diff --git "a/checkpoint-2060640/trainer_state.json" "b/checkpoint-2060640/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2060640/trainer_state.json" @@ -0,0 +1,24385 @@ +{ + "best_metric": 3.841780185699463, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/npi-sent-neg/transformer/2/checkpoints/checkpoint-915840", + "epoch": 1.0250006060157382, + "eval_steps": 10, + "global_step": 2060640, + "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": 11.0274, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8127, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1879, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9751, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8136, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.7053, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.5967, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5253, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4508, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.3976, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3482, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.305, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 5.2626, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.1983, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.1694, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.1287, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.1044, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.076, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0502, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0154, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983231380739706e-05, + "loss": 5.0069, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 4.9746, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.949, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9317, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9225, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790400448648195e-05, + "loss": 4.8901, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.8696, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.8548, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8301, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756873037409844e-05, + "loss": 4.824, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 4.8072, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740117521192533e-05, + "loss": 4.8019, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731731573682013e-05, + "loss": 4.7751, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.97233456261715e-05, + "loss": 4.7681, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.7583, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7458, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 4.7305, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968980183612942e-05, + "loss": 4.6997, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.96814158886189e-05, + "loss": 4.7022, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967302994110837e-05, + "loss": 4.6785, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.6833, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6691, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6645, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6479, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 4.6453, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6408, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.6266, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6306, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 4.5986, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.9589219602414374e-05, + "loss": 4.5918, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958083365490385e-05, + "loss": 4.6005, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957244770739333e-05, + "loss": 4.5893, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956406175988281e-05, + "loss": 4.5818, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 4.5532, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 4.5699, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 4.5471, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 4.5703, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522148401133936e-05, + "loss": 4.5256, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951377883242715e-05, + "loss": 4.5428, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5248, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.5093, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 4.5199, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.94802514211888e-05, + "loss": 4.5068, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.4859, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.4898, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 4.5036, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944672400995045e-05, + "loss": 4.4808, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 4.4746, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.4703, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.9421582546222625e-05, + "loss": 4.4572, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.9413196598712105e-05, + "loss": 4.47, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404810651201585e-05, + "loss": 4.4682, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396424703691065e-05, + "loss": 4.4562, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388038756180545e-05, + "loss": 4.4659, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379652808670025e-05, + "loss": 4.4531, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371266861159505e-05, + "loss": 4.4475, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362897292452714e-05, + "loss": 4.4295, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354511344942194e-05, + "loss": 4.4335, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346125397431674e-05, + "loss": 4.4281, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337739449921154e-05, + "loss": 4.4189, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.932936988121436e-05, + "loss": 4.4166, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932098393370384e-05, + "loss": 4.4235, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931259798619332e-05, + "loss": 4.4205, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930421203868281e-05, + "loss": 4.4125, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929582609117229e-05, + "loss": 4.3901, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.92874565224655e-05, + "loss": 4.4021, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927907057495498e-05, + "loss": 4.4051, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927068462744446e-05, + "loss": 4.4039, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926229867993394e-05, + "loss": 4.3885, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925391273242342e-05, + "loss": 4.3976, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924554316371663e-05, + "loss": 4.3851, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923715721620611e-05, + "loss": 4.3757, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922877126869559e-05, + "loss": 4.378, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922038532118507e-05, + "loss": 4.3745, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921201575247828e-05, + "loss": 4.3655, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920362980496776e-05, + "loss": 4.3764, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919524385745724e-05, + "loss": 4.3544, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918685790994672e-05, + "loss": 4.3509, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.91784719624362e-05, + "loss": 4.3501, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.9170086014925676e-05, + "loss": 4.3611, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.9161700067415156e-05, + "loss": 4.3547, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.9153314119904636e-05, + "loss": 4.3384, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914494455119785e-05, + "loss": 4.3399, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136558603687325e-05, + "loss": 4.3299, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.9128172656176805e-05, + "loss": 4.3384, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.9119786708666285e-05, + "loss": 4.3152, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.911143351876323e-05, + "loss": 4.3275, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910304757125272e-05, + "loss": 4.3251, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.90946616237422e-05, + "loss": 4.3212, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908627567623168e-05, + "loss": 4.3259, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907788972872115e-05, + "loss": 4.3178, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906950378121063e-05, + "loss": 4.3019, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906111783370011e-05, + "loss": 4.3151, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.9052748264993326e-05, + "loss": 4.3145, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.90443623174828e-05, + "loss": 4.3081, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903597636997228e-05, + "loss": 4.3097, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902759042246176e-05, + "loss": 4.3067, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.9019220853754975e-05, + "loss": 4.2998, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.9010834906244455e-05, + "loss": 4.2918, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.9002448958733935e-05, + "loss": 4.2937, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994063011223415e-05, + "loss": 4.2919, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985677063712895e-05, + "loss": 4.2802, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977291116202375e-05, + "loss": 4.283, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968905168691855e-05, + "loss": 4.2808, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960535599985064e-05, + "loss": 4.2889, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952149652474544e-05, + "loss": 4.2701, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943763704964024e-05, + "loss": 4.2737, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935377757453504e-05, + "loss": 4.2662, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.892700818874671e-05, + "loss": 4.2722, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.891862224123619e-05, + "loss": 4.2615, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.891023629372567e-05, + "loss": 4.2785, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890185034621515e-05, + "loss": 4.2633, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889346439870464e-05, + "loss": 4.2591, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888507845119412e-05, + "loss": 4.2604, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.88766925036836e-05, + "loss": 4.2623, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886830655617308e-05, + "loss": 4.2648, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885995336627002e-05, + "loss": 4.2638, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.88515674187595e-05, + "loss": 4.2564, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884318147124898e-05, + "loss": 4.2571, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883479552373846e-05, + "loss": 4.2533, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.8826425955031666e-05, + "loss": 4.2468, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.8818040007521146e-05, + "loss": 4.2377, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.8809654060010626e-05, + "loss": 4.2442, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.8801268112500106e-05, + "loss": 4.2371, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879289854379332e-05, + "loss": 4.2296, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.87845125962828e-05, + "loss": 4.2341, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877612664877228e-05, + "loss": 4.2306, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876774070126176e-05, + "loss": 4.2357, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875937113255497e-05, + "loss": 4.2357, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875098518504445e-05, + "loss": 4.2269, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.195883750915527, + "eval_runtime": 349.4311, + "eval_samples_per_second": 1092.035, + "eval_steps_per_second": 34.127, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.874259923753393e-05, + "loss": 4.21, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873421329002341e-05, + "loss": 4.2122, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.872582734251289e-05, + "loss": 4.2253, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.87174577738061e-05, + "loss": 4.216, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.870907182629558e-05, + "loss": 4.2197, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.870068587878506e-05, + "loss": 4.2054, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.869229993127454e-05, + "loss": 4.2011, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683913983764027e-05, + "loss": 4.2027, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.8675560793860965e-05, + "loss": 4.2093, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.8667174846350445e-05, + "loss": 4.2044, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.8658788898839925e-05, + "loss": 4.2021, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.8650402951329405e-05, + "loss": 4.2106, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.8642017003818885e-05, + "loss": 4.1792, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.8633631056308365e-05, + "loss": 4.1883, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.8625245108797845e-05, + "loss": 4.1854, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.8616859161287324e-05, + "loss": 4.1753, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.8608473213776804e-05, + "loss": 4.1893, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.8600103645070014e-05, + "loss": 4.1821, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.8591717697559493e-05, + "loss": 4.1764, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858333175004898e-05, + "loss": 4.2025, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.857494580253846e-05, + "loss": 4.1802, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.856657623383167e-05, + "loss": 4.1769, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.855819028632115e-05, + "loss": 4.179, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.854980433881063e-05, + "loss": 4.1878, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.854141839130011e-05, + "loss": 4.1691, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.853303244378958e-05, + "loss": 4.1674, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.85246628750828e-05, + "loss": 4.1695, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851627692757228e-05, + "loss": 4.1636, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.850789098006175e-05, + "loss": 4.1646, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.849950503255123e-05, + "loss": 4.1578, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849115184264818e-05, + "loss": 4.1767, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848276589513766e-05, + "loss": 4.1624, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847437994762714e-05, + "loss": 4.161, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846599400011662e-05, + "loss": 4.158, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.84576080526061e-05, + "loss": 4.1632, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844922210509558e-05, + "loss": 4.1557, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.8440836157585056e-05, + "loss": 4.1396, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.8432450210074536e-05, + "loss": 4.1436, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.8424064262564016e-05, + "loss": 4.1352, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.8415694693857225e-05, + "loss": 4.1487, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.8407308746346705e-05, + "loss": 4.1383, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.8398922798836185e-05, + "loss": 4.1467, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839053685132567e-05, + "loss": 4.1383, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.838216728261888e-05, + "loss": 4.1385, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.837378133510836e-05, + "loss": 4.1451, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836539538759784e-05, + "loss": 4.1344, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.835700944008732e-05, + "loss": 4.1403, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834863987138053e-05, + "loss": 4.127, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834025392387001e-05, + "loss": 4.1252, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.833186797635949e-05, + "loss": 4.1329, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.832348202884897e-05, + "loss": 4.1299, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.831511246014218e-05, + "loss": 4.1353, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.830672651263166e-05, + "loss": 4.1064, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.829834056512114e-05, + "loss": 4.128, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.8289954617610625e-05, + "loss": 4.108, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.8281585048903834e-05, + "loss": 4.1378, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273199101393314e-05, + "loss": 4.1065, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.8264813153882794e-05, + "loss": 4.1226, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.8256427206372274e-05, + "loss": 4.1144, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.8248057637665483e-05, + "loss": 4.0984, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823967169015496e-05, + "loss": 4.111, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823128574264444e-05, + "loss": 4.1089, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.822289979513392e-05, + "loss": 4.0913, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.821453022642713e-05, + "loss": 4.098, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820614427891661e-05, + "loss": 4.1142, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.819775833140609e-05, + "loss": 4.1007, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.818937238389558e-05, + "loss": 4.0982, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.818100281518879e-05, + "loss": 4.0969, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.817261686767827e-05, + "loss": 4.0838, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.816423092016775e-05, + "loss": 4.1035, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.815584497265723e-05, + "loss": 4.1021, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.814747540395044e-05, + "loss": 4.1003, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.813908945643992e-05, + "loss": 4.1085, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.81307035089294e-05, + "loss": 4.0999, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812231756141888e-05, + "loss": 4.1005, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.8113947992712086e-05, + "loss": 4.0832, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.8105562045201566e-05, + "loss": 4.0963, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.8097176097691046e-05, + "loss": 4.0883, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.808879015018053e-05, + "loss": 4.083, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808042058147374e-05, + "loss": 4.0856, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807203463396322e-05, + "loss": 4.0911, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.80636486864527e-05, + "loss": 4.097, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805526273894218e-05, + "loss": 4.0897, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804687679143166e-05, + "loss": 4.0711, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803850722272487e-05, + "loss": 4.0766, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.803012127521435e-05, + "loss": 4.0924, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.802173532770383e-05, + "loss": 4.0881, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801334938019331e-05, + "loss": 4.0807, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.800497981148652e-05, + "loss": 4.0869, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.7996610242779736e-05, + "loss": 4.084, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.7988224295269215e-05, + "loss": 4.0693, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.7979838347758695e-05, + "loss": 4.0761, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.7971452400248175e-05, + "loss": 4.0793, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.7963066452737655e-05, + "loss": 4.0702, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.7954696884030864e-05, + "loss": 4.0856, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.7946310936520344e-05, + "loss": 4.0653, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.7937924989009824e-05, + "loss": 4.0622, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.7929539041499304e-05, + "loss": 4.0678, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.7921153093988784e-05, + "loss": 4.0754, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.7912767146478264e-05, + "loss": 4.074, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.7904381198967744e-05, + "loss": 4.0623, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.7895995251457224e-05, + "loss": 4.0597, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.788762568275043e-05, + "loss": 4.0541, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.787923973523992e-05, + "loss": 4.0717, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.78708537877294e-05, + "loss": 4.0459, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.786248421902261e-05, + "loss": 4.0525, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.785409827151209e-05, + "loss": 4.0661, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.784571232400157e-05, + "loss": 4.058, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.783734275529478e-05, + "loss": 4.0561, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.782895680778426e-05, + "loss": 4.057, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782057086027374e-05, + "loss": 4.0476, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.781218491276322e-05, + "loss": 4.0591, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.78037989652527e-05, + "loss": 4.0539, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779541301774218e-05, + "loss": 4.0557, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.778702707023166e-05, + "loss": 4.0579, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777864112272114e-05, + "loss": 4.06, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.777028793281808e-05, + "loss": 4.0505, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.776190198530756e-05, + "loss": 4.0433, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775351603779704e-05, + "loss": 4.0498, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.774513009028652e-05, + "loss": 4.0472, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.7736744142776e-05, + "loss": 4.0357, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772835819526548e-05, + "loss": 4.0433, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.7719972247754956e-05, + "loss": 4.0397, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771160267904817e-05, + "loss": 4.0509, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770321673153765e-05, + "loss": 4.0341, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769483078402713e-05, + "loss": 4.043, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768644483651661e-05, + "loss": 4.0243, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.767807526780983e-05, + "loss": 4.042, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766968932029931e-05, + "loss": 4.0318, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766130337278878e-05, + "loss": 4.05, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765291742527826e-05, + "loss": 4.0403, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.7644547856571476e-05, + "loss": 4.0349, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.7636161909060956e-05, + "loss": 4.0288, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762777596155043e-05, + "loss": 4.0364, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761939001403991e-05, + "loss": 4.0444, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.7611020445333125e-05, + "loss": 4.0452, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.7602634497822605e-05, + "loss": 4.0398, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.759424855031208e-05, + "loss": 4.0392, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.7585862602801565e-05, + "loss": 4.0309, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.757749303409478e-05, + "loss": 4.0321, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.7569107086584254e-05, + "loss": 4.0244, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.7560721139073734e-05, + "loss": 4.0306, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.7552335191563214e-05, + "loss": 4.0252, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.754398200166016e-05, + "loss": 4.0176, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.753559605414964e-05, + "loss": 4.0285, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.752721010663912e-05, + "loss": 4.024, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.75188241591286e-05, + "loss": 4.0271, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.751043821161808e-05, + "loss": 4.0251, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.750206864291129e-05, + "loss": 4.0235, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.026477336883545, + "eval_runtime": 327.3586, + "eval_samples_per_second": 1165.667, + "eval_steps_per_second": 36.428, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.749368269540077e-05, + "loss": 4.0065, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748529674789025e-05, + "loss": 4.0118, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747691080037973e-05, + "loss": 4.0224, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746852485286921e-05, + "loss": 4.0192, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.746013890535869e-05, + "loss": 4.0261, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.745175295784817e-05, + "loss": 4.0023, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.744336701033765e-05, + "loss": 4.0103, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.743498106282713e-05, + "loss": 4.0057, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.742659511531661e-05, + "loss": 4.016, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.741820916780609e-05, + "loss": 4.014, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740982322029557e-05, + "loss": 4.0117, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.7401453651588777e-05, + "loss": 4.0139, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.7393084082881986e-05, + "loss": 3.993, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738469813537147e-05, + "loss": 4.0, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737631218786095e-05, + "loss": 4.0021, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736792624035043e-05, + "loss": 3.9937, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735955667164364e-05, + "loss": 4.002, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735117072413312e-05, + "loss": 3.9974, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.73427847766226e-05, + "loss": 3.995, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733439882911208e-05, + "loss": 4.0244, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732601288160156e-05, + "loss": 3.9972, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731762693409104e-05, + "loss": 4.0018, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.730924098658052e-05, + "loss": 3.9982, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730087141787373e-05, + "loss": 4.0105, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729248547036321e-05, + "loss": 3.991, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728409952285269e-05, + "loss": 3.9918, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727571357534217e-05, + "loss": 3.9965, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.7267344006635386e-05, + "loss": 3.9933, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.7258958059124866e-05, + "loss": 3.9851, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.7250572111614346e-05, + "loss": 3.9887, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.7242202542907555e-05, + "loss": 4.0053, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.7233816595397035e-05, + "loss": 3.9934, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.7225430647886515e-05, + "loss": 3.9907, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.7217044700375995e-05, + "loss": 3.996, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.7208658752865475e-05, + "loss": 3.9922, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.7200289184158684e-05, + "loss": 3.9901, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.7191903236648164e-05, + "loss": 3.9736, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.7183517289137644e-05, + "loss": 3.9859, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.7175131341627124e-05, + "loss": 3.9713, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.7166745394116604e-05, + "loss": 3.984, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.715835944660609e-05, + "loss": 3.9781, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.7149973499095564e-05, + "loss": 3.9881, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.7141587551585044e-05, + "loss": 3.9807, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.713321798287826e-05, + "loss": 3.9777, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712483203536774e-05, + "loss": 3.9857, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711644608785721e-05, + "loss": 3.9808, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710806014034669e-05, + "loss": 3.9828, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709970695044364e-05, + "loss": 3.9704, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.709132100293312e-05, + "loss": 3.9682, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.70829350554226e-05, + "loss": 3.9798, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.707454910791208e-05, + "loss": 3.974, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706616316040156e-05, + "loss": 3.9758, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705777721289104e-05, + "loss": 3.9576, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704939126538052e-05, + "loss": 3.9792, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704100531787e-05, + "loss": 3.9567, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703265212796694e-05, + "loss": 3.985, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.702426618045642e-05, + "loss": 3.9523, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.70158802329459e-05, + "loss": 3.9768, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.700749428543538e-05, + "loss": 3.9642, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.6999108337924855e-05, + "loss": 3.9571, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.6990722390414335e-05, + "loss": 3.9616, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.6982336442903815e-05, + "loss": 3.9627, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.6973950495393295e-05, + "loss": 3.9464, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696558092668651e-05, + "loss": 3.9539, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695719497917599e-05, + "loss": 3.9658, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694880903166547e-05, + "loss": 3.9619, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694042308415495e-05, + "loss": 3.9522, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693205351544816e-05, + "loss": 3.9528, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692366756793764e-05, + "loss": 3.9499, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691528162042712e-05, + "loss": 3.9559, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690691205172033e-05, + "loss": 3.9588, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689852610420981e-05, + "loss": 3.9587, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.689014015669929e-05, + "loss": 3.9696, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688175420918877e-05, + "loss": 3.9645, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.687336826167825e-05, + "loss": 3.9624, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.6864998692971465e-05, + "loss": 3.9447, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.6856612745460945e-05, + "loss": 3.9566, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6848226797950425e-05, + "loss": 3.9568, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.6839840850439905e-05, + "loss": 3.9441, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.6831471281733114e-05, + "loss": 3.9528, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.6823085334222594e-05, + "loss": 3.9547, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.6814699386712074e-05, + "loss": 3.961, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.6806313439201554e-05, + "loss": 3.9525, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.6797927491691034e-05, + "loss": 3.9385, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.6789541544180514e-05, + "loss": 3.9463, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.6781155596669993e-05, + "loss": 3.9554, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.6772769649159473e-05, + "loss": 3.9561, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676440008045269e-05, + "loss": 3.9493, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675601413294217e-05, + "loss": 3.9557, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674764456423538e-05, + "loss": 3.9564, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.673925861672486e-05, + "loss": 3.9363, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.673087266921434e-05, + "loss": 3.9497, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.672248672170382e-05, + "loss": 3.9461, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671411715299703e-05, + "loss": 3.9413, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.6705747584290236e-05, + "loss": 3.9609, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.6697361636779716e-05, + "loss": 3.9412, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.6688975689269196e-05, + "loss": 3.9302, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.6680589741758676e-05, + "loss": 3.9403, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.6672203794248156e-05, + "loss": 3.9512, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666381784673764e-05, + "loss": 3.9469, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665543189922712e-05, + "loss": 3.9388, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.66470459517166e-05, + "loss": 3.9315, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663866000420608e-05, + "loss": 3.9305, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663029043549929e-05, + "loss": 3.9484, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662190448798877e-05, + "loss": 3.9216, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661351854047825e-05, + "loss": 3.934, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660513259296773e-05, + "loss": 3.9443, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659674664545721e-05, + "loss": 3.9349, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.658837707675042e-05, + "loss": 3.9329, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.65799911292399e-05, + "loss": 3.9379, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657160518172938e-05, + "loss": 3.9299, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.656321923421886e-05, + "loss": 3.9395, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.6554849665512077e-05, + "loss": 3.9329, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.6546463718001557e-05, + "loss": 3.9339, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.6538077770491036e-05, + "loss": 3.9396, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.6529691822980516e-05, + "loss": 3.9411, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.6521322254273726e-05, + "loss": 3.9367, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.6512936306763206e-05, + "loss": 3.9234, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.6504550359252685e-05, + "loss": 3.9303, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.6496164411742165e-05, + "loss": 3.9287, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.6487794843035375e-05, + "loss": 3.9181, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.6479408895524854e-05, + "loss": 3.9303, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.6471022948014334e-05, + "loss": 3.9193, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.6462637000503814e-05, + "loss": 3.9356, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.6454251052993294e-05, + "loss": 3.9197, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644588148428651e-05, + "loss": 3.9276, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.643749553677599e-05, + "loss": 3.913, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.642910958926546e-05, + "loss": 3.9268, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642072364175494e-05, + "loss": 3.9171, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.641235407304816e-05, + "loss": 3.9373, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640396812553764e-05, + "loss": 3.9305, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.639558217802711e-05, + "loss": 3.9229, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.638719623051659e-05, + "loss": 3.9136, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637881028300607e-05, + "loss": 3.9234, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.637044071429929e-05, + "loss": 3.9306, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636205476678877e-05, + "loss": 3.9367, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.635366881927825e-05, + "loss": 3.9255, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.634528287176773e-05, + "loss": 3.9293, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633691330306094e-05, + "loss": 3.9236, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.632852735555042e-05, + "loss": 3.9236, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.63201414080399e-05, + "loss": 3.9144, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.631175546052938e-05, + "loss": 3.917, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.630336951301886e-05, + "loss": 3.9207, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629498356550834e-05, + "loss": 3.9095, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.6286613996801546e-05, + "loss": 3.9167, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.6278228049291026e-05, + "loss": 3.9201, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.6269842101780506e-05, + "loss": 3.9151, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.6261456154269986e-05, + "loss": 3.9168, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.62530865855632e-05, + "loss": 3.9131, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.9512994289398193, + "eval_runtime": 301.0079, + "eval_samples_per_second": 1267.711, + "eval_steps_per_second": 39.617, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624470063805268e-05, + "loss": 3.909, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.623631469054216e-05, + "loss": 3.9035, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.622792874303164e-05, + "loss": 3.9205, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.621955917432485e-05, + "loss": 3.9102, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621117322681433e-05, + "loss": 3.9229, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620278727930381e-05, + "loss": 3.8982, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.619440133179329e-05, + "loss": 3.9073, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.618601538428277e-05, + "loss": 3.8991, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.617764581557598e-05, + "loss": 3.9132, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.616925986806546e-05, + "loss": 3.9118, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.616087392055494e-05, + "loss": 3.9096, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.615248797304442e-05, + "loss": 3.9097, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.6144118404337635e-05, + "loss": 3.8913, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.6135732456827115e-05, + "loss": 3.8987, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.6127346509316595e-05, + "loss": 3.9002, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.6118960561806075e-05, + "loss": 3.8954, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.6110574614295555e-05, + "loss": 3.8984, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.6102188666785035e-05, + "loss": 3.9, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.6093802719274515e-05, + "loss": 3.8912, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.6085416771763995e-05, + "loss": 3.9282, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.6077047203057204e-05, + "loss": 3.8991, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.6068661255546684e-05, + "loss": 3.8998, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.6060275308036164e-05, + "loss": 3.9032, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.6051889360525644e-05, + "loss": 3.9089, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.604351979181886e-05, + "loss": 3.8929, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.603513384430834e-05, + "loss": 3.9024, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.602674789679782e-05, + "loss": 3.8959, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.60183619492873e-05, + "loss": 3.8959, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.600999238058051e-05, + "loss": 3.8851, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.600160643306999e-05, + "loss": 3.8943, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.599322048555947e-05, + "loss": 3.9062, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598483453804895e-05, + "loss": 3.8989, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.597646496934216e-05, + "loss": 3.8995, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.596807902183164e-05, + "loss": 3.8973, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.595969307432112e-05, + "loss": 3.8925, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.59513071268106e-05, + "loss": 3.8986, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.5942937558103813e-05, + "loss": 3.878, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.5934551610593293e-05, + "loss": 3.8915, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.5926165663082773e-05, + "loss": 3.8756, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.5917779715572247e-05, + "loss": 3.8906, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.590941014686546e-05, + "loss": 3.8849, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.590102419935494e-05, + "loss": 3.8955, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.589263825184442e-05, + "loss": 3.8889, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.5884252304333896e-05, + "loss": 3.8848, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.5875866356823375e-05, + "loss": 3.8954, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.586749678811659e-05, + "loss": 3.8895, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.5859110840606065e-05, + "loss": 3.8866, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585072489309555e-05, + "loss": 3.8837, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.584233894558503e-05, + "loss": 3.8699, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583396937687825e-05, + "loss": 3.8893, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582558342936772e-05, + "loss": 3.8823, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.58171974818572e-05, + "loss": 3.8866, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.580881153434668e-05, + "loss": 3.8706, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.5800441965639896e-05, + "loss": 3.8917, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.579205601812937e-05, + "loss": 3.8617, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.578367007061885e-05, + "loss": 3.8955, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.577528412310833e-05, + "loss": 3.8656, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.576691455440154e-05, + "loss": 3.8823, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.575852860689102e-05, + "loss": 3.8761, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.5750142659380505e-05, + "loss": 3.8707, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.5741756711869985e-05, + "loss": 3.8697, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.5733387143163194e-05, + "loss": 3.8814, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.5725001195652674e-05, + "loss": 3.859, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.5716615248142154e-05, + "loss": 3.8631, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.5708229300631634e-05, + "loss": 3.8827, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.569985973192484e-05, + "loss": 3.874, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.569147378441432e-05, + "loss": 3.8677, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.56830878369038e-05, + "loss": 3.8684, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.567470188939328e-05, + "loss": 3.8578, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.566633232068649e-05, + "loss": 3.8703, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.565794637317597e-05, + "loss": 3.8748, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.564956042566545e-05, + "loss": 3.8728, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.564117447815494e-05, + "loss": 3.8861, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.563280490944815e-05, + "loss": 3.8766, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.562441896193763e-05, + "loss": 3.879, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.561603301442711e-05, + "loss": 3.8599, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.560764706691659e-05, + "loss": 3.8695, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.55992774982098e-05, + "loss": 3.8734, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.5590891550699277e-05, + "loss": 3.8583, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.5582505603188757e-05, + "loss": 3.8708, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.5574119655678236e-05, + "loss": 3.8682, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.5565750086971446e-05, + "loss": 3.875, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.5557364139460926e-05, + "loss": 3.8692, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.5548978191950405e-05, + "loss": 3.8572, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.554059224443989e-05, + "loss": 3.8663, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.55322226757331e-05, + "loss": 3.8699, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.552383672822258e-05, + "loss": 3.8749, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.551545078071206e-05, + "loss": 3.868, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.550706483320154e-05, + "loss": 3.8689, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.549869526449475e-05, + "loss": 3.8775, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.549030931698423e-05, + "loss": 3.8546, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548192336947371e-05, + "loss": 3.8689, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.547353742196319e-05, + "loss": 3.8616, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.54651678532564e-05, + "loss": 3.8624, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.5456798284549615e-05, + "loss": 3.8781, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.5448412337039095e-05, + "loss": 3.8628, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.5440026389528575e-05, + "loss": 3.8512, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.5431640442018055e-05, + "loss": 3.86, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.5423254494507535e-05, + "loss": 3.8684, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.5414868546997015e-05, + "loss": 3.8691, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.5406482599486495e-05, + "loss": 3.8587, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.5398096651975975e-05, + "loss": 3.8532, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.5389727083269184e-05, + "loss": 3.8506, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.5381341135758664e-05, + "loss": 3.8702, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.5372955188248144e-05, + "loss": 3.8434, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.5364569240737624e-05, + "loss": 3.8541, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.535619967203083e-05, + "loss": 3.8654, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.534781372452031e-05, + "loss": 3.8614, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.53394277770098e-05, + "loss": 3.8504, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.533104182949928e-05, + "loss": 3.8615, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.532267226079249e-05, + "loss": 3.8542, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.531428631328197e-05, + "loss": 3.8577, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.530590036577145e-05, + "loss": 