, + "loss": 3.8725, + "step": 2006528 + }, + { + "epoch": 0.01, + "learning_rate": 1.713900952787771e-05, + "loss": 3.8777, + "step": 2007040 + }, + { + "epoch": 0.01, + "learning_rate": 1.7130623580367187e-05, + "loss": 3.8754, + "step": 2007552 + }, + { + "epoch": 0.01, + "learning_rate": 1.7122237632856667e-05, + "loss": 3.8788, + "step": 2008064 + }, + { + "epoch": 0.01, + "learning_rate": 1.711386806414988e-05, + "loss": 3.8721, + "step": 2008576 + }, + { + "epoch": 0.01, + "learning_rate": 1.710548211663936e-05, + "loss": 3.8447, + "step": 2009088 + }, + { + "epoch": 0.01, + "learning_rate": 1.709709616912884e-05, + "loss": 3.8865, + "step": 2009600 + }, + { + "epoch": 0.01, + "learning_rate": 1.708871022161832e-05, + "loss": 3.8651, + "step": 2010112 + }, + { + "epoch": 0.01, + "learning_rate": 1.70803242741078e-05, + "loss": 3.8731, + "step": 2010624 + }, + { + "epoch": 0.01, + "learning_rate": 1.707193832659728e-05, + "loss": 3.8695, + "step": 2011136 + }, + { + "epoch": 0.01, + "learning_rate": 1.706355237908676e-05, + "loss": 3.8601, + "step": 2011648 + }, + { + "epoch": 0.01, + "learning_rate": 1.705516643157624e-05, + "loss": 3.8675, + "step": 2012160 + }, + { + "epoch": 0.01, + "learning_rate": 1.704678048406572e-05, + "loss": 3.8583, + "step": 2012672 + }, + { + "epoch": 0.01, + "learning_rate": 1.7038410915358928e-05, + "loss": 3.874, + "step": 2013184 + }, + { + "epoch": 0.01, + "learning_rate": 1.703004134665214e-05, + "loss": 3.8612, + "step": 2013696 + }, + { + "epoch": 0.01, + "learning_rate": 1.702165539914162e-05, + "loss": 3.8814, + "step": 2014208 + }, + { + "epoch": 0.01, + "learning_rate": 1.70132694516311e-05, + "loss": 3.8673, + "step": 2014720 + }, + { + "epoch": 0.01, + "learning_rate": 1.700488350412058e-05, + "loss": 3.851, + "step": 2015232 + }, + { + "epoch": 0.01, + "learning_rate": 1.699649755661006e-05, + "loss": 3.8822, + "step": 2015744 + }, + { + "epoch": 0.01, + "learning_rate": 1.698811160909954e-05, + "loss": 3.8611, + "step": 2016256 + }, + { + "epoch": 0.01, + "learning_rate": 1.697972566158902e-05, + "loss": 3.8577, + "step": 2016768 + }, + { + "epoch": 0.01, + "learning_rate": 1.69713397140785e-05, + "loss": 3.8743, + "step": 2017280 + }, + { + "epoch": 0.01, + "learning_rate": 1.6962970145371712e-05, + "loss": 3.8792, + "step": 2017792 + }, + { + "epoch": 0.01, + "learning_rate": 1.6954584197861192e-05, + "loss": 3.8636, + "step": 2018304 + }, + { + "epoch": 0.01, + "learning_rate": 1.694619825035067e-05, + "loss": 3.8615, + "step": 2018816 + }, + { + "epoch": 0.01, + "learning_rate": 1.693782868164388e-05, + "loss": 3.8534, + "step": 2019328 + }, + { + "epoch": 0.01, + "learning_rate": 1.6929442734133365e-05, + "loss": 3.8639, + "step": 2019840 + }, + { + "epoch": 0.01, + "learning_rate": 1.692105678662284e-05, + "loss": 3.8777, + "step": 2020352 + }, + { + "epoch": 0.01, + "learning_rate": 1.691267083911232e-05, + "loss": 3.8747, + "step": 2020864 + }, + { + "epoch": 0.01, + "learning_rate": 1.69042848916018e-05, + "loss": 3.8736, + "step": 2021376 + }, + { + "epoch": 0.01, + "learning_rate": 1.689589894409128e-05, + "loss": 3.8726, + "step": 2021888 + }, + { + "epoch": 0.01, + "learning_rate": 1.6887529375384494e-05, + "loss": 3.8837, + "step": 2022400 + }, + { + "epoch": 0.01, + "learning_rate": 1.6879143427873974e-05, + "loss": 3.867, + "step": 2022912 + }, + { + "epoch": 0.01, + "learning_rate": 1.6870757480363454e-05, + "loss": 3.8769, + "step": 2023424 + }, + { + "epoch": 0.01, + "learning_rate": 1.6862371532852934e-05, + "loss": 3.8601, + "step": 2023936 + }, + { + "epoch": 0.01, + "learning_rate": 1.6853985585342414e-05, + "loss": 3.8693, + "step": 2024448 + }, + { + "epoch": 0.01, + "learning_rate": 1.6845599637831893e-05, + "loss": 3.8662, + "step": 2024960 + }, + { + "epoch": 0.01, + "learning_rate": 1.6837213690321373e-05, + "loss": 3.8726, + "step": 2025472 + }, + { + "epoch": 0.01, + "learning_rate": 1.682882774281085e-05, + "loss": 3.8774, + "step": 2025984 + }, + { + "epoch": 0.01, + "learning_rate": 1.6820474552907795e-05, + "loss": 3.8782, + "step": 2026496 + }, + { + "epoch": 0.01, + "learning_rate": 1.6812088605397275e-05, + "loss": 3.8641, + "step": 2027008 + }, + { + "epoch": 0.01, + "learning_rate": 1.6803702657886755e-05, + "loss": 3.8648, + "step": 2027520 + }, + { + "epoch": 0.01, + "learning_rate": 1.6795333089179964e-05, + "loss": 3.8708, + "step": 2028032 + }, + { + "epoch": 0.01, + "learning_rate": 1.6786947141669447e-05, + "loss": 3.8756, + "step": 2028544 + }, + { + "epoch": 0.01, + "learning_rate": 1.6778561194158927e-05, + "loss": 3.8611, + "step": 2029056 + }, + { + "epoch": 0.01, + "learning_rate": 1.6770175246648407e-05, + "loss": 3.8678, + "step": 2029568 + }, + { + "epoch": 0.01, + "learning_rate": 1.6761789299137887e-05, + "loss": 3.8773, + "step": 2030080 + }, + { + "epoch": 0.02, + "learning_rate": 1.6753403351627367e-05, + "loss": 3.8704, + "step": 2030592 + }, + { + "epoch": 0.02, + "learning_rate": 1.6745017404116844e-05, + "loss": 3.8675, + "step": 2031104 + }, + { + "epoch": 0.02, + "learning_rate": 1.6736631456606324e-05, + "loss": 3.859, + "step": 2031616 + }, + { + "epoch": 0.02, + "learning_rate": 1.6728245509095804e-05, + "loss": 3.876, + "step": 2032128 + }, + { + "epoch": 0.02, + "learning_rate": 1.6719859561585287e-05, + "loss": 3.8793, + "step": 2032640 + }, + { + "epoch": 0.02, + "learning_rate": 1.6711473614074767e-05, + "loss": 3.872, + "step": 2033152 + }, + { + "epoch": 0.02, + "learning_rate": 1.6703104045367976e-05, + "loss": 3.864, + "step": 2033664 + }, + { + "epoch": 0.02, + "learning_rate": 1.6694718097857456e-05, + "loss": 3.8649, + "step": 2034176 + }, + { + "epoch": 0.02, + "learning_rate": 1.668634852915067e-05, + "loss": 3.8634, + "step": 2034688 + }, + { + "epoch": 0.02, + "learning_rate": 1.667796258164015e-05, + "loss": 3.8767, + "step": 2035200 + }, + { + "epoch": 0.02, + "learning_rate": 1.666957663412963e-05, + "loss": 3.8794, + "step": 2035712 + }, + { + "epoch": 0.02, + "learning_rate": 1.666119068661911e-05, + "loss": 3.8666, + "step": 2036224 + }, + { + "epoch": 0.02, + "learning_rate": 1.665280473910859e-05, + "loss": 3.8683, + "step": 2036736 + }, + { + "epoch": 0.02, + "learning_rate": 1.6644418791598068e-05, + "loss": 3.8649, + "step": 2037248 + }, + { + "epoch": 0.02, + "learning_rate": 1.6636032844087548e-05, + "loss": 3.8578, + "step": 2037760 + }, + { + "epoch": 0.02, + "learning_rate": 1.6627646896577025e-05, + "loss": 3.8613, + "step": 2038272 + }, + { + "epoch": 0.02, + "learning_rate": 1.6619260949066505e-05, + "loss": 3.8597, + "step": 2038784 + }, + { + "epoch": 0.02, + "learning_rate": 1.6610875001555988e-05, + "loss": 3.8637, + "step": 2039296 + }, + { + "epoch": 0.02, + "learning_rate": 1.6602489054045468e-05, + "loss": 3.8643, + "step": 2039808 + }, + { + "epoch": 0.02, + "learning_rate": 1.6594103106534948e-05, + "loss": 3.8602, + "step": 2040320 + }, + { + "epoch": 0.02, + "learning_rate": 1.6585733537828157e-05, + "loss": 3.8672, + "step": 2040832 + }, + { + "epoch": 0.02, + "learning_rate": 1.6577347590317637e-05, + "loss": 3.8644, + "step": 2041344 + }, + { + "epoch": 0.02, + "learning_rate": 1.656897802161085e-05, + "loss": 3.8767, + "step": 2041856 + }, + { + "epoch": 0.02, + "learning_rate": 1.656059207410033e-05, + "loss": 3.8604, + "step": 2042368 + }, + { + "epoch": 0.02, + "learning_rate": 1.655220612658981e-05, + "loss": 3.8828, + "step": 2042880 + }, + { + "epoch": 0.02, + "learning_rate": 1.654382017907929e-05, + "loss": 3.8824, + "step": 2043392 + }, + { + "epoch": 0.02, + "learning_rate": 1.653543423156877e-05, + "loss": 3.8746, + "step": 2043904 + }, + { + "epoch": 0.02, + "learning_rate": 1.652704828405825e-05, + "loss": 3.8659, + "step": 2044416 + }, + { + "epoch": 0.02, + "learning_rate": 1.651866233654773e-05, + "loss": 3.8661, + "step": 2044928 + }, + { + "epoch": 0.02, + "learning_rate": 1.6510292767840942e-05, + "loss": 3.8688, + "step": 2045440 + }, + { + "epoch": 0.02, + "learning_rate": 1.6501906820330422e-05, + "loss": 3.8781, + "step": 2045952 + }, + { + "epoch": 0.02, + "learning_rate": 1.649353725162363e-05, + "loss": 3.8707, + "step": 2046464 + }, + { + "epoch": 0.02, + "learning_rate": 1.648515130411311e-05, + "loss": 3.8634, + "step": 2046976 + }, + { + "epoch": 0.02, + "learning_rate": 1.647676535660259e-05, + "loss": 3.8748, + "step": 2047488 + }, + { + "epoch": 0.02, + "learning_rate": 1.646837940909207e-05, + "loss": 3.882, + "step": 2048000 + }, + { + "epoch": 0.02, + "learning_rate": 1.645999346158155e-05, + "loss": 3.8648, + "step": 2048512 + }, + { + "epoch": 0.02, + "learning_rate": 1.6451607514071034e-05, + "loss": 3.8634, + "step": 2049024 + }, + { + "epoch": 0.02, + "learning_rate": 1.644322156656051e-05, + "loss": 3.871, + "step": 2049536 + }, + { + "epoch": 0.02, + "learning_rate": 1.643483561904999e-05, + "loss": 3.8576, + "step": 2050048 + }, + { + "epoch": 0.02, + "learning_rate": 1.6426466050343203e-05, + "loss": 3.8874, + "step": 2050560 + }, + { + "epoch": 0.02, + "learning_rate": 1.641808010283268e-05, + "loss": 3.8651, + "step": 2051072 + }, + { + "epoch": 0.02, + "learning_rate": 1.640969415532216e-05, + "loss": 3.8795, + "step": 2051584 + }, + { + "epoch": 0.02, + "learning_rate": 1.6401308207811643e-05, + "loss": 3.8563, + "step": 2052096 + }, + { + "epoch": 0.02, + "learning_rate": 1.6392938639104855e-05, + "loss": 3.8785, + "step": 2052608 + }, + { + "epoch": 0.02, + "learning_rate": 1.6384552691594332e-05, + "loss": 3.8719, + "step": 2053120 + }, + { + "epoch": 0.02, + "learning_rate": 1.6376166744083812e-05, + "loss": 3.872, + "step": 2053632 + }, + { + "epoch": 0.02, + "learning_rate": 1.6367780796573292e-05, + "loss": 3.8719, + "step": 2054144 + }, + { + "epoch": 0.02, + "learning_rate": 1.6359394849062772e-05, + "loss": 3.8677, + "step": 2054656 + }, + { + "epoch": 0.02, + "learning_rate": 1.6351008901552252e-05, + "loss": 3.875, + "step": 2055168 + }, + { + "epoch": 0.02, + "learning_rate": 1.6342622954041735e-05, + "loss": 3.8909, + "step": 2055680 + }, + { + "epoch": 0.02, + "learning_rate": 1.6334237006531215e-05, + "loss": 3.857, + "step": 2056192 + }, + { + "epoch": 0.02, + "learning_rate": 1.632585105902069e-05, + "loss": 3.8696, + "step": 2056704 + }, + { + "epoch": 0.02, + "learning_rate": 1.6317481490313904e-05, + "loss": 3.8723, + "step": 2057216 + }, + { + "epoch": 0.02, + "learning_rate": 1.6309095542803384e-05, + "loss": 3.864, + "step": 2057728 + }, + { + "epoch": 0.02, + "learning_rate": 1.6300709595292864e-05, + "loss": 3.8681, + "step": 2058240 + }, + { + "epoch": 0.02, + "learning_rate": 1.6292323647782344e-05, + "loss": 3.8717, + "step": 2058752 + }, + { + "epoch": 0.02, + "learning_rate": 1.6283954079075556e-05, + "loss": 3.8693, + "step": 2059264 + }, + { + "epoch": 0.02, + "learning_rate": 1.6275568131565036e-05, + "loss": 3.8699, + "step": 2059776 + }, + { + "epoch": 0.02, + "learning_rate": 1.6267182184054513e-05, + "loss": 3.8738, + "step": 2060288 + }, + { + "epoch": 0.03, + "eval_loss": 3.981278657913208, + "eval_runtime": 322.0953, + "eval_samples_per_second": 1184.714, + "eval_steps_per_second": 37.023, + "step": 2060640 + }, + { + "epoch": 1.0, + "learning_rate": 1.6258796236543993e-05, + "loss": 3.863, + "step": 2060800 + }, + { + "epoch": 1.0, + "learning_rate": 1.6250426667837205e-05, + "loss": 3.8641, + "step": 2061312 + }, + { + "epoch": 1.0, + "learning_rate": 1.624204072032669e-05, + "loss": 3.8712, + "step": 2061824 + }, + { + "epoch": 1.0, + "learning_rate": 1.6233671151619898e-05, + "loss": 3.8682, + "step": 2062336 + }, + { + "epoch": 1.0, + "learning_rate": 1.6225285204109378e-05, + "loss": 3.8759, + "step": 2062848 + }, + { + "epoch": 1.0, + "learning_rate": 1.6216899256598858e-05, + "loss": 3.8635, + "step": 2063360 + }, + { + "epoch": 1.0, + "learning_rate": 1.6208513309088334e-05, + "loss": 3.8727, + "step": 2063872 + }, + { + "epoch": 1.0, + "learning_rate": 1.6200127361577814e-05, + "loss": 3.8646, + "step": 2064384 + }, + { + "epoch": 1.0, + "learning_rate": 1.6191741414067298e-05, + "loss": 3.8704, + "step": 2064896 + }, + { + "epoch": 1.0, + "learning_rate": 1.618337184536051e-05, + "loss": 3.8637, + "step": 2065408 + }, + { + "epoch": 1.0, + "learning_rate": 1.6174985897849987e-05, + "loss": 3.8671, + "step": 2065920 + }, + { + "epoch": 1.0, + "learning_rate": 1.6166599950339467e-05, + "loss": 3.8817, + "step": 2066432 + }, + { + "epoch": 1.0, + "learning_rate": 1.615823038163268e-05, + "loss": 3.8766, + "step": 2066944 + }, + { + "epoch": 1.0, + "learning_rate": 1.614984443412216e-05, + "loss": 3.8617, + "step": 2067456 + }, + { + "epoch": 1.0, + "learning_rate": 1.614145848661164e-05, + "loss": 3.8684, + "step": 2067968 + }, + { + "epoch": 1.0, + "learning_rate": 1.613307253910112e-05, + "loss": 3.8589, + "step": 2068480 + }, + { + "epoch": 1.0, + "learning_rate": 1.61246865915906e-05, + "loss": 3.8608, + "step": 2068992 + }, + { + "epoch": 1.0, + "learning_rate": 1.6116317022883808e-05, + "loss": 3.8698, + "step": 2069504 + }, + { + "epoch": 1.0, + "learning_rate": 1.6107931075373288e-05, + "loss": 3.8582, + "step": 2070016 + }, + { + "epoch": 1.0, + "learning_rate": 1.6099545127862768e-05, + "loss": 3.8691, + "step": 2070528 + }, + { + "epoch": 1.0, + "learning_rate": 1.609115918035225e-05, + "loss": 3.8761, + "step": 2071040 + }, + { + "epoch": 1.0, + "learning_rate": 1.608277323284173e-05, + "loss": 3.8768, + "step": 2071552 + }, + { + "epoch": 1.0, + "learning_rate": 1.607438728533121e-05, + "loss": 3.8796, + "step": 2072064 + }, + { + "epoch": 1.0, + "learning_rate": 1.606600133782069e-05, + "loss": 3.8742, + "step": 2072576 + }, + { + "epoch": 1.0, + "learning_rate": 1.6057615390310168e-05, + "loss": 3.8661, + "step": 2073088 + }, + { + "epoch": 1.0, + "learning_rate": 1.6049229442799648e-05, + "loss": 3.8689, + "step": 2073600 + }, + { + "epoch": 1.0, + "learning_rate": 1.6040843495289128e-05, + "loss": 3.8626, + "step": 2074112 + }, + { + "epoch": 1.0, + "learning_rate": 1.603247392658234e-05, + "loss": 3.8699, + "step": 2074624 + }, + { + "epoch": 1.0, + "learning_rate": 1.602408797907182e-05, + "loss": 3.8625, + "step": 2075136 + }, + { + "epoch": 1.0, + "learning_rate": 1.60157020315613e-05, + "loss": 3.8663, + "step": 2075648 + }, + { + "epoch": 1.01, + "learning_rate": 1.600731608405078e-05, + "loss": 3.8678, + "step": 2076160 + }, + { + "epoch": 1.01, + "learning_rate": 1.599893013654026e-05, + "loss": 3.868, + "step": 2076672 + }, + { + "epoch": 1.01, + "learning_rate": 1.5990560567833472e-05, + "loss": 3.8698, + "step": 2077184 + }, + { + "epoch": 1.01, + "learning_rate": 1.5982174620322952e-05, + "loss": 3.8696, + "step": 2077696 + }, + { + "epoch": 1.01, + "learning_rate": 1.5973788672812432e-05, + "loss": 3.8662, + "step": 2078208 + }, + { + "epoch": 1.01, + "learning_rate": 1.596541910410564e-05, + "loss": 3.8712, + "step": 2078720 + }, + { + "epoch": 1.01, + "learning_rate": 1.595703315659512e-05, + "loss": 3.8765, + "step": 2079232 + }, + { + "epoch": 1.01, + "learning_rate": 1.59486472090846e-05, + "loss": 3.858, + "step": 2079744 + }, + { + "epoch": 1.01, + "learning_rate": 1.594026126157408e-05, + "loss": 3.8607, + "step": 2080256 + }, + { + "epoch": 1.01, + "learning_rate": 1.593187531406356e-05, + "loss": 3.8603, + "step": 2080768 + }, + { + "epoch": 1.01, + "learning_rate": 1.5923505745356774e-05, + "loss": 3.858, + "step": 2081280 + }, + { + "epoch": 1.01, + "learning_rate": 1.5915119797846254e-05, + "loss": 3.8699, + "step": 2081792 + }, + { + "epoch": 1.01, + "learning_rate": 1.5906733850335734e-05, + "loss": 3.8707, + "step": 2082304 + }, + { + "epoch": 1.01, + "learning_rate": 1.5898347902825214e-05, + "loss": 3.8725, + "step": 2082816 + }, + { + "epoch": 1.01, + "learning_rate": 1.5889961955314694e-05, + "loss": 3.8714, + "step": 2083328 + }, + { + "epoch": 1.01, + "learning_rate": 1.5881576007804174e-05, + "loss": 3.8716, + "step": 2083840 + }, + { + "epoch": 1.01, + "learning_rate": 1.5873190060293653e-05, + "loss": 3.8723, + "step": 2084352 + }, + { + "epoch": 1.01, + "learning_rate": 1.5864804112783133e-05, + "loss": 3.8692, + "step": 2084864 + }, + { + "epoch": 1.01, + "learning_rate": 1.5856434544076346e-05, + "loss": 3.8421, + "step": 2085376 + }, + { + "epoch": 1.01, + "learning_rate": 1.5848048596565822e-05, + "loss": 3.8791, + "step": 2085888 + }, + { + "epoch": 1.01, + "learning_rate": 1.5839662649055302e-05, + "loss": 3.8586, + "step": 2086400 + }, + { + "epoch": 1.01, + "learning_rate": 1.5831276701544782e-05, + "loss": 3.8698, + "step": 2086912 + }, + { + "epoch": 1.01, + "learning_rate": 1.5822890754034266e-05, + "loss": 3.8593, + "step": 2087424 + }, + { + "epoch": 1.01, + "learning_rate": 1.5814521185327475e-05, + "loss": 3.8558, + "step": 2087936 + }, + { + "epoch": 1.01, + "learning_rate": 1.5806135237816955e-05, + "loss": 3.8646, + "step": 2088448 + }, + { + "epoch": 1.01, + "learning_rate": 1.5797749290306435e-05, + "loss": 3.8575, + "step": 2088960 + }, + { + "epoch": 1.01, + "learning_rate": 1.5789363342795915e-05, + "loss": 3.8696, + "step": 2089472 + }, + { + "epoch": 1.01, + "learning_rate": 1.5780993774089127e-05, + "loss": 3.8518, + "step": 2089984 + }, + { + "epoch": 1.01, + "learning_rate": 1.5772607826578607e-05, + "loss": 3.8791, + "step": 2090496 + }, + { + "epoch": 1.01, + "learning_rate": 1.5764221879068087e-05, + "loss": 3.867, + "step": 2091008 + }, + { + "epoch": 1.01, + "learning_rate": 1.5755835931557567e-05, + "loss": 3.8421, + "step": 2091520 + }, + { + "epoch": 1.01, + "learning_rate": 1.5747449984047047e-05, + "loss": 3.8767, + "step": 2092032 + }, + { + "epoch": 1.01, + "learning_rate": 1.5739064036536527e-05, + "loss": 3.8564, + "step": 2092544 + }, + { + "epoch": 1.01, + "learning_rate": 1.5730678089026004e-05, + "loss": 3.8557, + "step": 2093056 + }, + { + "epoch": 1.01, + "learning_rate": 1.5722292141515483e-05, + "loss": 3.8669, + "step": 2093568 + }, + { + "epoch": 1.01, + "learning_rate": 1.57139225728087e-05, + "loss": 3.8749, + "step": 2094080 + }, + { + "epoch": 1.01, + "learning_rate": 1.5705536625298176e-05, + "loss": 3.8576, + "step": 2094592 + }, + { + "epoch": 1.01, + "learning_rate": 1.5697150677787656e-05, + "loss": 3.861, + "step": 2095104 + }, + { + "epoch": 1.01, + "learning_rate": 1.5688764730277136e-05, + "loss": 3.8474, + "step": 2095616 + }, + { + "epoch": 1.01, + "learning_rate": 1.568039516157035e-05, + "loss": 3.8601, + "step": 2096128 + }, + { + "epoch": 1.01, + "learning_rate": 1.5672009214059828e-05, + "loss": 3.8761, + "step": 2096640 + }, + { + "epoch": 1.01, + "learning_rate": 1.5663623266549308e-05, + "loss": 3.868, + "step": 2097152 + }, + { + "epoch": 1.01, + "learning_rate": 1.5655237319038788e-05, + "loss": 3.8675, + "step": 2097664 + }, + { + "epoch": 1.01, + "learning_rate": 1.5646851371528268e-05, + "loss": 3.8675, + "step": 2098176 + }, + { + "epoch": 1.01, + "learning_rate": 1.5638481802821477e-05, + "loss": 3.8781, + "step": 2098688 + }, + { + "epoch": 1.01, + "learning_rate": 1.5630095855310957e-05, + "loss": 3.8644, + "step": 