3.8578, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.529751441826093e-05, + "loss": 3.855, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.528914484955414e-05, + "loss": 3.868, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.528075890204362e-05, + "loss": 3.8586, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.527238933333683e-05, + "loss": 3.8606, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.5264003385826307e-05, + "loss": 3.8475, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.5255617438315787e-05, + "loss": 3.8535, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.5247231490805266e-05, + "loss": 3.8546, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.523884554329475e-05, + "loss": 3.8415, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.523045959578423e-05, + "loss": 3.8549, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.522207364827371e-05, + "loss": 3.8457, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.521368770076319e-05, + "loss": 3.8567, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.52053181320564e-05, + "loss": 3.8448, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.519693218454588e-05, + "loss": 3.8526, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.518854623703536e-05, + "loss": 3.8335, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.518016028952484e-05, + "loss": 3.8531, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.517179072081805e-05, + "loss": 3.8455, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.516340477330753e-05, + "loss": 3.8597, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515501882579701e-05, + "loss": 3.8528, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.514663287828649e-05, + "loss": 3.854, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513826330957971e-05, + "loss": 3.8368, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.512987736206919e-05, + "loss": 3.8526, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.512149141455867e-05, + "loss": 3.8527, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.511310546704815e-05, + "loss": 3.8607, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.5104735898341356e-05, + "loss": 3.8522, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.5096349950830836e-05, + "loss": 3.8523, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.5087964003320316e-05, + "loss": 3.852, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.5079578055809796e-05, + "loss": 3.8556, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.5071208487103005e-05, + "loss": 3.8402, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.5062822539592485e-05, + "loss": 3.8468, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.5054436592081965e-05, + "loss": 3.8458, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.5046050644571445e-05, + "loss": 3.8375, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.503768107586466e-05, + "loss": 3.8436, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.502929512835414e-05, + "loss": 3.8489, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.502090918084362e-05, + "loss": 3.842, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.5012523233333094e-05, + "loss": 3.841, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.5004137285822574e-05, + "loss": 3.85, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 3.9115359783172607, + "eval_runtime": 303.1157, + "eval_samples_per_second": 1258.896, + "eval_steps_per_second": 39.341, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.4995751338312054e-05, + "loss": 3.8273, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.4987365390801534e-05, + "loss": 3.8338, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.4978979443291013e-05, + "loss": 3.8459, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.4970593495780493e-05, + "loss": 3.8421, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.496220754826997e-05, + "loss": 3.8546, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.495382160075945e-05, + "loss": 3.8274, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.494543565324893e-05, + "loss": 3.8357, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.493704970573841e-05, + "loss": 3.8295, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.492868013703162e-05, + "loss": 3.8438, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.492031056832484e-05, + "loss": 3.844, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.491192462081432e-05, + "loss": 3.8317, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.49035386733038e-05, + "loss": 3.8473, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489516910459701e-05, + "loss": 3.8173, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.488678315708649e-05, + "loss": 3.8303, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487839720957597e-05, + "loss": 3.8319, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.487001126206545e-05, + "loss": 3.8245, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486162531455493e-05, + "loss": 3.8293, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485323936704441e-05, + "loss": 3.8309, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.484485341953389e-05, + "loss": 3.8268, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483646747202337e-05, + "loss": 3.8563, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482808152451285e-05, + "loss": 3.8315, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481971195580606e-05, + "loss": 3.8299, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481132600829554e-05, + "loss": 3.837, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480294006078502e-05, + "loss": 3.842, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.47945541132745e-05, + "loss": 3.824, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478616816576398e-05, + "loss": 3.8368, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.4777782218253456e-05, + "loss": 3.8273, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.4769396270742936e-05, + "loss": 3.8292, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476102670203615e-05, + "loss": 3.8188, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475264075452563e-05, + "loss": 3.8283, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.4744254807015105e-05, + "loss": 3.8429, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.4735868859504585e-05, + "loss": 3.8302, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.47274992907978e-05, + "loss": 3.8321, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.471911334328728e-05, + "loss": 3.8318, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.471072739577676e-05, + "loss": 3.8268, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470234144826624e-05, + "loss": 3.8307, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.4693971879559456e-05, + "loss": 3.8144, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468558593204893e-05, + "loss": 3.8247, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467719998453841e-05, + "loss": 3.8137, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466881403702789e-05, + "loss": 3.8207, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.4660460847124834e-05, + "loss": 3.8207, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.4652074899614314e-05, + "loss": 3.83, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.4643688952103794e-05, + "loss": 3.8241, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.4635303004593274e-05, + "loss": 3.8241, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.4626917057082754e-05, + "loss": 3.8289, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.4618531109572234e-05, + "loss": 3.8243, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.4610145162061714e-05, + "loss": 3.8243, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.4601759214551194e-05, + "loss": 3.8184, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.45933896458444e-05, + "loss": 3.8066, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.458500369833388e-05, + "loss": 3.8279, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457661775082336e-05, + "loss": 3.8152, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.456823180331284e-05, + "loss": 3.824, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.455986223460605e-05, + "loss": 3.8097, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.455147628709553e-05, + "loss": 3.8233, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.454309033958501e-05, + "loss": 3.801, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.453472077087822e-05, + "loss": 3.8322, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.452633482336771e-05, + "loss": 3.8035, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.451794887585719e-05, + "loss": 3.8142, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.450956292834667e-05, + "loss": 3.8186, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450117698083615e-05, + "loss": 3.8087, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.449279103332563e-05, + "loss": 3.81, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448440508581511e-05, + "loss": 3.8137, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.447601913830459e-05, + "loss": 3.8042, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.44676495695978e-05, + "loss": 3.7985, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445926362208728e-05, + "loss": 3.8184, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445087767457676e-05, + "loss": 3.8138, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.4442491727066237e-05, + "loss": 3.8032, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.4434122158359446e-05, + "loss": 3.8096, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.4425736210848926e-05, + "loss": 3.7957, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.4417350263338406e-05, + "loss": 3.8082, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440896431582789e-05, + "loss": 3.8147, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.44005947471211e-05, + "loss": 3.8083, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439220879961058e-05, + "loss": 3.8224, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438382285210006e-05, + "loss": 3.8143, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437543690458954e-05, + "loss": 3.8226, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436706733588275e-05, + "loss": 3.7995, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435868138837223e-05, + "loss": 3.809, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.435029544086171e-05, + "loss": 3.8116, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434190949335119e-05, + "loss": 3.7946, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.43335399246444e-05, + "loss": 3.8116, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.432515397713388e-05, + "loss": 3.8079, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431676802962336e-05, + "loss": 3.8121, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.430838208211284e-05, + "loss": 3.8101, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.4300012513406055e-05, + "loss": 3.7961, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.4291626565895535e-05, + "loss": 3.8085, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.4283240618385015e-05, + "loss": 3.8083, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.4274854670874495e-05, + "loss": 3.8137, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.4266485102167704e-05, + "loss": 3.8092, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.4258099154657184e-05, + "loss": 3.8114, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.424972958595039e-05, + "loss": 3.8141, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.424134363843987e-05, + "loss": 3.7967, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.423295769092935e-05, + "loss": 3.8085, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422457174341883e-05, + "loss": 3.7989, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.421618579590831e-05, + "loss": 3.8098, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420781622720153e-05, + "loss": 3.8192, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419943027969101e-05, + "loss": 3.8021, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.419104433218049e-05, + "loss": 3.7965, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.418265838466997e-05, + "loss": 3.8009, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.417427243715945e-05, + "loss": 3.8072, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.416588648964893e-05, + "loss": 3.8159, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415750054213841e-05, + "loss": 3.7986, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.414911459462788e-05, + "loss": 3.7975, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.41407450259211e-05, + "loss": 3.7941, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413235907841058e-05, + "loss": 3.8109, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412397313090006e-05, + "loss": 3.7857, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411558718338953e-05, + "loss": 3.7975, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.4107217614682747e-05, + "loss": 3.8066, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409883166717223e-05, + "loss": 3.8016, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409046209846544e-05, + "loss": 3.7934, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408207615095492e-05, + "loss": 3.8068, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.40736902034444e-05, + "loss": 3.7967, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406530425593388e-05, + "loss": 3.7968, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.4056918308423355e-05, + "loss": 3.8037, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.4048532360912835e-05, + "loss": 3.8015, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.4040146413402315e-05, + "loss": 3.8083, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.4031760465891795e-05, + "loss": 3.8036, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.4023390897185004e-05, + "loss": 3.8009, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.4015004949674484e-05, + "loss": 3.7889, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400661900216397e-05, + "loss": 3.7986, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399823305465345e-05, + "loss": 3.795, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398986348594666e-05, + "loss": 3.7832, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.3981493917239876e-05, + "loss": 3.8007, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.3973107969729356e-05, + "loss": 3.7867, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396472202221883e-05, + "loss": 3.8006, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.395633607470831e-05, + "loss": 3.7926, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394795012719779e-05, + "loss": 3.7961, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393956417968727e-05, + "loss": 3.7787, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.393117823217675e-05, + "loss": 3.7942, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392279228466623e-05, + "loss": 3.7949, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.391442271595944e-05, + "loss": 3.7978, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.3906036768448925e-05, + "loss": 3.7974, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.3897650820938405e-05, + "loss": 3.801, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.3889264873427885e-05, + "loss": 3.7803, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.3880895304721094e-05, + "loss": 3.7988, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.3872509357210574e-05, + "loss": 3.8019, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.3864123409700054e-05, + "loss": 3.8016, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.3855737462189534e-05, + "loss": 3.7997, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.384736789348274e-05, + "loss": 3.8024, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.383898194597222e-05, + "loss": 3.7931, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.383061237726543e-05, + "loss": 3.8006, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.382222642975491e-05, + "loss": 3.7824, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.381384048224439e-05, + "loss": 3.7945, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.380545453473388e-05, + "loss": 3.7871, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379706858722336e-05, + "loss": 3.7878, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378869901851657e-05, + "loss": 3.7909, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.378031307100605e-05, + "loss": 3.7885, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.377192712349553e-05, + "loss": 3.7935, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.376354117598501e-05, + "loss": 3.7825, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.3755171607278216e-05, + "loss": 3.7981, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.8857719898223877, + "eval_runtime": 310.6901, + "eval_samples_per_second": 1228.204, + "eval_steps_per_second": 38.382, + "step": 381600 + }, + { + "epoch": 0.0, + "learning_rate": 4.3746785659767696e-05, + "loss": 3.7791, + "step": 381952 + }, + { + "epoch": 0.0, + "learning_rate": 4.3738399712257176e-05, + "loss": 3.7797, + "step": 382464 + }, + { + "epoch": 0.0, + "learning_rate": 4.3730013764746656e-05, + "loss": 3.7908, + "step": 382976 + }, + { + "epoch": 0.0, + "learning_rate": 4.3721627817236136e-05, + "loss": 3.793, + "step": 383488 + }, + { + "epoch": 0.0, + "learning_rate": 4.3713241869725616e-05, + "loss": 3.7944, + "step": 384000 + }, + { + "epoch": 0.0, + "learning_rate": 4.3704855922215096e-05, + "loss": 3.7801, + "step": 384512 + }, + { + "epoch": 0.0, + "learning_rate": 4.3696469974704576e-05, + "loss": 3.7788, + "step": 385024 + }, + { + "epoch": 0.0, + "learning_rate": 4.368808402719406e-05, + "loss": 3.7795, + "step": 385536 + }, + { + "epoch": 0.0, + "learning_rate": 4.367971445848727e-05, + "loss": 3.7867, + "step": 386048 + }, + { + "epoch": 0.0, + "learning_rate": 4.367134488978048e-05, + "loss": 3.794, + "step": 386560 + }, + { + "epoch": 0.0, + "learning_rate": 4.366295894226996e-05, + "loss": 3.779, + "step": 387072 + }, + { + "epoch": 0.0, + "learning_rate": 4.365457299475944e-05, + "loss": 3.7926, + "step": 387584 + }, + { + "epoch": 0.0, + "learning_rate": 4.364618704724892e-05, + "loss": 3.7722, + "step": 388096 + }, + { + "epoch": 0.0, + "learning_rate": 4.36378010997384e-05, + "loss": 3.7766, + "step": 388608 + }, + { + "epoch": 0.0, + "learning_rate": 4.362941515222788e-05, + "loss": 3.7809, + "step": 389120 + }, + { + "epoch": 0.0, + "learning_rate": 4.362102920471736e-05, + "loss": 3.7723, + "step": 389632 + }, + { + "epoch": 0.0, + "learning_rate": 4.361265963601057e-05, + "loss": 3.7748, + "step": 390144 + }, + { + "epoch": 0.0, + "learning_rate": 4.360427368850005e-05, + "loss": 3.7798, + "step": 390656 + }, + { + "epoch": 0.0, + "learning_rate": 4.359588774098953e-05, + "loss": 3.7728, + "step": 391168 + }, + { + "epoch": 0.0, + "learning_rate": 4.358750179347901e-05, + "loss": 3.8014, + "step": 391680 + }, + { + "epoch": 0.0, + "learning_rate": 4.357911584596849e-05, + "loss": 3.7848, + "step": 392192 + }, + { + "epoch": 0.0, + "learning_rate": 4.3570746277261706e-05, + "loss": 3.7811, + "step": 392704 + }, + { + "epoch": 0.0, + "learning_rate": 4.3562360329751186e-05, + "loss": 3.7829, + "step": 393216 + }, + { + "epoch": 0.0, + "learning_rate": 4.3553974382240665e-05, + "loss": 3.7908, + "step": 393728 + }, + { + "epoch": 0.0, + "learning_rate": 4.354558843473014e-05, + "loss": 3.7739, + "step": 394240 + }, + { + "epoch": 0.0, + "learning_rate": 4.353720248721962e-05, + "loss": 3.785, + "step": 394752 + }, + { + "epoch": 0.0, + "learning_rate": 4.3528832918512834e-05, + "loss": 3.7804, + "step": 395264 + }, + { + "epoch": 0.0, + "learning_rate": 4.3520446971002314e-05, + "loss": 3.7736, + "step": 395776 + }, + { + "epoch": 0.0, + "learning_rate": 4.351206102349179e-05, + "loss": 3.7639, + "step": 396288 + }, + { + "epoch": 0.0, + "learning_rate": 4.350367507598127e-05, + "loss": 3.7788, + "step": 396800 + }, + { + "epoch": 0.01, + "learning_rate": 4.349528912847075e-05, + "loss": 3.7917, + "step": 397312 + }, + { + "epoch": 0.01, + "learning_rate": 4.3486903180960234e-05, + "loss": 3.7792, + "step": 397824 + }, + { + "epoch": 0.01, + "learning_rate": 4.3478517233449714e-05, + "loss": 3.7861, + "step": 398336 + }, + { + "epoch": 0.01, + "learning_rate": 4.347014766474292e-05, + "loss": 3.7804, + "step": 398848 + }, + { + "epoch": 0.01, + "learning_rate": 4.34617617172324e-05, + "loss": 3.7747, + "step": 399360 + }, + { + "epoch": 0.01, + "learning_rate": 4.345337576972188e-05, + "loss": 3.7801, + "step": 399872 + }, + { + "epoch": 0.01, + "learning_rate": 4.344498982221136e-05, + "loss": 3.7706, + "step": 400384 + }, + { + "epoch": 0.01, + "learning_rate": 4.343660387470084e-05, + "loss": 3.7703, + "step": 400896 + }, + { + "epoch": 0.01, + "learning_rate": 4.342823430599405e-05, + "loss": 3.7664, + "step": 401408 + }, + { + "epoch": 0.01, + "learning_rate": 4.341984835848353e-05, + "loss": 3.7718, + "step": 401920 + }, + { + "epoch": 0.01, + "learning_rate": 4.341146241097301e-05, + "loss": 3.7717, + "step": 402432 + }, + { + "epoch": 0.01, + "learning_rate": 4.340307646346249e-05, + "loss": 3.7789, + "step": 402944 + }, + { + "epoch": 0.01, + "learning_rate": 4.339469051595197e-05, + "loss": 3.772, + "step": 403456 + }, + { + "epoch": 0.01, + "learning_rate": 4.338630456844145e-05, + "loss": 3.7763, + "step": 403968 + }, + { + "epoch": 0.01, + "learning_rate": 4.337791862093093e-05, + "loss": 3.7782, + "step": 404480 + }, + { + "epoch": 0.01, + "learning_rate": 4.336954905222415e-05, + "loss": 3.7754, + "step": 404992 + }, + { + "epoch": 0.01, + "learning_rate": 4.336116310471363e-05, + "loss": 3.7766, + "step": 405504 + }, + { + "epoch": 0.01, + "learning_rate": 4.335277715720311e-05, + "loss": 3.7691, + "step": 406016 + }, + { + "epoch": 0.01, + "learning_rate": 4.334439120969259e-05, + "loss": 3.7552, + "step": 406528 + }, + { + "epoch": 0.01, + "learning_rate": 4.33360216409858e-05, + "loss": 3.7791, + "step": 407040 + }, + { + "epoch": 0.01, + "learning_rate": 4.332763569347528e-05, + "loss": 3.7663, + "step": 407552 + }, + { + "epoch": 0.01, + "learning_rate": 4.331924974596476e-05, + "loss": 3.775, + "step": 408064 + }, + { + "epoch": 0.01, + "learning_rate": 4.3310880177257966e-05, + "loss": 3.7631, + "step": 408576 + }, + { + "epoch": 0.01, + "learning_rate": 4.3302494229747446e-05, + "loss": 3.7719, + "step": 409088 + }, + { + "epoch": 0.01, + "learning_rate": 4.3294108282236926e-05, + "loss": 3.7519, + "step": 409600 + }, + { + "epoch": 0.01, + "learning_rate": 4.3285722334726406e-05, + "loss": 3.779, + "step": 410112 + }, + { + "epoch": 0.01, + "learning_rate": 4.3277336387215886e-05, + "loss": 3.757, + "step": 410624 + }, + { + "epoch": 0.01, + "learning_rate": 4.326895043970537e-05, + "loss": 3.767, + "step": 411136 + }, + { + "epoch": 0.01, + "learning_rate": 4.326056449219485e-05, + "loss": 3.7729, + "step": 411648 + }, + { + "epoch": 0.01, + "learning_rate": 4.3252178544684325e-05, + "loss": 3.7574, + "step": 412160 + }, + { + "epoch": 0.01, + "learning_rate": 4.324380897597754e-05, + "loss": 3.7606, + "step": 412672 + }, + { + "epoch": 0.01, + "learning_rate": 4.323542302846702e-05, + "loss": 3.7713, + "step": 413184 + }, + { + "epoch": 0.01, + "learning_rate": 4.322705345976023e-05, + "loss": 3.7531, + "step": 413696 + }, + { + "epoch": 0.01, + "learning_rate": 4.321866751224971e-05, + "loss": 3.7494, + "step": 414208 + }, + { + "epoch": 0.01, + "learning_rate": 4.321028156473919e-05, + "loss": 3.7694, + "step": 414720 + }, + { + "epoch": 0.01, + "learning_rate": 4.320189561722867e-05, + "loss": 3.7679, + "step": 415232 + }, + { + "epoch": 0.01, + "learning_rate": 4.319350966971815e-05, + "loss": 3.7539, + "step": 415744 + }, + { + "epoch": 0.01, + "learning_rate": 4.3185123722207623e-05, + "loss": 3.7646, + "step": 416256 + }, + { + "epoch": 0.01, + "learning_rate": 4.317673777469711e-05, + "loss": 3.7455, + "step": 416768 + }, + { + "epoch": 0.01, + "learning_rate": 4.316835182718659e-05, + "loss": 3.7576, + "step": 417280 + }, + { + "epoch": 0.01, + "learning_rate": 4.31599822584798e-05, + "loss": 3.766, + "step": 417792 + }, + { + "epoch": 0.01, + "learning_rate": 4.315159631096928e-05, + "loss": 3.7632, + "step": 418304 + }, + { + "epoch": 0.01, + "learning_rate": 4.314321036345876e-05, + "loss": 3.7715, + "step": 418816 + }, + { + "epoch": 0.01, + "learning_rate": 4.313482441594824e-05, + "loss": 3.7673, + "step": 419328 + }, + { + "epoch": 0.01, + "learning_rate": 4.312645484724145e-05, + "loss": 3.7773, + "step": 419840 + }, + { + "epoch": 0.01, + "learning_rate": 4.311806889973093e-05, + "loss": 3.7507, + "step": 420352 + }, + { + "epoch": 0.01, + "learning_rate": 4.310968295222041e-05, + "loss": 3.7648, + "step": 420864 + }, + { + "epoch": 0.01, + "learning_rate": 4.310129700470989e-05, + "loss": 3.7679, + "step": 421376 + }, + { + "epoch": 0.01, + "learning_rate": 4.309291105719937e-05, + "loss": 3.7447, + "step": 421888 + }, + { + "epoch": 0.01, + "learning_rate": 4.308452510968885e-05, + "loss": 3.7656, + "step": 422400 + }, + { + "epoch": 0.01, + "learning_rate": 4.307613916217833e-05, + "loss": 3.7631, + "step": 422912 + }, + { + "epoch": 0.01, + "learning_rate": 4.3067769593471544e-05, + "loss": 3.765, + "step": 423424 + }, + { + "epoch": 0.01, + "learning_rate": 4.3059383645961024e-05, + "loss": 3.7641, + "step": 423936 + }, + { + "epoch": 0.01, + "learning_rate": 4.3050997698450504e-05, + "loss": 3.7533, + "step": 424448 + }, + { + "epoch": 0.01, + "learning_rate": 4.3042611750939984e-05, + "loss": 3.756, + "step": 424960 + }, + { + "epoch": 0.01, + "learning_rate": 4.3034225803429464e-05, + "loss": 3.7608, + "step": 425472 + }, + { + "epoch": 0.01, + "learning_rate": 4.3025839855918944e-05, + "loss": 3.7703, + "step": 425984 + }, + { + "epoch": 0.01, + "learning_rate": 4.3017453908408424e-05, + "loss": 3.7605, + "step": 426496 + }, + { + "epoch": 0.01, + "learning_rate": 4.3009067960897903e-05, + "loss": 3.7667, + "step": 427008 + }, + { + "epoch": 0.02, + "learning_rate": 4.300069839219111e-05, + "loss": 3.7712, + "step": 427520 + }, + { + "epoch": 0.02, + "learning_rate": 4.299231244468059e-05, + "loss": 3.7519, + "step": 428032 + }, + { + "epoch": 0.02, + "learning_rate": 4.298392649717007e-05, + "loss": 3.7618, + "step": 428544 + }, + { + "epoch": 0.02, + "learning_rate": 4.297554054965955e-05, + "loss": 3.7505, + "step": 429056 + }, + { + "epoch": 0.02, + "learning_rate": 4.296715460214903e-05, + "loss": 3.7629, + "step": 429568 + }, + { + "epoch": 0.02, + "learning_rate": 4.295878503344224e-05, + "loss": 3.7776, + "step": 430080 + }, + { + "epoch": 0.02, + "learning_rate": 4.295039908593173e-05, + "loss": 3.7519, + "step": 430592 + }, + { + "epoch": 0.02, + "learning_rate": 4.294201313842121e-05, + "loss": 3.7551, + "step": 431104 + }, + { + "epoch": 0.02, + "learning_rate": 4.293362719091069e-05, + "loss": 3.7515, + "step": 431616 + }, + { + "epoch": 0.02, + "learning_rate": 4.292524124340016e-05, + "loss": 3.7628, + "step": 432128 + }, + { + "epoch": 0.02, + "learning_rate": 4.291685529588964e-05, + "loss": 3.7719, + "step": 432640 + }, + { + "epoch": 0.02, + "learning_rate": 4.290848572718286e-05, + "loss": 3.7536, + "step": 433152 + }, + { + "epoch": 0.02, + "learning_rate": 4.290009977967234e-05, + "loss": 3.7537, + "step": 433664 + }, + { + "epoch": 0.02, + "learning_rate": 4.289171383216181e-05, + "loss": 3.7447, + "step": 434176 + }, + { + "epoch": 0.02, + "learning_rate": 4.288332788465129e-05, + "loss": 3.767, + "step": 434688 + }, + { + "epoch": 0.02, + "learning_rate": 4.287494193714077e-05, + "loss": 3.7374, + "step": 435200 + }, + { + "epoch": 0.02, + "learning_rate": 4.286657236843398e-05, + "loss": 3.7549, + "step": 435712 + }, + { + "epoch": 0.02, + "learning_rate": 4.2858186420923466e-05, + "loss": 3.7576, + "step": 436224 + }, + { + "epoch": 0.02, + "learning_rate": 4.2849800473412946e-05, + "loss": 3.7612, + "step": 436736 + }, + { + "epoch": 0.02, + "learning_rate": 4.2841414525902426e-05, + "loss": 3.7495, + "step": 437248 + }, + { + "epoch": 0.02, + "learning_rate": 4.2833028578391906e-05, + "loss": 3.7584, + "step": 437760 + }, + { + "epoch": 0.02, + "learning_rate": 4.2824642630881386e-05, + "loss": 3.7541, + "step": 438272 + }, + { + "epoch": 0.02, + "learning_rate": 4.2816256683370866e-05, + "loss": 3.7512, + "step": 438784 + }, + { + "epoch": 0.02, + "learning_rate": 4.2807870735860346e-05, + "loss": 3.7587, + "step": 439296 + }, + { + "epoch": 0.02, + "learning_rate": 4.2799517545957284e-05, + "loss": 3.7551, + "step": 439808 + }, + { + "epoch": 0.02, + "learning_rate": 4.2791131598446764e-05, + "loss": 3.7609, + "step": 440320 + }, + { + "epoch": 0.02, + "learning_rate": 4.2782745650936244e-05, + "loss": 3.7621, + "step": 440832 + }, + { + "epoch": 0.02, + "learning_rate": 4.2774359703425724e-05, + "loss": 3.7536, + "step": 441344 + }, + { + "epoch": 0.02, + "learning_rate": 4.2765973755915204e-05, + "loss": 3.7445, + "step": 441856 + }, + { + "epoch": 0.02, + "learning_rate": 4.2757587808404684e-05, + "loss": 3.7528, + "step": 442368 + }, + { + "epoch": 0.02, + "learning_rate": 4.2749201860894164e-05, + "loss": 3.7541, + "step": 442880 + }, + { + "epoch": 0.02, + "learning_rate": 4.274081591338365e-05, + "loss": 3.7417, + "step": 443392 + }, + { + "epoch": 0.02, + "learning_rate": 4.273246272348059e-05, + "loss": 3.7527, + "step": 443904 + }, + { + "epoch": 0.02, + "learning_rate": 4.272407677597007e-05, + "loss": 3.7413, + "step": 444416 + }, + { + "epoch": 0.02, + "learning_rate": 4.271569082845955e-05, + "loss": 3.7557, + "step": 444928 + }, + { + "epoch": 0.02, + "learning_rate": 4.270730488094903e-05, + "loss": 3.7492, + "step": 445440 + }, + { + "epoch": 0.02, + "learning_rate": 4.269893531224224e-05, + "loss": 3.7501, + "step": 445952 + }, + { + "epoch": 0.02, + "learning_rate": 4.269054936473172e-05, + "loss": 3.7416, + "step": 446464 + }, + { + "epoch": 0.02, + "learning_rate": 4.26821634172212e-05, + "loss": 3.7458, + "step": 446976 + }, + { + "epoch": 0.02, + "learning_rate": 4.267377746971068e-05, + "loss": 3.7522, + "step": 447488 + }, + { + "epoch": 0.02, + "learning_rate": 4.266539152220016e-05, + "loss": 3.7575, + "step": 448000 + }, + { + "epoch": 0.02, + "learning_rate": 4.265700557468964e-05, + "loss": 3.7474, + "step": 448512 + }, + { + "epoch": 0.02, + "learning_rate": 4.264863600598285e-05, + "loss": 3.7557, + "step": 449024 + }, + { + "epoch": 0.02, + "learning_rate": 4.264025005847233e-05, + "loss": 3.7412, + "step": 449536 + }, + { + "epoch": 0.02, + "learning_rate": 4.263186411096181e-05, + "loss": 3.7544, + "step": 450048 + }, + { + "epoch": 0.02, + "learning_rate": 4.262347816345129e-05, + "loss": 3.7583, + "step": 450560 + }, + { + "epoch": 0.02, + "learning_rate": 4.261509221594077e-05, + "loss": 3.7573, + "step": 451072 + }, + { + "epoch": 0.02, + "learning_rate": 4.260672264723398e-05, + "loss": 3.7554, + "step": 451584 + }, + { + "epoch": 0.02, + "learning_rate": 4.259833669972346e-05, + "loss": 3.7618, + "step": 452096 + }, + { + "epoch": 0.02, + "learning_rate": 4.258995075221294e-05, + "loss": 3.7475, + "step": 452608 + }, + { + "epoch": 0.02, + "learning_rate": 4.258156480470242e-05, + "loss": 3.7595, + "step": 453120 + }, + { + "epoch": 0.02, + "learning_rate": 4.25731788571919e-05, + "loss": 3.7389, + "step": 453632 + }, + { + "epoch": 0.02, + "learning_rate": 4.256480928848511e-05, + "loss": 3.7504, + "step": 454144 + }, + { + "epoch": 0.02, + "learning_rate": 4.255642334097459e-05, + "loss": 3.7434, + "step": 454656 + }, + { + "epoch": 0.02, + "learning_rate": 4.254803739346407e-05, + "loss": 3.7441, + "step": 455168 + }, + { + "epoch": 0.02, + "learning_rate": 4.253965144595356e-05, + "loss": 3.7479, + "step": 455680 + }, + { + "epoch": 0.02, + "learning_rate": 4.253128187724677e-05, + "loss": 3.7424, + "step": 456192 + }, + { + "epoch": 0.02, + "learning_rate": 4.252289592973625e-05, + "loss": 3.7569, + "step": 456704 + }, + { + "epoch": 0.02, + "learning_rate": 4.251450998222573e-05, + "loss": 3.7332, + "step": 457216 + }, + { + "epoch": 0.02, + "learning_rate": 4.250612403471521e-05, + "loss": 3.7602, + "step": 457728 + }, + { + "epoch": 0.03, + "eval_loss": 3.8690614700317383, + "eval_runtime": 307.6763, + "eval_samples_per_second": 1240.235, + "eval_steps_per_second": 38.758, + "step": 457920 + }, + { + "epoch": 1.0, + "learning_rate": 4.249773808720469e-05, + "loss": 3.7374, + "step": 458240 + }, + { + "epoch": 1.0, + "learning_rate": 4.2489368518497896e-05, + "loss": 3.7366, + "step": 458752 + }, + { + "epoch": 1.0, + "learning_rate": 4.2480982570987376e-05, + "loss": 3.7475, + "step": 459264 + }, + { + "epoch": 1.0, + "learning_rate": 4.2472596623476856e-05, + "loss": 3.7508, + "step": 459776 + }, + { + "epoch": 1.0, + "learning_rate": 4.2464210675966336e-05, + "loss": 3.7514, + "step": 460288 + }, + { + "epoch": 1.0, + "learning_rate": 4.2455824728455816e-05, + "loss": 3.7368, + "step": 460800 + }, + { + "epoch": 1.0, + "learning_rate": 4.2447438780945296e-05, + "loss": 3.7301, + "step": 461312 + }, + { + "epoch": 1.0, + "learning_rate": 4.243906921223851e-05, + "loss": 3.7412, + "step": 461824 + }, + { + "epoch": 1.0, + "learning_rate": 4.243068326472799e-05, + "loss": 3.7443, + "step": 462336 + }, + { + "epoch": 1.0, + "learning_rate": 4.242229731721747e-05, + "loss": 3.7516, + "step": 462848 + }, + { + "epoch": 1.0, + "learning_rate": 4.2413911369706945e-05, + "loss": 3.7408, + "step": 463360 + }, + { + "epoch": 1.0, + "learning_rate": 4.240554180100016e-05, + "loss": 3.7459, + "step": 463872 + }, + { + "epoch": 1.0, + "learning_rate": 4.239717223229337e-05, + "loss": 3.7322, + "step": 464384 + }, + { + "epoch": 1.0, + "learning_rate": 4.238878628478285e-05, + "loss": 3.7328, + "step": 464896 + }, + { + "epoch": 1.0, + "learning_rate": 4.238040033727233e-05, + "loss": 3.7396, + "step": 465408 + }, + { + "epoch": 1.0, + "learning_rate": 4.237201438976181e-05, + "loss": 3.7304, + "step": 465920 + }, + { + "epoch": 1.0, + "learning_rate": 4.236362844225129e-05, + "loss": 3.7355, + "step": 466432 + }, + { + "epoch": 1.0, + "learning_rate": 4.235524249474076e-05, + "loss": 3.7398, + "step": 466944 + }, + { + "epoch": 1.0, + "learning_rate": 4.234685654723025e-05, + "loss": 3.7309, + "step": 467456 + }, + { + "epoch": 1.0, + "learning_rate": 4.233847059971973e-05, + "loss": 3.7577, + "step": 467968 + }, + { + "epoch": 1.0, + "learning_rate": 4.2330101031012945e-05, + "loss": 3.7451, + "step": 468480 + }, + { + "epoch": 1.0, + "learning_rate": 4.232171508350242e-05, + "loss": 3.737, + "step": 468992 + }, + { + "epoch": 1.0, + "learning_rate": 4.23133291359919e-05, + "loss": 3.7441, + "step": 469504 + }, + { + "epoch": 1.0, + "learning_rate": 4.230494318848138e-05, + "loss": 3.7504, + "step": 470016 + }, + { + "epoch": 1.0, + "learning_rate": 4.229657361977459e-05, + "loss": 3.7292, + "step": 470528 + }, + { + "epoch": 1.0, + "learning_rate": 4.228818767226407e-05, + "loss": 3.7452, + "step": 471040 + }, + { + "epoch": 1.0, + "learning_rate": 4.227980172475355e-05, + "loss": 3.7354, + "step": 471552 + }, + { + "epoch": 1.0, + "learning_rate": 4.227141577724303e-05, + "loss": 3.7354, + "step": 472064 + }, + { + "epoch": 1.0, + "learning_rate": 4.2263046208536236e-05, + "loss": 3.7267, + "step": 472576 + }, + { + "epoch": 1.0, + "learning_rate": 4.2254660261025716e-05, + "loss": 3.7364, + "step": 473088 + }, + { + "epoch": 1.01, + "learning_rate": 4.2246274313515196e-05, + "loss": 3.7487, + "step": 473600 + }, + { + "epoch": 1.01, + "learning_rate": 4.223788836600468e-05, + "loss": 3.7391, + "step": 474112 + }, + { + "epoch": 1.01, + "learning_rate": 4.222950241849416e-05, + "loss": 3.7461, + "step": 474624 + }, + { + "epoch": 1.01, + "learning_rate": 4.222113284978737e-05, + "loss": 3.7414, + "step": 475136 + }, + { + "epoch": 1.01, + "learning_rate": 4.221274690227685e-05, + "loss": 3.7313, + "step": 475648 + }, + { + "epoch": 1.01, + "learning_rate": 4.220436095476633e-05, + "loss": 3.7386, + "step": 476160 + }, + { + "epoch": 1.01, + "learning_rate": 4.219597500725581e-05, + "loss": 3.7319, + "step": 476672 + }, + { + "epoch": 1.01, + "learning_rate": 4.218760543854902e-05, + "loss": 3.7281, + "step": 477184 + }, + { + "epoch": 1.01, + "learning_rate": 4.21792194910385e-05, + "loss": 3.725, + "step": 477696 + }, + { + "epoch": 1.01, + "learning_rate": 4.217083354352798e-05, + "loss": 3.7291, + "step": 478208 + }, + { + "epoch": 1.01, + "learning_rate": 4.216244759601746e-05, + "loss": 3.7318, + "step": 478720 + }, + { + "epoch": 1.01, + "learning_rate": 4.215406164850694e-05, + "loss": 3.7388, + "step": 479232 + }, + { + "epoch": 1.01, + "learning_rate": 4.214569207980015e-05, + "loss": 3.7325, + "step": 479744 + }, + { + "epoch": 1.01, + "learning_rate": 4.2137306132289637e-05, + "loss": 3.7339, + "step": 480256 + }, + { + "epoch": 1.01, + "learning_rate": 4.2128920184779116e-05, + "loss": 3.7403, + "step": 480768 + }, + { + "epoch": 1.01, + "learning_rate": 4.2120534237268596e-05, + "loss": 3.7336, + "step": 481280 + }, + { + "epoch": 1.01, + "learning_rate": 4.2112164668561806e-05, + "loss": 3.739, + "step": 481792 + }, + { + "epoch": 1.01, + "learning_rate": 4.2103778721051285e-05, + "loss": 3.7294, + "step": 482304 + }, + { + "epoch": 1.01, + "learning_rate": 4.2095392773540765e-05, + "loss": 3.7107, + "step": 482816 + }, + { + "epoch": 1.01, + "learning_rate": 4.2087006826030245e-05, + "loss": 3.7431, + "step": 483328 + }, + { + "epoch": 1.01, + "learning_rate": 4.2078620878519725e-05, + "loss": 3.7267, + "step": 483840 + }, + { + "epoch": 1.01, + "learning_rate": 4.2070251309812934e-05, + "loss": 3.7356, + "step": 484352 + }, + { + "epoch": 1.01, + "learning_rate": 4.2061865362302414e-05, + "loss": 3.7275, + "step": 484864 + }, + { + "epoch": 1.01, + "learning_rate": 4.2053479414791894e-05, + "loss": 3.7278, + "step": 485376 + }, + { + "epoch": 1.01, + "learning_rate": 4.2045093467281374e-05, + "loss": 3.7183, + "step": 485888 + }, + { + "epoch": 1.01, + "learning_rate": 4.203672389857459e-05, + "loss": 3.7367, + "step": 486400 + }, + { + "epoch": 1.01, + "learning_rate": 4.202833795106407e-05, + "loss": 3.7202, + "step": 486912 + }, + { + "epoch": 1.01, + "learning_rate": 4.201995200355355e-05, + "loss": 3.7261, + "step": 487424 + }, + { + "epoch": 1.01, + "learning_rate": 4.201156605604303e-05, + "loss": 3.7367, + "step": 487936 + }, + { + "epoch": 1.01, + "learning_rate": 4.200319648733624e-05, + "loss": 3.7169, + "step": 488448 + }, + { + "epoch": 1.01, + "learning_rate": 4.199481053982572e-05, + "loss": 3.7191, + "step": 488960 + }, + { + "epoch": 1.01, + "learning_rate": 4.19864245923152e-05, + "loss": 3.738, + "step": 489472 + }, + { + "epoch": 1.01, + "learning_rate": 4.197803864480468e-05, + "loss": 3.7104, + "step": 489984 + }, + { + "epoch": 1.01, + "learning_rate": 4.196966907609789e-05, + "loss": 3.7109, + "step": 490496 + }, + { + "epoch": 1.01, + "learning_rate": 4.196128312858737e-05, + "loss": 3.7291, + "step": 491008 + }, + { + "epoch": 1.01, + "learning_rate": 4.195289718107685e-05, + "loss": 3.7275, + "step": 491520 + }, + { + "epoch": 1.01, + "learning_rate": 4.194451123356633e-05, + "loss": 3.7167, + "step": 492032 + }, + { + "epoch": 1.01, + "learning_rate": 4.193612528605581e-05, + "loss": 3.7257, + "step": 492544 + }, + { + "epoch": 1.01, + "learning_rate": 4.1927755717349024e-05, + "loss": 3.7083, + "step": 493056 + }, + { + "epoch": 1.01, + "learning_rate": 4.1919369769838504e-05, + "loss": 3.7166, + "step": 493568 + }, + { + "epoch": 1.01, + "learning_rate": 4.1910983822327984e-05, + "loss": 3.73, + "step": 494080 + }, + { + "epoch": 1.01, + "learning_rate": 4.190261425362119e-05, + "loss": 3.7223, + "step": 494592 + }, + { + "epoch": 1.01, + "learning_rate": 4.189422830611067e-05, + "loss": 3.7327, + "step": 495104 + }, + { + "epoch": 1.01, + "learning_rate": 4.188584235860015e-05, + "loss": 3.7308, + "step": 495616 + }, + { + "epoch": 1.01, + "learning_rate": 4.187745641108963e-05, + "loss": 3.7378, + "step": 496128 + }, + { + "epoch": 1.01, + "learning_rate": 4.186907046357911e-05, + "loss": 3.714, + "step": 496640 + }, + { + "epoch": 1.01, + "learning_rate": 4.186070089487232e-05, + "loss": 3.7261, + "step": 497152 + }, + { + "epoch": 1.01, + "learning_rate": 4.18523149473618e-05, + "loss": 3.7282, + "step": 497664 + }, + { + "epoch": 1.01, + "learning_rate": 4.184392899985128e-05, + "loss": 3.7087, + "step": 498176 + }, + { + "epoch": 1.01, + "learning_rate": 4.183554305234076e-05, + "loss": 3.7256, + "step": 498688 + }, + { + "epoch": 1.01, + "learning_rate": 4.182715710483024e-05, + "loss": 3.7254, + "step": 499200 + }, + { + "epoch": 1.01, + "learning_rate": 4.181878753612346e-05, + "loss": 3.7285, + "step": 499712 + }, + { + "epoch": 1.01, + "learning_rate": 4.181040158861294e-05, + "loss": 3.7235, + "step": 500224 + }, + { + "epoch": 1.01, + "learning_rate": 4.180201564110242e-05, + "loss": 3.7185, + "step": 500736 + }, + { + "epoch": 1.01, + "learning_rate": 4.17936296935919e-05, + "loss": 3.7161, + "step": 501248 + }, + { + "epoch": 1.01, + "learning_rate": 4.1785260124885106e-05, + "loss": 3.7252, + "step": 501760 + }, + { + "epoch": 1.01, + "learning_rate": 4.1776874177374586e-05, + "loss": 3.727, + "step": 502272 + }, + { + "epoch": 1.01, + "learning_rate": 4.1768488229864066e-05, + "loss": 3.724, + "step": 502784 + }, + { + "epoch": 1.01, + "learning_rate": 4.1760102282353546e-05, + "loss": 3.7277, + "step": 503296 + }, + { + "epoch": 1.02, + "learning_rate": 4.1751732713646755e-05, + "loss": 3.7308, + "step": 503808 + }, + { + "epoch": 1.02, + "learning_rate": 4.1743346766136235e-05, + "loss": 3.7169, + "step": 504320 + }, + { + "epoch": 1.02, + "learning_rate": 4.1734960818625715e-05, + "loss": 3.723, + "step": 504832 + }, + { + "epoch": 1.02, + "learning_rate": 4.1726574871115195e-05, + "loss": 3.7115, + "step": 505344 + }, + { + "epoch": 1.02, + "learning_rate": 4.1718188923604675e-05, + "loss": 3.7308, + "step": 505856 + }, + { + "epoch": 1.02, + "learning_rate": 4.170981935489789e-05, + "loss": 3.7347, + "step": 506368 + }, + { + "epoch": 1.02, + "learning_rate": 4.170143340738737e-05, + "loss": 3.7184, + "step": 506880 + }, + { + "epoch": 1.02, + "learning_rate": 4.1693047459876844e-05, + "loss": 3.715, + "step": 507392 + }, + { + "epoch": 1.02, + "learning_rate": 4.1684661512366324e-05, + "loss": 3.7106, + "step": 507904 + }, + { + "epoch": 1.02, + "learning_rate": 4.167629194365954e-05, + "loss": 3.7254, + "step": 508416 + }, + { + "epoch": 1.02, + "learning_rate": 4.166790599614902e-05, + "loss": 3.731, + "step": 508928 + }, + { + "epoch": 1.02, + "learning_rate": 4.165952004863849e-05, + "loss": 3.7166, + "step": 509440 + }, + { + "epoch": 1.02, + "learning_rate": 4.165113410112797e-05, + "loss": 3.7176, + "step": 509952 + }, + { + "epoch": 1.02, + "learning_rate": 4.164276453242119e-05, + "loss": 3.7106, + "step": 510464 + }, + { + "epoch": 1.02, + "learning_rate": 4.163437858491067e-05, + "loss": 3.7251, + "step": 510976 + }, + { + "epoch": 1.02, + "learning_rate": 4.162599263740015e-05, + "loss": 3.7061, + "step": 511488 + }, + { + "epoch": 1.02, + "learning_rate": 4.161760668988963e-05, + "loss": 3.7181, + "step": 512000 + }, + { + "epoch": 1.02, + "learning_rate": 4.1609237121182845e-05, + "loss": 3.7133, + "step": 512512 + }, + { + "epoch": 1.02, + "learning_rate": 4.160085117367232e-05, + "loss": 3.7277, + "step": 513024 + }, + { + "epoch": 1.02, + "learning_rate": 4.15924652261618e-05, + "loss": 3.7131, + "step": 513536 + }, + { + "epoch": 1.02, + "learning_rate": 4.158407927865128e-05, + "loss": 3.7208, + "step": 514048 + }, + { + "epoch": 1.02, + "learning_rate": 4.157569333114076e-05, + "loss": 3.7193, + "step": 514560 + }, + { + "epoch": 1.02, + "learning_rate": 4.156730738363024e-05, + "loss": 3.7103, + "step": 515072 + }, + { + "epoch": 1.02, + "learning_rate": 4.155893781492345e-05, + "loss": 3.7245, + "step": 515584 + }, + { + "epoch": 1.02, + "learning_rate": 4.155055186741293e-05, + "loss": 3.7197, + "step": 516096 + }, + { + "epoch": 1.02, + "learning_rate": 4.154216591990241e-05, + "loss": 3.7233, + "step": 516608 + }, + { + "epoch": 1.02, + "learning_rate": 4.153377997239189e-05, + "loss": 3.7257, + "step": 517120 + }, + { + "epoch": 1.02, + "learning_rate": 4.15254104036851e-05, + "loss": 3.7123, + "step": 517632 + }, + { + "epoch": 1.02, + "learning_rate": 4.151702445617458e-05, + "loss": 3.7172, + "step": 518144 + }, + { + "epoch": 1.02, + "learning_rate": 4.150863850866406e-05, + "loss": 3.7126, + "step": 518656 + }, + { + "epoch": 1.02, + "learning_rate": 4.150025256115354e-05, + "loss": 3.7182, + "step": 519168 + }, + { + "epoch": 1.02, + "learning_rate": 4.149186661364302e-05, + "loss": 3.7117, + "step": 519680 + }, + { + "epoch": 1.02, + "learning_rate": 4.148349704493623e-05, + "loss": 3.7147, + "step": 520192 + }, + { + "epoch": 1.02, + "learning_rate": 4.147511109742571e-05, + "loss": 3.7026, + "step": 520704 + }, + { + "epoch": 1.02, + "learning_rate": 4.146672514991519e-05, + "loss": 3.7179, + "step": 521216 + }, + { + "epoch": 1.02, + "learning_rate": 4.145833920240467e-05, + "loss": 3.7112, + "step": 521728 + }, + { + "epoch": 1.02, + "learning_rate": 4.144996963369788e-05, + "loss": 3.7186, + "step": 522240 + }, + { + "epoch": 1.02, + "learning_rate": 4.144158368618736e-05, + "loss": 3.7029, + "step": 522752 + }, + { + "epoch": 1.02, + "learning_rate": 4.143319773867684e-05, + "loss": 3.7134, + "step": 523264 + }, + { + "epoch": 1.02, + "learning_rate": 4.142481179116632e-05, + "loss": 3.714, + "step": 523776 + }, + { + "epoch": 1.02, + "learning_rate": 4.1416442222459536e-05, + "loss": 3.7232, + "step": 524288 + }, + { + "epoch": 1.02, + "learning_rate": 4.1408056274949016e-05, + "loss": 3.7117, + "step": 524800 + }, + { + "epoch": 1.02, + "learning_rate": 4.1399670327438496e-05, + "loss": 3.7185, + "step": 525312 + }, + { + "epoch": 1.02, + "learning_rate": 4.1391284379927976e-05, + "loss": 3.7044, + "step": 525824 + }, + { + "epoch": 1.02, + "learning_rate": 4.1382898432417456e-05, + "loss": 3.7188, + "step": 526336 + }, + { + "epoch": 1.02, + "learning_rate": 4.1374528863710665e-05, + "loss": 3.7193, + "step": 526848 + }, + { + "epoch": 1.02, + "learning_rate": 4.1366142916200145e-05, + "loss": 3.7205, + "step": 527360 + }, + { + "epoch": 1.02, + "learning_rate": 4.1357756968689625e-05, + "loss": 3.7173, + "step": 527872 + }, + { + "epoch": 1.02, + "learning_rate": 4.1349371021179105e-05, + "loss": 3.726, + "step": 528384 + }, + { + "epoch": 1.02, + "learning_rate": 4.1341001452472314e-05, + "loss": 3.7119, + "step": 528896 + }, + { + "epoch": 1.02, + "learning_rate": 4.1332615504961794e-05, + "loss": 3.7258, + "step": 529408 + }, + { + "epoch": 1.02, + "learning_rate": 4.1324229557451274e-05, + "loss": 3.704, + "step": 529920 + }, + { + "epoch": 1.02, + "learning_rate": 4.131584360994076e-05, + "loss": 3.7147, + "step": 530432 + }, + { + "epoch": 1.02, + "learning_rate": 4.130747404123397e-05, + "loss": 3.7082, + "step": 530944 + }, + { + "epoch": 1.02, + "learning_rate": 4.129908809372345e-05, + "loss": 3.7117, + "step": 531456 + }, + { + "epoch": 1.02, + "learning_rate": 4.129070214621293e-05, + "loss": 3.7101, + "step": 531968 + }, + { + "epoch": 1.02, + "learning_rate": 4.128231619870241e-05, + "loss": 3.7058, + "step": 532480 + }, + { + "epoch": 1.02, + "learning_rate": 4.127394662999562e-05, + "loss": 3.7189, + "step": 532992 + }, + { + "epoch": 1.02, + "learning_rate": 4.12655606824851e-05, + "loss": 3.7003, + "step": 533504 + }, + { + "epoch": 1.02, + "learning_rate": 4.125717473497458e-05, + "loss": 3.7266, + "step": 534016 + }, + { + "epoch": 1.03, + "eval_loss": 3.8584578037261963, + "eval_runtime": 305.7013, + "eval_samples_per_second": 1248.248, + "eval_steps_per_second": 39.009, + "step": 534240 + }, + { + "epoch": 0.0, + "learning_rate": 4.124878878746406e-05, + "loss": 3.7049, + "step": 534528 + }, + { + "epoch": 0.0, + "learning_rate": 4.124040283995354e-05, + "loss": 3.6994, + "step": 535040 + }, + { + "epoch": 0.0, + "learning_rate": 4.123201689244302e-05, + "loss": 3.7107, + "step": 535552 + }, + { + "epoch": 0.0, + "learning_rate": 4.12236309449325e-05, + "loss": 3.7155, + "step": 536064 + }, + { + "epoch": 0.0, + "learning_rate": 4.1215261376225714e-05, + "loss": 3.7124, + "step": 536576 + }, + { + "epoch": 0.0, + "learning_rate": 4.1206875428715194e-05, + "loss": 3.7069, + "step": 537088 + }, + { + "epoch": 0.0, + "learning_rate": 4.1198489481204674e-05, + "loss": 3.7009, + "step": 537600 + }, + { + "epoch": 0.0, + "learning_rate": 4.1190103533694154e-05, + "loss": 3.7036, + "step": 538112 + }, + { + "epoch": 0.0, + "learning_rate": 4.118173396498736e-05, + "loss": 3.7109, + "step": 538624 + }, + { + "epoch": 0.0, + "learning_rate": 4.117334801747684e-05, + "loss": 3.7171, + "step": 539136 + }, + { + "epoch": 0.0, + "learning_rate": 4.116496206996632e-05, + "loss": 3.7067, + "step": 539648 + }, + { + "epoch": 0.0, + "learning_rate": 4.1156576122455796e-05, + "loss": 3.7064, + "step": 540160 + }, + { + "epoch": 0.0, + "learning_rate": 4.114820655374901e-05, + "loss": 3.7026, + "step": 540672 + }, + { + "epoch": 0.0, + "learning_rate": 4.113982060623849e-05, + "loss": 3.6969, + "step": 541184 + }, + { + "epoch": 0.0, + "learning_rate": 4.113143465872797e-05, + "loss": 3.7025, + "step": 541696 + }, + { + "epoch": 0.0, + "learning_rate": 4.112304871121745e-05, + "loss": 3.6944, + "step": 542208 + }, + { + "epoch": 0.0, + "learning_rate": 4.111467914251067e-05, + "loss": 3.7026, + "step": 542720 + }, + { + "epoch": 0.0, + "learning_rate": 4.110629319500015e-05, + "loss": 3.7037, + "step": 543232 + }, + { + "epoch": 0.0, + "learning_rate": 4.109790724748963e-05, + "loss": 3.6967, + "step": 543744 + }, + { + "epoch": 0.0, + "learning_rate": 4.10895212999791e-05, + "loss": 3.7197, + "step": 544256 + }, + { + "epoch": 0.0, + "learning_rate": 4.108115173127232e-05, + "loss": 3.7151, + "step": 544768 + }, + { + "epoch": 0.0, + "learning_rate": 4.10727657837618e-05, + "loss": 3.7004, + "step": 545280 + }, + { + "epoch": 0.0, + "learning_rate": 4.106437983625127e-05, + "loss": 