2099200 + }, + { + "epoch": 1.01, + "learning_rate": 1.5621709907800437e-05, + "loss": 3.8709, + "step": 2099712 + }, + { + "epoch": 1.01, + "learning_rate": 1.561332396028992e-05, + "loss": 3.8579, + "step": 2100224 + }, + { + "epoch": 1.01, + "learning_rate": 1.56049380127794e-05, + "loss": 3.8646, + "step": 2100736 + }, + { + "epoch": 1.01, + "learning_rate": 1.559655206526888e-05, + "loss": 3.8619, + "step": 2101248 + }, + { + "epoch": 1.01, + "learning_rate": 1.5588166117758357e-05, + "loss": 3.8652, + "step": 2101760 + }, + { + "epoch": 1.01, + "learning_rate": 1.557979654905157e-05, + "loss": 3.8708, + "step": 2102272 + }, + { + "epoch": 1.01, + "learning_rate": 1.557141060154105e-05, + "loss": 3.8741, + "step": 2102784 + }, + { + "epoch": 1.01, + "learning_rate": 1.556302465403053e-05, + "loss": 3.8692, + "step": 2103296 + }, + { + "epoch": 1.01, + "learning_rate": 1.555467146412747e-05, + "loss": 3.857, + "step": 2103808 + }, + { + "epoch": 1.01, + "learning_rate": 1.554628551661695e-05, + "loss": 3.8689, + "step": 2104320 + }, + { + "epoch": 1.01, + "learning_rate": 1.553789956910643e-05, + "loss": 3.869, + "step": 2104832 + }, + { + "epoch": 1.01, + "learning_rate": 1.552951362159591e-05, + "loss": 3.8564, + "step": 2105344 + }, + { + "epoch": 1.01, + "learning_rate": 1.552112767408539e-05, + "loss": 3.8636, + "step": 2105856 + }, + { + "epoch": 1.01, + "learning_rate": 1.5512741726574874e-05, + "loss": 3.8727, + "step": 2106368 + }, + { + "epoch": 1.02, + "learning_rate": 1.5504355779064354e-05, + "loss": 3.8633, + "step": 2106880 + }, + { + "epoch": 1.02, + "learning_rate": 1.549596983155383e-05, + "loss": 3.869, + "step": 2107392 + }, + { + "epoch": 1.02, + "learning_rate": 1.548758388404331e-05, + "loss": 3.8545, + "step": 2107904 + }, + { + "epoch": 1.02, + "learning_rate": 1.5479214315336523e-05, + "loss": 3.8723, + "step": 2108416 + }, + { + "epoch": 1.02, + "learning_rate": 1.5470828367826003e-05, + "loss": 3.8709, + "step": 2108928 + }, + { + "epoch": 1.02, + "learning_rate": 1.5462442420315483e-05, + "loss": 3.8712, + "step": 2109440 + }, + { + "epoch": 1.02, + "learning_rate": 1.5454056472804963e-05, + "loss": 3.8542, + "step": 2109952 + }, + { + "epoch": 1.02, + "learning_rate": 1.5445686904098175e-05, + "loss": 3.8653, + "step": 2110464 + }, + { + "epoch": 1.02, + "learning_rate": 1.5437317335391385e-05, + "loss": 3.8571, + "step": 2110976 + }, + { + "epoch": 1.02, + "learning_rate": 1.5428931387880865e-05, + "loss": 3.8707, + "step": 2111488 + }, + { + "epoch": 1.02, + "learning_rate": 1.5420545440370344e-05, + "loss": 3.88, + "step": 2112000 + }, + { + "epoch": 1.02, + "learning_rate": 1.5412159492859828e-05, + "loss": 3.8578, + "step": 2112512 + }, + { + "epoch": 1.02, + "learning_rate": 1.5403773545349304e-05, + "loss": 3.8674, + "step": 2113024 + }, + { + "epoch": 1.02, + "learning_rate": 1.5395387597838784e-05, + "loss": 3.8571, + "step": 2113536 + }, + { + "epoch": 1.02, + "learning_rate": 1.5387001650328264e-05, + "loss": 3.855, + "step": 2114048 + }, + { + "epoch": 1.02, + "learning_rate": 1.5378615702817744e-05, + "loss": 3.8588, + "step": 2114560 + }, + { + "epoch": 1.02, + "learning_rate": 1.5370229755307224e-05, + "loss": 3.8564, + "step": 2115072 + }, + { + "epoch": 1.02, + "learning_rate": 1.5361860186600437e-05, + "loss": 3.8602, + "step": 2115584 + }, + { + "epoch": 1.02, + "learning_rate": 1.5353474239089917e-05, + "loss": 3.8595, + "step": 2116096 + }, + { + "epoch": 1.02, + "learning_rate": 1.5345088291579397e-05, + "loss": 3.8583, + "step": 2116608 + }, + { + "epoch": 1.02, + "learning_rate": 1.5336702344068877e-05, + "loss": 3.8549, + "step": 2117120 + }, + { + "epoch": 1.02, + "learning_rate": 1.5328316396558357e-05, + "loss": 3.8605, + "step": 2117632 + }, + { + "epoch": 1.02, + "learning_rate": 1.5319930449047833e-05, + "loss": 3.8743, + "step": 2118144 + }, + { + "epoch": 1.02, + "learning_rate": 1.5311544501537313e-05, + "loss": 3.8589, + "step": 2118656 + }, + { + "epoch": 1.02, + "learning_rate": 1.530317493283053e-05, + "loss": 3.8741, + "step": 2119168 + }, + { + "epoch": 1.02, + "learning_rate": 1.529478898532001e-05, + "loss": 3.8731, + "step": 2119680 + }, + { + "epoch": 1.02, + "learning_rate": 1.5286403037809485e-05, + "loss": 3.8765, + "step": 2120192 + }, + { + "epoch": 1.02, + "learning_rate": 1.5278017090298965e-05, + "loss": 3.8592, + "step": 2120704 + }, + { + "epoch": 1.02, + "learning_rate": 1.5269631142788445e-05, + "loss": 3.8619, + "step": 2121216 + }, + { + "epoch": 1.02, + "learning_rate": 1.5261261574081658e-05, + "loss": 3.8638, + "step": 2121728 + }, + { + "epoch": 1.02, + "learning_rate": 1.5252875626571136e-05, + "loss": 3.8709, + "step": 2122240 + }, + { + "epoch": 1.02, + "learning_rate": 1.5244489679060616e-05, + "loss": 3.8702, + "step": 2122752 + }, + { + "epoch": 1.02, + "learning_rate": 1.5236103731550098e-05, + "loss": 3.8607, + "step": 2123264 + }, + { + "epoch": 1.02, + "learning_rate": 1.5227717784039578e-05, + "loss": 3.8645, + "step": 2123776 + }, + { + "epoch": 1.02, + "learning_rate": 1.5219348215332788e-05, + "loss": 3.8767, + "step": 2124288 + }, + { + "epoch": 1.02, + "learning_rate": 1.5210962267822268e-05, + "loss": 3.8647, + "step": 2124800 + }, + { + "epoch": 1.02, + "learning_rate": 1.5202576320311748e-05, + "loss": 3.8556, + "step": 2125312 + }, + { + "epoch": 1.02, + "learning_rate": 1.5194190372801228e-05, + "loss": 3.8641, + "step": 2125824 + }, + { + "epoch": 1.02, + "learning_rate": 1.5185804425290708e-05, + "loss": 3.8561, + "step": 2126336 + }, + { + "epoch": 1.02, + "learning_rate": 1.5177434856583919e-05, + "loss": 3.8807, + "step": 2126848 + }, + { + "epoch": 1.02, + "learning_rate": 1.5169048909073399e-05, + "loss": 3.8623, + "step": 2127360 + }, + { + "epoch": 1.02, + "learning_rate": 1.5160662961562879e-05, + "loss": 3.8754, + "step": 2127872 + }, + { + "epoch": 1.02, + "learning_rate": 1.515227701405236e-05, + "loss": 3.8531, + "step": 2128384 + }, + { + "epoch": 1.02, + "learning_rate": 1.514389106654184e-05, + "loss": 3.8743, + "step": 2128896 + }, + { + "epoch": 1.02, + "learning_rate": 1.5135521497835051e-05, + "loss": 3.8662, + "step": 2129408 + }, + { + "epoch": 1.02, + "learning_rate": 1.5127135550324531e-05, + "loss": 3.8665, + "step": 2129920 + }, + { + "epoch": 1.02, + "learning_rate": 1.5118749602814011e-05, + "loss": 3.87, + "step": 2130432 + }, + { + "epoch": 1.02, + "learning_rate": 1.511036365530349e-05, + "loss": 3.8621, + "step": 2130944 + }, + { + "epoch": 1.02, + "learning_rate": 1.510197770779297e-05, + "loss": 3.873, + "step": 2131456 + }, + { + "epoch": 1.02, + "learning_rate": 1.509359176028245e-05, + "loss": 3.8859, + "step": 2131968 + }, + { + "epoch": 1.02, + "learning_rate": 1.508520581277193e-05, + "loss": 3.8543, + "step": 2132480 + }, + { + "epoch": 1.02, + "learning_rate": 1.507681986526141e-05, + "loss": 3.8641, + "step": 2132992 + }, + { + "epoch": 1.02, + "learning_rate": 1.506845029655462e-05, + "loss": 3.8686, + "step": 2133504 + }, + { + "epoch": 1.02, + "learning_rate": 1.50600643490441e-05, + "loss": 3.8603, + "step": 2134016 + }, + { + "epoch": 1.02, + "learning_rate": 1.5051678401533582e-05, + "loss": 3.8639, + "step": 2134528 + }, + { + "epoch": 1.02, + "learning_rate": 1.5043308832826791e-05, + "loss": 3.8711, + "step": 2135040 + }, + { + "epoch": 1.02, + "learning_rate": 1.503492288531627e-05, + "loss": 3.8627, + "step": 2135552 + }, + { + "epoch": 1.02, + "learning_rate": 1.5026536937805752e-05, + "loss": 3.8644, + "step": 2136064 + }, + { + "epoch": 1.02, + "learning_rate": 1.5018150990295232e-05, + "loss": 3.8713, + "step": 2136576 + }, + { + "epoch": 1.03, + "eval_loss": 3.979785919189453, + "eval_runtime": 295.6507, + "eval_samples_per_second": 1290.682, + "eval_steps_per_second": 40.335, + "step": 2136960 + }, + { + "epoch": 0.0, + "learning_rate": 1.5009765042784712e-05, + "loss": 3.8563, + "step": 2137088 + }, + { + "epoch": 0.0, + "learning_rate": 1.5001379095274192e-05, + "loss": 3.8566, + "step": 2137600 + }, + { + "epoch": 0.0, + "learning_rate": 1.499299314776367e-05, + "loss": 3.8683, + "step": 2138112 + }, + { + "epoch": 0.0, + "learning_rate": 1.498460720025315e-05, + "loss": 3.8639, + "step": 2138624 + }, + { + "epoch": 0.0, + "learning_rate": 1.497622125274263e-05, + "loss": 3.8677, + "step": 2139136 + }, + { + "epoch": 0.0, + "learning_rate": 1.496783530523211e-05, + "loss": 3.8597, + "step": 2139648 + }, + { + "epoch": 0.0, + "learning_rate": 1.4959449357721592e-05, + "loss": 3.8728, + "step": 2140160 + }, + { + "epoch": 0.0, + "learning_rate": 1.4951063410211072e-05, + "loss": 3.8584, + "step": 2140672 + }, + { + "epoch": 0.0, + "learning_rate": 1.4942677462700552e-05, + "loss": 3.8637, + "step": 2141184 + }, + { + "epoch": 0.0, + "learning_rate": 1.493429151519003e-05, + "loss": 3.8604, + "step": 2141696 + }, + { + "epoch": 0.0, + "learning_rate": 1.492590556767951e-05, + "loss": 3.8654, + "step": 2142208 + }, + { + "epoch": 0.0, + "learning_rate": 1.491751962016899e-05, + "loss": 3.8736, + "step": 2142720 + }, + { + "epoch": 0.0, + "learning_rate": 1.4909150051462201e-05, + "loss": 3.8753, + "step": 2143232 + }, + { + "epoch": 0.0, + "learning_rate": 1.4900764103951681e-05, + "loss": 3.8547, + "step": 2143744 + }, + { + "epoch": 0.0, + "learning_rate": 1.4892378156441161e-05, + "loss": 3.8684, + "step": 2144256 + }, + { + "epoch": 0.0, + "learning_rate": 1.4883992208930641e-05, + "loss": 3.851, + "step": 2144768 + }, + { + "epoch": 0.0, + "learning_rate": 1.4875606261420122e-05, + "loss": 3.86, + "step": 2145280 + }, + { + "epoch": 0.0, + "learning_rate": 1.4867220313909602e-05, + "loss": 3.8626, + "step": 2145792 + }, + { + "epoch": 0.0, + "learning_rate": 1.4858834366399082e-05, + "loss": 3.8559, + "step": 2146304 + }, + { + "epoch": 0.0, + "learning_rate": 1.485044841888856e-05, + "loss": 3.8664, + "step": 2146816 + }, + { + "epoch": 0.0, + "learning_rate": 1.484206247137804e-05, + "loss": 3.8714, + "step": 2147328 + }, + { + "epoch": 0.0, + "learning_rate": 1.4833692902671253e-05, + "loss": 3.8664, + "step": 2147840 + }, + { + "epoch": 0.0, + "learning_rate": 1.4825306955160733e-05, + "loss": 3.876, + "step": 2148352 + }, + { + "epoch": 0.0, + "learning_rate": 1.4816921007650211e-05, + "loss": 3.8741, + "step": 2148864 + }, + { + "epoch": 0.0, + "learning_rate": 1.4808535060139691e-05, + "loss": 3.861, + "step": 2149376 + }, + { + "epoch": 0.0, + "learning_rate": 1.4800149112629171e-05, + "loss": 3.8682, + "step": 2149888 + }, + { + "epoch": 0.0, + "learning_rate": 1.4791763165118653e-05, + "loss": 3.8576, + "step": 2150400 + }, + { + "epoch": 0.0, + "learning_rate": 1.4783377217608133e-05, + "loss": 3.8648, + "step": 2150912 + }, + { + "epoch": 0.0, + "learning_rate": 1.4774991270097613e-05, + "loss": 3.8602, + "step": 2151424 + }, + { + "epoch": 0.0, + "learning_rate": 1.4766638080194556e-05, + "loss": 3.8607, + "step": 2151936 + }, + { + "epoch": 0.01, + "learning_rate": 1.4758252132684033e-05, + "loss": 3.866, + "step": 2152448 + }, + { + "epoch": 0.01, + "learning_rate": 1.4749866185173514e-05, + "loss": 3.8613, + "step": 2152960 + }, + { + "epoch": 0.01, + "learning_rate": 1.4741480237662994e-05, + "loss": 3.8627, + "step": 2153472 + }, + { + "epoch": 0.01, + "learning_rate": 1.4733094290152474e-05, + "loss": 3.8693, + "step": 2153984 + }, + { + "epoch": 0.01, + "learning_rate": 1.4724708342641954e-05, + "loss": 3.8614, + "step": 2154496 + }, + { + "epoch": 0.01, + "learning_rate": 1.4716338773935165e-05, + "loss": 3.8647, + "step": 2155008 + }, + { + "epoch": 0.01, + "learning_rate": 1.4707952826424645e-05, + "loss": 3.8714, + "step": 2155520 + }, + { + "epoch": 0.01, + "learning_rate": 1.4699566878914125e-05, + "loss": 3.85, + "step": 2156032 + }, + { + "epoch": 0.01, + "learning_rate": 1.4691180931403607e-05, + "loss": 3.8621, + "step": 2156544 + }, + { + "epoch": 0.01, + "learning_rate": 1.4682811362696816e-05, + "loss": 3.8577, + "step": 2157056 + }, + { + "epoch": 0.01, + "learning_rate": 1.4674425415186296e-05, + "loss": 3.8541, + "step": 2157568 + }, + { + "epoch": 0.01, + "learning_rate": 1.4666039467675777e-05, + "loss": 3.8619, + "step": 2158080 + }, + { + "epoch": 0.01, + "learning_rate": 1.4657653520165257e-05, + "loss": 3.8662, + "step": 2158592 + }, + { + "epoch": 0.01, + "learning_rate": 1.4649267572654737e-05, + "loss": 3.8663, + "step": 2159104 + }, + { + "epoch": 0.01, + "learning_rate": 1.4640881625144215e-05, + "loss": 3.8681, + "step": 2159616 + }, + { + "epoch": 0.01, + "learning_rate": 1.4632495677633695e-05, + "loss": 3.8672, + "step": 2160128 + }, + { + "epoch": 0.01, + "learning_rate": 1.4624126108926908e-05, + "loss": 3.8694, + "step": 2160640 + }, + { + "epoch": 0.01, + "learning_rate": 1.4615740161416388e-05, + "loss": 3.8621, + "step": 2161152 + }, + { + "epoch": 0.01, + "learning_rate": 1.4607354213905866e-05, + "loss": 3.8419, + "step": 2161664 + }, + { + "epoch": 0.01, + "learning_rate": 1.4598968266395346e-05, + "loss": 3.8704, + "step": 2162176 + }, + { + "epoch": 0.01, + "learning_rate": 1.4590582318884826e-05, + "loss": 3.8579, + "step": 2162688 + }, + { + "epoch": 0.01, + "learning_rate": 1.4582212750178037e-05, + "loss": 3.864, + "step": 2163200 + }, + { + "epoch": 0.01, + "learning_rate": 1.4573826802667517e-05, + "loss": 3.8567, + "step": 2163712 + }, + { + "epoch": 0.01, + "learning_rate": 1.4565440855156998e-05, + "loss": 3.8513, + "step": 2164224 + }, + { + "epoch": 0.01, + "learning_rate": 1.4557054907646478e-05, + "loss": 3.8591, + "step": 2164736 + }, + { + "epoch": 0.01, + "learning_rate": 1.4548685338939687e-05, + "loss": 3.8495, + "step": 2165248 + }, + { + "epoch": 0.01, + "learning_rate": 1.4540299391429169e-05, + "loss": 3.8658, + "step": 2165760 + }, + { + "epoch": 0.01, + "learning_rate": 1.4531913443918649e-05, + "loss": 3.8461, + "step": 2166272 + }, + { + "epoch": 0.01, + "learning_rate": 1.4523527496408129e-05, + "loss": 3.876, + "step": 2166784 + }, + { + "epoch": 0.01, + "learning_rate": 1.4515141548897609e-05, + "loss": 3.8625, + "step": 2167296 + }, + { + "epoch": 0.01, + "learning_rate": 1.450675560138709e-05, + "loss": 3.841, + "step": 2167808 + }, + { + "epoch": 0.01, + "learning_rate": 1.449836965387657e-05, + "loss": 3.8711, + "step": 2168320 + }, + { + "epoch": 0.01, + "learning_rate": 1.449000008516978e-05, + "loss": 3.85, + "step": 2168832 + }, + { + "epoch": 0.01, + "learning_rate": 1.4481614137659261e-05, + "loss": 3.8535, + "step": 2169344 + }, + { + "epoch": 0.01, + "learning_rate": 1.4473228190148741e-05, + "loss": 3.8583, + "step": 2169856 + }, + { + "epoch": 0.01, + "learning_rate": 1.4464842242638218e-05, + "loss": 3.8714, + "step": 2170368 + }, + { + "epoch": 0.01, + "learning_rate": 1.44564562951277e-05, + "loss": 3.8533, + "step": 2170880 + }, + { + "epoch": 0.01, + "learning_rate": 1.444807034761718e-05, + "loss": 3.8572, + "step": 2171392 + }, + { + "epoch": 0.01, + "learning_rate": 1.443968440010666e-05, + "loss": 3.8398, + "step": 2171904 + }, + { + "epoch": 0.01, + "learning_rate": 1.443131483139987e-05, + "loss": 3.8593, + "step": 2172416 + }, + { + "epoch": 0.01, + "learning_rate": 1.442292888388935e-05, + "loss": 3.8694, + "step": 2172928 + }, + { + "epoch": 0.01, + "learning_rate": 1.441454293637883e-05, + "loss": 3.867, + "step": 2173440 + }, + { + "epoch": 0.01, + "learning_rate": 1.440615698886831e-05, + "loss": 3.8612, + "step": 2173952 + }, + { + "epoch": 0.01, + "learning_rate": 1.4397771041357792e-05, + "loss": 3.8655, + "step": 2174464 + }, + { + "epoch": 0.01, + "learning_rate": 1.4389385093847272e-05, + "loss": 3.8773, + "step": 2174976 + }, + { + "epoch": 0.01, + "learning_rate": 1.4380999146336748e-05, + "loss": 3.86, + "step": 2175488 + }, + { + "epoch": 0.01, + "learning_rate": 1.4372629577629962e-05, + "loss": 3.8657, + "step": 2176000 + }, + { + "epoch": 0.01, + "learning_rate": 1.4364243630119442e-05, + "loss": 3.8554, + "step": 2176512 + }, + { + "epoch": 0.01, + "learning_rate": 1.4355857682608922e-05, + "loss": 3.8623, + "step": 2177024 + }, + { + "epoch": 0.01, + "learning_rate": 1.43474717350984e-05, + "loss": 3.8551, + "step": 2177536 + }, + { + "epoch": 0.01, + "learning_rate": 1.4339102166391613e-05, + "loss": 3.8582, + "step": 2178048 + }, + { + "epoch": 0.01, + "learning_rate": 1.4330716218881093e-05, + "loss": 3.8688, + "step": 2178560 + }, + { + "epoch": 0.01, + "learning_rate": 1.4322330271370573e-05, + "loss": 3.8665, + "step": 2179072 + }, + { + "epoch": 0.01, + "learning_rate": 1.4313944323860051e-05, + "loss": 3.8698, + "step": 2179584 + }, + { + "epoch": 0.01, + "learning_rate": 1.4305558376349531e-05, + "loss": 3.8491, + "step": 2180096 + }, + { + "epoch": 0.01, + "learning_rate": 1.4297188807642745e-05, + "loss": 3.8635, + "step": 2180608 + }, + { + "epoch": 0.01, + "learning_rate": 1.4288802860132222e-05, + "loss": 3.8643, + "step": 2181120 + }, + { + "epoch": 0.01, + "learning_rate": 1.4280433291425434e-05, + "loss": 3.8543, + "step": 2181632 + }, + { + "epoch": 0.01, + "learning_rate": 1.4272047343914916e-05, + "loss": 3.8569, + "step": 2182144 + }, + { + "epoch": 0.01, + "learning_rate": 1.4263661396404396e-05, + "loss": 3.868, + "step": 2182656 + }, + { + "epoch": 0.02, + "learning_rate": 1.4255275448893873e-05, + "loss": 3.862, + "step": 2183168 + }, + { + "epoch": 0.02, + "learning_rate": 1.4246889501383354e-05, + "loss": 3.8591, + "step": 2183680 + }, + { + "epoch": 0.02, + "learning_rate": 1.4238503553872834e-05, + "loss": 3.8552, + "step": 2184192 + }, + { + "epoch": 0.02, + "learning_rate": 1.4230117606362314e-05, + "loss": 3.8635, + "step": 2184704 + }, + { + "epoch": 0.02, + "learning_rate": 1.4221731658851794e-05, + "loss": 3.8712, + "step": 2185216 + }, + { + "epoch": 0.02, + "learning_rate": 1.4213345711341274e-05, + "loss": 3.8648, + "step": 2185728 + }, + { + "epoch": 0.02, + "learning_rate": 1.4204959763830756e-05, + "loss": 3.8517, + "step": 2186240 + }, + { + "epoch": 0.02, + "learning_rate": 1.4196573816320232e-05, + "loss": 3.8596, + "step": 2186752 + }, + { + "epoch": 0.02, + "learning_rate": 1.4188204247613446e-05, + "loss": 3.8546, + "step": 2187264 + }, + { + "epoch": 0.02, + "learning_rate": 1.4179818300102926e-05, + "loss": 3.8647, + "step": 2187776 + }, + { + "epoch": 0.02, + "learning_rate": 1.4171432352592403e-05, + "loss": 3.8726, + "step": 2188288 + }, + { + "epoch": 0.02, + "learning_rate": 1.4163046405081885e-05, + "loss": 3.8558, + "step": 2188800 + }, + { + "epoch": 0.02, + "learning_rate": 1.4154660457571365e-05, + "loss": 3.8596, + "step": 2189312 + }, + { + "epoch": 0.02, + "learning_rate": 1.4146274510060845e-05, + "loss": 3.8569, + "step": 2189824 + }, + { + "epoch": 0.02, + "learning_rate": 1.4137888562550325e-05, + "loss": 3.8529, + "step": 2190336 + }, + { + "epoch": 0.02, + "learning_rate": 1.4129502615039804e-05, + "loss": 3.849, + "step": 2190848 + }, + { + "epoch": 0.02, + "learning_rate": 1.4121133046333015e-05, + "loss": 3.8564, + "step": 2191360 + }, + { + "epoch": 0.02, + "learning_rate": 1.4112747098822495e-05, + "loss": 3.8556, + "step": 2191872 + }, + { + "epoch": 0.02, + "learning_rate": 1.4104377530115706e-05, + "loss": 3.8573, + "step": 2192384 + }, + { + "epoch": 0.02, + "learning_rate": 1.4095991582605186e-05, + "loss": 3.8503, + "step": 2192896 + }, + { + "epoch": 0.02, + "learning_rate": 1.4087605635094666e-05, + "loss": 3.8534, + "step": 2193408 + }, + { + "epoch": 0.02, + "learning_rate": 1.4079219687584148e-05, + "loss": 3.8526, + "step": 2193920 + }, + { + "epoch": 0.02, + "learning_rate": 1.4070833740073628e-05, + "loss": 3.8703, + "step": 2194432 + }, + { + "epoch": 0.02, + "learning_rate": 1.4062464171366838e-05, + "loss": 3.8528, + "step": 2194944 + }, + { + "epoch": 0.02, + "learning_rate": 1.4054078223856318e-05, + "loss": 3.8703, + "step": 2195456 + }, + { + "epoch": 0.02, + "learning_rate": 1.4045692276345798e-05, + "loss": 3.8672, + "step": 2195968 + }, + { + "epoch": 0.02, + "learning_rate": 1.4037322707639009e-05, + "loss": 3.8757, + "step": 2196480 + }, + { + "epoch": 0.02, + "learning_rate": 1.4028936760128489e-05, + "loss": 3.8609, + "step": 2196992 + }, + { + "epoch": 0.02, + "learning_rate": 1.4020550812617969e-05, + "loss": 3.857, + "step": 2197504 + }, + { + "epoch": 0.02, + "learning_rate": 1.4012164865107449e-05, + "loss": 3.8613, + "step": 2198016 + }, + { + "epoch": 0.02, + "learning_rate": 1.400377891759693e-05, + "loss": 3.8645, + "step": 2198528 + }, + { + "epoch": 0.02, + "learning_rate": 1.399539297008641e-05, + "loss": 3.8614, + "step": 2199040 + }, + { + "epoch": 0.02, + "learning_rate": 1.3987007022575887e-05, + "loss": 3.8631, + "step": 2199552 + }, + { + "epoch": 0.02, + "learning_rate": 1.3978621075065369e-05, + "loss": 3.8578, + "step": 2200064 + }, + { + "epoch": 0.02, + "learning_rate": 1.3970251506358581e-05, + "loss": 3.8723, + "step": 2200576 + }, + { + "epoch": 0.02, + "learning_rate": 1.3961865558848058e-05, + "loss": 3.8584, + "step": 2201088 + }, + { + "epoch": 0.02, + "learning_rate": 1.395347961133754e-05, + "loss": 3.8554, + "step": 2201600 + }, + { + "epoch": 0.02, + "learning_rate": 1.3945110042630752e-05, + "loss": 3.8583, + "step": 2202112 + }, + { + "epoch": 0.02, + "learning_rate": 1.3936724095120232e-05, + "loss": 3.8546, + "step": 2202624 + }, + { + "epoch": 0.02, + "learning_rate": 1.392833814760971e-05, + "loss": 3.8761, + "step": 2203136 + }, + { + "epoch": 0.02, + "learning_rate": 1.391995220009919e-05, + "loss": 3.856, + "step": 2203648 + }, + { + "epoch": 0.02, + "learning_rate": 1.391156625258867e-05, + "loss": 3.8695, + "step": 2204160 + }, + { + "epoch": 0.02, + "learning_rate": 1.390318030507815e-05, + "loss": 3.8542, + "step": 2204672 + }, + { + "epoch": 0.02, + "learning_rate": 1.3894794357567632e-05, + "loss": 3.8658, + "step": 2205184 + }, + { + "epoch": 0.02, + "learning_rate": 1.3886408410057112e-05, + "loss": 3.865, + "step": 2205696 + }, + { + "epoch": 0.02, + "learning_rate": 1.3878022462546592e-05, + "loss": 3.8641, + "step": 2206208 + }, + { + "epoch": 0.02, + "learning_rate": 1.386963651503607e-05, + "loss": 3.8602, + "step": 2206720 + }, + { + "epoch": 0.02, + "learning_rate": 1.386125056752555e-05, + "loss": 3.8645, + "step": 2207232 + }, + { + "epoch": 0.02, + "learning_rate": 1.385286462001503e-05, + "loss": 3.8701, + "step": 2207744 + }, + { + "epoch": 0.02, + "learning_rate": 1.384449505130824e-05, + "loss": 3.8774, + "step": 2208256 + }, + { + "epoch": 0.02, + "learning_rate": 1.3836125482601453e-05, + "loss": 3.8524, + "step": 2208768 + }, + { + "epoch": 0.02, + "learning_rate": 1.3827739535090933e-05, + "loss": 3.8565, + "step": 2209280 + }, + { + "epoch": 0.02, + "learning_rate": 1.3819353587580413e-05, + "loss": 3.8626, + "step": 2209792 + }, + { + "epoch": 0.02, + "learning_rate": 1.3810967640069891e-05, + "loss": 3.856, + "step": 2210304 + }, + { + "epoch": 0.02, + "learning_rate": 1.3802581692559371e-05, + "loss": 3.8561, + "step": 2210816 + }, + { + "epoch": 0.02, + "learning_rate": 1.3794195745048851e-05, + "loss": 3.8669, + "step": 2211328 + }, + { + "epoch": 0.02, + "learning_rate": 1.3785809797538333e-05, + "loss": 3.8577, + "step": 2211840 + }, + { + "epoch": 0.02, + "learning_rate": 1.3777423850027813e-05, + "loss": 3.8666, + "step": 2212352 + }, + { + "epoch": 0.02, + "learning_rate": 1.3769037902517293e-05, + "loss": 3.8624, + "step": 2212864 + }, + { + "epoch": 0.03, + "eval_loss": 3.9783999919891357, + "eval_runtime": 304.1458, + "eval_samples_per_second": 1254.632, + "eval_steps_per_second": 39.208, + "step": 2213280 + }, + { + "epoch": 0.0, + "learning_rate": 1.3760651955006771e-05, + "loss": 3.8587, + "step": 2213376 + }, + { + "epoch": 0.0, + "learning_rate": 1.375226600749625e-05, + "loss": 3.8489, + "step": 2213888 + }, + { + "epoch": 0.0, + "learning_rate": 1.374388005998573e-05, + "loss": 3.8628, + "step": 2214400 + }, + { + "epoch": 0.0, + "learning_rate": 1.373549411247521e-05, + "loss": 3.8613, + "step": 2214912 + }, + { + "epoch": 0.0, + "learning_rate": 1.372710816496469e-05, + "loss": 3.8623, + "step": 2215424 + }, + { + "epoch": 0.0, + "learning_rate": 1.3718722217454172e-05, + "loss": 3.858, + "step": 2215936 + }, + { + "epoch": 0.0, + "learning_rate": 1.3710336269943652e-05, + "loss": 3.8627, + "step": 2216448 + }, + { + "epoch": 0.0, + "learning_rate": 1.3701950322433129e-05, + "loss": 3.8571, + "step": 2216960 + }, + { + "epoch": 0.0, + "learning_rate": 1.369356437492261e-05, + "loss": 3.8573, + "step": 2217472 + }, + { + "epoch": 0.0, + "learning_rate": 1.368517842741209e-05, + "loss": 3.8591, + "step": 2217984 + }, + { + "epoch": 0.0, + "learning_rate": 1.367679247990157e-05, + "loss": 3.8587, + "step": 2218496 + }, + { + "epoch": 0.0, + "learning_rate": 1.366840653239105e-05, + "loss": 3.8673, + "step": 2219008 + }, + { + "epoch": 0.0, + "learning_rate": 1.3660036963684261e-05, + "loss": 3.8753, + "step": 2219520 + }, + { + "epoch": 0.0, + "learning_rate": 1.3651651016173741e-05, + "loss": 3.8501, + "step": 2220032 + }, + { + "epoch": 0.0, + "learning_rate": 1.3643265068663221e-05, + "loss": 3.8569, + "step": 2220544 + }, + { + "epoch": 0.0, + "learning_rate": 1.3634879121152703e-05, + "loss": 3.8528, + "step": 2221056 + }, + { + "epoch": 0.0, + "learning_rate": 1.3626493173642183e-05, + "loss": 3.8552, + "step": 2221568 + }, + { + "epoch": 0.0, + "learning_rate": 1.361810722613166e-05, + "loss": 3.8599, + "step": 2222080 + }, + { + "epoch": 0.0, + "learning_rate": 1.3609721278621141e-05, + "loss": 3.8508, + "step": 2222592 + }, + { + "epoch": 0.0, + "learning_rate": 1.3601335331110621e-05, + "loss": 3.8566, + "step": 2223104 + }, + { + "epoch": 0.0, + "learning_rate": 1.3592965762403833e-05, + "loss": 3.8731, + "step": 2223616 + }, + { + "epoch": 0.0, + "learning_rate": 1.3584579814893312e-05, + "loss": 3.8616, + "step": 2224128 + }, + { + "epoch": 0.0, + "learning_rate": 1.3576193867382792e-05, + "loss": 3.8717, + "step": 2224640 + }, + { + "epoch": 0.0, + "learning_rate": 1.3567807919872272e-05, + "loss": 3.8709, + "step": 2225152 + }, + { + "epoch": 0.0, + "learning_rate": 1.3559421972361751e-05, + "loss": 3.8563, + "step": 2225664 + }, + { + "epoch": 0.0, + "learning_rate": 1.3551036024851233e-05, + "loss": 3.8654, + "step": 2226176 + }, + { + "epoch": 0.0, + "learning_rate": 1.3542650077340713e-05, + "loss": 3.8533, + "step": 2226688 + }, + { + "epoch": 0.0, + "learning_rate": 1.3534280508633924e-05, + "loss": 3.8586, + "step": 2227200 + }, + { + "epoch": 0.0, + "learning_rate": 1.3525894561123404e-05, + "loss": 3.8559, + "step": 2227712 + }, + { + "epoch": 0.0, + "learning_rate": 1.3517508613612884e-05, + "loss": 3.8526, + "step": 2228224 + }, + { + "epoch": 0.01, + "learning_rate": 1.3509122666102364e-05, + "loss": 3.8646, + "step": 2228736 + }, + { + "epoch": 0.01, + "learning_rate": 1.3500736718591842e-05, + "loss": 3.8582, + "step": 2229248 + }, + { + "epoch": 0.01, + "learning_rate": 1.3492350771081322e-05, + "loss": 3.8641, + "step": 2229760 + }, + { + "epoch": 0.01, + "learning_rate": 1.3483964823570802e-05, + "loss": 3.8589, + "step": 2230272 + }, + { + "epoch": 0.01, + "learning_rate": 1.3475578876060282e-05, + "loss": 3.8584, + "step": 2230784 + }, + { + "epoch": 0.01, + "learning_rate": 1.3467225686157225e-05, + "loss": 3.8644, + "step": 2231296 + }, + { + "epoch": 0.01, + "learning_rate": 1.3458839738646705e-05, + "loss": 3.8685, + "step": 2231808 + }, + { + "epoch": 0.01, + "learning_rate": 1.3450453791136187e-05, + "loss": 3.841, + "step": 2232320 + }, + { + "epoch": 0.01, + "learning_rate": 1.3442067843625667e-05, + "loss": 3.8593, + "step": 2232832 + }, + { + "epoch": 0.01, + "learning_rate": 1.3433681896115143e-05, + "loss": 3.8548, + "step": 2233344 + }, + { + "epoch": 0.01, + "learning_rate": 1.3425312327408358e-05, + "loss": 3.8465, + "step": 2233856 + }, + { + "epoch": 0.01, + "learning_rate": 1.3416926379897837e-05, + "loss": 3.8577, + "step": 2234368 + }, + { + "epoch": 0.01, + "learning_rate": 1.3408540432387314e-05, + "loss": 3.8668, + "step": 2234880 + }, + { + "epoch": 0.01, + "learning_rate": 1.3400154484876796e-05, + "loss": 3.8602, + "step": 2235392 + }, + { + "epoch": 0.01, + "learning_rate": 1.3391768537366276e-05, + "loss": 3.8627, + "step": 2235904 + }, + { + "epoch": 0.01, + "learning_rate": 1.3383382589855756e-05, + "loss": 3.8629, + "step": 2236416 + }, + { + "epoch": 0.01, + "learning_rate": 1.3374996642345236e-05, + "loss": 3.8639, + "step": 2236928 + }, + { + "epoch": 0.01, + "learning_rate": 1.3366610694834717e-05, + "loss": 3.8572, + "step": 2237440 + }, + { + "epoch": 0.01, + "learning_rate": 1.3358224747324197e-05, + "loss": 3.8383, + "step": 2237952 + }, + { + "epoch": 0.01, + "learning_rate": 1.3349838799813674e-05, + "loss": 3.8645, + "step": 2238464 + }, + { + "epoch": 0.01, + "learning_rate": 1.3341452852303155e-05, + "loss": 3.8563, + "step": 2238976 + }, + { + "epoch": 0.01, + "learning_rate": 1.3333083283596368e-05, + "loss": 3.861, + "step": 2239488 + }, + { + "epoch": 0.01, + "learning_rate": 1.3324697336085848e-05, + "loss": 3.8521, + "step": 2240000 + }, + { + "epoch": 0.01, + "learning_rate": 1.3316311388575326e-05, + "loss": 3.8481, + "step": 2240512 + }, + { + "epoch": 0.01, + "learning_rate": 1.3307925441064806e-05, + "loss": 3.8506, + "step": 2241024 + }, + { + "epoch": 0.01, + "learning_rate": 1.3299539493554286e-05, + "loss": 3.8448, + "step": 2241536 + }, + { + "epoch": 0.01, + "learning_rate": 1.3291169924847497e-05, + "loss": 3.8638, + "step": 2242048 + }, + { + "epoch": 0.01, + "learning_rate": 1.328280035614071e-05, + "loss": 3.846, + "step": 2242560 + }, + { + "epoch": 0.01, + "learning_rate": 1.327441440863019e-05, + "loss": 3.8679, + "step": 2243072 + }, + { + "epoch": 0.01, + "learning_rate": 1.3266028461119671e-05, + "loss": 3.8599, + "step": 2243584 + }, + { + "epoch": 0.01, + "learning_rate": 1.3257642513609147e-05, + "loss": 3.8395, + "step": 2244096 + }, + { + "epoch": 0.01, + "learning_rate": 1.3249256566098627e-05, + "loss": 3.8636, + "step": 2244608 + }, + { + "epoch": 0.01, + "learning_rate": 1.3240870618588107e-05, + "loss": 3.8465, + "step": 2245120 + }, + { + "epoch": 0.01, + "learning_rate": 1.3232484671077589e-05, + "loss": 3.8493, + "step": 2245632 + }, + { + "epoch": 0.01, + "learning_rate": 1.3224098723567069e-05, + "loss": 3.8487, + "step": 2246144 + }, + { + "epoch": 0.01, + "learning_rate": 1.321572915486028e-05, + "loss": 3.8686, + "step": 2246656 + }, + { + "epoch": 0.01, + "learning_rate": 1.320734320734976e-05, + "loss": 3.8518, + "step": 2247168 + }, + { + "epoch": 0.01, + "learning_rate": 1.319895725983924e-05, + "loss": 3.8506, + "step": 2247680 + }, + { + "epoch": 0.01, + "learning_rate": 1.319058769113245e-05, + "loss": 3.8344, + "step": 2248192 + }, + { + "epoch": 0.01, + "learning_rate": 1.318220174362193e-05, + "loss": 3.8535, + "step": 2248704 + }, + { + "epoch": 0.01, + "learning_rate": 1.317381579611141e-05, + "loss": 3.8661, + "step": 2249216 + }, + { + "epoch": 0.01, + "learning_rate": 1.316542984860089e-05, + "loss": 3.8669, + "step": 2249728 + }, + { + "epoch": 0.01, + "learning_rate": 1.3157043901090372e-05, + "loss": 3.8556, + "step": 2250240 + }, + { + "epoch": 0.01, + "learning_rate": 1.3148657953579852e-05, + "loss": 3.8622, + "step": 2250752 + }, + { + "epoch": 0.01, + "learning_rate": 1.3140288384873061e-05, + "loss": 3.8727, + "step": 2251264 + }, + { + "epoch": 0.01, + "learning_rate": 1.3131902437362543e-05, + "loss": 3.8534, + "step": 2251776 + }, + { + "epoch": 0.01, + "learning_rate": 1.3123532868655752e-05, + "loss": 3.8586, + "step": 2252288 + }, + { + "epoch": 0.01, + "learning_rate": 1.3115146921145233e-05, + "loss": 3.8566, + "step": 2252800 + }, + { + "epoch": 0.01, + "learning_rate": 1.3106760973634713e-05, + "loss": 3.856, + "step": 2253312 + }, + { + "epoch": 0.01, + "learning_rate": 1.3098375026124193e-05, + "loss": 3.8499, + "step": 2253824 + }, + { + "epoch": 0.01, + "learning_rate": 1.3089989078613673e-05, + "loss": 3.8583, + "step": 2254336 + }, + { + "epoch": 0.01, + "learning_rate": 1.3081603131103152e-05, + "loss": 3.8671, + "step": 2254848 + }, + { + "epoch": 0.01, + "learning_rate": 1.3073217183592631e-05, + "loss": 3.8653, + "step": 2255360 + }, + { + "epoch": 0.01, + "learning_rate": 1.3064831236082111e-05, + "loss": 3.8628, + "step": 2255872 + }, + { + "epoch": 0.01, + "learning_rate": 1.3056461667375326e-05, + "loss": 3.8451, + "step": 2256384 + }, + { + "epoch": 0.01, + "learning_rate": 1.3048075719864802e-05, + "loss": 3.8608, + "step": 2256896 + }, + { + "epoch": 0.01, + "learning_rate": 1.3039689772354282e-05, + "loss": 3.8601, + "step": 2257408 + }, + { + "epoch": 0.01, + "learning_rate": 1.3031303824843764e-05, + "loss": 3.8522, + "step": 2257920 + }, + { + "epoch": 0.01, + "learning_rate": 1.3022917877333244e-05, + "loss": 3.8534, + "step": 2258432 + }, + { + "epoch": 0.01, + "learning_rate": 1.3014531929822724e-05, + "loss": 3.8619, + "step": 2258944 + }, + { + "epoch": 0.02, + "learning_rate": 1.3006145982312204e-05, + "loss": 3.8574, + "step": 2259456 + }, + { + "epoch": 0.02, + "learning_rate": 1.2997760034801682e-05, + "loss": 3.8576, + "step": 2259968 + }, + { + "epoch": 0.02, + "learning_rate": 1.2989406844898625e-05, + "loss": 3.8491, + "step": 2260480 + }, + { + "epoch": 0.02, + "learning_rate": 1.2981020897388105e-05, + "loss": 3.8632, + "step": 2260992 + }, + { + "epoch": 0.02, + "learning_rate": 1.2972634949877585e-05, + "loss": 3.8652, + "step": 2261504 + }, + { + "epoch": 0.02, + "learning_rate": 1.2964249002367065e-05, + "loss": 3.8605, + "step": 2262016 + }, + { + "epoch": 0.02, + "learning_rate": 1.2955863054856545e-05, + "loss": 3.8426, + "step": 2262528 + }, + { + "epoch": 0.02, + "learning_rate": 1.2947477107346027e-05, + "loss": 3.8587, + "step": 2263040 + }, + { + "epoch": 0.02, + "learning_rate": 1.2939091159835507e-05, + "loss": 3.8519, + "step": 2263552 + }, + { + "epoch": 0.02, + "learning_rate": 1.2930705212324983e-05, + "loss": 3.8584, + "step": 2264064 + }, + { + "epoch": 0.02, + "learning_rate": 1.2922319264814465e-05, + "loss": 3.8718, + "step": 2264576 + }, + { + "epoch": 0.02, + "learning_rate": 1.2913949696107677e-05, + "loss": 3.8504, + "step": 2265088 + }, + { + "epoch": 0.02, + "learning_rate": 1.2905563748597154e-05, + "loss": 3.8554, + "step": 2265600 + }, + { + "epoch": 0.02, + "learning_rate": 1.2897177801086636e-05, + "loss": 3.8501, + "step": 2266112 + }, + { + "epoch": 0.02, + "learning_rate": 1.2888791853576116e-05, + "loss": 3.8545, + "step": 2266624 + }, + { + "epoch": 0.02, + "learning_rate": 1.2880405906065595e-05, + "loss": 3.8431, + "step": 2267136 + }, + { + "epoch": 0.02, + "learning_rate": 1.2872019958555075e-05, + "loss": 3.8499, + "step": 2267648 + }, + { + "epoch": 0.02, + "learning_rate": 1.2863634011044557e-05, + "loss": 3.852, + "step": 2268160 + }, + { + "epoch": 0.02, + "learning_rate": 1.2855248063534037e-05, + "loss": 3.8551, + "step": 2268672 + }, + { + "epoch": 0.02, + "learning_rate": 1.2846878494827246e-05, + "loss": 3.8477, + "step": 2269184 + }, + { + "epoch": 0.02, + "learning_rate": 1.2838508926120457e-05, + "loss": 3.8498, + "step": 2269696 + }, + { + "epoch": 0.02, + "learning_rate": 1.2830122978609937e-05, + "loss": 3.8487, + "step": 2270208 + }, + { + "epoch": 0.02, + "learning_rate": 1.2821737031099419e-05, + "loss": 3.8657, + "step": 2270720 + }, + { + "epoch": 0.02, + "learning_rate": 1.2813351083588899e-05, + "loss": 3.8519, + "step": 2271232 + }, + { + "epoch": 0.02, + "learning_rate": 1.2804997893685842e-05, + "loss": 3.8647, + "step": 2271744 + }, + { + "epoch": 0.02, + "learning_rate": 1.2796611946175322e-05, + "loss": 3.8656, + "step": 2272256 + }, + { + "epoch": 0.02, + "learning_rate": 1.2788225998664802e-05, + "loss": 3.873, + "step": 2272768 + }, + { + "epoch": 0.02, + "learning_rate": 1.277984005115428e-05, + "loss": 3.8562, + "step": 2273280 + }, + { + "epoch": 0.02, + "learning_rate": 1.277145410364376e-05, + "loss": 3.8521, + "step": 2273792 + }, + { + "epoch": 0.02, + "learning_rate": 1.276306815613324e-05, + "loss": 3.859, + "step": 2274304 + }, + { + "epoch": 0.02, + "learning_rate": 1.275468220862272e-05, + "loss": 3.8574, + "step": 2274816 + }, + { + "epoch": 0.02, + "learning_rate": 1.274631263991593e-05, + "loss": 3.8566, + "step": 2275328 + }, + { + "epoch": 0.02, + "learning_rate": 1.273792669240541e-05, + "loss": 3.8583, + "step": 2275840 + }, + { + "epoch": 0.02, + "learning_rate": 1.272954074489489e-05, + "loss": 3.8567, + "step": 2276352 + }, + { + "epoch": 0.02, + "learning_rate": 1.2721154797384372e-05, + "loss": 3.8653, + "step": 2276864 + }, + { + "epoch": 0.02, + "learning_rate": 1.2712768849873852e-05, + "loss": 3.8559, + "step": 2277376 + }, + { + "epoch": 0.02, + "learning_rate": 1.2704382902363332e-05, + "loss": 3.8513, + "step": 2277888 + }, + { + "epoch": 0.02, + "learning_rate": 1.269599695485281e-05, + "loss": 3.8533, + "step": 2278400 + }, + { + "epoch": 0.02, + "learning_rate": 1.2687627386146023e-05, + "loss": 3.8539, + "step": 2278912 + }, + { + "epoch": 0.02, + "learning_rate": 1.2679241438635503e-05, + "loss": 3.8633, + "step": 2279424 + }, + { + "epoch": 0.02, + "learning_rate": 1.2670855491124983e-05, + "loss": 3.8586, + "step": 2279936 + }, + { + "epoch": 0.02, + "learning_rate": 1.2662469543614461e-05, + "loss": 3.862, + "step": 2280448 + }, + { + "epoch": 0.02, + "learning_rate": 1.2654083596103941e-05, + "loss": 3.8532, + "step": 2280960 + }, + { + "epoch": 0.02, + "learning_rate": 1.2645697648593421e-05, + "loss": 3.8605, + "step": 2281472 + }, + { + "epoch": 0.02, + "learning_rate": 1.2637311701082901e-05, + "loss": 3.8644, + "step": 2281984 + }, + { + "epoch": 0.02, + "learning_rate": 1.2628925753572383e-05, + "loss": 3.8576, + "step": 2282496 + }, + { + "epoch": 0.02, + "learning_rate": 1.2620539806061863e-05, + "loss": 3.8576, + "step": 2283008 + }, + { + "epoch": 0.02, + "learning_rate": 1.2612153858551339e-05, + "loss": 3.8572, + "step": 2283520 + }, + { + "epoch": 0.02, + "learning_rate": 1.260376791104082e-05, + "loss": 3.8646, + "step": 2284032 + }, + { + "epoch": 0.02, + "learning_rate": 1.2595398342334033e-05, + "loss": 