3.709, + "step": 545792 + }, + { + "epoch": 0.0, + "learning_rate": 4.105599388874075e-05, + "loss": 3.7142, + "step": 546304 + }, + { + "epoch": 0.0, + "learning_rate": 4.1047624320033966e-05, + "loss": 3.6928, + "step": 546816 + }, + { + "epoch": 0.0, + "learning_rate": 4.1039238372523446e-05, + "loss": 3.7114, + "step": 547328 + }, + { + "epoch": 0.0, + "learning_rate": 4.103085242501292e-05, + "loss": 3.7024, + "step": 547840 + }, + { + "epoch": 0.0, + "learning_rate": 4.1022466477502406e-05, + "loss": 3.6989, + "step": 548352 + }, + { + "epoch": 0.0, + "learning_rate": 4.101409690879562e-05, + "loss": 3.6915, + "step": 548864 + }, + { + "epoch": 0.0, + "learning_rate": 4.10057109612851e-05, + "loss": 3.7056, + "step": 549376 + }, + { + "epoch": 0.01, + "learning_rate": 4.0997325013774575e-05, + "loss": 3.7115, + "step": 549888 + }, + { + "epoch": 0.01, + "learning_rate": 4.0988939066264055e-05, + "loss": 3.7077, + "step": 550400 + }, + { + "epoch": 0.01, + "learning_rate": 4.098056949755727e-05, + "loss": 3.7132, + "step": 550912 + }, + { + "epoch": 0.01, + "learning_rate": 4.0972183550046744e-05, + "loss": 3.7021, + "step": 551424 + }, + { + "epoch": 0.01, + "learning_rate": 4.0963797602536224e-05, + "loss": 3.6976, + "step": 551936 + }, + { + "epoch": 0.01, + "learning_rate": 4.0955411655025704e-05, + "loss": 3.7056, + "step": 552448 + }, + { + "epoch": 0.01, + "learning_rate": 4.094704208631892e-05, + "loss": 3.6999, + "step": 552960 + }, + { + "epoch": 0.01, + "learning_rate": 4.093865613880839e-05, + "loss": 3.6899, + "step": 553472 + }, + { + "epoch": 0.01, + "learning_rate": 4.093027019129787e-05, + "loss": 3.6912, + "step": 553984 + }, + { + "epoch": 0.01, + "learning_rate": 4.092188424378736e-05, + "loss": 3.6963, + "step": 554496 + }, + { + "epoch": 0.01, + "learning_rate": 4.091349829627684e-05, + "loss": 3.6979, + "step": 555008 + }, + { + "epoch": 0.01, + "learning_rate": 4.090512872757005e-05, + "loss": 3.7048, + "step": 555520 + }, + { + "epoch": 0.01, + "learning_rate": 4.089674278005953e-05, + "loss": 3.7025, + "step": 556032 + }, + { + "epoch": 0.01, + "learning_rate": 4.088835683254901e-05, + "loss": 3.6987, + "step": 556544 + }, + { + "epoch": 0.01, + "learning_rate": 4.087997088503849e-05, + "loss": 3.7063, + "step": 557056 + }, + { + "epoch": 0.01, + "learning_rate": 4.08716013163317e-05, + "loss": 3.7033, + "step": 557568 + }, + { + "epoch": 0.01, + "learning_rate": 4.086321536882118e-05, + "loss": 3.7039, + "step": 558080 + }, + { + "epoch": 0.01, + "learning_rate": 4.085482942131066e-05, + "loss": 3.6962, + "step": 558592 + }, + { + "epoch": 0.01, + "learning_rate": 4.084644347380014e-05, + "loss": 3.6741, + "step": 559104 + }, + { + "epoch": 0.01, + "learning_rate": 4.0838073905093346e-05, + "loss": 3.7124, + "step": 559616 + }, + { + "epoch": 0.01, + "learning_rate": 4.0829687957582826e-05, + "loss": 3.6907, + "step": 560128 + }, + { + "epoch": 0.01, + "learning_rate": 4.082130201007231e-05, + "loss": 3.7049, + "step": 560640 + }, + { + "epoch": 0.01, + "learning_rate": 4.081291606256179e-05, + "loss": 3.6921, + "step": 561152 + }, + { + "epoch": 0.01, + "learning_rate": 4.0804546493855e-05, + "loss": 3.6952, + "step": 561664 + }, + { + "epoch": 0.01, + "learning_rate": 4.079616054634448e-05, + "loss": 3.6837, + "step": 562176 + }, + { + "epoch": 0.01, + "learning_rate": 4.078777459883396e-05, + "loss": 3.7004, + "step": 562688 + }, + { + "epoch": 0.01, + "learning_rate": 4.077938865132344e-05, + "loss": 3.6883, + "step": 563200 + }, + { + "epoch": 0.01, + "learning_rate": 4.077101908261665e-05, + "loss": 3.6908, + "step": 563712 + }, + { + "epoch": 0.01, + "learning_rate": 4.076263313510613e-05, + "loss": 3.7055, + "step": 564224 + }, + { + "epoch": 0.01, + "learning_rate": 4.075424718759561e-05, + "loss": 3.6864, + "step": 564736 + }, + { + "epoch": 0.01, + "learning_rate": 4.074586124008509e-05, + "loss": 3.6826, + "step": 565248 + }, + { + "epoch": 0.01, + "learning_rate": 4.07374916713783e-05, + "loss": 3.7021, + "step": 565760 + }, + { + "epoch": 0.01, + "learning_rate": 4.072910572386778e-05, + "loss": 3.6798, + "step": 566272 + }, + { + "epoch": 0.01, + "learning_rate": 4.072071977635726e-05, + "loss": 3.6778, + "step": 566784 + }, + { + "epoch": 0.01, + "learning_rate": 4.071233382884675e-05, + "loss": 3.6958, + "step": 567296 + }, + { + "epoch": 0.01, + "learning_rate": 4.070394788133623e-05, + "loss": 3.6924, + "step": 567808 + }, + { + "epoch": 0.01, + "learning_rate": 4.0695578312629436e-05, + "loss": 3.6876, + "step": 568320 + }, + { + "epoch": 0.01, + "learning_rate": 4.0687192365118916e-05, + "loss": 3.6938, + "step": 568832 + }, + { + "epoch": 0.01, + "learning_rate": 4.0678806417608396e-05, + "loss": 3.6743, + "step": 569344 + }, + { + "epoch": 0.01, + "learning_rate": 4.0670420470097876e-05, + "loss": 3.6873, + "step": 569856 + }, + { + "epoch": 0.01, + "learning_rate": 4.0662050901391085e-05, + "loss": 3.6969, + "step": 570368 + }, + { + "epoch": 0.01, + "learning_rate": 4.0653664953880565e-05, + "loss": 3.6895, + "step": 570880 + }, + { + "epoch": 0.01, + "learning_rate": 4.0645279006370045e-05, + "loss": 3.7038, + "step": 571392 + }, + { + "epoch": 0.01, + "learning_rate": 4.0636893058859525e-05, + "loss": 3.6955, + "step": 571904 + }, + { + "epoch": 0.01, + "learning_rate": 4.0628523490152734e-05, + "loss": 3.703, + "step": 572416 + }, + { + "epoch": 0.01, + "learning_rate": 4.0620137542642214e-05, + "loss": 3.6819, + "step": 572928 + }, + { + "epoch": 0.01, + "learning_rate": 4.06117515951317e-05, + "loss": 3.696, + "step": 573440 + }, + { + "epoch": 0.01, + "learning_rate": 4.060336564762118e-05, + "loss": 3.6933, + "step": 573952 + }, + { + "epoch": 0.01, + "learning_rate": 4.059499607891439e-05, + "loss": 3.6788, + "step": 574464 + }, + { + "epoch": 0.01, + "learning_rate": 4.058661013140387e-05, + "loss": 3.6923, + "step": 574976 + }, + { + "epoch": 0.01, + "learning_rate": 4.057822418389335e-05, + "loss": 3.693, + "step": 575488 + }, + { + "epoch": 0.01, + "learning_rate": 4.056983823638283e-05, + "loss": 3.6948, + "step": 576000 + }, + { + "epoch": 0.01, + "learning_rate": 4.056146866767604e-05, + "loss": 3.6966, + "step": 576512 + }, + { + "epoch": 0.01, + "learning_rate": 4.055308272016552e-05, + "loss": 3.6809, + "step": 577024 + }, + { + "epoch": 0.01, + "learning_rate": 4.0544696772655e-05, + "loss": 3.6824, + "step": 577536 + }, + { + "epoch": 0.01, + "learning_rate": 4.053631082514448e-05, + "loss": 3.6944, + "step": 578048 + }, + { + "epoch": 0.01, + "learning_rate": 4.052794125643769e-05, + "loss": 3.6935, + "step": 578560 + }, + { + "epoch": 0.01, + "learning_rate": 4.051955530892717e-05, + "loss": 3.6931, + "step": 579072 + }, + { + "epoch": 0.01, + "learning_rate": 4.0511169361416654e-05, + "loss": 3.6928, + "step": 579584 + }, + { + "epoch": 0.02, + "learning_rate": 4.0502783413906134e-05, + "loss": 3.6972, + "step": 580096 + }, + { + "epoch": 0.02, + "learning_rate": 4.049441384519934e-05, + "loss": 3.6892, + "step": 580608 + }, + { + "epoch": 0.02, + "learning_rate": 4.048602789768882e-05, + "loss": 3.6879, + "step": 581120 + }, + { + "epoch": 0.02, + "learning_rate": 4.04776419501783e-05, + "loss": 3.6811, + "step": 581632 + }, + { + "epoch": 0.02, + "learning_rate": 4.046925600266778e-05, + "loss": 3.6964, + "step": 582144 + }, + { + "epoch": 0.02, + "learning_rate": 4.046088643396099e-05, + "loss": 3.7018, + "step": 582656 + }, + { + "epoch": 0.02, + "learning_rate": 4.045250048645047e-05, + "loss": 3.6905, + "step": 583168 + }, + { + "epoch": 0.02, + "learning_rate": 4.044411453893995e-05, + "loss": 3.6826, + "step": 583680 + }, + { + "epoch": 0.02, + "learning_rate": 4.043572859142943e-05, + "loss": 3.6811, + "step": 584192 + }, + { + "epoch": 0.02, + "learning_rate": 4.042734264391891e-05, + "loss": 3.6915, + "step": 584704 + }, + { + "epoch": 0.02, + "learning_rate": 4.041897307521212e-05, + "loss": 3.7032, + "step": 585216 + }, + { + "epoch": 0.02, + "learning_rate": 4.041058712770161e-05, + "loss": 3.684, + "step": 585728 + }, + { + "epoch": 0.02, + "learning_rate": 4.040220118019109e-05, + "loss": 3.6868, + "step": 586240 + }, + { + "epoch": 0.02, + "learning_rate": 4.039381523268057e-05, + "loss": 3.6826, + "step": 586752 + }, + { + "epoch": 0.02, + "learning_rate": 4.038544566397378e-05, + "loss": 3.6876, + "step": 587264 + }, + { + "epoch": 0.02, + "learning_rate": 4.037705971646326e-05, + "loss": 3.6763, + "step": 587776 + }, + { + "epoch": 0.02, + "learning_rate": 4.036867376895274e-05, + "loss": 3.6889, + "step": 588288 + }, + { + "epoch": 0.02, + "learning_rate": 4.036028782144222e-05, + "loss": 3.6792, + "step": 588800 + }, + { + "epoch": 0.02, + "learning_rate": 4.0351918252735426e-05, + "loss": 3.6955, + "step": 589312 + }, + { + "epoch": 0.02, + "learning_rate": 4.0343532305224906e-05, + "loss": 3.6838, + "step": 589824 + }, + { + "epoch": 0.02, + "learning_rate": 4.0335146357714386e-05, + "loss": 3.6854, + "step": 590336 + }, + { + "epoch": 0.02, + "learning_rate": 4.0326760410203866e-05, + "loss": 3.685, + "step": 590848 + }, + { + "epoch": 0.02, + "learning_rate": 4.0318390841497075e-05, + "loss": 3.6877, + "step": 591360 + }, + { + "epoch": 0.02, + "learning_rate": 4.031000489398656e-05, + "loss": 3.6883, + "step": 591872 + }, + { + "epoch": 0.02, + "learning_rate": 4.030161894647604e-05, + "loss": 3.6879, + "step": 592384 + }, + { + "epoch": 0.02, + "learning_rate": 4.029323299896552e-05, + "loss": 3.6887, + "step": 592896 + }, + { + "epoch": 0.02, + "learning_rate": 4.0284847051455e-05, + "loss": 3.6965, + "step": 593408 + }, + { + "epoch": 0.02, + "learning_rate": 4.027647748274821e-05, + "loss": 3.6826, + "step": 593920 + }, + { + "epoch": 0.02, + "learning_rate": 4.026809153523769e-05, + "loss": 3.6855, + "step": 594432 + }, + { + "epoch": 0.02, + "learning_rate": 4.025970558772717e-05, + "loss": 3.6818, + "step": 594944 + }, + { + "epoch": 0.02, + "learning_rate": 4.025131964021665e-05, + "loss": 3.6829, + "step": 595456 + }, + { + "epoch": 0.02, + "learning_rate": 4.024295007150986e-05, + "loss": 3.6825, + "step": 595968 + }, + { + "epoch": 0.02, + "learning_rate": 4.023456412399934e-05, + "loss": 3.6842, + "step": 596480 + }, + { + "epoch": 0.02, + "learning_rate": 4.022617817648882e-05, + "loss": 3.6739, + "step": 596992 + }, + { + "epoch": 0.02, + "learning_rate": 4.02177922289783e-05, + "loss": 3.684, + "step": 597504 + }, + { + "epoch": 0.02, + "learning_rate": 4.0209422660271515e-05, + "loss": 3.6846, + "step": 598016 + }, + { + "epoch": 0.02, + "learning_rate": 4.0201036712760995e-05, + "loss": 3.684, + "step": 598528 + }, + { + "epoch": 0.02, + "learning_rate": 4.0192650765250475e-05, + "loss": 3.6705, + "step": 599040 + }, + { + "epoch": 0.02, + "learning_rate": 4.018426481773995e-05, + "loss": 3.6859, + "step": 599552 + }, + { + "epoch": 0.02, + "learning_rate": 4.0175895249033164e-05, + "loss": 3.6817, + "step": 600064 + }, + { + "epoch": 0.02, + "learning_rate": 4.0167509301522644e-05, + "loss": 3.6932, + "step": 600576 + }, + { + "epoch": 0.02, + "learning_rate": 4.0159123354012124e-05, + "loss": 3.6824, + "step": 601088 + }, + { + "epoch": 0.02, + "learning_rate": 4.01507374065016e-05, + "loss": 3.687, + "step": 601600 + }, + { + "epoch": 0.02, + "learning_rate": 4.014236783779481e-05, + "loss": 3.6749, + "step": 602112 + }, + { + "epoch": 0.02, + "learning_rate": 4.013398189028429e-05, + "loss": 3.691, + "step": 602624 + }, + { + "epoch": 0.02, + "learning_rate": 4.0125595942773766e-05, + "loss": 3.689, + "step": 603136 + }, + { + "epoch": 0.02, + "learning_rate": 4.011720999526325e-05, + "loss": 3.6909, + "step": 603648 + }, + { + "epoch": 0.02, + "learning_rate": 4.010884042655647e-05, + "loss": 3.6885, + "step": 604160 + }, + { + "epoch": 0.02, + "learning_rate": 4.010045447904595e-05, + "loss": 3.691, + "step": 604672 + }, + { + "epoch": 0.02, + "learning_rate": 4.009206853153542e-05, + "loss": 3.6853, + "step": 605184 + }, + { + "epoch": 0.02, + "learning_rate": 4.00836825840249e-05, + "loss": 3.6928, + "step": 605696 + }, + { + "epoch": 0.02, + "learning_rate": 4.007529663651438e-05, + "loss": 3.6756, + "step": 606208 + }, + { + "epoch": 0.02, + "learning_rate": 4.00669270678076e-05, + "loss": 3.6851, + "step": 606720 + }, + { + "epoch": 0.02, + "learning_rate": 4.005854112029707e-05, + "loss": 3.6761, + "step": 607232 + }, + { + "epoch": 0.02, + "learning_rate": 4.005015517278655e-05, + "loss": 3.6854, + "step": 607744 + }, + { + "epoch": 0.02, + "learning_rate": 4.004176922527603e-05, + "loss": 3.6753, + "step": 608256 + }, + { + "epoch": 0.02, + "learning_rate": 4.003339965656924e-05, + "loss": 3.6759, + "step": 608768 + }, + { + "epoch": 0.02, + "learning_rate": 4.002501370905872e-05, + "loss": 3.6838, + "step": 609280 + }, + { + "epoch": 0.02, + "learning_rate": 4.0016627761548207e-05, + "loss": 3.6719, + "step": 609792 + }, + { + "epoch": 0.02, + "learning_rate": 4.0008241814037687e-05, + "loss": 3.6964, + "step": 610304 + }, + { + "epoch": 0.03, + "eval_loss": 3.8516294956207275, + "eval_runtime": 303.4774, + "eval_samples_per_second": 1257.395, + "eval_steps_per_second": 39.295, + "step": 610560 + }, + { + "epoch": 1.0, + "learning_rate": 3.9999872245330896e-05, + "loss": 3.6719, + "step": 610816 + }, + { + "epoch": 1.0, + "learning_rate": 3.9991486297820376e-05, + "loss": 3.6742, + "step": 611328 + }, + { + "epoch": 1.0, + "learning_rate": 3.9983100350309856e-05, + "loss": 3.6759, + "step": 611840 + }, + { + "epoch": 1.0, + "learning_rate": 3.9974714402799336e-05, + "loss": 3.6836, + "step": 612352 + }, + { + "epoch": 1.0, + "learning_rate": 3.9966344834092545e-05, + "loss": 3.6856, + "step": 612864 + }, + { + "epoch": 1.0, + "learning_rate": 3.9957958886582025e-05, + "loss": 3.6733, + "step": 613376 + }, + { + "epoch": 1.0, + "learning_rate": 3.9949572939071505e-05, + "loss": 3.6772, + "step": 613888 + }, + { + "epoch": 1.0, + "learning_rate": 3.9941186991560984e-05, + "loss": 3.6735, + "step": 614400 + }, + { + "epoch": 1.0, + "learning_rate": 3.9932817422854194e-05, + "loss": 3.6777, + "step": 614912 + }, + { + "epoch": 1.0, + "learning_rate": 3.9924431475343674e-05, + "loss": 3.6884, + "step": 615424 + }, + { + "epoch": 1.0, + "learning_rate": 3.991604552783316e-05, + "loss": 3.6746, + "step": 615936 + }, + { + "epoch": 1.0, + "learning_rate": 3.990765958032264e-05, + "loss": 3.6771, + "step": 616448 + }, + { + "epoch": 1.0, + "learning_rate": 3.989929001161585e-05, + "loss": 3.671, + "step": 616960 + }, + { + "epoch": 1.0, + "learning_rate": 3.989090406410533e-05, + "loss": 3.6652, + "step": 617472 + }, + { + "epoch": 1.0, + "learning_rate": 3.988251811659481e-05, + "loss": 3.6776, + "step": 617984 + }, + { + "epoch": 1.0, + "learning_rate": 3.987413216908429e-05, + "loss": 3.665, + "step": 618496 + }, + { + "epoch": 1.0, + "learning_rate": 3.98657626003775e-05, + "loss": 3.6739, + "step": 619008 + }, + { + "epoch": 1.0, + "learning_rate": 3.985737665286698e-05, + "loss": 3.6762, + "step": 619520 + }, + { + "epoch": 1.0, + "learning_rate": 3.984899070535646e-05, + "loss": 3.6652, + "step": 620032 + }, + { + "epoch": 1.0, + "learning_rate": 3.984060475784594e-05, + "loss": 3.6881, + "step": 620544 + }, + { + "epoch": 1.0, + "learning_rate": 3.983223518913915e-05, + "loss": 3.6863, + "step": 621056 + }, + { + "epoch": 1.0, + "learning_rate": 3.982384924162863e-05, + "loss": 3.6744, + "step": 621568 + }, + { + "epoch": 1.0, + "learning_rate": 3.981546329411811e-05, + "loss": 3.6755, + "step": 622080 + }, + { + "epoch": 1.0, + "learning_rate": 3.9807077346607594e-05, + "loss": 3.6846, + "step": 622592 + }, + { + "epoch": 1.0, + "learning_rate": 3.97987077779008e-05, + "loss": 3.6715, + "step": 623104 + }, + { + "epoch": 1.0, + "learning_rate": 3.979032183039028e-05, + "loss": 3.6756, + "step": 623616 + }, + { + "epoch": 1.0, + "learning_rate": 3.978193588287976e-05, + "loss": 3.6759, + "step": 624128 + }, + { + "epoch": 1.0, + "learning_rate": 3.977354993536924e-05, + "loss": 3.6721, + "step": 624640 + }, + { + "epoch": 1.0, + "learning_rate": 3.976518036666245e-05, + "loss": 3.6676, + "step": 625152 + }, + { + "epoch": 1.0, + "learning_rate": 3.975679441915193e-05, + "loss": 3.6707, + "step": 625664 + }, + { + "epoch": 1.01, + "learning_rate": 3.974840847164141e-05, + "loss": 3.6777, + "step": 626176 + }, + { + "epoch": 1.01, + "learning_rate": 3.974002252413089e-05, + "loss": 3.683, + "step": 626688 + }, + { + "epoch": 1.01, + "learning_rate": 3.97316529554241e-05, + "loss": 3.6821, + "step": 627200 + }, + { + "epoch": 1.01, + "learning_rate": 3.972326700791358e-05, + "loss": 3.6729, + "step": 627712 + }, + { + "epoch": 1.01, + "learning_rate": 3.971488106040306e-05, + "loss": 3.6663, + "step": 628224 + }, + { + "epoch": 1.01, + "learning_rate": 3.970649511289255e-05, + "loss": 3.6783, + "step": 628736 + }, + { + "epoch": 1.01, + "learning_rate": 3.969812554418576e-05, + "loss": 3.6726, + "step": 629248 + }, + { + "epoch": 1.01, + "learning_rate": 3.9689739596675237e-05, + "loss": 3.6621, + "step": 629760 + }, + { + "epoch": 1.01, + "learning_rate": 3.9681353649164717e-05, + "loss": 3.6637, + "step": 630272 + }, + { + "epoch": 1.01, + "learning_rate": 3.9672967701654197e-05, + "loss": 3.6657, + "step": 630784 + }, + { + "epoch": 1.01, + "learning_rate": 3.9664598132947406e-05, + "loss": 3.6679, + "step": 631296 + }, + { + "epoch": 1.01, + "learning_rate": 3.9656212185436886e-05, + "loss": 3.6756, + "step": 631808 + }, + { + "epoch": 1.01, + "learning_rate": 3.9647826237926366e-05, + "loss": 3.6767, + "step": 632320 + }, + { + "epoch": 1.01, + "learning_rate": 3.9639440290415845e-05, + "loss": 3.6736, + "step": 632832 + }, + { + "epoch": 1.01, + "learning_rate": 3.9631070721709055e-05, + "loss": 3.672, + "step": 633344 + }, + { + "epoch": 1.01, + "learning_rate": 3.9622684774198535e-05, + "loss": 3.6748, + "step": 633856 + }, + { + "epoch": 1.01, + "learning_rate": 3.9614298826688014e-05, + "loss": 3.6727, + "step": 634368 + }, + { + "epoch": 1.01, + "learning_rate": 3.96059128791775e-05, + "loss": 3.67, + "step": 634880 + }, + { + "epoch": 1.01, + "learning_rate": 3.959754331047071e-05, + "loss": 3.6457, + "step": 635392 + }, + { + "epoch": 1.01, + "learning_rate": 3.958915736296019e-05, + "loss": 3.6837, + "step": 635904 + }, + { + "epoch": 1.01, + "learning_rate": 3.958077141544967e-05, + "loss": 3.6639, + "step": 636416 + }, + { + "epoch": 1.01, + "learning_rate": 3.957238546793915e-05, + "loss": 3.6779, + "step": 636928 + }, + { + "epoch": 1.01, + "learning_rate": 3.956401589923236e-05, + "loss": 3.662, + "step": 637440 + }, + { + "epoch": 1.01, + "learning_rate": 3.955562995172184e-05, + "loss": 3.664, + "step": 637952 + }, + { + "epoch": 1.01, + "learning_rate": 3.954724400421132e-05, + "loss": 3.6565, + "step": 638464 + }, + { + "epoch": 1.01, + "learning_rate": 3.95388580567008e-05, + "loss": 3.6718, + "step": 638976 + }, + { + "epoch": 1.01, + "learning_rate": 3.953048848799401e-05, + "loss": 3.6629, + "step": 639488 + }, + { + "epoch": 1.01, + "learning_rate": 3.952210254048349e-05, + "loss": 3.6613, + "step": 640000 + }, + { + "epoch": 1.01, + "learning_rate": 3.951371659297297e-05, + "loss": 3.6743, + "step": 640512 + }, + { + "epoch": 1.01, + "learning_rate": 3.9505330645462455e-05, + "loss": 3.6603, + "step": 641024 + }, + { + "epoch": 1.01, + "learning_rate": 3.9496961076755664e-05, + "loss": 3.6513, + "step": 641536 + }, + { + "epoch": 1.01, + "learning_rate": 3.9488575129245144e-05, + "loss": 3.6783, + "step": 642048 + }, + { + "epoch": 1.01, + "learning_rate": 3.9480189181734624e-05, + "loss": 3.6521, + "step": 642560 + }, + { + "epoch": 1.01, + "learning_rate": 3.9471803234224104e-05, + "loss": 3.6479, + "step": 643072 + }, + { + "epoch": 1.01, + "learning_rate": 3.946343366551731e-05, + "loss": 3.6685, + "step": 643584 + }, + { + "epoch": 1.01, + "learning_rate": 3.945504771800679e-05, + "loss": 3.665, + "step": 644096 + }, + { + "epoch": 1.01, + "learning_rate": 3.944666177049627e-05, + "loss": 3.6601, + "step": 644608 + }, + { + "epoch": 1.01, + "learning_rate": 3.943827582298575e-05, + "loss": 3.6628, + "step": 645120 + }, + { + "epoch": 1.01, + "learning_rate": 3.942990625427896e-05, + "loss": 3.6472, + "step": 645632 + }, + { + "epoch": 1.01, + "learning_rate": 3.942152030676844e-05, + "loss": 3.6581, + "step": 646144 + }, + { + "epoch": 1.01, + "learning_rate": 3.941313435925792e-05, + "loss": 3.6689, + "step": 646656 + }, + { + "epoch": 1.01, + "learning_rate": 3.940474841174741e-05, + "loss": 3.6601, + "step": 647168 + }, + { + "epoch": 1.01, + "learning_rate": 3.939637884304062e-05, + "loss": 3.6766, + "step": 647680 + }, + { + "epoch": 1.01, + "learning_rate": 3.93879928955301e-05, + "loss": 3.6649, + "step": 648192 + }, + { + "epoch": 1.01, + "learning_rate": 3.937960694801958e-05, + "loss": 3.6761, + "step": 648704 + }, + { + "epoch": 1.01, + "learning_rate": 3.937122100050906e-05, + "loss": 3.6537, + "step": 649216 + }, + { + "epoch": 1.01, + "learning_rate": 3.9362851431802267e-05, + "loss": 3.6694, + "step": 649728 + }, + { + "epoch": 1.01, + "learning_rate": 3.9354465484291747e-05, + "loss": 3.6607, + "step": 650240 + }, + { + "epoch": 1.01, + "learning_rate": 3.9346079536781227e-05, + "loss": 3.6539, + "step": 650752 + }, + { + "epoch": 1.01, + "learning_rate": 3.9337693589270706e-05, + "loss": 3.6643, + "step": 651264 + }, + { + "epoch": 1.01, + "learning_rate": 3.9329324020563916e-05, + "loss": 3.6676, + "step": 651776 + }, + { + "epoch": 1.01, + "learning_rate": 3.9320938073053396e-05, + "loss": 3.6632, + "step": 652288 + }, + { + "epoch": 1.01, + "learning_rate": 3.9312552125542875e-05, + "loss": 3.6715, + "step": 652800 + }, + { + "epoch": 1.01, + "learning_rate": 3.930416617803236e-05, + "loss": 3.6509, + "step": 653312 + }, + { + "epoch": 1.01, + "learning_rate": 3.929579660932557e-05, + "loss": 3.6533, + "step": 653824 + }, + { + "epoch": 1.01, + "learning_rate": 3.928741066181505e-05, + "loss": 3.6685, + "step": 654336 + }, + { + "epoch": 1.01, + "learning_rate": 3.927902471430453e-05, + "loss": 3.6659, + "step": 654848 + }, + { + "epoch": 1.01, + "learning_rate": 3.927063876679401e-05, + "loss": 3.6645, + "step": 655360 + }, + { + "epoch": 1.01, + "learning_rate": 3.926226919808722e-05, + "loss": 3.6677, + "step": 655872 + }, + { + "epoch": 1.02, + "learning_rate": 3.92538832505767e-05, + "loss": 3.6656, + "step": 656384 + }, + { + "epoch": 1.02, + "learning_rate": 3.924549730306618e-05, + "loss": 3.666, + "step": 656896 + }, + { + "epoch": 1.02, + "learning_rate": 3.923711135555566e-05, + "loss": 3.6612, + "step": 657408 + }, + { + "epoch": 1.02, + "learning_rate": 3.922874178684887e-05, + "loss": 3.6534, + "step": 657920 + }, + { + "epoch": 1.02, + "learning_rate": 3.922035583933835e-05, + "loss": 3.6713, + "step": 658432 + }, + { + "epoch": 1.02, + "learning_rate": 3.921196989182783e-05, + "loss": 3.669, + "step": 658944 + }, + { + "epoch": 1.02, + "learning_rate": 3.9203583944317316e-05, + "loss": 3.6634, + "step": 659456 + }, + { + "epoch": 1.02, + "learning_rate": 3.9195214375610525e-05, + "loss": 3.6572, + "step": 659968 + }, + { + "epoch": 1.02, + "learning_rate": 3.9186828428100005e-05, + "loss": 3.6539, + "step": 660480 + }, + { + "epoch": 1.02, + "learning_rate": 3.9178442480589485e-05, + "loss": 3.6597, + "step": 660992 + }, + { + "epoch": 1.02, + "learning_rate": 3.9170056533078965e-05, + "loss": 3.6747, + "step": 661504 + }, + { + "epoch": 1.02, + "learning_rate": 3.9161686964372174e-05, + "loss": 3.6595, + "step": 662016 + }, + { + "epoch": 1.02, + "learning_rate": 3.9153301016861654e-05, + "loss": 3.6602, + "step": 662528 + }, + { + "epoch": 1.02, + "learning_rate": 3.9144915069351134e-05, + "loss": 3.6537, + "step": 663040 + }, + { + "epoch": 1.02, + "learning_rate": 3.9136529121840614e-05, + "loss": 3.6571, + "step": 663552 + }, + { + "epoch": 1.02, + "learning_rate": 3.912815955313382e-05, + "loss": 3.6557, + "step": 664064 + }, + { + "epoch": 1.02, + "learning_rate": 3.91197736056233e-05, + "loss": 3.6563, + "step": 664576 + }, + { + "epoch": 1.02, + "learning_rate": 3.911138765811278e-05, + "loss": 3.6491, + "step": 665088 + }, + { + "epoch": 1.02, + "learning_rate": 3.910300171060226e-05, + "loss": 3.6697, + "step": 665600 + }, + { + "epoch": 1.02, + "learning_rate": 3.909463214189548e-05, + "loss": 3.6592, + "step": 666112 + }, + { + "epoch": 1.02, + "learning_rate": 3.908624619438496e-05, + "loss": 3.6572, + "step": 666624 + }, + { + "epoch": 1.02, + "learning_rate": 3.907786024687444e-05, + "loss": 3.6529, + "step": 667136 + }, + { + "epoch": 1.02, + "learning_rate": 3.906947429936392e-05, + "loss": 3.6633, + "step": 667648 + }, + { + "epoch": 1.02, + "learning_rate": 3.906110473065713e-05, + "loss": 3.6628, + "step": 668160 + }, + { + "epoch": 1.02, + "learning_rate": 3.905271878314661e-05, + "loss": 3.6607, + "step": 668672 + }, + { + "epoch": 1.02, + "learning_rate": 3.904433283563609e-05, + "loss": 3.6628, + "step": 669184 + }, + { + "epoch": 1.02, + "learning_rate": 3.903594688812556e-05, + "loss": 3.6687, + "step": 669696 + }, + { + "epoch": 1.02, + "learning_rate": 3.9027577319418777e-05, + "loss": 3.6545, + "step": 670208 + }, + { + "epoch": 1.02, + "learning_rate": 3.9019191371908257e-05, + "loss": 3.6606, + "step": 670720 + }, + { + "epoch": 1.02, + "learning_rate": 3.9010805424397736e-05, + "loss": 3.6503, + "step": 671232 + }, + { + "epoch": 1.02, + "learning_rate": 3.9002419476887216e-05, + "loss": 3.6591, + "step": 671744 + }, + { + "epoch": 1.02, + "learning_rate": 3.899404990818043e-05, + "loss": 3.6547, + "step": 672256 + }, + { + "epoch": 1.02, + "learning_rate": 3.898566396066991e-05, + "loss": 3.65, + "step": 672768 + }, + { + "epoch": 1.02, + "learning_rate": 3.897727801315939e-05, + "loss": 3.6524, + "step": 673280 + }, + { + "epoch": 1.02, + "learning_rate": 3.8968892065648865e-05, + "loss": 3.6576, + "step": 673792 + }, + { + "epoch": 1.02, + "learning_rate": 3.896052249694208e-05, + "loss": 3.659, + "step": 674304 + }, + { + "epoch": 1.02, + "learning_rate": 3.895213654943156e-05, + "loss": 3.6576, + "step": 674816 + }, + { + "epoch": 1.02, + "learning_rate": 3.8943750601921034e-05, + "loss": 3.6456, + "step": 675328 + }, + { + "epoch": 1.02, + "learning_rate": 3.8935364654410514e-05, + "loss": 3.6558, + "step": 675840 + }, + { + "epoch": 1.02, + "learning_rate": 3.892699508570373e-05, + "loss": 3.6544, + "step": 676352 + }, + { + "epoch": 1.02, + "learning_rate": 3.891860913819321e-05, + "loss": 3.6653, + "step": 676864 + }, + { + "epoch": 1.02, + "learning_rate": 3.891022319068269e-05, + "loss": 3.658, + "step": 677376 + }, + { + "epoch": 1.02, + "learning_rate": 3.890183724317217e-05, + "loss": 3.6569, + "step": 677888 + }, + { + "epoch": 1.02, + "learning_rate": 3.8893467674465386e-05, + "loss": 3.648, + "step": 678400 + }, + { + "epoch": 1.02, + "learning_rate": 3.8885081726954866e-05, + "loss": 3.6627, + "step": 678912 + }, + { + "epoch": 1.02, + "learning_rate": 3.887669577944434e-05, + "loss": 3.6622, + "step": 679424 + }, + { + "epoch": 1.02, + "learning_rate": 3.886830983193382e-05, + "loss": 3.6638, + "step": 679936 + }, + { + "epoch": 1.02, + "learning_rate": 3.8859940263227035e-05, + "loss": 3.6624, + "step": 680448 + }, + { + "epoch": 1.02, + "learning_rate": 3.885155431571651e-05, + "loss": 3.6652, + "step": 680960 + }, + { + "epoch": 1.02, + "learning_rate": 3.884316836820599e-05, + "loss": 3.6575, + "step": 681472 + }, + { + "epoch": 1.02, + "learning_rate": 3.883478242069547e-05, + "loss": 3.6661, + "step": 681984 + }, + { + "epoch": 1.02, + "learning_rate": 3.8826412851988684e-05, + "loss": 3.6475, + "step": 682496 + }, + { + "epoch": 1.02, + "learning_rate": 3.8818026904478164e-05, + "loss": 3.661, + "step": 683008 + }, + { + "epoch": 1.02, + "learning_rate": 3.8809640956967644e-05, + "loss": 3.6512, + "step": 683520 + }, + { + "epoch": 1.02, + "learning_rate": 3.8801255009457124e-05, + "loss": 3.6565, + "step": 684032 + }, + { + "epoch": 1.02, + "learning_rate": 3.8792869061946604e-05, + "loss": 3.6471, + "step": 684544 + }, + { + "epoch": 1.02, + "learning_rate": 3.878449949323981e-05, + "loss": 3.65, + "step": 685056 + }, + { + "epoch": 1.02, + "learning_rate": 3.877611354572929e-05, + "loss": 3.6592, + "step": 685568 + }, + { + "epoch": 1.02, + "learning_rate": 3.876772759821877e-05, + "loss": 3.6524, + "step": 686080 + }, + { + "epoch": 1.02, + "learning_rate": 3.875934165070825e-05, + "loss": 3.6658, + "step": 686592 + }, + { + "epoch": 1.03, + "eval_loss": 3.8457534313201904, + "eval_runtime": 303.4298, + "eval_samples_per_second": 1257.592, + "eval_steps_per_second": 39.301, + "step": 686880 + }, + { + "epoch": 0.0, + "learning_rate": 3.875097208200146e-05, + "loss": 3.6429, + "step": 687104 + }, + { + "epoch": 0.0, + "learning_rate": 3.874258613449094e-05, + "loss": 3.6462, + "step": 687616 + }, + { + "epoch": 0.0, + "learning_rate": 3.873420018698042e-05, + "loss": 3.6461, + "step": 688128 + }, + { + "epoch": 0.0, + "learning_rate": 3.87258142394699e-05, + "loss": 3.6641, + "step": 688640 + }, + { + "epoch": 0.0, + "learning_rate": 3.871744467076312e-05, + "loss": 3.6601, + "step": 689152 + }, + { + "epoch": 0.0, + "learning_rate": 3.87090587232526e-05, + "loss": 3.6451, + "step": 689664 + }, + { + "epoch": 0.0, + "learning_rate": 3.870067277574208e-05, + "loss": 3.6514, + "step": 690176 + }, + { + "epoch": 0.0, + "learning_rate": 3.869228682823156e-05, + "loss": 3.6468, + "step": 690688 + }, + { + "epoch": 0.0, + "learning_rate": 3.8683917259524766e-05, + "loss": 3.6505, + "step": 691200 + }, + { + "epoch": 0.0, + "learning_rate": 3.8675531312014246e-05, + "loss": 3.6646, + "step": 691712 + }, + { + "epoch": 0.0, + "learning_rate": 3.8667145364503726e-05, + "loss": 3.6469, + "step": 692224 + }, + { + "epoch": 0.0, + "learning_rate": 3.8658759416993206e-05, + "loss": 3.6467, + "step": 692736 + }, + { + "epoch": 0.0, + "learning_rate": 3.8650389848286415e-05, + "loss": 3.6573, + "step": 693248 + }, + { + "epoch": 0.0, + "learning_rate": 3.8642003900775895e-05, + "loss": 3.6352, + "step": 693760 + }, + { + "epoch": 0.0, + "learning_rate": 3.8633617953265375e-05, + "loss": 3.6472, + "step": 694272 + }, + { + "epoch": 0.0, + "learning_rate": 3.8625232005754855e-05, + "loss": 3.6394, + "step": 694784 + }, + { + "epoch": 0.0, + "learning_rate": 3.861686243704807e-05, + "loss": 3.65, + "step": 695296 + }, + { + "epoch": 0.0, + "learning_rate": 3.860847648953755e-05, + "loss": 3.6491, + "step": 695808 + }, + { + "epoch": 0.0, + "learning_rate": 3.860009054202703e-05, + "loss": 3.6397, + "step": 696320 + }, + { + "epoch": 0.0, + "learning_rate": 3.859170459451651e-05, + "loss": 3.6613, + "step": 696832 + }, + { + "epoch": 0.0, + "learning_rate": 3.858333502580972e-05, + "loss": 3.6605, + "step": 697344 + }, + { + "epoch": 0.0, + "learning_rate": 3.85749490782992e-05, + "loss": 3.6509, + "step": 697856 + }, + { + "epoch": 0.0, + "learning_rate": 3.856656313078868e-05, + "loss": 3.6524, + "step": 698368 + }, + { + "epoch": 0.0, + "learning_rate": 3.855817718327816e-05, + "loss": 3.6538, + "step": 698880 + }, + { + "epoch": 0.0, + "learning_rate": 3.854980761457137e-05, + "loss": 3.6492, + "step": 699392 + }, + { + "epoch": 0.0, + "learning_rate": 3.854142166706085e-05, + "loss": 3.6473, + "step": 699904 + }, + { + "epoch": 0.0, + "learning_rate": 3.853303571955033e-05, + "loss": 3.652, + "step": 700416 + }, + { + "epoch": 0.0, + "learning_rate": 3.852464977203981e-05, + "loss": 3.6488, + "step": 700928 + }, + { + "epoch": 0.0, + "learning_rate": 3.8516280203333025e-05, + "loss": 3.6379, + "step": 701440 + }, + { + "epoch": 0.0, + "learning_rate": 3.8507894255822505e-05, + "loss": 3.6454, + "step": 701952 + }, + { + "epoch": 0.01, + "learning_rate": 3.8499508308311985e-05, + "loss": 3.6497, + "step": 702464 + }, + { + "epoch": 0.01, + "learning_rate": 3.8491122360801465e-05, + "loss": 3.6602, + "step": 702976 + }, + { + "epoch": 0.01, + "learning_rate": 3.8482752792094674e-05, + "loss": 3.6558, + "step": 703488 + }, + { + "epoch": 0.01, + "learning_rate": 3.8474366844584154e-05, + "loss": 3.6502, + "step": 704000 + }, + { + "epoch": 0.01, + "learning_rate": 3.8465980897073634e-05, + "loss": 3.6406, + "step": 704512 + }, + { + "epoch": 0.01, + "learning_rate": 3.8457594949563114e-05, + "loss": 3.6465, + "step": 705024 + }, + { + "epoch": 0.01, + "learning_rate": 3.844922538085632e-05, + "loss": 3.6527, + "step": 705536 + }, + { + "epoch": 0.01, + "learning_rate": 3.84408394333458e-05, + "loss": 3.639, + "step": 706048 + }, + { + "epoch": 0.01, + "learning_rate": 3.843245348583528e-05, + "loss": 3.6379, + "step": 706560 + }, + { + "epoch": 0.01, + "learning_rate": 3.842406753832476e-05, + "loss": 3.6403, + "step": 707072 + }, + { + "epoch": 0.01, + "learning_rate": 3.841569796961798e-05, + "loss": 3.6432, + "step": 707584 + }, + { + "epoch": 0.01, + "learning_rate": 3.840731202210746e-05, + "loss": 3.6469, + "step": 708096 + }, + { + "epoch": 0.01, + "learning_rate": 3.839892607459694e-05, + "loss": 3.65, + "step": 708608 + }, + { + "epoch": 0.01, + "learning_rate": 3.839054012708642e-05, + "loss": 3.6492, + "step": 709120 + }, + { + "epoch": 0.01, + "learning_rate": 3.838217055837963e-05, + "loss": 3.6486, + "step": 709632 + }, + { + "epoch": 0.01, + "learning_rate": 3.837378461086911e-05, + "loss": 3.6447, + "step": 710144 + }, + { + "epoch": 0.01, + "learning_rate": 3.836539866335859e-05, + "loss": 3.645, + "step": 710656 + }, + { + "epoch": 0.01, + "learning_rate": 3.835701271584807e-05, + "loss": 3.6521, + "step": 711168 + }, + { + "epoch": 0.01, + "learning_rate": 3.8348643147141276e-05, + "loss": 3.6179, + "step": 711680 + }, + { + "epoch": 0.01, + "learning_rate": 3.8340257199630756e-05, + "loss": 3.6529, + "step": 712192 + }, + { + "epoch": 0.01, + "learning_rate": 3.8331871252120236e-05, + "loss": 3.6389, + "step": 712704 + }, + { + "epoch": 0.01, + "learning_rate": 3.8323485304609716e-05, + "loss": 3.6549, + "step": 713216 + }, + { + "epoch": 0.01, + "learning_rate": 3.831511573590293e-05, + "loss": 3.6409, + "step": 713728 + }, + { + "epoch": 0.01, + "learning_rate": 3.830672978839241e-05, + "loss": 3.6396, + "step": 714240 + }, + { + "epoch": 0.01, + "learning_rate": 3.829834384088189e-05, + "loss": 3.6301, + "step": 714752 + }, + { + "epoch": 0.01, + "learning_rate": 3.828995789337137e-05, + "loss": 3.6459, + "step": 715264 + }, + { + "epoch": 0.01, + "learning_rate": 3.828158832466458e-05, + "loss": 3.6432, + "step": 715776 + }, + { + "epoch": 0.01, + "learning_rate": 3.827320237715406e-05, + "loss": 3.6332, + "step": 716288 + }, + { + "epoch": 0.01, + "learning_rate": 3.826481642964354e-05, + "loss": 3.6512, + "step": 716800 + }, + { + "epoch": 0.01, + "learning_rate": 3.825643048213302e-05, + "loss": 3.6407, + "step": 717312 + }, + { + "epoch": 0.01, + "learning_rate": 3.824806091342623e-05, + "loss": 3.6216, + "step": 717824 + }, + { + "epoch": 0.01, + "learning_rate": 3.823967496591571e-05, + "loss": 3.6513, + "step": 718336 + }, + { + "epoch": 0.01, + "learning_rate": 3.823128901840519e-05, + "loss": 3.6311, + "step": 718848 + }, + { + "epoch": 0.01, + "learning_rate": 3.822290307089467e-05, + "loss": 3.6237, + "step": 719360 + }, + { + "epoch": 0.01, + "learning_rate": 3.8214533502187886e-05, + "loss": 3.643, + "step": 719872 + }, + { + "epoch": 0.01, + "learning_rate": 3.8206147554677366e-05, + "loss": 3.6396, + "step": 720384 + }, + { + "epoch": 0.01, + "learning_rate": 3.8197761607166846e-05, + "loss": 3.629, + "step": 720896 + }, + { + "epoch": 0.01, + "learning_rate": 3.8189375659656326e-05, + "loss": 3.6443, + "step": 721408 + }, + { + "epoch": 0.01, + "learning_rate": 3.8181006090949535e-05, + "loss": 3.6247, + "step": 721920 + }, + { + "epoch": 0.01, + "learning_rate": 3.8172620143439015e-05, + "loss": 3.6299, + "step": 722432 + }, + { + "epoch": 0.01, + "learning_rate": 3.8164234195928495e-05, + "loss": 3.6442, + "step": 722944 + }, + { + "epoch": 0.01, + "learning_rate": 3.8155848248417975e-05, + "loss": 3.635, + "step": 723456 + }, + { + "epoch": 0.01, + "learning_rate": 3.8147478679711184e-05, + "loss": 3.6544, + "step": 723968 + }, + { + "epoch": 0.01, + "learning_rate": 3.8139092732200664e-05, + "loss": 3.6376, + "step": 724480 + }, + { + "epoch": 0.01, + "learning_rate": 3.8130706784690144e-05, + "loss": 3.6503, + "step": 724992 + }, + { + "epoch": 0.01, + "learning_rate": 3.8122320837179624e-05, + "loss": 3.6339, + "step": 725504 + }, + { + "epoch": 0.01, + "learning_rate": 3.811395126847284e-05, + "loss": 3.6484, + "step": 726016 + }, + { + "epoch": 0.01, + "learning_rate": 3.810556532096232e-05, + "loss": 3.6321, + "step": 726528 + }, + { + "epoch": 0.01, + "learning_rate": 3.80971793734518e-05, + "loss": 3.633, + "step": 727040 + }, + { + "epoch": 0.01, + "learning_rate": 3.808879342594128e-05, + "loss": 3.6373, + "step": 727552 + }, + { + "epoch": 0.01, + "learning_rate": 3.808042385723449e-05, + "loss": 3.6407, + "step": 728064 + }, + { + "epoch": 0.01, + "learning_rate": 3.807203790972397e-05, + "loss": 3.64, + "step": 728576 + }, + { + "epoch": 0.01, + "learning_rate": 3.806365196221345e-05, + "loss": 3.6483, + "step": 729088 + }, + { + "epoch": 0.01, + "learning_rate": 3.805526601470293e-05, + "loss": 3.6245, + "step": 729600 + }, + { + "epoch": 0.01, + "learning_rate": 3.804689644599614e-05, + "loss": 3.6286, + "step": 730112 + }, + { + "epoch": 0.01, + "learning_rate": 3.803851049848562e-05, + "loss": 3.6413, + "step": 730624 + }, + { + "epoch": 0.01, + "learning_rate": 3.80301245509751e-05, + "loss": 3.6431, + "step": 731136 + }, + { + "epoch": 0.01, + "learning_rate": 3.802173860346458e-05, + "loss": 3.6383, + "step": 731648 + }, + { + "epoch": 0.01, + "learning_rate": 3.8013369034757786e-05, + "loss": 3.6447, + "step": 732160 + }, + { + "epoch": 0.02, + "learning_rate": 3.800498308724727e-05, + "loss": 3.6405, + "step": 732672 + }, + { + "epoch": 0.02, + "learning_rate": 3.799659713973675e-05, + "loss": 3.6411, + "step": 733184 + }, + { + "epoch": 0.02, + "learning_rate": 3.798821119222623e-05, + "loss": 3.6394, + "step": 733696 + }, + { + "epoch": 0.02, + "learning_rate": 3.797984162351944e-05, + "loss": 3.6287, + "step": 734208 + }, + { + "epoch": 0.02, + "learning_rate": 3.797145567600892e-05, + "loss": 3.6456, + "step": 734720 + }, + { + "epoch": 0.02, + "learning_rate": 3.79630697284984e-05, + "loss": 3.6468, + "step": 735232 + }, + { + "epoch": 0.02, + "learning_rate": 3.795468378098788e-05, + "loss": 3.6387, + "step": 735744 + }, + { + "epoch": 0.02, + "learning_rate": 3.794631421228109e-05, + "loss": 3.637, + "step": 736256 + }, + { + "epoch": 0.02, + "learning_rate": 3.793792826477057e-05, + "loss": 3.625, + "step": 736768 + }, + { + "epoch": 0.02, + "learning_rate": 3.792954231726005e-05, + "loss": 3.6366, + "step": 737280 + }, + { + "epoch": 0.02, + "learning_rate": 3.792115636974953e-05, + "loss": 3.6501, + "step": 737792 + }, + { + "epoch": 0.02, + "learning_rate": 3.791278680104274e-05, + "loss": 3.6363, + "step": 738304 + }, + { + "epoch": 0.02, + "learning_rate": 3.790440085353223e-05, + "loss": 3.6379, + "step": 738816 + }, + { + "epoch": 0.02, + "learning_rate": 3.789601490602171e-05, + "loss": 3.6306, + "step": 739328 + }, + { + "epoch": 0.02, + "learning_rate": 3.788762895851119e-05, + "loss": 3.63, + "step": 739840 + }, + { + "epoch": 0.02, + "learning_rate": 3.7879259389804396e-05, + "loss": 3.6353, + "step": 740352 + }, + { + "epoch": 0.02, + "learning_rate": 3.7870873442293876e-05, + "loss": 3.6293, + "step": 740864 + }, + { + "epoch": 0.02, + "learning_rate": 3.7862487494783356e-05, + "loss": 3.6273, + "step": 741376 + }, + { + "epoch": 0.02, + "learning_rate": 3.785410154727283e-05, + "loss": 3.6434, + "step": 741888 + }, + { + "epoch": 0.02, + "learning_rate": 3.7845731978566045e-05, + "loss": 3.6405, + "step": 742400 + }, + { + "epoch": 0.02, + "learning_rate": 3.7837346031055525e-05, + "loss": 3.6268, + "step": 742912 + }, + { + "epoch": 0.02, + "learning_rate": 3.7828960083545005e-05, + "loss": 3.6332, + "step": 743424 + }, + { + "epoch": 0.02, + "learning_rate": 3.782057413603448e-05, + "loss": 3.6339, + "step": 743936 + }, + { + "epoch": 0.02, + "learning_rate": 3.7812204567327694e-05, + "loss": 3.6416, + "step": 744448 + }, + { + "epoch": 0.02, + "learning_rate": 3.780381861981718e-05, + "loss": 3.6329, + "step": 744960 + }, + { + "epoch": 0.02, + "learning_rate": 3.779543267230666e-05, + "loss": 3.6422, + "step": 745472 + }, + { + "epoch": 0.02, + "learning_rate": 3.7787046724796134e-05, + "loss": 3.6431, + "step": 745984 + }, + { + "epoch": 0.02, + "learning_rate": 3.777867715608935e-05, + "loss": 3.6289, + "step": 746496 + }, + { + "epoch": 0.02, + "learning_rate": 3.777029120857883e-05, + "loss": 3.6373, + "step": 747008 + }, + { + "epoch": 0.02, + "learning_rate": 3.77619052610683e-05, + "loss": 3.6292, + "step": 747520 + }, + { + "epoch": 0.02, + "learning_rate": 3.775351931355778e-05, + "loss": 3.6321, + "step": 748032 + }, + { + "epoch": 0.02, + "learning_rate": 3.7745149744851e-05, + "loss": 3.6361, + "step": 748544 + }, + { + "epoch": 0.02, + "learning_rate": 3.773676379734048e-05, + "loss": 3.6251, + "step": 749056 + }, + { + "epoch": 0.02, + "learning_rate": 3.772837784982995e-05, + "loss": 3.6277, + "step": 749568 + }, + { + "epoch": 0.02, + "learning_rate": 3.771999190231943e-05, + "loss": 3.636, + "step": 750080 + }, + { + "epoch": 0.02, + "learning_rate": 3.771162233361265e-05, + "loss": 3.6373, + "step": 750592 + }, + { + "epoch": 0.02, + "learning_rate": 3.770325276490586e-05, + "loss": 3.6351, + "step": 751104 + }, + { + "epoch": 0.02, + "learning_rate": 3.769486681739534e-05, + "loss": 3.6224, + "step": 751616 + }, + { + "epoch": 0.02, + "learning_rate": 3.768648086988482e-05, + "loss": 3.6299, + "step": 752128 + }, + { + "epoch": 0.02, + "learning_rate": 3.76780949223743e-05, + "loss": 3.6307, + "step": 752640 + }, + { + "epoch": 0.02, + "learning_rate": 3.7669708974863776e-05, + "loss": 3.6428, + "step": 753152 + }, + { + "epoch": 0.02, + "learning_rate": 3.7661323027353256e-05, + "loss": 3.6366, + "step": 753664 + }, + { + "epoch": 0.02, + "learning_rate": 3.7652937079842736e-05, + "loss": 3.6347, + "step": 754176 + }, + { + "epoch": 0.02, + "learning_rate": 3.7644551132332216e-05, + "loss": 3.6221, + "step": 754688 + }, + { + "epoch": 0.02, + "learning_rate": 3.7636181563625425e-05, + "loss": 3.6434, + "step": 755200 + }, + { + "epoch": 0.02, + "learning_rate": 3.7627795616114905e-05, + "loss": 3.6341, + "step": 755712 + }, + { + "epoch": 0.02, + "learning_rate": 3.7619409668604385e-05, + "loss": 3.6411, + "step": 756224 + }, + { + "epoch": 0.02, + "learning_rate": 3.761102372109387e-05, + "loss": 3.6352, + "step": 756736 + }, + { + "epoch": 0.02, + "learning_rate": 3.760265415238708e-05, + "loss": 3.6395, + "step": 757248 + }, + { + "epoch": 0.02, + "learning_rate": 3.759426820487656e-05, + "loss": 3.6355, + "step": 757760 + }, + { + "epoch": 0.02, + "learning_rate": 3.758588225736604e-05, + "loss": 3.6483, + "step": 758272 + }, + { + "epoch": 0.02, + "learning_rate": 3.757749630985552e-05, + "loss": 3.6207, + "step": 758784 + }, + { + "epoch": 0.02, + "learning_rate": 3.756912674114873e-05, + "loss": 3.6379, + "step": 759296 + }, + { + "epoch": 0.02, + "learning_rate": 3.756074079363821e-05, + "loss": 3.6265, + "step": 759808 + }, + { + "epoch": 0.02, + "learning_rate": 3.755235484612769e-05, + "loss": 3.6326, + "step": 760320 + }, + { + "epoch": 0.02, + "learning_rate": 3.754396889861717e-05, + "loss": 3.6259, + "step": 760832 + }, + { + "epoch": 0.02, + "learning_rate": 3.753559932991038e-05, + "loss": 3.6278, + "step": 761344 + }, + { + "epoch": 0.02, + "learning_rate": 3.752721338239986e-05, + "loss": 3.6322, + "step": 761856 + }, + { + "epoch": 0.02, + "learning_rate": 3.751882743488934e-05, + "loss": 3.6302, + "step": 762368 + }, + { + "epoch": 0.02, + "learning_rate": 3.7510441487378826e-05, + "loss": 3.6398, + "step": 762880 + }, + { + "epoch": 0.03, + "eval_loss": 3.8437931537628174, + "eval_runtime": 302.5204, + "eval_samples_per_second": 1261.373, + "eval_steps_per_second": 39.419, + "step": 763200 + }, + { + "epoch": 1.0, + "learning_rate": 3.7502071918672035e-05, + "loss": 3.6246, + "step": 763392 + }, + { + "epoch": 1.0, + "learning_rate": 3.7493685971161515e-05, + "loss": 3.6244, + "step": 763904 + }, + { + "epoch": 1.0, + "learning_rate": 3.7485300023650995e-05, + "loss": 3.6213, + "step": 764416 + }, + { + "epoch": 1.0, + "learning_rate": 3.7476914076140475e-05, + "loss": 3.6408, + "step": 764928 + }, + { + "epoch": 1.0, + "learning_rate": 3.7468544507433684e-05, + "loss": 3.6402, + "step": 765440 + }, + { + "epoch": 1.0, + "learning_rate": 3.7460158559923164e-05, + "loss": 3.6204, + "step": 765952 + }, + { + "epoch": 1.0, + "learning_rate": 3.7451772612412644e-05, + "loss": 3.6275, + "step": 766464 + }, + { + "epoch": 1.0, + "learning_rate": 3.7443386664902124e-05, + "loss": 3.6246, + "step": 766976 + }, + { + "epoch": 1.0, + "learning_rate": 3.743501709619533e-05, + "loss": 3.6311, + "step": 767488 + }, + { + "epoch": 1.0, + "learning_rate": 3.742663114868481e-05, + "loss": 3.6383, + "step": 768000 + }, + { + "epoch": 1.0, + "learning_rate": 3.741824520117429e-05, + "loss": 3.6244, + "step": 768512 + }, + { + "epoch": 1.0, + "learning_rate": 3.740985925366378e-05, + "loss": 3.6268, + "step": 769024 + }, + { + "epoch": 1.0, + "learning_rate": 3.740148968495699e-05, + "loss": 3.6332, + "step": 769536 + }, + { + "epoch": 1.0, + "learning_rate": 3.739310373744647e-05, + "loss": 3.6133, + "step": 770048 + }, + { + "epoch": 1.0, + "learning_rate": 3.738471778993595e-05, + "loss": 3.6238, + "step": 770560 + }, + { + "epoch": 1.0, + "learning_rate": 3.737633184242543e-05, + "loss": 3.6148, + "step": 771072 + }, + { + "epoch": 1.0, + "learning_rate": 3.736796227371864e-05, + "loss": 3.6264, + "step": 771584 + }, + { + "epoch": 1.0, + "learning_rate": 3.735957632620812e-05, + "loss": 3.6274, + "step": 772096 + }, + { + "epoch": 1.0, + "learning_rate": 3.73511903786976e-05, + "loss": 3.617, + "step": 772608 + }, + { + "epoch": 1.0, + "learning_rate": 3.734280443118708e-05, + "loss": 3.6366, + "step": 773120 + }, + { + "epoch": 1.0, + "learning_rate": 3.7334434862480286e-05, + "loss": 3.639, + "step": 773632 + }, + { + "epoch": 1.0, + "learning_rate": 3.7326048914969766e-05, + "loss": 3.6268, + "step": 774144 + }, + { + "epoch": 1.0, + "learning_rate": 3.7317662967459246e-05, + "loss": 3.6312, + "step": 774656 + }, + { + "epoch": 1.0, + "learning_rate": 3.730927701994873e-05, + "loss": 3.6288, + "step": 775168 + }, + { + "epoch": 1.0, + "learning_rate": 3.730090745124194e-05, + "loss": 3.6295, + "step": 775680 + }, + { + "epoch": 1.0, + "learning_rate": 3.729252150373142e-05, + "loss": 3.6233, + "step": 776192 + }, + { + "epoch": 1.0, + "learning_rate": 3.72841355562209e-05, + "loss": 3.6255, + "step": 776704 + }, + { + "epoch": 1.0, + "learning_rate": 3.727574960871038e-05, + "loss": 3.6278, + "step": 777216 + }, + { + "epoch": 1.0, + "learning_rate": 3.726738004000359e-05, + "loss": 3.6146, + "step": 777728 + }, + { + "epoch": 1.0, + "learning_rate": 3.725899409249307e-05, + "loss": 3.6228, + "step": 778240 + }, + { + "epoch": 1.01, + "learning_rate": 3.725060814498255e-05, + "loss": 3.6289, + "step": 778752 + }, + { + "epoch": 1.01, + "learning_rate": 3.724222219747203e-05, + "loss": 3.6313, + "step": 779264 + }, + { + "epoch": 1.01, + "learning_rate": 3.723385262876524e-05, + "loss": 3.6389, + "step": 779776 + }, + { + "epoch": 1.01, + "learning_rate": 3.722546668125472e-05, + "loss": 3.6265, + "step": 780288 + }, + { + "epoch": 1.01, + "learning_rate": 3.72170807337442e-05, + "loss": 3.6198, + "step": 780800 + }, + { + "epoch": 1.01, + "learning_rate": 3.720869478623368e-05, + "loss": 3.6242, + "step": 781312 + }, + { + "epoch": 1.01, + "learning_rate": 3.7200325217526896e-05, + "loss": 3.6298, + "step": 781824 + }, + { + "epoch": 1.01, + "learning_rate": 3.7191939270016376e-05, + "loss": 3.6143, + "step": 782336 + }, + { + "epoch": 1.01, + "learning_rate": 3.7183553322505856e-05, + "loss": 3.6162, + "step": 782848 + }, + { + "epoch": 1.01, + "learning_rate": 3.7175167374995336e-05, + "loss": 3.6206, + "step": 783360 + }, + { + "epoch": 1.01, + "learning_rate": 3.7166797806288545e-05, + "loss": 3.6159, + "step": 783872 + }, + { + "epoch": 1.01, + "learning_rate": 3.7158411858778025e-05, + "loss": 3.6264, + "step": 784384 + }, + { + "epoch": 1.01, + "learning_rate": 3.7150025911267505e-05, + "loss": 3.6274, + "step": 784896 + }, + { + "epoch": 1.01, + "learning_rate": 3.7141639963756985e-05, + "loss": 3.6283, + "step": 785408 + }, + { + "epoch": 1.01, + "learning_rate": 3.7133270395050194e-05, + "loss": 3.6202, + "step": 785920 + }, + { + "epoch": 1.01, + "learning_rate": 3.7124884447539674e-05, + "loss": 3.628, + "step": 786432 + }, + { + "epoch": 1.01, + "learning_rate": 3.7116498500029154e-05, + "loss": 3.6217, + "step": 786944 + }, + { + "epoch": 1.01, + "learning_rate": 3.7108112552518634e-05, + "loss": 3.6289, + "step": 787456 + }, + { + "epoch": 1.01, + "learning_rate": 3.709974298381185e-05, + "loss": 3.5985, + "step": 787968 + }, + { + "epoch": 1.01, + "learning_rate": 3.709135703630133e-05, + "loss": 3.6281, + "step": 788480 + }, + { + "epoch": 1.01, + "learning_rate": 3.708297108879081e-05, + "loss": 3.6187, + "step": 788992 + }, + { + "epoch": 1.01, + "learning_rate": 3.707458514128029e-05, + "loss": 3.632, + "step": 789504 + }, + { + "epoch": 1.01, + "learning_rate": 3.70662155725735e-05, + "loss": 3.6167, + "step": 790016 + }, + { + "epoch": 1.01, + "learning_rate": 3.705782962506298e-05, + "loss": 3.6141, + "step": 790528 + }, + { + "epoch": 1.01, + "learning_rate": 3.704944367755246e-05, + "loss": 3.6107, + "step": 791040 + }, + { + "epoch": 1.01, + "learning_rate": 3.704105773004194e-05, + "loss": 3.6182, + "step": 791552 + }, + { + "epoch": 1.01, + "learning_rate": 3.703268816133515e-05, + "loss": 3.6278, + "step": 792064 + }, + { + "epoch": 1.01, + "learning_rate": 3.702430221382463e-05, + "loss": 3.6056, + "step": 792576 + }, + { + "epoch": 1.01, + "learning_rate": 3.701591626631411e-05, + "loss": 3.6306, + "step": 793088 + }, + { + "epoch": 1.01, + "learning_rate": 3.700753031880359e-05, + "loss": 3.6179, + "step": 793600 + }, + { + "epoch": 1.01, + "learning_rate": 3.69991607500968e-05, + "loss": 3.5962, + "step": 794112 + }, + { + "epoch": 1.01, + "learning_rate": 3.699077480258628e-05, + "loss": 3.6311, + "step": 794624 + }, + { + "epoch": 1.01, + "learning_rate": 3.698238885507576e-05, + "loss": 3.6091, + "step": 795136 + }, + { + "epoch": 1.01, + "learning_rate": 3.697400290756524e-05, + "loss": 3.6018, + "step": 795648 + }, + { + "epoch": 1.01, + "learning_rate": 3.696563333885845e-05, + "loss": 3.6214, + "step": 796160 + }, + { + "epoch": 1.01, + "learning_rate": 3.695724739134793e-05, + "loss": 3.6153, + "step": 796672 + }, + { + "epoch": 1.01, + "learning_rate": 3.694886144383741e-05, + "loss": 3.6057, + "step": 797184 + }, + { + "epoch": 1.01, + "learning_rate": 3.694049187513062e-05, + "loss": 3.6247, + "step": 797696 + }, + { + "epoch": 1.01, + "learning_rate": 3.69321059276201e-05, + "loss": 3.5999, + "step": 798208 + }, + { + "epoch": 1.01, + "learning_rate": 3.692371998010958e-05, + "loss": 3.6075, + "step": 798720 + }, + { + "epoch": 1.01, + "learning_rate": 3.691533403259906e-05, + "loss": 3.6221, + "step": 799232 + }, + { + "epoch": 1.01, + "learning_rate": 3.690696446389228e-05, + "loss": 3.6167, + "step": 799744 + }, + { + "epoch": 1.01, + "learning_rate": 3.689857851638176e-05, + "loss": 3.6268, + "step": 800256 + }, + { + "epoch": 1.01, + "learning_rate": 3.689019256887124e-05, + "loss": 3.6166, + "step": 800768 + }, + { + "epoch": 1.01, + "learning_rate": 3.688180662136072e-05, + "loss": 3.6278, + "step": 801280 + }, + { + "epoch": 1.01, + "learning_rate": 3.6873437052653926e-05, + "loss": 3.6117, + "step": 801792 + }, + { + "epoch": 1.01, + "learning_rate": 3.6865051105143406e-05, + "loss": 3.6288, + "step": 802304 + }, + { + "epoch": 1.01, + "learning_rate": 3.6856665157632886e-05, + "loss": 3.607, + "step": 802816 + }, + { + "epoch": 1.01, + "learning_rate": 3.6848279210122366e-05, + "loss": 3.6111, + "step": 803328 + }, + { + "epoch": 1.01, + "learning_rate": 3.6839909641415575e-05, + "loss": 3.6177, + "step": 803840 + }, + { + "epoch": 1.01, + "learning_rate": 3.6831523693905055e-05, + "loss": 3.6149, + "step": 804352 + }, + { + "epoch": 1.01, + "learning_rate": 3.6823137746394535e-05, + "loss": 3.6226, + "step": 804864 + }, + { + "epoch": 1.01, + "learning_rate": 3.6814751798884015e-05, + "loss": 3.6251, + "step": 805376 + }, + { + "epoch": 1.01, + "learning_rate": 3.680638223017723e-05, + "loss": 3.6091, + "step": 805888 + }, + { + "epoch": 1.01, + "learning_rate": 3.679799628266671e-05, + "loss": 3.6061, + "step": 806400 + }, + { + "epoch": 1.01, + "learning_rate": 3.678961033515619e-05, + "loss": 3.6153, + "step": 806912 + }, + { + "epoch": 1.01, + "learning_rate": 3.678122438764567e-05, + "loss": 3.6244, + "step": 807424 + }, + { + "epoch": 1.01, + "learning_rate": 3.677285481893888e-05, + "loss": 3.6133, + "step": 807936 + }, + { + "epoch": 1.01, + "learning_rate": 3.676446887142836e-05, + "loss": 3.6234, + "step": 808448 + }, + { + "epoch": 1.01, + "learning_rate": 3.675608292391784e-05, + "loss": 3.6204, + "step": 808960 + }, + { + "epoch": 1.02, + "learning_rate": 3.674769697640732e-05, + "loss": 3.6216, + "step": 809472 + }, + { + "epoch": 1.02, + "learning_rate": 3.673932740770053e-05, + "loss": 3.615, + "step": 809984 + }, + { + "epoch": 1.02, + "learning_rate": 3.673094146019001e-05, + "loss": 3.6081, + "step": 810496 + }, + { + "epoch": 1.02, + "learning_rate": 3.672255551267949e-05, + "loss": 3.6224, + "step": 811008 + }, + { + "epoch": 1.02, + "learning_rate": 3.671416956516897e-05, + "loss": 3.6222, + "step": 811520 + }, + { + "epoch": 1.02, + "learning_rate": 3.6705799996462184e-05, + "loss": 3.6221, + "step": 812032 + }, + { + "epoch": 1.02, + "learning_rate": 3.6697414048951664e-05, + "loss": 3.612, + "step": 812544 + }, + { + "epoch": 1.02, + "learning_rate": 3.6689028101441144e-05, + "loss": 3.6049, + "step": 813056 + }, + { + "epoch": 1.02, + "learning_rate": 3.6680642153930624e-05, + "loss": 3.6161, + "step": 813568 + }, + { + "epoch": 1.02, + "learning_rate": 3.667227258522383e-05, + "loss": 3.6273, + "step": 814080 + }, + { + "epoch": 1.02, + "learning_rate": 3.666388663771331e-05, + "loss": 3.6148, + "step": 814592 + }, + { + "epoch": 1.02, + "learning_rate": 3.665550069020279e-05, + "loss": 3.6167, + "step": 815104 + }, + { + "epoch": 1.02, + "learning_rate": 3.664711474269227e-05, + "loss": 3.6116, + "step": 815616 + }, + { + "epoch": 1.02, + "learning_rate": 3.663874517398548e-05, + "loss": 3.6074, + "step": 816128 + }, + { + "epoch": 1.02, + "learning_rate": 3.663035922647496e-05, + "loss": 3.6165, + "step": 816640 + }, + { + "epoch": 1.02, + "learning_rate": 3.662197327896444e-05, + "loss": 3.6035, + "step": 817152 + }, + { + "epoch": 1.02, + "learning_rate": 3.661358733145392e-05, + "loss": 3.609, + "step": 817664 + }, + { + "epoch": 1.02, + "learning_rate": 3.660521776274714e-05, + "loss": 3.6187, + "step": 818176 + }, + { + "epoch": 1.02, + "learning_rate": 3.659683181523662e-05, + "loss": 3.6201, + "step": 818688 + }, + { + "epoch": 1.02, + "learning_rate": 3.65884458677261e-05, + "loss": 3.6093, + "step": 819200 + }, + { + "epoch": 1.02, + "learning_rate": 3.658005992021557e-05, + "loss": 3.6085, + "step": 819712 + }, + { + "epoch": 1.02, + "learning_rate": 3.657169035150879e-05, + "loss": 3.6092, + "step": 820224 + }, + { + "epoch": 1.02, + "learning_rate": 3.656330440399827e-05, + "loss": 3.6225, + "step": 820736 + }, + { + "epoch": 1.02, + "learning_rate": 3.655491845648775e-05, + "loss": 3.6105, + "step": 821248 + }, + { + "epoch": 1.02, + "learning_rate": 3.654653250897722e-05, + "loss": 3.6225, + "step": 821760 + }, + { + "epoch": 1.02, + "learning_rate": 3.6538162940270436e-05, + "loss": 3.6189, + "step": 822272 + }, + { + "epoch": 1.02, + "learning_rate": 3.6529776992759916e-05, + "loss": 3.6131, + "step": 822784 + }, + { + "epoch": 1.02, + "learning_rate": 3.6521391045249396e-05, + "loss": 3.6118, + "step": 823296 + }, + { + "epoch": 1.02, + "learning_rate": 3.6513005097738876e-05, + "loss": 3.6116, + "step": 823808 + }, + { + "epoch": 1.02, + "learning_rate": 3.650463552903209e-05, + "loss": 3.6091, + "step": 824320 + }, + { + "epoch": 1.02, + "learning_rate": 3.649624958152157e-05, + "loss": 3.6174, + "step": 824832 + }, + { + "epoch": 1.02, + "learning_rate": 3.6487863634011045e-05, + "loss": 3.6012, + "step": 825344 + }, + { + "epoch": 1.02, + "learning_rate": 3.6479477686500525e-05, + "loss": 3.6039, + "step": 825856 + }, + { + "epoch": 1.02, + "learning_rate": 3.647110811779374e-05, + "loss": 3.6115, + "step": 826368 + }, + { + "epoch": 1.02, + "learning_rate": 3.646272217028322e-05, + "loss": 3.616, + "step": 826880 + }, + { + "epoch": 1.02, + "learning_rate": 3.6454336222772694e-05, + "loss": 3.61, + "step": 827392 + }, + { + "epoch": 1.02, + "learning_rate": 3.6445950275262173e-05, + "loss": 3.6029, + "step": 827904 + }, + { + "epoch": 1.02, + "learning_rate": 3.643758070655539e-05, + "loss": 3.6099, + "step": 828416 + }, + { + "epoch": 1.02, + "learning_rate": 3.642919475904487e-05, + "loss": 3.6069, + "step": 828928 + }, + { + "epoch": 1.02, + "learning_rate": 3.642080881153435e-05, + "loss": 3.6248, + "step": 829440 + }, + { + "epoch": 1.02, + "learning_rate": 3.641242286402383e-05, + "loss": 3.6124, + "step": 829952 + }, + { + "epoch": 1.02, + "learning_rate": 3.6404053295317045e-05, + "loss": 3.6158, + "step": 830464 + }, + { + "epoch": 1.02, + "learning_rate": 3.639566734780652e-05, + "loss": 3.6004, + "step": 830976 + }, + { + "epoch": 1.02, + "learning_rate": 3.6387281400296e-05, + "loss": 3.6207, + "step": 831488 + }, + { + "epoch": 1.02, + "learning_rate": 3.637889545278548e-05, + "loss": 3.6116, + "step": 832000 + }, + { + "epoch": 1.02, + "learning_rate": 3.6370525884078694e-05, + "loss": 3.6198, + "step": 832512 + }, + { + "epoch": 1.02, + "learning_rate": 3.636213993656817e-05, + "loss": 3.6192, + "step": 833024 + }, + { + "epoch": 1.02, + "learning_rate": 3.635375398905765e-05, + "loss": 3.6166, + "step": 833536 + }, + { + "epoch": 1.02, + "learning_rate": 3.634536804154713e-05, + "loss": 3.6116, + "step": 834048 + }, + { + "epoch": 1.02, + "learning_rate": 3.633699847284034e-05, + "loss": 3.6285, + "step": 834560 + }, + { + "epoch": 1.02, + "learning_rate": 3.6328612525329816e-05, + "loss": 3.6006, + "step": 835072 + }, + { + "epoch": 1.02, + "learning_rate": 3.63202265778193e-05, + "loss": 3.6163, + "step": 835584 + }, + { + "epoch": 1.02, + "learning_rate": 3.631184063030878e-05, + "loss": 3.6072, + "step": 836096 + }, + { + "epoch": 1.02, + "learning_rate": 3.630347106160199e-05, + "loss": 3.6115, + "step": 836608 + }, + { + "epoch": 1.02, + "learning_rate": 3.629508511409147e-05, + "loss": 3.6052, + "step": 837120 + }, + { + "epoch": 1.02, + "learning_rate": 3.628669916658095e-05, + "loss": 3.6064, + "step": 837632 + }, + { + "epoch": 1.02, + "learning_rate": 3.627831321907043e-05, + "loss": 3.6069, + "step": 838144 + }, + { + "epoch": 1.02, + "learning_rate": 3.626994365036364e-05, + "loss": 3.6156, + "step": 838656 + }, + { + "epoch": 1.02, + "learning_rate": 3.626155770285312e-05, + "loss": 3.6126, + "step": 839168 + }, + { + "epoch": 1.03, + "eval_loss": 3.8424277305603027, + "eval_runtime": 303.9128, + "eval_samples_per_second": 1255.594, + "eval_steps_per_second": 39.238, + "step": 839520 + }, + { + "epoch": 0.0, + "learning_rate": 3.62531717553426e-05, + "loss": 3.6021, + "step": 839680 + }, + { + "epoch": 0.0, + "learning_rate": 3.624478580783208e-05, + "loss": 3.5999, + "step": 840192 + }, + { + "epoch": 0.0, + "learning_rate": 3.623639986032156e-05, + "loss": 3.5994, + "step": 840704 + }, + { + "epoch": 0.0, + "learning_rate": 3.622801391281104e-05, + "loss": 3.6201, + "step": 841216 + }, + { + "epoch": 0.0, + "learning_rate": 3.6219644344104257e-05, + "loss": 3.6177, + "step": 841728 + }, + { + "epoch": 0.0, + "learning_rate": 3.6211258396593737e-05, + "loss": 3.6007, + "step": 842240 + }, + { + "epoch": 0.0, + "learning_rate": 3.6202872449083217e-05, + "loss": 3.6072, + "step": 842752 + }, + { + "epoch": 0.0, + "learning_rate": 3.6194486501572696e-05, + "loss": 3.6034, + "step": 843264 + }, + { + "epoch": 0.0, + "learning_rate": 3.6186116932865906e-05, + "loss": 3.6079, + "step": 843776 + }, + { + "epoch": 0.0, + "learning_rate": 3.6177730985355386e-05, + "loss": 3.6114, + "step": 844288 + }, + { + "epoch": 0.0, + "learning_rate": 3.6169345037844865e-05, + "loss": 3.6093, + "step": 844800 + }, + { + "epoch": 0.0, + "learning_rate": 3.6160959090334345e-05, + "loss": 3.6052, + "step": 845312 + }, + { + "epoch": 0.0, + "learning_rate": 3.6152589521627555e-05, + "loss": 3.6129, + "step": 845824 + }, + { + "epoch": 0.0, + "learning_rate": 3.6144203574117034e-05, + "loss": 3.5915, + "step": 846336 + }, + { + "epoch": 0.0, + "learning_rate": 3.6135817626606514e-05, + "loss": 3.6014, + "step": 846848 + }, + { + "epoch": 0.0, + "learning_rate": 3.6127431679095994e-05, + "loss": 3.5911, + "step": 847360 + }, + { + "epoch": 0.0, + "learning_rate": 3.6119062110389203e-05, + "loss": 3.6089, + "step": 847872 + }, + { + "epoch": 0.0, + "learning_rate": 3.611067616287869e-05, + "loss": 3.6073, + "step": 848384 + }, + { + "epoch": 0.0, + "learning_rate": 3.610229021536817e-05, + "loss": 3.5917, + "step": 848896 + }, + { + "epoch": 0.0, + "learning_rate": 3.609390426785765e-05, + "loss": 3.6131, + "step": 849408 + }, + { + "epoch": 0.0, + "learning_rate": 3.608553469915086e-05, + "loss": 3.6209, + "step": 849920 + }, + { + "epoch": 0.0, + "learning_rate": 3.607714875164034e-05, + "loss": 3.6057, + "step": 850432 + }, + { + "epoch": 0.0, + "learning_rate": 3.606876280412982e-05, + "loss": 3.6134, + "step": 850944 + }, + { + "epoch": 0.0, + "learning_rate": 3.60603768566193e-05, + "loss": 3.6103, + "step": 851456 + }, + { + "epoch": 0.0, + "learning_rate": 3.605200728791251e-05, + "loss": 3.6085, + "step": 851968 + }, + { + "epoch": 0.0, + "learning_rate": 3.604362134040199e-05, + "loss": 3.6035, + "step": 852480 + }, + { + "epoch": 0.0, + "learning_rate": 3.603523539289147e-05, + "loss": 3.6019, + "step": 852992 + }, + { + "epoch": 0.0, + "learning_rate": 3.602684944538095e-05, + "loss": 3.6071, + "step": 853504 + }, + { + "epoch": 0.0, + "learning_rate": 3.601847987667416e-05, + "loss": 3.5974, + "step": 854016 + }, + { + "epoch": 0.0, + "learning_rate": 3.6010093929163644e-05, + "loss": 3.603, + "step": 854528 + }, + { + "epoch": 0.01, + "learning_rate": 3.6001707981653124e-05, + "loss": 3.6087, + "step": 855040 + }, + { + "epoch": 0.01, + "learning_rate": 3.5993322034142604e-05, + "loss": 3.6139, + "step": 855552 + }, + { + "epoch": 0.01, + "learning_rate": 3.598495246543581e-05, + "loss": 3.6091, + "step": 856064 + }, + { + "epoch": 0.01, + "learning_rate": 3.597656651792529e-05, + "loss": 3.6141, + "step": 856576 + }, + { + "epoch": 0.01, + "learning_rate": 3.596818057041477e-05, + "loss": 3.5942, + "step": 857088 + }, + { + "epoch": 0.01, + "learning_rate": 3.595979462290425e-05, + "loss": 3.6053, + "step": 857600 + }, + { + "epoch": 0.01, + "learning_rate": 3.595142505419746e-05, + "loss": 3.6127, + "step": 858112 + }, + { + "epoch": 0.01, + "learning_rate": 3.594303910668694e-05, + "loss": 3.5895, + "step": 858624 + }, + { + "epoch": 0.01, + "learning_rate": 3.593465315917642e-05, + "loss": 3.5987, + "step": 859136 + }, + { + "epoch": 0.01, + "learning_rate": 3.59262672116659e-05, + "loss": 3.6023, + "step": 859648 + }, + { + "epoch": 0.01, + "learning_rate": 3.591789764295911e-05, + "loss": 3.5962, + "step": 860160 + }, + { + "epoch": 0.01, + "learning_rate": 3.59095116954486e-05, + "loss": 3.6021, + "step": 860672 + }, + { + "epoch": 0.01, + "learning_rate": 3.590112574793808e-05, + "loss": 3.609, + "step": 861184 + }, + { + "epoch": 0.01, + "learning_rate": 3.589273980042756e-05, + "loss": 3.6065, + "step": 861696 + }, + { + "epoch": 0.01, + "learning_rate": 3.5884370231720767e-05, + "loss": 3.603, + "step": 862208 + }, + { + "epoch": 0.01, + "learning_rate": 3.5875984284210247e-05, + "loss": 3.6063, + "step": 862720 + }, + { + "epoch": 0.01, + "learning_rate": 3.5867598336699726e-05, + "loss": 3.5995, + "step": 863232 + }, + { + "epoch": 0.01, + "learning_rate": 3.5859212389189206e-05, + "loss": 3.6086, + "step": 863744 + }, + { + "epoch": 0.01, + "learning_rate": 3.5850842820482416e-05, + "loss": 3.5837, + "step": 864256 + }, + { + "epoch": 0.01, + "learning_rate": 3.5842456872971895e-05, + "loss": 3.6057, + "step": 864768 + }, + { + "epoch": 0.01, + "learning_rate": 3.5834070925461375e-05, + "loss": 3.5948, + "step": 865280 + }, + { + "epoch": 0.01, + "learning_rate": 3.5825684977950855e-05, + "loss": 3.6122, + "step": 865792 + }, + { + "epoch": 0.01, + "learning_rate": 3.5817315409244064e-05, + "loss": 3.5975, + "step": 866304 + }, + { + "epoch": 0.01, + "learning_rate": 3.580892946173355e-05, + "loss": 3.5927, + "step": 866816 + }, + { + "epoch": 0.01, + "learning_rate": 3.580054351422303e-05, + "loss": 3.5919, + "step": 867328 + }, + { + "epoch": 0.01, + "learning_rate": 3.579215756671251e-05, + "loss": 3.6004, + "step": 867840 + }, + { + "epoch": 0.01, + "learning_rate": 3.578378799800572e-05, + "loss": 3.6082, + "step": 868352 + }, + { + "epoch": 0.01, + "learning_rate": 3.57754020504952e-05, + "loss": 3.5861, + "step": 868864 + }, + { + "epoch": 0.01, + "learning_rate": 3.576701610298468e-05, + "loss": 3.6098, + "step": 869376 + }, + { + "epoch": 0.01, + "learning_rate": 3.575864653427789e-05, + "loss": 3.6014, + "step": 869888 + }, + { + "epoch": 0.01, + "learning_rate": 3.575026058676737e-05, + "loss": 3.5749, + "step": 870400 + }, + { + "epoch": 0.01, + "learning_rate": 3.574187463925685e-05, + "loss": 3.6095, + "step": 870912 + }, + { + "epoch": 0.01, + "learning_rate": 3.573348869174633e-05, + "loss": 3.5885, + "step": 871424 + }, + { + "epoch": 0.01, + "learning_rate": 3.572511912303954e-05, + "loss": 3.5826, + "step": 871936 + }, + { + "epoch": 0.01, + "learning_rate": 3.571673317552902e-05, + "loss": 3.5987, + "step": 872448 + }, + { + "epoch": 0.01, + "learning_rate": 3.5708347228018505e-05, + "loss": 3.5972, + "step": 872960 + }, + { + "epoch": 0.01, + "learning_rate": 3.5699961280507985e-05, + "loss": 3.5892, + "step": 873472 + }, + { + "epoch": 0.01, + "learning_rate": 3.5691591711801194e-05, + "loss": 3.604, + "step": 873984 + }, + { + "epoch": 0.01, + "learning_rate": 3.5683205764290674e-05, + "loss": 3.5769, + "step": 874496 + }, + { + "epoch": 0.01, + "learning_rate": 3.5674819816780154e-05, + "loss": 3.5868, + "step": 875008 + }, + { + "epoch": 0.01, + "learning_rate": 3.5666433869269634e-05, + "loss": 3.6039, + "step": 875520 + }, + { + "epoch": 0.01, + "learning_rate": 3.565806430056284e-05, + "loss": 3.5993, + "step": 876032 + }, + { + "epoch": 0.01, + "learning_rate": 3.564967835305232e-05, + "loss": 3.6037, + "step": 876544 + }, + { + "epoch": 0.01, + "learning_rate": 3.56412924055418e-05, + "loss": 3.5981, + "step": 877056 + }, + { + "epoch": 0.01, + "learning_rate": 3.563290645803128e-05, + "loss": 3.6043, + "step": 877568 + }, + { + "epoch": 0.01, + "learning_rate": 3.562453688932449e-05, + "loss": 3.5928, + "step": 878080 + }, + { + "epoch": 0.01, + "learning_rate": 3.561615094181397e-05, + "loss": 3.6097, + "step": 878592 + }, + { + "epoch": 0.01, + "learning_rate": 3.560776499430346e-05, + "loss": 3.5918, + "step": 879104 + }, + { + "epoch": 0.01, + "learning_rate": 3.559937904679294e-05, + "loss": 3.5898, + "step": 879616 + }, + { + "epoch": 0.01, + "learning_rate": 3.559100947808615e-05, + "loss": 3.5947, + "step": 880128 + }, + { + "epoch": 0.01, + "learning_rate": 3.558262353057563e-05, + "loss": 3.5971, + "step": 880640 + }, + { + "epoch": 0.01, + "learning_rate": 3.557423758306511e-05, + "loss": 3.6016, + "step": 881152 + }, + { + "epoch": 0.01, + "learning_rate": 3.556585163555459e-05, + "loss": 3.6064, + "step": 881664 + }, + { + "epoch": 0.01, + "learning_rate": 3.5557482066847797e-05, + "loss": 3.5901, + "step": 882176 + }, + { + "epoch": 0.01, + "learning_rate": 3.5549096119337277e-05, + "loss": 3.5841, + "step": 882688 + }, + { + "epoch": 0.01, + "learning_rate": 3.5540710171826756e-05, + "loss": 3.5976, + "step": 883200 + }, + { + "epoch": 0.01, + "learning_rate": 3.5532324224316236e-05, + "loss": 3.6057, + "step": 883712 + }, + { + "epoch": 0.01, + "learning_rate": 3.5523954655609446e-05, + "loss": 3.5935, + "step": 884224 + }, + { + "epoch": 0.01, + "learning_rate": 3.5515568708098925e-05, + "loss": 3.6016, + "step": 884736 + }, + { + "epoch": 0.01, + "learning_rate": 3.550718276058841e-05, + "loss": 3.6036, + "step": 885248 + }, + { + "epoch": 0.02, + "learning_rate": 3.549879681307789e-05, + "loss": 3.5991, + "step": 885760 + }, + { + "epoch": 0.02, + "learning_rate": 3.54904272443711e-05, + "loss": 3.5962, + "step": 886272 + }, + { + "epoch": 0.02, + "learning_rate": 3.548204129686058e-05, + "loss": 3.5884, + "step": 886784 + }, + { + "epoch": 0.02, + "learning_rate": 3.547365534935006e-05, + "loss": 3.604, + "step": 887296 + }, + { + "epoch": 0.02, + "learning_rate": 3.546526940183954e-05, + "loss": 3.6029, + "step": 887808 + }, + { + "epoch": 0.02, + "learning_rate": 3.545689983313275e-05, + "loss": 3.6001, + "step": 888320 + }, + { + "epoch": 0.02, + "learning_rate": 3.544851388562223e-05, + "loss": 3.594, + "step": 888832 + }, + { + "epoch": 0.02, + "learning_rate": 3.544012793811171e-05, + "loss": 3.5835, + "step": 889344 + }, + { + "epoch": 0.02, + "learning_rate": 3.543174199060119e-05, + "loss": 3.5953, + "step": 889856 + }, + { + "epoch": 0.02, + "learning_rate": 3.54233724218944e-05, + "loss": 3.6063, + "step": 890368 + }, + { + "epoch": 0.02, + "learning_rate": 3.541498647438388e-05, + "loss": 3.5945, + "step": 890880 + }, + { + "epoch": 0.02, + "learning_rate": 3.540660052687336e-05, + "loss": 3.5964, + "step": 891392 + }, + { + "epoch": 0.02, + "learning_rate": 3.5398214579362846e-05, + "loss": 3.5915, + "step": 891904 + }, + { + "epoch": 0.02, + "learning_rate": 3.5389845010656055e-05, + "loss": 3.5921, + "step": 892416 + }, + { + "epoch": 0.02, + "learning_rate": 3.5381459063145535e-05, + "loss": 3.5933, + "step": 892928 + }, + { + "epoch": 0.02, + "learning_rate": 3.5373073115635015e-05, + "loss": 3.5891, + "step": 893440 + }, + { + "epoch": 0.02, + "learning_rate": 3.536468716812449e-05, + "loss": 3.5866, + "step": 893952 + }, + { + "epoch": 0.02, + "learning_rate": 3.5356317599417704e-05, + "loss": 3.6007, + "step": 894464 + }, + { + "epoch": 0.02, + "learning_rate": 3.5347931651907184e-05, + "loss": 3.5985, + "step": 894976 + }, + { + "epoch": 0.02, + "learning_rate": 3.5339545704396664e-05, + "loss": 3.5914, + "step": 895488 + }, + { + "epoch": 0.02, + "learning_rate": 3.533115975688614e-05, + "loss": 3.5923, + "step": 896000 + }, + { + "epoch": 0.02, + "learning_rate": 3.532279018817935e-05, + "loss": 3.5866, + "step": 896512 + }, + { + "epoch": 0.02, + "learning_rate": 3.531440424066883e-05, + "loss": 3.6021, + "step": 897024 + }, + { + "epoch": 0.02, + "learning_rate": 3.530601829315831e-05, + "loss": 3.5924, + "step": 897536 + }, + { + "epoch": 0.02, + "learning_rate": 3.529763234564779e-05, + "loss": 3.6002, + "step": 898048 + }, + { + "epoch": 0.02, + "learning_rate": 3.528926277694101e-05, + "loss": 3.5987, + "step": 898560 + }, + { + "epoch": 0.02, + "learning_rate": 3.528087682943049e-05, + "loss": 3.5931, + "step": 899072 + }, + { + "epoch": 0.02, + "learning_rate": 3.527249088191996e-05, + "loss": 3.5961, + "step": 899584 + }, + { + "epoch": 0.02, + "learning_rate": 3.526410493440944e-05, + "loss": 3.5921, + "step": 900096 + }, + { + "epoch": 0.02, + "learning_rate": 3.525573536570266e-05, + "loss": 3.5911, + "step": 900608 + }, + { + "epoch": 0.02, + "learning_rate": 3.524734941819214e-05, + "loss": 3.5975, + "step": 901120 + }, + { + "epoch": 0.02, + "learning_rate": 3.523896347068161e-05, + "loss": 3.5849, + "step": 901632 + }, + { + "epoch": 0.02, + "learning_rate": 3.523057752317109e-05, + "loss": 3.5871, + "step": 902144 + }, + { + "epoch": 0.02, + "learning_rate": 3.5222207954464307e-05, + "loss": 3.5941, + "step": 902656 + }, + { + "epoch": 0.02, + "learning_rate": 3.5213822006953786e-05, + "loss": 3.5942, + "step": 903168 + }, + { + "epoch": 0.02, + "learning_rate": 3.5205452438247e-05, + "loss": 3.5921, + "step": 903680 + }, + { + "epoch": 0.02, + "learning_rate": 3.519706649073648e-05, + "loss": 3.5847, + "step": 904192 + }, + { + "epoch": 0.02, + "learning_rate": 3.518868054322596e-05, + "loss": 3.5868, + "step": 904704 + }, + { + "epoch": 0.02, + "learning_rate": 3.5180294595715435e-05, + "loss": 3.5897, + "step": 905216 + }, + { + "epoch": 0.02, + "learning_rate": 3.5171908648204915e-05, + "loss": 3.605, + "step": 905728 + }, + { + "epoch": 0.02, + "learning_rate": 3.5163522700694395e-05, + "loss": 3.5902, + "step": 906240 + }, + { + "epoch": 0.02, + "learning_rate": 3.5155136753183875e-05, + "loss": 3.6007, + "step": 906752 + }, + { + "epoch": 0.02, + "learning_rate": 3.5146750805673355e-05, + "loss": 3.5825, + "step": 907264 + }, + { + "epoch": 0.02, + "learning_rate": 3.5138381236966564e-05, + "loss": 3.5972, + "step": 907776 + }, + { + "epoch": 0.02, + "learning_rate": 3.5129995289456044e-05, + "loss": 3.5943, + "step": 908288 + }, + { + "epoch": 0.02, + "learning_rate": 3.5121609341945524e-05, + "loss": 3.5983, + "step": 908800 + }, + { + "epoch": 0.02, + "learning_rate": 3.5113223394435004e-05, + "loss": 3.6023, + "step": 909312 + }, + { + "epoch": 0.02, + "learning_rate": 3.510485382572822e-05, + "loss": 3.5952, + "step": 909824 + }, + { + "epoch": 0.02, + "learning_rate": 3.50964678782177e-05, + "loss": 3.5951, + "step": 910336 + }, + { + "epoch": 0.02, + "learning_rate": 3.508808193070718e-05, + "loss": 3.6035, + "step": 910848 + }, + { + "epoch": 0.02, + "learning_rate": 3.507969598319666e-05, + "loss": 3.5863, + "step": 911360 + }, + { + "epoch": 0.02, + "learning_rate": 3.507132641448987e-05, + "loss": 3.5971, + "step": 911872 + }, + { + "epoch": 0.02, + "learning_rate": 3.506294046697935e-05, + "loss": 3.5895, + "step": 912384 + }, + { + "epoch": 0.02, + "learning_rate": 3.505455451946883e-05, + "loss": 3.5912, + "step": 912896 + }, + { + "epoch": 0.02, + "learning_rate": 3.504616857195831e-05, + "loss": 3.5852, + "step": 913408 + }, + { + "epoch": 0.02, + "learning_rate": 3.503779900325152e-05, + "loss": 3.5915, + "step": 913920 + }, + { + "epoch": 0.02, + "learning_rate": 3.5029413055741e-05, + "loss": 3.5874, + "step": 914432 + }, + { + "epoch": 0.02, + "learning_rate": 3.502102710823048e-05, + "loss": 3.5893, + "step": 914944 + }, + { + "epoch": 0.02, + "learning_rate": 3.501264116071996e-05, + "loss": 3.5966, + "step": 915456 + }, + { + "epoch": 0.03, + "eval_loss": 3.841780185699463, + "eval_runtime": 304.822, + "eval_samples_per_second": 1251.849, + "eval_steps_per_second": 39.121, + "step": 915840 + }, + { + "epoch": 1.0, + "learning_rate": 3.5004271592013174e-05, + "loss": 3.5945, + "step": 915968 + }, + { + "epoch": 1.0, + "learning_rate": 3.4995885644502654e-05, + "loss": 3.5795, + "step": 916480 + }, + { + "epoch": 1.0, + "learning_rate": 3.4987499696992134e-05, + "loss": 3.5837, + "step": 916992 + }, + { + "epoch": 1.0, + "learning_rate": 3.4979113749481614e-05, + "loss": 3.5978, + "step": 917504 + }, + { + "epoch": 1.0, + "learning_rate": 3.497074418077482e-05, + "loss": 3.5948, + "step": 918016 + }, + { + "epoch": 1.0, + "learning_rate": 3.49623582332643e-05, + "loss": 3.5858, + "step": 918528 + }, + { + "epoch": 1.0, + "learning_rate": 3.495397228575378e-05, + "loss": 3.5928, + "step": 919040 + }, + { + "epoch": 1.0, + "learning_rate": 3.494558633824326e-05, + "loss": 3.5838, + "step": 919552 + }, + { + "epoch": 1.0, + "learning_rate": 3.493721676953647e-05, + "loss": 3.587, + "step": 920064 + }, + { + "epoch": 1.0, + "learning_rate": 3.492883082202595e-05, + "loss": 3.5891, + "step": 920576 + }, + { + "epoch": 1.0, + "learning_rate": 3.492044487451543e-05, + "loss": 3.5953, + "step": 921088 + }, + { + "epoch": 1.0, + "learning_rate": 3.491205892700491e-05, + "loss": 3.5833, + "step": 921600 + }, + { + "epoch": 1.0, + "learning_rate": 3.490368935829813e-05, + "loss": 3.5967, + "step": 922112 + }, + { + "epoch": 1.0, + "learning_rate": 3.489530341078761e-05, + "loss": 3.5697, + "step": 922624 + }, + { + "epoch": 1.0, + "learning_rate": 3.488691746327709e-05, + "loss": 3.5851, + "step": 923136 + }, + { + "epoch": 1.0, + "learning_rate": 3.487853151576657e-05, + "loss": 3.5729, + "step": 923648 + }, + { + "epoch": 1.0, + "learning_rate": 3.4870161947059776e-05, + "loss": 3.5882, + "step": 924160 + }, + { + "epoch": 1.0, + "learning_rate": 3.4861775999549256e-05, + "loss": 3.5889, + "step": 924672 + }, + { + "epoch": 1.0, + "learning_rate": 3.4853390052038736e-05, + "loss": 3.5733, + "step": 925184 + }, + { + "epoch": 1.0, + "learning_rate": 3.4845004104528216e-05, + "loss": 3.5909, + "step": 925696 + }, + { + "epoch": 1.0, + "learning_rate": 3.4836634535821425e-05, + "loss": 3.6036, + "step": 926208 + }, + { + "epoch": 1.0, + "learning_rate": 3.4828248588310905e-05, + "loss": 3.5859, + "step": 926720 + }, + { + "epoch": 1.0, + "learning_rate": 3.4819862640800385e-05, + "loss": 3.5923, + "step": 927232 + }, + { + "epoch": 1.0, + "learning_rate": 3.4811476693289865e-05, + "loss": 3.5911, + "step": 927744 + }, + { + "epoch": 1.0, + "learning_rate": 3.480310712458308e-05, + "loss": 3.5916, + "step": 928256 + }, + { + "epoch": 1.0, + "learning_rate": 3.479472117707256e-05, + "loss": 3.585, + "step": 928768 + }, + { + "epoch": 1.0, + "learning_rate": 3.478633522956204e-05, + "loss": 3.5805, + "step": 929280 + }, + { + "epoch": 1.0, + "learning_rate": 3.477794928205152e-05, + "loss": 3.5897, + "step": 929792 + }, + { + "epoch": 1.0, + "learning_rate": 3.476957971334473e-05, + "loss": 3.5785, + "step": 930304 + }, + { + "epoch": 1.0, + "learning_rate": 3.476119376583421e-05, + "loss": 3.5815, + "step": 930816 + }, + { + "epoch": 1.01, + "learning_rate": 3.475280781832369e-05, + "loss": 3.5924, + "step": 931328 + }, + { + "epoch": 1.01, + "learning_rate": 3.47444382496169e-05, + "loss": 3.5919, + "step": 931840 + }, + { + "epoch": 1.01, + "learning_rate": 3.473605230210638e-05, + "loss": 3.5884, + "step": 932352 + }, + { + "epoch": 1.01, + "learning_rate": 3.472766635459586e-05, + "loss": 3.598, + "step": 932864 + }, + { + "epoch": 1.01, + "learning_rate": 3.471928040708534e-05, + "loss": 3.5797, + "step": 933376 + }, + { + "epoch": 1.01, + "learning_rate": 3.4710910838378555e-05, + "loss": 3.5854, + "step": 933888 + }, + { + "epoch": 1.01, + "learning_rate": 3.4702524890868035e-05, + "loss": 3.5899, + "step": 934400 + }, + { + "epoch": 1.01, + "learning_rate": 3.4694138943357515e-05, + "loss": 3.5739, + "step": 934912 + }, + { + "epoch": 1.01, + "learning_rate": 3.4685752995846995e-05, + "loss": 3.5798, + "step": 935424 + }, + { + "epoch": 1.01, + "learning_rate": 3.4677383427140204e-05, + "loss": 3.5823, + "step": 935936 + }, + { + "epoch": 1.01, + "learning_rate": 3.4668997479629684e-05, + "loss": 3.5761, + "step": 936448 + }, + { + "epoch": 1.01, + "learning_rate": 3.4660611532119164e-05, + "loss": 3.5854, + "step": 936960 + }, + { + "epoch": 1.01, + "learning_rate": 3.4652225584608644e-05, + "loss": 3.5911, + "step": 937472 + }, + { + "epoch": 1.01, + "learning_rate": 3.464385601590185e-05, + "loss": 3.5866, + "step": 937984 + }, + { + "epoch": 1.01, + "learning_rate": 3.463547006839133e-05, + "loss": 3.5855, + "step": 938496 + }, + { + "epoch": 1.01, + "learning_rate": 3.462708412088081e-05, + "loss": 3.5906, + "step": 939008 + }, + { + "epoch": 1.01, + "learning_rate": 3.461869817337029e-05, + "loss": 3.5784, + "step": 939520 + }, + { + "epoch": 1.01, + "learning_rate": 3.461032860466351e-05, + "loss": 3.5892, + "step": 940032 + }, + { + "epoch": 1.01, + "learning_rate": 3.460194265715299e-05, + "loss": 3.5679, + "step": 940544 + }, + { + "epoch": 1.01, + "learning_rate": 3.459355670964247e-05, + "loss": 3.5845, + "step": 941056 + }, + { + "epoch": 1.01, + "learning_rate": 3.458517076213195e-05, + "loss": 3.578, + "step": 941568 + }, + { + "epoch": 1.01, + "learning_rate": 3.457680119342516e-05, + "loss": 3.5927, + "step": 942080 + }, + { + "epoch": 1.01, + "learning_rate": 3.456841524591464e-05, + "loss": 3.5807, + "step": 942592 + }, + { + "epoch": 1.01, + "learning_rate": 3.456002929840412e-05, + "loss": 3.5713, + "step": 943104 + }, + { + "epoch": 1.01, + "learning_rate": 3.45516433508936e-05, + "loss": 3.575, + "step": 943616 + }, + { + "epoch": 1.01, + "learning_rate": 3.4543273782186806e-05, + "loss": 3.5802, + "step": 944128 + }, + { + "epoch": 1.01, + "learning_rate": 3.4534904213480016e-05, + "loss": 3.5926, + "step": 944640 + }, + { + "epoch": 1.01, + "learning_rate": 3.4526518265969495e-05, + "loss": 3.5636, + "step": 945152 + }, + { + "epoch": 1.01, + "learning_rate": 3.451813231845898e-05, + "loss": 3.5928, + "step": 945664 + }, + { + "epoch": 1.01, + "learning_rate": 3.450974637094846e-05, + "loss": 3.5822, + "step": 946176 + }, + { + "epoch": 1.01, + "learning_rate": 3.450136042343794e-05, + "loss": 3.5604, + "step": 946688 + }, + { + "epoch": 1.01, + "learning_rate": 3.449297447592742e-05, + "loss": 3.5898, + "step": 947200 + }, + { + "epoch": 1.01, + "learning_rate": 3.44845885284169e-05, + "loss": 3.5684, + "step": 947712 + }, + { + "epoch": 1.01, + "learning_rate": 3.447620258090638e-05, + "loss": 3.5653, + "step": 948224 + }, + { + "epoch": 1.01, + "learning_rate": 3.446783301219959e-05, + "loss": 3.5771, + "step": 948736 + }, + { + "epoch": 1.01, + "learning_rate": 3.445944706468907e-05, + "loss": 3.5822, + "step": 949248 + }, + { + "epoch": 1.01, + "learning_rate": 3.445106111717855e-05, + "loss": 3.5752, + "step": 949760 + }, + { + "epoch": 1.01, + "learning_rate": 3.444267516966803e-05, + "loss": 3.579, + "step": 950272 + }, + { + "epoch": 1.01, + "learning_rate": 3.443430560096124e-05, + "loss": 3.5642, + "step": 950784 + }, + { + "epoch": 1.01, + "learning_rate": 3.442591965345072e-05, + "loss": 3.5667, + "step": 951296 + }, + { + "epoch": 1.01, + "learning_rate": 3.44175337059402e-05, + "loss": 3.583, + "step": 951808 + }, + { + "epoch": 1.01, + "learning_rate": 3.4409164137233416e-05, + "loss": 3.585, + "step": 952320 + }, + { + "epoch": 1.01, + "learning_rate": 3.4400778189722896e-05, + "loss": 3.5858, + "step": 952832 + }, + { + "epoch": 1.01, + "learning_rate": 3.4392392242212376e-05, + "loss": 3.5784, + "step": 953344 + }, + { + "epoch": 1.01, + "learning_rate": 3.4384006294701856e-05, + "loss": 3.589, + "step": 953856 + }, + { + "epoch": 1.01, + "learning_rate": 3.4375636725995065e-05, + "loss": 3.5747, + "step": 954368 + }, + { + "epoch": 1.01, + "learning_rate": 3.4367250778484545e-05, + "loss": 3.5859, + "step": 954880 + }, + { + "epoch": 1.01, + "learning_rate": 3.4358864830974025e-05, + "loss": 3.5755, + "step": 955392 + }, + { + "epoch": 1.01, + "learning_rate": 3.4350478883463505e-05, + "loss": 3.572, + "step": 955904 + }, + { + "epoch": 1.01, + "learning_rate": 3.4342109314756714e-05, + "loss": 3.5795, + "step": 956416 + }, + { + "epoch": 1.01, + "learning_rate": 3.4333723367246194e-05, + "loss": 3.5695, + "step": 956928 + }, + { + "epoch": 1.01, + "learning_rate": 3.4325337419735674e-05, + "loss": 3.586, + "step": 957440 + }, + { + "epoch": 1.01, + "learning_rate": 3.4316951472225154e-05, + "loss": 3.5884, + "step": 957952 + }, + { + "epoch": 1.01, + "learning_rate": 3.430858190351837e-05, + "loss": 3.5771, + "step": 958464 + }, + { + "epoch": 1.01, + "learning_rate": 3.430019595600785e-05, + "loss": 3.5597, + "step": 958976 + }, + { + "epoch": 1.01, + "learning_rate": 3.429181000849733e-05, + "loss": 3.5801, + "step": 959488 + }, + { + "epoch": 1.01, + "learning_rate": 3.428342406098681e-05, + "loss": 3.5838, + "step": 960000 + }, + { + "epoch": 1.01, + "learning_rate": 3.427505449228002e-05, + "loss": 3.5795, + "step": 960512 + }, + { + "epoch": 1.01, + "learning_rate": 3.42666685447695e-05, + "loss": 3.5828, + "step": 961024 + }, + { + "epoch": 1.01, + "learning_rate": 3.425828259725898e-05, + "loss": 3.5874, + "step": 961536 + }, + { + "epoch": 1.02, + "learning_rate": 3.424989664974846e-05, + "loss": 3.5767, + "step": 962048 + }, + { + "epoch": 1.02, + "learning_rate": 3.424152708104167e-05, + "loss": 3.5803, + "step": 962560 + }, + { + "epoch": 1.02, + "learning_rate": 3.423314113353115e-05, + "loss": 3.5708, + "step": 963072 + }, + { + "epoch": 1.02, + "learning_rate": 3.422475518602063e-05, + "loss": 3.5874, + "step": 963584 + }, + { + "epoch": 1.02, + "learning_rate": 3.421636923851011e-05, + "loss": 3.5831, + "step": 964096 + }, + { + "epoch": 1.02, + "learning_rate": 3.420799966980332e-05, + "loss": 3.5833, + "step": 964608 + }, + { + "epoch": 1.02, + "learning_rate": 3.41996137222928e-05, + "loss": 3.5742, + "step": 965120 + }, + { + "epoch": 1.02, + "learning_rate": 3.419122777478228e-05, + "loss": 3.568, + "step": 965632 + }, + { + "epoch": 1.02, + "learning_rate": 3.4182841827271756e-05, + "loss": 3.5774, + "step": 966144 + }, + { + "epoch": 1.02, + "learning_rate": 3.417447225856497e-05, + "loss": 3.5892, + "step": 966656 + }, + { + "epoch": 1.02, + "learning_rate": 3.416608631105445e-05, + "loss": 3.5787, + "step": 967168 + }, + { + "epoch": 1.02, + "learning_rate": 3.415770036354393e-05, + "loss": 3.5741, + "step": 967680 + }, + { + "epoch": 1.02, + "learning_rate": 3.4149314416033405e-05, + "loss": 3.5753, + "step": 968192 + }, + { + "epoch": 1.02, + "learning_rate": 3.414094484732662e-05, + "loss": 3.5735, + "step": 968704 + }, + { + "epoch": 1.02, + "learning_rate": 3.41325588998161e-05, + "loss": 3.5759, + "step": 969216 + }, + { + "epoch": 1.02, + "learning_rate": 3.412417295230558e-05, + "loss": 3.5734, + "step": 969728 + }, + { + "epoch": 1.02, + "learning_rate": 3.411578700479506e-05, + "loss": 3.5677, + "step": 970240 + }, + { + "epoch": 1.02, + "learning_rate": 3.410741743608828e-05, + "loss": 3.578, + "step": 970752 + }, + { + "epoch": 1.02, + "learning_rate": 3.409903148857776e-05, + "loss": 3.5817, + "step": 971264 + }, + { + "epoch": 1.02, + "learning_rate": 3.409064554106723e-05, + "loss": 3.5748, + "step": 971776 + }, + { + "epoch": 1.02, + "learning_rate": 3.408225959355671e-05, + "loss": 3.5726, + "step": 972288 + }, + { + "epoch": 1.02, + "learning_rate": 3.4073890024849926e-05, + "loss": 3.5719, + "step": 972800 + }, + { + "epoch": 1.02, + "learning_rate": 3.4065504077339406e-05, + "loss": 3.5827, + "step": 973312 + }, + { + "epoch": 1.02, + "learning_rate": 3.405711812982888e-05, + "loss": 3.5752, + "step": 973824 + }, + { + "epoch": 1.02, + "learning_rate": 3.404873218231836e-05, + "loss": 3.5779, + "step": 974336 + }, + { + "epoch": 1.02, + "learning_rate": 3.4040362613611575e-05, + "loss": 3.5806, + "step": 974848 + }, + { + "epoch": 1.02, + "learning_rate": 3.403197666610105e-05, + "loss": 3.5796, + "step": 975360 + }, + { + "epoch": 1.02, + "learning_rate": 3.402359071859053e-05, + "loss": 3.5759, + "step": 975872 + }, + { + "epoch": 1.02, + "learning_rate": 3.4015204771080015e-05, + "loss": 3.5741, + "step": 976384 + }, + { + "epoch": 1.02, + "learning_rate": 3.400683520237323e-05, + "loss": 3.5761, + "step": 976896 + }, + { + "epoch": 1.02, + "learning_rate": 3.3998449254862704e-05, + "loss": 3.5771, + "step": 977408 + }, + { + "epoch": 1.02, + "learning_rate": 3.3990063307352184e-05, + "loss": 3.564, + "step": 977920 + }, + { + "epoch": 1.02, + "learning_rate": 3.3981677359841664e-05, + "loss": 3.5745, + "step": 978432 + }, + { + "epoch": 1.02, + "learning_rate": 3.397330779113488e-05, + "loss": 3.5709, + "step": 978944 + }, + { + "epoch": 1.02, + "learning_rate": 3.396492184362435e-05, + "loss": 3.5771, + "step": 979456 + }, + { + "epoch": 1.02, + "learning_rate": 3.395655227491757e-05, + "loss": 3.5751, + "step": 979968 + }, + { + "epoch": 1.02, + "learning_rate": 3.394816632740705e-05, + "loss": 3.5689, + "step": 980480 + }, + { + "epoch": 1.02, + "learning_rate": 3.393978037989652e-05, + "loss": 3.5647, + "step": 980992 + }, + { + "epoch": 1.02, + "learning_rate": 3.3931394432386e-05, + "loss": 3.5722, + "step": 981504 + }, + { + "epoch": 1.02, + "learning_rate": 3.392300848487548e-05, + "loss": 3.5876, + "step": 982016 + }, + { + "epoch": 1.02, + "learning_rate": 3.391462253736497e-05, + "loss": 3.5744, + "step": 982528 + }, + { + "epoch": 1.02, + "learning_rate": 3.390623658985445e-05, + "loss": 3.5796, + "step": 983040 + }, + { + "epoch": 1.02, + "learning_rate": 3.389785064234393e-05, + "loss": 3.5659, + "step": 983552 + }, + { + "epoch": 1.02, + "learning_rate": 3.388948107363714e-05, + "loss": 3.5783, + "step": 984064 + }, + { + "epoch": 1.02, + "learning_rate": 3.388109512612662e-05, + "loss": 3.5782, + "step": 984576 + }, + { + "epoch": 1.02, + "learning_rate": 3.38727091786161e-05, + "loss": 3.5789, + "step": 985088 + }, + { + "epoch": 1.02, + "learning_rate": 3.386432323110558e-05, + "loss": 3.5829, + "step": 985600 + }, + { + "epoch": 1.02, + "learning_rate": 3.3855953662398786e-05, + "loss": 3.5758, + "step": 986112 + }, + { + "epoch": 1.02, + "learning_rate": 3.3847567714888266e-05, + "loss": 3.584, + "step": 986624 + }, + { + "epoch": 1.02, + "learning_rate": 3.3839181767377746e-05, + "loss": 3.5856, + "step": 987136 + }, + { + "epoch": 1.02, + "learning_rate": 3.3830795819867226e-05, + "loss": 3.5671, + "step": 987648 + }, + { + "epoch": 1.02, + "learning_rate": 3.3822426251160435e-05, + "loss": 3.5795, + "step": 988160 + }, + { + "epoch": 1.02, + "learning_rate": 3.381404030364992e-05, + "loss": 3.5706, + "step": 988672 + }, + { + "epoch": 1.02, + "learning_rate": 3.38056543561394e-05, + "loss": 3.5745, + "step": 989184 + }, + { + "epoch": 1.02, + "learning_rate": 3.379726840862888e-05, + "loss": 3.5682, + "step": 989696 + }, + { + "epoch": 1.02, + "learning_rate": 3.378889883992209e-05, + "loss": 3.574, + "step": 990208 + }, + { + "epoch": 1.02, + "learning_rate": 3.378051289241157e-05, + "loss": 3.5698, + "step": 990720 + }, + { + "epoch": 1.02, + "learning_rate": 3.377212694490105e-05, + "loss": 3.5728, + "step": 991232 + }, + { + "epoch": 1.02, + "learning_rate": 3.376374099739053e-05, + "loss": 3.5748, + "step": 991744 + }, + { + "epoch": 1.03, + "eval_loss": 3.8419694900512695, + "eval_runtime": 305.0706, + "eval_samples_per_second": 1250.829, + "eval_steps_per_second": 39.089, + "step": 992160 + }, + { + "epoch": 0.0, + "learning_rate": 3.375537142868374e-05, + "loss": 3.588, + "step": 992256 + }, + { + "epoch": 0.0, + "learning_rate": 3.374698548117322e-05, + "loss": 3.561, + "step": 992768 + }, + { + "epoch": 0.0, + "learning_rate": 3.37385995336627e-05, + "loss": 3.5649, + "step": 993280 + }, + { + "epoch": 0.0, + "learning_rate": 3.373021358615218e-05, + "loss": 3.5803, + "step": 993792 + }, + { + "epoch": 0.0, + "learning_rate": 3.372184401744539e-05, + "loss": 3.5754, + "step": 994304 + }, + { + "epoch": 0.0, + "learning_rate": 3.3713458069934876e-05, + "loss": 3.5706, + "step": 994816 + }, + { + "epoch": 0.0, + "learning_rate": 3.3705072122424356e-05, + "loss": 3.5718, + "step": 995328 + }, + { + "epoch": 0.0, + "learning_rate": 3.3696686174913836e-05, + "loss": 3.5669, + "step": 995840 + }, + { + "epoch": 0.0, + "learning_rate": 3.3688316606207045e-05, + "loss": 3.5699, + "step": 996352 + }, + { + "epoch": 0.0, + "learning_rate": 3.3679930658696525e-05, + "loss": 3.5741, + "step": 996864 + }, + { + "epoch": 0.0, + "learning_rate": 3.3671544711186005e-05, + "loss": 3.5746, + "step": 997376 + }, + { + "epoch": 0.0, + "learning_rate": 3.3663158763675484e-05, + "loss": 3.5688, + "step": 997888 + }, + { + "epoch": 0.0, + "learning_rate": 3.3654789194968694e-05, + "loss": 3.581, + "step": 998400 + }, + { + "epoch": 0.0, + "learning_rate": 3.3646403247458174e-05, + "loss": 3.5481, + "step": 998912 + }, + { + "epoch": 0.0, + "learning_rate": 3.3638017299947654e-05, + "loss": 3.5661, + "step": 999424 + }, + { + "epoch": 0.0, + "learning_rate": 3.3629631352437133e-05, + "loss": 3.5559, + "step": 999936 + }, + { + "epoch": 0.0, + "learning_rate": 3.362126178373034e-05, + "loss": 3.5749, + "step": 1000448 + }, + { + "epoch": 0.0, + "learning_rate": 3.361287583621983e-05, + "loss": 3.5678, + "step": 1000960 + }, + { + "epoch": 0.0, + "learning_rate": 3.360448988870931e-05, + "loss": 3.5597, + "step": 1001472 + }, + { + "epoch": 0.0, + "learning_rate": 3.359610394119879e-05, + "loss": 3.5686, + "step": 1001984 + }, + { + "epoch": 0.0, + "learning_rate": 3.3587734372492e-05, + "loss": 3.5873, + "step": 1002496 + }, + { + "epoch": 0.0, + "learning_rate": 3.357934842498148e-05, + "loss": 3.5661, + "step": 1003008 + }, + { + "epoch": 0.0, + "learning_rate": 3.357096247747096e-05, + "loss": 3.5739, + "step": 1003520 + }, + { + "epoch": 0.0, + "learning_rate": 3.356257652996044e-05, + "loss": 3.5758, + "step": 1004032 + }, + { + "epoch": 0.0, + "learning_rate": 3.355420696125365e-05, + "loss": 3.5761, + "step": 1004544 + }, + { + "epoch": 0.0, + "learning_rate": 3.354582101374313e-05, + "loss": 3.5656, + "step": 1005056 + }, + { + "epoch": 0.0, + "learning_rate": 3.353743506623261e-05, + "loss": 3.5648, + "step": 1005568 + }, + { + "epoch": 0.0, + "learning_rate": 3.352904911872209e-05, + "loss": 3.5716, + "step": 1006080 + }, + { + "epoch": 0.0, + "learning_rate": 3.3520679550015296e-05, + "loss": 3.5587, + "step": 1006592 + }, + { + "epoch": 0.0, + "learning_rate": 3.3512293602504776e-05, + "loss": 3.5653, + "step": 1007104 + }, + { + "epoch": 0.01, + "learning_rate": 3.350390765499426e-05, + "loss": 3.5753, + "step": 1007616 + }, + { + "epoch": 0.01, + "learning_rate": 3.349552170748374e-05, + "loss": 3.5767, + "step": 1008128 + }, + { + "epoch": 0.01, + "learning_rate": 3.348715213877695e-05, + "loss": 3.5732, + "step": 1008640 + }, + { + "epoch": 0.01, + "learning_rate": 3.347876619126643e-05, + "loss": 3.5764, + "step": 1009152 + }, + { + "epoch": 0.01, + "learning_rate": 3.347038024375591e-05, + "loss": 3.5624, + "step": 1009664 + }, + { + "epoch": 0.01, + "learning_rate": 3.346199429624539e-05, + "loss": 3.5689, + "step": 1010176 + }, + { + "epoch": 0.01, + "learning_rate": 3.34536247275386e-05, + "loss": 3.5739, + "step": 1010688 + }, + { + "epoch": 0.01, + "learning_rate": 3.344523878002808e-05, + "loss": 3.5534, + "step": 1011200 + }, + { + "epoch": 0.01, + "learning_rate": 3.343685283251756e-05, + "loss": 3.5678, + "step": 1011712 + }, + { + "epoch": 0.01, + "learning_rate": 3.342846688500704e-05, + "loss": 3.5625, + "step": 1012224 + }, + { + "epoch": 0.01, + "learning_rate": 3.342009731630025e-05, + "loss": 3.5569, + "step": 1012736 + }, + { + "epoch": 0.01, + "learning_rate": 3.3411727747593466e-05, + "loss": 3.5688, + "step": 1013248 + }, + { + "epoch": 0.01, + "learning_rate": 3.3403341800082946e-05, + "loss": 3.579, + "step": 1013760 + }, + { + "epoch": 0.01, + "learning_rate": 3.3394955852572426e-05, + "loss": 3.5635, + "step": 1014272 + }, + { + "epoch": 0.01, + "learning_rate": 3.3386569905061906e-05, + "loss": 3.5701, + "step": 1014784 + }, + { + "epoch": 0.01, + "learning_rate": 3.3378183957551386e-05, + "loss": 3.5701, + "step": 1015296 + }, + { + "epoch": 0.01, + "learning_rate": 3.3369798010040866e-05, + "loss": 3.563, + "step": 1015808 + }, + { + "epoch": 0.01, + "learning_rate": 3.3361412062530345e-05, + "loss": 3.5717, + "step": 1016320 + }, + { + "epoch": 0.01, + "learning_rate": 3.3353026115019825e-05, + "loss": 3.5529, + "step": 1016832 + }, + { + "epoch": 0.01, + "learning_rate": 3.3344656546313035e-05, + "loss": 3.5657, + "step": 1017344 + }, + { + "epoch": 0.01, + "learning_rate": 3.3336270598802515e-05, + "loss": 3.5634, + "step": 1017856 + }, + { + "epoch": 0.01, + "learning_rate": 3.3327884651291994e-05, + "loss": 3.5758, + "step": 1018368 + }, + { + "epoch": 0.01, + "learning_rate": 3.3319498703781474e-05, + "loss": 3.5646, + "step": 1018880 + }, + { + "epoch": 0.01, + "learning_rate": 3.3311129135074684e-05, + "loss": 3.5544, + "step": 1019392 + }, + { + "epoch": 0.01, + "learning_rate": 3.330274318756417e-05, + "loss": 3.5567, + "step": 1019904 + }, + { + "epoch": 0.01, + "learning_rate": 3.329435724005365e-05, + "loss": 3.5605, + "step": 1020416 + }, + { + "epoch": 0.01, + "learning_rate": 3.328598767134686e-05, + "loss": 3.5756, + "step": 1020928 + }, + { + "epoch": 0.01, + "learning_rate": 3.327760172383634e-05, + "loss": 3.5494, + "step": 1021440 + }, + { + "epoch": 0.01, + "learning_rate": 3.326921577632582e-05, + "loss": 3.5732, + "step": 1021952 + }, + { + "epoch": 0.01, + "learning_rate": 3.32608298288153e-05, + "loss": 3.5619, + "step": 1022464 + }, + { + "epoch": 0.01, + "learning_rate": 3.325244388130478e-05, + "loss": 3.5468, + "step": 1022976 + }, + { + "epoch": 0.01, + "learning_rate": 3.324405793379425e-05, + "loss": 3.5699, + "step": 1023488 + }, + { + "epoch": 0.01, + "learning_rate": 3.323567198628373e-05, + "loss": 3.5539, + "step": 1024000 + }, + { + "epoch": 0.01, + "learning_rate": 3.322728603877321e-05, + "loss": 3.5491, + "step": 1024512 + }, + { + "epoch": 0.01, + "learning_rate": 3.321891647006643e-05, + "loss": 3.5565, + "step": 1025024 + }, + { + "epoch": 0.01, + "learning_rate": 3.321053052255591e-05, + "loss": 3.5664, + "step": 1025536 + }, + { + "epoch": 0.01, + "learning_rate": 3.320214457504539e-05, + "loss": 3.5611, + "step": 1026048 + }, + { + "epoch": 0.01, + "learning_rate": 3.319375862753487e-05, + "loss": 3.5555, + "step": 1026560 + }, + { + "epoch": 0.01, + "learning_rate": 3.318538905882808e-05, + "loss": 3.5543, + "step": 1027072 + }, + { + "epoch": 0.01, + "learning_rate": 3.317700311131756e-05, + "loss": 3.5513, + "step": 1027584 + }, + { + "epoch": 0.01, + "learning_rate": 3.316861716380704e-05, + "loss": 3.5623, + "step": 1028096 + }, + { + "epoch": 0.01, + "learning_rate": 3.316023121629652e-05, + "loss": 3.5649, + "step": 1028608 + }, + { + "epoch": 0.01, + "learning_rate": 3.3151861647589726e-05, + "loss": 3.5675, + "step": 1029120 + }, + { + "epoch": 0.01, + "learning_rate": 3.3143475700079206e-05, + "loss": 3.569, + "step": 1029632 + }, + { + "epoch": 0.01, + "learning_rate": 3.3135089752568686e-05, + "loss": 3.5671, + "step": 1030144 + }, + { + "epoch": 0.01, + "learning_rate": 3.3126703805058166e-05, + "loss": 3.5578, + "step": 1030656 + }, + { + "epoch": 0.01, + "learning_rate": 3.3118334236351375e-05, + "loss": 3.5673, + "step": 1031168 + }, + { + "epoch": 0.01, + "learning_rate": 3.310994828884086e-05, + "loss": 3.5631, + "step": 1031680 + }, + { + "epoch": 0.01, + "learning_rate": 3.310156234133034e-05, + "loss": 3.5583, + "step": 1032192 + }, + { + "epoch": 0.01, + "learning_rate": 3.309317639381982e-05, + "loss": 3.5552, + "step": 1032704 + }, + { + "epoch": 0.01, + "learning_rate": 3.308480682511303e-05, + "loss": 3.5581, + "step": 1033216 + }, + { + "epoch": 0.01, + "learning_rate": 3.307642087760251e-05, + "loss": 3.5709, + "step": 1033728 + }, + { + "epoch": 0.01, + "learning_rate": 3.306803493009199e-05, + "loss": 3.5703, + "step": 1034240 + }, + { + "epoch": 0.01, + "learning_rate": 3.305964898258147e-05, + "loss": 3.5632, + "step": 1034752 + }, + { + "epoch": 0.01, + "learning_rate": 3.305127941387468e-05, + "loss": 3.5443, + "step": 1035264 + }, + { + "epoch": 0.01, + "learning_rate": 3.304289346636416e-05, + "loss": 3.5624, + "step": 1035776 + }, + { + "epoch": 0.01, + "learning_rate": 3.303450751885364e-05, + "loss": 3.5669, + "step": 1036288 + }, + { + "epoch": 0.01, + "learning_rate": 3.302613795014685e-05, + "loss": 3.5658, + "step": 1036800 + }, + { + "epoch": 0.01, + "learning_rate": 3.301775200263633e-05, + "loss": 3.5617, + "step": 1037312 + }, + { + "epoch": 0.01, + "learning_rate": 3.3009366055125815e-05, + "loss": 3.5715, + "step": 1037824 + }, + { + "epoch": 0.02, + "learning_rate": 3.3000980107615295e-05, + "loss": 3.5597, + "step": 1038336 + }, + { + "epoch": 0.02, + "learning_rate": 3.2992610538908504e-05, + "loss": 3.5622, + "step": 1038848 + }, + { + "epoch": 0.02, + "learning_rate": 3.2984224591397984e-05, + "loss": 3.5573, + "step": 1039360 + }, + { + "epoch": 0.02, + "learning_rate": 3.2975838643887464e-05, + "loss": 3.5674, + "step": 1039872 + }, + { + "epoch": 0.02, + "learning_rate": 3.2967452696376944e-05, + "loss": 3.5671, + "step": 1040384 + }, + { + "epoch": 0.02, + "learning_rate": 3.295908312767015e-05, + "loss": 3.5707, + "step": 1040896 + }, + { + "epoch": 0.02, + "learning_rate": 3.295069718015963e-05, + "loss": 3.5539, + "step": 1041408 + }, + { + "epoch": 0.02, + "learning_rate": 3.294231123264911e-05, + "loss": 3.554, + "step": 1041920 + }, + { + "epoch": 0.02, + "learning_rate": 3.293392528513859e-05, + "loss": 3.5574, + "step": 1042432 + }, + { + "epoch": 0.02, + "learning_rate": 3.29255557164318e-05, + "loss": 3.5717, + "step": 1042944 + }, + { + "epoch": 0.02, + "learning_rate": 3.291716976892128e-05, + "loss": 3.5607, + "step": 1043456 + }, + { + "epoch": 0.02, + "learning_rate": 3.290878382141077e-05, + "loss": 3.5586, + "step": 1043968 + }, + { + "epoch": 0.02, + "learning_rate": 