3.8751, + "step": 2284544 + }, + { + "epoch": 0.02, + "learning_rate": 1.2587012394823513e-05, + "loss": 3.8511, + "step": 2285056 + }, + { + "epoch": 0.02, + "learning_rate": 1.2578626447312991e-05, + "loss": 3.8518, + "step": 2285568 + }, + { + "epoch": 0.02, + "learning_rate": 1.2570240499802471e-05, + "loss": 3.8559, + "step": 2286080 + }, + { + "epoch": 0.02, + "learning_rate": 1.2561854552291951e-05, + "loss": 3.8549, + "step": 2286592 + }, + { + "epoch": 0.02, + "learning_rate": 1.2553468604781431e-05, + "loss": 3.8513, + "step": 2287104 + }, + { + "epoch": 0.02, + "learning_rate": 1.2545082657270913e-05, + "loss": 3.8649, + "step": 2287616 + }, + { + "epoch": 0.02, + "learning_rate": 1.2536713088564122e-05, + "loss": 3.8537, + "step": 2288128 + }, + { + "epoch": 0.02, + "learning_rate": 1.2528327141053604e-05, + "loss": 3.8626, + "step": 2288640 + }, + { + "epoch": 0.02, + "learning_rate": 1.2519957572346813e-05, + "loss": 3.8527, + "step": 2289152 + }, + { + "epoch": 0.03, + "eval_loss": 3.977250099182129, + "eval_runtime": 290.2379, + "eval_samples_per_second": 1314.752, + "eval_steps_per_second": 41.087, + "step": 2289600 + }, + { + "epoch": 1.0, + "learning_rate": 1.2511571624836293e-05, + "loss": 3.8586, + "step": 2289664 + }, + { + "epoch": 1.0, + "learning_rate": 1.2503185677325774e-05, + "loss": 3.8492, + "step": 2290176 + }, + { + "epoch": 1.0, + "learning_rate": 1.2494799729815254e-05, + "loss": 3.8594, + "step": 2290688 + }, + { + "epoch": 1.0, + "learning_rate": 1.2486413782304734e-05, + "loss": 3.8582, + "step": 2291200 + }, + { + "epoch": 1.0, + "learning_rate": 1.2478027834794213e-05, + "loss": 3.8595, + "step": 2291712 + }, + { + "epoch": 1.0, + "learning_rate": 1.2469641887283694e-05, + "loss": 3.8529, + "step": 2292224 + }, + { + "epoch": 1.0, + "learning_rate": 1.2461255939773174e-05, + "loss": 3.8551, + "step": 2292736 + }, + { + "epoch": 1.0, + "learning_rate": 1.2452869992262654e-05, + "loss": 3.8536, + "step": 2293248 + }, + { + "epoch": 1.0, + "learning_rate": 1.2444484044752134e-05, + "loss": 3.8544, + "step": 2293760 + }, + { + "epoch": 1.0, + "learning_rate": 1.2436098097241614e-05, + "loss": 3.857, + "step": 2294272 + }, + { + "epoch": 1.0, + "learning_rate": 1.2427712149731094e-05, + "loss": 3.8566, + "step": 2294784 + }, + { + "epoch": 1.0, + "learning_rate": 1.2419358959828037e-05, + "loss": 3.8658, + "step": 2295296 + }, + { + "epoch": 1.0, + "learning_rate": 1.2410989391121246e-05, + "loss": 3.8694, + "step": 2295808 + }, + { + "epoch": 1.0, + "learning_rate": 1.2402603443610728e-05, + "loss": 3.8464, + "step": 2296320 + }, + { + "epoch": 1.0, + "learning_rate": 1.2394217496100208e-05, + "loss": 3.8548, + "step": 2296832 + }, + { + "epoch": 1.0, + "learning_rate": 1.2385831548589686e-05, + "loss": 3.8459, + "step": 2297344 + }, + { + "epoch": 1.0, + "learning_rate": 1.2377445601079166e-05, + "loss": 3.8525, + "step": 2297856 + }, + { + "epoch": 1.0, + "learning_rate": 1.2369059653568648e-05, + "loss": 3.8521, + "step": 2298368 + }, + { + "epoch": 1.0, + "learning_rate": 1.2360673706058128e-05, + "loss": 3.8515, + "step": 2298880 + }, + { + "epoch": 1.0, + "learning_rate": 1.2352287758547606e-05, + "loss": 3.8471, + "step": 2299392 + }, + { + "epoch": 1.0, + "learning_rate": 1.2343901811037086e-05, + "loss": 3.8714, + "step": 2299904 + }, + { + "epoch": 1.0, + "learning_rate": 1.2335515863526568e-05, + "loss": 3.8582, + "step": 2300416 + }, + { + "epoch": 1.0, + "learning_rate": 1.2327129916016046e-05, + "loss": 3.8677, + "step": 2300928 + }, + { + "epoch": 1.0, + "learning_rate": 1.231877672611299e-05, + "loss": 3.8631, + "step": 2301440 + }, + { + "epoch": 1.0, + "learning_rate": 1.231039077860247e-05, + "loss": 3.8605, + "step": 2301952 + }, + { + "epoch": 1.0, + "learning_rate": 1.230200483109195e-05, + "loss": 3.857, + "step": 2302464 + }, + { + "epoch": 1.0, + "learning_rate": 1.229361888358143e-05, + "loss": 3.8495, + "step": 2302976 + }, + { + "epoch": 1.0, + "learning_rate": 1.2285232936070909e-05, + "loss": 3.8549, + "step": 2303488 + }, + { + "epoch": 1.0, + "learning_rate": 1.2276846988560389e-05, + "loss": 3.853, + "step": 2304000 + }, + { + "epoch": 1.0, + "learning_rate": 1.2268461041049869e-05, + "loss": 3.85, + "step": 2304512 + }, + { + "epoch": 1.01, + "learning_rate": 1.2260075093539349e-05, + "loss": 3.8587, + "step": 2305024 + }, + { + "epoch": 1.01, + "learning_rate": 1.225170552483256e-05, + "loss": 3.85, + "step": 2305536 + }, + { + "epoch": 1.01, + "learning_rate": 1.224331957732204e-05, + "loss": 3.8619, + "step": 2306048 + }, + { + "epoch": 1.01, + "learning_rate": 1.223493362981152e-05, + "loss": 3.8542, + "step": 2306560 + }, + { + "epoch": 1.01, + "learning_rate": 1.2226547682301e-05, + "loss": 3.856, + "step": 2307072 + }, + { + "epoch": 1.01, + "learning_rate": 1.221816173479048e-05, + "loss": 3.8669, + "step": 2307584 + }, + { + "epoch": 1.01, + "learning_rate": 1.220977578727996e-05, + "loss": 3.8611, + "step": 2308096 + }, + { + "epoch": 1.01, + "learning_rate": 1.220138983976944e-05, + "loss": 3.8369, + "step": 2308608 + }, + { + "epoch": 1.01, + "learning_rate": 1.219300389225892e-05, + "loss": 3.8568, + "step": 2309120 + }, + { + "epoch": 1.01, + "learning_rate": 1.21846179447484e-05, + "loss": 3.8506, + "step": 2309632 + }, + { + "epoch": 1.01, + "learning_rate": 1.217623199723788e-05, + "loss": 3.8398, + "step": 2310144 + }, + { + "epoch": 1.01, + "learning_rate": 1.216784604972736e-05, + "loss": 3.858, + "step": 2310656 + }, + { + "epoch": 1.01, + "learning_rate": 1.215946010221684e-05, + "loss": 3.8643, + "step": 2311168 + }, + { + "epoch": 1.01, + "learning_rate": 1.215109053351005e-05, + "loss": 3.8517, + "step": 2311680 + }, + { + "epoch": 1.01, + "learning_rate": 1.214270458599953e-05, + "loss": 3.8589, + "step": 2312192 + }, + { + "epoch": 1.01, + "learning_rate": 1.213431863848901e-05, + "loss": 3.8617, + "step": 2312704 + }, + { + "epoch": 1.01, + "learning_rate": 1.212593269097849e-05, + "loss": 3.8582, + "step": 2313216 + }, + { + "epoch": 1.01, + "learning_rate": 1.21175631222717e-05, + "loss": 3.8549, + "step": 2313728 + }, + { + "epoch": 1.01, + "learning_rate": 1.210917717476118e-05, + "loss": 3.8387, + "step": 2314240 + }, + { + "epoch": 1.01, + "learning_rate": 1.2100807606054393e-05, + "loss": 3.8571, + "step": 2314752 + }, + { + "epoch": 1.01, + "learning_rate": 1.2092421658543871e-05, + "loss": 3.8541, + "step": 2315264 + }, + { + "epoch": 1.01, + "learning_rate": 1.2084035711033351e-05, + "loss": 3.8546, + "step": 2315776 + }, + { + "epoch": 1.01, + "learning_rate": 1.2075649763522833e-05, + "loss": 3.8472, + "step": 2316288 + }, + { + "epoch": 1.01, + "learning_rate": 1.2067280194816044e-05, + "loss": 3.8468, + "step": 2316800 + }, + { + "epoch": 1.01, + "learning_rate": 1.2058894247305524e-05, + "loss": 3.8425, + "step": 2317312 + }, + { + "epoch": 1.01, + "learning_rate": 1.2050508299795004e-05, + "loss": 3.8436, + "step": 2317824 + }, + { + "epoch": 1.01, + "learning_rate": 1.2042122352284484e-05, + "loss": 3.8642, + "step": 2318336 + }, + { + "epoch": 1.01, + "learning_rate": 1.2033736404773962e-05, + "loss": 3.8396, + "step": 2318848 + }, + { + "epoch": 1.01, + "learning_rate": 1.2025366836067174e-05, + "loss": 3.8609, + "step": 2319360 + }, + { + "epoch": 1.01, + "learning_rate": 1.2016980888556654e-05, + "loss": 3.8546, + "step": 2319872 + }, + { + "epoch": 1.01, + "learning_rate": 1.2008594941046134e-05, + "loss": 3.8405, + "step": 2320384 + }, + { + "epoch": 1.01, + "learning_rate": 1.2000208993535614e-05, + "loss": 3.8539, + "step": 2320896 + }, + { + "epoch": 1.01, + "learning_rate": 1.1991823046025094e-05, + "loss": 3.8465, + "step": 2321408 + }, + { + "epoch": 1.01, + "learning_rate": 1.1983437098514574e-05, + "loss": 3.8473, + "step": 2321920 + }, + { + "epoch": 1.01, + "learning_rate": 1.1975067529807787e-05, + "loss": 3.8424, + "step": 2322432 + }, + { + "epoch": 1.01, + "learning_rate": 1.1966681582297265e-05, + "loss": 3.8673, + "step": 2322944 + }, + { + "epoch": 1.01, + "learning_rate": 1.1958295634786745e-05, + "loss": 3.8515, + "step": 2323456 + }, + { + "epoch": 1.01, + "learning_rate": 1.1949909687276225e-05, + "loss": 3.8416, + "step": 2323968 + }, + { + "epoch": 1.01, + "learning_rate": 1.1941523739765705e-05, + "loss": 3.833, + "step": 2324480 + }, + { + "epoch": 1.01, + "learning_rate": 1.1933154171058916e-05, + "loss": 3.8472, + "step": 2324992 + }, + { + "epoch": 1.01, + "learning_rate": 1.1924768223548397e-05, + "loss": 3.8604, + "step": 2325504 + }, + { + "epoch": 1.01, + "learning_rate": 1.1916382276037877e-05, + "loss": 3.8662, + "step": 2326016 + }, + { + "epoch": 1.01, + "learning_rate": 1.1907996328527355e-05, + "loss": 3.8483, + "step": 2326528 + }, + { + "epoch": 1.01, + "learning_rate": 1.1899610381016835e-05, + "loss": 3.8628, + "step": 2327040 + }, + { + "epoch": 1.01, + "learning_rate": 1.1891224433506317e-05, + "loss": 3.8643, + "step": 2327552 + }, + { + "epoch": 1.01, + "learning_rate": 1.1882838485995795e-05, + "loss": 3.8531, + "step": 2328064 + }, + { + "epoch": 1.01, + "learning_rate": 1.1874468917289006e-05, + "loss": 3.851, + "step": 2328576 + }, + { + "epoch": 1.01, + "learning_rate": 1.1866082969778488e-05, + "loss": 3.8516, + "step": 2329088 + }, + { + "epoch": 1.01, + "learning_rate": 1.1857697022267968e-05, + "loss": 3.8554, + "step": 2329600 + }, + { + "epoch": 1.01, + "learning_rate": 1.1849311074757446e-05, + "loss": 3.8464, + "step": 2330112 + }, + { + "epoch": 1.01, + "learning_rate": 1.1840941506050658e-05, + "loss": 3.8517, + "step": 2330624 + }, + { + "epoch": 1.01, + "learning_rate": 1.1832555558540138e-05, + "loss": 3.8622, + "step": 2331136 + }, + { + "epoch": 1.01, + "learning_rate": 1.1824169611029617e-05, + "loss": 3.8638, + "step": 2331648 + }, + { + "epoch": 1.01, + "learning_rate": 1.1815783663519098e-05, + "loss": 3.8553, + "step": 2332160 + }, + { + "epoch": 1.01, + "learning_rate": 1.1807397716008578e-05, + "loss": 3.8415, + "step": 2332672 + }, + { + "epoch": 1.01, + "learning_rate": 1.1799028147301789e-05, + "loss": 3.8559, + "step": 2333184 + }, + { + "epoch": 1.01, + "learning_rate": 1.1790642199791269e-05, + "loss": 3.8542, + "step": 2333696 + }, + { + "epoch": 1.01, + "learning_rate": 1.178227263108448e-05, + "loss": 3.8527, + "step": 2334208 + }, + { + "epoch": 1.01, + "learning_rate": 1.177388668357396e-05, + "loss": 3.8508, + "step": 2334720 + }, + { + "epoch": 1.01, + "learning_rate": 1.1765500736063441e-05, + "loss": 3.8558, + "step": 2335232 + }, + { + "epoch": 1.02, + "learning_rate": 1.175711478855292e-05, + "loss": 3.8552, + "step": 2335744 + }, + { + "epoch": 1.02, + "learning_rate": 1.17487288410424e-05, + "loss": 3.8488, + "step": 2336256 + }, + { + "epoch": 1.02, + "learning_rate": 1.174034289353188e-05, + "loss": 3.8499, + "step": 2336768 + }, + { + "epoch": 1.02, + "learning_rate": 1.173195694602136e-05, + "loss": 3.8556, + "step": 2337280 + }, + { + "epoch": 1.02, + "learning_rate": 1.172357099851084e-05, + "loss": 3.8555, + "step": 2337792 + }, + { + "epoch": 1.02, + "learning_rate": 1.1715201429804052e-05, + "loss": 3.8628, + "step": 2338304 + }, + { + "epoch": 1.02, + "learning_rate": 1.1706815482293532e-05, + "loss": 3.8399, + "step": 2338816 + }, + { + "epoch": 1.02, + "learning_rate": 1.169842953478301e-05, + "loss": 3.8537, + "step": 2339328 + }, + { + "epoch": 1.02, + "learning_rate": 1.169004358727249e-05, + "loss": 3.8521, + "step": 2339840 + }, + { + "epoch": 1.02, + "learning_rate": 1.1681657639761972e-05, + "loss": 3.8486, + "step": 2340352 + }, + { + "epoch": 1.02, + "learning_rate": 1.1673288071055181e-05, + "loss": 3.8702, + "step": 2340864 + }, + { + "epoch": 1.02, + "learning_rate": 1.1664902123544663e-05, + "loss": 3.8518, + "step": 2341376 + }, + { + "epoch": 1.02, + "learning_rate": 1.1656516176034143e-05, + "loss": 3.8458, + "step": 2341888 + }, + { + "epoch": 1.02, + "learning_rate": 1.1648130228523623e-05, + "loss": 3.8493, + "step": 2342400 + }, + { + "epoch": 1.02, + "learning_rate": 1.16397442810131e-05, + "loss": 3.8509, + "step": 2342912 + }, + { + "epoch": 1.02, + "learning_rate": 1.1631374712306313e-05, + "loss": 3.8373, + "step": 2343424 + }, + { + "epoch": 1.02, + "learning_rate": 1.1622988764795793e-05, + "loss": 3.8482, + "step": 2343936 + }, + { + "epoch": 1.02, + "learning_rate": 1.1614602817285271e-05, + "loss": 3.8474, + "step": 2344448 + }, + { + "epoch": 1.02, + "learning_rate": 1.1606216869774753e-05, + "loss": 3.8479, + "step": 2344960 + }, + { + "epoch": 1.02, + "learning_rate": 1.1597847301067964e-05, + "loss": 3.8438, + "step": 2345472 + }, + { + "epoch": 1.02, + "learning_rate": 1.1589461353557444e-05, + "loss": 3.8507, + "step": 2345984 + }, + { + "epoch": 1.02, + "learning_rate": 1.1581075406046924e-05, + "loss": 3.8396, + "step": 2346496 + }, + { + "epoch": 1.02, + "learning_rate": 1.1572689458536404e-05, + "loss": 3.8619, + "step": 2347008 + }, + { + "epoch": 1.02, + "learning_rate": 1.1564303511025884e-05, + "loss": 3.8494, + "step": 2347520 + }, + { + "epoch": 1.02, + "learning_rate": 1.1555933942319096e-05, + "loss": 3.8565, + "step": 2348032 + }, + { + "epoch": 1.02, + "learning_rate": 1.1547547994808574e-05, + "loss": 3.8601, + "step": 2348544 + }, + { + "epoch": 1.02, + "learning_rate": 1.1539162047298054e-05, + "loss": 3.872, + "step": 2349056 + }, + { + "epoch": 1.02, + "learning_rate": 1.1530776099787536e-05, + "loss": 3.8511, + "step": 2349568 + }, + { + "epoch": 1.02, + "learning_rate": 1.1522390152277014e-05, + "loss": 3.8471, + "step": 2350080 + }, + { + "epoch": 1.02, + "learning_rate": 1.1514004204766494e-05, + "loss": 3.855, + "step": 2350592 + }, + { + "epoch": 1.02, + "learning_rate": 1.1505618257255974e-05, + "loss": 3.8501, + "step": 2351104 + }, + { + "epoch": 1.02, + "learning_rate": 1.1497232309745454e-05, + "loss": 3.8546, + "step": 2351616 + }, + { + "epoch": 1.02, + "learning_rate": 1.1488862741038665e-05, + "loss": 3.8556, + "step": 2352128 + }, + { + "epoch": 1.02, + "learning_rate": 1.1480476793528145e-05, + "loss": 3.8527, + "step": 2352640 + }, + { + "epoch": 1.02, + "learning_rate": 1.1472090846017627e-05, + "loss": 3.8606, + "step": 2353152 + }, + { + "epoch": 1.02, + "learning_rate": 1.1463704898507105e-05, + "loss": 3.8509, + "step": 2353664 + }, + { + "epoch": 1.02, + "learning_rate": 1.1455335329800317e-05, + "loss": 3.8473, + "step": 2354176 + }, + { + "epoch": 1.02, + "learning_rate": 1.1446965761093528e-05, + "loss": 3.8499, + "step": 2354688 + }, + { + "epoch": 1.02, + "learning_rate": 1.1438579813583008e-05, + "loss": 3.8575, + "step": 2355200 + }, + { + "epoch": 1.02, + "learning_rate": 1.1430193866072488e-05, + "loss": 3.854, + "step": 2355712 + }, + { + "epoch": 1.02, + "learning_rate": 1.1421807918561968e-05, + "loss": 3.8576, + "step": 2356224 + }, + { + "epoch": 1.02, + "learning_rate": 1.1413421971051448e-05, + "loss": 3.8567, + "step": 2356736 + }, + { + "epoch": 1.02, + "learning_rate": 1.1405036023540926e-05, + "loss": 3.8485, + "step": 2357248 + }, + { + "epoch": 1.02, + "learning_rate": 1.1396650076030408e-05, + "loss": 3.8558, + "step": 2357760 + }, + { + "epoch": 1.02, + "learning_rate": 1.1388264128519888e-05, + "loss": 3.8589, + "step": 2358272 + }, + { + "epoch": 1.02, + "learning_rate": 1.1379878181009366e-05, + "loss": 3.859, + "step": 2358784 + }, + { + "epoch": 1.02, + "learning_rate": 1.1371508612302579e-05, + "loss": 3.8509, + "step": 2359296 + }, + { + "epoch": 1.02, + "learning_rate": 1.1363122664792059e-05, + "loss": 3.8554, + "step": 2359808 + }, + { + "epoch": 1.02, + "learning_rate": 1.1354736717281538e-05, + "loss": 3.8617, + "step": 2360320 + }, + { + "epoch": 1.02, + "learning_rate": 1.134636714857475e-05, + "loss": 3.8656, + "step": 2360832 + }, + { + "epoch": 1.02, + "learning_rate": 1.133799757986796e-05, + "loss": 3.851, + "step": 2361344 + }, + { + "epoch": 1.02, + "learning_rate": 1.1329611632357442e-05, + "loss": 3.851, + "step": 2361856 + }, + { + "epoch": 1.02, + "learning_rate": 1.1321225684846922e-05, + "loss": 3.8464, + "step": 2362368 + }, + { + "epoch": 1.02, + "learning_rate": 1.13128397373364e-05, + "loss": 3.8546, + "step": 2362880 + }, + { + "epoch": 1.02, + "learning_rate": 1.130445378982588e-05, + "loss": 3.845, + "step": 2363392 + }, + { + "epoch": 1.02, + "learning_rate": 1.1296067842315362e-05, + "loss": 3.862, + "step": 2363904 + }, + { + "epoch": 1.02, + "learning_rate": 1.128768189480484e-05, + "loss": 3.8514, + "step": 2364416 + }, + { + "epoch": 1.02, + "learning_rate": 1.127929594729432e-05, + "loss": 3.8564, + "step": 2364928 + }, + { + "epoch": 1.02, + "learning_rate": 1.1270942757391263e-05, + "loss": 3.8497, + "step": 2365440 + }, + { + "epoch": 1.03, + "eval_loss": 3.975832223892212, + "eval_runtime": 289.7033, + "eval_samples_per_second": 1317.179, + "eval_steps_per_second": 41.163, + "step": 2365920 + }, + { + "epoch": 0.0, + "learning_rate": 1.1262556809880743e-05, + "loss": 3.7959, + "step": 2365952 + }, + { + "epoch": 0.0, + "learning_rate": 1.1254170862370223e-05, + "loss": 3.846, + "step": 2366464 + }, + { + "epoch": 0.0, + "learning_rate": 1.1245784914859703e-05, + "loss": 3.8549, + "step": 2366976 + }, + { + "epoch": 0.0, + "learning_rate": 1.1237398967349183e-05, + "loss": 3.8536, + "step": 2367488 + }, + { + "epoch": 0.0, + "learning_rate": 1.1229013019838663e-05, + "loss": 3.8534, + "step": 2368000 + }, + { + "epoch": 0.0, + "learning_rate": 1.1220627072328143e-05, + "loss": 3.8547, + "step": 2368512 + }, + { + "epoch": 0.0, + "learning_rate": 1.1212241124817623e-05, + "loss": 3.8481, + "step": 2369024 + }, + { + "epoch": 0.0, + "learning_rate": 1.1203855177307103e-05, + "loss": 3.848, + "step": 2369536 + }, + { + "epoch": 0.0, + "learning_rate": 1.1195469229796583e-05, + "loss": 3.8521, + "step": 2370048 + }, + { + "epoch": 0.0, + "learning_rate": 1.1187099661089793e-05, + "loss": 3.8527, + "step": 2370560 + }, + { + "epoch": 0.0, + "learning_rate": 1.1178713713579273e-05, + "loss": 3.8514, + "step": 2371072 + }, + { + "epoch": 0.0, + "learning_rate": 1.1170327766068753e-05, + "loss": 3.8616, + "step": 2371584 + }, + { + "epoch": 0.0, + "learning_rate": 1.1161958197361964e-05, + "loss": 3.8649, + "step": 2372096 + }, + { + "epoch": 0.0, + "learning_rate": 1.1153572249851444e-05, + "loss": 3.8427, + "step": 2372608 + }, + { + "epoch": 0.0, + "learning_rate": 1.1145186302340926e-05, + "loss": 3.8519, + "step": 2373120 + }, + { + "epoch": 0.0, + "learning_rate": 1.1136800354830404e-05, + "loss": 3.843, + "step": 2373632 + }, + { + "epoch": 0.0, + "learning_rate": 1.1128414407319884e-05, + "loss": 3.8532, + "step": 2374144 + }, + { + "epoch": 0.0, + "learning_rate": 1.1120028459809364e-05, + "loss": 3.8444, + "step": 2374656 + }, + { + "epoch": 0.0, + "learning_rate": 1.1111642512298846e-05, + "loss": 3.8482, + "step": 2375168 + }, + { + "epoch": 0.0, + "learning_rate": 1.1103256564788324e-05, + "loss": 3.8487, + "step": 2375680 + }, + { + "epoch": 0.0, + "learning_rate": 1.1094870617277804e-05, + "loss": 3.8614, + "step": 2376192 + }, + { + "epoch": 0.0, + "learning_rate": 1.1086484669767284e-05, + "loss": 3.8561, + "step": 2376704 + }, + { + "epoch": 0.0, + "learning_rate": 1.1078098722256764e-05, + "loss": 3.859, + "step": 2377216 + }, + { + "epoch": 0.0, + "learning_rate": 1.1069712774746244e-05, + "loss": 3.8596, + "step": 2377728 + }, + { + "epoch": 0.0, + "learning_rate": 1.1061326827235724e-05, + "loss": 3.8598, + "step": 2378240 + }, + { + "epoch": 0.0, + "learning_rate": 1.1052940879725204e-05, + "loss": 3.8527, + "step": 2378752 + }, + { + "epoch": 0.0, + "learning_rate": 1.1044554932214684e-05, + "loss": 3.8455, + "step": 2379264 + }, + { + "epoch": 0.0, + "learning_rate": 1.1036168984704164e-05, + "loss": 3.8526, + "step": 2379776 + }, + { + "epoch": 0.0, + "learning_rate": 1.1027799415997376e-05, + "loss": 3.8454, + "step": 2380288 + }, + { + "epoch": 0.0, + "learning_rate": 1.1019413468486854e-05, + "loss": 3.8472, + "step": 2380800 + }, + { + "epoch": 0.01, + "learning_rate": 1.1011027520976334e-05, + "loss": 3.8547, + "step": 2381312 + }, + { + "epoch": 0.01, + "learning_rate": 1.1002641573465814e-05, + "loss": 3.8493, + "step": 2381824 + }, + { + "epoch": 0.01, + "learning_rate": 1.0994255625955294e-05, + "loss": 3.8588, + "step": 2382336 + }, + { + "epoch": 0.01, + "learning_rate": 1.0985869678444774e-05, + "loss": 3.849, + "step": 2382848 + }, + { + "epoch": 0.01, + "learning_rate": 1.0977483730934254e-05, + "loss": 3.8525, + "step": 2383360 + }, + { + "epoch": 0.01, + "learning_rate": 1.0969114162227467e-05, + "loss": 3.8614, + "step": 2383872 + }, + { + "epoch": 0.01, + "learning_rate": 1.0960728214716945e-05, + "loss": 3.8544, + "step": 2384384 + }, + { + "epoch": 0.01, + "learning_rate": 1.0952342267206425e-05, + "loss": 3.833, + "step": 2384896 + }, + { + "epoch": 0.01, + "learning_rate": 1.0943956319695905e-05, + "loss": 3.8598, + "step": 2385408 + }, + { + "epoch": 0.01, + "learning_rate": 1.0935570372185385e-05, + "loss": 3.8424, + "step": 2385920 + }, + { + "epoch": 0.01, + "learning_rate": 1.0927184424674865e-05, + "loss": 3.8359, + "step": 2386432 + }, + { + "epoch": 0.01, + "learning_rate": 1.0918814855968077e-05, + "loss": 3.8537, + "step": 2386944 + }, + { + "epoch": 0.01, + "learning_rate": 1.0910428908457557e-05, + "loss": 3.863, + "step": 2387456 + }, + { + "epoch": 0.01, + "learning_rate": 1.0902042960947035e-05, + "loss": 3.8467, + "step": 2387968 + }, + { + "epoch": 0.01, + "learning_rate": 1.0893657013436515e-05, + "loss": 3.8532, + "step": 2388480 + }, + { + "epoch": 0.01, + "learning_rate": 1.0885287444729728e-05, + "loss": 3.8604, + "step": 2388992 + }, + { + "epoch": 0.01, + "learning_rate": 1.0876901497219206e-05, + "loss": 3.8549, + "step": 2389504 + }, + { + "epoch": 0.01, + "learning_rate": 1.0868515549708688e-05, + "loss": 3.8499, + "step": 2390016 + }, + { + "epoch": 0.01, + "learning_rate": 1.0860129602198168e-05, + "loss": 3.8323, + "step": 2390528 + }, + { + "epoch": 0.01, + "learning_rate": 1.0851760033491378e-05, + "loss": 3.8517, + "step": 2391040 + }, + { + "epoch": 0.01, + "learning_rate": 1.0843374085980858e-05, + "loss": 3.8552, + "step": 2391552 + }, + { + "epoch": 0.01, + "learning_rate": 1.0834988138470338e-05, + "loss": 3.8494, + "step": 2392064 + }, + { + "epoch": 0.01, + "learning_rate": 1.0826602190959818e-05, + "loss": 3.842, + "step": 2392576 + }, + { + "epoch": 0.01, + "learning_rate": 1.0818216243449297e-05, + "loss": 3.8396, + "step": 2393088 + }, + { + "epoch": 0.01, + "learning_rate": 1.0809830295938778e-05, + "loss": 3.8456, + "step": 2393600 + }, + { + "epoch": 0.01, + "learning_rate": 1.0801444348428258e-05, + "loss": 3.8363, + "step": 2394112 + }, + { + "epoch": 0.01, + "learning_rate": 1.0793058400917738e-05, + "loss": 3.8611, + "step": 2394624 + }, + { + "epoch": 0.01, + "learning_rate": 1.0784688832210949e-05, + "loss": 3.8384, + "step": 2395136 + }, + { + "epoch": 0.01, + "learning_rate": 1.0776302884700429e-05, + "loss": 3.8577, + "step": 2395648 + }, + { + "epoch": 0.01, + "learning_rate": 1.0767916937189909e-05, + "loss": 3.8509, + "step": 2396160 + }, + { + "epoch": 0.01, + "learning_rate": 1.0759530989679389e-05, + "loss": 3.8375, + "step": 2396672 + }, + { + "epoch": 0.01, + "learning_rate": 1.07511614209726e-05, + "loss": 3.849, + "step": 2397184 + }, + { + "epoch": 0.01, + "learning_rate": 1.074277547346208e-05, + "loss": 3.8455, + "step": 2397696 + }, + { + "epoch": 0.01, + "learning_rate": 1.0734405904755292e-05, + "loss": 3.8416, + "step": 2398208 + }, + { + "epoch": 0.01, + "learning_rate": 1.072601995724477e-05, + "loss": 3.8369, + "step": 2398720 + }, + { + "epoch": 0.01, + "learning_rate": 1.071763400973425e-05, + "loss": 3.8667, + "step": 2399232 + }, + { + "epoch": 0.01, + "learning_rate": 1.0709264441027463e-05, + "loss": 3.8477, + "step": 2399744 + }, + { + "epoch": 0.01, + "learning_rate": 1.0700878493516943e-05, + "loss": 3.8419, + "step": 2400256 + }, + { + "epoch": 0.01, + "learning_rate": 1.0692492546006423e-05, + "loss": 3.8296, + "step": 2400768 + }, + { + "epoch": 0.01, + "learning_rate": 1.0684106598495903e-05, + "loss": 3.8435, + "step": 2401280 + }, + { + "epoch": 0.01, + "learning_rate": 1.0675720650985383e-05, + "loss": 3.8565, + "step": 2401792 + }, + { + "epoch": 0.01, + "learning_rate": 1.066733470347486e-05, + "loss": 3.8611, + "step": 2402304 + }, + { + "epoch": 0.01, + "learning_rate": 1.0658965134768073e-05, + "loss": 3.8453, + "step": 2402816 + }, + { + "epoch": 0.01, + "learning_rate": 1.0650579187257553e-05, + "loss": 3.8571, + "step": 2403328 + }, + { + "epoch": 0.01, + "learning_rate": 1.0642193239747033e-05, + "loss": 3.861, + "step": 2403840 + }, + { + "epoch": 0.01, + "learning_rate": 1.0633807292236513e-05, + "loss": 3.8484, + "step": 2404352 + }, + { + "epoch": 0.01, + "learning_rate": 1.0625421344725993e-05, + "loss": 3.8453, + "step": 2404864 + }, + { + "epoch": 0.01, + "learning_rate": 1.0617035397215473e-05, + "loss": 3.852, + "step": 2405376 + }, + { + "epoch": 0.01, + "learning_rate": 1.0608649449704951e-05, + "loss": 3.8488, + "step": 2405888 + }, + { + "epoch": 0.01, + "learning_rate": 1.0600263502194433e-05, + "loss": 3.845, + "step": 2406400 + }, + { + "epoch": 0.01, + "learning_rate": 1.0591877554683913e-05, + "loss": 3.8472, + "step": 2406912 + }, + { + "epoch": 0.01, + "learning_rate": 1.0583507985977124e-05, + "loss": 3.8578, + "step": 2407424 + }, + { + "epoch": 0.01, + "learning_rate": 1.0575122038466604e-05, + "loss": 3.8565, + "step": 2407936 + }, + { + "epoch": 0.01, + "learning_rate": 1.0566736090956084e-05, + "loss": 3.8552, + "step": 2408448 + }, + { + "epoch": 0.01, + "learning_rate": 1.0558350143445564e-05, + "loss": 3.8369, + "step": 2408960 + }, + { + "epoch": 0.01, + "learning_rate": 1.0549964195935044e-05, + "loss": 3.8512, + "step": 2409472 + }, + { + "epoch": 0.01, + "learning_rate": 1.0541578248424523e-05, + "loss": 3.8543, + "step": 2409984 + }, + { + "epoch": 0.01, + "learning_rate": 1.0533208679717734e-05, + "loss": 3.8515, + "step": 2410496 + }, + { + "epoch": 0.01, + "learning_rate": 1.0524822732207216e-05, + "loss": 3.8456, + "step": 2411008 + }, + { + "epoch": 0.01, + "learning_rate": 1.0516436784696694e-05, + "loss": 3.849, + "step": 2411520 + }, + { + "epoch": 0.02, + "learning_rate": 1.0508050837186174e-05, + "loss": 3.8559, + "step": 2412032 + }, + { + "epoch": 0.02, + "learning_rate": 1.0499664889675654e-05, + "loss": 3.8422, + "step": 2412544 + }, + { + "epoch": 0.02, + "learning_rate": 1.0491278942165134e-05, + "loss": 3.8466, + "step": 2413056 + }, + { + "epoch": 0.02, + "learning_rate": 1.0482892994654614e-05, + "loss": 3.8524, + "step": 2413568 + }, + { + "epoch": 0.02, + "learning_rate": 1.0474507047144094e-05, + "loss": 3.8509, + "step": 2414080 + }, + { + "epoch": 0.02, + "learning_rate": 1.0466137478437306e-05, + "loss": 3.8588, + "step": 2414592 + }, + { + "epoch": 0.02, + "learning_rate": 1.0457751530926785e-05, + "loss": 3.8445, + "step": 2415104 + }, + { + "epoch": 0.02, + "learning_rate": 1.0449381962219997e-05, + "loss": 3.844, + "step": 2415616 + }, + { + "epoch": 0.02, + "learning_rate": 1.0440996014709477e-05, + "loss": 3.8495, + "step": 2416128 + }, + { + "epoch": 0.02, + "learning_rate": 1.0432610067198957e-05, + "loss": 3.8501, + "step": 2416640 + }, + { + "epoch": 0.02, + "learning_rate": 1.0424224119688435e-05, + "loss": 3.8609, + "step": 2417152 + }, + { + "epoch": 0.02, + "learning_rate": 1.0415838172177917e-05, + "loss": 3.8508, + "step": 2417664 + }, + { + "epoch": 0.02, + "learning_rate": 1.0407452224667397e-05, + "loss": 3.8417, + "step": 2418176 + }, + { + "epoch": 0.02, + "learning_rate": 1.0399082655960608e-05, + "loss": 3.8434, + "step": 2418688 + }, + { + "epoch": 0.02, + "learning_rate": 1.0390696708450088e-05, + "loss": 3.8539, + "step": 2419200 + }, + { + "epoch": 0.02, + "learning_rate": 1.0382310760939568e-05, + "loss": 3.825, + "step": 2419712 + }, + { + "epoch": 0.02, + "learning_rate": 1.0373941192232778e-05, + "loss": 3.8446, + "step": 2420224 + }, + { + "epoch": 0.02, + "learning_rate": 1.0365555244722258e-05, + "loss": 3.8482, + "step": 2420736 + }, + { + "epoch": 0.02, + "learning_rate": 1.0357169297211738e-05, + "loss": 3.8423, + "step": 2421248 + }, + { + "epoch": 0.02, + "learning_rate": 1.0348783349701218e-05, + "loss": 3.8391, + "step": 2421760 + }, + { + "epoch": 0.02, + "learning_rate": 1.0340397402190698e-05, + "loss": 3.8483, + "step": 2422272 + }, + { + "epoch": 0.02, + "learning_rate": 1.0332011454680178e-05, + "loss": 3.8346, + "step": 2422784 + }, + { + "epoch": 0.02, + "learning_rate": 1.0323625507169658e-05, + "loss": 3.8604, + "step": 2423296 + }, + { + "epoch": 0.02, + "learning_rate": 1.0315239559659136e-05, + "loss": 3.8435, + "step": 2423808 + }, + { + "epoch": 0.02, + "learning_rate": 1.0306853612148618e-05, + "loss": 3.852, + "step": 2424320 + }, + { + "epoch": 0.02, + "learning_rate": 1.0298467664638098e-05, + "loss": 3.8551, + "step": 2424832 + }, + { + "epoch": 0.02, + "learning_rate": 1.0290081717127578e-05, + "loss": 3.869, + "step": 2425344 + }, + { + "epoch": 0.02, + "learning_rate": 1.0281712148420789e-05, + "loss": 3.8479, + "step": 2425856 + }, + { + "epoch": 0.02, + "learning_rate": 1.0273326200910269e-05, + "loss": 3.8411, + "step": 2426368 + }, + { + "epoch": 0.02, + "learning_rate": 1.0264940253399749e-05, + "loss": 3.8536, + "step": 2426880 + }, + { + "epoch": 0.02, + "learning_rate": 1.0256570684692961e-05, + "loss": 3.8457, + "step": 2427392 + }, + { + "epoch": 0.02, + "learning_rate": 1.024818473718244e-05, + "loss": 3.8501, + "step": 2427904 + }, + { + "epoch": 0.02, + "learning_rate": 1.023979878967192e-05, + "loss": 3.8502, + "step": 2428416 + }, + { + "epoch": 0.02, + "learning_rate": 1.0231412842161401e-05, + "loss": 3.849, + "step": 2428928 + }, + { + "epoch": 0.02, + "learning_rate": 1.022302689465088e-05, + "loss": 3.8597, + "step": 2429440 + }, + { + "epoch": 0.02, + "learning_rate": 1.021465732594409e-05, + "loss": 3.8479, + "step": 2429952 + }, + { + "epoch": 0.02, + "learning_rate": 1.0206271378433572e-05, + "loss": 3.8443, + "step": 2430464 + }, + { + "epoch": 0.02, + "learning_rate": 1.0197885430923052e-05, + "loss": 3.846, + "step": 2430976 + }, + { + "epoch": 0.02, + "learning_rate": 1.018949948341253e-05, + "loss": 3.8492, + "step": 2431488 + }, + { + "epoch": 0.02, + "learning_rate": 1.018111353590201e-05, + "loss": 3.8469, + "step": 2432000 + }, + { + "epoch": 0.02, + "learning_rate": 1.0172727588391492e-05, + "loss": 3.855, + "step": 2432512 + }, + { + "epoch": 0.02, + "learning_rate": 1.016434164088097e-05, + "loss": 3.858, + "step": 2433024 + }, + { + "epoch": 0.02, + "learning_rate": 1.015595569337045e-05, + "loss": 3.8506, + "step": 2433536 + }, + { + "epoch": 0.02, + "learning_rate": 1.014756974585993e-05, + "loss": 3.8419, + "step": 2434048 + }, + { + "epoch": 0.02, + "learning_rate": 1.013918379834941e-05, + "loss": 3.8541, + "step": 2434560 + }, + { + "epoch": 0.02, + "learning_rate": 1.013081422964262e-05, + "loss": 3.8537, + "step": 2435072 + }, + { + "epoch": 0.02, + "learning_rate": 1.0122428282132102e-05, + "loss": 3.8505, + "step": 2435584 + }, + { + "epoch": 0.02, + "learning_rate": 1.0114042334621582e-05, + "loss": 3.8527, + "step": 2436096 + }, + { + "epoch": 0.02, + "learning_rate": 1.010565638711106e-05, + "loss": 3.8599, + "step": 2436608 + }, + { + "epoch": 0.02, + "learning_rate": 1.009727043960054e-05, + "loss": 3.8567, + "step": 2437120 + }, + { + "epoch": 0.02, + "learning_rate": 1.0088884492090022e-05, + "loss": 3.8494, + "step": 2437632 + }, + { + "epoch": 0.02, + "learning_rate": 1.00804985445795e-05, + "loss": 3.8459, + "step": 2438144 + }, + { + "epoch": 0.02, + "learning_rate": 1.007211259706898e-05, + "loss": 3.8477, + "step": 2438656 + }, + { + "epoch": 0.02, + "learning_rate": 1.0063743028362193e-05, + "loss": 3.8502, + "step": 2439168 + }, + { + "epoch": 0.02, + "learning_rate": 1.0055357080851673e-05, + "loss": 3.8374, + "step": 2439680 + }, + { + "epoch": 0.02, + "learning_rate": 1.0046971133341151e-05, + "loss": 3.8584, + "step": 2440192 + }, + { + "epoch": 0.02, + "learning_rate": 1.0038585185830633e-05, + "loss": 3.8519, + "step": 2440704 + }, + { + "epoch": 0.02, + "learning_rate": 1.0030215617123843e-05, + "loss": 3.852, + "step": 2441216 + }, + { + "epoch": 0.02, + "learning_rate": 1.0021846048417056e-05, + "loss": 3.8454, + "step": 2441728 + }, + { + "epoch": 0.03, + "learning_rate": 1.0013476479710265e-05, + "loss": 3.8542, + "step": 2442240 + }, + { + "epoch": 0.03, + "eval_loss": 3.974241256713867, + "eval_runtime": 290.3628, + "eval_samples_per_second": 1314.187, + "eval_steps_per_second": 41.069, + "step": 2442240 + }, + { + "epoch": 0.0, + "learning_rate": 1.0005090532199745e-05, + "loss": 3.8392, + "step": 2442752 + }, + { + "epoch": 0.0, + "learning_rate": 9.996704584689227e-06, + "loss": 3.8472, + "step": 2443264 + }, + { + "epoch": 0.0, + "learning_rate": 9.988318637178706e-06, + "loss": 3.8521, + "step": 2443776 + }, + { + "epoch": 0.0, + "learning_rate": 9.979932689668185e-06, + "loss": 3.8515, + "step": 2444288 + }, + { + "epoch": 0.0, + "learning_rate": 9.971546742157666e-06, + "loss": 3.8528, + "step": 2444800 + }, + { + "epoch": 0.0, + "learning_rate": 9.963160794647146e-06, + "loss": 3.8444, + "step": 2445312 + }, + { + "epoch": 0.0, + "learning_rate": 9.954774847136625e-06, + "loss": 3.847, + "step": 2445824 + }, + { + "epoch": 0.0, + "learning_rate": 9.946388899626105e-06, + "loss": 3.8421, + "step": 2446336 + }, + { + "epoch": 0.0, + "learning_rate": 9.938002952115586e-06, + "loss": 3.8542, + "step": 2446848 + }, + { + "epoch": 0.0, + "learning_rate": 9.929617004605064e-06, + "loss": 3.8415, + "step": 2447360 + }, + { + "epoch": 0.0, + "learning_rate": 9.921231057094544e-06, + "loss": 3.8618, + "step": 2447872 + }, + { + "epoch": 0.0, + "learning_rate": 9.912861488387757e-06, + "loss": 3.8638, + "step": 2448384 + }, + { + "epoch": 0.0, + "learning_rate": 9.904475540877237e-06, + "loss": 3.8385, + "step": 2448896 + }, + { + "epoch": 0.0, + "learning_rate": 9.896089593366715e-06, + "loss": 3.846, + "step": 2449408 + }, + { + "epoch": 0.0, + "learning_rate": 9.887703645856195e-06, + "loss": 3.8384, + "step": 2449920 + }, + { + "epoch": 0.0, + "learning_rate": 9.879317698345677e-06, + "loss": 3.8463, + "step": 2450432 + }, + { + "epoch": 0.0, + "learning_rate": 9.870931750835155e-06, + "loss": 3.8444, + "step": 2450944 + }, + { + "epoch": 0.0, + "learning_rate": 9.862545803324635e-06, + "loss": 3.8443, + "step": 2451456 + }, + { + "epoch": 0.0, + "learning_rate": 9.854159855814115e-06, + "loss": 3.8452, + "step": 2451968 + }, + { + "epoch": 0.0, + "learning_rate": 9.845773908303597e-06, + "loss": 3.8555, + "step": 2452480 + }, + { + "epoch": 0.0, + "learning_rate": 9.837387960793075e-06, + "loss": 3.8511, + "step": 2452992 + }, + { + "epoch": 0.0, + "learning_rate": 9.829002013282555e-06, + "loss": 3.8552, + "step": 2453504 + }, + { + "epoch": 0.0, + "learning_rate": 9.820616065772036e-06, + "loss": 3.8554, + "step": 2454016 + }, + { + "epoch": 0.0, + "learning_rate": 9.812230118261515e-06, + "loss": 3.8584, + "step": 2454528 + }, + { + "epoch": 0.0, + "learning_rate": 9.803876928358458e-06, + "loss": 3.8477, + "step": 2455040 + }, + { + "epoch": 0.0, + "learning_rate": 9.795490980847938e-06, + "loss": 3.8419, + "step": 2455552 + }, + { + "epoch": 0.0, + "learning_rate": 9.787105033337418e-06, + "loss": 3.8479, + "step": 2456064 + }, + { + "epoch": 0.0, + "learning_rate": 9.778719085826898e-06, + "loss": 3.8424, + "step": 2456576 + }, + { + "epoch": 0.0, + "learning_rate": 9.770333138316378e-06, + "loss": 3.8449, + "step": 2457088 + }, + { + "epoch": 0.01, + "learning_rate": 9.761947190805858e-06, + "loss": 3.8454, + "step": 2457600 + }, + { + "epoch": 0.01, + "learning_rate": 9.753561243295336e-06, + "loss": 3.8492, + "step": 2458112 + }, + { + "epoch": 0.01, + "learning_rate": 9.745175295784818e-06, + "loss": 3.8536, + "step": 2458624 + }, + { + "epoch": 0.01, + "learning_rate": 9.736805727078028e-06, + "loss": 3.8413, + "step": 2459136 + }, + { + "epoch": 0.01, + "learning_rate": 9.728419779567508e-06, + "loss": 3.8505, + "step": 2459648 + }, + { + "epoch": 0.01, + "learning_rate": 9.72005021086072e-06, + "loss": 3.8577, + "step": 2460160 + }, + { + "epoch": 0.01, + "learning_rate": 9.7116642633502e-06, + "loss": 3.8512, + "step": 2460672 + }, + { + "epoch": 0.01, + "learning_rate": 9.703278315839679e-06, + "loss": 3.833, + "step": 2461184 + }, + { + "epoch": 0.01, + "learning_rate": 9.694892368329159e-06, + "loss": 3.8532, + "step": 2461696 + }, + { + "epoch": 0.01, + "learning_rate": 9.686506420818639e-06, + "loss": 3.8348, + "step": 2462208 + }, + { + "epoch": 0.01, + "learning_rate": 9.678120473308119e-06, + "loss": 3.8406, + "step": 2462720 + }, + { + "epoch": 0.01, + "learning_rate": 9.669734525797599e-06, + "loss": 3.8487, + "step": 2463232 + }, + { + "epoch": 0.01, + "learning_rate": 9.661348578287079e-06, + "loss": 3.8569, + "step": 2463744 + }, + { + "epoch": 0.01, + "learning_rate": 9.65297900958029e-06, + "loss": 3.8448, + "step": 2464256 + }, + { + "epoch": 0.01, + "learning_rate": 9.644593062069771e-06, + "loss": 3.8514, + "step": 2464768 + }, + { + "epoch": 0.01, + "learning_rate": 9.63620711455925e-06, + "loss": 3.8549, + "step": 2465280 + }, + { + "epoch": 0.01, + "learning_rate": 9.62782116704873e-06, + "loss": 3.8518, + "step": 2465792 + }, + { + "epoch": 0.01, + "learning_rate": 9.61943521953821e-06, + "loss": 3.8487, + "step": 2466304 + }, + { + "epoch": 0.01, + "learning_rate": 9.611049272027691e-06, + "loss": 3.8299, + "step": 2466816 + }, + { + "epoch": 0.01, + "learning_rate": 9.6026797033209e-06, + "loss": 3.844, + "step": 2467328 + }, + { + "epoch": 0.01, + "learning_rate": 9.59429375581038e-06, + "loss": 3.8532, + "step": 2467840 + }, + { + "epoch": 0.01, + "learning_rate": 9.585907808299862e-06, + "loss": 3.8471, + "step": 2468352 + }, + { + "epoch": 0.01, + "learning_rate": 9.57752186078934e-06, + "loss": 3.8387, + "step": 2468864 + }, + { + "epoch": 0.01, + "learning_rate": 