3.290039787390025e-05, + "loss": 3.557, + "step": 1044480 + }, + { + "epoch": 0.02, + "learning_rate": 3.289202830519346e-05, + "loss": 3.5556, + "step": 1044992 + }, + { + "epoch": 0.02, + "learning_rate": 3.288364235768294e-05, + "loss": 3.5592, + "step": 1045504 + }, + { + "epoch": 0.02, + "learning_rate": 3.287525641017242e-05, + "loss": 3.5544, + "step": 1046016 + }, + { + "epoch": 0.02, + "learning_rate": 3.28668704626619e-05, + "loss": 3.5564, + "step": 1046528 + }, + { + "epoch": 0.02, + "learning_rate": 3.285850089395511e-05, + "loss": 3.5636, + "step": 1047040 + }, + { + "epoch": 0.02, + "learning_rate": 3.285011494644459e-05, + "loss": 3.5637, + "step": 1047552 + }, + { + "epoch": 0.02, + "learning_rate": 3.284172899893407e-05, + "loss": 3.554, + "step": 1048064 + }, + { + "epoch": 0.02, + "learning_rate": 3.283334305142355e-05, + "loss": 3.5563, + "step": 1048576 + }, + { + "epoch": 0.02, + "learning_rate": 3.2824973482716756e-05, + "loss": 3.5553, + "step": 1049088 + }, + { + "epoch": 0.02, + "learning_rate": 3.2816587535206236e-05, + "loss": 3.5664, + "step": 1049600 + }, + { + "epoch": 0.02, + "learning_rate": 3.280820158769572e-05, + "loss": 3.5604, + "step": 1050112 + }, + { + "epoch": 0.02, + "learning_rate": 3.27998156401852e-05, + "loss": 3.5617, + "step": 1050624 + }, + { + "epoch": 0.02, + "learning_rate": 3.279144607147841e-05, + "loss": 3.5592, + "step": 1051136 + }, + { + "epoch": 0.02, + "learning_rate": 3.278306012396789e-05, + "loss": 3.566, + "step": 1051648 + }, + { + "epoch": 0.02, + "learning_rate": 3.277467417645737e-05, + "loss": 3.5597, + "step": 1052160 + }, + { + "epoch": 0.02, + "learning_rate": 3.276628822894685e-05, + "loss": 3.5543, + "step": 1052672 + }, + { + "epoch": 0.02, + "learning_rate": 3.275791866024006e-05, + "loss": 3.5626, + "step": 1053184 + }, + { + "epoch": 0.02, + "learning_rate": 3.274953271272954e-05, + "loss": 3.5565, + "step": 1053696 + }, + { + "epoch": 0.02, + "learning_rate": 3.274114676521902e-05, + "loss": 3.5485, + "step": 1054208 + }, + { + "epoch": 0.02, + "learning_rate": 3.27327608177085e-05, + "loss": 3.5551, + "step": 1054720 + }, + { + "epoch": 0.02, + "learning_rate": 3.272439124900171e-05, + "loss": 3.555, + "step": 1055232 + }, + { + "epoch": 0.02, + "learning_rate": 3.271600530149119e-05, + "loss": 3.5608, + "step": 1055744 + }, + { + "epoch": 0.02, + "learning_rate": 3.2707635732784406e-05, + "loss": 3.5558, + "step": 1056256 + }, + { + "epoch": 0.02, + "learning_rate": 3.2699249785273885e-05, + "loss": 3.5547, + "step": 1056768 + }, + { + "epoch": 0.02, + "learning_rate": 3.2690863837763365e-05, + "loss": 3.5489, + "step": 1057280 + }, + { + "epoch": 0.02, + "learning_rate": 3.2682477890252845e-05, + "loss": 3.5559, + "step": 1057792 + }, + { + "epoch": 0.02, + "learning_rate": 3.2674091942742325e-05, + "loss": 3.5694, + "step": 1058304 + }, + { + "epoch": 0.02, + "learning_rate": 3.2665705995231805e-05, + "loss": 3.5577, + "step": 1058816 + }, + { + "epoch": 0.02, + "learning_rate": 3.2657320047721285e-05, + "loss": 3.5638, + "step": 1059328 + }, + { + "epoch": 0.02, + "learning_rate": 3.2648934100210765e-05, + "loss": 3.5481, + "step": 1059840 + }, + { + "epoch": 0.02, + "learning_rate": 3.2640564531503974e-05, + "loss": 3.5623, + "step": 1060352 + }, + { + "epoch": 0.02, + "learning_rate": 3.2632178583993454e-05, + "loss": 3.5631, + "step": 1060864 + }, + { + "epoch": 0.02, + "learning_rate": 3.2623792636482934e-05, + "loss": 3.5626, + "step": 1061376 + }, + { + "epoch": 0.02, + "learning_rate": 3.2615406688972414e-05, + "loss": 3.5625, + "step": 1061888 + }, + { + "epoch": 0.02, + "learning_rate": 3.260703712026562e-05, + "loss": 3.5592, + "step": 1062400 + }, + { + "epoch": 0.02, + "learning_rate": 3.259865117275511e-05, + "loss": 3.5691, + "step": 1062912 + }, + { + "epoch": 0.02, + "learning_rate": 3.259026522524459e-05, + "loss": 3.5667, + "step": 1063424 + }, + { + "epoch": 0.02, + "learning_rate": 3.258187927773407e-05, + "loss": 3.5531, + "step": 1063936 + }, + { + "epoch": 0.02, + "learning_rate": 3.257350970902728e-05, + "loss": 3.5593, + "step": 1064448 + }, + { + "epoch": 0.02, + "learning_rate": 3.256512376151676e-05, + "loss": 3.5572, + "step": 1064960 + }, + { + "epoch": 0.02, + "learning_rate": 3.255673781400624e-05, + "loss": 3.5593, + "step": 1065472 + }, + { + "epoch": 0.02, + "learning_rate": 3.254835186649572e-05, + "loss": 3.5512, + "step": 1065984 + }, + { + "epoch": 0.02, + "learning_rate": 3.253998229778893e-05, + "loss": 3.5592, + "step": 1066496 + }, + { + "epoch": 0.02, + "learning_rate": 3.253159635027841e-05, + "loss": 3.5495, + "step": 1067008 + }, + { + "epoch": 0.02, + "learning_rate": 3.252321040276789e-05, + "loss": 3.5638, + "step": 1067520 + }, + { + "epoch": 0.02, + "learning_rate": 3.251482445525737e-05, + "loss": 3.5537, + "step": 1068032 + }, + { + "epoch": 0.03, + "eval_loss": 3.8422229290008545, + "eval_runtime": 303.4845, + "eval_samples_per_second": 1257.366, + "eval_steps_per_second": 39.294, + "step": 1068480 + }, + { + "epoch": 1.0, + "learning_rate": 3.250645488655058e-05, + "loss": 3.5605, + "step": 1068544 + }, + { + "epoch": 1.0, + "learning_rate": 3.2498068939040064e-05, + "loss": 3.5456, + "step": 1069056 + }, + { + "epoch": 1.0, + "learning_rate": 3.2489682991529544e-05, + "loss": 3.5491, + "step": 1069568 + }, + { + "epoch": 1.0, + "learning_rate": 3.2481297044019024e-05, + "loss": 3.5641, + "step": 1070080 + }, + { + "epoch": 1.0, + "learning_rate": 3.247292747531223e-05, + "loss": 3.5611, + "step": 1070592 + }, + { + "epoch": 1.0, + "learning_rate": 3.246454152780171e-05, + "loss": 3.558, + "step": 1071104 + }, + { + "epoch": 1.0, + "learning_rate": 3.245615558029119e-05, + "loss": 3.5494, + "step": 1071616 + }, + { + "epoch": 1.0, + "learning_rate": 3.244776963278067e-05, + "loss": 3.5486, + "step": 1072128 + }, + { + "epoch": 1.0, + "learning_rate": 3.243940006407388e-05, + "loss": 3.5532, + "step": 1072640 + }, + { + "epoch": 1.0, + "learning_rate": 3.243101411656336e-05, + "loss": 3.561, + "step": 1073152 + }, + { + "epoch": 1.0, + "learning_rate": 3.242262816905284e-05, + "loss": 3.5572, + "step": 1073664 + }, + { + "epoch": 1.0, + "learning_rate": 3.241424222154232e-05, + "loss": 3.5555, + "step": 1074176 + }, + { + "epoch": 1.0, + "learning_rate": 3.240587265283553e-05, + "loss": 3.5621, + "step": 1074688 + }, + { + "epoch": 1.0, + "learning_rate": 3.239748670532502e-05, + "loss": 3.5368, + "step": 1075200 + }, + { + "epoch": 1.0, + "learning_rate": 3.23891007578145e-05, + "loss": 3.5497, + "step": 1075712 + }, + { + "epoch": 1.0, + "learning_rate": 3.238071481030398e-05, + "loss": 3.5427, + "step": 1076224 + }, + { + "epoch": 1.0, + "learning_rate": 3.2372345241597186e-05, + "loss": 3.5551, + "step": 1076736 + }, + { + "epoch": 1.0, + "learning_rate": 3.2363959294086666e-05, + "loss": 3.5463, + "step": 1077248 + }, + { + "epoch": 1.0, + "learning_rate": 3.2355573346576146e-05, + "loss": 3.5504, + "step": 1077760 + }, + { + "epoch": 1.0, + "learning_rate": 3.2347187399065626e-05, + "loss": 3.5519, + "step": 1078272 + }, + { + "epoch": 1.0, + "learning_rate": 3.2338817830358835e-05, + "loss": 3.5699, + "step": 1078784 + }, + { + "epoch": 1.0, + "learning_rate": 3.2330431882848315e-05, + "loss": 3.5528, + "step": 1079296 + }, + { + "epoch": 1.0, + "learning_rate": 3.2322045935337795e-05, + "loss": 3.5554, + "step": 1079808 + }, + { + "epoch": 1.0, + "learning_rate": 3.2313659987827275e-05, + "loss": 3.5576, + "step": 1080320 + }, + { + "epoch": 1.0, + "learning_rate": 3.2305290419120484e-05, + "loss": 3.5678, + "step": 1080832 + }, + { + "epoch": 1.0, + "learning_rate": 3.229690447160997e-05, + "loss": 3.5425, + "step": 1081344 + }, + { + "epoch": 1.0, + "learning_rate": 3.228851852409945e-05, + "loss": 3.5507, + "step": 1081856 + }, + { + "epoch": 1.0, + "learning_rate": 3.228013257658893e-05, + "loss": 3.5571, + "step": 1082368 + }, + { + "epoch": 1.0, + "learning_rate": 3.227176300788214e-05, + "loss": 3.5411, + "step": 1082880 + }, + { + "epoch": 1.0, + "learning_rate": 3.226337706037162e-05, + "loss": 3.5478, + "step": 1083392 + }, + { + "epoch": 1.01, + "learning_rate": 3.22549911128611e-05, + "loss": 3.5563, + "step": 1083904 + }, + { + "epoch": 1.01, + "learning_rate": 3.224660516535057e-05, + "loss": 3.5618, + "step": 1084416 + }, + { + "epoch": 1.01, + "learning_rate": 3.223823559664379e-05, + "loss": 3.5569, + "step": 1084928 + }, + { + "epoch": 1.01, + "learning_rate": 3.222984964913327e-05, + "loss": 3.5617, + "step": 1085440 + }, + { + "epoch": 1.01, + "learning_rate": 3.222146370162275e-05, + "loss": 3.5458, + "step": 1085952 + }, + { + "epoch": 1.01, + "learning_rate": 3.221307775411222e-05, + "loss": 3.5567, + "step": 1086464 + }, + { + "epoch": 1.01, + "learning_rate": 3.220470818540544e-05, + "loss": 3.5547, + "step": 1086976 + }, + { + "epoch": 1.01, + "learning_rate": 3.2196322237894925e-05, + "loss": 3.5387, + "step": 1087488 + }, + { + "epoch": 1.01, + "learning_rate": 3.2187936290384405e-05, + "loss": 3.5532, + "step": 1088000 + }, + { + "epoch": 1.01, + "learning_rate": 3.217955034287388e-05, + "loss": 3.545, + "step": 1088512 + }, + { + "epoch": 1.01, + "learning_rate": 3.2171180774167094e-05, + "loss": 3.5448, + "step": 1089024 + }, + { + "epoch": 1.01, + "learning_rate": 3.2162794826656574e-05, + "loss": 3.5521, + "step": 1089536 + }, + { + "epoch": 1.01, + "learning_rate": 3.215440887914605e-05, + "loss": 3.5631, + "step": 1090048 + }, + { + "epoch": 1.01, + "learning_rate": 3.214602293163553e-05, + "loss": 3.5453, + "step": 1090560 + }, + { + "epoch": 1.01, + "learning_rate": 3.213765336292874e-05, + "loss": 3.5581, + "step": 1091072 + }, + { + "epoch": 1.01, + "learning_rate": 3.212926741541822e-05, + "loss": 3.5531, + "step": 1091584 + }, + { + "epoch": 1.01, + "learning_rate": 3.2120881467907696e-05, + "loss": 3.5522, + "step": 1092096 + }, + { + "epoch": 1.01, + "learning_rate": 3.211251189920091e-05, + "loss": 3.5537, + "step": 1092608 + }, + { + "epoch": 1.01, + "learning_rate": 3.210412595169039e-05, + "loss": 3.5374, + "step": 1093120 + }, + { + "epoch": 1.01, + "learning_rate": 3.209574000417987e-05, + "loss": 3.5509, + "step": 1093632 + }, + { + "epoch": 1.01, + "learning_rate": 3.208735405666935e-05, + "loss": 3.5493, + "step": 1094144 + }, + { + "epoch": 1.01, + "learning_rate": 3.207898448796257e-05, + "loss": 3.5544, + "step": 1094656 + }, + { + "epoch": 1.01, + "learning_rate": 3.207059854045205e-05, + "loss": 3.5516, + "step": 1095168 + }, + { + "epoch": 1.01, + "learning_rate": 3.206221259294152e-05, + "loss": 3.5369, + "step": 1095680 + }, + { + "epoch": 1.01, + "learning_rate": 3.2053826645431e-05, + "loss": 3.5386, + "step": 1096192 + }, + { + "epoch": 1.01, + "learning_rate": 3.2045457076724216e-05, + "loss": 3.5431, + "step": 1096704 + }, + { + "epoch": 1.01, + "learning_rate": 3.2037087508017425e-05, + "loss": 3.5644, + "step": 1097216 + }, + { + "epoch": 1.01, + "learning_rate": 3.2028701560506905e-05, + "loss": 3.5333, + "step": 1097728 + }, + { + "epoch": 1.01, + "learning_rate": 3.2020315612996385e-05, + "loss": 3.5571, + "step": 1098240 + }, + { + "epoch": 1.01, + "learning_rate": 3.2011929665485865e-05, + "loss": 3.5492, + "step": 1098752 + }, + { + "epoch": 1.01, + "learning_rate": 3.2003543717975345e-05, + "loss": 3.5319, + "step": 1099264 + }, + { + "epoch": 1.01, + "learning_rate": 3.1995157770464825e-05, + "loss": 3.5517, + "step": 1099776 + }, + { + "epoch": 1.01, + "learning_rate": 3.1986771822954305e-05, + "loss": 3.5418, + "step": 1100288 + }, + { + "epoch": 1.01, + "learning_rate": 3.1978385875443785e-05, + "loss": 3.5345, + "step": 1100800 + }, + { + "epoch": 1.01, + "learning_rate": 3.1970016306736994e-05, + "loss": 3.536, + "step": 1101312 + }, + { + "epoch": 1.01, + "learning_rate": 3.1961630359226474e-05, + "loss": 3.5531, + "step": 1101824 + }, + { + "epoch": 1.01, + "learning_rate": 3.1953244411715954e-05, + "loss": 3.5455, + "step": 1102336 + }, + { + "epoch": 1.01, + "learning_rate": 3.1944858464205434e-05, + "loss": 3.5376, + "step": 1102848 + }, + { + "epoch": 1.01, + "learning_rate": 3.193648889549864e-05, + "loss": 3.536, + "step": 1103360 + }, + { + "epoch": 1.01, + "learning_rate": 3.192810294798812e-05, + "loss": 3.5371, + "step": 1103872 + }, + { + "epoch": 1.01, + "learning_rate": 3.19197170004776e-05, + "loss": 3.5458, + "step": 1104384 + }, + { + "epoch": 1.01, + "learning_rate": 3.191133105296708e-05, + "loss": 3.5492, + "step": 1104896 + }, + { + "epoch": 1.01, + "learning_rate": 3.19029614842603e-05, + "loss": 3.5508, + "step": 1105408 + }, + { + "epoch": 1.01, + "learning_rate": 3.189457553674978e-05, + "loss": 3.5533, + "step": 1105920 + }, + { + "epoch": 1.01, + "learning_rate": 3.188618958923926e-05, + "loss": 3.5509, + "step": 1106432 + }, + { + "epoch": 1.01, + "learning_rate": 3.187780364172874e-05, + "loss": 3.5496, + "step": 1106944 + }, + { + "epoch": 1.01, + "learning_rate": 3.186943407302195e-05, + "loss": 3.5457, + "step": 1107456 + }, + { + "epoch": 1.01, + "learning_rate": 3.186104812551143e-05, + "loss": 3.5443, + "step": 1107968 + }, + { + "epoch": 1.01, + "learning_rate": 3.185266217800091e-05, + "loss": 3.5425, + "step": 1108480 + }, + { + "epoch": 1.01, + "learning_rate": 3.184427623049039e-05, + "loss": 3.543, + "step": 1108992 + }, + { + "epoch": 1.01, + "learning_rate": 3.18359066617836e-05, + "loss": 3.5449, + "step": 1109504 + }, + { + "epoch": 1.01, + "learning_rate": 3.182752071427308e-05, + "loss": 3.5492, + "step": 1110016 + }, + { + "epoch": 1.01, + "learning_rate": 3.181915114556629e-05, + "loss": 3.5574, + "step": 1110528 + }, + { + "epoch": 1.01, + "learning_rate": 3.181076519805577e-05, + "loss": 3.5449, + "step": 1111040 + }, + { + "epoch": 1.01, + "learning_rate": 3.180237925054525e-05, + "loss": 3.5297, + "step": 1111552 + }, + { + "epoch": 1.01, + "learning_rate": 3.179399330303473e-05, + "loss": 3.5449, + "step": 1112064 + }, + { + "epoch": 1.01, + "learning_rate": 3.178560735552421e-05, + "loss": 3.5497, + "step": 1112576 + }, + { + "epoch": 1.01, + "learning_rate": 3.177722140801369e-05, + "loss": 3.5537, + "step": 1113088 + }, + { + "epoch": 1.01, + "learning_rate": 3.176883546050317e-05, + "loss": 3.5421, + "step": 1113600 + }, + { + "epoch": 1.01, + "learning_rate": 3.176044951299265e-05, + "loss": 3.5567, + "step": 1114112 + }, + { + "epoch": 1.02, + "learning_rate": 3.175207994428586e-05, + "loss": 3.5468, + "step": 1114624 + }, + { + "epoch": 1.02, + "learning_rate": 3.174369399677534e-05, + "loss": 3.543, + "step": 1115136 + }, + { + "epoch": 1.02, + "learning_rate": 3.173530804926482e-05, + "loss": 3.5432, + "step": 1115648 + }, + { + "epoch": 1.02, + "learning_rate": 3.17269221017543e-05, + "loss": 3.5523, + "step": 1116160 + }, + { + "epoch": 1.02, + "learning_rate": 3.171855253304751e-05, + "loss": 3.548, + "step": 1116672 + }, + { + "epoch": 1.02, + "learning_rate": 3.171016658553699e-05, + "loss": 3.5549, + "step": 1117184 + }, + { + "epoch": 1.02, + "learning_rate": 3.170178063802647e-05, + "loss": 3.5389, + "step": 1117696 + }, + { + "epoch": 1.02, + "learning_rate": 3.169339469051596e-05, + "loss": 3.5389, + "step": 1118208 + }, + { + "epoch": 1.02, + "learning_rate": 3.1685025121809166e-05, + "loss": 3.5428, + "step": 1118720 + }, + { + "epoch": 1.02, + "learning_rate": 3.1676639174298646e-05, + "loss": 3.5554, + "step": 1119232 + }, + { + "epoch": 1.02, + "learning_rate": 3.1668253226788126e-05, + "loss": 3.5471, + "step": 1119744 + }, + { + "epoch": 1.02, + "learning_rate": 3.1659867279277606e-05, + "loss": 3.5428, + "step": 1120256 + }, + { + "epoch": 1.02, + "learning_rate": 3.1651497710570815e-05, + "loss": 3.5381, + "step": 1120768 + }, + { + "epoch": 1.02, + "learning_rate": 3.1643111763060295e-05, + "loss": 3.5399, + "step": 1121280 + }, + { + "epoch": 1.02, + "learning_rate": 3.1634725815549775e-05, + "loss": 3.5478, + "step": 1121792 + }, + { + "epoch": 1.02, + "learning_rate": 3.1626339868039255e-05, + "loss": 3.5372, + "step": 1122304 + }, + { + "epoch": 1.02, + "learning_rate": 3.1617970299332464e-05, + "loss": 3.5405, + "step": 1122816 + }, + { + "epoch": 1.02, + "learning_rate": 3.1609584351821944e-05, + "loss": 3.5473, + "step": 1123328 + }, + { + "epoch": 1.02, + "learning_rate": 3.1601198404311424e-05, + "loss": 3.5495, + "step": 1123840 + }, + { + "epoch": 1.02, + "learning_rate": 3.159281245680091e-05, + "loss": 3.5417, + "step": 1124352 + }, + { + "epoch": 1.02, + "learning_rate": 3.158444288809412e-05, + "loss": 3.5426, + "step": 1124864 + }, + { + "epoch": 1.02, + "learning_rate": 3.15760569405836e-05, + "loss": 3.5366, + "step": 1125376 + }, + { + "epoch": 1.02, + "learning_rate": 3.156767099307308e-05, + "loss": 3.5509, + "step": 1125888 + }, + { + "epoch": 1.02, + "learning_rate": 3.155928504556256e-05, + "loss": 3.5472, + "step": 1126400 + }, + { + "epoch": 1.02, + "learning_rate": 3.155091547685577e-05, + "loss": 3.5424, + "step": 1126912 + }, + { + "epoch": 1.02, + "learning_rate": 3.154252952934525e-05, + "loss": 3.5485, + "step": 1127424 + }, + { + "epoch": 1.02, + "learning_rate": 3.153414358183473e-05, + "loss": 3.5498, + "step": 1127936 + }, + { + "epoch": 1.02, + "learning_rate": 3.152575763432421e-05, + "loss": 3.543, + "step": 1128448 + }, + { + "epoch": 1.02, + "learning_rate": 3.151738806561742e-05, + "loss": 3.5414, + "step": 1128960 + }, + { + "epoch": 1.02, + "learning_rate": 3.15090021181069e-05, + "loss": 3.5473, + "step": 1129472 + }, + { + "epoch": 1.02, + "learning_rate": 3.150061617059638e-05, + "loss": 3.5377, + "step": 1129984 + }, + { + "epoch": 1.02, + "learning_rate": 3.1492230223085864e-05, + "loss": 3.533, + "step": 1130496 + }, + { + "epoch": 1.02, + "learning_rate": 3.1483860654379074e-05, + "loss": 3.5411, + "step": 1131008 + }, + { + "epoch": 1.02, + "learning_rate": 3.1475474706868553e-05, + "loss": 3.5404, + "step": 1131520 + }, + { + "epoch": 1.02, + "learning_rate": 3.1467088759358033e-05, + "loss": 3.5492, + "step": 1132032 + }, + { + "epoch": 1.02, + "learning_rate": 3.145871919065124e-05, + "loss": 3.536, + "step": 1132544 + }, + { + "epoch": 1.02, + "learning_rate": 3.145033324314072e-05, + "loss": 3.5435, + "step": 1133056 + }, + { + "epoch": 1.02, + "learning_rate": 3.14419472956302e-05, + "loss": 3.534, + "step": 1133568 + }, + { + "epoch": 1.02, + "learning_rate": 3.143356134811968e-05, + "loss": 3.5405, + "step": 1134080 + }, + { + "epoch": 1.02, + "learning_rate": 3.142517540060916e-05, + "loss": 3.5473, + "step": 1134592 + }, + { + "epoch": 1.02, + "learning_rate": 3.141678945309864e-05, + "loss": 3.5471, + "step": 1135104 + }, + { + "epoch": 1.02, + "learning_rate": 3.140840350558812e-05, + "loss": 3.545, + "step": 1135616 + }, + { + "epoch": 1.02, + "learning_rate": 3.14000175580776e-05, + "loss": 3.5328, + "step": 1136128 + }, + { + "epoch": 1.02, + "learning_rate": 3.139164798937082e-05, + "loss": 3.548, + "step": 1136640 + }, + { + "epoch": 1.02, + "learning_rate": 3.13832620418603e-05, + "loss": 3.547, + "step": 1137152 + }, + { + "epoch": 1.02, + "learning_rate": 3.137487609434978e-05, + "loss": 3.5439, + "step": 1137664 + }, + { + "epoch": 1.02, + "learning_rate": 3.136649014683925e-05, + "loss": 3.5481, + "step": 1138176 + }, + { + "epoch": 1.02, + "learning_rate": 3.135812057813247e-05, + "loss": 3.5447, + "step": 1138688 + }, + { + "epoch": 1.02, + "learning_rate": 3.134973463062195e-05, + "loss": 3.556, + "step": 1139200 + }, + { + "epoch": 1.02, + "learning_rate": 3.134134868311142e-05, + "loss": 3.5509, + "step": 1139712 + }, + { + "epoch": 1.02, + "learning_rate": 3.13329627356009e-05, + "loss": 3.5384, + "step": 1140224 + }, + { + "epoch": 1.02, + "learning_rate": 3.1324593166894116e-05, + "loss": 3.5431, + "step": 1140736 + }, + { + "epoch": 1.02, + "learning_rate": 3.1316207219383596e-05, + "loss": 3.5409, + "step": 1141248 + }, + { + "epoch": 1.02, + "learning_rate": 3.130782127187307e-05, + "loss": 3.5398, + "step": 1141760 + }, + { + "epoch": 1.02, + "learning_rate": 3.1299435324362556e-05, + "loss": 3.5369, + "step": 1142272 + }, + { + "epoch": 1.02, + "learning_rate": 3.129106575565577e-05, + "loss": 3.5448, + "step": 1142784 + }, + { + "epoch": 1.02, + "learning_rate": 3.128267980814525e-05, + "loss": 3.5358, + "step": 1143296 + }, + { + "epoch": 1.02, + "learning_rate": 3.1274293860634725e-05, + "loss": 3.5478, + "step": 1143808 + }, + { + "epoch": 1.02, + "learning_rate": 3.1265907913124205e-05, + "loss": 3.5371, + "step": 1144320 + }, + { + "epoch": 1.03, + "eval_loss": 3.842536449432373, + "eval_runtime": 303.3677, + "eval_samples_per_second": 1257.85, + "eval_steps_per_second": 39.309, + "step": 1144800 + }, + { + "epoch": 0.0, + "learning_rate": 3.125753834441742e-05, + "loss": 3.5117, + "step": 1144832 + }, + { + "epoch": 0.0, + "learning_rate": 3.1249152396906894e-05, + "loss": 3.5367, + "step": 1145344 + }, + { + "epoch": 0.0, + "learning_rate": 3.1240766449396374e-05, + "loss": 3.5307, + "step": 1145856 + }, + { + "epoch": 0.0, + "learning_rate": 3.1232380501885854e-05, + "loss": 3.5482, + "step": 1146368 + }, + { + "epoch": 0.0, + "learning_rate": 3.122401093317907e-05, + "loss": 3.5468, + "step": 1146880 + }, + { + "epoch": 0.0, + "learning_rate": 3.121562498566854e-05, + "loss": 3.5413, + "step": 1147392 + }, + { + "epoch": 0.0, + "learning_rate": 3.120723903815802e-05, + "loss": 3.5339, + "step": 1147904 + }, + { + "epoch": 0.0, + "learning_rate": 3.119885309064751e-05, + "loss": 3.5319, + "step": 1148416 + }, + { + "epoch": 0.0, + "learning_rate": 3.1190483521940725e-05, + "loss": 3.5439, + "step": 1148928 + }, + { + "epoch": 0.0, + "learning_rate": 3.11820975744302e-05, + "loss": 3.543, + "step": 1149440 + }, + { + "epoch": 0.0, + "learning_rate": 3.117371162691968e-05, + "loss": 3.5437, + "step": 1149952 + }, + { + "epoch": 0.0, + "learning_rate": 3.116532567940916e-05, + "loss": 3.5394, + "step": 1150464 + }, + { + "epoch": 0.0, + "learning_rate": 3.115695611070237e-05, + "loss": 3.5499, + "step": 1150976 + }, + { + "epoch": 0.0, + "learning_rate": 3.114857016319185e-05, + "loss": 3.5212, + "step": 1151488 + }, + { + "epoch": 0.0, + "learning_rate": 3.114018421568133e-05, + "loss": 3.5351, + "step": 1152000 + }, + { + "epoch": 0.0, + "learning_rate": 3.113179826817081e-05, + "loss": 3.5285, + "step": 1152512 + }, + { + "epoch": 0.0, + "learning_rate": 3.1123428699464017e-05, + "loss": 3.5378, + "step": 1153024 + }, + { + "epoch": 0.0, + "learning_rate": 3.1115042751953497e-05, + "loss": 3.5328, + "step": 1153536 + }, + { + "epoch": 0.0, + "learning_rate": 3.1106656804442976e-05, + "loss": 3.5337, + "step": 1154048 + }, + { + "epoch": 0.0, + "learning_rate": 3.109827085693246e-05, + "loss": 3.5347, + "step": 1154560 + }, + { + "epoch": 0.0, + "learning_rate": 3.108990128822567e-05, + "loss": 3.556, + "step": 1155072 + }, + { + "epoch": 0.0, + "learning_rate": 3.108153171951889e-05, + "loss": 3.5379, + "step": 1155584 + }, + { + "epoch": 0.0, + "learning_rate": 3.107314577200837e-05, + "loss": 3.5345, + "step": 1156096 + }, + { + "epoch": 0.0, + "learning_rate": 3.106475982449784e-05, + "loss": 3.5446, + "step": 1156608 + }, + { + "epoch": 0.0, + "learning_rate": 3.105637387698732e-05, + "loss": 3.5496, + "step": 1157120 + }, + { + "epoch": 0.0, + "learning_rate": 3.10479879294768e-05, + "loss": 3.5315, + "step": 1157632 + }, + { + "epoch": 0.0, + "learning_rate": 3.103960198196628e-05, + "loss": 3.5329, + "step": 1158144 + }, + { + "epoch": 0.0, + "learning_rate": 3.103121603445576e-05, + "loss": 3.5451, + "step": 1158656 + }, + { + "epoch": 0.0, + "learning_rate": 3.102283008694524e-05, + "loss": 3.5275, + "step": 1159168 + }, + { + "epoch": 0.0, + "learning_rate": 3.101446051823845e-05, + "loss": 3.5329, + "step": 1159680 + }, + { + "epoch": 0.01, + "learning_rate": 3.100607457072793e-05, + "loss": 3.538, + "step": 1160192 + }, + { + "epoch": 0.01, + "learning_rate": 3.099768862321742e-05, + "loss": 3.5492, + "step": 1160704 + }, + { + "epoch": 0.01, + "learning_rate": 3.09893026757069e-05, + "loss": 3.5418, + "step": 1161216 + }, + { + "epoch": 0.01, + "learning_rate": 3.0980933107000106e-05, + "loss": 3.5424, + "step": 1161728 + }, + { + "epoch": 0.01, + "learning_rate": 3.0972547159489586e-05, + "loss": 3.5326, + "step": 1162240 + }, + { + "epoch": 0.01, + "learning_rate": 3.0964161211979066e-05, + "loss": 3.5442, + "step": 1162752 + }, + { + "epoch": 0.01, + "learning_rate": 3.0955775264468546e-05, + "loss": 3.542, + "step": 1163264 + }, + { + "epoch": 0.01, + "learning_rate": 3.0947405695761755e-05, + "loss": 3.5229, + "step": 1163776 + }, + { + "epoch": 0.01, + "learning_rate": 3.0939019748251235e-05, + "loss": 3.5382, + "step": 1164288 + }, + { + "epoch": 0.01, + "learning_rate": 3.0930633800740715e-05, + "loss": 3.5271, + "step": 1164800 + }, + { + "epoch": 0.01, + "learning_rate": 3.0922247853230195e-05, + "loss": 3.5317, + "step": 1165312 + }, + { + "epoch": 0.01, + "learning_rate": 3.091389466332714e-05, + "loss": 3.5338, + "step": 1165824 + }, + { + "epoch": 0.01, + "learning_rate": 3.090550871581662e-05, + "loss": 3.5466, + "step": 1166336 + }, + { + "epoch": 0.01, + "learning_rate": 3.08971227683061e-05, + "loss": 3.5361, + "step": 1166848 + }, + { + "epoch": 0.01, + "learning_rate": 3.088873682079558e-05, + "loss": 3.5375, + "step": 1167360 + }, + { + "epoch": 0.01, + "learning_rate": 3.088035087328506e-05, + "loss": 3.5421, + "step": 1167872 + }, + { + "epoch": 0.01, + "learning_rate": 3.087196492577454e-05, + "loss": 3.5302, + "step": 1168384 + }, + { + "epoch": 0.01, + "learning_rate": 3.086357897826402e-05, + "loss": 3.5455, + "step": 1168896 + }, + { + "epoch": 0.01, + "learning_rate": 3.08551930307535e-05, + "loss": 3.5214, + "step": 1169408 + }, + { + "epoch": 0.01, + "learning_rate": 3.084682346204671e-05, + "loss": 3.5304, + "step": 1169920 + }, + { + "epoch": 0.01, + "learning_rate": 3.083843751453619e-05, + "loss": 3.537, + "step": 1170432 + }, + { + "epoch": 0.01, + "learning_rate": 3.083005156702567e-05, + "loss": 3.537, + "step": 1170944 + }, + { + "epoch": 0.01, + "learning_rate": 3.082166561951515e-05, + "loss": 3.5379, + "step": 1171456 + }, + { + "epoch": 0.01, + "learning_rate": 3.081329605080836e-05, + "loss": 3.5207, + "step": 1171968 + }, + { + "epoch": 0.01, + "learning_rate": 3.080491010329784e-05, + "loss": 3.5296, + "step": 1172480 + }, + { + "epoch": 0.01, + "learning_rate": 3.079652415578732e-05, + "loss": 3.5248, + "step": 1172992 + }, + { + "epoch": 0.01, + "learning_rate": 3.078815458708053e-05, + "loss": 3.5515, + "step": 1173504 + }, + { + "epoch": 0.01, + "learning_rate": 3.077976863957001e-05, + "loss": 3.5174, + "step": 1174016 + }, + { + "epoch": 0.01, + "learning_rate": 3.077138269205949e-05, + "loss": 3.5414, + "step": 1174528 + }, + { + "epoch": 0.01, + "learning_rate": 3.076299674454897e-05, + "loss": 3.5332, + "step": 1175040 + }, + { + "epoch": 0.01, + "learning_rate": 3.075461079703845e-05, + "loss": 3.515, + "step": 1175552 + }, + { + "epoch": 0.01, + "learning_rate": 3.074622484952793e-05, + "loss": 3.5372, + "step": 1176064 + }, + { + "epoch": 0.01, + "learning_rate": 3.073783890201741e-05, + "loss": 3.5284, + "step": 1176576 + }, + { + "epoch": 0.01, + "learning_rate": 3.072945295450689e-05, + "loss": 3.5163, + "step": 1177088 + }, + { + "epoch": 0.01, + "learning_rate": 3.07210833858001e-05, + "loss": 3.5249, + "step": 1177600 + }, + { + "epoch": 0.01, + "learning_rate": 3.071269743828958e-05, + "loss": 3.5416, + "step": 1178112 + }, + { + "epoch": 0.01, + "learning_rate": 3.070431149077906e-05, + "loss": 3.528, + "step": 1178624 + }, + { + "epoch": 0.01, + "learning_rate": 3.069592554326854e-05, + "loss": 3.526, + "step": 1179136 + }, + { + "epoch": 0.01, + "learning_rate": 3.068755597456176e-05, + "loss": 3.5215, + "step": 1179648 + }, + { + "epoch": 0.01, + "learning_rate": 3.067917002705124e-05, + "loss": 3.5199, + "step": 1180160 + }, + { + "epoch": 0.01, + "learning_rate": 3.067078407954072e-05, + "loss": 3.5346, + "step": 1180672 + }, + { + "epoch": 0.01, + "learning_rate": 3.06623981320302e-05, + "loss": 3.5334, + "step": 1181184 + }, + { + "epoch": 0.01, + "learning_rate": 3.065402856332341e-05, + "loss": 3.5342, + "step": 1181696 + }, + { + "epoch": 0.01, + "learning_rate": 3.064564261581289e-05, + "loss": 3.5382, + "step": 1182208 + }, + { + "epoch": 0.01, + "learning_rate": 3.063725666830237e-05, + "loss": 3.5352, + "step": 1182720 + }, + { + "epoch": 0.01, + "learning_rate": 3.0628887099595576e-05, + "loss": 3.5333, + "step": 1183232 + }, + { + "epoch": 0.01, + "learning_rate": 3.0620501152085056e-05, + "loss": 3.531, + "step": 1183744 + }, + { + "epoch": 0.01, + "learning_rate": 3.0612115204574536e-05, + "loss": 3.5292, + "step": 1184256 + }, + { + "epoch": 0.01, + "learning_rate": 3.0603729257064016e-05, + "loss": 3.5283, + "step": 1184768 + }, + { + "epoch": 0.01, + "learning_rate": 3.0595359688357225e-05, + "loss": 3.5321, + "step": 1185280 + }, + { + "epoch": 0.01, + "learning_rate": 3.058697374084671e-05, + "loss": 3.5275, + "step": 1185792 + }, + { + "epoch": 0.01, + "learning_rate": 3.057858779333619e-05, + "loss": 3.5361, + "step": 1186304 + }, + { + "epoch": 0.01, + "learning_rate": 3.057020184582567e-05, + "loss": 3.5365, + "step": 1186816 + }, + { + "epoch": 0.01, + "learning_rate": 3.056183227711888e-05, + "loss": 3.5318, + "step": 1187328 + }, + { + "epoch": 0.01, + "learning_rate": 3.055344632960836e-05, + "loss": 3.5173, + "step": 1187840 + }, + { + "epoch": 0.01, + "learning_rate": 3.054506038209784e-05, + "loss": 3.5254, + "step": 1188352 + }, + { + "epoch": 0.01, + "learning_rate": 3.053667443458732e-05, + "loss": 3.5404, + "step": 1188864 + }, + { + "epoch": 0.01, + "learning_rate": 3.052830486588053e-05, + "loss": 3.534, + "step": 1189376 + }, + { + "epoch": 0.01, + "learning_rate": 3.051991891837001e-05, + "loss": 3.5314, + "step": 1189888 + }, + { + "epoch": 0.01, + "learning_rate": 3.051153297085949e-05, + "loss": 3.5423, + "step": 1190400 + }, + { + "epoch": 0.02, + "learning_rate": 3.0503147023348973e-05, + "loss": 3.5306, + "step": 1190912 + }, + { + "epoch": 0.02, + "learning_rate": 3.0494777454642182e-05, + "loss": 3.529, + "step": 1191424 + }, + { + "epoch": 0.02, + "learning_rate": 3.0486391507131662e-05, + "loss": 3.5276, + "step": 1191936 + }, + { + "epoch": 0.02, + "learning_rate": 3.0478005559621142e-05, + "loss": 3.538, + "step": 1192448 + }, + { + "epoch": 0.02, + "learning_rate": 3.046961961211062e-05, + "loss": 3.5322, + "step": 1192960 + }, + { + "epoch": 0.02, + "learning_rate": 3.0461250043403834e-05, + "loss": 3.5431, + "step": 1193472 + }, + { + "epoch": 0.02, + "learning_rate": 3.0452864095893314e-05, + "loss": 3.5195, + "step": 1193984 + }, + { + "epoch": 0.02, + "learning_rate": 3.0444478148382794e-05, + "loss": 3.5301, + "step": 1194496 + }, + { + "epoch": 0.02, + "learning_rate": 3.0436092200872274e-05, + "loss": 3.5257, + "step": 1195008 + }, + { + "epoch": 0.02, + "learning_rate": 3.0427722632165483e-05, + "loss": 3.5375, + "step": 1195520 + }, + { + "epoch": 0.02, + "learning_rate": 3.0419336684654963e-05, + "loss": 3.5358, + "step": 1196032 + }, + { + "epoch": 0.02, + "learning_rate": 3.0410950737144443e-05, + "loss": 3.5245, + "step": 1196544 + }, + { + "epoch": 0.02, + "learning_rate": 3.040256478963392e-05, + "loss": 3.5279, + "step": 1197056 + }, + { + "epoch": 0.02, + "learning_rate": 3.0394195220927135e-05, + "loss": 3.5268, + "step": 1197568 + }, + { + "epoch": 0.02, + "learning_rate": 3.0385809273416615e-05, + "loss": 3.5331, + "step": 1198080 + }, + { + "epoch": 0.02, + "learning_rate": 3.0377423325906095e-05, + "loss": 3.5178, + "step": 1198592 + }, + { + "epoch": 0.02, + "learning_rate": 3.0369037378395572e-05, + "loss": 3.528, + "step": 1199104 + }, + { + "epoch": 0.02, + "learning_rate": 3.0360667809688788e-05, + "loss": 3.5337, + "step": 1199616 + }, + { + "epoch": 0.02, + "learning_rate": 3.0352281862178268e-05, + "loss": 3.5296, + "step": 1200128 + }, + { + "epoch": 0.02, + "learning_rate": 3.0343895914667748e-05, + "loss": 3.5307, + "step": 1200640 + }, + { + "epoch": 0.02, + "learning_rate": 3.033550996715722e-05, + "loss": 3.5294, + "step": 1201152 + }, + { + "epoch": 0.02, + "learning_rate": 3.0327140398450437e-05, + "loss": 3.5188, + "step": 1201664 + }, + { + "epoch": 0.02, + "learning_rate": 3.0318754450939917e-05, + "loss": 3.5374, + "step": 1202176 + }, + { + "epoch": 0.02, + "learning_rate": 3.0310368503429393e-05, + "loss": 3.5313, + "step": 1202688 + }, + { + "epoch": 0.02, + "learning_rate": 3.0301982555918873e-05, + "loss": 3.5276, + "step": 1203200 + }, + { + "epoch": 0.02, + "learning_rate": 3.029361298721209e-05, + "loss": 3.5362, + "step": 1203712 + }, + { + "epoch": 0.02, + "learning_rate": 3.028522703970157e-05, + "loss": 3.5355, + "step": 1204224 + }, + { + "epoch": 0.02, + "learning_rate": 3.0276841092191042e-05, + "loss": 3.5288, + "step": 1204736 + }, + { + "epoch": 0.02, + "learning_rate": 3.0268455144680526e-05, + "loss": 3.5227, + "step": 1205248 + }, + { + "epoch": 0.02, + "learning_rate": 3.026008557597374e-05, + "loss": 3.5307, + "step": 1205760 + }, + { + "epoch": 0.02, + "learning_rate": 3.025169962846322e-05, + "loss": 3.5235, + "step": 1206272 + }, + { + "epoch": 0.02, + "learning_rate": 3.0243313680952695e-05, + "loss": 3.5214, + "step": 1206784 + }, + { + "epoch": 0.02, + "learning_rate": 3.0234927733442175e-05, + "loss": 3.5232, + "step": 1207296 + }, + { + "epoch": 0.02, + "learning_rate": 3.022655816473539e-05, + "loss": 3.5266, + "step": 1207808 + }, + { + "epoch": 0.02, + "learning_rate": 3.0218172217224867e-05, + "loss": 3.5319, + "step": 1208320 + }, + { + "epoch": 0.02, + "learning_rate": 3.0209786269714347e-05, + "loss": 3.5232, + "step": 1208832 + }, + { + "epoch": 0.02, + "learning_rate": 3.0201400322203827e-05, + "loss": 3.5278, + "step": 1209344 + }, + { + "epoch": 0.02, + "learning_rate": 3.0193030753497043e-05, + "loss": 3.5209, + "step": 1209856 + }, + { + "epoch": 0.02, + "learning_rate": 3.0184644805986516e-05, + "loss": 3.5284, + "step": 1210368 + }, + { + "epoch": 0.02, + "learning_rate": 3.0176258858475996e-05, + "loss": 3.5313, + "step": 1210880 + }, + { + "epoch": 0.02, + "learning_rate": 3.016787291096548e-05, + "loss": 3.5331, + "step": 1211392 + }, + { + "epoch": 0.02, + "learning_rate": 3.015950334225869e-05, + "loss": 3.531, + "step": 1211904 + }, + { + "epoch": 0.02, + "learning_rate": 3.015111739474817e-05, + "loss": 3.5207, + "step": 1212416 + }, + { + "epoch": 0.02, + "learning_rate": 3.014273144723765e-05, + "loss": 3.5276, + "step": 1212928 + }, + { + "epoch": 0.02, + "learning_rate": 3.0134345499727128e-05, + "loss": 3.5334, + "step": 1213440 + }, + { + "epoch": 0.02, + "learning_rate": 3.012597593102034e-05, + "loss": 3.5311, + "step": 1213952 + }, + { + "epoch": 0.02, + "learning_rate": 3.011758998350982e-05, + "loss": 3.5356, + "step": 1214464 + }, + { + "epoch": 0.02, + "learning_rate": 3.01092040359993e-05, + "loss": 3.5292, + "step": 1214976 + }, + { + "epoch": 0.02, + "learning_rate": 3.010081808848878e-05, + "loss": 3.5424, + "step": 1215488 + }, + { + "epoch": 0.02, + "learning_rate": 3.009244851978199e-05, + "loss": 3.5327, + "step": 1216000 + }, + { + "epoch": 0.02, + "learning_rate": 3.008406257227147e-05, + "loss": 3.5276, + "step": 1216512 + }, + { + "epoch": 0.02, + "learning_rate": 3.007567662476095e-05, + "loss": 3.5295, + "step": 1217024 + }, + { + "epoch": 0.02, + "learning_rate": 3.0067290677250433e-05, + "loss": 3.5255, + "step": 1217536 + }, + { + "epoch": 0.02, + "learning_rate": 3.0058921108543642e-05, + "loss": 3.5242, + "step": 1218048 + }, + { + "epoch": 0.02, + "learning_rate": 3.0050535161033122e-05, + "loss": 3.5213, + "step": 1218560 + }, + { + "epoch": 0.02, + "learning_rate": 3.0042149213522602e-05, + "loss": 3.5334, + "step": 1219072 + }, + { + "epoch": 0.02, + "learning_rate": 3.003377964481581e-05, + "loss": 3.5205, + "step": 1219584 + }, + { + "epoch": 0.02, + "learning_rate": 3.0025393697305294e-05, + "loss": 3.5333, + "step": 1220096 + }, + { + "epoch": 0.02, + "learning_rate": 3.0017007749794774e-05, + "loss": 3.5245, + "step": 1220608 + }, + { + "epoch": 0.03, + "learning_rate": 3.0008621802284254e-05, + "loss": 3.5303, + "step": 1221120 + }, + { + "epoch": 0.03, + "eval_loss": 3.8430826663970947, + "eval_runtime": 304.2619, + "eval_samples_per_second": 1254.153, + "eval_steps_per_second": 39.193, + "step": 1221120 + }, + { + "epoch": 1.0, + "learning_rate": 3.0000252233577463e-05, + "loss": 3.5187, + "step": 1221632 + }, + { + "epoch": 1.0, + "learning_rate": 2.9991866286066943e-05, + "loss": 3.5174, + "step": 1222144 + }, + { + "epoch": 1.0, + "learning_rate": 2.9983480338556423e-05, + "loss": 3.5311, + "step": 1222656 + }, + { + "epoch": 1.0, + "learning_rate": 2.9975094391045903e-05, + "loss": 3.5343, + "step": 1223168 + }, + { + "epoch": 1.0, + "learning_rate": 2.9966724822339116e-05, + "loss": 3.5299, + "step": 1223680 + }, + { + "epoch": 1.0, + "learning_rate": 2.9958338874828596e-05, + "loss": 3.5173, + "step": 1224192 + }, + { + "epoch": 1.0, + "learning_rate": 2.9949952927318076e-05, + "loss": 3.5213, + "step": 1224704 + }, + { + "epoch": 1.0, + "learning_rate": 2.9941566979807556e-05, + "loss": 3.5206, + "step": 1225216 + }, + { + "epoch": 1.0, + "learning_rate": 2.9933197411100765e-05, + "loss": 3.531, + "step": 1225728 + }, + { + "epoch": 1.0, + "learning_rate": 2.9924811463590248e-05, + "loss": 3.5257, + "step": 1226240 + }, + { + "epoch": 1.0, + "learning_rate": 2.9916425516079728e-05, + "loss": 3.5305, + "step": 1226752 + }, + { + "epoch": 1.0, + "learning_rate": 2.9908039568569208e-05, + "loss": 3.5339, + "step": 1227264 + }, + { + "epoch": 1.0, + "learning_rate": 2.9899669999862417e-05, + "loss": 3.51, + "step": 1227776 + }, + { + "epoch": 1.0, + "learning_rate": 2.9891284052351897e-05, + "loss": 3.5141, + "step": 1228288 + }, + { + "epoch": 1.0, + "learning_rate": 2.9882898104841377e-05, + "loss": 3.515, + "step": 1228800 + }, + { + "epoch": 1.0, + "learning_rate": 2.9874512157330857e-05, + "loss": 3.5243, + "step": 1229312 + }, + { + "epoch": 1.0, + "learning_rate": 2.986614258862407e-05, + "loss": 3.5214, + "step": 1229824 + }, + { + "epoch": 1.0, + "learning_rate": 2.985775664111355e-05, + "loss": 3.5223, + "step": 1230336 + }, + { + "epoch": 1.0, + "learning_rate": 2.984937069360303e-05, + "loss": 3.5205, + "step": 1230848 + }, + { + "epoch": 1.0, + "learning_rate": 2.984098474609251e-05, + "loss": 3.5418, + "step": 1231360 + }, + { + "epoch": 1.0, + "learning_rate": 2.9832631556189454e-05, + "loss": 3.5246, + "step": 1231872 + }, + { + "epoch": 1.0, + "learning_rate": 2.9824245608678934e-05, + "loss": 3.5227, + "step": 1232384 + }, + { + "epoch": 1.0, + "learning_rate": 2.981585966116841e-05, + "loss": 3.5277, + "step": 1232896 + }, + { + "epoch": 1.0, + "learning_rate": 2.980747371365789e-05, + "loss": 3.5387, + "step": 1233408 + }, + { + "epoch": 1.0, + "learning_rate": 2.979908776614737e-05, + "loss": 3.5166, + "step": 1233920 + }, + { + "epoch": 1.0, + "learning_rate": 2.979070181863685e-05, + "loss": 3.5224, + "step": 1234432 + }, + { + "epoch": 1.0, + "learning_rate": 2.978231587112633e-05, + "loss": 3.5258, + "step": 1234944 + }, + { + "epoch": 1.0, + "learning_rate": 2.977392992361581e-05, + "loss": 3.5148, + "step": 1235456 + }, + { + "epoch": 1.0, + "learning_rate": 2.9765560354909023e-05, + "loss": 3.5201, + "step": 1235968 + }, + { + "epoch": 1.01, + "learning_rate": 2.9757174407398503e-05, + "loss": 3.5232, + "step": 1236480 + }, + { + "epoch": 1.01, + "learning_rate": 2.9748788459887983e-05, + "loss": 3.5365, + "step": 1236992 + }, + { + "epoch": 1.01, + "learning_rate": 2.9740402512377463e-05, + "loss": 3.5248, + "step": 1237504 + }, + { + "epoch": 1.01, + "learning_rate": 2.9732032943670672e-05, + "loss": 3.531, + "step": 1238016 + }, + { + "epoch": 1.01, + "learning_rate": 2.9723646996160155e-05, + "loss": 3.5239, + "step": 1238528 + }, + { + "epoch": 1.01, + "learning_rate": 2.9715261048649635e-05, + "loss": 3.5256, + "step": 1239040 + }, + { + "epoch": 1.01, + "learning_rate": 2.9706875101139115e-05, + "loss": 3.5266, + "step": 1239552 + }, + { + "epoch": 1.01, + "learning_rate": 2.9698505532432324e-05, + "loss": 3.5107, + "step": 1240064 + }, + { + "epoch": 1.01, + "learning_rate": 2.9690119584921804e-05, + "loss": 3.5226, + "step": 1240576 + }, + { + "epoch": 1.01, + "learning_rate": 2.9681733637411284e-05, + "loss": 3.514, + "step": 1241088 + }, + { + "epoch": 1.01, + "learning_rate": 2.9673347689900764e-05, + "loss": 3.5203, + "step": 1241600 + }, + { + "epoch": 1.01, + "learning_rate": 2.9664994499997706e-05, + "loss": 3.5182, + "step": 1242112 + }, + { + "epoch": 1.01, + "learning_rate": 2.9656608552487186e-05, + "loss": 3.5312, + "step": 1242624 + }, + { + "epoch": 1.01, + "learning_rate": 2.9648222604976666e-05, + "loss": 3.5223, + "step": 1243136 + }, + { + "epoch": 1.01, + "learning_rate": 2.9639836657466146e-05, + "loss": 3.5228, + "step": 1243648 + }, + { + "epoch": 1.01, + "learning_rate": 2.9631450709955626e-05, + "loss": 3.529, + "step": 1244160 + }, + { + "epoch": 1.01, + "learning_rate": 2.962306476244511e-05, + "loss": 3.5187, + "step": 1244672 + }, + { + "epoch": 1.01, + "learning_rate": 2.961467881493459e-05, + "loss": 3.5308, + "step": 1245184 + }, + { + "epoch": 1.01, + "learning_rate": 2.960629286742407e-05, + "loss": 3.5073, + "step": 1245696 + }, + { + "epoch": 1.01, + "learning_rate": 2.9597923298717278e-05, + "loss": 3.5167, + "step": 1246208 + }, + { + "epoch": 1.01, + "learning_rate": 2.9589537351206758e-05, + "loss": 3.5243, + "step": 1246720 + }, + { + "epoch": 1.01, + "learning_rate": 2.9581151403696238e-05, + "loss": 3.525, + "step": 1247232 + }, + { + "epoch": 1.01, + "learning_rate": 2.9572765456185718e-05, + "loss": 3.5221, + "step": 1247744 + }, + { + "epoch": 1.01, + "learning_rate": 2.956439588747893e-05, + "loss": 3.5021, + "step": 1248256 + }, + { + "epoch": 1.01, + "learning_rate": 2.955600993996841e-05, + "loss": 3.5209, + "step": 1248768 + }, + { + "epoch": 1.01, + "learning_rate": 2.954762399245789e-05, + "loss": 3.5078, + "step": 1249280 + }, + { + "epoch": 1.01, + "learning_rate": 2.95392544237511e-05, + "loss": 3.5352, + "step": 1249792 + }, + { + "epoch": 1.01, + "learning_rate": 2.953086847624058e-05, + "loss": 3.5096, + "step": 1250304 + }, + { + "epoch": 1.01, + "learning_rate": 2.952248252873006e-05, + "loss": 3.5261, + "step": 1250816 + }, + { + "epoch": 1.01, + "learning_rate": 2.9514096581219543e-05, + "loss": 3.5152, + "step": 1251328 + }, + { + "epoch": 1.01, + "learning_rate": 2.9505710633709023e-05, + "loss": 3.5025, + "step": 1251840 + }, + { + "epoch": 1.01, + "learning_rate": 2.9497324686198503e-05, + "loss": 3.5237, + "step": 1252352 + }, + { + "epoch": 1.01, + "learning_rate": 2.9488938738687983e-05, + "loss": 3.5134, + "step": 1252864 + }, + { + "epoch": 1.01, + "learning_rate": 2.9480552791177463e-05, + "loss": 3.5021, + "step": 1253376 + }, + { + "epoch": 1.01, + "learning_rate": 2.947218322247067e-05, + "loss": 3.5098, + "step": 1253888 + }, + { + "epoch": 1.01, + "learning_rate": 2.946379727496015e-05, + "loss": 3.528, + "step": 1254400 + }, + { + "epoch": 1.01, + "learning_rate": 2.9455411327449635e-05, + "loss": 3.515, + "step": 1254912 + }, + { + "epoch": 1.01, + "learning_rate": 2.9447025379939115e-05, + "loss": 3.5083, + "step": 1255424 + }, + { + "epoch": 1.01, + "learning_rate": 2.9438655811232324e-05, + "loss": 3.5092, + "step": 1255936 + }, + { + "epoch": 1.01, + "learning_rate": 2.9430269863721804e-05, + "loss": 3.5074, + "step": 1256448 + }, + { + "epoch": 1.01, + "learning_rate": 2.9421883916211284e-05, + "loss": 3.5161, + "step": 1256960 + }, + { + "epoch": 1.01, + "learning_rate": 2.9413497968700764e-05, + "loss": 3.5215, + "step": 1257472 + }, + { + "epoch": 1.01, + "learning_rate": 2.9405128399993976e-05, + "loss": 3.5197, + "step": 1257984 + }, + { + "epoch": 1.01, + "learning_rate": 2.9396742452483456e-05, + "loss": 3.5282, + "step": 1258496 + }, + { + "epoch": 1.01, + "learning_rate": 2.9388356504972936e-05, + "loss": 3.5186, + "step": 1259008 + }, + { + "epoch": 1.01, + "learning_rate": 2.9379970557462416e-05, + "loss": 3.5225, + "step": 1259520 + }, + { + "epoch": 1.01, + "learning_rate": 2.9371600988755625e-05, + "loss": 3.5119, + "step": 1260032 + }, + { + "epoch": 1.01, + "learning_rate": 2.9363215041245105e-05, + "loss": 3.5195, + "step": 1260544 + }, + { + "epoch": 1.01, + "learning_rate": 2.935482909373459e-05, + "loss": 3.5176, + "step": 1261056 + }, + { + "epoch": 1.01, + "learning_rate": 2.934644314622407e-05, + "loss": 3.511, + "step": 1261568 + }, + { + "epoch": 1.01, + "learning_rate": 2.9338073577517278e-05, + "loss": 3.5126, + "step": 1262080 + }, + { + "epoch": 1.01, + "learning_rate": 2.9329687630006758e-05, + "loss": 3.5224, + "step": 1262592 + }, + { + "epoch": 1.01, + "learning_rate": 2.9321318061299967e-05, + "loss": 3.5232, + "step": 1263104 + }, + { + "epoch": 1.01, + "learning_rate": 2.931293211378945e-05, + "loss": 3.5161, + "step": 1263616 + }, + { + "epoch": 1.01, + "learning_rate": 2.930454616627893e-05, + "loss": 3.5023, + "step": 1264128 + }, + { + "epoch": 1.01, + "learning_rate": 2.929616021876841e-05, + "loss": 3.5153, + "step": 1264640 + }, + { + "epoch": 1.01, + "learning_rate": 2.928777427125789e-05, + "loss": 3.5248, + "step": 1265152 + }, + { + "epoch": 1.01, + "learning_rate": 2.9279388323747363e-05, + "loss": 3.5247, + "step": 1265664 + }, + { + "epoch": 1.01, + "learning_rate": 2.9271002376236843e-05, + "loss": 3.5144, + "step": 1266176 + }, + { + "epoch": 1.01, + "learning_rate": 2.9262616428726326e-05, + "loss": 3.5267, + "step": 1266688 + }, + { + "epoch": 1.02, + "learning_rate": 2.9254246860019542e-05, + "loss": 3.519, + "step": 1267200 + }, + { + "epoch": 1.02, + "learning_rate": 2.9245860912509015e-05, + "loss": 3.5123, + "step": 1267712 + }, + { + "epoch": 1.02, + "learning_rate": 2.9237474964998495e-05, + "loss": 3.5136, + "step": 1268224 + }, + { + "epoch": 1.02, + "learning_rate": 2.9229089017487975e-05, + "loss": 3.5232, + "step": 1268736 + }, + { + "epoch": 1.02, + "learning_rate": 2.9220719448781188e-05, + "loss": 3.5184, + "step": 1269248 + }, + { + "epoch": 1.02, + "learning_rate": 2.9212333501270668e-05, + "loss": 3.5315, + "step": 1269760 + }, + { + "epoch": 1.02, + "learning_rate": 2.9203947553760148e-05, + "loss": 3.5068, + "step": 1270272 + }, + { + "epoch": 1.02, + "learning_rate": 2.9195561606249628e-05, + "loss": 3.5127, + "step": 1270784 + }, + { + "epoch": 1.02, + "learning_rate": 2.9187192037542837e-05, + "loss": 3.5145, + "step": 1271296 + }, + { + "epoch": 1.02, + "learning_rate": 2.9178806090032317e-05, + "loss": 3.5254, + "step": 1271808 + }, + { + "epoch": 1.02, + "learning_rate": 2.9170420142521797e-05, + "loss": 3.5191, + "step": 1272320 + }, + { + "epoch": 1.02, + "learning_rate": 2.916203419501128e-05, + "loss": 3.5141, + "step": 1272832 + }, + { + "epoch": 1.02, + "learning_rate": 2.915366462630449e-05, + "loss": 3.5133, + "step": 1273344 + }, + { + "epoch": 1.02, + "learning_rate": 2.914527867879397e-05, + "loss": 3.5115, + "step": 1273856 + }, + { + "epoch": 1.02, + "learning_rate": 2.913689273128345e-05, + "loss": 3.5222, + "step": 1274368 + }, + { + "epoch": 1.02, + "learning_rate": 2.912850678377293e-05, + "loss": 3.5014, + "step": 1274880 + }, + { + "epoch": 1.02, + "learning_rate": 2.912013721506614e-05, + "loss": 3.5145, + "step": 1275392 + }, + { + "epoch": 1.02, + "learning_rate": 2.911175126755562e-05, + "loss": 3.5211, + "step": 1275904 + }, + { + "epoch": 1.02, + "learning_rate": 2.91033653200451e-05, + "loss": 3.5168, + "step": 1276416 + }, + { + "epoch": 1.02, + "learning_rate": 2.909497937253458e-05, + "loss": 3.5148, + "step": 1276928 + }, + { + "epoch": 1.02, + "learning_rate": 2.908660980382779e-05, + "loss": 3.5186, + "step": 1277440 + }, + { + "epoch": 1.02, + "learning_rate": 2.907822385631727e-05, + "loss": 3.5064, + "step": 1277952 + }, + { + "epoch": 1.02, + "learning_rate": 2.906983790880675e-05, + "loss": 3.5172, + "step": 1278464 + }, + { + "epoch": 1.02, + "learning_rate": 2.9061451961296234e-05, + "loss": 3.5177, + "step": 1278976 + }, + { + "epoch": 1.02, + "learning_rate": 2.9053082392589443e-05, + "loss": 3.5176, + "step": 1279488 + }, + { + "epoch": 1.02, + "learning_rate": 2.9044696445078923e-05, + "loss": 3.5203, + "step": 1280000 + }, + { + "epoch": 1.02, + "learning_rate": 2.9036310497568403e-05, + "loss": 3.5202, + "step": 1280512 + }, + { + "epoch": 1.02, + "learning_rate": 2.9027924550057883e-05, + "loss": 3.5158, + "step": 1281024 + }, + { + "epoch": 1.02, + "learning_rate": 2.9019554981351095e-05, + "loss": 3.5121, + "step": 1281536 + }, + { + "epoch": 1.02, + "learning_rate": 2.9011169033840575e-05, + "loss": 3.5161, + "step": 1282048 + }, + { + "epoch": 1.02, + "learning_rate": 2.9002783086330055e-05, + "loss": 3.5104, + "step": 1282560 + }, + { + "epoch": 1.02, + "learning_rate": 2.8994397138819535e-05, + "loss": 3.5062, + "step": 1283072 + }, + { + "epoch": 1.02, + "learning_rate": 2.8986027570112744e-05, + "loss": 3.5094, + "step": 1283584 + }, + { + "epoch": 1.02, + "learning_rate": 2.8977641622602224e-05, + "loss": 3.511, + "step": 1284096 + }, + { + "epoch": 1.02, + "learning_rate": 2.8969255675091704e-05, + "loss": 3.5225, + "step": 1284608 + }, + { + "epoch": 1.02, + "learning_rate": 2.8960869727581187e-05, + "loss": 3.5073, + "step": 1285120 + }, + { + "epoch": 1.02, + "learning_rate": 2.8952500158874396e-05, + "loss": 3.5145, + "step": 1285632 + }, + { + "epoch": 1.02, + "learning_rate": 2.8944114211363876e-05, + "loss": 3.5066, + "step": 1286144 + }, + { + "epoch": 1.02, + "learning_rate": 2.8935728263853356e-05, + "loss": 3.5165, + "step": 1286656 + }, + { + "epoch": 1.02, + "learning_rate": 2.8927342316342836e-05, + "loss": 3.5111, + "step": 1287168 + }, + { + "epoch": 1.02, + "learning_rate": 2.8918956368832316e-05, + "loss": 3.5253, + "step": 1287680 + }, + { + "epoch": 1.02, + "learning_rate": 2.8910570421321796e-05, + "loss": 3.5149, + "step": 1288192 + }, + { + "epoch": 1.02, + "learning_rate": 2.890218447381128e-05, + "loss": 3.5105, + "step": 1288704 + }, + { + "epoch": 1.02, + "learning_rate": 2.889381490510449e-05, + "loss": 3.511, + "step": 1289216 + }, + { + "epoch": 1.02, + "learning_rate": 2.888542895759397e-05, + "loss": 3.5153, + "step": 1289728 + }, + { + "epoch": 1.02, + "learning_rate": 2.887704301008345e-05, + "loss": 3.5193, + "step": 1290240 + }, + { + "epoch": 1.02, + "learning_rate": 2.886865706257293e-05, + "loss": 3.5216, + "step": 1290752 + }, + { + "epoch": 1.02, + "learning_rate": 