9.56913591327882e-06, + "loss": 3.8363, + "step": 2469376 + }, + { + "epoch": 0.01, + "learning_rate": 9.5607499657683e-06, + "loss": 3.8442, + "step": 2469888 + }, + { + "epoch": 0.01, + "learning_rate": 9.552380397061513e-06, + "loss": 3.8312, + "step": 2470400 + }, + { + "epoch": 0.01, + "learning_rate": 9.54399444955099e-06, + "loss": 3.8533, + "step": 2470912 + }, + { + "epoch": 0.01, + "learning_rate": 9.535608502040472e-06, + "loss": 3.8373, + "step": 2471424 + }, + { + "epoch": 0.01, + "learning_rate": 9.527222554529952e-06, + "loss": 3.8523, + "step": 2471936 + }, + { + "epoch": 0.01, + "learning_rate": 9.51883660701943e-06, + "loss": 3.8461, + "step": 2472448 + }, + { + "epoch": 0.01, + "learning_rate": 9.51045065950891e-06, + "loss": 3.8324, + "step": 2472960 + }, + { + "epoch": 0.01, + "learning_rate": 9.502064711998392e-06, + "loss": 3.8472, + "step": 2473472 + }, + { + "epoch": 0.01, + "learning_rate": 9.493678764487872e-06, + "loss": 3.8414, + "step": 2473984 + }, + { + "epoch": 0.01, + "learning_rate": 9.485309195781083e-06, + "loss": 3.8359, + "step": 2474496 + }, + { + "epoch": 0.01, + "learning_rate": 9.476923248270563e-06, + "loss": 3.8332, + "step": 2475008 + }, + { + "epoch": 0.01, + "learning_rate": 9.468537300760043e-06, + "loss": 3.8566, + "step": 2475520 + }, + { + "epoch": 0.01, + "learning_rate": 9.460151353249521e-06, + "loss": 3.8445, + "step": 2476032 + }, + { + "epoch": 0.01, + "learning_rate": 9.451781784542734e-06, + "loss": 3.838, + "step": 2476544 + }, + { + "epoch": 0.01, + "learning_rate": 9.443395837032214e-06, + "loss": 3.8265, + "step": 2477056 + }, + { + "epoch": 0.01, + "learning_rate": 9.435009889521694e-06, + "loss": 3.8377, + "step": 2477568 + }, + { + "epoch": 0.01, + "learning_rate": 9.426623942011174e-06, + "loss": 3.8522, + "step": 2478080 + }, + { + "epoch": 0.01, + "learning_rate": 9.418237994500653e-06, + "loss": 3.8596, + "step": 2478592 + }, + { + "epoch": 0.01, + "learning_rate": 9.409868425793864e-06, + "loss": 3.8421, + "step": 2479104 + }, + { + "epoch": 0.01, + "learning_rate": 9.401482478283346e-06, + "loss": 3.8565, + "step": 2479616 + }, + { + "epoch": 0.01, + "learning_rate": 9.393096530772824e-06, + "loss": 3.8569, + "step": 2480128 + }, + { + "epoch": 0.01, + "learning_rate": 9.384726962066035e-06, + "loss": 3.8464, + "step": 2480640 + }, + { + "epoch": 0.01, + "learning_rate": 9.376341014555517e-06, + "loss": 3.8387, + "step": 2481152 + }, + { + "epoch": 0.01, + "learning_rate": 9.367955067044995e-06, + "loss": 3.8501, + "step": 2481664 + }, + { + "epoch": 0.01, + "learning_rate": 9.359569119534475e-06, + "loss": 3.8461, + "step": 2482176 + }, + { + "epoch": 0.01, + "learning_rate": 9.351183172023957e-06, + "loss": 3.843, + "step": 2482688 + }, + { + "epoch": 0.01, + "learning_rate": 9.342797224513436e-06, + "loss": 3.8451, + "step": 2483200 + }, + { + "epoch": 0.01, + "learning_rate": 9.334411277002915e-06, + "loss": 3.8481, + "step": 2483712 + }, + { + "epoch": 0.01, + "learning_rate": 9.326025329492395e-06, + "loss": 3.8544, + "step": 2484224 + }, + { + "epoch": 0.01, + "learning_rate": 9.317655760785607e-06, + "loss": 3.8498, + "step": 2484736 + }, + { + "epoch": 0.01, + "learning_rate": 9.309269813275085e-06, + "loss": 3.8395, + "step": 2485248 + }, + { + "epoch": 0.01, + "learning_rate": 9.300883865764565e-06, + "loss": 3.8462, + "step": 2485760 + }, + { + "epoch": 0.01, + "learning_rate": 9.292497918254047e-06, + "loss": 3.8516, + "step": 2486272 + }, + { + "epoch": 0.01, + "learning_rate": 9.284128349547258e-06, + "loss": 3.8452, + "step": 2486784 + }, + { + "epoch": 0.01, + "learning_rate": 9.275742402036738e-06, + "loss": 3.8446, + "step": 2487296 + }, + { + "epoch": 0.01, + "learning_rate": 9.267372833329949e-06, + "loss": 3.8441, + "step": 2487808 + }, + { + "epoch": 0.02, + "learning_rate": 9.258986885819429e-06, + "loss": 3.851, + "step": 2488320 + }, + { + "epoch": 0.02, + "learning_rate": 9.250600938308908e-06, + "loss": 3.8415, + "step": 2488832 + }, + { + "epoch": 0.02, + "learning_rate": 9.242214990798388e-06, + "loss": 3.8439, + "step": 2489344 + }, + { + "epoch": 0.02, + "learning_rate": 9.233829043287868e-06, + "loss": 3.8423, + "step": 2489856 + }, + { + "epoch": 0.02, + "learning_rate": 9.225459474581081e-06, + "loss": 3.8524, + "step": 2490368 + }, + { + "epoch": 0.02, + "learning_rate": 9.217073527070559e-06, + "loss": 3.8494, + "step": 2490880 + }, + { + "epoch": 0.02, + "learning_rate": 9.208687579560039e-06, + "loss": 3.8481, + "step": 2491392 + }, + { + "epoch": 0.02, + "learning_rate": 9.200301632049519e-06, + "loss": 3.8351, + "step": 2491904 + }, + { + "epoch": 0.02, + "learning_rate": 9.191915684539e-06, + "loss": 3.8448, + "step": 2492416 + }, + { + "epoch": 0.02, + "learning_rate": 9.18354611583221e-06, + "loss": 3.8451, + "step": 2492928 + }, + { + "epoch": 0.02, + "learning_rate": 9.175160168321691e-06, + "loss": 3.8589, + "step": 2493440 + }, + { + "epoch": 0.02, + "learning_rate": 9.166774220811171e-06, + "loss": 3.8483, + "step": 2493952 + }, + { + "epoch": 0.02, + "learning_rate": 9.15838827330065e-06, + "loss": 3.8401, + "step": 2494464 + }, + { + "epoch": 0.02, + "learning_rate": 9.15000232579013e-06, + "loss": 3.8397, + "step": 2494976 + }, + { + "epoch": 0.02, + "learning_rate": 9.141616378279611e-06, + "loss": 3.8496, + "step": 2495488 + }, + { + "epoch": 0.02, + "learning_rate": 9.13323043076909e-06, + "loss": 3.8258, + "step": 2496000 + }, + { + "epoch": 0.02, + "learning_rate": 9.1248608620623e-06, + "loss": 3.8376, + "step": 2496512 + }, + { + "epoch": 0.02, + "learning_rate": 9.116474914551782e-06, + "loss": 3.8427, + "step": 2497024 + }, + { + "epoch": 0.02, + "learning_rate": 9.108088967041262e-06, + "loss": 3.8429, + "step": 2497536 + }, + { + "epoch": 0.02, + "learning_rate": 9.09970301953074e-06, + "loss": 3.8339, + "step": 2498048 + }, + { + "epoch": 0.02, + "learning_rate": 9.09131707202022e-06, + "loss": 3.8488, + "step": 2498560 + }, + { + "epoch": 0.02, + "learning_rate": 9.082931124509702e-06, + "loss": 3.8302, + "step": 2499072 + }, + { + "epoch": 0.02, + "learning_rate": 9.07454517699918e-06, + "loss": 3.8571, + "step": 2499584 + }, + { + "epoch": 0.02, + "learning_rate": 9.06615922948866e-06, + "loss": 3.8389, + "step": 2500096 + }, + { + "epoch": 0.02, + "learning_rate": 9.057789660781872e-06, + "loss": 3.8505, + "step": 2500608 + }, + { + "epoch": 0.02, + "learning_rate": 9.049403713271352e-06, + "loss": 3.8519, + "step": 2501120 + }, + { + "epoch": 0.02, + "learning_rate": 9.041034144564563e-06, + "loss": 3.8668, + "step": 2501632 + }, + { + "epoch": 0.02, + "learning_rate": 9.032648197054043e-06, + "loss": 3.8433, + "step": 2502144 + }, + { + "epoch": 0.02, + "learning_rate": 9.024262249543523e-06, + "loss": 3.8406, + "step": 2502656 + }, + { + "epoch": 0.02, + "learning_rate": 9.015876302033003e-06, + "loss": 3.8496, + "step": 2503168 + }, + { + "epoch": 0.02, + "learning_rate": 9.007506733326214e-06, + "loss": 3.8399, + "step": 2503680 + }, + { + "epoch": 0.02, + "learning_rate": 8.999120785815694e-06, + "loss": 3.8504, + "step": 2504192 + }, + { + "epoch": 0.02, + "learning_rate": 8.990734838305174e-06, + "loss": 3.8483, + "step": 2504704 + }, + { + "epoch": 0.02, + "learning_rate": 8.982348890794654e-06, + "loss": 3.8416, + "step": 2505216 + }, + { + "epoch": 0.02, + "learning_rate": 8.973962943284134e-06, + "loss": 3.8626, + "step": 2505728 + }, + { + "epoch": 0.02, + "learning_rate": 8.965576995773614e-06, + "loss": 3.8443, + "step": 2506240 + }, + { + "epoch": 0.02, + "learning_rate": 8.957191048263094e-06, + "loss": 3.8402, + "step": 2506752 + }, + { + "epoch": 0.02, + "learning_rate": 8.948805100752574e-06, + "loss": 3.8429, + "step": 2507264 + }, + { + "epoch": 0.02, + "learning_rate": 8.940435532045784e-06, + "loss": 3.8473, + "step": 2507776 + }, + { + "epoch": 0.02, + "learning_rate": 8.932049584535266e-06, + "loss": 3.8419, + "step": 2508288 + }, + { + "epoch": 0.02, + "learning_rate": 8.923663637024744e-06, + "loss": 3.8559, + "step": 2508800 + }, + { + "epoch": 0.02, + "learning_rate": 8.915294068317955e-06, + "loss": 3.8543, + "step": 2509312 + }, + { + "epoch": 0.02, + "learning_rate": 8.906908120807437e-06, + "loss": 3.8443, + "step": 2509824 + }, + { + "epoch": 0.02, + "learning_rate": 8.898522173296917e-06, + "loss": 3.8381, + "step": 2510336 + }, + { + "epoch": 0.02, + "learning_rate": 8.890136225786395e-06, + "loss": 3.8497, + "step": 2510848 + }, + { + "epoch": 0.02, + "learning_rate": 8.881750278275875e-06, + "loss": 3.8486, + "step": 2511360 + }, + { + "epoch": 0.02, + "learning_rate": 8.873364330765357e-06, + "loss": 3.8517, + "step": 2511872 + }, + { + "epoch": 0.02, + "learning_rate": 8.864978383254835e-06, + "loss": 3.8483, + "step": 2512384 + }, + { + "epoch": 0.02, + "learning_rate": 8.856608814548047e-06, + "loss": 3.8584, + "step": 2512896 + }, + { + "epoch": 0.02, + "learning_rate": 8.848222867037527e-06, + "loss": 3.8513, + "step": 2513408 + }, + { + "epoch": 0.02, + "learning_rate": 8.839836919527007e-06, + "loss": 3.848, + "step": 2513920 + }, + { + "epoch": 0.02, + "learning_rate": 8.831450972016485e-06, + "loss": 3.8442, + "step": 2514432 + }, + { + "epoch": 0.02, + "learning_rate": 8.823065024505967e-06, + "loss": 3.843, + "step": 2514944 + }, + { + "epoch": 0.02, + "learning_rate": 8.814679076995447e-06, + "loss": 3.8502, + "step": 2515456 + }, + { + "epoch": 0.02, + "learning_rate": 8.806309508288658e-06, + "loss": 3.8337, + "step": 2515968 + }, + { + "epoch": 0.02, + "learning_rate": 8.797923560778138e-06, + "loss": 3.8558, + "step": 2516480 + }, + { + "epoch": 0.02, + "learning_rate": 8.789537613267618e-06, + "loss": 3.8537, + "step": 2516992 + }, + { + "epoch": 0.02, + "learning_rate": 8.781151665757098e-06, + "loss": 3.8459, + "step": 2517504 + }, + { + "epoch": 0.02, + "learning_rate": 8.772765718246578e-06, + "loss": 3.842, + "step": 2518016 + }, + { + "epoch": 0.02, + "learning_rate": 8.764396149539788e-06, + "loss": 3.8492, + "step": 2518528 + }, + { + "epoch": 0.03, + "eval_loss": 3.9731252193450928, + "eval_runtime": 310.925, + "eval_samples_per_second": 1227.277, + "eval_steps_per_second": 38.353, + "step": 2518560 + }, + { + "epoch": 1.0, + "learning_rate": 8.756010202029268e-06, + "loss": 3.8328, + "step": 2519040 + }, + { + "epoch": 1.0, + "learning_rate": 8.747624254518748e-06, + "loss": 3.8452, + "step": 2519552 + }, + { + "epoch": 1.0, + "learning_rate": 8.739238307008228e-06, + "loss": 3.8525, + "step": 2520064 + }, + { + "epoch": 1.0, + "learning_rate": 8.730852359497708e-06, + "loss": 3.8433, + "step": 2520576 + }, + { + "epoch": 1.0, + "learning_rate": 8.722466411987188e-06, + "loss": 3.8496, + "step": 2521088 + }, + { + "epoch": 1.0, + "learning_rate": 8.714080464476668e-06, + "loss": 3.8435, + "step": 2521600 + }, + { + "epoch": 1.0, + "learning_rate": 8.705694516966148e-06, + "loss": 3.8412, + "step": 2522112 + }, + { + "epoch": 1.0, + "learning_rate": 8.697324948259359e-06, + "loss": 3.8409, + "step": 2522624 + }, + { + "epoch": 1.0, + "learning_rate": 8.68893900074884e-06, + "loss": 3.8498, + "step": 2523136 + }, + { + "epoch": 1.0, + "learning_rate": 8.680553053238319e-06, + "loss": 3.8403, + "step": 2523648 + }, + { + "epoch": 1.0, + "learning_rate": 8.672167105727799e-06, + "loss": 3.8589, + "step": 2524160 + }, + { + "epoch": 1.0, + "learning_rate": 8.663797537021011e-06, + "loss": 3.8542, + "step": 2524672 + }, + { + "epoch": 1.0, + "learning_rate": 8.655427968314222e-06, + "loss": 3.8399, + "step": 2525184 + }, + { + "epoch": 1.0, + "learning_rate": 8.647042020803702e-06, + "loss": 3.8397, + "step": 2525696 + }, + { + "epoch": 1.0, + "learning_rate": 8.638656073293182e-06, + "loss": 3.8414, + "step": 2526208 + }, + { + "epoch": 1.0, + "learning_rate": 8.630270125782662e-06, + "loss": 3.84, + "step": 2526720 + }, + { + "epoch": 1.0, + "learning_rate": 8.621900557075873e-06, + "loss": 3.8406, + "step": 2527232 + }, + { + "epoch": 1.0, + "learning_rate": 8.613514609565353e-06, + "loss": 3.8438, + "step": 2527744 + }, + { + "epoch": 1.0, + "learning_rate": 8.605128662054833e-06, + "loss": 3.8391, + "step": 2528256 + }, + { + "epoch": 1.0, + "learning_rate": 8.596742714544313e-06, + "loss": 3.8575, + "step": 2528768 + }, + { + "epoch": 1.0, + "learning_rate": 8.588356767033793e-06, + "loss": 3.8472, + "step": 2529280 + }, + { + "epoch": 1.0, + "learning_rate": 8.579970819523273e-06, + "loss": 3.8544, + "step": 2529792 + }, + { + "epoch": 1.0, + "learning_rate": 8.571584872012752e-06, + "loss": 3.852, + "step": 2530304 + }, + { + "epoch": 1.0, + "learning_rate": 8.563198924502232e-06, + "loss": 3.8595, + "step": 2530816 + }, + { + "epoch": 1.0, + "learning_rate": 8.554829355795443e-06, + "loss": 3.8375, + "step": 2531328 + }, + { + "epoch": 1.0, + "learning_rate": 8.546443408284923e-06, + "loss": 3.8425, + "step": 2531840 + }, + { + "epoch": 1.0, + "learning_rate": 8.538073839578136e-06, + "loss": 3.8399, + "step": 2532352 + }, + { + "epoch": 1.0, + "learning_rate": 8.529687892067614e-06, + "loss": 3.8418, + "step": 2532864 + }, + { + "epoch": 1.0, + "learning_rate": 8.521301944557094e-06, + "loss": 3.8409, + "step": 2533376 + }, + { + "epoch": 1.01, + "learning_rate": 8.512915997046576e-06, + "loss": 3.8412, + "step": 2533888 + }, + { + "epoch": 1.01, + "learning_rate": 8.504530049536054e-06, + "loss": 3.8501, + "step": 2534400 + }, + { + "epoch": 1.01, + "learning_rate": 8.496144102025534e-06, + "loss": 3.8492, + "step": 2534912 + }, + { + "epoch": 1.01, + "learning_rate": 8.487758154515014e-06, + "loss": 3.8386, + "step": 2535424 + }, + { + "epoch": 1.01, + "learning_rate": 8.479372207004494e-06, + "loss": 3.852, + "step": 2535936 + }, + { + "epoch": 1.01, + "learning_rate": 8.471002638297704e-06, + "loss": 3.8568, + "step": 2536448 + }, + { + "epoch": 1.01, + "learning_rate": 8.462616690787186e-06, + "loss": 3.8445, + "step": 2536960 + }, + { + "epoch": 1.01, + "learning_rate": 8.454247122080397e-06, + "loss": 3.8307, + "step": 2537472 + }, + { + "epoch": 1.01, + "learning_rate": 8.445861174569875e-06, + "loss": 3.8496, + "step": 2537984 + }, + { + "epoch": 1.01, + "learning_rate": 8.437475227059357e-06, + "loss": 3.8326, + "step": 2538496 + }, + { + "epoch": 1.01, + "learning_rate": 8.429089279548837e-06, + "loss": 3.8389, + "step": 2539008 + }, + { + "epoch": 1.01, + "learning_rate": 8.420703332038317e-06, + "loss": 3.8433, + "step": 2539520 + }, + { + "epoch": 1.01, + "learning_rate": 8.412317384527795e-06, + "loss": 3.8556, + "step": 2540032 + }, + { + "epoch": 1.01, + "learning_rate": 8.403931437017277e-06, + "loss": 3.8407, + "step": 2540544 + }, + { + "epoch": 1.01, + "learning_rate": 8.395561868310487e-06, + "loss": 3.8458, + "step": 2541056 + }, + { + "epoch": 1.01, + "learning_rate": 8.387175920799967e-06, + "loss": 3.8526, + "step": 2541568 + }, + { + "epoch": 1.01, + "learning_rate": 8.378789973289447e-06, + "loss": 3.8466, + "step": 2542080 + }, + { + "epoch": 1.01, + "learning_rate": 8.370404025778927e-06, + "loss": 3.8475, + "step": 2542592 + }, + { + "epoch": 1.01, + "learning_rate": 8.362018078268407e-06, + "loss": 3.8277, + "step": 2543104 + }, + { + "epoch": 1.01, + "learning_rate": 8.353632130757887e-06, + "loss": 3.8432, + "step": 2543616 + }, + { + "epoch": 1.01, + "learning_rate": 8.345246183247367e-06, + "loss": 3.8489, + "step": 2544128 + }, + { + "epoch": 1.01, + "learning_rate": 8.336860235736847e-06, + "loss": 3.8439, + "step": 2544640 + }, + { + "epoch": 1.01, + "learning_rate": 8.328490667030058e-06, + "loss": 3.8384, + "step": 2545152 + }, + { + "epoch": 1.01, + "learning_rate": 8.320104719519538e-06, + "loss": 3.8298, + "step": 2545664 + }, + { + "epoch": 1.01, + "learning_rate": 8.311718772009018e-06, + "loss": 3.8412, + "step": 2546176 + }, + { + "epoch": 1.01, + "learning_rate": 8.303332824498498e-06, + "loss": 3.8277, + "step": 2546688 + }, + { + "epoch": 1.01, + "learning_rate": 8.294963255791709e-06, + "loss": 3.8488, + "step": 2547200 + }, + { + "epoch": 1.01, + "learning_rate": 8.286593687084921e-06, + "loss": 3.838, + "step": 2547712 + }, + { + "epoch": 1.01, + "learning_rate": 8.278207739574401e-06, + "loss": 3.8481, + "step": 2548224 + }, + { + "epoch": 1.01, + "learning_rate": 8.269821792063881e-06, + "loss": 3.8474, + "step": 2548736 + }, + { + "epoch": 1.01, + "learning_rate": 8.26143584455336e-06, + "loss": 3.8271, + "step": 2549248 + }, + { + "epoch": 1.01, + "learning_rate": 8.253049897042841e-06, + "loss": 3.841, + "step": 2549760 + }, + { + "epoch": 1.01, + "learning_rate": 8.24466394953232e-06, + "loss": 3.8436, + "step": 2550272 + }, + { + "epoch": 1.01, + "learning_rate": 8.236278002021799e-06, + "loss": 3.8329, + "step": 2550784 + }, + { + "epoch": 1.01, + "learning_rate": 8.227892054511279e-06, + "loss": 3.8338, + "step": 2551296 + }, + { + "epoch": 1.01, + "learning_rate": 8.219522485804492e-06, + "loss": 3.8523, + "step": 2551808 + }, + { + "epoch": 1.01, + "learning_rate": 8.211136538293971e-06, + "loss": 3.8453, + "step": 2552320 + }, + { + "epoch": 1.01, + "learning_rate": 8.202750590783451e-06, + "loss": 3.8328, + "step": 2552832 + }, + { + "epoch": 1.01, + "learning_rate": 8.194381022076662e-06, + "loss": 3.8232, + "step": 2553344 + }, + { + "epoch": 1.01, + "learning_rate": 8.185995074566142e-06, + "loss": 3.8385, + "step": 2553856 + }, + { + "epoch": 1.01, + "learning_rate": 8.177609127055622e-06, + "loss": 3.8478, + "step": 2554368 + }, + { + "epoch": 1.01, + "learning_rate": 8.169223179545102e-06, + "loss": 3.8537, + "step": 2554880 + }, + { + "epoch": 1.01, + "learning_rate": 8.160837232034582e-06, + "loss": 3.8412, + "step": 2555392 + }, + { + "epoch": 1.01, + "learning_rate": 8.152451284524062e-06, + "loss": 3.8534, + "step": 2555904 + }, + { + "epoch": 1.01, + "learning_rate": 8.144065337013542e-06, + "loss": 3.8496, + "step": 2556416 + }, + { + "epoch": 1.01, + "learning_rate": 8.135679389503022e-06, + "loss": 3.8462, + "step": 2556928 + }, + { + "epoch": 1.01, + "learning_rate": 8.127309820796233e-06, + "loss": 3.8339, + "step": 2557440 + }, + { + "epoch": 1.01, + "learning_rate": 8.118940252089445e-06, + "loss": 3.8509, + "step": 2557952 + }, + { + "epoch": 1.01, + "learning_rate": 8.110554304578923e-06, + "loss": 3.8432, + "step": 2558464 + }, + { + "epoch": 1.01, + "learning_rate": 8.102168357068405e-06, + "loss": 3.8403, + "step": 2558976 + }, + { + "epoch": 1.01, + "learning_rate": 8.093782409557885e-06, + "loss": 3.8424, + "step": 2559488 + }, + { + "epoch": 1.01, + "learning_rate": 8.085396462047363e-06, + "loss": 3.842, + "step": 2560000 + }, + { + "epoch": 1.01, + "learning_rate": 8.077010514536843e-06, + "loss": 3.8581, + "step": 2560512 + }, + { + "epoch": 1.01, + "learning_rate": 8.068640945830056e-06, + "loss": 3.8445, + "step": 2561024 + }, + { + "epoch": 1.01, + "learning_rate": 8.060254998319536e-06, + "loss": 3.8388, + "step": 2561536 + }, + { + "epoch": 1.01, + "learning_rate": 8.051869050809014e-06, + "loss": 3.842, + "step": 2562048 + }, + { + "epoch": 1.01, + "learning_rate": 8.043483103298496e-06, + "loss": 