2.886028749386614e-05, + "loss": 3.5164, + "step": 1291264 + }, + { + "epoch": 1.02, + "learning_rate": 2.885190154635562e-05, + "loss": 3.5259, + "step": 1291776 + }, + { + "epoch": 1.02, + "learning_rate": 2.88435155988451e-05, + "loss": 3.5166, + "step": 1292288 + }, + { + "epoch": 1.02, + "learning_rate": 2.883512965133458e-05, + "loss": 3.5141, + "step": 1292800 + }, + { + "epoch": 1.02, + "learning_rate": 2.882676008262779e-05, + "loss": 3.5134, + "step": 1293312 + }, + { + "epoch": 1.02, + "learning_rate": 2.881837413511727e-05, + "loss": 3.518, + "step": 1293824 + }, + { + "epoch": 1.02, + "learning_rate": 2.880998818760675e-05, + "loss": 3.5121, + "step": 1294336 + }, + { + "epoch": 1.02, + "learning_rate": 2.880160224009623e-05, + "loss": 3.5045, + "step": 1294848 + }, + { + "epoch": 1.02, + "learning_rate": 2.8793232671389442e-05, + "loss": 3.5151, + "step": 1295360 + }, + { + "epoch": 1.02, + "learning_rate": 2.8784846723878922e-05, + "loss": 3.5101, + "step": 1295872 + }, + { + "epoch": 1.02, + "learning_rate": 2.8776460776368402e-05, + "loss": 3.5193, + "step": 1296384 + }, + { + "epoch": 1.02, + "learning_rate": 2.8768074828857882e-05, + "loss": 3.5095, + "step": 1296896 + }, + { + "epoch": 1.02, + "learning_rate": 2.875970526015109e-05, + "loss": 3.5156, + "step": 1297408 + }, + { + "epoch": 1.03, + "eval_loss": 3.8453149795532227, + "eval_runtime": 304.1957, + "eval_samples_per_second": 1254.426, + "eval_steps_per_second": 39.202, + "step": 1297440 + }, + { + "epoch": 0.0, + "learning_rate": 2.8751319312640575e-05, + "loss": 3.5031, + "step": 1297920 + }, + { + "epoch": 0.0, + "learning_rate": 2.8742933365130055e-05, + "loss": 3.5058, + "step": 1298432 + }, + { + "epoch": 0.0, + "learning_rate": 2.8734547417619535e-05, + "loss": 3.5186, + "step": 1298944 + }, + { + "epoch": 0.0, + "learning_rate": 2.8726177848912744e-05, + "loss": 3.5139, + "step": 1299456 + }, + { + "epoch": 0.0, + "learning_rate": 2.8717791901402224e-05, + "loss": 3.5189, + "step": 1299968 + }, + { + "epoch": 0.0, + "learning_rate": 2.8709405953891704e-05, + "loss": 3.5048, + "step": 1300480 + }, + { + "epoch": 0.0, + "learning_rate": 2.8701020006381184e-05, + "loss": 3.505, + "step": 1300992 + }, + { + "epoch": 0.0, + "learning_rate": 2.8692650437674396e-05, + "loss": 3.5081, + "step": 1301504 + }, + { + "epoch": 0.0, + "learning_rate": 2.8684264490163876e-05, + "loss": 3.517, + "step": 1302016 + }, + { + "epoch": 0.0, + "learning_rate": 2.8675878542653356e-05, + "loss": 3.5158, + "step": 1302528 + }, + { + "epoch": 0.0, + "learning_rate": 2.8667492595142836e-05, + "loss": 3.5116, + "step": 1303040 + }, + { + "epoch": 0.0, + "learning_rate": 2.8659123026436045e-05, + "loss": 3.518, + "step": 1303552 + }, + { + "epoch": 0.0, + "learning_rate": 2.865073707892553e-05, + "loss": 3.4985, + "step": 1304064 + }, + { + "epoch": 0.0, + "learning_rate": 2.8642351131415008e-05, + "loss": 3.5035, + "step": 1304576 + }, + { + "epoch": 0.0, + "learning_rate": 2.8633965183904488e-05, + "loss": 3.5068, + "step": 1305088 + }, + { + "epoch": 0.0, + "learning_rate": 2.8625595615197697e-05, + "loss": 3.5026, + "step": 1305600 + }, + { + "epoch": 0.0, + "learning_rate": 2.8617209667687177e-05, + "loss": 3.5086, + "step": 1306112 + }, + { + "epoch": 0.0, + "learning_rate": 2.8608823720176657e-05, + "loss": 3.507, + "step": 1306624 + }, + { + "epoch": 0.0, + "learning_rate": 2.8600437772666137e-05, + "loss": 3.5039, + "step": 1307136 + }, + { + "epoch": 0.0, + "learning_rate": 2.859206820395935e-05, + "loss": 3.5334, + "step": 1307648 + }, + { + "epoch": 0.0, + "learning_rate": 2.858368225644883e-05, + "loss": 3.5117, + "step": 1308160 + }, + { + "epoch": 0.0, + "learning_rate": 2.857529630893831e-05, + "loss": 3.5109, + "step": 1308672 + }, + { + "epoch": 0.0, + "learning_rate": 2.856691036142779e-05, + "loss": 3.5113, + "step": 1309184 + }, + { + "epoch": 0.0, + "learning_rate": 2.8558540792721e-05, + "loss": 3.5228, + "step": 1309696 + }, + { + "epoch": 0.0, + "learning_rate": 2.8550154845210482e-05, + "loss": 3.5051, + "step": 1310208 + }, + { + "epoch": 0.0, + "learning_rate": 2.8541768897699962e-05, + "loss": 3.5081, + "step": 1310720 + }, + { + "epoch": 0.0, + "learning_rate": 2.8533382950189442e-05, + "loss": 3.5102, + "step": 1311232 + }, + { + "epoch": 0.0, + "learning_rate": 2.852501338148265e-05, + "loss": 3.5066, + "step": 1311744 + }, + { + "epoch": 0.0, + "learning_rate": 2.851662743397213e-05, + "loss": 3.5051, + "step": 1312256 + }, + { + "epoch": 0.01, + "learning_rate": 2.850824148646161e-05, + "loss": 3.5032, + "step": 1312768 + }, + { + "epoch": 0.01, + "learning_rate": 2.849985553895109e-05, + "loss": 3.5281, + "step": 1313280 + }, + { + "epoch": 0.01, + "learning_rate": 2.8491485970244303e-05, + "loss": 3.5133, + "step": 1313792 + }, + { + "epoch": 0.01, + "learning_rate": 2.8483100022733783e-05, + "loss": 3.5127, + "step": 1314304 + }, + { + "epoch": 0.01, + "learning_rate": 2.8474714075223263e-05, + "loss": 3.5117, + "step": 1314816 + }, + { + "epoch": 0.01, + "learning_rate": 2.8466328127712736e-05, + "loss": 3.5127, + "step": 1315328 + }, + { + "epoch": 0.01, + "learning_rate": 2.8457958559005952e-05, + "loss": 3.5119, + "step": 1315840 + }, + { + "epoch": 0.01, + "learning_rate": 2.8449572611495436e-05, + "loss": 3.4979, + "step": 1316352 + }, + { + "epoch": 0.01, + "learning_rate": 2.8441186663984916e-05, + "loss": 3.506, + "step": 1316864 + }, + { + "epoch": 0.01, + "learning_rate": 2.843280071647439e-05, + "loss": 3.4981, + "step": 1317376 + }, + { + "epoch": 0.01, + "learning_rate": 2.8424431147767605e-05, + "loss": 3.51, + "step": 1317888 + }, + { + "epoch": 0.01, + "learning_rate": 2.8416061579060814e-05, + "loss": 3.5046, + "step": 1318400 + }, + { + "epoch": 0.01, + "learning_rate": 2.8407675631550297e-05, + "loss": 3.5168, + "step": 1318912 + }, + { + "epoch": 0.01, + "learning_rate": 2.8399289684039777e-05, + "loss": 3.5086, + "step": 1319424 + }, + { + "epoch": 0.01, + "learning_rate": 2.8390903736529257e-05, + "loss": 3.508, + "step": 1319936 + }, + { + "epoch": 0.01, + "learning_rate": 2.8382517789018737e-05, + "loss": 3.5151, + "step": 1320448 + }, + { + "epoch": 0.01, + "learning_rate": 2.837413184150821e-05, + "loss": 3.5049, + "step": 1320960 + }, + { + "epoch": 0.01, + "learning_rate": 2.836574589399769e-05, + "loss": 3.5123, + "step": 1321472 + }, + { + "epoch": 0.01, + "learning_rate": 2.8357359946487173e-05, + "loss": 3.4967, + "step": 1321984 + }, + { + "epoch": 0.01, + "learning_rate": 2.834899037778039e-05, + "loss": 3.5027, + "step": 1322496 + }, + { + "epoch": 0.01, + "learning_rate": 2.8340604430269863e-05, + "loss": 3.5098, + "step": 1323008 + }, + { + "epoch": 0.01, + "learning_rate": 2.8332218482759342e-05, + "loss": 3.5087, + "step": 1323520 + }, + { + "epoch": 0.01, + "learning_rate": 2.8323832535248822e-05, + "loss": 3.5133, + "step": 1324032 + }, + { + "epoch": 0.01, + "learning_rate": 2.831546296654204e-05, + "loss": 3.4887, + "step": 1324544 + }, + { + "epoch": 0.01, + "learning_rate": 2.8307077019031515e-05, + "loss": 3.509, + "step": 1325056 + }, + { + "epoch": 0.01, + "learning_rate": 2.8298691071520995e-05, + "loss": 3.4914, + "step": 1325568 + }, + { + "epoch": 0.01, + "learning_rate": 2.829032150281421e-05, + "loss": 3.5229, + "step": 1326080 + }, + { + "epoch": 0.01, + "learning_rate": 2.8281935555303684e-05, + "loss": 3.496, + "step": 1326592 + }, + { + "epoch": 0.01, + "learning_rate": 2.8273549607793164e-05, + "loss": 3.5121, + "step": 1327104 + }, + { + "epoch": 0.01, + "learning_rate": 2.8265163660282644e-05, + "loss": 3.5057, + "step": 1327616 + }, + { + "epoch": 0.01, + "learning_rate": 2.8256777712772127e-05, + "loss": 3.492, + "step": 1328128 + }, + { + "epoch": 0.01, + "learning_rate": 2.8248391765261607e-05, + "loss": 3.5041, + "step": 1328640 + }, + { + "epoch": 0.01, + "learning_rate": 2.8240005817751087e-05, + "loss": 3.5004, + "step": 1329152 + }, + { + "epoch": 0.01, + "learning_rate": 2.8231619870240567e-05, + "loss": 3.4894, + "step": 1329664 + }, + { + "epoch": 0.01, + "learning_rate": 2.8223250301533776e-05, + "loss": 3.4971, + "step": 1330176 + }, + { + "epoch": 0.01, + "learning_rate": 2.8214864354023256e-05, + "loss": 3.5106, + "step": 1330688 + }, + { + "epoch": 0.01, + "learning_rate": 2.8206478406512736e-05, + "loss": 3.5035, + "step": 1331200 + }, + { + "epoch": 0.01, + "learning_rate": 2.819809245900222e-05, + "loss": 3.4966, + "step": 1331712 + }, + { + "epoch": 0.01, + "learning_rate": 2.818972289029543e-05, + "loss": 3.4984, + "step": 1332224 + }, + { + "epoch": 0.01, + "learning_rate": 2.818133694278491e-05, + "loss": 3.4903, + "step": 1332736 + }, + { + "epoch": 0.01, + "learning_rate": 2.817295099527439e-05, + "loss": 3.5049, + "step": 1333248 + }, + { + "epoch": 0.01, + "learning_rate": 2.816456504776387e-05, + "loss": 3.5058, + "step": 1333760 + }, + { + "epoch": 0.01, + "learning_rate": 2.815619547905708e-05, + "loss": 3.5066, + "step": 1334272 + }, + { + "epoch": 0.01, + "learning_rate": 2.814780953154656e-05, + "loss": 3.5163, + "step": 1334784 + }, + { + "epoch": 0.01, + "learning_rate": 2.813942358403604e-05, + "loss": 3.5056, + "step": 1335296 + }, + { + "epoch": 0.01, + "learning_rate": 2.813103763652552e-05, + "loss": 3.5106, + "step": 1335808 + }, + { + "epoch": 0.01, + "learning_rate": 2.812266806781873e-05, + "loss": 3.4967, + "step": 1336320 + }, + { + "epoch": 0.01, + "learning_rate": 2.811428212030821e-05, + "loss": 3.5089, + "step": 1336832 + }, + { + "epoch": 0.01, + "learning_rate": 2.810589617279769e-05, + "loss": 3.5007, + "step": 1337344 + }, + { + "epoch": 0.01, + "learning_rate": 2.8097510225287173e-05, + "loss": 3.4983, + "step": 1337856 + }, + { + "epoch": 0.01, + "learning_rate": 2.8089140656580382e-05, + "loss": 3.5021, + "step": 1338368 + }, + { + "epoch": 0.01, + "learning_rate": 2.8080754709069862e-05, + "loss": 3.5075, + "step": 1338880 + }, + { + "epoch": 0.01, + "learning_rate": 2.807238514036307e-05, + "loss": 3.5114, + "step": 1339392 + }, + { + "epoch": 0.01, + "learning_rate": 2.806399919285255e-05, + "loss": 3.5032, + "step": 1339904 + }, + { + "epoch": 0.01, + "learning_rate": 2.8055613245342034e-05, + "loss": 3.4905, + "step": 1340416 + }, + { + "epoch": 0.01, + "learning_rate": 2.8047227297831514e-05, + "loss": 3.497, + "step": 1340928 + }, + { + "epoch": 0.01, + "learning_rate": 2.8038841350320994e-05, + "loss": 3.5132, + "step": 1341440 + }, + { + "epoch": 0.01, + "learning_rate": 2.8030455402810474e-05, + "loss": 3.5101, + "step": 1341952 + }, + { + "epoch": 0.01, + "learning_rate": 2.8022069455299954e-05, + "loss": 3.5043, + "step": 1342464 + }, + { + "epoch": 0.01, + "learning_rate": 2.8013683507789434e-05, + "loss": 3.5127, + "step": 1342976 + }, + { + "epoch": 0.02, + "learning_rate": 2.8005313939082643e-05, + "loss": 3.511, + "step": 1343488 + }, + { + "epoch": 0.02, + "learning_rate": 2.7996927991572123e-05, + "loss": 3.4963, + "step": 1344000 + }, + { + "epoch": 0.02, + "learning_rate": 2.7988542044061607e-05, + "loss": 3.4998, + "step": 1344512 + }, + { + "epoch": 0.02, + "learning_rate": 2.7980172475354816e-05, + "loss": 3.5094, + "step": 1345024 + }, + { + "epoch": 0.02, + "learning_rate": 2.7971786527844296e-05, + "loss": 3.5044, + "step": 1345536 + }, + { + "epoch": 0.02, + "learning_rate": 2.7963400580333776e-05, + "loss": 3.5157, + "step": 1346048 + }, + { + "epoch": 0.02, + "learning_rate": 2.7955014632823256e-05, + "loss": 3.4977, + "step": 1346560 + }, + { + "epoch": 0.02, + "learning_rate": 2.7946628685312736e-05, + "loss": 3.4989, + "step": 1347072 + }, + { + "epoch": 0.02, + "learning_rate": 2.7938242737802216e-05, + "loss": 3.5037, + "step": 1347584 + }, + { + "epoch": 0.02, + "learning_rate": 2.79298567902917e-05, + "loss": 3.5091, + "step": 1348096 + }, + { + "epoch": 0.02, + "learning_rate": 2.7921470842781172e-05, + "loss": 3.5064, + "step": 1348608 + }, + { + "epoch": 0.02, + "learning_rate": 2.7913101274074388e-05, + "loss": 3.5031, + "step": 1349120 + }, + { + "epoch": 0.02, + "learning_rate": 2.7904715326563868e-05, + "loss": 3.4979, + "step": 1349632 + }, + { + "epoch": 0.02, + "learning_rate": 2.7896329379053344e-05, + "loss": 3.4974, + "step": 1350144 + }, + { + "epoch": 0.02, + "learning_rate": 2.788795981034656e-05, + "loss": 3.5114, + "step": 1350656 + }, + { + "epoch": 0.02, + "learning_rate": 2.787957386283604e-05, + "loss": 3.4874, + "step": 1351168 + }, + { + "epoch": 0.02, + "learning_rate": 2.787118791532552e-05, + "loss": 3.495, + "step": 1351680 + }, + { + "epoch": 0.02, + "learning_rate": 2.7862801967814993e-05, + "loss": 3.5122, + "step": 1352192 + }, + { + "epoch": 0.02, + "learning_rate": 2.785443239910821e-05, + "loss": 3.5047, + "step": 1352704 + }, + { + "epoch": 0.02, + "learning_rate": 2.784604645159769e-05, + "loss": 3.4974, + "step": 1353216 + }, + { + "epoch": 0.02, + "learning_rate": 2.783766050408717e-05, + "loss": 3.5039, + "step": 1353728 + }, + { + "epoch": 0.02, + "learning_rate": 2.7829274556576646e-05, + "loss": 3.4967, + "step": 1354240 + }, + { + "epoch": 0.02, + "learning_rate": 2.782090498786986e-05, + "loss": 3.5066, + "step": 1354752 + }, + { + "epoch": 0.02, + "learning_rate": 2.781251904035934e-05, + "loss": 3.5017, + "step": 1355264 + }, + { + "epoch": 0.02, + "learning_rate": 2.7804133092848815e-05, + "loss": 3.5038, + "step": 1355776 + }, + { + "epoch": 0.02, + "learning_rate": 2.7795747145338298e-05, + "loss": 3.5105, + "step": 1356288 + }, + { + "epoch": 0.02, + "learning_rate": 2.7787377576631514e-05, + "loss": 3.5113, + "step": 1356800 + }, + { + "epoch": 0.02, + "learning_rate": 2.7778991629120994e-05, + "loss": 3.4997, + "step": 1357312 + }, + { + "epoch": 0.02, + "learning_rate": 2.7770605681610467e-05, + "loss": 3.4993, + "step": 1357824 + }, + { + "epoch": 0.02, + "learning_rate": 2.7762219734099947e-05, + "loss": 3.5031, + "step": 1358336 + }, + { + "epoch": 0.02, + "learning_rate": 2.7753850165393163e-05, + "loss": 3.498, + "step": 1358848 + }, + { + "epoch": 0.02, + "learning_rate": 2.7745464217882643e-05, + "loss": 3.4903, + "step": 1359360 + }, + { + "epoch": 0.02, + "learning_rate": 2.773707827037212e-05, + "loss": 3.4985, + "step": 1359872 + }, + { + "epoch": 0.02, + "learning_rate": 2.77286923228616e-05, + "loss": 3.496, + "step": 1360384 + }, + { + "epoch": 0.02, + "learning_rate": 2.7720322754154815e-05, + "loss": 3.5074, + "step": 1360896 + }, + { + "epoch": 0.02, + "learning_rate": 2.771193680664429e-05, + "loss": 3.4942, + "step": 1361408 + }, + { + "epoch": 0.02, + "learning_rate": 2.7703567237937504e-05, + "loss": 3.504, + "step": 1361920 + }, + { + "epoch": 0.02, + "learning_rate": 2.7695181290426984e-05, + "loss": 3.4873, + "step": 1362432 + }, + { + "epoch": 0.02, + "learning_rate": 2.7686795342916468e-05, + "loss": 3.5043, + "step": 1362944 + }, + { + "epoch": 0.02, + "learning_rate": 2.767840939540594e-05, + "loss": 3.5001, + "step": 1363456 + }, + { + "epoch": 0.02, + "learning_rate": 2.767002344789542e-05, + "loss": 3.5127, + "step": 1363968 + }, + { + "epoch": 0.02, + "learning_rate": 2.76616375003849e-05, + "loss": 3.5086, + "step": 1364480 + }, + { + "epoch": 0.02, + "learning_rate": 2.765325155287438e-05, + "loss": 3.5019, + "step": 1364992 + }, + { + "epoch": 0.02, + "learning_rate": 2.7644881984167593e-05, + "loss": 3.4912, + "step": 1365504 + }, + { + "epoch": 0.02, + "learning_rate": 2.7636496036657073e-05, + "loss": 3.5002, + "step": 1366016 + }, + { + "epoch": 0.02, + "learning_rate": 2.7628110089146553e-05, + "loss": 3.5084, + "step": 1366528 + }, + { + "epoch": 0.02, + "learning_rate": 2.7619724141636033e-05, + "loss": 3.5103, + "step": 1367040 + }, + { + "epoch": 0.02, + "learning_rate": 2.7611354572929242e-05, + "loss": 3.5083, + "step": 1367552 + }, + { + "epoch": 0.02, + "learning_rate": 2.7602968625418722e-05, + "loss": 3.5124, + "step": 1368064 + }, + { + "epoch": 0.02, + "learning_rate": 2.7594582677908205e-05, + "loss": 3.5006, + "step": 1368576 + }, + { + "epoch": 0.02, + "learning_rate": 2.7586196730397685e-05, + "loss": 3.5048, + "step": 1369088 + }, + { + "epoch": 0.02, + "learning_rate": 2.7577827161690894e-05, + "loss": 3.5015, + "step": 1369600 + }, + { + "epoch": 0.02, + "learning_rate": 2.7569441214180374e-05, + "loss": 3.504, + "step": 1370112 + }, + { + "epoch": 0.02, + "learning_rate": 2.7561055266669854e-05, + "loss": 3.5021, + "step": 1370624 + }, + { + "epoch": 0.02, + "learning_rate": 2.7552669319159334e-05, + "loss": 3.4897, + "step": 1371136 + }, + { + "epoch": 0.02, + "learning_rate": 2.7544299750452547e-05, + "loss": 3.5031, + "step": 1371648 + }, + { + "epoch": 0.02, + "learning_rate": 2.7535913802942027e-05, + "loss": 3.4971, + "step": 1372160 + }, + { + "epoch": 0.02, + "learning_rate": 2.7527527855431507e-05, + "loss": 3.5054, + "step": 1372672 + }, + { + "epoch": 0.02, + "learning_rate": 2.7519141907920987e-05, + "loss": 3.4956, + "step": 1373184 + }, + { + "epoch": 0.02, + "learning_rate": 2.7510772339214196e-05, + "loss": 3.504, + "step": 1373696 + }, + { + "epoch": 0.03, + "eval_loss": 3.8460566997528076, + "eval_runtime": 304.5243, + "eval_samples_per_second": 1253.072, + "eval_steps_per_second": 39.159, + "step": 1373760 + }, + { + "epoch": 1.0, + "learning_rate": 2.7502386391703676e-05, + "loss": 3.4913, + "step": 1374208 + }, + { + "epoch": 1.0, + "learning_rate": 2.749400044419316e-05, + "loss": 3.4942, + "step": 1374720 + }, + { + "epoch": 1.0, + "learning_rate": 2.748561449668264e-05, + "loss": 3.5032, + "step": 1375232 + }, + { + "epoch": 1.0, + "learning_rate": 2.7477244927975848e-05, + "loss": 3.5032, + "step": 1375744 + }, + { + "epoch": 1.0, + "learning_rate": 2.7468858980465328e-05, + "loss": 3.5098, + "step": 1376256 + }, + { + "epoch": 1.0, + "learning_rate": 2.7460473032954808e-05, + "loss": 3.4874, + "step": 1376768 + }, + { + "epoch": 1.0, + "learning_rate": 2.7452087085444288e-05, + "loss": 3.4952, + "step": 1377280 + }, + { + "epoch": 1.0, + "learning_rate": 2.74437175167375e-05, + "loss": 3.4944, + "step": 1377792 + }, + { + "epoch": 1.0, + "learning_rate": 2.743533156922698e-05, + "loss": 3.5032, + "step": 1378304 + }, + { + "epoch": 1.0, + "learning_rate": 2.742694562171646e-05, + "loss": 3.5054, + "step": 1378816 + }, + { + "epoch": 1.0, + "learning_rate": 2.741855967420594e-05, + "loss": 3.4974, + "step": 1379328 + }, + { + "epoch": 1.0, + "learning_rate": 2.741019010549915e-05, + "loss": 3.5017, + "step": 1379840 + }, + { + "epoch": 1.0, + "learning_rate": 2.740180415798863e-05, + "loss": 3.4866, + "step": 1380352 + }, + { + "epoch": 1.0, + "learning_rate": 2.7393418210478113e-05, + "loss": 3.4898, + "step": 1380864 + }, + { + "epoch": 1.0, + "learning_rate": 2.7385032262967593e-05, + "loss": 3.4994, + "step": 1381376 + }, + { + "epoch": 1.0, + "learning_rate": 2.7376662694260802e-05, + "loss": 3.4909, + "step": 1381888 + }, + { + "epoch": 1.0, + "learning_rate": 2.7368276746750282e-05, + "loss": 3.4948, + "step": 1382400 + }, + { + "epoch": 1.0, + "learning_rate": 2.7359890799239762e-05, + "loss": 3.4939, + "step": 1382912 + }, + { + "epoch": 1.0, + "learning_rate": 2.7351504851729242e-05, + "loss": 3.4903, + "step": 1383424 + }, + { + "epoch": 1.0, + "learning_rate": 2.7343135283022454e-05, + "loss": 3.5221, + "step": 1383936 + }, + { + "epoch": 1.0, + "learning_rate": 2.7334765714315663e-05, + "loss": 3.4954, + "step": 1384448 + }, + { + "epoch": 1.0, + "learning_rate": 2.7326379766805143e-05, + "loss": 3.5004, + "step": 1384960 + }, + { + "epoch": 1.0, + "learning_rate": 2.7317993819294623e-05, + "loss": 3.5, + "step": 1385472 + }, + { + "epoch": 1.0, + "learning_rate": 2.7309607871784103e-05, + "loss": 3.5078, + "step": 1385984 + }, + { + "epoch": 1.0, + "learning_rate": 2.7301221924273583e-05, + "loss": 3.49, + "step": 1386496 + }, + { + "epoch": 1.0, + "learning_rate": 2.7292835976763066e-05, + "loss": 3.4951, + "step": 1387008 + }, + { + "epoch": 1.0, + "learning_rate": 2.7284450029252546e-05, + "loss": 3.4986, + "step": 1387520 + }, + { + "epoch": 1.0, + "learning_rate": 2.7276064081742026e-05, + "loss": 3.4954, + "step": 1388032 + }, + { + "epoch": 1.0, + "learning_rate": 2.7267694513035235e-05, + "loss": 3.4873, + "step": 1388544 + }, + { + "epoch": 1.01, + "learning_rate": 2.7259308565524715e-05, + "loss": 3.4925, + "step": 1389056 + }, + { + "epoch": 1.01, + "learning_rate": 2.7250922618014195e-05, + "loss": 3.512, + "step": 1389568 + }, + { + "epoch": 1.01, + "learning_rate": 2.7242536670503675e-05, + "loss": 3.5005, + "step": 1390080 + }, + { + "epoch": 1.01, + "learning_rate": 2.7234167101796888e-05, + "loss": 3.5004, + "step": 1390592 + }, + { + "epoch": 1.01, + "learning_rate": 2.7225781154286368e-05, + "loss": 3.5009, + "step": 1391104 + }, + { + "epoch": 1.01, + "learning_rate": 2.7217395206775848e-05, + "loss": 3.4977, + "step": 1391616 + }, + { + "epoch": 1.01, + "learning_rate": 2.7209025638069057e-05, + "loss": 3.4979, + "step": 1392128 + }, + { + "epoch": 1.01, + "learning_rate": 2.7200639690558537e-05, + "loss": 3.4848, + "step": 1392640 + }, + { + "epoch": 1.01, + "learning_rate": 2.719225374304802e-05, + "loss": 3.4991, + "step": 1393152 + }, + { + "epoch": 1.01, + "learning_rate": 2.71838677955375e-05, + "loss": 3.4845, + "step": 1393664 + }, + { + "epoch": 1.01, + "learning_rate": 2.717548184802698e-05, + "loss": 3.4946, + "step": 1394176 + }, + { + "epoch": 1.01, + "learning_rate": 2.716711227932019e-05, + "loss": 3.4917, + "step": 1394688 + }, + { + "epoch": 1.01, + "learning_rate": 2.715872633180967e-05, + "loss": 3.5045, + "step": 1395200 + }, + { + "epoch": 1.01, + "learning_rate": 2.715034038429915e-05, + "loss": 3.4977, + "step": 1395712 + }, + { + "epoch": 1.01, + "learning_rate": 2.714195443678863e-05, + "loss": 3.4935, + "step": 1396224 + }, + { + "epoch": 1.01, + "learning_rate": 2.713356848927811e-05, + "loss": 3.5021, + "step": 1396736 + }, + { + "epoch": 1.01, + "learning_rate": 2.7125182541767592e-05, + "loss": 3.4972, + "step": 1397248 + }, + { + "epoch": 1.01, + "learning_rate": 2.7116796594257072e-05, + "loss": 3.4986, + "step": 1397760 + }, + { + "epoch": 1.01, + "learning_rate": 2.7108410646746545e-05, + "loss": 3.4844, + "step": 1398272 + }, + { + "epoch": 1.01, + "learning_rate": 2.710004107803976e-05, + "loss": 3.4884, + "step": 1398784 + }, + { + "epoch": 1.01, + "learning_rate": 2.709165513052924e-05, + "loss": 3.4977, + "step": 1399296 + }, + { + "epoch": 1.01, + "learning_rate": 2.708326918301872e-05, + "loss": 3.4958, + "step": 1399808 + }, + { + "epoch": 1.01, + "learning_rate": 2.7074883235508198e-05, + "loss": 3.4946, + "step": 1400320 + }, + { + "epoch": 1.01, + "learning_rate": 2.7066513666801414e-05, + "loss": 3.4779, + "step": 1400832 + }, + { + "epoch": 1.01, + "learning_rate": 2.7058127719290894e-05, + "loss": 3.4976, + "step": 1401344 + }, + { + "epoch": 1.01, + "learning_rate": 2.7049741771780367e-05, + "loss": 3.4782, + "step": 1401856 + }, + { + "epoch": 1.01, + "learning_rate": 2.7041372203073583e-05, + "loss": 3.5071, + "step": 1402368 + }, + { + "epoch": 1.01, + "learning_rate": 2.7032986255563063e-05, + "loss": 3.4796, + "step": 1402880 + }, + { + "epoch": 1.01, + "learning_rate": 2.7024600308052546e-05, + "loss": 3.5024, + "step": 1403392 + }, + { + "epoch": 1.01, + "learning_rate": 2.701621436054202e-05, + "loss": 3.4897, + "step": 1403904 + }, + { + "epoch": 1.01, + "learning_rate": 2.70078284130315e-05, + "loss": 3.4856, + "step": 1404416 + }, + { + "epoch": 1.01, + "learning_rate": 2.699944246552098e-05, + "loss": 3.489, + "step": 1404928 + }, + { + "epoch": 1.01, + "learning_rate": 2.699105651801046e-05, + "loss": 3.4915, + "step": 1405440 + }, + { + "epoch": 1.01, + "learning_rate": 2.698267057049994e-05, + "loss": 3.4772, + "step": 1405952 + }, + { + "epoch": 1.01, + "learning_rate": 2.697430100179315e-05, + "loss": 3.4864, + "step": 1406464 + }, + { + "epoch": 1.01, + "learning_rate": 2.696591505428263e-05, + "loss": 3.495, + "step": 1406976 + }, + { + "epoch": 1.01, + "learning_rate": 2.695752910677211e-05, + "loss": 3.4942, + "step": 1407488 + }, + { + "epoch": 1.01, + "learning_rate": 2.694914315926159e-05, + "loss": 3.4813, + "step": 1408000 + }, + { + "epoch": 1.01, + "learning_rate": 2.69407735905548e-05, + "loss": 3.4839, + "step": 1408512 + }, + { + "epoch": 1.01, + "learning_rate": 2.6932387643044284e-05, + "loss": 3.482, + "step": 1409024 + }, + { + "epoch": 1.01, + "learning_rate": 2.6924001695533764e-05, + "loss": 3.487, + "step": 1409536 + }, + { + "epoch": 1.01, + "learning_rate": 2.6915615748023244e-05, + "loss": 3.4908, + "step": 1410048 + }, + { + "epoch": 1.01, + "learning_rate": 2.6907246179316453e-05, + "loss": 3.4929, + "step": 1410560 + }, + { + "epoch": 1.01, + "learning_rate": 2.6898860231805933e-05, + "loss": 3.5038, + "step": 1411072 + }, + { + "epoch": 1.01, + "learning_rate": 2.6890474284295413e-05, + "loss": 3.4962, + "step": 1411584 + }, + { + "epoch": 1.01, + "learning_rate": 2.6882088336784893e-05, + "loss": 3.4965, + "step": 1412096 + }, + { + "epoch": 1.01, + "learning_rate": 2.6873718768078105e-05, + "loss": 3.4832, + "step": 1412608 + }, + { + "epoch": 1.01, + "learning_rate": 2.6865332820567585e-05, + "loss": 3.4947, + "step": 1413120 + }, + { + "epoch": 1.01, + "learning_rate": 2.6856946873057065e-05, + "loss": 3.4928, + "step": 1413632 + }, + { + "epoch": 1.01, + "learning_rate": 2.6848560925546545e-05, + "loss": 3.4821, + "step": 1414144 + }, + { + "epoch": 1.01, + "learning_rate": 2.6840191356839754e-05, + "loss": 3.4941, + "step": 1414656 + }, + { + "epoch": 1.01, + "learning_rate": 2.6831805409329237e-05, + "loss": 3.492, + "step": 1415168 + }, + { + "epoch": 1.01, + "learning_rate": 2.6823419461818717e-05, + "loss": 3.4991, + "step": 1415680 + }, + { + "epoch": 1.01, + "learning_rate": 2.6815049893111926e-05, + "loss": 3.4903, + "step": 1416192 + }, + { + "epoch": 1.01, + "learning_rate": 2.6806663945601406e-05, + "loss": 3.4782, + "step": 1416704 + }, + { + "epoch": 1.01, + "learning_rate": 2.6798277998090886e-05, + "loss": 3.4854, + "step": 1417216 + }, + { + "epoch": 1.01, + "learning_rate": 2.6789892050580366e-05, + "loss": 3.4973, + "step": 1417728 + }, + { + "epoch": 1.01, + "learning_rate": 2.6781506103069846e-05, + "loss": 3.4973, + "step": 1418240 + }, + { + "epoch": 1.01, + "learning_rate": 2.677312015555933e-05, + "loss": 3.4939, + "step": 1418752 + }, + { + "epoch": 1.01, + "learning_rate": 2.676473420804881e-05, + "loss": 3.4992, + "step": 1419264 + }, + { + "epoch": 1.02, + "learning_rate": 2.675636463934202e-05, + "loss": 3.4981, + "step": 1419776 + }, + { + "epoch": 1.02, + "learning_rate": 2.67479786918315e-05, + "loss": 3.4783, + "step": 1420288 + }, + { + "epoch": 1.02, + "learning_rate": 2.673959274432098e-05, + "loss": 3.4945, + "step": 1420800 + }, + { + "epoch": 1.02, + "learning_rate": 2.673120679681046e-05, + "loss": 3.4915, + "step": 1421312 + }, + { + "epoch": 1.02, + "learning_rate": 2.672283722810367e-05, + "loss": 3.4915, + "step": 1421824 + }, + { + "epoch": 1.02, + "learning_rate": 2.671445128059315e-05, + "loss": 3.5043, + "step": 1422336 + }, + { + "epoch": 1.02, + "learning_rate": 2.670606533308263e-05, + "loss": 3.4874, + "step": 1422848 + }, + { + "epoch": 1.02, + "learning_rate": 2.669767938557211e-05, + "loss": 3.482, + "step": 1423360 + }, + { + "epoch": 1.02, + "learning_rate": 2.668930981686532e-05, + "loss": 3.4907, + "step": 1423872 + }, + { + "epoch": 1.02, + "learning_rate": 2.66809238693548e-05, + "loss": 3.4985, + "step": 1424384 + }, + { + "epoch": 1.02, + "learning_rate": 2.6672537921844283e-05, + "loss": 3.4931, + "step": 1424896 + }, + { + "epoch": 1.02, + "learning_rate": 2.6664151974333763e-05, + "loss": 3.4916, + "step": 1425408 + }, + { + "epoch": 1.02, + "learning_rate": 2.6655782405626972e-05, + "loss": 3.481, + "step": 1425920 + }, + { + "epoch": 1.02, + "learning_rate": 2.6647396458116452e-05, + "loss": 3.4834, + "step": 1426432 + }, + { + "epoch": 1.02, + "learning_rate": 2.6639010510605932e-05, + "loss": 3.5002, + "step": 1426944 + }, + { + "epoch": 1.02, + "learning_rate": 2.6630624563095412e-05, + "loss": 3.4752, + "step": 1427456 + }, + { + "epoch": 1.02, + "learning_rate": 2.6622254994388625e-05, + "loss": 3.4883, + "step": 1427968 + }, + { + "epoch": 1.02, + "learning_rate": 2.6613869046878105e-05, + "loss": 3.4967, + "step": 1428480 + }, + { + "epoch": 1.02, + "learning_rate": 2.6605483099367585e-05, + "loss": 3.4891, + "step": 1428992 + }, + { + "epoch": 1.02, + "learning_rate": 2.6597097151857065e-05, + "loss": 3.4829, + "step": 1429504 + }, + { + "epoch": 1.02, + "learning_rate": 2.6588727583150274e-05, + "loss": 3.4932, + "step": 1430016 + }, + { + "epoch": 1.02, + "learning_rate": 2.6580341635639754e-05, + "loss": 3.4868, + "step": 1430528 + }, + { + "epoch": 1.02, + "learning_rate": 2.6571955688129237e-05, + "loss": 3.492, + "step": 1431040 + }, + { + "epoch": 1.02, + "learning_rate": 2.6563569740618717e-05, + "loss": 3.4878, + "step": 1431552 + }, + { + "epoch": 1.02, + "learning_rate": 2.6555200171911926e-05, + "loss": 3.4882, + "step": 1432064 + }, + { + "epoch": 1.02, + "learning_rate": 2.6546814224401406e-05, + "loss": 3.496, + "step": 1432576 + }, + { + "epoch": 1.02, + "learning_rate": 2.6538428276890886e-05, + "loss": 3.4992, + "step": 1433088 + }, + { + "epoch": 1.02, + "learning_rate": 2.6530042329380366e-05, + "loss": 3.4894, + "step": 1433600 + }, + { + "epoch": 1.02, + "learning_rate": 2.652167276067358e-05, + "loss": 3.4826, + "step": 1434112 + }, + { + "epoch": 1.02, + "learning_rate": 2.651328681316306e-05, + "loss": 3.4886, + "step": 1434624 + }, + { + "epoch": 1.02, + "learning_rate": 2.6504900865652538e-05, + "loss": 3.4854, + "step": 1435136 + }, + { + "epoch": 1.02, + "learning_rate": 2.6496514918142018e-05, + "loss": 3.476, + "step": 1435648 + }, + { + "epoch": 1.02, + "learning_rate": 2.6488145349435227e-05, + "loss": 3.4912, + "step": 1436160 + }, + { + "epoch": 1.02, + "learning_rate": 2.6479759401924707e-05, + "loss": 3.4802, + "step": 1436672 + }, + { + "epoch": 1.02, + "learning_rate": 2.6471373454414187e-05, + "loss": 3.4974, + "step": 1437184 + }, + { + "epoch": 1.02, + "learning_rate": 2.646298750690367e-05, + "loss": 3.483, + "step": 1437696 + }, + { + "epoch": 1.02, + "learning_rate": 2.645461793819688e-05, + "loss": 3.4923, + "step": 1438208 + }, + { + "epoch": 1.02, + "learning_rate": 2.644623199068636e-05, + "loss": 3.477, + "step": 1438720 + }, + { + "epoch": 1.02, + "learning_rate": 2.643784604317584e-05, + "loss": 3.4905, + "step": 1439232 + }, + { + "epoch": 1.02, + "learning_rate": 2.642946009566532e-05, + "loss": 3.4829, + "step": 1439744 + }, + { + "epoch": 1.02, + "learning_rate": 2.64210741481548e-05, + "loss": 3.499, + "step": 1440256 + }, + { + "epoch": 1.02, + "learning_rate": 2.6412688200644276e-05, + "loss": 3.4976, + "step": 1440768 + }, + { + "epoch": 1.02, + "learning_rate": 2.6404302253133756e-05, + "loss": 3.49, + "step": 1441280 + }, + { + "epoch": 1.02, + "learning_rate": 2.6395916305623236e-05, + "loss": 3.4782, + "step": 1441792 + }, + { + "epoch": 1.02, + "learning_rate": 2.6387546736916445e-05, + "loss": 3.4891, + "step": 1442304 + }, + { + "epoch": 1.02, + "learning_rate": 2.6379160789405925e-05, + "loss": 3.495, + "step": 1442816 + }, + { + "epoch": 1.02, + "learning_rate": 2.637077484189541e-05, + "loss": 3.4992, + "step": 1443328 + }, + { + "epoch": 1.02, + "learning_rate": 2.636238889438489e-05, + "loss": 3.4904, + "step": 1443840 + }, + { + "epoch": 1.02, + "learning_rate": 2.6354019325678097e-05, + "loss": 3.5, + "step": 1444352 + }, + { + "epoch": 1.02, + "learning_rate": 2.6345633378167577e-05, + "loss": 3.4905, + "step": 1444864 + }, + { + "epoch": 1.02, + "learning_rate": 2.6337247430657057e-05, + "loss": 3.4935, + "step": 1445376 + }, + { + "epoch": 1.02, + "learning_rate": 2.632887786195027e-05, + "loss": 3.4897, + "step": 1445888 + }, + { + "epoch": 1.02, + "learning_rate": 2.632049191443975e-05, + "loss": 3.4879, + "step": 1446400 + }, + { + "epoch": 1.02, + "learning_rate": 2.631210596692923e-05, + "loss": 3.4907, + "step": 1446912 + }, + { + "epoch": 1.02, + "learning_rate": 2.630372001941871e-05, + "loss": 3.4796, + "step": 1447424 + }, + { + "epoch": 1.02, + "learning_rate": 2.629533407190819e-05, + "loss": 3.4885, + "step": 1447936 + }, + { + "epoch": 1.02, + "learning_rate": 2.62869645032014e-05, + "loss": 3.4912, + "step": 1448448 + }, + { + "epoch": 1.02, + "learning_rate": 2.627857855569088e-05, + "loss": 3.4882, + "step": 1448960 + }, + { + "epoch": 1.02, + "learning_rate": 2.6270192608180362e-05, + "loss": 3.4838, + "step": 1449472 + }, + { + "epoch": 1.02, + "learning_rate": 2.626182303947357e-05, + "loss": 3.4866, + "step": 1449984 + }, + { + "epoch": 1.03, + "eval_loss": 3.8476407527923584, + "eval_runtime": 305.1312, + "eval_samples_per_second": 1250.58, + "eval_steps_per_second": 39.082, + "step": 1450080 + }, + { + "epoch": 0.0, + "learning_rate": 2.625343709196305e-05, + "loss": 3.4775, + "step": 1450496 + }, + { + "epoch": 0.0, + "learning_rate": 2.624505114445253e-05, + "loss": 3.481, + "step": 1451008 + }, + { + "epoch": 0.0, + "learning_rate": 2.623666519694201e-05, + "loss": 3.4946, + "step": 1451520 + }, + { + "epoch": 0.0, + "learning_rate": 2.622827924943149e-05, + "loss": 3.4875, + "step": 1452032 + }, + { + "epoch": 0.0, + "learning_rate": 2.6219909680724703e-05, + "loss": 3.4993, + "step": 1452544 + }, + { + "epoch": 0.0, + "learning_rate": 2.6211523733214183e-05, + "loss": 3.4738, + "step": 1453056 + }, + { + "epoch": 0.0, + "learning_rate": 2.6203137785703663e-05, + "loss": 3.484, + "step": 1453568 + }, + { + "epoch": 0.0, + "learning_rate": 2.6194751838193143e-05, + "loss": 3.4766, + "step": 1454080 + }, + { + "epoch": 0.0, + "learning_rate": 2.6186382269486352e-05, + "loss": 3.4925, + "step": 1454592 + }, + { + "epoch": 0.0, + "learning_rate": 2.6177996321975832e-05, + "loss": 3.4908, + "step": 1455104 + }, + { + "epoch": 0.0, + "learning_rate": 2.6169610374465316e-05, + "loss": 3.4867, + "step": 1455616 + }, + { + "epoch": 0.0, + "learning_rate": 2.6161224426954796e-05, + "loss": 3.4861, + "step": 1456128 + }, + { + "epoch": 0.0, + "learning_rate": 2.6152854858248005e-05, + "loss": 3.4723, + "step": 1456640 + }, + { + "epoch": 0.0, + "learning_rate": 2.6144468910737485e-05, + "loss": 3.4786, + "step": 1457152 + }, + { + "epoch": 0.0, + "learning_rate": 2.6136082963226965e-05, + "loss": 3.4856, + "step": 1457664 + }, + { + "epoch": 0.0, + "learning_rate": 2.6127713394520177e-05, + "loss": 3.4831, + "step": 1458176 + }, + { + "epoch": 0.0, + "learning_rate": 2.6119327447009657e-05, + "loss": 3.4797, + "step": 1458688 + }, + { + "epoch": 0.0, + "learning_rate": 2.6110941499499137e-05, + "loss": 3.485, + "step": 1459200 + }, + { + "epoch": 0.0, + "learning_rate": 2.6102555551988617e-05, + "loss": 3.4746, + "step": 1459712 + }, + { + "epoch": 0.0, + "learning_rate": 2.6094185983281826e-05, + "loss": 3.5091, + "step": 1460224 + }, + { + "epoch": 0.0, + "learning_rate": 2.6085800035771306e-05, + "loss": 3.4847, + "step": 1460736 + }, + { + "epoch": 0.0, + "learning_rate": 2.607743046706452e-05, + "loss": 3.4849, + "step": 1461248 + }, + { + "epoch": 0.0, + "learning_rate": 2.6069044519554e-05, + "loss": 3.488, + "step": 1461760 + }, + { + "epoch": 0.0, + "learning_rate": 2.606065857204348e-05, + "loss": 3.4939, + "step": 1462272 + }, + { + "epoch": 0.0, + "learning_rate": 2.605227262453296e-05, + "loss": 3.4774, + "step": 1462784 + }, + { + "epoch": 0.0, + "learning_rate": 2.604388667702244e-05, + "loss": 3.4903, + "step": 1463296 + }, + { + "epoch": 0.0, + "learning_rate": 2.603550072951192e-05, + "loss": 3.4816, + "step": 1463808 + }, + { + "epoch": 0.0, + "learning_rate": 2.6027114782001398e-05, + "loss": 3.4826, + "step": 1464320 + }, + { + "epoch": 0.0, + "learning_rate": 2.601874521329461e-05, + "loss": 3.4722, + "step": 1464832 + }, + { + "epoch": 0.01, + "learning_rate": 2.601035926578409e-05, + "loss": 3.4841, + "step": 1465344 + }, + { + "epoch": 0.01, + "learning_rate": 2.600197331827357e-05, + "loss": 3.4999, + "step": 1465856 + }, + { + "epoch": 0.01, + "learning_rate": 2.599358737076305e-05, + "loss": 3.487, + "step": 1466368 + }, + { + "epoch": 0.01, + "learning_rate": 2.598521780205626e-05, + "loss": 3.4913, + "step": 1466880 + }, + { + "epoch": 0.01, + "learning_rate": 2.597683185454574e-05, + "loss": 3.4904, + "step": 1467392 + }, + { + "epoch": 0.01, + "learning_rate": 2.5968445907035223e-05, + "loss": 3.4803, + "step": 1467904 + }, + { + "epoch": 0.01, + "learning_rate": 2.5960076338328432e-05, + "loss": 3.4905, + "step": 1468416 + }, + { + "epoch": 0.01, + "learning_rate": 2.5951690390817912e-05, + "loss": 3.4702, + "step": 1468928 + }, + { + "epoch": 0.01, + "learning_rate": 2.5943304443307392e-05, + "loss": 3.4859, + "step": 1469440 + }, + { + "epoch": 0.01, + "learning_rate": 2.5934918495796872e-05, + "loss": 3.4702, + "step": 1469952 + }, + { + "epoch": 0.01, + "learning_rate": 2.5926532548286352e-05, + "loss": 3.485, + "step": 1470464 + }, + { + "epoch": 0.01, + "learning_rate": 2.5918162979579564e-05, + "loss": 3.4777, + "step": 1470976 + }, + { + "epoch": 0.01, + "learning_rate": 2.5909777032069044e-05, + "loss": 3.4931, + "step": 1471488 + }, + { + "epoch": 0.01, + "learning_rate": 2.5901391084558524e-05, + "loss": 3.4859, + "step": 1472000 + }, + { + "epoch": 0.01, + "learning_rate": 2.5893005137048004e-05, + "loss": 3.4792, + "step": 1472512 + }, + { + "epoch": 0.01, + "learning_rate": 2.5884619189537484e-05, + "loss": 3.49, + "step": 1473024 + }, + { + "epoch": 0.01, + "learning_rate": 2.5876233242026964e-05, + "loss": 3.4847, + "step": 1473536 + }, + { + "epoch": 0.01, + "learning_rate": 2.5867847294516444e-05, + "loss": 3.4851, + "step": 1474048 + }, + { + "epoch": 0.01, + "learning_rate": 2.5859461347005924e-05, + "loss": 3.478, + "step": 1474560 + }, + { + "epoch": 0.01, + "learning_rate": 2.5851091778299137e-05, + "loss": 3.4692, + "step": 1475072 + }, + { + "epoch": 0.01, + "learning_rate": 2.5842705830788617e-05, + "loss": 3.4869, + "step": 1475584 + }, + { + "epoch": 0.01, + "learning_rate": 2.5834319883278097e-05, + "loss": 3.4824, + "step": 1476096 + }, + { + "epoch": 0.01, + "learning_rate": 2.5825933935767576e-05, + "loss": 3.4828, + "step": 1476608 + }, + { + "epoch": 0.01, + "learning_rate": 2.5817564367060786e-05, + "loss": 3.4705, + "step": 1477120 + }, + { + "epoch": 0.01, + "learning_rate": 2.580917841955027e-05, + "loss": 3.4879, + "step": 1477632 + }, + { + "epoch": 0.01, + "learning_rate": 2.580079247203975e-05, + "loss": 3.4632, + "step": 1478144 + }, + { + "epoch": 0.01, + "learning_rate": 2.5792422903332958e-05, + "loss": 3.4943, + "step": 1478656 + }, + { + "epoch": 0.01, + "learning_rate": 2.5784036955822438e-05, + "loss": 3.4706, + "step": 1479168 + }, + { + "epoch": 0.01, + "learning_rate": 2.5775651008311918e-05, + "loss": 3.4855, + "step": 1479680 + }, + { + "epoch": 0.01, + "learning_rate": 2.5767265060801398e-05, + "loss": 3.4793, + "step": 1480192 + }, + { + "epoch": 0.01, + "learning_rate": 2.5758879113290878e-05, + "loss": 3.4749, + "step": 1480704 + }, + { + "epoch": 0.01, + "learning_rate": 2.5750493165780354e-05, + "loss": 3.4732, + "step": 1481216 + }, + { + "epoch": 0.01, + "learning_rate": 2.5742107218269834e-05, + "loss": 3.484, + "step": 1481728 + }, + { + "epoch": 0.01, + "learning_rate": 2.5733721270759314e-05, + "loss": 3.463, + "step": 1482240 + }, + { + "epoch": 0.01, + "learning_rate": 2.5725351702052523e-05, + "loss": 3.4698, + "step": 1482752 + }, + { + "epoch": 0.01, + "learning_rate": 2.5716965754542007e-05, + "loss": 3.4855, + "step": 1483264 + }, + { + "epoch": 0.01, + "learning_rate": 2.5708579807031487e-05, + "loss": 3.4808, + "step": 1483776 + }, + { + "epoch": 0.01, + "learning_rate": 2.5700193859520967e-05, + "loss": 3.4726, + "step": 1484288 + }, + { + "epoch": 0.01, + "learning_rate": 2.5691824290814176e-05, + "loss": 3.4725, + "step": 1484800 + }, + { + "epoch": 0.01, + "learning_rate": 2.5683438343303656e-05, + "loss": 3.4648, + "step": 1485312 + }, + { + "epoch": 0.01, + "learning_rate": 2.5675052395793136e-05, + "loss": 3.4748, + "step": 1485824 + }, + { + "epoch": 0.01, + "learning_rate": 2.5666666448282616e-05, + "loss": 3.4808, + "step": 1486336 + }, + { + "epoch": 0.01, + "learning_rate": 2.5658296879575828e-05, + "loss": 3.4813, + "step": 1486848 + }, + { + "epoch": 0.01, + "learning_rate": 2.5649910932065308e-05, + "loss": 3.4913, + "step": 1487360 + }, + { + "epoch": 0.01, + "learning_rate": 2.5641524984554788e-05, + "loss": 3.4826, + "step": 1487872 + }, + { + "epoch": 0.01, + "learning_rate": 2.5633139037044268e-05, + "loss": 3.4882, + "step": 1488384 + }, + { + "epoch": 0.01, + "learning_rate": 2.5624769468337477e-05, + "loss": 3.4701, + "step": 1488896 + }, + { + "epoch": 0.01, + "learning_rate": 2.5616383520826957e-05, + "loss": 3.4814, + "step": 1489408 + }, + { + "epoch": 0.01, + "learning_rate": 2.560799757331644e-05, + "loss": 3.4823, + "step": 1489920 + }, + { + "epoch": 0.01, + "learning_rate": 2.559961162580592e-05, + "loss": 3.4676, + "step": 1490432 + }, + { + "epoch": 0.01, + "learning_rate": 2.559124205709913e-05, + "loss": 3.4852, + "step": 1490944 + }, + { + "epoch": 0.01, + "learning_rate": 2.558285610958861e-05, + "loss": 3.48, + "step": 1491456 + }, + { + "epoch": 0.01, + "learning_rate": 2.557447016207809e-05, + "loss": 3.4864, + "step": 1491968 + }, + { + "epoch": 0.01, + "learning_rate": 2.5566100593371302e-05, + "loss": 3.478, + "step": 1492480 + }, + { + "epoch": 0.01, + "learning_rate": 2.5557714645860782e-05, + "loss": 3.468, + "step": 1492992 + }, + { + "epoch": 0.01, + "learning_rate": 2.5549328698350262e-05, + "loss": 3.4767, + "step": 1493504 + }, + { + "epoch": 0.01, + "learning_rate": 2.554094275083974e-05, + "loss": 3.4811, + "step": 1494016 + }, + { + "epoch": 0.01, + "learning_rate": 2.553255680332922e-05, + "loss": 3.4853, + "step": 1494528 + }, + { + "epoch": 0.01, + "learning_rate": 2.55241708558187e-05, + "loss": 3.483, + "step": 1495040 + }, + { + "epoch": 0.01, + "learning_rate": 2.551578490830818e-05, + "loss": 3.4838, + "step": 1495552 + }, + { + "epoch": 0.02, + "learning_rate": 2.5507415339601394e-05, + "loss": 3.4905, + "step": 1496064 + }, + { + "epoch": 0.02, + "learning_rate": 2.5499029392090874e-05, + "loss": 3.4663, + "step": 1496576 + }, + { + "epoch": 0.02, + "learning_rate": 2.5490643444580354e-05, + "loss": 3.483, + "step": 1497088 + }, + { + "epoch": 0.02, + "learning_rate": 2.5482257497069834e-05, + "loss": 3.4764, + "step": 1497600 + }, + { + "epoch": 0.02, + "learning_rate": 2.5473887928363043e-05, + "loss": 3.4796, + "step": 1498112 + }, + { + "epoch": 0.02, + "learning_rate": 2.5465501980852523e-05, + "loss": 3.4907, + "step": 1498624 + }, + { + "epoch": 0.02, + "learning_rate": 2.5457116033342003e-05, + "loss": 3.4779, + "step": 1499136 + }, + { + "epoch": 0.02, + "learning_rate": 2.5448730085831486e-05, + "loss": 3.4687, + "step": 1499648 + }, + { + "epoch": 0.02, + "learning_rate": 2.5440360517124695e-05, + "loss": 3.4808, + "step": 1500160 + }, + { + "epoch": 0.02, + "learning_rate": 2.5431974569614175e-05, + "loss": 3.4847, + "step": 1500672 + }, + { + "epoch": 0.02, + "learning_rate": 2.5423588622103655e-05, + "loss": 3.4816, + "step": 1501184 + }, + { + "epoch": 0.02, + "learning_rate": 2.5415202674593135e-05, + "loss": 3.4801, + "step": 1501696 + }, + { + "epoch": 0.02, + "learning_rate": 2.5406833105886348e-05, + "loss": 3.4702, + "step": 1502208 + }, + { + "epoch": 0.02, + "learning_rate": 2.5398447158375828e-05, + "loss": 3.4733, + "step": 1502720 + }, + { + "epoch": 0.02, + "learning_rate": 2.5390061210865308e-05, + "loss": 3.4887, + "step": 1503232 + }, + { + "epoch": 0.02, + "learning_rate": 2.5381675263354788e-05, + "loss": 3.4618, + "step": 1503744 + }, + { + "epoch": 0.02, + "learning_rate": 2.5373305694647997e-05, + "loss": 3.476, + "step": 1504256 + }, + { + "epoch": 0.02, + "learning_rate": 2.5364919747137477e-05, + "loss": 3.4831, + "step": 1504768 + }, + { + "epoch": 0.02, + "learning_rate": 2.5356533799626957e-05, + "loss": 3.4802, + "step": 1505280 + }, + { + "epoch": 0.02, + "learning_rate": 2.534814785211644e-05, + "loss": 3.4716, + "step": 1505792 + }, + { + "epoch": 0.02, + "learning_rate": 2.533977828340965e-05, + "loss": 3.4816, + "step": 1506304 + }, + { + "epoch": 0.02, + "learning_rate": 2.533139233589913e-05, + "loss": 3.4755, + "step": 1506816 + }, + { + "epoch": 0.02, + "learning_rate": 2.532300638838861e-05, + "loss": 3.4777, + "step": 1507328 + }, + { + "epoch": 0.02, + "learning_rate": 2.531462044087809e-05, + "loss": 3.479, + "step": 1507840 + }, + { + "epoch": 0.02, + "learning_rate": 2.53062508721713e-05, + "loss": 3.4749, + "step": 1508352 + }, + { + "epoch": 0.02, + "learning_rate": 2.529786492466078e-05, + "loss": 3.4885, + "step": 1508864 + }, + { + "epoch": 0.02, + "learning_rate": 2.528947897715026e-05, + "loss": 3.4833, + "step": 1509376 + }, + { + "epoch": 0.02, + "learning_rate": 2.528109302963974e-05, + "loss": 3.4818, + "step": 1509888 + }, + { + "epoch": 0.02, + "learning_rate": 2.527272346093295e-05, + "loss": 3.4702, + "step": 1510400 + }, + { + "epoch": 0.02, + "learning_rate": 2.526433751342243e-05, + "loss": 3.4792, + "step": 1510912 + }, + { + "epoch": 0.02, + "learning_rate": 2.525595156591191e-05, + "loss": 3.4748, + "step": 1511424 + }, + { + "epoch": 0.02, + "learning_rate": 2.5247565618401394e-05, + "loss": 3.4643, + "step": 1511936 + }, + { + "epoch": 0.02, + "learning_rate": 2.5239196049694603e-05, + "loss": 3.4769, + "step": 1512448 + }, + { + "epoch": 0.02, + "learning_rate": 2.5230810102184083e-05, + "loss": 3.4723, + "step": 1512960 + }, + { + "epoch": 0.02, + "learning_rate": 2.5222424154673563e-05, + "loss": 3.4815, + "step": 1513472 + }, + { + "epoch": 0.02, + "learning_rate": 2.5214038207163043e-05, + "loss": 3.4703, + "step": 1513984 + }, + { + "epoch": 0.02, + "learning_rate": 2.5205668638456255e-05, + "loss": 3.4812, + "step": 1514496 + }, + { + "epoch": 0.02, + "learning_rate": 2.5197282690945735e-05, + "loss": 3.4614, + "step": 1515008 + }, + { + "epoch": 0.02, + "learning_rate": 2.5188896743435215e-05, + "loss": 3.4797, + "step": 1515520 + }, + { + "epoch": 0.02, + "learning_rate": 2.5180510795924695e-05, + "loss": 3.477, + "step": 1516032 + }, + { + "epoch": 0.02, + "learning_rate": 2.5172124848414175e-05, + "loss": 3.4836, + "step": 1516544 + }, + { + "epoch": 0.02, + "learning_rate": 2.5163738900903655e-05, + "loss": 3.4826, + "step": 1517056 + }, + { + "epoch": 0.02, + "learning_rate": 2.515535295339313e-05, + "loss": 3.4817, + "step": 1517568 + }, + { + "epoch": 0.02, + "learning_rate": 2.514696700588261e-05, + "loss": 3.4647, + "step": 1518080 + }, + { + "epoch": 0.02, + "learning_rate": 2.5138597437175827e-05, + "loss": 3.4793, + "step": 1518592 + }, + { + "epoch": 0.02, + "learning_rate": 2.5130211489665307e-05, + "loss": 3.4804, + "step": 1519104 + }, + { + "epoch": 0.02, + "learning_rate": 2.512182554215478e-05, + "loss": 3.4869, + "step": 1519616 + }, + { + "epoch": 0.02, + "learning_rate": 2.511343959464426e-05, + "loss": 3.4821, + "step": 1520128 + }, + { + "epoch": 0.02, + "learning_rate": 2.5105070025937476e-05, + "loss": 3.4849, + "step": 1520640 + }, + { + "epoch": 0.02, + "learning_rate": 2.5096684078426956e-05, + "loss": 3.4798, + "step": 1521152 + }, + { + "epoch": 0.02, + "learning_rate": 2.5088298130916433e-05, + "loss": 3.4857, + "step": 1521664 + }, + { + "epoch": 0.02, + "learning_rate": 2.5079912183405913e-05, + "loss": 3.4739, + "step": 1522176 + }, + { + "epoch": 0.02, + "learning_rate": 2.507154261469913e-05, + "loss": 3.4753, + "step": 1522688 + }, + { + "epoch": 0.02, + "learning_rate": 2.50631566671886e-05, + "loss": 3.4776, + "step": 1523200 + }, + { + "epoch": 0.02, + "learning_rate": 2.5054770719678085e-05, + "loss": 3.4709, + "step": 1523712 + }, + { + "epoch": 0.02, + "learning_rate": 2.50464011509713e-05, + "loss": 3.4721, + "step": 1524224 + }, + { + "epoch": 0.02, + "learning_rate": 2.503801520346078e-05, + "loss": 3.4795, + "step": 1524736 + }, + { + "epoch": 0.02, + "learning_rate": 2.5029629255950254e-05, + "loss": 3.4755, + "step": 1525248 + }, + { + "epoch": 0.02, + "learning_rate": 2.5021243308439734e-05, + "loss": 3.4697, + "step": 1525760 + }, + { + "epoch": 0.02, + "learning_rate": 2.501287373973295e-05, + "loss": 3.4807, + "step": 1526272 + }, + { + "epoch": 0.03, + "eval_loss": 3.848757028579712, + "eval_runtime": 322.7385, + "eval_samples_per_second": 1182.353, + "eval_steps_per_second": 36.949, + "step": 1526400 + }, + { + "epoch": 1.0, + "learning_rate": 2.5004487792222426e-05, + "loss": 3.468, + "step": 1526784 + }, + { + "epoch": 1.0, + "learning_rate": 2.499610184471191e-05, + "loss": 3.4693, + "step": 1527296 + }, + { + "epoch": 1.0, + "learning_rate": 2.498771589720139e-05, + "loss": 3.4794, + "step": 1527808 + }, + { + "epoch": 1.0, + "learning_rate": 2.49793463284946e-05, + "loss": 3.4776, + "step": 1528320 + }, + { + "epoch": 1.0, + "learning_rate": 2.497096038098408e-05, + "loss": 3.49, + "step": 1528832 + }, + { + "epoch": 1.0, + "learning_rate": 2.496257443347356e-05, + "loss": 3.4637, + "step": 1529344 + }, + { + "epoch": 1.0, + "learning_rate": 2.495418848596304e-05, + "loss": 3.4698, + "step": 1529856 + }, + { + "epoch": 1.0, + "learning_rate": 2.494581891725625e-05, + "loss": 3.4644, + "step": 1530368 + }, + { + "epoch": 1.0, + "learning_rate": 2.493743296974573e-05, + "loss": 3.4792, + "step": 1530880 + }, + { + "epoch": 1.0, + "learning_rate": 2.492904702223521e-05, + "loss": 3.4806, + "step": 1531392 + }, + { + "epoch": 1.0, + "learning_rate": 2.492066107472469e-05, + "loss": 3.4681, + "step": 1531904 + }, + { + "epoch": 1.0, + "learning_rate": 2.49122915060179e-05, + "loss": 3.4845, + "step": 1532416 + }, + { + "epoch": 1.0, + "learning_rate": 2.490390555850738e-05, + "loss": 3.4584, + "step": 1532928 + }, + { + "epoch": 1.0, + "learning_rate": 2.4895519610996863e-05, + "loss": 3.4669, + "step": 1533440 + }, + { + "epoch": 1.0, + "learning_rate": 2.4887133663486343e-05, + "loss": 3.4728, + "step": 1533952 + }, + { + "epoch": 1.0, + "learning_rate": 2.4878764094779552e-05, + "loss": 3.4674, + "step": 1534464 + }, + { + "epoch": 1.0, + "learning_rate": 2.4870378147269032e-05, + "loss": 3.4682, + "step": 1534976 + }, + { + "epoch": 1.0, + "learning_rate": 2.4861992199758512e-05, + "loss": 3.4714, + "step": 1535488 + }, + { + "epoch": 1.0, + "learning_rate": 2.485360625224799e-05, + "loss": 3.4667, + "step": 1536000 + }, + { + "epoch": 1.0, + "learning_rate": 2.4845236683541205e-05, + "loss": 3.4972, + "step": 1536512 + }, + { + "epoch": 