3.8467, + "step": 2562560 + }, + { + "epoch": 1.01, + "learning_rate": 8.035097155787976e-06, + "loss": 3.8436, + "step": 2563072 + }, + { + "epoch": 1.01, + "learning_rate": 8.026711208277454e-06, + "loss": 3.8429, + "step": 2563584 + }, + { + "epoch": 1.01, + "learning_rate": 8.018325260766934e-06, + "loss": 3.8382, + "step": 2564096 + }, + { + "epoch": 1.02, + "learning_rate": 8.009939313256415e-06, + "loss": 3.8519, + "step": 2564608 + }, + { + "epoch": 1.02, + "learning_rate": 8.001569744549626e-06, + "loss": 3.8356, + "step": 2565120 + }, + { + "epoch": 1.02, + "learning_rate": 7.993200175842837e-06, + "loss": 3.8409, + "step": 2565632 + }, + { + "epoch": 1.02, + "learning_rate": 7.984814228332317e-06, + "loss": 3.8361, + "step": 2566144 + }, + { + "epoch": 1.02, + "learning_rate": 7.976428280821797e-06, + "loss": 3.8494, + "step": 2566656 + }, + { + "epoch": 1.02, + "learning_rate": 7.968042333311277e-06, + "loss": 3.8489, + "step": 2567168 + }, + { + "epoch": 1.02, + "learning_rate": 7.959656385800757e-06, + "loss": 3.8469, + "step": 2567680 + }, + { + "epoch": 1.02, + "learning_rate": 7.951270438290237e-06, + "loss": 3.8322, + "step": 2568192 + }, + { + "epoch": 1.02, + "learning_rate": 7.942884490779715e-06, + "loss": 3.8444, + "step": 2568704 + }, + { + "epoch": 1.02, + "learning_rate": 7.934498543269197e-06, + "loss": 3.8431, + "step": 2569216 + }, + { + "epoch": 1.02, + "learning_rate": 7.926112595758677e-06, + "loss": 3.8542, + "step": 2569728 + }, + { + "epoch": 1.02, + "learning_rate": 7.917726648248157e-06, + "loss": 3.8453, + "step": 2570240 + }, + { + "epoch": 1.02, + "learning_rate": 7.909357079541367e-06, + "loss": 3.8397, + "step": 2570752 + }, + { + "epoch": 1.02, + "learning_rate": 7.900971132030847e-06, + "loss": 3.8339, + "step": 2571264 + }, + { + "epoch": 1.02, + "learning_rate": 7.892585184520327e-06, + "loss": 3.8469, + "step": 2571776 + }, + { + "epoch": 1.02, + "learning_rate": 7.88421561581354e-06, + "loss": 3.8197, + "step": 2572288 + }, + { + "epoch": 1.02, + "learning_rate": 7.875829668303018e-06, + "loss": 3.8361, + "step": 2572800 + }, + { + "epoch": 1.02, + "learning_rate": 7.867443720792498e-06, + "loss": 3.8414, + "step": 2573312 + }, + { + "epoch": 1.02, + "learning_rate": 7.85905777328198e-06, + "loss": 3.8421, + "step": 2573824 + }, + { + "epoch": 1.02, + "learning_rate": 7.850671825771458e-06, + "loss": 3.8292, + "step": 2574336 + }, + { + "epoch": 1.02, + "learning_rate": 7.842285878260938e-06, + "loss": 3.8441, + "step": 2574848 + }, + { + "epoch": 1.02, + "learning_rate": 7.833899930750418e-06, + "loss": 3.8339, + "step": 2575360 + }, + { + "epoch": 1.02, + "learning_rate": 7.82553036204363e-06, + "loss": 3.853, + "step": 2575872 + }, + { + "epoch": 1.02, + "learning_rate": 7.817144414533109e-06, + "loss": 3.8373, + "step": 2576384 + }, + { + "epoch": 1.02, + "learning_rate": 7.808758467022589e-06, + "loss": 3.8407, + "step": 2576896 + }, + { + "epoch": 1.02, + "learning_rate": 7.800388898315801e-06, + "loss": 3.8562, + "step": 2577408 + }, + { + "epoch": 1.02, + "learning_rate": 7.79200295080528e-06, + "loss": 3.8611, + "step": 2577920 + }, + { + "epoch": 1.02, + "learning_rate": 7.783617003294761e-06, + "loss": 3.8395, + "step": 2578432 + }, + { + "epoch": 1.02, + "learning_rate": 7.775231055784241e-06, + "loss": 3.8374, + "step": 2578944 + }, + { + "epoch": 1.02, + "learning_rate": 7.766845108273721e-06, + "loss": 3.8463, + "step": 2579456 + }, + { + "epoch": 1.02, + "learning_rate": 7.758459160763199e-06, + "loss": 3.8364, + "step": 2579968 + }, + { + "epoch": 1.02, + "learning_rate": 7.750089592056412e-06, + "loss": 3.8418, + "step": 2580480 + }, + { + "epoch": 1.02, + "learning_rate": 7.741703644545892e-06, + "loss": 3.8481, + "step": 2580992 + }, + { + "epoch": 1.02, + "learning_rate": 7.733317697035372e-06, + "loss": 3.8393, + "step": 2581504 + }, + { + "epoch": 1.02, + "learning_rate": 7.724931749524851e-06, + "loss": 3.8573, + "step": 2582016 + }, + { + "epoch": 1.02, + "learning_rate": 7.716562180818062e-06, + "loss": 3.8407, + "step": 2582528 + }, + { + "epoch": 1.02, + "learning_rate": 7.708176233307542e-06, + "loss": 3.8433, + "step": 2583040 + }, + { + "epoch": 1.02, + "learning_rate": 7.699790285797022e-06, + "loss": 3.8353, + "step": 2583552 + }, + { + "epoch": 1.02, + "learning_rate": 7.691420717090233e-06, + "loss": 3.8447, + "step": 2584064 + }, + { + "epoch": 1.02, + "learning_rate": 7.683034769579715e-06, + "loss": 3.839, + "step": 2584576 + }, + { + "epoch": 1.02, + "learning_rate": 7.674648822069195e-06, + "loss": 3.8536, + "step": 2585088 + }, + { + "epoch": 1.02, + "learning_rate": 7.666262874558673e-06, + "loss": 3.8546, + "step": 2585600 + }, + { + "epoch": 1.02, + "learning_rate": 7.657876927048153e-06, + "loss": 3.8451, + "step": 2586112 + }, + { + "epoch": 1.02, + "learning_rate": 7.649490979537634e-06, + "loss": 3.8312, + "step": 2586624 + }, + { + "epoch": 1.02, + "learning_rate": 7.641105032027113e-06, + "loss": 3.8509, + "step": 2587136 + }, + { + "epoch": 1.02, + "learning_rate": 7.632719084516593e-06, + "loss": 3.8427, + "step": 2587648 + }, + { + "epoch": 1.02, + "learning_rate": 7.6243331370060735e-06, + "loss": 3.8497, + "step": 2588160 + }, + { + "epoch": 1.02, + "learning_rate": 7.615979947103016e-06, + "loss": 3.8447, + "step": 2588672 + }, + { + "epoch": 1.02, + "learning_rate": 7.607593999592495e-06, + "loss": 3.8498, + "step": 2589184 + }, + { + "epoch": 1.02, + "learning_rate": 7.599208052081976e-06, + "loss": 3.8461, + "step": 2589696 + }, + { + "epoch": 1.02, + "learning_rate": 7.590822104571456e-06, + "loss": 3.8495, + "step": 2590208 + }, + { + "epoch": 1.02, + "learning_rate": 7.582436157060935e-06, + "loss": 3.8381, + "step": 2590720 + }, + { + "epoch": 1.02, + "learning_rate": 7.574050209550415e-06, + "loss": 3.839, + "step": 2591232 + }, + { + "epoch": 1.02, + "learning_rate": 7.5656806408436265e-06, + "loss": 3.847, + "step": 2591744 + }, + { + "epoch": 1.02, + "learning_rate": 7.557294693333107e-06, + "loss": 3.8317, + "step": 2592256 + }, + { + "epoch": 1.02, + "learning_rate": 7.548908745822586e-06, + "loss": 3.8481, + "step": 2592768 + }, + { + "epoch": 1.02, + "learning_rate": 7.540522798312066e-06, + "loss": 3.8568, + "step": 2593280 + }, + { + "epoch": 1.02, + "learning_rate": 7.532136850801546e-06, + "loss": 3.8414, + "step": 2593792 + }, + { + "epoch": 1.02, + "learning_rate": 7.5237509032910254e-06, + "loss": 3.8391, + "step": 2594304 + }, + { + "epoch": 1.02, + "learning_rate": 7.515364955780506e-06, + "loss": 3.8441, + "step": 2594816 + }, + { + "epoch": 1.03, + "eval_loss": 3.9721503257751465, + "eval_runtime": 318.9518, + "eval_samples_per_second": 1196.391, + "eval_steps_per_second": 37.388, + "step": 2594880 + }, + { + "epoch": 0.0, + "learning_rate": 7.506979008269986e-06, + "loss": 3.8332, + "step": 2595328 + }, + { + "epoch": 0.0, + "learning_rate": 7.498593060759466e-06, + "loss": 3.8404, + "step": 2595840 + }, + { + "epoch": 0.0, + "learning_rate": 7.490207113248945e-06, + "loss": 3.8473, + "step": 2596352 + }, + { + "epoch": 0.0, + "learning_rate": 7.481821165738426e-06, + "loss": 3.8434, + "step": 2596864 + }, + { + "epoch": 0.0, + "learning_rate": 7.473435218227906e-06, + "loss": 3.8483, + "step": 2597376 + }, + { + "epoch": 0.0, + "learning_rate": 7.465049270717385e-06, + "loss": 3.8353, + "step": 2597888 + }, + { + "epoch": 0.0, + "learning_rate": 7.456663323206865e-06, + "loss": 3.846, + "step": 2598400 + }, + { + "epoch": 0.0, + "learning_rate": 7.448277375696346e-06, + "loss": 3.8325, + "step": 2598912 + }, + { + "epoch": 0.0, + "learning_rate": 7.439891428185824e-06, + "loss": 3.8462, + "step": 2599424 + }, + { + "epoch": 0.0, + "learning_rate": 7.431505480675305e-06, + "loss": 3.8399, + "step": 2599936 + }, + { + "epoch": 0.0, + "learning_rate": 7.423119533164785e-06, + "loss": 3.8498, + "step": 2600448 + }, + { + "epoch": 0.0, + "learning_rate": 7.414733585654266e-06, + "loss": 3.855, + "step": 2600960 + }, + { + "epoch": 0.0, + "learning_rate": 7.406364016947476e-06, + "loss": 3.8366, + "step": 2601472 + }, + { + "epoch": 0.0, + "learning_rate": 7.3979780694369565e-06, + "loss": 3.8394, + "step": 2601984 + }, + { + "epoch": 0.0, + "learning_rate": 7.389592121926436e-06, + "loss": 3.8415, + "step": 2602496 + }, + { + "epoch": 0.0, + "learning_rate": 7.3812061744159155e-06, + "loss": 3.835, + "step": 2603008 + }, + { + "epoch": 0.0, + "learning_rate": 7.3728202269053955e-06, + "loss": 3.8349, + "step": 2603520 + }, + { + "epoch": 0.0, + "learning_rate": 7.364434279394876e-06, + "loss": 3.8391, + "step": 2604032 + }, + { + "epoch": 0.0, + "learning_rate": 7.3560483318843545e-06, + "loss": 3.8339, + "step": 2604544 + }, + { + "epoch": 0.0, + "learning_rate": 7.347662384373835e-06, + "loss": 3.8577, + "step": 2605056 + }, + { + "epoch": 0.0, + "learning_rate": 7.339276436863315e-06, + "loss": 3.8384, + "step": 2605568 + }, + { + "epoch": 0.0, + "learning_rate": 7.330890489352796e-06, + "loss": 3.8544, + "step": 2606080 + }, + { + "epoch": 0.0, + "learning_rate": 7.322504541842274e-06, + "loss": 3.8502, + "step": 2606592 + }, + { + "epoch": 0.0, + "learning_rate": 7.314118594331755e-06, + "loss": 3.8574, + "step": 2607104 + }, + { + "epoch": 0.0, + "learning_rate": 7.305765404428698e-06, + "loss": 3.8294, + "step": 2607616 + }, + { + "epoch": 0.0, + "learning_rate": 7.2973794569181784e-06, + "loss": 3.8424, + "step": 2608128 + }, + { + "epoch": 0.0, + "learning_rate": 7.2889935094076575e-06, + "loss": 3.8341, + "step": 2608640 + }, + { + "epoch": 0.0, + "learning_rate": 7.2806075618971375e-06, + "loss": 3.8449, + "step": 2609152 + }, + { + "epoch": 0.0, + "learning_rate": 7.2722216143866175e-06, + "loss": 3.8359, + "step": 2609664 + }, + { + "epoch": 0.01, + "learning_rate": 7.2638356668760966e-06, + "loss": 3.839, + "step": 2610176 + }, + { + "epoch": 0.01, + "learning_rate": 7.255466098169308e-06, + "loss": 3.8488, + "step": 2610688 + }, + { + "epoch": 0.01, + "learning_rate": 7.247080150658789e-06, + "loss": 3.8465, + "step": 2611200 + }, + { + "epoch": 0.01, + "learning_rate": 7.238694203148269e-06, + "loss": 3.8324, + "step": 2611712 + }, + { + "epoch": 0.01, + "learning_rate": 7.230308255637748e-06, + "loss": 3.8515, + "step": 2612224 + }, + { + "epoch": 0.01, + "learning_rate": 7.22193868693096e-06, + "loss": 3.8481, + "step": 2612736 + }, + { + "epoch": 0.01, + "learning_rate": 7.21355273942044e-06, + "loss": 3.8411, + "step": 2613248 + }, + { + "epoch": 0.01, + "learning_rate": 7.205166791909919e-06, + "loss": 3.831, + "step": 2613760 + }, + { + "epoch": 0.01, + "learning_rate": 7.1967808443994e-06, + "loss": 3.8472, + "step": 2614272 + }, + { + "epoch": 0.01, + "learning_rate": 7.1883948968888795e-06, + "loss": 3.8282, + "step": 2614784 + }, + { + "epoch": 0.01, + "learning_rate": 7.180025328182091e-06, + "loss": 3.8423, + "step": 2615296 + }, + { + "epoch": 0.01, + "learning_rate": 7.17163938067157e-06, + "loss": 3.8383, + "step": 2615808 + }, + { + "epoch": 0.01, + "learning_rate": 7.16325343316105e-06, + "loss": 3.8508, + "step": 2616320 + }, + { + "epoch": 0.01, + "learning_rate": 7.154867485650531e-06, + "loss": 3.84, + "step": 2616832 + }, + { + "epoch": 0.01, + "learning_rate": 7.146481538140009e-06, + "loss": 3.8433, + "step": 2617344 + }, + { + "epoch": 0.01, + "learning_rate": 7.13809559062949e-06, + "loss": 3.8505, + "step": 2617856 + }, + { + "epoch": 0.01, + "learning_rate": 7.12970964311897e-06, + "loss": 3.8458, + "step": 2618368 + }, + { + "epoch": 0.01, + "learning_rate": 7.121323695608451e-06, + "loss": 3.8456, + "step": 2618880 + }, + { + "epoch": 0.01, + "learning_rate": 7.112954126901661e-06, + "loss": 3.8269, + "step": 2619392 + }, + { + "epoch": 0.01, + "learning_rate": 7.104568179391141e-06, + "loss": 3.8368, + "step": 2619904 + }, + { + "epoch": 0.01, + "learning_rate": 7.096198610684353e-06, + "loss": 3.8487, + "step": 2620416 + }, + { + "epoch": 0.01, + "learning_rate": 7.087812663173833e-06, + "loss": 3.8407, + "step": 2620928 + }, + { + "epoch": 0.01, + "learning_rate": 7.079426715663312e-06, + "loss": 3.8363, + "step": 2621440 + }, + { + "epoch": 0.01, + "learning_rate": 7.071040768152792e-06, + "loss": 3.8269, + "step": 2621952 + }, + { + "epoch": 0.01, + "learning_rate": 7.062654820642273e-06, + "loss": 3.8387, + "step": 2622464 + }, + { + "epoch": 0.01, + "learning_rate": 7.054268873131751e-06, + "loss": 3.8242, + "step": 2622976 + }, + { + "epoch": 0.01, + "learning_rate": 7.045882925621232e-06, + "loss": 3.8442, + "step": 2623488 + }, + { + "epoch": 0.01, + "learning_rate": 7.037496978110712e-06, + "loss": 3.8354, + "step": 2624000 + }, + { + "epoch": 0.01, + "learning_rate": 7.029127409403924e-06, + "loss": 3.8487, + "step": 2624512 + }, + { + "epoch": 0.01, + "learning_rate": 7.020741461893403e-06, + "loss": 3.8426, + "step": 2625024 + }, + { + "epoch": 0.01, + "learning_rate": 7.012355514382883e-06, + "loss": 3.828, + "step": 2625536 + }, + { + "epoch": 0.01, + "learning_rate": 7.003969566872364e-06, + "loss": 3.8354, + "step": 2626048 + }, + { + "epoch": 0.01, + "learning_rate": 6.995583619361843e-06, + "loss": 3.8409, + "step": 2626560 + }, + { + "epoch": 0.01, + "learning_rate": 6.987197671851323e-06, + "loss": 3.8283, + "step": 2627072 + }, + { + "epoch": 0.01, + "learning_rate": 6.978811724340803e-06, + "loss": 3.838, + "step": 2627584 + }, + { + "epoch": 0.01, + "learning_rate": 6.970425776830282e-06, + "loss": 3.8445, + "step": 2628096 + }, + { + "epoch": 0.01, + "learning_rate": 6.962056208123493e-06, + "loss": 3.8431, + "step": 2628608 + }, + { + "epoch": 0.01, + "learning_rate": 6.953670260612974e-06, + "loss": 3.8317, + "step": 2629120 + }, + { + "epoch": 0.01, + "learning_rate": 6.945284313102454e-06, + "loss": 3.8219, + "step": 2629632 + }, + { + "epoch": 0.01, + "learning_rate": 6.936898365591933e-06, + "loss": 3.8335, + "step": 2630144 + }, + { + "epoch": 0.01, + "learning_rate": 6.928512418081413e-06, + "loss": 3.8441, + "step": 2630656 + }, + { + "epoch": 0.01, + "learning_rate": 6.920126470570894e-06, + "loss": 3.852, + "step": 2631168 + }, + { + "epoch": 0.01, + "learning_rate": 6.911740523060373e-06, + "loss": 3.8395, + "step": 2631680 + }, + { + "epoch": 0.01, + "learning_rate": 6.903354575549853e-06, + "loss": 3.8496, + "step": 2632192 + }, + { + "epoch": 0.01, + "learning_rate": 6.895001385646796e-06, + "loss": 3.8489, + "step": 2632704 + }, + { + "epoch": 0.01, + "learning_rate": 6.886615438136276e-06, + "loss": 3.8489, + "step": 2633216 + }, + { + "epoch": 0.01, + "learning_rate": 6.8782294906257554e-06, + "loss": 3.8267, + "step": 2633728 + }, + { + "epoch": 0.01, + "learning_rate": 6.869843543115235e-06, + "loss": 3.8485, + "step": 2634240 + }, + { + "epoch": 0.01, + "learning_rate": 6.861457595604716e-06, + "loss": 3.8436, + "step": 2634752 + }, + { + "epoch": 0.01, + "learning_rate": 6.853071648094196e-06, + "loss": 3.8345, + "step": 2635264 + }, + { + "epoch": 0.01, + "learning_rate": 6.844685700583675e-06, + "loss": 3.8439, + "step": 2635776 + }, + { + "epoch": 0.01, + "learning_rate": 6.836299753073155e-06, + "loss": 3.8386, + "step": 2636288 + }, + { + "epoch": 0.01, + "learning_rate": 6.827930184366367e-06, + "loss": 3.8515, + "step": 2636800 + }, + { + "epoch": 0.01, + "learning_rate": 6.819544236855846e-06, + "loss": 3.8425, + "step": 2637312 + }, + { + "epoch": 0.01, + "learning_rate": 6.811174668149058e-06, + "loss": 3.8327, + "step": 2637824 + }, + { + "epoch": 0.01, + "learning_rate": 6.8027887206385375e-06, + "loss": 3.8404, + "step": 2638336 + }, + { + "epoch": 0.01, + "learning_rate": 6.794402773128018e-06, + "loss": 3.8425, + "step": 2638848 + }, + { + "epoch": 0.01, + "learning_rate": 6.7860168256174975e-06, + "loss": 3.8424, + "step": 2639360 + }, + { + "epoch": 0.01, + "learning_rate": 6.777630878106977e-06, + "loss": 3.8393, + "step": 2639872 + }, + { + "epoch": 0.01, + "learning_rate": 6.769261309400189e-06, + "loss": 3.837, + "step": 2640384 + }, + { + "epoch": 0.02, + "learning_rate": 6.760875361889668e-06, + "loss": 3.8448, + "step": 2640896 + }, + { + "epoch": 0.02, + "learning_rate": 6.752489414379148e-06, + "loss": 3.8352, + "step": 2641408 + }, + { + "epoch": 0.02, + "learning_rate": 6.744103466868629e-06, + "loss": 3.8415, + "step": 2641920 + }, + { + "epoch": 0.02, + "learning_rate": 6.735717519358109e-06, + "loss": 3.8337, + "step": 2642432 + }, + { + "epoch": 0.02, + "learning_rate": 6.727331571847588e-06, + "loss": 3.8489, + "step": 2642944 + }, + { + "epoch": 0.02, + "learning_rate": 6.718945624337068e-06, + "loss": 3.8465, + "step": 2643456 + }, + { + "epoch": 0.02, + "learning_rate": 6.710559676826549e-06, + "loss": 3.842, + "step": 2643968 + }, + { + "epoch": 0.02, + "learning_rate": 6.702206486923491e-06, + "loss": 3.8323, + "step": 2644480 + }, + { + "epoch": 0.02, + "learning_rate": 6.69382053941297e-06, + "loss": 3.8441, + "step": 2644992 + }, + { + "epoch": 0.02, + "learning_rate": 6.685450970706182e-06, + "loss": 3.8342, + "step": 2645504 + }, + { + "epoch": 0.02, + "learning_rate": 6.677065023195663e-06, + "loss": 3.8544, + "step": 2646016 + }, + { + "epoch": 0.02, + "learning_rate": 6.668679075685141e-06, + "loss": 3.8434, + "step": 2646528 + }, + { + "epoch": 0.02, + "learning_rate": 6.660293128174622e-06, + "loss": 3.837, + "step": 2647040 + }, + { + "epoch": 0.02, + "learning_rate": 6.651907180664102e-06, + "loss": 3.8324, + "step": 2647552 + }, + { + "epoch": 0.02, + "learning_rate": 6.643521233153583e-06, + "loss": 3.8433, + "step": 2648064 + }, + { + "epoch": 0.02, + "learning_rate": 6.635135285643061e-06, + "loss": 3.8202, + "step": 2648576 + }, + { + "epoch": 0.02, + "learning_rate": 6.626749338132542e-06, + "loss": 3.8355, + "step": 2649088 + }, + { + "epoch": 0.02, + "learning_rate": 6.618363390622022e-06, + "loss": 3.8364, + "step": 2649600 + }, + { + "epoch": 0.02, + "learning_rate": 6.609977443111501e-06, + "loss": 3.8396, + "step": 2650112 + }, + { + "epoch": 0.02, + "learning_rate": 6.6015914956009815e-06, + "loss": 3.8266, + "step": 2650624 + }, + { + "epoch": 0.02, + "learning_rate": 6.593221926894193e-06, + "loss": 3.8429, + "step": 2651136 + }, + { + "epoch": 0.02, + "learning_rate": 6.584835979383673e-06, + "loss": 3.8286, + "step": 2651648 + }, + { + "epoch": 0.02, + "learning_rate": 6.576450031873152e-06, + "loss": 3.851, + "step": 2652160 + }, + { + "epoch": 0.02, + "learning_rate": 6.568080463166364e-06, + "loss": 3.8355, + "step": 2652672 + }, + { + "epoch": 0.02, + "learning_rate": 6.5597108944595755e-06, + "loss": 3.8369, + "step": 2653184 + }, + { + "epoch": 0.02, + "learning_rate": 6.5513249469490554e-06, + "loss": 3.8548, + "step": 2653696 + }, + { + "epoch": 0.02, + "learning_rate": 6.5429389994385346e-06, + "loss": 3.8602, + "step": 2654208 + }, + { + "epoch": 0.02, + "learning_rate": 6.5345530519280145e-06, + "loss": 3.8395, + "step": 2654720 + }, + { + "epoch": 0.02, + "learning_rate": 6.526167104417495e-06, + "loss": 3.8347, + "step": 2655232 + }, + { + "epoch": 0.02, + "learning_rate": 6.5177811569069744e-06, + "loss": 