1.0, + "learning_rate": 2.4836850736030685e-05, + "loss": 3.4728, + "step": 1537024 + }, + { + "epoch": 1.0, + "learning_rate": 2.4828481167323894e-05, + "loss": 3.4712, + "step": 1537536 + }, + { + "epoch": 1.0, + "learning_rate": 2.4820095219813374e-05, + "loss": 3.4784, + "step": 1538048 + }, + { + "epoch": 1.0, + "learning_rate": 2.4811709272302854e-05, + "loss": 3.482, + "step": 1538560 + }, + { + "epoch": 1.0, + "learning_rate": 2.4803323324792334e-05, + "loss": 3.4662, + "step": 1539072 + }, + { + "epoch": 1.0, + "learning_rate": 2.4794937377281817e-05, + "loss": 3.4791, + "step": 1539584 + }, + { + "epoch": 1.0, + "learning_rate": 2.4786551429771294e-05, + "loss": 3.4679, + "step": 1540096 + }, + { + "epoch": 1.0, + "learning_rate": 2.4778165482260774e-05, + "loss": 3.4702, + "step": 1540608 + }, + { + "epoch": 1.0, + "learning_rate": 2.4769795913553986e-05, + "loss": 3.4592, + "step": 1541120 + }, + { + "epoch": 1.0, + "learning_rate": 2.4761409966043463e-05, + "loss": 3.4743, + "step": 1541632 + }, + { + "epoch": 1.01, + "learning_rate": 2.4753024018532943e-05, + "loss": 3.4887, + "step": 1542144 + }, + { + "epoch": 1.01, + "learning_rate": 2.4744638071022426e-05, + "loss": 3.4756, + "step": 1542656 + }, + { + "epoch": 1.01, + "learning_rate": 2.473626850231564e-05, + "loss": 3.477, + "step": 1543168 + }, + { + "epoch": 1.01, + "learning_rate": 2.4727882554805115e-05, + "loss": 3.4785, + "step": 1543680 + }, + { + "epoch": 1.01, + "learning_rate": 2.4719496607294595e-05, + "loss": 3.468, + "step": 1544192 + }, + { + "epoch": 1.01, + "learning_rate": 2.4711110659784075e-05, + "loss": 3.4779, + "step": 1544704 + }, + { + "epoch": 1.01, + "learning_rate": 2.4702741091077287e-05, + "loss": 3.4586, + "step": 1545216 + }, + { + "epoch": 1.01, + "learning_rate": 2.4694355143566767e-05, + "loss": 3.4717, + "step": 1545728 + }, + { + "epoch": 1.01, + "learning_rate": 2.4685969196056247e-05, + "loss": 3.463, + "step": 1546240 + }, + { + "epoch": 1.01, + "learning_rate": 2.4677583248545727e-05, + "loss": 3.4688, + "step": 1546752 + }, + { + "epoch": 1.01, + "learning_rate": 2.466923005864267e-05, + "loss": 3.4687, + "step": 1547264 + }, + { + "epoch": 1.01, + "learning_rate": 2.466084411113215e-05, + "loss": 3.4793, + "step": 1547776 + }, + { + "epoch": 1.01, + "learning_rate": 2.4652458163621632e-05, + "loss": 3.4744, + "step": 1548288 + }, + { + "epoch": 1.01, + "learning_rate": 2.4644072216111112e-05, + "loss": 3.4705, + "step": 1548800 + }, + { + "epoch": 1.01, + "learning_rate": 2.463568626860059e-05, + "loss": 3.4778, + "step": 1549312 + }, + { + "epoch": 1.01, + "learning_rate": 2.462730032109007e-05, + "loss": 3.4717, + "step": 1549824 + }, + { + "epoch": 1.01, + "learning_rate": 2.461891437357955e-05, + "loss": 3.4745, + "step": 1550336 + }, + { + "epoch": 1.01, + "learning_rate": 2.461052842606903e-05, + "loss": 3.4675, + "step": 1550848 + }, + { + "epoch": 1.01, + "learning_rate": 2.460215885736224e-05, + "loss": 3.4581, + "step": 1551360 + }, + { + "epoch": 1.01, + "learning_rate": 2.459377290985172e-05, + "loss": 3.4763, + "step": 1551872 + }, + { + "epoch": 1.01, + "learning_rate": 2.45853869623412e-05, + "loss": 3.4678, + "step": 1552384 + }, + { + "epoch": 1.01, + "learning_rate": 2.457700101483068e-05, + "loss": 3.4736, + "step": 1552896 + }, + { + "epoch": 1.01, + "learning_rate": 2.456863144612389e-05, + "loss": 3.4638, + "step": 1553408 + }, + { + "epoch": 1.01, + "learning_rate": 2.456024549861337e-05, + "loss": 3.4717, + "step": 1553920 + }, + { + "epoch": 1.01, + "learning_rate": 2.455185955110285e-05, + "loss": 3.4533, + "step": 1554432 + }, + { + "epoch": 1.01, + "learning_rate": 2.4543489982396062e-05, + "loss": 3.4815, + "step": 1554944 + }, + { + "epoch": 1.01, + "learning_rate": 2.4535104034885542e-05, + "loss": 3.4591, + "step": 1555456 + }, + { + "epoch": 1.01, + "learning_rate": 2.4526718087375022e-05, + "loss": 3.468, + "step": 1555968 + }, + { + "epoch": 1.01, + "learning_rate": 2.4518332139864502e-05, + "loss": 3.4709, + "step": 1556480 + }, + { + "epoch": 1.01, + "learning_rate": 2.4509946192353982e-05, + "loss": 3.4624, + "step": 1556992 + }, + { + "epoch": 1.01, + "learning_rate": 2.4501560244843462e-05, + "loss": 3.4655, + "step": 1557504 + }, + { + "epoch": 1.01, + "learning_rate": 2.4493174297332942e-05, + "loss": 3.4663, + "step": 1558016 + }, + { + "epoch": 1.01, + "learning_rate": 2.4484788349822422e-05, + "loss": 3.4587, + "step": 1558528 + }, + { + "epoch": 1.01, + "learning_rate": 2.4476418781115635e-05, + "loss": 3.4556, + "step": 1559040 + }, + { + "epoch": 1.01, + "learning_rate": 2.4468032833605115e-05, + "loss": 3.4705, + "step": 1559552 + }, + { + "epoch": 1.01, + "learning_rate": 2.445964688609459e-05, + "loss": 3.4693, + "step": 1560064 + }, + { + "epoch": 1.01, + "learning_rate": 2.445126093858407e-05, + "loss": 3.459, + "step": 1560576 + }, + { + "epoch": 1.01, + "learning_rate": 2.4442891369877287e-05, + "loss": 3.4651, + "step": 1561088 + }, + { + "epoch": 1.01, + "learning_rate": 2.4434505422366767e-05, + "loss": 3.4527, + "step": 1561600 + }, + { + "epoch": 1.01, + "learning_rate": 2.4426119474856244e-05, + "loss": 3.4628, + "step": 1562112 + }, + { + "epoch": 1.01, + "learning_rate": 2.4417733527345723e-05, + "loss": 3.4712, + "step": 1562624 + }, + { + "epoch": 1.01, + "learning_rate": 2.4409363958638936e-05, + "loss": 3.4672, + "step": 1563136 + }, + { + "epoch": 1.01, + "learning_rate": 2.4400978011128413e-05, + "loss": 3.4783, + "step": 1563648 + }, + { + "epoch": 1.01, + "learning_rate": 2.4392592063617896e-05, + "loss": 3.4699, + "step": 1564160 + }, + { + "epoch": 1.01, + "learning_rate": 2.4384206116107376e-05, + "loss": 3.4788, + "step": 1564672 + }, + { + "epoch": 1.01, + "learning_rate": 2.4375836547400588e-05, + "loss": 3.4597, + "step": 1565184 + }, + { + "epoch": 1.01, + "learning_rate": 2.4367450599890065e-05, + "loss": 3.4686, + "step": 1565696 + }, + { + "epoch": 1.01, + "learning_rate": 2.4359064652379545e-05, + "loss": 3.4701, + "step": 1566208 + }, + { + "epoch": 1.01, + "learning_rate": 2.4350678704869025e-05, + "loss": 3.4531, + "step": 1566720 + }, + { + "epoch": 1.01, + "learning_rate": 2.434230913616224e-05, + "loss": 3.4749, + "step": 1567232 + }, + { + "epoch": 1.01, + "learning_rate": 2.4333923188651717e-05, + "loss": 3.4688, + "step": 1567744 + }, + { + "epoch": 1.01, + "learning_rate": 2.4325537241141197e-05, + "loss": 3.4733, + "step": 1568256 + }, + { + "epoch": 1.01, + "learning_rate": 2.431716767243441e-05, + "loss": 3.4686, + "step": 1568768 + }, + { + "epoch": 1.01, + "learning_rate": 2.4308781724923886e-05, + "loss": 3.4548, + "step": 1569280 + }, + { + "epoch": 1.01, + "learning_rate": 2.4300395777413366e-05, + "loss": 3.4681, + "step": 1569792 + }, + { + "epoch": 1.01, + "learning_rate": 2.429200982990285e-05, + "loss": 3.4664, + "step": 1570304 + }, + { + "epoch": 1.01, + "learning_rate": 2.428362388239233e-05, + "loss": 3.4728, + "step": 1570816 + }, + { + "epoch": 1.01, + "learning_rate": 2.427523793488181e-05, + "loss": 3.4691, + "step": 1571328 + }, + { + "epoch": 1.01, + "learning_rate": 2.426685198737129e-05, + "loss": 3.4741, + "step": 1571840 + }, + { + "epoch": 1.02, + "learning_rate": 2.425846603986077e-05, + "loss": 3.4727, + "step": 1572352 + }, + { + "epoch": 1.02, + "learning_rate": 2.425009647115398e-05, + "loss": 3.4582, + "step": 1572864 + }, + { + "epoch": 1.02, + "learning_rate": 2.424171052364346e-05, + "loss": 3.4684, + "step": 1573376 + }, + { + "epoch": 1.02, + "learning_rate": 2.4233324576132942e-05, + "loss": 3.463, + "step": 1573888 + }, + { + "epoch": 1.02, + "learning_rate": 2.422495500742615e-05, + "loss": 3.4734, + "step": 1574400 + }, + { + "epoch": 1.02, + "learning_rate": 2.421656905991563e-05, + "loss": 3.4785, + "step": 1574912 + }, + { + "epoch": 1.02, + "learning_rate": 2.420818311240511e-05, + "loss": 3.4642, + "step": 1575424 + }, + { + "epoch": 1.02, + "learning_rate": 2.419979716489459e-05, + "loss": 3.4617, + "step": 1575936 + }, + { + "epoch": 1.02, + "learning_rate": 2.4191427596187803e-05, + "loss": 3.4663, + "step": 1576448 + }, + { + "epoch": 1.02, + "learning_rate": 2.4183041648677283e-05, + "loss": 3.47, + "step": 1576960 + }, + { + "epoch": 1.02, + "learning_rate": 2.4174655701166763e-05, + "loss": 3.4772, + "step": 1577472 + }, + { + "epoch": 1.02, + "learning_rate": 2.4166269753656243e-05, + "loss": 3.4642, + "step": 1577984 + }, + { + "epoch": 1.02, + "learning_rate": 2.4157900184949452e-05, + "loss": 3.4618, + "step": 1578496 + }, + { + "epoch": 1.02, + "learning_rate": 2.4149514237438932e-05, + "loss": 3.4605, + "step": 1579008 + }, + { + "epoch": 1.02, + "learning_rate": 2.4141128289928412e-05, + "loss": 3.4729, + "step": 1579520 + }, + { + "epoch": 1.02, + "learning_rate": 2.4132742342417895e-05, + "loss": 3.4525, + "step": 1580032 + }, + { + "epoch": 1.02, + "learning_rate": 2.4124372773711105e-05, + "loss": 3.4642, + "step": 1580544 + }, + { + "epoch": 1.02, + "learning_rate": 2.4115986826200584e-05, + "loss": 3.4708, + "step": 1581056 + }, + { + "epoch": 1.02, + "learning_rate": 2.4107600878690064e-05, + "loss": 3.4663, + "step": 1581568 + }, + { + "epoch": 1.02, + "learning_rate": 2.409921493117954e-05, + "loss": 3.4601, + "step": 1582080 + }, + { + "epoch": 1.02, + "learning_rate": 2.4090845362472757e-05, + "loss": 3.4731, + "step": 1582592 + }, + { + "epoch": 1.02, + "learning_rate": 2.4082459414962237e-05, + "loss": 3.4637, + "step": 1583104 + }, + { + "epoch": 1.02, + "learning_rate": 2.4074073467451717e-05, + "loss": 3.4614, + "step": 1583616 + }, + { + "epoch": 1.02, + "learning_rate": 2.4065687519941193e-05, + "loss": 3.4676, + "step": 1584128 + }, + { + "epoch": 1.02, + "learning_rate": 2.4057317951234406e-05, + "loss": 3.4663, + "step": 1584640 + }, + { + "epoch": 1.02, + "learning_rate": 2.404894838252762e-05, + "loss": 3.4745, + "step": 1585152 + }, + { + "epoch": 1.02, + "learning_rate": 2.4040562435017098e-05, + "loss": 3.4726, + "step": 1585664 + }, + { + "epoch": 1.02, + "learning_rate": 2.4032176487506578e-05, + "loss": 3.468, + "step": 1586176 + }, + { + "epoch": 1.02, + "learning_rate": 2.4023790539996058e-05, + "loss": 3.4561, + "step": 1586688 + }, + { + "epoch": 1.02, + "learning_rate": 2.4015404592485538e-05, + "loss": 3.4679, + "step": 1587200 + }, + { + "epoch": 1.02, + "learning_rate": 2.4007018644975015e-05, + "loss": 3.4628, + "step": 1587712 + }, + { + "epoch": 1.02, + "learning_rate": 2.3998632697464495e-05, + "loss": 3.4512, + "step": 1588224 + }, + { + "epoch": 1.02, + "learning_rate": 2.3990246749953975e-05, + "loss": 3.4684, + "step": 1588736 + }, + { + "epoch": 1.02, + "learning_rate": 2.398187718124719e-05, + "loss": 3.4582, + "step": 1589248 + }, + { + "epoch": 1.02, + "learning_rate": 2.3973491233736667e-05, + "loss": 3.4711, + "step": 1589760 + }, + { + "epoch": 1.02, + "learning_rate": 2.3965105286226147e-05, + "loss": 3.4622, + "step": 1590272 + }, + { + "epoch": 1.02, + "learning_rate": 2.395673571751936e-05, + "loss": 3.4687, + "step": 1590784 + }, + { + "epoch": 1.02, + "learning_rate": 2.394834977000884e-05, + "loss": 3.4493, + "step": 1591296 + }, + { + "epoch": 1.02, + "learning_rate": 2.393996382249832e-05, + "loss": 3.4639, + "step": 1591808 + }, + { + "epoch": 1.02, + "learning_rate": 2.39315778749878e-05, + "loss": 3.4685, + "step": 1592320 + }, + { + "epoch": 1.02, + "learning_rate": 2.392319192747728e-05, + "loss": 3.4663, + "step": 1592832 + }, + { + "epoch": 1.02, + "learning_rate": 2.391480597996676e-05, + "loss": 3.4705, + "step": 1593344 + }, + { + "epoch": 1.02, + "learning_rate": 2.390642003245624e-05, + "loss": 3.4731, + "step": 1593856 + }, + { + "epoch": 1.02, + "learning_rate": 2.389803408494572e-05, + "loss": 3.4521, + "step": 1594368 + }, + { + "epoch": 1.02, + "learning_rate": 2.3889664516238928e-05, + "loss": 3.4671, + "step": 1594880 + }, + { + "epoch": 1.02, + "learning_rate": 2.388127856872841e-05, + "loss": 3.4728, + "step": 1595392 + }, + { + "epoch": 1.02, + "learning_rate": 2.387289262121789e-05, + "loss": 3.4713, + "step": 1595904 + }, + { + "epoch": 1.02, + "learning_rate": 2.386450667370737e-05, + "loss": 3.4717, + "step": 1596416 + }, + { + "epoch": 1.02, + "learning_rate": 2.385613710500058e-05, + "loss": 3.4746, + "step": 1596928 + }, + { + "epoch": 1.02, + "learning_rate": 2.384775115749006e-05, + "loss": 3.4653, + "step": 1597440 + }, + { + "epoch": 1.02, + "learning_rate": 2.383936520997954e-05, + "loss": 3.4732, + "step": 1597952 + }, + { + "epoch": 1.02, + "learning_rate": 2.383097926246902e-05, + "loss": 3.4598, + "step": 1598464 + }, + { + "epoch": 1.02, + "learning_rate": 2.3822609693762233e-05, + "loss": 3.4668, + "step": 1598976 + }, + { + "epoch": 1.02, + "learning_rate": 2.3814223746251713e-05, + "loss": 3.4609, + "step": 1599488 + }, + { + "epoch": 1.02, + "learning_rate": 2.3805837798741193e-05, + "loss": 3.4638, + "step": 1600000 + }, + { + "epoch": 1.02, + "learning_rate": 2.3797468230034402e-05, + "loss": 3.4637, + "step": 1600512 + }, + { + "epoch": 1.02, + "learning_rate": 2.3789082282523882e-05, + "loss": 3.4624, + "step": 1601024 + }, + { + "epoch": 1.02, + "learning_rate": 2.3780696335013365e-05, + "loss": 3.4693, + "step": 1601536 + }, + { + "epoch": 1.02, + "learning_rate": 2.3772310387502845e-05, + "loss": 3.4543, + "step": 1602048 + }, + { + "epoch": 1.02, + "learning_rate": 2.3763924439992322e-05, + "loss": 3.4697, + "step": 1602560 + }, + { + "epoch": 1.03, + "eval_loss": 3.8502883911132812, + "eval_runtime": 328.8188, + "eval_samples_per_second": 1160.49, + "eval_steps_per_second": 36.266, + "step": 1602720 + }, + { + "epoch": 0.0, + "learning_rate": 2.3755554871285534e-05, + "loss": 3.4541, + "step": 1603072 + }, + { + "epoch": 0.0, + "learning_rate": 2.3747168923775014e-05, + "loss": 3.4582, + "step": 1603584 + }, + { + "epoch": 0.0, + "learning_rate": 2.3738782976264494e-05, + "loss": 3.4661, + "step": 1604096 + }, + { + "epoch": 0.0, + "learning_rate": 2.3730397028753974e-05, + "loss": 3.4688, + "step": 1604608 + }, + { + "epoch": 0.0, + "learning_rate": 2.3722027460047187e-05, + "loss": 3.4705, + "step": 1605120 + }, + { + "epoch": 0.0, + "learning_rate": 2.3713641512536667e-05, + "loss": 3.4564, + "step": 1605632 + }, + { + "epoch": 0.0, + "learning_rate": 2.3705255565026143e-05, + "loss": 3.4575, + "step": 1606144 + }, + { + "epoch": 0.0, + "learning_rate": 2.3696869617515623e-05, + "loss": 3.4581, + "step": 1606656 + }, + { + "epoch": 0.0, + "learning_rate": 2.3688500048808836e-05, + "loss": 3.4632, + "step": 1607168 + }, + { + "epoch": 0.0, + "learning_rate": 2.368011410129832e-05, + "loss": 3.4724, + "step": 1607680 + }, + { + "epoch": 0.0, + "learning_rate": 2.3671728153787796e-05, + "loss": 3.4557, + "step": 1608192 + }, + { + "epoch": 0.0, + "learning_rate": 2.3663342206277275e-05, + "loss": 3.4684, + "step": 1608704 + }, + { + "epoch": 0.0, + "learning_rate": 2.3654972637570488e-05, + "loss": 3.4521, + "step": 1609216 + }, + { + "epoch": 0.0, + "learning_rate": 2.3646586690059965e-05, + "loss": 3.4535, + "step": 1609728 + }, + { + "epoch": 0.0, + "learning_rate": 2.3638200742549444e-05, + "loss": 3.4626, + "step": 1610240 + }, + { + "epoch": 0.0, + "learning_rate": 2.3629814795038928e-05, + "loss": 3.4544, + "step": 1610752 + }, + { + "epoch": 0.0, + "learning_rate": 2.362144522633214e-05, + "loss": 3.457, + "step": 1611264 + }, + { + "epoch": 0.0, + "learning_rate": 2.3613059278821617e-05, + "loss": 3.4603, + "step": 1611776 + }, + { + "epoch": 0.0, + "learning_rate": 2.3604673331311097e-05, + "loss": 3.4539, + "step": 1612288 + }, + { + "epoch": 0.0, + "learning_rate": 2.3596287383800577e-05, + "loss": 3.4827, + "step": 1612800 + }, + { + "epoch": 0.0, + "learning_rate": 2.358791781509379e-05, + "loss": 3.4659, + "step": 1613312 + }, + { + "epoch": 0.0, + "learning_rate": 2.3579548246387002e-05, + "loss": 3.4611, + "step": 1613824 + }, + { + "epoch": 0.0, + "learning_rate": 2.3571162298876482e-05, + "loss": 3.4659, + "step": 1614336 + }, + { + "epoch": 0.0, + "learning_rate": 2.356277635136596e-05, + "loss": 3.471, + "step": 1614848 + }, + { + "epoch": 0.0, + "learning_rate": 2.3554390403855438e-05, + "loss": 3.4535, + "step": 1615360 + }, + { + "epoch": 0.0, + "learning_rate": 2.3546004456344918e-05, + "loss": 3.4669, + "step": 1615872 + }, + { + "epoch": 0.0, + "learning_rate": 2.3537618508834398e-05, + "loss": 3.4617, + "step": 1616384 + }, + { + "epoch": 0.0, + "learning_rate": 2.352923256132388e-05, + "loss": 3.456, + "step": 1616896 + }, + { + "epoch": 0.0, + "learning_rate": 2.352084661381336e-05, + "loss": 3.4472, + "step": 1617408 + }, + { + "epoch": 0.0, + "learning_rate": 2.351247704510657e-05, + "loss": 3.4616, + "step": 1617920 + }, + { + "epoch": 0.01, + "learning_rate": 2.350409109759605e-05, + "loss": 3.4784, + "step": 1618432 + }, + { + "epoch": 0.01, + "learning_rate": 2.349570515008553e-05, + "loss": 3.4626, + "step": 1618944 + }, + { + "epoch": 0.01, + "learning_rate": 2.3487335581378743e-05, + "loss": 3.4681, + "step": 1619456 + }, + { + "epoch": 0.01, + "learning_rate": 2.3478949633868223e-05, + "loss": 3.4634, + "step": 1619968 + }, + { + "epoch": 0.01, + "learning_rate": 2.3470563686357703e-05, + "loss": 3.4544, + "step": 1620480 + }, + { + "epoch": 0.01, + "learning_rate": 2.3462194117650912e-05, + "loss": 3.4655, + "step": 1620992 + }, + { + "epoch": 0.01, + "learning_rate": 2.3453808170140392e-05, + "loss": 3.4537, + "step": 1621504 + }, + { + "epoch": 0.01, + "learning_rate": 2.3445422222629872e-05, + "loss": 3.4559, + "step": 1622016 + }, + { + "epoch": 0.01, + "learning_rate": 2.3437036275119352e-05, + "loss": 3.4538, + "step": 1622528 + }, + { + "epoch": 0.01, + "learning_rate": 2.3428650327608835e-05, + "loss": 3.4587, + "step": 1623040 + }, + { + "epoch": 0.01, + "learning_rate": 2.3420264380098315e-05, + "loss": 3.4591, + "step": 1623552 + }, + { + "epoch": 0.01, + "learning_rate": 2.3411894811391524e-05, + "loss": 3.4667, + "step": 1624064 + }, + { + "epoch": 0.01, + "learning_rate": 2.3403508863881004e-05, + "loss": 3.4625, + "step": 1624576 + }, + { + "epoch": 0.01, + "learning_rate": 2.3395122916370484e-05, + "loss": 3.4601, + "step": 1625088 + }, + { + "epoch": 0.01, + "learning_rate": 2.3386736968859964e-05, + "loss": 3.4669, + "step": 1625600 + }, + { + "epoch": 0.01, + "learning_rate": 2.3378351021349444e-05, + "loss": 3.462, + "step": 1626112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3369965073838924e-05, + "loss": 3.4634, + "step": 1626624 + }, + { + "epoch": 0.01, + "learning_rate": 2.3361579126328404e-05, + "loss": 3.4568, + "step": 1627136 + }, + { + "epoch": 0.01, + "learning_rate": 2.3353209557621616e-05, + "loss": 3.4451, + "step": 1627648 + }, + { + "epoch": 0.01, + "learning_rate": 2.3344823610111093e-05, + "loss": 3.4647, + "step": 1628160 + }, + { + "epoch": 0.01, + "learning_rate": 2.3336437662600573e-05, + "loss": 3.4578, + "step": 1628672 + }, + { + "epoch": 0.01, + "learning_rate": 2.3328051715090053e-05, + "loss": 3.4612, + "step": 1629184 + }, + { + "epoch": 0.01, + "learning_rate": 2.331968214638327e-05, + "loss": 3.4519, + "step": 1629696 + }, + { + "epoch": 0.01, + "learning_rate": 2.3311296198872745e-05, + "loss": 3.4575, + "step": 1630208 + }, + { + "epoch": 0.01, + "learning_rate": 2.3302910251362225e-05, + "loss": 3.4407, + "step": 1630720 + }, + { + "epoch": 0.01, + "learning_rate": 2.3294540682655438e-05, + "loss": 3.4687, + "step": 1631232 + }, + { + "epoch": 0.01, + "learning_rate": 2.3286154735144918e-05, + "loss": 3.4489, + "step": 1631744 + }, + { + "epoch": 0.01, + "learning_rate": 2.3277768787634398e-05, + "loss": 3.4594, + "step": 1632256 + }, + { + "epoch": 0.01, + "learning_rate": 2.3269382840123878e-05, + "loss": 3.4614, + "step": 1632768 + }, + { + "epoch": 0.01, + "learning_rate": 2.3260996892613358e-05, + "loss": 3.4475, + "step": 1633280 + }, + { + "epoch": 0.01, + "learning_rate": 2.3252610945102838e-05, + "loss": 3.4511, + "step": 1633792 + }, + { + "epoch": 0.01, + "learning_rate": 2.3244224997592318e-05, + "loss": 3.4626, + "step": 1634304 + }, + { + "epoch": 0.01, + "learning_rate": 2.3235839050081797e-05, + "loss": 3.4436, + "step": 1634816 + }, + { + "epoch": 0.01, + "learning_rate": 2.3227469481375007e-05, + "loss": 3.4441, + "step": 1635328 + }, + { + "epoch": 0.01, + "learning_rate": 2.321908353386449e-05, + "loss": 3.4597, + "step": 1635840 + }, + { + "epoch": 0.01, + "learning_rate": 2.321069758635397e-05, + "loss": 3.46, + "step": 1636352 + }, + { + "epoch": 0.01, + "learning_rate": 2.320231163884345e-05, + "loss": 3.4457, + "step": 1636864 + }, + { + "epoch": 0.01, + "learning_rate": 2.319394207013666e-05, + "loss": 3.4564, + "step": 1637376 + }, + { + "epoch": 0.01, + "learning_rate": 2.318555612262614e-05, + "loss": 3.4399, + "step": 1637888 + }, + { + "epoch": 0.01, + "learning_rate": 2.317717017511562e-05, + "loss": 3.4478, + "step": 1638400 + }, + { + "epoch": 0.01, + "learning_rate": 2.31687842276051e-05, + "loss": 3.461, + "step": 1638912 + }, + { + "epoch": 0.01, + "learning_rate": 2.316041465889831e-05, + "loss": 3.456, + "step": 1639424 + }, + { + "epoch": 0.01, + "learning_rate": 2.315202871138779e-05, + "loss": 3.4644, + "step": 1639936 + }, + { + "epoch": 0.01, + "learning_rate": 2.314364276387727e-05, + "loss": 3.4592, + "step": 1640448 + }, + { + "epoch": 0.01, + "learning_rate": 2.3135256816366748e-05, + "loss": 3.4702, + "step": 1640960 + }, + { + "epoch": 0.01, + "learning_rate": 2.312688724765996e-05, + "loss": 3.4446, + "step": 1641472 + }, + { + "epoch": 0.01, + "learning_rate": 2.3118501300149444e-05, + "loss": 3.4606, + "step": 1641984 + }, + { + "epoch": 0.01, + "learning_rate": 2.3110115352638924e-05, + "loss": 3.4608, + "step": 1642496 + }, + { + "epoch": 0.01, + "learning_rate": 2.31017294051284e-05, + "loss": 3.4401, + "step": 1643008 + }, + { + "epoch": 0.01, + "learning_rate": 2.3093359836421613e-05, + "loss": 3.4611, + "step": 1643520 + }, + { + "epoch": 0.01, + "learning_rate": 2.3084973888911093e-05, + "loss": 3.4586, + "step": 1644032 + }, + { + "epoch": 0.01, + "learning_rate": 2.3076587941400573e-05, + "loss": 3.4601, + "step": 1644544 + }, + { + "epoch": 0.01, + "learning_rate": 2.3068218372693785e-05, + "loss": 3.458, + "step": 1645056 + }, + { + "epoch": 0.01, + "learning_rate": 2.3059832425183265e-05, + "loss": 3.4475, + "step": 1645568 + }, + { + "epoch": 0.01, + "learning_rate": 2.3051446477672745e-05, + "loss": 3.4504, + "step": 1646080 + }, + { + "epoch": 0.01, + "learning_rate": 2.304306053016222e-05, + "loss": 3.4559, + "step": 1646592 + }, + { + "epoch": 0.01, + "learning_rate": 2.30346745826517e-05, + "loss": 3.4642, + "step": 1647104 + }, + { + "epoch": 0.01, + "learning_rate": 2.302628863514118e-05, + "loss": 3.4567, + "step": 1647616 + }, + { + "epoch": 0.01, + "learning_rate": 2.3017902687630665e-05, + "loss": 3.4654, + "step": 1648128 + }, + { + "epoch": 0.02, + "learning_rate": 2.3009516740120145e-05, + "loss": 3.4628, + "step": 1648640 + }, + { + "epoch": 0.02, + "learning_rate": 2.3001147171413354e-05, + "loss": 3.449, + "step": 1649152 + }, + { + "epoch": 0.02, + "learning_rate": 2.2992761223902834e-05, + "loss": 3.4574, + "step": 1649664 + }, + { + "epoch": 0.02, + "learning_rate": 2.2984375276392314e-05, + "loss": 3.4493, + "step": 1650176 + }, + { + "epoch": 0.02, + "learning_rate": 2.2976005707685526e-05, + "loss": 3.4627, + "step": 1650688 + }, + { + "epoch": 0.02, + "learning_rate": 2.2967619760175006e-05, + "loss": 3.4719, + "step": 1651200 + }, + { + "epoch": 0.02, + "learning_rate": 2.2959233812664486e-05, + "loss": 3.4476, + "step": 1651712 + }, + { + "epoch": 0.02, + "learning_rate": 2.2950847865153966e-05, + "loss": 3.4511, + "step": 1652224 + }, + { + "epoch": 0.02, + "learning_rate": 2.2942478296447175e-05, + "loss": 3.4533, + "step": 1652736 + }, + { + "epoch": 0.02, + "learning_rate": 2.2934092348936655e-05, + "loss": 3.4597, + "step": 1653248 + }, + { + "epoch": 0.02, + "learning_rate": 2.2925706401426135e-05, + "loss": 3.468, + "step": 1653760 + }, + { + "epoch": 0.02, + "learning_rate": 2.2917320453915615e-05, + "loss": 3.4528, + "step": 1654272 + }, + { + "epoch": 0.02, + "learning_rate": 2.2908950885208827e-05, + "loss": 3.4512, + "step": 1654784 + }, + { + "epoch": 0.02, + "learning_rate": 2.2900564937698307e-05, + "loss": 3.4452, + "step": 1655296 + }, + { + "epoch": 0.02, + "learning_rate": 2.2892178990187787e-05, + "loss": 3.4649, + "step": 1655808 + }, + { + "epoch": 0.02, + "learning_rate": 2.2883793042677267e-05, + "loss": 3.4393, + "step": 1656320 + }, + { + "epoch": 0.02, + "learning_rate": 2.2875423473970476e-05, + "loss": 3.4527, + "step": 1656832 + }, + { + "epoch": 0.02, + "learning_rate": 2.286703752645996e-05, + "loss": 3.4558, + "step": 1657344 + }, + { + "epoch": 0.02, + "learning_rate": 2.285865157894944e-05, + "loss": 3.4596, + "step": 1657856 + }, + { + "epoch": 0.02, + "learning_rate": 2.285026563143892e-05, + "loss": 3.4492, + "step": 1658368 + }, + { + "epoch": 0.02, + "learning_rate": 2.284189606273213e-05, + "loss": 3.4572, + "step": 1658880 + }, + { + "epoch": 0.02, + "learning_rate": 2.283351011522161e-05, + "loss": 3.4555, + "step": 1659392 + }, + { + "epoch": 0.02, + "learning_rate": 2.282512416771109e-05, + "loss": 3.4522, + "step": 1659904 + }, + { + "epoch": 0.02, + "learning_rate": 2.281673822020057e-05, + "loss": 3.4581, + "step": 1660416 + }, + { + "epoch": 0.02, + "learning_rate": 2.280836865149378e-05, + "loss": 3.4542, + "step": 1660928 + }, + { + "epoch": 0.02, + "learning_rate": 2.279998270398326e-05, + "loss": 3.4623, + "step": 1661440 + }, + { + "epoch": 0.02, + "learning_rate": 2.279159675647274e-05, + "loss": 3.4643, + "step": 1661952 + }, + { + "epoch": 0.02, + "learning_rate": 2.278321080896222e-05, + "loss": 3.4519, + "step": 1662464 + }, + { + "epoch": 0.02, + "learning_rate": 2.277484124025543e-05, + "loss": 3.4463, + "step": 1662976 + }, + { + "epoch": 0.02, + "learning_rate": 2.2766455292744913e-05, + "loss": 3.4546, + "step": 1663488 + }, + { + "epoch": 0.02, + "learning_rate": 2.2758069345234393e-05, + "loss": 3.4541, + "step": 1664000 + }, + { + "epoch": 0.02, + "learning_rate": 2.2749683397723873e-05, + "loss": 3.4426, + "step": 1664512 + }, + { + "epoch": 0.02, + "learning_rate": 2.2741313829017082e-05, + "loss": 3.4542, + "step": 1665024 + }, + { + "epoch": 0.02, + "learning_rate": 2.2732927881506562e-05, + "loss": 3.4434, + "step": 1665536 + }, + { + "epoch": 0.02, + "learning_rate": 2.2724541933996042e-05, + "loss": 3.4602, + "step": 1666048 + }, + { + "epoch": 0.02, + "learning_rate": 2.2716155986485522e-05, + "loss": 3.4507, + "step": 1666560 + }, + { + "epoch": 0.02, + "learning_rate": 2.2707786417778735e-05, + "loss": 3.4559, + "step": 1667072 + }, + { + "epoch": 0.02, + "learning_rate": 2.2699400470268215e-05, + "loss": 3.4447, + "step": 1667584 + }, + { + "epoch": 0.02, + "learning_rate": 2.2691014522757695e-05, + "loss": 3.4479, + "step": 1668096 + }, + { + "epoch": 0.02, + "learning_rate": 2.268262857524717e-05, + "loss": 3.4582, + "step": 1668608 + }, + { + "epoch": 0.02, + "learning_rate": 2.267424262773665e-05, + "loss": 3.4597, + "step": 1669120 + }, + { + "epoch": 0.02, + "learning_rate": 2.2665856680226135e-05, + "loss": 3.4528, + "step": 1669632 + }, + { + "epoch": 0.02, + "learning_rate": 2.2657470732715615e-05, + "loss": 3.4599, + "step": 1670144 + }, + { + "epoch": 0.02, + "learning_rate": 2.2649084785205095e-05, + "loss": 3.4446, + "step": 1670656 + }, + { + "epoch": 0.02, + "learning_rate": 2.2640715216498304e-05, + "loss": 3.4565, + "step": 1671168 + }, + { + "epoch": 0.02, + "learning_rate": 2.2632329268987784e-05, + "loss": 3.4602, + "step": 1671680 + }, + { + "epoch": 0.02, + "learning_rate": 2.2623943321477264e-05, + "loss": 3.4606, + "step": 1672192 + }, + { + "epoch": 0.02, + "learning_rate": 2.2615557373966743e-05, + "loss": 3.4596, + "step": 1672704 + }, + { + "epoch": 0.02, + "learning_rate": 2.2607187805259956e-05, + "loss": 3.4679, + "step": 1673216 + }, + { + "epoch": 0.02, + "learning_rate": 2.2598801857749436e-05, + "loss": 3.4535, + "step": 1673728 + }, + { + "epoch": 0.02, + "learning_rate": 2.2590415910238916e-05, + "loss": 3.4646, + "step": 1674240 + }, + { + "epoch": 0.02, + "learning_rate": 2.2582029962728396e-05, + "loss": 3.446, + "step": 1674752 + }, + { + "epoch": 0.02, + "learning_rate": 2.2573660394021605e-05, + "loss": 3.4555, + "step": 1675264 + }, + { + "epoch": 0.02, + "learning_rate": 2.2565274446511085e-05, + "loss": 3.4508, + "step": 1675776 + }, + { + "epoch": 0.02, + "learning_rate": 2.2556888499000568e-05, + "loss": 3.4508, + "step": 1676288 + }, + { + "epoch": 0.02, + "learning_rate": 2.2548502551490048e-05, + "loss": 3.4521, + "step": 1676800 + }, + { + "epoch": 0.02, + "learning_rate": 2.2540132982783257e-05, + "loss": 3.45, + "step": 1677312 + }, + { + "epoch": 0.02, + "learning_rate": 2.2531747035272737e-05, + "loss": 3.4636, + "step": 1677824 + }, + { + "epoch": 0.02, + "learning_rate": 2.2523361087762217e-05, + "loss": 3.4359, + "step": 1678336 + }, + { + "epoch": 0.02, + "learning_rate": 2.2514975140251697e-05, + "loss": 3.4651, + "step": 1678848 + }, + { + "epoch": 0.03, + "eval_loss": 3.8520522117614746, + "eval_runtime": 310.4823, + "eval_samples_per_second": 1229.027, + "eval_steps_per_second": 38.408, + "step": 1679040 + }, + { + "epoch": 1.0, + "learning_rate": 2.250660557154491e-05, + "loss": 3.4456, + "step": 1679360 + }, + { + "epoch": 1.0, + "learning_rate": 2.249821962403439e-05, + "loss": 3.4454, + "step": 1679872 + }, + { + "epoch": 1.0, + "learning_rate": 2.248983367652387e-05, + "loss": 3.454, + "step": 1680384 + }, + { + "epoch": 1.0, + "learning_rate": 2.248144772901335e-05, + "loss": 3.4593, + "step": 1680896 + }, + { + "epoch": 1.0, + "learning_rate": 2.247307816030656e-05, + "loss": 3.461, + "step": 1681408 + }, + { + "epoch": 1.0, + "learning_rate": 2.246469221279604e-05, + "loss": 3.4449, + "step": 1681920 + }, + { + "epoch": 1.0, + "learning_rate": 2.2456306265285522e-05, + "loss": 3.4388, + "step": 1682432 + }, + { + "epoch": 1.0, + "learning_rate": 2.2447920317775002e-05, + "loss": 3.4479, + "step": 1682944 + }, + { + "epoch": 1.0, + "learning_rate": 2.243955074906821e-05, + "loss": 3.4528, + "step": 1683456 + }, + { + "epoch": 1.0, + "learning_rate": 2.243116480155769e-05, + "loss": 3.4592, + "step": 1683968 + }, + { + "epoch": 1.0, + "learning_rate": 2.242277885404717e-05, + "loss": 3.4499, + "step": 1684480 + }, + { + "epoch": 1.0, + "learning_rate": 2.241439290653665e-05, + "loss": 3.4545, + "step": 1684992 + }, + { + "epoch": 1.0, + "learning_rate": 2.2406023337829863e-05, + "loss": 3.4419, + "step": 1685504 + }, + { + "epoch": 1.0, + "learning_rate": 2.2397637390319343e-05, + "loss": 3.4405, + "step": 1686016 + }, + { + "epoch": 1.0, + "learning_rate": 2.2389251442808823e-05, + "loss": 3.4505, + "step": 1686528 + }, + { + "epoch": 1.0, + "learning_rate": 2.23808654952983e-05, + "loss": 3.4434, + "step": 1687040 + }, + { + "epoch": 1.0, + "learning_rate": 2.2372495926591512e-05, + "loss": 3.4458, + "step": 1687552 + }, + { + "epoch": 1.0, + "learning_rate": 2.2364109979080992e-05, + "loss": 3.4509, + "step": 1688064 + }, + { + "epoch": 1.0, + "learning_rate": 2.2355724031570476e-05, + "loss": 3.4429, + "step": 1688576 + }, + { + "epoch": 1.0, + "learning_rate": 2.2347338084059952e-05, + "loss": 3.4694, + "step": 1689088 + }, + { + "epoch": 1.0, + "learning_rate": 2.2338968515353165e-05, + "loss": 3.4582, + "step": 1689600 + }, + { + "epoch": 1.0, + "learning_rate": 2.2330598946646374e-05, + "loss": 3.4475, + "step": 1690112 + }, + { + "epoch": 1.0, + "learning_rate": 2.2322212999135854e-05, + "loss": 3.4553, + "step": 1690624 + }, + { + "epoch": 1.0, + "learning_rate": 2.2313827051625337e-05, + "loss": 3.4622, + "step": 1691136 + }, + { + "epoch": 1.0, + "learning_rate": 2.2305441104114817e-05, + "loss": 3.4413, + "step": 1691648 + }, + { + "epoch": 1.0, + "learning_rate": 2.2297055156604297e-05, + "loss": 3.4579, + "step": 1692160 + }, + { + "epoch": 1.0, + "learning_rate": 2.2288669209093773e-05, + "loss": 3.4449, + "step": 1692672 + }, + { + "epoch": 1.0, + "learning_rate": 2.2280283261583253e-05, + "loss": 3.4452, + "step": 1693184 + }, + { + "epoch": 1.0, + "learning_rate": 2.2271897314072733e-05, + "loss": 3.4382, + "step": 1693696 + }, + { + "epoch": 1.0, + "learning_rate": 2.2263527745365946e-05, + "loss": 3.4512, + "step": 1694208 + }, + { + "epoch": 1.01, + "learning_rate": 2.2255141797855426e-05, + "loss": 3.4649, + "step": 1694720 + }, + { + "epoch": 1.01, + "learning_rate": 2.2246755850344906e-05, + "loss": 3.4513, + "step": 1695232 + }, + { + "epoch": 1.01, + "learning_rate": 2.2238386281638118e-05, + "loss": 3.4593, + "step": 1695744 + }, + { + "epoch": 1.01, + "learning_rate": 2.2230000334127595e-05, + "loss": 3.4555, + "step": 1696256 + }, + { + "epoch": 1.01, + "learning_rate": 2.2221614386617075e-05, + "loss": 3.4451, + "step": 1696768 + }, + { + "epoch": 1.01, + "learning_rate": 2.221324481791029e-05, + "loss": 3.4524, + "step": 1697280 + }, + { + "epoch": 1.01, + "learning_rate": 2.220485887039977e-05, + "loss": 3.4461, + "step": 1697792 + }, + { + "epoch": 1.01, + "learning_rate": 2.2196472922889247e-05, + "loss": 3.4454, + "step": 1698304 + }, + { + "epoch": 1.01, + "learning_rate": 2.2188086975378727e-05, + "loss": 3.4418, + "step": 1698816 + }, + { + "epoch": 1.01, + "learning_rate": 2.2179701027868207e-05, + "loss": 3.4446, + "step": 1699328 + }, + { + "epoch": 1.01, + "learning_rate": 2.2171315080357687e-05, + "loss": 3.4475, + "step": 1699840 + }, + { + "epoch": 1.01, + "learning_rate": 2.21629455116509e-05, + "loss": 3.4556, + "step": 1700352 + }, + { + "epoch": 1.01, + "learning_rate": 2.215455956414038e-05, + "loss": 3.4511, + "step": 1700864 + }, + { + "epoch": 1.01, + "learning_rate": 2.214617361662986e-05, + "loss": 3.4488, + "step": 1701376 + }, + { + "epoch": 1.01, + "learning_rate": 2.213778766911934e-05, + "loss": 3.4557, + "step": 1701888 + }, + { + "epoch": 1.01, + "learning_rate": 2.212940172160882e-05, + "loss": 3.4486, + "step": 1702400 + }, + { + "epoch": 1.01, + "learning_rate": 2.21210157740983e-05, + "loss": 3.4558, + "step": 1702912 + }, + { + "epoch": 1.01, + "learning_rate": 2.2112629826587776e-05, + "loss": 3.4439, + "step": 1703424 + }, + { + "epoch": 1.01, + "learning_rate": 2.2104260257880992e-05, + "loss": 3.4306, + "step": 1703936 + }, + { + "epoch": 1.01, + "learning_rate": 2.2095874310370472e-05, + "loss": 3.4581, + "step": 1704448 + }, + { + "epoch": 1.01, + "learning_rate": 2.208748836285995e-05, + "loss": 3.4451, + "step": 1704960 + }, + { + "epoch": 1.01, + "learning_rate": 2.2079102415349428e-05, + "loss": 3.4527, + "step": 1705472 + }, + { + "epoch": 1.01, + "learning_rate": 2.207073284664264e-05, + "loss": 3.4447, + "step": 1705984 + }, + { + "epoch": 1.01, + "learning_rate": 2.206234689913212e-05, + "loss": 3.4405, + "step": 1706496 + }, + { + "epoch": 1.01, + "learning_rate": 2.20539609516216e-05, + "loss": 3.4348, + "step": 1707008 + }, + { + "epoch": 1.01, + "learning_rate": 2.2045591382914813e-05, + "loss": 3.4495, + "step": 1707520 + }, + { + "epoch": 1.01, + "learning_rate": 2.2037205435404293e-05, + "loss": 3.4426, + "step": 1708032 + }, + { + "epoch": 1.01, + "learning_rate": 2.2028819487893773e-05, + "loss": 3.4451, + "step": 1708544 + }, + { + "epoch": 1.01, + "learning_rate": 2.202043354038325e-05, + "loss": 3.4529, + "step": 1709056 + }, + { + "epoch": 1.01, + "learning_rate": 2.201204759287273e-05, + "loss": 3.4345, + "step": 1709568 + }, + { + "epoch": 1.01, + "learning_rate": 2.2003661645362213e-05, + "loss": 3.4383, + "step": 1710080 + }, + { + "epoch": 1.01, + "learning_rate": 2.1995275697851693e-05, + "loss": 3.4569, + "step": 1710592 + }, + { + "epoch": 1.01, + "learning_rate": 2.1986889750341173e-05, + "loss": 3.4281, + "step": 1711104 + }, + { + "epoch": 1.01, + "learning_rate": 2.1978520181634382e-05, + "loss": 3.4343, + "step": 1711616 + }, + { + "epoch": 1.01, + "learning_rate": 2.1970134234123862e-05, + "loss": 3.4491, + "step": 1712128 + }, + { + "epoch": 1.01, + "learning_rate": 2.1961748286613342e-05, + "loss": 3.4475, + "step": 1712640 + }, + { + "epoch": 1.01, + "learning_rate": 2.1953362339102822e-05, + "loss": 3.4375, + "step": 1713152 + }, + { + "epoch": 1.01, + "learning_rate": 2.1944992770396034e-05, + "loss": 3.4454, + "step": 1713664 + }, + { + "epoch": 1.01, + "learning_rate": 2.1936606822885514e-05, + "loss": 3.4306, + "step": 1714176 + }, + { + "epoch": 1.01, + "learning_rate": 2.1928220875374994e-05, + "loss": 3.4336, + "step": 1714688 + }, + { + "epoch": 1.01, + "learning_rate": 2.1919834927864474e-05, + "loss": 3.4503, + "step": 1715200 + }, + { + "epoch": 1.01, + "learning_rate": 2.1911465359157683e-05, + "loss": 3.4446, + "step": 1715712 + }, + { + "epoch": 1.01, + "learning_rate": 2.1903079411647167e-05, + "loss": 3.4508, + "step": 1716224 + }, + { + "epoch": 1.01, + "learning_rate": 2.1894693464136647e-05, + "loss": 3.4496, + "step": 1716736 + }, + { + "epoch": 1.01, + "learning_rate": 2.1886307516626126e-05, + "loss": 3.4564, + "step": 1717248 + }, + { + "epoch": 1.01, + "learning_rate": 2.1877937947919336e-05, + "loss": 3.4375, + "step": 1717760 + }, + { + "epoch": 1.01, + "learning_rate": 2.1869552000408816e-05, + "loss": 3.4461, + "step": 1718272 + }, + { + "epoch": 1.01, + "learning_rate": 2.1861166052898295e-05, + "loss": 3.4496, + "step": 1718784 + }, + { + "epoch": 1.01, + "learning_rate": 2.1852780105387775e-05, + "loss": 3.4299, + "step": 1719296 + }, + { + "epoch": 1.01, + "learning_rate": 2.1844410536680988e-05, + "loss": 3.4506, + "step": 1719808 + }, + { + "epoch": 1.01, + "learning_rate": 2.1836024589170468e-05, + "loss": 3.4485, + "step": 1720320 + }, + { + "epoch": 1.01, + "learning_rate": 2.1827638641659948e-05, + "loss": 3.4484, + "step": 1720832 + }, + { + "epoch": 1.01, + "learning_rate": 2.1819269072953157e-05, + "loss": 3.4468, + "step": 1721344 + }, + { + "epoch": 1.01, + "learning_rate": 2.1810883125442637e-05, + "loss": 3.4386, + "step": 1721856 + }, + { + "epoch": 1.01, + "learning_rate": 2.180249717793212e-05, + "loss": 3.4384, + "step": 1722368 + }, + { + "epoch": 1.01, + "learning_rate": 2.17941112304216e-05, + "loss": 3.4458, + "step": 1722880 + }, + { + "epoch": 1.01, + "learning_rate": 2.178572528291108e-05, + "loss": 3.4484, + "step": 1723392 + }, + { + "epoch": 1.01, + "learning_rate": 2.1777339335400557e-05, + "loss": 3.4468, + "step": 1723904 + }, + { + "epoch": 1.01, + "learning_rate": 2.1768953387890037e-05, + "loss": 3.4535, + "step": 1724416 + }, + { + "epoch": 1.02, + "learning_rate": 2.1760567440379517e-05, + "loss": 3.4519, + "step": 1724928 + }, + { + "epoch": 1.02, + "learning_rate": 2.175219787167273e-05, + "loss": 3.441, + "step": 1725440 + }, + { + "epoch": 1.02, + "learning_rate": 2.174381192416221e-05, + "loss": 3.446, + "step": 1725952 + }, + { + "epoch": 1.02, + "learning_rate": 2.173542597665169e-05, + "loss": 3.4365, + "step": 1726464 + }, + { + "epoch": 1.02, + "learning_rate": 2.172704002914117e-05, + "loss": 3.4539, + "step": 1726976 + }, + { + "epoch": 1.02, + "learning_rate": 2.1718670460434378e-05, + "loss": 3.457, + "step": 1727488 + }, + { + "epoch": 1.02, + "learning_rate": 2.1710284512923858e-05, + "loss": 3.439, + "step": 1728000 + }, + { + "epoch": 1.02, + "learning_rate": 2.1701898565413338e-05, + "loss": 3.4393, + "step": 1728512 + }, + { + "epoch": 1.02, + "learning_rate": 2.169351261790282e-05, + "loss": 3.437, + "step": 1729024 + }, + { + "epoch": 1.02, + "learning_rate": 2.168514304919603e-05, + "loss": 3.4495, + "step": 1729536 + }, + { + "epoch": 1.02, + "learning_rate": 2.167675710168551e-05, + "loss": 3.4547, + "step": 1730048 + }, + { + "epoch": 1.02, + "learning_rate": 2.166837115417499e-05, + "loss": 3.4439, + "step": 1730560 + }, + { + "epoch": 1.02, + "learning_rate": 2.16600015854682e-05, + "loss": 3.4443, + "step": 1731072 + }, + { + "epoch": 1.02, + "learning_rate": 2.1651615637957683e-05, + "loss": 3.4372, + "step": 1731584 + }, + { + "epoch": 1.02, + "learning_rate": 2.1643229690447163e-05, + "loss": 3.4478, + "step": 1732096 + }, + { + "epoch": 1.02, + "learning_rate": 2.1634843742936643e-05, + "loss": 3.4327, + "step": 1732608 + }, + { + "epoch": 1.02, + "learning_rate": 2.1626474174229852e-05, + "loss": 3.4428, + "step": 1733120 + }, + { + "epoch": 1.02, + "learning_rate": 2.1618088226719332e-05, + "loss": 3.4361, + "step": 1733632 + }, + { + "epoch": 1.02, + "learning_rate": 2.1609702279208812e-05, + "loss": 3.4524, + "step": 1734144 + }, + { + "epoch": 1.02, + "learning_rate": 2.160131633169829e-05, + "loss": 3.4396, + "step": 1734656 + }, + { + "epoch": 1.02, + "learning_rate": 2.1592946762991504e-05, + "loss": 3.4455, + "step": 1735168 + }, + { + "epoch": 1.02, + "learning_rate": 2.1584560815480984e-05, + "loss": 3.4458, + "step": 1735680 + }, + { + "epoch": 1.02, + "learning_rate": 2.1576174867970464e-05, + "loss": 3.4379, + "step": 1736192 + }, + { + "epoch": 1.02, + "learning_rate": 2.1567788920459944e-05, + "loss": 3.4479, + "step": 1736704 + }, + { + "epoch": 1.02, + "learning_rate": 2.1559419351753153e-05, + "loss": 3.4429, + "step": 1737216 + }, + { + "epoch": 1.02, + "learning_rate": 2.1551033404242636e-05, + "loss": 3.4486, + "step": 1737728 + }, + { + "epoch": 1.02, + "learning_rate": 2.1542647456732116e-05, + "loss": 3.4519, + "step": 1738240 + }, + { + "epoch": 1.02, + "learning_rate": 2.1534261509221596e-05, + "loss": 3.4372, + "step": 1738752 + }, + { + "epoch": 1.02, + "learning_rate": 2.1525891940514805e-05, + "loss": 3.443, + "step": 1739264 + }, + { + "epoch": 1.02, + "learning_rate": 2.1517505993004285e-05, + "loss": 3.4389, + "step": 1739776 + }, + { + "epoch": 1.02, + "learning_rate": 2.1509120045493765e-05, + "loss": 3.4447, + "step": 1740288 + }, + { + "epoch": 1.02, + "learning_rate": 2.1500734097983245e-05, + "loss": 3.4393, + "step": 1740800 + }, + { + "epoch": 1.02, + "learning_rate": 2.1492364529276458e-05, + "loss": 3.4407, + "step": 1741312 + }, + { + "epoch": 1.02, + "learning_rate": 2.1483978581765938e-05, + "loss": 3.4302, + "step": 1741824 + }, + { + "epoch": 1.02, + "learning_rate": 2.1475592634255418e-05, + "loss": 3.4483, + "step": 1742336 + }, + { + "epoch": 1.02, + "learning_rate": 2.1467206686744898e-05, + "loss": 3.4398, + "step": 1742848 + }, + { + "epoch": 1.02, + "learning_rate": 2.1458837118038107e-05, + "loss": 3.4459, + "step": 1743360 + }, + { + "epoch": 1.02, + "learning_rate": 2.145045117052759e-05, + "loss": 3.4324, + "step": 1743872 + }, + { + "epoch": 1.02, + "learning_rate": 2.144206522301707e-05, + "loss": 3.4415, + "step": 1744384 + }, + { + "epoch": 1.02, + "learning_rate": 2.143367927550655e-05, + "loss": 3.4453, + "step": 1744896 + }, + { + "epoch": 1.02, + "learning_rate": 2.142529332799603e-05, + "loss": 3.4506, + "step": 1745408 + }, + { + "epoch": 1.02, + "learning_rate": 2.1416907380485507e-05, + "loss": 3.4413, + "step": 1745920 + }, + { + "epoch": 1.02, + "learning_rate": 2.1408521432974987e-05, + "loss": 3.4489, + "step": 1746432 + }, + { + "epoch": 1.02, + "learning_rate": 2.1400135485464466e-05, + "loss": 3.433, + "step": 1746944 + }, + { + "epoch": 1.02, + "learning_rate": 2.139176591675768e-05, + "loss": 3.4465, + "step": 1747456 + }, + { + "epoch": 1.02, + "learning_rate": 2.138337996924716e-05, + "loss": 3.4488, + "step": 1747968 + }, + { + "epoch": 1.02, + "learning_rate": 2.137499402173664e-05, + "loss": 3.4508, + "step": 1748480 + }, + { + "epoch": 1.02, + "learning_rate": 2.136660807422612e-05, + "loss": 3.4465, + "step": 1748992 + }, + { + "epoch": 1.02, + "learning_rate": 2.1358238505519328e-05, + "loss": 3.4551, + "step": 1749504 + }, + { + "epoch": 1.02, + "learning_rate": 2.1349852558008808e-05, + "loss": 3.4416, + "step": 1750016 + }, + { + "epoch": 1.02, + "learning_rate": 2.134146661049829e-05, + "loss": 3.4536, + "step": 1750528 + }, + { + "epoch": 1.02, + "learning_rate": 2.133308066298777e-05, + "loss": 3.436, + "step": 1751040 + }, + { + "epoch": 1.02, + "learning_rate": 2.132471109428098e-05, + "loss": 3.4468, + "step": 1751552 + }, + { + "epoch": 1.02, + "learning_rate": 2.131632514677046e-05, + "loss": 3.4389, + "step": 1752064 + }, + { + "epoch": 1.02, + "learning_rate": 2.130793919925994e-05, + "loss": 3.4446, + "step": 1752576 + }, + { + "epoch": 1.02, + "learning_rate": 2.129955325174942e-05, + "loss": 3.4395, + "step": 1753088 + }, + { + "epoch": 1.02, + "learning_rate": 2.1291183683042633e-05, + "loss": 3.4374, + "step": 1753600 + }, + { + "epoch": 1.02, + "learning_rate": 2.1282797735532113e-05, + "loss": 3.45, + "step": 1754112 + }, + { + "epoch": 1.02, + "learning_rate": 2.1274411788021593e-05, + "loss": 3.4285, + "step": 1754624 + }, + { + "epoch": 1.02, + "learning_rate": 2.1266025840511072e-05, + "loss": 3.4555, + "step": 1755136 + }, + { + "epoch": 1.03, + "eval_loss": 3.852264881134033, + "eval_runtime": 305.9706, + "eval_samples_per_second": 1247.149, + "eval_steps_per_second": 38.974, + "step": 1755360 + }, + { + "epoch": 0.0, + "learning_rate": 2.125765627180428e-05, + "loss": 3.4341, + "step": 1755648 + }, + { + "epoch": 0.0, + "learning_rate": 2.124927032429376e-05, + "loss": 3.4321, + "step": 1756160 + }, + { + "epoch": 0.0, + "learning_rate": 2.1240884376783245e-05, + "loss": 3.4402, + "step": 1756672 + }, + { + "epoch": 0.0, + "learning_rate": 2.1232498429272725e-05, + "loss": 3.4468, + "step": 1757184 + }, + { + "epoch": 0.0, + "learning_rate": 2.1224128860565934e-05, + "loss": 3.448, + "step": 1757696 + }, + { + "epoch": 0.0, + "learning_rate": 2.1215742913055414e-05, + "loss": 3.4361, + "step": 1758208 + }, + { + "epoch": 0.0, + "learning_rate": 2.1207356965544894e-05, + "loss": 3.4351, + "step": 1758720 + }, + { + "epoch": 0.0, + "learning_rate": 2.1198971018034374e-05, + "loss": 3.4352, + "step": 1759232 + }, + { + "epoch": 0.0, + "learning_rate": 2.1190601449327586e-05, + "loss": 3.4438, + "step": 1759744 + }, + { + "epoch": 0.0, + "learning_rate": 2.1182215501817066e-05, + "loss": 3.4469, + "step": 1760256 + }, + { + "epoch": 0.0, + "learning_rate": 2.1173829554306546e-05, + "loss": 3.4404, + "step": 1760768 + }, + { + "epoch": 0.0, + "learning_rate": 2.1165443606796026e-05, + "loss": 3.4392, + "step": 1761280 + }, + { + "epoch": 0.0, + "learning_rate": 2.1157074038089235e-05, + "loss": 3.4364, + "step": 1761792 + }, + { + "epoch": 0.0, + "learning_rate": 2.1148688090578715e-05, + "loss": 3.429, + "step": 1762304 + }, + { + "epoch": 0.0, + "learning_rate": 2.11403021430682e-05, + "loss": 3.4362, + "step": 1762816 + }, + { + "epoch": 0.0, + "learning_rate": 2.113191619555768e-05, + "loss": 3.4298, + "step": 1763328 + }, + { + "epoch": 0.0, + "learning_rate": 2.1123546626850888e-05, + "loss": 3.4375, + "step": 1763840 + }, + { + "epoch": 0.0, + "learning_rate": 2.1115160679340368e-05, + "loss": 3.4389, + "step": 1764352 + }, + { + "epoch": 0.0, + "learning_rate": 2.1106774731829848e-05, + "loss": 3.4303, + "step": 1764864 + }, + { + "epoch": 0.0, + "learning_rate": 2.1098388784319327e-05, + "loss": 3.4533, + "step": 1765376 + }, + { + "epoch": 0.0, + "learning_rate": 2.109001921561254e-05, + "loss": 3.4511, + "step": 1765888 + }, + { + "epoch": 0.0, + "learning_rate": 2.108164964690575e-05, + "loss": 3.4354, + "step": 1766400 + }, + { + "epoch": 0.0, + "learning_rate": 2.107326369939523e-05, + "loss": 3.4435, + "step": 1766912 + }, + { + "epoch": 0.0, + "learning_rate": 2.106487775188471e-05, + "loss": 3.4485, + "step": 1767424 + }, + { + "epoch": 0.0, + "learning_rate": 2.105649180437419e-05, + "loss": 3.4323, + "step": 1767936 + }, + { + "epoch": 0.0, + "learning_rate": 2.104810585686367e-05, + "loss": 3.4466, + "step": 1768448 + }, + { + "epoch": 0.0, + "learning_rate": 2.1039719909353152e-05, + "loss": 3.4388, + "step": 1768960 + }, + { + "epoch": 0.0, + "learning_rate": 2.1031333961842632e-05, + "loss": 3.4337, + "step": 1769472 + }, + { + "epoch": 0.0, + "learning_rate": 2.102294801433211e-05, + "loss": 3.4264, + "step": 1769984 + }, + { + "epoch": 0.0, + "learning_rate": 2.101457844562532e-05, + "loss": 3.4434, + "step": 1770496 + }, + { + "epoch": 0.01, + "learning_rate": 2.10061924981148e-05, + "loss": 3.4497, + "step": 1771008 + }, + { + "epoch": 0.01, + "learning_rate": 2.0997806550604278e-05, + "loss": 3.4453, + "step": 1771520 + }, + { + "epoch": 0.01, + "learning_rate": 2.098942060309376e-05, + "loss": 3.4493, + "step": 1772032 + }, + { + "epoch": 0.01, + "learning_rate": 2.0981051034386974e-05, + "loss": 3.4394, + "step": 1772544 + }, + { + "epoch": 0.01, + "learning_rate": 2.0972665086876454e-05, + "loss": 3.4335, + "step": 1773056 + }, + { + "epoch": 0.01, + "learning_rate": 2.096427913936593e-05, + "loss": 3.4433, + "step": 1773568 + }, + { + "epoch": 0.01, + "learning_rate": 2.095589319185541e-05, + "loss": 3.4385, + "step": 1774080 + }, + { + "epoch": 0.01, + "learning_rate": 2.0947523623148623e-05, + "loss": 3.4286, + "step": 1774592 + }, + { + "epoch": 0.01, + "learning_rate": 2.0939137675638102e-05, + "loss": 3.4298, + "step": 1775104 + }, + { + "epoch": 0.01, + "learning_rate": 2.0930751728127582e-05, + "loss": 3.4354, + "step": 1775616 + }, + { + "epoch": 0.01, + "learning_rate": 2.0922382159420795e-05, + "loss": 3.4361, + "step": 1776128 + }, + { + "epoch": 0.01, + "learning_rate": 2.0914012590714004e-05, + "loss": 3.4446, + "step": 1776640 + }, + { + "epoch": 0.01, + "learning_rate": 2.0905626643203484e-05, + "loss": 3.4416, + "step": 1777152 + }, + { + "epoch": 0.01, + "learning_rate": 2.0897240695692964e-05, + "loss": 3.4366, + "step": 1777664 + }, + { + "epoch": 0.01, + "learning_rate": 2.0888854748182447e-05, + "loss": 3.4442, + "step": 1778176 + }, + { + "epoch": 0.01, + "learning_rate": 2.0880468800671927e-05, + "loss": 3.4418, + "step": 1778688 + }, + { + "epoch": 0.01, + "learning_rate": 2.0872082853161404e-05, + "loss": 3.4418, + "step": 1779200 + }, + { + "epoch": 0.01, + "learning_rate": 2.0863696905650884e-05, + "loss": 3.437, + "step": 1779712 + }, + { + "epoch": 0.01, + "learning_rate": 2.0855310958140364e-05, + "loss": 3.415, + "step": 1780224 + }, + { + "epoch": 0.01, + "learning_rate": 2.0846941389433576e-05, + "loss": 3.449, + "step": 1780736 + }, + { + "epoch": 0.01, + "learning_rate": 2.0838555441923056e-05, + "loss": 3.4316, + "step": 1781248 + }, + { + "epoch": 0.01, + "learning_rate": 2.0830169494412536e-05, + "loss": 3.4458, + "step": 1781760 + }, + { + "epoch": 0.01, + "learning_rate": 2.082179992570575e-05, + "loss": 3.4314, + "step": 1782272 + }, + { + "epoch": 0.01, + "learning_rate": 2.0813413978195225e-05, + "loss": 3.4317, + "step": 