3.8439, + "step": 2655744 + }, + { + "epoch": 0.02, + "learning_rate": 6.509411588200186e-06, + "loss": 3.8363, + "step": 2656256 + }, + { + "epoch": 0.02, + "learning_rate": 6.501025640689666e-06, + "loss": 3.8361, + "step": 2656768 + }, + { + "epoch": 0.02, + "learning_rate": 6.492639693179146e-06, + "loss": 3.8494, + "step": 2657280 + }, + { + "epoch": 0.02, + "learning_rate": 6.484253745668625e-06, + "loss": 3.8333, + "step": 2657792 + }, + { + "epoch": 0.02, + "learning_rate": 6.475867798158106e-06, + "loss": 3.8535, + "step": 2658304 + }, + { + "epoch": 0.02, + "learning_rate": 6.467481850647586e-06, + "loss": 3.8413, + "step": 2658816 + }, + { + "epoch": 0.02, + "learning_rate": 6.459095903137065e-06, + "loss": 3.8396, + "step": 2659328 + }, + { + "epoch": 0.02, + "learning_rate": 6.450709955626545e-06, + "loss": 3.8318, + "step": 2659840 + }, + { + "epoch": 0.02, + "learning_rate": 6.442324008116026e-06, + "loss": 3.8452, + "step": 2660352 + }, + { + "epoch": 0.02, + "learning_rate": 6.433938060605505e-06, + "loss": 3.8329, + "step": 2660864 + }, + { + "epoch": 0.02, + "learning_rate": 6.425552113094985e-06, + "loss": 3.8528, + "step": 2661376 + }, + { + "epoch": 0.02, + "learning_rate": 6.417166165584465e-06, + "loss": 3.8473, + "step": 2661888 + }, + { + "epoch": 0.02, + "learning_rate": 6.408796596877676e-06, + "loss": 3.8421, + "step": 2662400 + }, + { + "epoch": 0.02, + "learning_rate": 6.4004106493671555e-06, + "loss": 3.8279, + "step": 2662912 + }, + { + "epoch": 0.02, + "learning_rate": 6.392024701856636e-06, + "loss": 3.8499, + "step": 2663424 + }, + { + "epoch": 0.02, + "learning_rate": 6.383638754346116e-06, + "loss": 3.8448, + "step": 2663936 + }, + { + "epoch": 0.02, + "learning_rate": 6.375252806835595e-06, + "loss": 3.842, + "step": 2664448 + }, + { + "epoch": 0.02, + "learning_rate": 6.366883238128807e-06, + "loss": 3.8421, + "step": 2664960 + }, + { + "epoch": 0.02, + "learning_rate": 6.358497290618287e-06, + "loss": 3.8513, + "step": 2665472 + }, + { + "epoch": 0.02, + "learning_rate": 6.3501277219114986e-06, + "loss": 3.8459, + "step": 2665984 + }, + { + "epoch": 0.02, + "learning_rate": 6.341741774400978e-06, + "loss": 3.851, + "step": 2666496 + }, + { + "epoch": 0.02, + "learning_rate": 6.333355826890458e-06, + "loss": 3.8333, + "step": 2667008 + }, + { + "epoch": 0.02, + "learning_rate": 6.3249698793799384e-06, + "loss": 3.8375, + "step": 2667520 + }, + { + "epoch": 0.02, + "learning_rate": 6.316583931869418e-06, + "loss": 3.8438, + "step": 2668032 + }, + { + "epoch": 0.02, + "learning_rate": 6.3081979843588975e-06, + "loss": 3.8276, + "step": 2668544 + }, + { + "epoch": 0.02, + "learning_rate": 6.299812036848378e-06, + "loss": 3.8427, + "step": 2669056 + }, + { + "epoch": 0.02, + "learning_rate": 6.291426089337858e-06, + "loss": 3.8536, + "step": 2669568 + }, + { + "epoch": 0.02, + "learning_rate": 6.283040141827337e-06, + "loss": 3.8376, + "step": 2670080 + }, + { + "epoch": 0.02, + "learning_rate": 6.274654194316817e-06, + "loss": 3.8352, + "step": 2670592 + }, + { + "epoch": 0.02, + "learning_rate": 6.266268246806298e-06, + "loss": 3.845, + "step": 2671104 + }, + { + "epoch": 0.03, + "eval_loss": 3.971656084060669, + "eval_runtime": 294.702, + "eval_samples_per_second": 1294.837, + "eval_steps_per_second": 40.465, + "step": 2671200 + }, + { + "epoch": 0.0, + "learning_rate": 6.257882299295776e-06, + "loss": 3.831, + "step": 2671616 + }, + { + "epoch": 0.0, + "learning_rate": 6.249496351785257e-06, + "loss": 3.8384, + "step": 2672128 + }, + { + "epoch": 0.0, + "learning_rate": 6.241110404274737e-06, + "loss": 3.8464, + "step": 2672640 + }, + { + "epoch": 0.0, + "learning_rate": 6.232724456764217e-06, + "loss": 3.8375, + "step": 2673152 + }, + { + "epoch": 0.0, + "learning_rate": 6.224338509253696e-06, + "loss": 3.8485, + "step": 2673664 + }, + { + "epoch": 0.0, + "learning_rate": 6.215952561743177e-06, + "loss": 3.8327, + "step": 2674176 + }, + { + "epoch": 0.0, + "learning_rate": 6.207566614232656e-06, + "loss": 3.8453, + "step": 2674688 + }, + { + "epoch": 0.0, + "learning_rate": 6.199180666722137e-06, + "loss": 3.8302, + "step": 2675200 + }, + { + "epoch": 0.0, + "learning_rate": 6.190794719211616e-06, + "loss": 3.8438, + "step": 2675712 + }, + { + "epoch": 0.0, + "learning_rate": 6.182408771701096e-06, + "loss": 3.8361, + "step": 2676224 + }, + { + "epoch": 0.0, + "learning_rate": 6.174022824190576e-06, + "loss": 3.8485, + "step": 2676736 + }, + { + "epoch": 0.0, + "learning_rate": 6.165636876680056e-06, + "loss": 3.8502, + "step": 2677248 + }, + { + "epoch": 0.0, + "learning_rate": 6.1572673079732675e-06, + "loss": 3.8353, + "step": 2677760 + }, + { + "epoch": 0.0, + "learning_rate": 6.1488813604627475e-06, + "loss": 3.8389, + "step": 2678272 + }, + { + "epoch": 0.0, + "learning_rate": 6.1404954129522274e-06, + "loss": 3.837, + "step": 2678784 + }, + { + "epoch": 0.0, + "learning_rate": 6.132109465441707e-06, + "loss": 3.8365, + "step": 2679296 + }, + { + "epoch": 0.0, + "learning_rate": 6.1237235179311865e-06, + "loss": 3.831, + "step": 2679808 + }, + { + "epoch": 0.0, + "learning_rate": 6.115337570420667e-06, + "loss": 3.8359, + "step": 2680320 + }, + { + "epoch": 0.0, + "learning_rate": 6.106951622910146e-06, + "loss": 3.8318, + "step": 2680832 + }, + { + "epoch": 0.0, + "learning_rate": 6.098565675399627e-06, + "loss": 3.8613, + "step": 2681344 + }, + { + "epoch": 0.0, + "learning_rate": 6.090179727889106e-06, + "loss": 3.8378, + "step": 2681856 + }, + { + "epoch": 0.0, + "learning_rate": 6.081793780378586e-06, + "loss": 3.8462, + "step": 2682368 + }, + { + "epoch": 0.0, + "learning_rate": 6.073407832868066e-06, + "loss": 3.8524, + "step": 2682880 + }, + { + "epoch": 0.0, + "learning_rate": 6.065021885357546e-06, + "loss": 3.8506, + "step": 2683392 + }, + { + "epoch": 0.0, + "learning_rate": 6.056652316650758e-06, + "loss": 3.8318, + "step": 2683904 + }, + { + "epoch": 0.0, + "learning_rate": 6.048266369140238e-06, + "loss": 3.8404, + "step": 2684416 + }, + { + "epoch": 0.0, + "learning_rate": 6.039880421629718e-06, + "loss": 3.8327, + "step": 2684928 + }, + { + "epoch": 0.0, + "learning_rate": 6.031494474119198e-06, + "loss": 3.8406, + "step": 2685440 + }, + { + "epoch": 0.0, + "learning_rate": 6.023124905412409e-06, + "loss": 3.8334, + "step": 2685952 + }, + { + "epoch": 0.01, + "learning_rate": 6.01475533670562e-06, + "loss": 3.8359, + "step": 2686464 + }, + { + "epoch": 0.01, + "learning_rate": 6.0063693891951e-06, + "loss": 3.8462, + "step": 2686976 + }, + { + "epoch": 0.01, + "learning_rate": 5.99798344168458e-06, + "loss": 3.8451, + "step": 2687488 + }, + { + "epoch": 0.01, + "learning_rate": 5.98959749417406e-06, + "loss": 3.8369, + "step": 2688000 + }, + { + "epoch": 0.01, + "learning_rate": 5.98121154666354e-06, + "loss": 3.8451, + "step": 2688512 + }, + { + "epoch": 0.01, + "learning_rate": 5.972841977956751e-06, + "loss": 3.844, + "step": 2689024 + }, + { + "epoch": 0.01, + "learning_rate": 5.9644560304462315e-06, + "loss": 3.8369, + "step": 2689536 + }, + { + "epoch": 0.01, + "learning_rate": 5.956070082935711e-06, + "loss": 3.8256, + "step": 2690048 + }, + { + "epoch": 0.01, + "learning_rate": 5.9476841354251915e-06, + "loss": 3.846, + "step": 2690560 + }, + { + "epoch": 0.01, + "learning_rate": 5.9392981879146706e-06, + "loss": 3.8247, + "step": 2691072 + }, + { + "epoch": 0.01, + "learning_rate": 5.930928619207882e-06, + "loss": 3.8386, + "step": 2691584 + }, + { + "epoch": 0.01, + "learning_rate": 5.922542671697362e-06, + "loss": 3.8344, + "step": 2692096 + }, + { + "epoch": 0.01, + "learning_rate": 5.914156724186841e-06, + "loss": 3.8472, + "step": 2692608 + }, + { + "epoch": 0.01, + "learning_rate": 5.905770776676322e-06, + "loss": 3.8447, + "step": 2693120 + }, + { + "epoch": 0.01, + "learning_rate": 5.897384829165801e-06, + "loss": 3.8367, + "step": 2693632 + }, + { + "epoch": 0.01, + "learning_rate": 5.888998881655281e-06, + "loss": 3.8492, + "step": 2694144 + }, + { + "epoch": 0.01, + "learning_rate": 5.880612934144761e-06, + "loss": 3.8453, + "step": 2694656 + }, + { + "epoch": 0.01, + "learning_rate": 5.872226986634241e-06, + "loss": 3.8439, + "step": 2695168 + }, + { + "epoch": 0.01, + "learning_rate": 5.863857417927453e-06, + "loss": 3.8258, + "step": 2695680 + }, + { + "epoch": 0.01, + "learning_rate": 5.8554878492206635e-06, + "loss": 3.833, + "step": 2696192 + }, + { + "epoch": 0.01, + "learning_rate": 5.847101901710144e-06, + "loss": 3.8479, + "step": 2696704 + }, + { + "epoch": 0.01, + "learning_rate": 5.838715954199623e-06, + "loss": 3.8351, + "step": 2697216 + }, + { + "epoch": 0.01, + "learning_rate": 5.830330006689104e-06, + "loss": 3.8328, + "step": 2697728 + }, + { + "epoch": 0.01, + "learning_rate": 5.821944059178583e-06, + "loss": 3.8292, + "step": 2698240 + }, + { + "epoch": 0.01, + "learning_rate": 5.813558111668063e-06, + "loss": 3.8386, + "step": 2698752 + }, + { + "epoch": 0.01, + "learning_rate": 5.805172164157543e-06, + "loss": 3.8258, + "step": 2699264 + }, + { + "epoch": 0.01, + "learning_rate": 5.796802595450755e-06, + "loss": 3.8368, + "step": 2699776 + }, + { + "epoch": 0.01, + "learning_rate": 5.788416647940235e-06, + "loss": 3.8362, + "step": 2700288 + }, + { + "epoch": 0.01, + "learning_rate": 5.780030700429715e-06, + "loss": 3.8416, + "step": 2700800 + }, + { + "epoch": 0.01, + "learning_rate": 5.771644752919195e-06, + "loss": 3.8411, + "step": 2701312 + }, + { + "epoch": 0.01, + "learning_rate": 5.763258805408675e-06, + "loss": 3.8275, + "step": 2701824 + }, + { + "epoch": 0.01, + "learning_rate": 5.754889236701886e-06, + "loss": 3.83, + "step": 2702336 + }, + { + "epoch": 0.01, + "learning_rate": 5.746503289191365e-06, + "loss": 3.8427, + "step": 2702848 + }, + { + "epoch": 0.01, + "learning_rate": 5.738117341680845e-06, + "loss": 3.825, + "step": 2703360 + }, + { + "epoch": 0.01, + "learning_rate": 5.729731394170325e-06, + "loss": 3.8337, + "step": 2703872 + }, + { + "epoch": 0.01, + "learning_rate": 5.721345446659805e-06, + "loss": 3.8412, + "step": 2704384 + }, + { + "epoch": 0.01, + "learning_rate": 5.712959499149285e-06, + "loss": 3.8456, + "step": 2704896 + }, + { + "epoch": 0.01, + "learning_rate": 5.704589930442496e-06, + "loss": 3.829, + "step": 2705408 + }, + { + "epoch": 0.01, + "learning_rate": 5.696203982931977e-06, + "loss": 3.8207, + "step": 2705920 + }, + { + "epoch": 0.01, + "learning_rate": 5.687818035421456e-06, + "loss": 3.8276, + "step": 2706432 + }, + { + "epoch": 0.01, + "learning_rate": 5.679432087910936e-06, + "loss": 3.8403, + "step": 2706944 + }, + { + "epoch": 0.01, + "learning_rate": 5.671046140400417e-06, + "loss": 3.8468, + "step": 2707456 + }, + { + "epoch": 0.01, + "learning_rate": 5.662660192889896e-06, + "loss": 3.8353, + "step": 2707968 + }, + { + "epoch": 0.01, + "learning_rate": 5.654274245379377e-06, + "loss": 3.8451, + "step": 2708480 + }, + { + "epoch": 0.01, + "learning_rate": 5.645888297868856e-06, + "loss": 3.847, + "step": 2708992 + }, + { + "epoch": 0.01, + "learning_rate": 5.637502350358336e-06, + "loss": 3.8461, + "step": 2709504 + }, + { + "epoch": 0.01, + "learning_rate": 5.629132781651547e-06, + "loss": 3.8255, + "step": 2710016 + }, + { + "epoch": 0.01, + "learning_rate": 5.620763212944759e-06, + "loss": 3.8454, + "step": 2710528 + }, + { + "epoch": 0.01, + "learning_rate": 5.612377265434238e-06, + "loss": 3.8417, + "step": 2711040 + }, + { + "epoch": 0.01, + "learning_rate": 5.603991317923718e-06, + "loss": 3.8315, + "step": 2711552 + }, + { + "epoch": 0.01, + "learning_rate": 5.59562174921693e-06, + "loss": 3.8387, + "step": 2712064 + }, + { + "epoch": 0.01, + "learning_rate": 5.58723580170641e-06, + "loss": 3.8383, + "step": 2712576 + }, + { + "epoch": 0.01, + "learning_rate": 5.5788498541958896e-06, + "loss": 3.8459, + "step": 2713088 + }, + { + "epoch": 0.01, + "learning_rate": 5.5704639066853695e-06, + "loss": 3.8409, + "step": 2713600 + }, + { + "epoch": 0.01, + "learning_rate": 5.5620779591748495e-06, + "loss": 3.8325, + "step": 2714112 + }, + { + "epoch": 0.01, + "learning_rate": 5.5536920116643294e-06, + "loss": 3.8416, + "step": 2714624 + }, + { + "epoch": 0.01, + "learning_rate": 5.5453060641538085e-06, + "loss": 3.8379, + "step": 2715136 + }, + { + "epoch": 0.01, + "learning_rate": 5.536920116643289e-06, + "loss": 3.8394, + "step": 2715648 + }, + { + "epoch": 0.01, + "learning_rate": 5.5285341691327684e-06, + "loss": 3.8383, + "step": 2716160 + }, + { + "epoch": 0.01, + "learning_rate": 5.520148221622249e-06, + "loss": 3.8333, + "step": 2716672 + }, + { + "epoch": 0.02, + "learning_rate": 5.511762274111728e-06, + "loss": 3.845, + "step": 2717184 + }, + { + "epoch": 0.02, + "learning_rate": 5.503376326601208e-06, + "loss": 3.8364, + "step": 2717696 + }, + { + "epoch": 0.02, + "learning_rate": 5.49500675789442e-06, + "loss": 3.8346, + "step": 2718208 + }, + { + "epoch": 0.02, + "learning_rate": 5.4866208103839e-06, + "loss": 3.8321, + "step": 2718720 + }, + { + "epoch": 0.02, + "learning_rate": 5.47823486287338e-06, + "loss": 3.849, + "step": 2719232 + }, + { + "epoch": 0.02, + "learning_rate": 5.46984891536286e-06, + "loss": 3.8408, + "step": 2719744 + }, + { + "epoch": 0.02, + "learning_rate": 5.4614793466560715e-06, + "loss": 3.8376, + "step": 2720256 + }, + { + "epoch": 0.02, + "learning_rate": 5.4530933991455506e-06, + "loss": 3.8306, + "step": 2720768 + }, + { + "epoch": 0.02, + "learning_rate": 5.444723830438762e-06, + "loss": 3.8397, + "step": 2721280 + }, + { + "epoch": 0.02, + "learning_rate": 5.436337882928242e-06, + "loss": 3.8298, + "step": 2721792 + }, + { + "epoch": 0.02, + "learning_rate": 5.427951935417722e-06, + "loss": 3.8566, + "step": 2722304 + }, + { + "epoch": 0.02, + "learning_rate": 5.419565987907202e-06, + "loss": 3.8376, + "step": 2722816 + }, + { + "epoch": 0.02, + "learning_rate": 5.411180040396681e-06, + "loss": 3.8348, + "step": 2723328 + }, + { + "epoch": 0.02, + "learning_rate": 5.402794092886162e-06, + "loss": 3.8317, + "step": 2723840 + }, + { + "epoch": 0.02, + "learning_rate": 5.394408145375641e-06, + "loss": 3.8409, + "step": 2724352 + }, + { + "epoch": 0.02, + "learning_rate": 5.386038576668853e-06, + "loss": 3.8155, + "step": 2724864 + }, + { + "epoch": 0.02, + "learning_rate": 5.377652629158333e-06, + "loss": 3.8336, + "step": 2725376 + }, + { + "epoch": 0.02, + "learning_rate": 5.3692666816478135e-06, + "loss": 3.8344, + "step": 2725888 + }, + { + "epoch": 0.02, + "learning_rate": 5.360880734137293e-06, + "loss": 3.8379, + "step": 2726400 + }, + { + "epoch": 0.02, + "learning_rate": 5.3524947866267725e-06, + "loss": 3.8239, + "step": 2726912 + }, + { + "epoch": 0.02, + "learning_rate": 5.3441088391162525e-06, + "loss": 3.842, + "step": 2727424 + }, + { + "epoch": 0.02, + "learning_rate": 5.3357228916057325e-06, + "loss": 3.8242, + "step": 2727936 + }, + { + "epoch": 0.02, + "learning_rate": 5.327353322898944e-06, + "loss": 3.8454, + "step": 2728448 + }, + { + "epoch": 0.02, + "learning_rate": 5.318967375388423e-06, + "loss": 3.8367, + "step": 2728960 + }, + { + "epoch": 0.02, + "learning_rate": 5.310581427877903e-06, + "loss": 3.8342, + "step": 2729472 + }, + { + "epoch": 0.02, + "learning_rate": 5.302195480367383e-06, + "loss": 3.849, + "step": 2729984 + }, + { + "epoch": 0.02, + "learning_rate": 5.293809532856863e-06, + "loss": 3.858, + "step": 2730496 + }, + { + "epoch": 0.02, + "learning_rate": 5.285423585346343e-06, + "loss": 3.8397, + "step": 2731008 + }, + { + "epoch": 0.02, + "learning_rate": 5.277037637835823e-06, + "loss": 3.834, + "step": 2731520 + }, + { + "epoch": 0.02, + "learning_rate": 5.268651690325303e-06, + "loss": 3.8419, + "step": 2732032 + }, + { + "epoch": 0.02, + "learning_rate": 5.260282121618515e-06, + "loss": 3.8325, + "step": 2732544 + }, + { + "epoch": 0.02, + "learning_rate": 5.251896174107994e-06, + "loss": 3.8336, + "step": 2733056 + }, + { + "epoch": 0.02, + "learning_rate": 5.243526605401205e-06, + "loss": 3.8488, + "step": 2733568 + }, + { + "epoch": 0.02, + "learning_rate": 5.235140657890685e-06, + "loss": 3.8324, + "step": 2734080 + }, + { + "epoch": 0.02, + "learning_rate": 5.226754710380165e-06, + "loss": 3.8485, + "step": 2734592 + }, + { + "epoch": 0.02, + "learning_rate": 5.218368762869645e-06, + "loss": 3.839, + "step": 2735104 + }, + { + "epoch": 0.02, + "learning_rate": 5.209999194162857e-06, + "loss": 3.8422, + "step": 2735616 + }, + { + "epoch": 0.02, + "learning_rate": 5.201613246652337e-06, + "loss": 3.8216, + "step": 2736128 + }, + { + "epoch": 0.02, + "learning_rate": 5.193243677945548e-06, + "loss": 3.844, + "step": 2736640 + }, + { + "epoch": 0.02, + "learning_rate": 5.1848577304350275e-06, + "loss": 3.8313, + "step": 2737152 + }, + { + "epoch": 0.02, + "learning_rate": 5.176471782924508e-06, + "loss": 3.8472, + "step": 2737664 + }, + { + "epoch": 0.02, + "learning_rate": 5.1680858354139874e-06, + "loss": 3.8418, + "step": 2738176 + }, + { + "epoch": 0.02, + "learning_rate": 5.159699887903467e-06, + "loss": 3.8475, + "step": 2738688 + }, + { + "epoch": 0.02, + "learning_rate": 5.151313940392947e-06, + "loss": 3.8261, + "step": 2739200 + }, + { + "epoch": 0.02, + "learning_rate": 5.142927992882427e-06, + "loss": 3.8504, + "step": 2739712 + }, + { + "epoch": 0.02, + "learning_rate": 5.134542045371907e-06, + "loss": 3.8393, + "step": 2740224 + }, + { + "epoch": 0.02, + "learning_rate": 5.126156097861387e-06, + "loss": 3.8417, + "step": 2740736 + }, + { + "epoch": 0.02, + "learning_rate": 5.117786529154599e-06, + "loss": 3.8403, + "step": 2741248 + }, + { + "epoch": 0.02, + "learning_rate": 5.109400581644078e-06, + "loss": 3.8478, + "step": 2741760 + }, + { + "epoch": 0.02, + "learning_rate": 5.10103101293729e-06, + "loss": 3.8432, + "step": 2742272 + }, + { + "epoch": 0.02, + "learning_rate": 5.0926450654267696e-06, + "loss": 3.8464, + "step": 2742784 + }, + { + "epoch": 0.02, + "learning_rate": 5.0842591179162495e-06, + "loss": 3.829, + "step": 2743296 + }, + { + "epoch": 0.02, + "learning_rate": 5.0758731704057295e-06, + "loss": 3.8373, + "step": 2743808 + }, + { + "epoch": 0.02, + "learning_rate": 5.0674872228952094e-06, + "loss": 3.8383, + "step": 2744320 + }, + { + "epoch": 0.02, + "learning_rate": 5.059101275384689e-06, + "loss": 3.831, + "step": 2744832 + }, + { + "epoch": 0.02, + "learning_rate": 5.050715327874169e-06, + "loss": 3.8407, + "step": 2745344 + }, + { + "epoch": 0.02, + "learning_rate": 5.0423293803636484e-06, + "loss": 3.8508, + "step": 2745856 + }, + { + "epoch": 0.02, + "learning_rate": 5.033943432853129e-06, + "loss": 3.8355, + "step": 2746368 + }, + { + "epoch": 0.02, + "learning_rate": 5.02557386414634e-06, + "loss": 3.8317, + "step": 2746880 + }, + { + "epoch": 0.02, + "learning_rate": 5.01718791663582e-06, + "loss": 3.8432, + "step": 2747392 + }, + { + "epoch": 0.03, + "eval_loss": 3.9711503982543945, + "eval_runtime": 652.5989, + "eval_samples_per_second": 584.725, + "eval_steps_per_second": 18.273, + "step": 2747520 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.1430365826415877e+18, + "trial_name": null, + "trial_params": null +}