1782784 + }, + { + "epoch": 0.01, + "learning_rate": 2.0805028030684705e-05, + "loss": 3.4229, + "step": 1783296 + }, + { + "epoch": 0.01, + "learning_rate": 2.0796658461977918e-05, + "loss": 3.4388, + "step": 1783808 + }, + { + "epoch": 0.01, + "learning_rate": 2.07882725144674e-05, + "loss": 3.4304, + "step": 1784320 + }, + { + "epoch": 0.01, + "learning_rate": 2.0779886566956878e-05, + "loss": 3.4327, + "step": 1784832 + }, + { + "epoch": 0.01, + "learning_rate": 2.0771500619446357e-05, + "loss": 3.4454, + "step": 1785344 + }, + { + "epoch": 0.01, + "learning_rate": 2.0763114671935837e-05, + "loss": 3.426, + "step": 1785856 + }, + { + "epoch": 0.01, + "learning_rate": 2.0754728724425317e-05, + "loss": 3.4265, + "step": 1786368 + }, + { + "epoch": 0.01, + "learning_rate": 2.0746342776914797e-05, + "loss": 3.4434, + "step": 1786880 + }, + { + "epoch": 0.01, + "learning_rate": 2.0737956829404277e-05, + "loss": 3.421, + "step": 1787392 + }, + { + "epoch": 0.01, + "learning_rate": 2.072958726069749e-05, + "loss": 3.4208, + "step": 1787904 + }, + { + "epoch": 0.01, + "learning_rate": 2.072120131318697e-05, + "loss": 3.4386, + "step": 1788416 + }, + { + "epoch": 0.01, + "learning_rate": 2.071281536567645e-05, + "loss": 3.4364, + "step": 1788928 + }, + { + "epoch": 0.01, + "learning_rate": 2.070442941816593e-05, + "loss": 3.4293, + "step": 1789440 + }, + { + "epoch": 0.01, + "learning_rate": 2.069605984945914e-05, + "loss": 3.433, + "step": 1789952 + }, + { + "epoch": 0.01, + "learning_rate": 2.0687673901948622e-05, + "loss": 3.4176, + "step": 1790464 + }, + { + "epoch": 0.01, + "learning_rate": 2.0679287954438102e-05, + "loss": 3.426, + "step": 1790976 + }, + { + "epoch": 0.01, + "learning_rate": 2.0670902006927582e-05, + "loss": 3.4407, + "step": 1791488 + }, + { + "epoch": 0.01, + "learning_rate": 2.066253243822079e-05, + "loss": 3.4345, + "step": 1792000 + }, + { + "epoch": 0.01, + "learning_rate": 2.065414649071027e-05, + "loss": 3.4457, + "step": 1792512 + }, + { + "epoch": 0.01, + "learning_rate": 2.064576054319975e-05, + "loss": 3.4368, + "step": 1793024 + }, + { + "epoch": 0.01, + "learning_rate": 2.063737459568923e-05, + "loss": 3.4432, + "step": 1793536 + }, + { + "epoch": 0.01, + "learning_rate": 2.0629005026982443e-05, + "loss": 3.425, + "step": 1794048 + }, + { + "epoch": 0.01, + "learning_rate": 2.0620619079471923e-05, + "loss": 3.4388, + "step": 1794560 + }, + { + "epoch": 0.01, + "learning_rate": 2.0612233131961403e-05, + "loss": 3.436, + "step": 1795072 + }, + { + "epoch": 0.01, + "learning_rate": 2.060384718445088e-05, + "loss": 3.4208, + "step": 1795584 + }, + { + "epoch": 0.01, + "learning_rate": 2.0595477615744092e-05, + "loss": 3.4385, + "step": 1796096 + }, + { + "epoch": 0.01, + "learning_rate": 2.0587091668233572e-05, + "loss": 3.4375, + "step": 1796608 + }, + { + "epoch": 0.01, + "learning_rate": 2.0578705720723056e-05, + "loss": 3.4373, + "step": 1797120 + }, + { + "epoch": 0.01, + "learning_rate": 2.0570336152016265e-05, + "loss": 3.4424, + "step": 1797632 + }, + { + "epoch": 0.01, + "learning_rate": 2.0561950204505745e-05, + "loss": 3.4245, + "step": 1798144 + }, + { + "epoch": 0.01, + "learning_rate": 2.0553564256995225e-05, + "loss": 3.4262, + "step": 1798656 + }, + { + "epoch": 0.01, + "learning_rate": 2.05451783094847e-05, + "loss": 3.4362, + "step": 1799168 + }, + { + "epoch": 0.01, + "learning_rate": 2.0536792361974185e-05, + "loss": 3.4371, + "step": 1799680 + }, + { + "epoch": 0.01, + "learning_rate": 2.0528406414463665e-05, + "loss": 3.4386, + "step": 1800192 + }, + { + "epoch": 0.01, + "learning_rate": 2.0520020466953145e-05, + "loss": 3.4392, + "step": 1800704 + }, + { + "epoch": 0.02, + "learning_rate": 2.0511634519442624e-05, + "loss": 3.4402, + "step": 1801216 + }, + { + "epoch": 0.02, + "learning_rate": 2.0503264950735834e-05, + "loss": 3.4353, + "step": 1801728 + }, + { + "epoch": 0.02, + "learning_rate": 2.0494879003225314e-05, + "loss": 3.4303, + "step": 1802240 + }, + { + "epoch": 0.02, + "learning_rate": 2.0486493055714793e-05, + "loss": 3.4255, + "step": 1802752 + }, + { + "epoch": 0.02, + "learning_rate": 2.0478107108204277e-05, + "loss": 3.4411, + "step": 1803264 + }, + { + "epoch": 0.02, + "learning_rate": 2.0469737539497486e-05, + "loss": 3.4432, + "step": 1803776 + }, + { + "epoch": 0.02, + "learning_rate": 2.0461351591986966e-05, + "loss": 3.4314, + "step": 1804288 + }, + { + "epoch": 0.02, + "learning_rate": 2.0452965644476446e-05, + "loss": 3.4278, + "step": 1804800 + }, + { + "epoch": 0.02, + "learning_rate": 2.0444596075769655e-05, + "loss": 3.4285, + "step": 1805312 + }, + { + "epoch": 0.02, + "learning_rate": 2.0436210128259138e-05, + "loss": 3.4345, + "step": 1805824 + }, + { + "epoch": 0.02, + "learning_rate": 2.0427824180748618e-05, + "loss": 3.4467, + "step": 1806336 + }, + { + "epoch": 0.02, + "learning_rate": 2.0419438233238098e-05, + "loss": 3.4292, + "step": 1806848 + }, + { + "epoch": 0.02, + "learning_rate": 2.0411052285727578e-05, + "loss": 3.4331, + "step": 1807360 + }, + { + "epoch": 0.02, + "learning_rate": 2.0402666338217058e-05, + "loss": 3.4286, + "step": 1807872 + }, + { + "epoch": 0.02, + "learning_rate": 2.0394280390706535e-05, + "loss": 3.4349, + "step": 1808384 + }, + { + "epoch": 0.02, + "learning_rate": 2.0385894443196015e-05, + "loss": 3.4243, + "step": 1808896 + }, + { + "epoch": 0.02, + "learning_rate": 2.037752487448923e-05, + "loss": 3.4356, + "step": 1809408 + }, + { + "epoch": 0.02, + "learning_rate": 2.036913892697871e-05, + "loss": 3.4233, + "step": 1809920 + }, + { + "epoch": 0.02, + "learning_rate": 2.0360752979468187e-05, + "loss": 3.44, + "step": 1810432 + }, + { + "epoch": 0.02, + "learning_rate": 2.0352367031957667e-05, + "loss": 3.4311, + "step": 1810944 + }, + { + "epoch": 0.02, + "learning_rate": 2.034399746325088e-05, + "loss": 3.4309, + "step": 1811456 + }, + { + "epoch": 0.02, + "learning_rate": 2.0335611515740356e-05, + "loss": 3.4333, + "step": 1811968 + }, + { + "epoch": 0.02, + "learning_rate": 2.032722556822984e-05, + "loss": 3.4351, + "step": 1812480 + }, + { + "epoch": 0.02, + "learning_rate": 2.031883962071932e-05, + "loss": 3.4325, + "step": 1812992 + }, + { + "epoch": 0.02, + "learning_rate": 2.0310470052012532e-05, + "loss": 3.4324, + "step": 1813504 + }, + { + "epoch": 0.02, + "learning_rate": 2.030208410450201e-05, + "loss": 3.4369, + "step": 1814016 + }, + { + "epoch": 0.02, + "learning_rate": 2.029371453579522e-05, + "loss": 3.444, + "step": 1814528 + }, + { + "epoch": 0.02, + "learning_rate": 2.02853285882847e-05, + "loss": 3.4267, + "step": 1815040 + }, + { + "epoch": 0.02, + "learning_rate": 2.0276942640774184e-05, + "loss": 3.4336, + "step": 1815552 + }, + { + "epoch": 0.02, + "learning_rate": 2.026855669326366e-05, + "loss": 3.4291, + "step": 1816064 + }, + { + "epoch": 0.02, + "learning_rate": 2.026017074575314e-05, + "loss": 3.4292, + "step": 1816576 + }, + { + "epoch": 0.02, + "learning_rate": 2.025178479824262e-05, + "loss": 3.4259, + "step": 1817088 + }, + { + "epoch": 0.02, + "learning_rate": 2.02433988507321e-05, + "loss": 3.4293, + "step": 1817600 + }, + { + "epoch": 0.02, + "learning_rate": 2.023502928202531e-05, + "loss": 3.4232, + "step": 1818112 + }, + { + "epoch": 0.02, + "learning_rate": 2.0226643334514793e-05, + "loss": 3.4337, + "step": 1818624 + }, + { + "epoch": 0.02, + "learning_rate": 2.0218257387004273e-05, + "loss": 3.4307, + "step": 1819136 + }, + { + "epoch": 0.02, + "learning_rate": 2.0209887818297482e-05, + "loss": 3.4362, + "step": 1819648 + }, + { + "epoch": 0.02, + "learning_rate": 2.0201501870786962e-05, + "loss": 3.4197, + "step": 1820160 + }, + { + "epoch": 0.02, + "learning_rate": 2.0193115923276442e-05, + "loss": 3.432, + "step": 1820672 + }, + { + "epoch": 0.02, + "learning_rate": 2.0184729975765922e-05, + "loss": 3.4325, + "step": 1821184 + }, + { + "epoch": 0.02, + "learning_rate": 2.0176344028255402e-05, + "loss": 3.4403, + "step": 1821696 + }, + { + "epoch": 0.02, + "learning_rate": 2.0167958080744885e-05, + "loss": 3.432, + "step": 1822208 + }, + { + "epoch": 0.02, + "learning_rate": 2.0159572133234365e-05, + "loss": 3.4383, + "step": 1822720 + }, + { + "epoch": 0.02, + "learning_rate": 2.0151186185723842e-05, + "loss": 3.4224, + "step": 1823232 + }, + { + "epoch": 0.02, + "learning_rate": 2.0142816617017054e-05, + "loss": 3.4384, + "step": 1823744 + }, + { + "epoch": 0.02, + "learning_rate": 2.0134430669506534e-05, + "loss": 3.4362, + "step": 1824256 + }, + { + "epoch": 0.02, + "learning_rate": 2.012604472199601e-05, + "loss": 3.4389, + "step": 1824768 + }, + { + "epoch": 0.02, + "learning_rate": 2.0117658774485494e-05, + "loss": 3.4395, + "step": 1825280 + }, + { + "epoch": 0.02, + "learning_rate": 2.0109289205778707e-05, + "loss": 3.4417, + "step": 1825792 + }, + { + "epoch": 0.02, + "learning_rate": 2.0100903258268187e-05, + "loss": 3.4328, + "step": 1826304 + }, + { + "epoch": 0.02, + "learning_rate": 2.0092517310757663e-05, + "loss": 3.4431, + "step": 1826816 + }, + { + "epoch": 0.02, + "learning_rate": 2.0084131363247143e-05, + "loss": 3.4254, + "step": 1827328 + }, + { + "epoch": 0.02, + "learning_rate": 2.0075761794540356e-05, + "loss": 3.4358, + "step": 1827840 + }, + { + "epoch": 0.02, + "learning_rate": 2.006737584702984e-05, + "loss": 3.4282, + "step": 1828352 + }, + { + "epoch": 0.02, + "learning_rate": 2.0058989899519316e-05, + "loss": 3.4364, + "step": 1828864 + }, + { + "epoch": 0.02, + "learning_rate": 2.0050603952008795e-05, + "loss": 3.4242, + "step": 1829376 + }, + { + "epoch": 0.02, + "learning_rate": 2.0042234383302008e-05, + "loss": 3.4268, + "step": 1829888 + }, + { + "epoch": 0.02, + "learning_rate": 2.0033848435791485e-05, + "loss": 3.4353, + "step": 1830400 + }, + { + "epoch": 0.02, + "learning_rate": 2.0025462488280964e-05, + "loss": 3.4201, + "step": 1830912 + }, + { + "epoch": 0.02, + "learning_rate": 2.0017076540770448e-05, + "loss": 3.446, + "step": 1831424 + }, + { + "epoch": 0.03, + "eval_loss": 3.853567123413086, + "eval_runtime": 302.8935, + "eval_samples_per_second": 1259.819, + "eval_steps_per_second": 39.37, + "step": 1831680 + }, + { + "epoch": 1.0, + "learning_rate": 2.000870697206366e-05, + "loss": 3.4229, + "step": 1831936 + }, + { + "epoch": 1.0, + "learning_rate": 2.0000321024553137e-05, + "loss": 3.4267, + "step": 1832448 + }, + { + "epoch": 1.0, + "learning_rate": 1.9991935077042617e-05, + "loss": 3.4256, + "step": 1832960 + }, + { + "epoch": 1.0, + "learning_rate": 1.9983549129532097e-05, + "loss": 3.4371, + "step": 1833472 + }, + { + "epoch": 1.0, + "learning_rate": 1.997517956082531e-05, + "loss": 3.439, + "step": 1833984 + }, + { + "epoch": 1.0, + "learning_rate": 1.996679361331479e-05, + "loss": 3.4237, + "step": 1834496 + }, + { + "epoch": 1.0, + "learning_rate": 1.995840766580427e-05, + "loss": 3.4281, + "step": 1835008 + }, + { + "epoch": 1.0, + "learning_rate": 1.995002171829375e-05, + "loss": 3.4237, + "step": 1835520 + }, + { + "epoch": 1.0, + "learning_rate": 1.9941652149586958e-05, + "loss": 3.4284, + "step": 1836032 + }, + { + "epoch": 1.0, + "learning_rate": 1.9933266202076438e-05, + "loss": 3.4384, + "step": 1836544 + }, + { + "epoch": 1.0, + "learning_rate": 1.9924880254565918e-05, + "loss": 3.4263, + "step": 1837056 + }, + { + "epoch": 1.0, + "learning_rate": 1.99164943070554e-05, + "loss": 3.429, + "step": 1837568 + }, + { + "epoch": 1.0, + "learning_rate": 1.990812473834861e-05, + "loss": 3.4261, + "step": 1838080 + }, + { + "epoch": 1.0, + "learning_rate": 1.989973879083809e-05, + "loss": 3.416, + "step": 1838592 + }, + { + "epoch": 1.0, + "learning_rate": 1.989135284332757e-05, + "loss": 3.4292, + "step": 1839104 + }, + { + "epoch": 1.0, + "learning_rate": 1.988296689581705e-05, + "loss": 3.421, + "step": 1839616 + }, + { + "epoch": 1.0, + "learning_rate": 1.9874597327110263e-05, + "loss": 3.426, + "step": 1840128 + }, + { + "epoch": 1.0, + "learning_rate": 1.9866211379599743e-05, + "loss": 3.4314, + "step": 1840640 + }, + { + "epoch": 1.0, + "learning_rate": 1.9857825432089223e-05, + "loss": 3.418, + "step": 1841152 + }, + { + "epoch": 1.0, + "learning_rate": 1.9849455863382432e-05, + "loss": 3.442, + "step": 1841664 + }, + { + "epoch": 1.0, + "learning_rate": 1.9841069915871912e-05, + "loss": 3.4401, + "step": 1842176 + }, + { + "epoch": 1.0, + "learning_rate": 1.9832683968361392e-05, + "loss": 3.4263, + "step": 1842688 + }, + { + "epoch": 1.0, + "learning_rate": 1.9824298020850872e-05, + "loss": 3.4275, + "step": 1843200 + }, + { + "epoch": 1.0, + "learning_rate": 1.9815928452144084e-05, + "loss": 3.4374, + "step": 1843712 + }, + { + "epoch": 1.0, + "learning_rate": 1.9807542504633564e-05, + "loss": 3.4279, + "step": 1844224 + }, + { + "epoch": 1.0, + "learning_rate": 1.9799156557123044e-05, + "loss": 3.4309, + "step": 1844736 + }, + { + "epoch": 1.0, + "learning_rate": 1.9790770609612524e-05, + "loss": 3.4261, + "step": 1845248 + }, + { + "epoch": 1.0, + "learning_rate": 1.9782401040905733e-05, + "loss": 3.4269, + "step": 1845760 + }, + { + "epoch": 1.0, + "learning_rate": 1.9774015093395217e-05, + "loss": 3.4201, + "step": 1846272 + }, + { + "epoch": 1.0, + "learning_rate": 1.9765629145884697e-05, + "loss": 3.4275, + "step": 1846784 + }, + { + "epoch": 1.01, + "learning_rate": 1.9757243198374177e-05, + "loss": 3.4345, + "step": 1847296 + }, + { + "epoch": 1.01, + "learning_rate": 1.9748873629667386e-05, + "loss": 3.4378, + "step": 1847808 + }, + { + "epoch": 1.01, + "learning_rate": 1.9740487682156866e-05, + "loss": 3.4384, + "step": 1848320 + }, + { + "epoch": 1.01, + "learning_rate": 1.9732101734646346e-05, + "loss": 3.4293, + "step": 1848832 + }, + { + "epoch": 1.01, + "learning_rate": 1.9723715787135825e-05, + "loss": 3.4211, + "step": 1849344 + }, + { + "epoch": 1.01, + "learning_rate": 1.9715346218429038e-05, + "loss": 3.4318, + "step": 1849856 + }, + { + "epoch": 1.01, + "learning_rate": 1.9706960270918518e-05, + "loss": 3.4287, + "step": 1850368 + }, + { + "epoch": 1.01, + "learning_rate": 1.9698574323407998e-05, + "loss": 3.4204, + "step": 1850880 + }, + { + "epoch": 1.01, + "learning_rate": 1.9690188375897478e-05, + "loss": 3.4211, + "step": 1851392 + }, + { + "epoch": 1.01, + "learning_rate": 1.9681818807190687e-05, + "loss": 3.4199, + "step": 1851904 + }, + { + "epoch": 1.01, + "learning_rate": 1.967343285968017e-05, + "loss": 3.4238, + "step": 1852416 + }, + { + "epoch": 1.01, + "learning_rate": 1.966506329097338e-05, + "loss": 3.4326, + "step": 1852928 + }, + { + "epoch": 1.01, + "learning_rate": 1.965667734346286e-05, + "loss": 3.4342, + "step": 1853440 + }, + { + "epoch": 1.01, + "learning_rate": 1.964829139595234e-05, + "loss": 3.4294, + "step": 1853952 + }, + { + "epoch": 1.01, + "learning_rate": 1.963990544844182e-05, + "loss": 3.4288, + "step": 1854464 + }, + { + "epoch": 1.01, + "learning_rate": 1.96315195009313e-05, + "loss": 3.432, + "step": 1854976 + }, + { + "epoch": 1.01, + "learning_rate": 1.962313355342078e-05, + "loss": 3.4284, + "step": 1855488 + }, + { + "epoch": 1.01, + "learning_rate": 1.9614747605910262e-05, + "loss": 3.4268, + "step": 1856000 + }, + { + "epoch": 1.01, + "learning_rate": 1.960636165839974e-05, + "loss": 3.4046, + "step": 1856512 + }, + { + "epoch": 1.01, + "learning_rate": 1.959799208969295e-05, + "loss": 3.4394, + "step": 1857024 + }, + { + "epoch": 1.01, + "learning_rate": 1.958960614218243e-05, + "loss": 3.4216, + "step": 1857536 + }, + { + "epoch": 1.01, + "learning_rate": 1.9581220194671908e-05, + "loss": 3.4357, + "step": 1858048 + }, + { + "epoch": 1.01, + "learning_rate": 1.9572850625965124e-05, + "loss": 3.4207, + "step": 1858560 + }, + { + "epoch": 1.01, + "learning_rate": 1.9564464678454604e-05, + "loss": 3.4194, + "step": 1859072 + }, + { + "epoch": 1.01, + "learning_rate": 1.9556078730944084e-05, + "loss": 3.4134, + "step": 1859584 + }, + { + "epoch": 1.01, + "learning_rate": 1.9547709162237293e-05, + "loss": 3.4265, + "step": 1860096 + }, + { + "epoch": 1.01, + "learning_rate": 1.9539323214726773e-05, + "loss": 3.4227, + "step": 1860608 + }, + { + "epoch": 1.01, + "learning_rate": 1.9530937267216253e-05, + "loss": 3.4214, + "step": 1861120 + }, + { + "epoch": 1.01, + "learning_rate": 1.9522551319705733e-05, + "loss": 3.4328, + "step": 1861632 + }, + { + "epoch": 1.01, + "learning_rate": 1.9514165372195213e-05, + "loss": 3.4188, + "step": 1862144 + }, + { + "epoch": 1.01, + "learning_rate": 1.9505779424684693e-05, + "loss": 3.4117, + "step": 1862656 + }, + { + "epoch": 1.01, + "learning_rate": 1.9497393477174173e-05, + "loss": 3.4344, + "step": 1863168 + }, + { + "epoch": 1.01, + "learning_rate": 1.9489007529663653e-05, + "loss": 3.4107, + "step": 1863680 + }, + { + "epoch": 1.01, + "learning_rate": 1.9480637960956862e-05, + "loss": 3.4106, + "step": 1864192 + }, + { + "epoch": 1.01, + "learning_rate": 1.947225201344634e-05, + "loss": 3.4255, + "step": 1864704 + }, + { + "epoch": 1.01, + "learning_rate": 1.9463866065935825e-05, + "loss": 3.425, + "step": 1865216 + }, + { + "epoch": 1.01, + "learning_rate": 1.9455480118425305e-05, + "loss": 3.42, + "step": 1865728 + }, + { + "epoch": 1.01, + "learning_rate": 1.9447110549718514e-05, + "loss": 3.4207, + "step": 1866240 + }, + { + "epoch": 1.01, + "learning_rate": 1.9438724602207994e-05, + "loss": 3.4078, + "step": 1866752 + }, + { + "epoch": 1.01, + "learning_rate": 1.9430338654697474e-05, + "loss": 3.4173, + "step": 1867264 + }, + { + "epoch": 1.01, + "learning_rate": 1.9421952707186954e-05, + "loss": 3.4304, + "step": 1867776 + }, + { + "epoch": 1.01, + "learning_rate": 1.9413583138480166e-05, + "loss": 3.4193, + "step": 1868288 + }, + { + "epoch": 1.01, + "learning_rate": 1.9405197190969646e-05, + "loss": 3.4371, + "step": 1868800 + }, + { + "epoch": 1.01, + "learning_rate": 1.9396811243459126e-05, + "loss": 3.4241, + "step": 1869312 + }, + { + "epoch": 1.01, + "learning_rate": 1.9388425295948606e-05, + "loss": 3.4342, + "step": 1869824 + }, + { + "epoch": 1.01, + "learning_rate": 1.9380055727241815e-05, + "loss": 3.4141, + "step": 1870336 + }, + { + "epoch": 1.01, + "learning_rate": 1.9371669779731295e-05, + "loss": 3.4303, + "step": 1870848 + }, + { + "epoch": 1.01, + "learning_rate": 1.936328383222078e-05, + "loss": 3.4213, + "step": 1871360 + }, + { + "epoch": 1.01, + "learning_rate": 1.935489788471026e-05, + "loss": 3.4145, + "step": 1871872 + }, + { + "epoch": 1.01, + "learning_rate": 1.9346528316003468e-05, + "loss": 3.426, + "step": 1872384 + }, + { + "epoch": 1.01, + "learning_rate": 1.9338142368492948e-05, + "loss": 3.4293, + "step": 1872896 + }, + { + "epoch": 1.01, + "learning_rate": 1.9329756420982428e-05, + "loss": 3.4241, + "step": 1873408 + }, + { + "epoch": 1.01, + "learning_rate": 1.9321370473471908e-05, + "loss": 3.4351, + "step": 1873920 + }, + { + "epoch": 1.01, + "learning_rate": 1.931300090476512e-05, + "loss": 3.4115, + "step": 1874432 + }, + { + "epoch": 1.01, + "learning_rate": 1.93046149572546e-05, + "loss": 3.4143, + "step": 1874944 + }, + { + "epoch": 1.01, + "learning_rate": 1.929622900974408e-05, + "loss": 3.4284, + "step": 1875456 + }, + { + "epoch": 1.01, + "learning_rate": 1.928784306223356e-05, + "loss": 3.4283, + "step": 1875968 + }, + { + "epoch": 1.01, + "learning_rate": 1.927947349352677e-05, + "loss": 3.4274, + "step": 1876480 + }, + { + "epoch": 1.01, + "learning_rate": 1.927108754601625e-05, + "loss": 3.4325, + "step": 1876992 + }, + { + "epoch": 1.02, + "learning_rate": 1.9262701598505732e-05, + "loss": 3.4253, + "step": 1877504 + }, + { + "epoch": 1.02, + "learning_rate": 1.9254315650995212e-05, + "loss": 3.427, + "step": 1878016 + }, + { + "epoch": 1.02, + "learning_rate": 1.924594608228842e-05, + "loss": 3.4217, + "step": 1878528 + }, + { + "epoch": 1.02, + "learning_rate": 1.92375601347779e-05, + "loss": 3.416, + "step": 1879040 + }, + { + "epoch": 1.02, + "learning_rate": 1.922917418726738e-05, + "loss": 3.4358, + "step": 1879552 + }, + { + "epoch": 1.02, + "learning_rate": 1.9220788239756858e-05, + "loss": 3.4282, + "step": 1880064 + }, + { + "epoch": 1.02, + "learning_rate": 1.9212418671050074e-05, + "loss": 3.4253, + "step": 1880576 + }, + { + "epoch": 1.02, + "learning_rate": 1.9204032723539554e-05, + "loss": 3.419, + "step": 1881088 + }, + { + "epoch": 1.02, + "learning_rate": 1.9195646776029034e-05, + "loss": 3.4189, + "step": 1881600 + }, + { + "epoch": 1.02, + "learning_rate": 1.918726082851851e-05, + "loss": 3.4198, + "step": 1882112 + }, + { + "epoch": 1.02, + "learning_rate": 1.9178891259811723e-05, + "loss": 3.435, + "step": 1882624 + }, + { + "epoch": 1.02, + "learning_rate": 1.9170505312301203e-05, + "loss": 3.4204, + "step": 1883136 + }, + { + "epoch": 1.02, + "learning_rate": 1.9162119364790686e-05, + "loss": 3.4252, + "step": 1883648 + }, + { + "epoch": 1.02, + "learning_rate": 1.9153733417280163e-05, + "loss": 3.4178, + "step": 1884160 + }, + { + "epoch": 1.02, + "learning_rate": 1.9145363848573375e-05, + "loss": 3.4193, + "step": 1884672 + }, + { + "epoch": 1.02, + "learning_rate": 1.9136977901062855e-05, + "loss": 3.4208, + "step": 1885184 + }, + { + "epoch": 1.02, + "learning_rate": 1.912859195355233e-05, + "loss": 3.4177, + "step": 1885696 + }, + { + "epoch": 1.02, + "learning_rate": 1.912020600604181e-05, + "loss": 3.4142, + "step": 1886208 + }, + { + "epoch": 1.02, + "learning_rate": 1.9111836437335027e-05, + "loss": 3.4316, + "step": 1886720 + }, + { + "epoch": 1.02, + "learning_rate": 1.9103450489824507e-05, + "loss": 3.422, + "step": 1887232 + }, + { + "epoch": 1.02, + "learning_rate": 1.9095064542313984e-05, + "loss": 3.4194, + "step": 1887744 + }, + { + "epoch": 1.02, + "learning_rate": 1.9086694973607196e-05, + "loss": 3.4166, + "step": 1888256 + }, + { + "epoch": 1.02, + "learning_rate": 1.9078309026096676e-05, + "loss": 3.426, + "step": 1888768 + }, + { + "epoch": 1.02, + "learning_rate": 1.9069923078586156e-05, + "loss": 3.4231, + "step": 1889280 + }, + { + "epoch": 1.02, + "learning_rate": 1.9061537131075636e-05, + "loss": 3.4239, + "step": 1889792 + }, + { + "epoch": 1.02, + "learning_rate": 1.905316756236885e-05, + "loss": 3.4261, + "step": 1890304 + }, + { + "epoch": 1.02, + "learning_rate": 1.9044797993662058e-05, + "loss": 3.4315, + "step": 1890816 + }, + { + "epoch": 1.02, + "learning_rate": 1.9036412046151538e-05, + "loss": 3.4166, + "step": 1891328 + }, + { + "epoch": 1.02, + "learning_rate": 1.9028026098641018e-05, + "loss": 3.4255, + "step": 1891840 + }, + { + "epoch": 1.02, + "learning_rate": 1.90196401511305e-05, + "loss": 3.4147, + "step": 1892352 + }, + { + "epoch": 1.02, + "learning_rate": 1.901125420361998e-05, + "loss": 3.4221, + "step": 1892864 + }, + { + "epoch": 1.02, + "learning_rate": 1.9002868256109458e-05, + "loss": 3.4186, + "step": 1893376 + }, + { + "epoch": 1.02, + "learning_rate": 1.8994482308598938e-05, + "loss": 3.4157, + "step": 1893888 + }, + { + "epoch": 1.02, + "learning_rate": 1.8986096361088418e-05, + "loss": 3.417, + "step": 1894400 + }, + { + "epoch": 1.02, + "learning_rate": 1.897772679238163e-05, + "loss": 3.4238, + "step": 1894912 + }, + { + "epoch": 1.02, + "learning_rate": 1.896934084487111e-05, + "loss": 3.4234, + "step": 1895424 + }, + { + "epoch": 1.02, + "learning_rate": 1.8960971276164322e-05, + "loss": 3.4235, + "step": 1895936 + }, + { + "epoch": 1.02, + "learning_rate": 1.8952585328653802e-05, + "loss": 3.4111, + "step": 1896448 + }, + { + "epoch": 1.02, + "learning_rate": 1.894419938114328e-05, + "loss": 3.4181, + "step": 1896960 + }, + { + "epoch": 1.02, + "learning_rate": 1.893581343363276e-05, + "loss": 3.4206, + "step": 1897472 + }, + { + "epoch": 1.02, + "learning_rate": 1.892742748612224e-05, + "loss": 3.4299, + "step": 1897984 + }, + { + "epoch": 1.02, + "learning_rate": 1.891904153861172e-05, + "loss": 3.4224, + "step": 1898496 + }, + { + "epoch": 1.02, + "learning_rate": 1.8910655591101202e-05, + "loss": 3.4241, + "step": 1899008 + }, + { + "epoch": 1.02, + "learning_rate": 1.8902269643590682e-05, + "loss": 3.4134, + "step": 1899520 + }, + { + "epoch": 1.02, + "learning_rate": 1.889390007488389e-05, + "loss": 3.4284, + "step": 1900032 + }, + { + "epoch": 1.02, + "learning_rate": 1.888551412737337e-05, + "loss": 3.4258, + "step": 1900544 + }, + { + "epoch": 1.02, + "learning_rate": 1.887712817986285e-05, + "loss": 3.4295, + "step": 1901056 + }, + { + "epoch": 1.02, + "learning_rate": 1.886874223235233e-05, + "loss": 3.4286, + "step": 1901568 + }, + { + "epoch": 1.02, + "learning_rate": 1.8860372663645544e-05, + "loss": 3.4291, + "step": 1902080 + }, + { + "epoch": 1.02, + "learning_rate": 1.8851986716135024e-05, + "loss": 3.4246, + "step": 1902592 + }, + { + "epoch": 1.02, + "learning_rate": 1.8843600768624504e-05, + "loss": 3.4313, + "step": 1903104 + }, + { + "epoch": 1.02, + "learning_rate": 1.8835214821113983e-05, + "loss": 3.4162, + "step": 1903616 + }, + { + "epoch": 1.02, + "learning_rate": 1.8826845252407193e-05, + "loss": 3.4262, + "step": 1904128 + }, + { + "epoch": 1.02, + "learning_rate": 1.8818459304896673e-05, + "loss": 3.4193, + "step": 1904640 + }, + { + "epoch": 1.02, + "learning_rate": 1.8810073357386156e-05, + "loss": 3.4237, + "step": 1905152 + }, + { + "epoch": 1.02, + "learning_rate": 1.8801687409875636e-05, + "loss": 3.4122, + "step": 1905664 + }, + { + "epoch": 1.02, + "learning_rate": 1.8793317841168845e-05, + "loss": 3.415, + "step": 1906176 + }, + { + "epoch": 1.02, + "learning_rate": 1.8784931893658325e-05, + "loss": 3.4252, + "step": 1906688 + }, + { + "epoch": 1.02, + "learning_rate": 1.8776545946147805e-05, + "loss": 3.4172, + "step": 1907200 + }, + { + "epoch": 1.02, + "learning_rate": 1.8768159998637285e-05, + "loss": 3.4332, + "step": 1907712 + }, + { + "epoch": 1.03, + "eval_loss": 3.854677200317383, + "eval_runtime": 303.2211, + "eval_samples_per_second": 1258.458, + "eval_steps_per_second": 39.328, + "step": 1908000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8759790429930497e-05, + "loss": 3.4083, + "step": 1908224 + }, + { + "epoch": 0.0, + "learning_rate": 1.8751404482419977e-05, + "loss": 3.4157, + "step": 1908736 + }, + { + "epoch": 0.0, + "learning_rate": 1.8743018534909457e-05, + "loss": 3.4131, + "step": 1909248 + }, + { + "epoch": 0.0, + "learning_rate": 1.8734632587398934e-05, + "loss": 3.4317, + "step": 1909760 + }, + { + "epoch": 0.0, + "learning_rate": 1.8726263018692146e-05, + "loss": 3.4286, + "step": 1910272 + }, + { + "epoch": 0.0, + "learning_rate": 1.8717877071181626e-05, + "loss": 3.412, + "step": 1910784 + }, + { + "epoch": 0.0, + "learning_rate": 1.870949112367111e-05, + "loss": 3.418, + "step": 1911296 + }, + { + "epoch": 0.0, + "learning_rate": 1.8701105176160586e-05, + "loss": 3.4135, + "step": 1911808 + }, + { + "epoch": 0.0, + "learning_rate": 1.86927356074538e-05, + "loss": 3.4198, + "step": 1912320 + }, + { + "epoch": 0.0, + "learning_rate": 1.868434965994328e-05, + "loss": 3.4307, + "step": 1912832 + }, + { + "epoch": 0.0, + "learning_rate": 1.8675963712432755e-05, + "loss": 3.4164, + "step": 1913344 + }, + { + "epoch": 0.0, + "learning_rate": 1.8667577764922235e-05, + "loss": 3.4138, + "step": 1913856 + }, + { + "epoch": 0.0, + "learning_rate": 1.865920819621545e-05, + "loss": 3.4269, + "step": 1914368 + }, + { + "epoch": 0.0, + "learning_rate": 1.865082224870493e-05, + "loss": 3.4002, + "step": 1914880 + }, + { + "epoch": 0.0, + "learning_rate": 1.8642436301194407e-05, + "loss": 3.4173, + "step": 1915392 + }, + { + "epoch": 0.0, + "learning_rate": 1.8634050353683887e-05, + "loss": 3.408, + "step": 1915904 + }, + { + "epoch": 0.0, + "learning_rate": 1.86256807849771e-05, + "loss": 3.4176, + "step": 1916416 + }, + { + "epoch": 0.0, + "learning_rate": 1.861729483746658e-05, + "loss": 3.418, + "step": 1916928 + }, + { + "epoch": 0.0, + "learning_rate": 1.860890888995606e-05, + "loss": 3.4078, + "step": 1917440 + }, + { + "epoch": 0.0, + "learning_rate": 1.860052294244554e-05, + "loss": 3.4287, + "step": 1917952 + }, + { + "epoch": 0.0, + "learning_rate": 1.8592153373738752e-05, + "loss": 3.4308, + "step": 1918464 + }, + { + "epoch": 0.0, + "learning_rate": 1.858378380503196e-05, + "loss": 3.4202, + "step": 1918976 + }, + { + "epoch": 0.0, + "learning_rate": 1.857539785752144e-05, + "loss": 3.4224, + "step": 1919488 + }, + { + "epoch": 0.0, + "learning_rate": 1.8567011910010925e-05, + "loss": 3.42, + "step": 1920000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8558625962500405e-05, + "loss": 3.4199, + "step": 1920512 + }, + { + "epoch": 0.0, + "learning_rate": 1.855024001498988e-05, + "loss": 3.4179, + "step": 1921024 + }, + { + "epoch": 0.0, + "learning_rate": 1.854185406747936e-05, + "loss": 3.419, + "step": 1921536 + }, + { + "epoch": 0.0, + "learning_rate": 1.853346811996884e-05, + "loss": 3.4176, + "step": 1922048 + }, + { + "epoch": 0.0, + "learning_rate": 1.852508217245832e-05, + "loss": 3.4078, + "step": 1922560 + }, + { + "epoch": 0.0, + "learning_rate": 1.8516712603751534e-05, + "loss": 3.4165, + "step": 1923072 + }, + { + "epoch": 0.01, + "learning_rate": 1.8508326656241014e-05, + "loss": 3.4214, + "step": 1923584 + }, + { + "epoch": 0.01, + "learning_rate": 1.8499940708730493e-05, + "loss": 3.4308, + "step": 1924096 + }, + { + "epoch": 0.01, + "learning_rate": 1.8491554761219973e-05, + "loss": 3.4267, + "step": 1924608 + }, + { + "epoch": 0.01, + "learning_rate": 1.8483185192513183e-05, + "loss": 3.4236, + "step": 1925120 + }, + { + "epoch": 0.01, + "learning_rate": 1.8474799245002662e-05, + "loss": 3.4107, + "step": 1925632 + }, + { + "epoch": 0.01, + "learning_rate": 1.8466429676295875e-05, + "loss": 3.4153, + "step": 1926144 + }, + { + "epoch": 0.01, + "learning_rate": 1.8458043728785355e-05, + "loss": 3.4224, + "step": 1926656 + }, + { + "epoch": 0.01, + "learning_rate": 1.8449657781274835e-05, + "loss": 3.4111, + "step": 1927168 + }, + { + "epoch": 0.01, + "learning_rate": 1.8441271833764315e-05, + "loss": 3.4101, + "step": 1927680 + }, + { + "epoch": 0.01, + "learning_rate": 1.8432885886253795e-05, + "loss": 3.4106, + "step": 1928192 + }, + { + "epoch": 0.01, + "learning_rate": 1.8424499938743275e-05, + "loss": 3.414, + "step": 1928704 + }, + { + "epoch": 0.01, + "learning_rate": 1.8416130370036487e-05, + "loss": 3.4186, + "step": 1929216 + }, + { + "epoch": 0.01, + "learning_rate": 1.8407744422525967e-05, + "loss": 3.4237, + "step": 1929728 + }, + { + "epoch": 0.01, + "learning_rate": 1.8399358475015447e-05, + "loss": 3.4186, + "step": 1930240 + }, + { + "epoch": 0.01, + "learning_rate": 1.8390972527504927e-05, + "loss": 3.4204, + "step": 1930752 + }, + { + "epoch": 0.01, + "learning_rate": 1.8382586579994407e-05, + "loss": 3.42, + "step": 1931264 + }, + { + "epoch": 0.01, + "learning_rate": 1.8374200632483884e-05, + "loss": 3.4162, + "step": 1931776 + }, + { + "epoch": 0.01, + "learning_rate": 1.8365814684973364e-05, + "loss": 3.4247, + "step": 1932288 + }, + { + "epoch": 0.01, + "learning_rate": 1.8357428737462844e-05, + "loss": 3.3907, + "step": 1932800 + }, + { + "epoch": 0.01, + "learning_rate": 1.834905916875606e-05, + "loss": 3.4243, + "step": 1933312 + }, + { + "epoch": 0.01, + "learning_rate": 1.8340673221245536e-05, + "loss": 3.4123, + "step": 1933824 + }, + { + "epoch": 0.01, + "learning_rate": 1.8332287273735016e-05, + "loss": 3.4272, + "step": 1934336 + }, + { + "epoch": 0.01, + "learning_rate": 1.8323901326224496e-05, + "loss": 3.4101, + "step": 1934848 + }, + { + "epoch": 0.01, + "learning_rate": 1.831553175751771e-05, + "loss": 3.4109, + "step": 1935360 + }, + { + "epoch": 0.01, + "learning_rate": 1.830714581000719e-05, + "loss": 3.4019, + "step": 1935872 + }, + { + "epoch": 0.01, + "learning_rate": 1.82987762413004e-05, + "loss": 3.4165, + "step": 1936384 + }, + { + "epoch": 0.01, + "learning_rate": 1.829039029378988e-05, + "loss": 3.4169, + "step": 1936896 + }, + { + "epoch": 0.01, + "learning_rate": 1.8282004346279357e-05, + "loss": 3.4076, + "step": 1937408 + }, + { + "epoch": 0.01, + "learning_rate": 1.8273618398768837e-05, + "loss": 3.4234, + "step": 1937920 + }, + { + "epoch": 0.01, + "learning_rate": 1.8265232451258317e-05, + "loss": 3.413, + "step": 1938432 + }, + { + "epoch": 0.01, + "learning_rate": 1.8256846503747797e-05, + "loss": 3.3951, + "step": 1938944 + }, + { + "epoch": 0.01, + "learning_rate": 1.824846055623728e-05, + "loss": 3.4263, + "step": 1939456 + }, + { + "epoch": 0.01, + "learning_rate": 1.824007460872676e-05, + "loss": 3.403, + "step": 1939968 + }, + { + "epoch": 0.01, + "learning_rate": 1.823170504001997e-05, + "loss": 3.3997, + "step": 1940480 + }, + { + "epoch": 0.01, + "learning_rate": 1.822331909250945e-05, + "loss": 3.4171, + "step": 1940992 + }, + { + "epoch": 0.01, + "learning_rate": 1.821493314499893e-05, + "loss": 3.4148, + "step": 1941504 + }, + { + "epoch": 0.01, + "learning_rate": 1.820654719748841e-05, + "loss": 3.402, + "step": 1942016 + }, + { + "epoch": 0.01, + "learning_rate": 1.8198177628781622e-05, + "loss": 3.4187, + "step": 1942528 + }, + { + "epoch": 0.01, + "learning_rate": 1.8189791681271102e-05, + "loss": 3.3992, + "step": 1943040 + }, + { + "epoch": 0.01, + "learning_rate": 1.8181405733760582e-05, + "loss": 3.4014, + "step": 1943552 + }, + { + "epoch": 0.01, + "learning_rate": 1.8173019786250062e-05, + "loss": 3.4209, + "step": 1944064 + }, + { + "epoch": 0.01, + "learning_rate": 1.816465021754327e-05, + "loss": 3.4106, + "step": 1944576 + }, + { + "epoch": 0.01, + "learning_rate": 1.815626427003275e-05, + "loss": 3.425, + "step": 1945088 + }, + { + "epoch": 0.01, + "learning_rate": 1.8147878322522234e-05, + "loss": 3.4107, + "step": 1945600 + }, + { + "epoch": 0.01, + "learning_rate": 1.8139492375011714e-05, + "loss": 3.4227, + "step": 1946112 + }, + { + "epoch": 0.01, + "learning_rate": 1.8131122806304923e-05, + "loss": 3.405, + "step": 1946624 + }, + { + "epoch": 0.01, + "learning_rate": 1.8122736858794403e-05, + "loss": 3.4223, + "step": 1947136 + }, + { + "epoch": 0.01, + "learning_rate": 1.8114350911283883e-05, + "loss": 3.4069, + "step": 1947648 + }, + { + "epoch": 0.01, + "learning_rate": 1.8105964963773363e-05, + "loss": 3.408, + "step": 1948160 + }, + { + "epoch": 0.01, + "learning_rate": 1.8097595395066576e-05, + "loss": 3.4168, + "step": 1948672 + }, + { + "epoch": 0.01, + "learning_rate": 1.8089209447556056e-05, + "loss": 3.4163, + "step": 1949184 + }, + { + "epoch": 0.01, + "learning_rate": 1.8080823500045536e-05, + "loss": 3.4138, + "step": 1949696 + }, + { + "epoch": 0.01, + "learning_rate": 1.8072453931338745e-05, + "loss": 3.4241, + "step": 1950208 + }, + { + "epoch": 0.01, + "learning_rate": 1.8064067983828225e-05, + "loss": 3.3987, + "step": 1950720 + }, + { + "epoch": 0.01, + "learning_rate": 1.8055682036317705e-05, + "loss": 3.4047, + "step": 1951232 + }, + { + "epoch": 0.01, + "learning_rate": 1.8047296088807188e-05, + "loss": 3.4165, + "step": 1951744 + }, + { + "epoch": 0.01, + "learning_rate": 1.8038910141296664e-05, + "loss": 3.4179, + "step": 1952256 + }, + { + "epoch": 0.01, + "learning_rate": 1.8030524193786144e-05, + "loss": 3.4135, + "step": 1952768 + }, + { + "epoch": 0.01, + "learning_rate": 1.8022138246275624e-05, + "loss": 3.4222, + "step": 1953280 + }, + { + "epoch": 0.02, + "learning_rate": 1.8013752298765104e-05, + "loss": 3.4134, + "step": 1953792 + }, + { + "epoch": 0.02, + "learning_rate": 1.8005382730058313e-05, + "loss": 3.4186, + "step": 1954304 + }, + { + "epoch": 0.02, + "learning_rate": 1.7996996782547797e-05, + "loss": 3.4126, + "step": 1954816 + }, + { + "epoch": 0.02, + "learning_rate": 1.7988610835037277e-05, + "loss": 3.4045, + "step": 1955328 + }, + { + "epoch": 0.02, + "learning_rate": 1.7980224887526757e-05, + "loss": 3.4222, + "step": 1955840 + }, + { + "epoch": 0.02, + "learning_rate": 1.7971855318819966e-05, + "loss": 3.421, + "step": 1956352 + }, + { + "epoch": 0.02, + "learning_rate": 1.7963469371309446e-05, + "loss": 3.4129, + "step": 1956864 + }, + { + "epoch": 0.02, + "learning_rate": 1.7955083423798926e-05, + "loss": 3.4109, + "step": 1957376 + }, + { + "epoch": 0.02, + "learning_rate": 1.7946713855092138e-05, + "loss": 3.4036, + "step": 1957888 + }, + { + "epoch": 0.02, + "learning_rate": 1.7938327907581618e-05, + "loss": 3.4124, + "step": 1958400 + }, + { + "epoch": 0.02, + "learning_rate": 1.7929941960071098e-05, + "loss": 3.4231, + "step": 1958912 + }, + { + "epoch": 0.02, + "learning_rate": 1.7921556012560578e-05, + "loss": 3.4108, + "step": 1959424 + }, + { + "epoch": 0.02, + "learning_rate": 1.7913170065050058e-05, + "loss": 3.4152, + "step": 1959936 + }, + { + "epoch": 0.02, + "learning_rate": 1.7904784117539538e-05, + "loss": 3.406, + "step": 1960448 + }, + { + "epoch": 0.02, + "learning_rate": 1.7896398170029018e-05, + "loss": 3.4077, + "step": 1960960 + }, + { + "epoch": 0.02, + "learning_rate": 1.7888012222518498e-05, + "loss": 3.4113, + "step": 1961472 + }, + { + "epoch": 0.02, + "learning_rate": 1.787964265381171e-05, + "loss": 3.4058, + "step": 1961984 + }, + { + "epoch": 0.02, + "learning_rate": 1.787125670630119e-05, + "loss": 3.4051, + "step": 1962496 + }, + { + "epoch": 0.02, + "learning_rate": 1.7862870758790667e-05, + "loss": 3.4223, + "step": 1963008 + }, + { + "epoch": 0.02, + "learning_rate": 1.7854484811280147e-05, + "loss": 3.418, + "step": 1963520 + }, + { + "epoch": 0.02, + "learning_rate": 1.784611524257336e-05, + "loss": 3.404, + "step": 1964032 + }, + { + "epoch": 0.02, + "learning_rate": 1.7837729295062843e-05, + "loss": 3.411, + "step": 1964544 + }, + { + "epoch": 0.02, + "learning_rate": 1.782934334755232e-05, + "loss": 3.4121, + "step": 1965056 + }, + { + "epoch": 0.02, + "learning_rate": 1.78209574000418e-05, + "loss": 3.4159, + "step": 1965568 + }, + { + "epoch": 0.02, + "learning_rate": 1.781258783133501e-05, + "loss": 3.4085, + "step": 1966080 + }, + { + "epoch": 0.02, + "learning_rate": 1.7804201883824488e-05, + "loss": 3.4183, + "step": 1966592 + }, + { + "epoch": 0.02, + "learning_rate": 1.7795832315117704e-05, + "loss": 3.4221, + "step": 1967104 + }, + { + "epoch": 0.02, + "learning_rate": 1.7787446367607184e-05, + "loss": 3.4069, + "step": 1967616 + }, + { + "epoch": 0.02, + "learning_rate": 1.7779060420096664e-05, + "loss": 3.4149, + "step": 1968128 + }, + { + "epoch": 0.02, + "learning_rate": 1.777067447258614e-05, + "loss": 3.4079, + "step": 1968640 + }, + { + "epoch": 0.02, + "learning_rate": 1.776228852507562e-05, + "loss": 3.4089, + "step": 1969152 + }, + { + "epoch": 0.02, + "learning_rate": 1.77539025775651e-05, + "loss": 3.412, + "step": 1969664 + }, + { + "epoch": 0.02, + "learning_rate": 1.774551663005458e-05, + "loss": 3.4023, + "step": 1970176 + }, + { + "epoch": 0.02, + "learning_rate": 1.773713068254406e-05, + "loss": 3.4038, + "step": 1970688 + }, + { + "epoch": 0.02, + "learning_rate": 1.7728761113837273e-05, + "loss": 3.4151, + "step": 1971200 + }, + { + "epoch": 0.02, + "learning_rate": 1.7720375166326753e-05, + "loss": 3.4151, + "step": 1971712 + }, + { + "epoch": 0.02, + "learning_rate": 1.7712005597619962e-05, + "loss": 3.4139, + "step": 1972224 + }, + { + "epoch": 0.02, + "learning_rate": 1.7703619650109442e-05, + "loss": 3.3994, + "step": 1972736 + }, + { + "epoch": 0.02, + "learning_rate": 1.7695233702598922e-05, + "loss": 3.4045, + "step": 1973248 + }, + { + "epoch": 0.02, + "learning_rate": 1.7686847755088405e-05, + "loss": 3.41, + "step": 1973760 + }, + { + "epoch": 0.02, + "learning_rate": 1.7678461807577885e-05, + "loss": 3.4203, + "step": 1974272 + }, + { + "epoch": 0.02, + "learning_rate": 1.7670075860067365e-05, + "loss": 3.4134, + "step": 1974784 + }, + { + "epoch": 0.02, + "learning_rate": 1.7661689912556845e-05, + "loss": 3.4173, + "step": 1975296 + }, + { + "epoch": 0.02, + "learning_rate": 1.765330396504632e-05, + "loss": 3.4004, + "step": 1975808 + }, + { + "epoch": 0.02, + "learning_rate": 1.7644934396339534e-05, + "loss": 3.4215, + "step": 1976320 + }, + { + "epoch": 0.02, + "learning_rate": 1.7636548448829014e-05, + "loss": 3.4109, + "step": 1976832 + }, + { + "epoch": 0.02, + "learning_rate": 1.7628162501318497e-05, + "loss": 3.4214, + "step": 1977344 + }, + { + "epoch": 0.02, + "learning_rate": 1.7619776553807974e-05, + "loss": 3.4138, + "step": 1977856 + }, + { + "epoch": 0.02, + "learning_rate": 1.7611406985101186e-05, + "loss": 3.4184, + "step": 1978368 + }, + { + "epoch": 0.02, + "learning_rate": 1.7603021037590666e-05, + "loss": 3.4129, + "step": 1978880 + }, + { + "epoch": 0.02, + "learning_rate": 1.7594635090080143e-05, + "loss": 3.4252, + "step": 1979392 + }, + { + "epoch": 0.02, + "learning_rate": 1.7586249142569626e-05, + "loss": 3.4007, + "step": 1979904 + }, + { + "epoch": 0.02, + "learning_rate": 1.757787957386284e-05, + "loss": 3.4178, + "step": 1980416 + }, + { + "epoch": 0.02, + "learning_rate": 1.756949362635232e-05, + "loss": 3.4071, + "step": 1980928 + }, + { + "epoch": 0.02, + "learning_rate": 1.7561107678841795e-05, + "loss": 3.4111, + "step": 1981440 + }, + { + "epoch": 0.02, + "learning_rate": 1.7552721731331275e-05, + "loss": 3.406, + "step": 1981952 + }, + { + "epoch": 0.02, + "learning_rate": 1.7544352162624488e-05, + "loss": 3.4056, + "step": 1982464 + }, + { + "epoch": 0.02, + "learning_rate": 1.7535966215113968e-05, + "loss": 3.413, + "step": 1982976 + }, + { + "epoch": 0.02, + "learning_rate": 1.7527580267603448e-05, + "loss": 3.4094, + "step": 1983488 + }, + { + "epoch": 0.02, + "learning_rate": 1.7519194320092928e-05, + "loss": 3.4185, + "step": 1984000 + }, + { + "epoch": 0.03, + "eval_loss": 3.8567733764648438, + "eval_runtime": 305.0607, + "eval_samples_per_second": 1250.869, + "eval_steps_per_second": 39.091, + "step": 1984320 + }, + { + "epoch": 1.0, + "learning_rate": 1.751082475138614e-05, + "loss": 3.4044, + "step": 1984512 + }, + { + "epoch": 1.0, + "learning_rate": 1.7502438803875617e-05, + "loss": 3.4042, + "step": 1985024 + }, + { + "epoch": 1.0, + "learning_rate": 1.7494052856365097e-05, + "loss": 3.4013, + "step": 1985536 + }, + { + "epoch": 1.0, + "learning_rate": 1.7485666908854577e-05, + "loss": 3.4193, + "step": 1986048 + }, + { + "epoch": 1.0, + "learning_rate": 1.7477297340147792e-05, + "loss": 3.4217, + "step": 1986560 + }, + { + "epoch": 1.0, + "learning_rate": 1.746891139263727e-05, + "loss": 3.4019, + "step": 1987072 + }, + { + "epoch": 1.0, + "learning_rate": 1.746052544512675e-05, + "loss": 3.4078, + "step": 1987584 + }, + { + "epoch": 1.0, + "learning_rate": 1.745213949761623e-05, + "loss": 3.4018, + "step": 1988096 + }, + { + "epoch": 1.0, + "learning_rate": 1.744376992890944e-05, + "loss": 3.4108, + "step": 1988608 + }, + { + "epoch": 1.0, + "learning_rate": 1.743538398139892e-05, + "loss": 3.416, + "step": 1989120 + }, + { + "epoch": 1.0, + "learning_rate": 1.74269980338884e-05, + "loss": 3.4076, + "step": 1989632 + }, + { + "epoch": 1.0, + "learning_rate": 1.741861208637788e-05, + "loss": 3.4062, + "step": 1990144 + }, + { + "epoch": 1.0, + "learning_rate": 1.741024251767109e-05, + "loss": 3.4156, + "step": 1990656 + }, + { + "epoch": 1.0, + "learning_rate": 1.740185657016057e-05, + "loss": 3.3926, + "step": 1991168 + }, + { + "epoch": 1.0, + "learning_rate": 1.739347062265005e-05, + "loss": 3.4063, + "step": 1991680 + }, + { + "epoch": 1.0, + "learning_rate": 1.738508467513953e-05, + "loss": 3.3976, + "step": 1992192 + }, + { + "epoch": 1.0, + "learning_rate": 1.7376715106432743e-05, + "loss": 3.409, + "step": 1992704 + }, + { + "epoch": 1.0, + "learning_rate": 1.7368329158922223e-05, + "loss": 3.4093, + "step": 1993216 + }, + { + "epoch": 1.0, + "learning_rate": 1.7359943211411703e-05, + "loss": 3.3988, + "step": 1993728 + }, + { + "epoch": 1.0, + "learning_rate": 1.7351557263901183e-05, + "loss": 3.4176, + "step": 1994240 + }, + { + "epoch": 1.0, + "learning_rate": 1.7343187695194392e-05, + "loss": 3.4208, + "step": 1994752 + }, + { + "epoch": 1.0, + "learning_rate": 1.7334801747683875e-05, + "loss": 3.4089, + "step": 1995264 + }, + { + "epoch": 1.0, + "learning_rate": 1.7326415800173355e-05, + "loss": 3.411, + "step": 1995776 + }, + { + "epoch": 1.0, + "learning_rate": 1.7318046231466564e-05, + "loss": 3.4121, + "step": 1996288 + }, + { + "epoch": 1.0, + "learning_rate": 1.7309660283956044e-05, + "loss": 3.4121, + "step": 1996800 + }, + { + "epoch": 1.0, + "learning_rate": 1.7301274336445524e-05, + "loss": 3.4057, + "step": 1997312 + }, + { + "epoch": 1.0, + "learning_rate": 1.7292888388935004e-05, + "loss": 3.4044, + "step": 1997824 + }, + { + "epoch": 1.0, + "learning_rate": 1.7284518820228216e-05, + "loss": 3.4106, + "step": 1998336 + }, + { + "epoch": 1.0, + "learning_rate": 1.7276132872717696e-05, + "loss": 3.3973, + "step": 1998848 + }, + { + "epoch": 1.0, + "learning_rate": 1.7267746925207176e-05, + "loss": 3.406, + "step": 1999360 + }, + { + "epoch": 1.01, + "learning_rate": 1.7259360977696656e-05, + "loss": 3.414, + "step": 1999872 + }, + { + "epoch": 1.01, + "learning_rate": 1.7250991408989865e-05, + "loss": 3.4152, + "step": 2000384 + }, + { + "epoch": 1.01, + "learning_rate": 1.7242605461479345e-05, + "loss": 3.4215, + "step": 2000896 + }, + { + "epoch": 1.01, + "learning_rate": 1.723421951396883e-05, + "loss": 3.4104, + "step": 2001408 + }, + { + "epoch": 1.01, + "learning_rate": 1.722583356645831e-05, + "loss": 3.4011, + "step": 2001920 + }, + { + "epoch": 1.01, + "learning_rate": 1.7217463997751518e-05, + "loss": 3.4064, + "step": 2002432 + }, + { + "epoch": 1.01, + "learning_rate": 1.7209078050240998e-05, + "loss": 3.4134, + "step": 2002944 + }, + { + "epoch": 1.01, + "learning_rate": 1.7200692102730478e-05, + "loss": 3.3978, + "step": 2003456 + }, + { + "epoch": 1.01, + "learning_rate": 1.7192306155219958e-05, + "loss": 3.4002, + "step": 2003968 + }, + { + "epoch": 1.01, + "learning_rate": 1.718393658651317e-05, + "loss": 3.4043, + "step": 2004480 + }, + { + "epoch": 1.01, + "learning_rate": 1.717555063900265e-05, + "loss": 3.3993, + "step": 2004992 + }, + { + "epoch": 1.01, + "learning_rate": 1.716718107029586e-05, + "loss": 3.4093, + "step": 2005504 + }, + { + "epoch": 1.01, + "learning_rate": 1.715879512278534e-05, + "loss": 3.411, + "step": 2006016 + }, + { + "epoch": 1.01, + "learning_rate": 1.715040917527482e-05, + "loss": 3.4125, + "step": 2006528 + }, + { + "epoch": 1.01, + "learning_rate": 1.71420232277643e-05, + "loss": 3.4024, + "step": 2007040 + }, + { + "epoch": 1.01, + "learning_rate": 1.7133637280253782e-05, + "loss": 3.4123, + "step": 2007552 + }, + { + "epoch": 1.01, + "learning_rate": 1.7125251332743262e-05, + "loss": 3.4069, + "step": 2008064 + }, + { + "epoch": 1.01, + "learning_rate": 1.7116865385232742e-05, + "loss": 3.4128, + "step": 2008576 + }, + { + "epoch": 1.01, + "learning_rate": 1.710847943772222e-05, + "loss": 3.3837, + "step": 2009088 + }, + { + "epoch": 1.01, + "learning_rate": 1.710010986901543e-05, + "loss": 3.4116, + "step": 2009600 + }, + { + "epoch": 1.01, + "learning_rate": 1.709172392150491e-05, + "loss": 3.404, + "step": 2010112 + }, + { + "epoch": 1.01, + "learning_rate": 1.708333797399439e-05, + "loss": 3.4173, + "step": 2010624 + }, + { + "epoch": 1.01, + "learning_rate": 1.707495202648387e-05, + "loss": 3.4003, + "step": 2011136 + }, + { + "epoch": 1.01, + "learning_rate": 1.7066582457777084e-05, + "loss": 3.3982, + "step": 2011648 + }, + { + "epoch": 1.01, + "learning_rate": 1.7058196510266564e-05, + "loss": 3.3958, + "step": 2012160 + }, + { + "epoch": 1.01, + "learning_rate": 1.704981056275604e-05, + "loss": 3.4006, + "step": 2012672 + }, + { + "epoch": 1.01, + "learning_rate": 1.7041440994049253e-05, + "loss": 3.4129, + "step": 2013184 + }, + { + "epoch": 1.01, + "learning_rate": 1.7033055046538736e-05, + "loss": 3.3926, + "step": 2013696 + }, + { + "epoch": 1.01, + "learning_rate": 1.7024669099028216e-05, + "loss": 3.4166, + "step": 2014208 + }, + { + "epoch": 1.01, + "learning_rate": 1.7016283151517693e-05, + "loss": 3.4007, + "step": 2014720 + }, + { + "epoch": 1.01, + "learning_rate": 1.7007897204007173e-05, + "loss": 3.3838, + "step": 2015232 + }, + { + "epoch": 1.01, + "learning_rate": 1.6999511256496652e-05, + "loss": 3.4166, + "step": 2015744 + }, + { + "epoch": 1.01, + "learning_rate": 1.6991125308986132e-05, + "loss": 3.3947, + "step": 2016256 + }, + { + "epoch": 1.01, + "learning_rate": 1.6982755740279345e-05, + "loss": 3.3877, + "step": 2016768 + }, + { + "epoch": 1.01, + "learning_rate": 1.6974369792768825e-05, + "loss": 3.4077, + "step": 2017280 + }, + { + "epoch": 1.01, + "learning_rate": 1.6965983845258305e-05, + "loss": 3.403, + "step": 2017792 + }, + { + "epoch": 1.01, + "learning_rate": 1.6957597897747785e-05, + "loss": 3.3921, + "step": 2018304 + }, + { + "epoch": 1.01, + "learning_rate": 1.6949228329040994e-05, + "loss": 3.4084, + "step": 2018816 + }, + { + "epoch": 1.01, + "learning_rate": 1.6940842381530474e-05, + "loss": 3.3867, + "step": 2019328 + }, + { + "epoch": 1.01, + "learning_rate": 1.6932456434019954e-05, + "loss": 3.3922, + "step": 2019840 + }, + { + "epoch": 1.01, + "learning_rate": 1.6924070486509437e-05, + "loss": 3.4093, + "step": 2020352 + }, + { + "epoch": 1.01, + "learning_rate": 1.6915700917802646e-05, + "loss": 3.4039, + "step": 2020864 + }, + { + "epoch": 1.01, + "learning_rate": 1.6907314970292126e-05, + "loss": 3.4137, + "step": 2021376 + }, + { + "epoch": 1.01, + "learning_rate": 1.6898929022781606e-05, + "loss": 3.4024, + "step": 2021888 + }, + { + "epoch": 1.01, + "learning_rate": 1.6890543075271086e-05, + "loss": 3.4125, + "step": 2022400 + }, + { + "epoch": 1.01, + "learning_rate": 1.68821735065643e-05, + "loss": 3.3969, + "step": 2022912 + }, + { + "epoch": 1.01, + "learning_rate": 1.687378755905378e-05, + "loss": 3.4159, + "step": 2023424 + }, + { + "epoch": 1.01, + "learning_rate": 1.686540161154326e-05, + "loss": 3.3932, + "step": 2023936 + }, + { + "epoch": 1.01, + "learning_rate": 1.685701566403274e-05, + "loss": 3.3979, + "step": 2024448 + }, + { + "epoch": 1.01, + "learning_rate": 1.6848646095325948e-05, + "loss": 3.4052, + "step": 2024960 + }, + { + "epoch": 1.01, + "learning_rate": 1.6840260147815428e-05, + "loss": 3.4027, + "step": 2025472 + }, + { + "epoch": 1.01, + "learning_rate": 1.6831874200304907e-05, + "loss": 3.4085, + "step": 2025984 + }, + { + "epoch": 1.01, + "learning_rate": 1.682350463159812e-05, + "loss": 3.4134, + "step": 2026496 + }, + { + "epoch": 1.01, + "learning_rate": 1.68151186840876e-05, + "loss": 3.3947, + "step": 2027008 + }, + { + "epoch": 1.01, + "learning_rate": 1.680673273657708e-05, + "loss": 3.3934, + "step": 2027520 + }, + { + "epoch": 1.01, + "learning_rate": 1.679834678906656e-05, + "loss": 3.4021, + "step": 2028032 + }, + { + "epoch": 1.01, + "learning_rate": 1.678996084155604e-05, + "loss": 3.4111, + "step": 2028544 + }, + { + "epoch": 1.01, + "learning_rate": 1.678157489404552e-05, + "loss": 3.401, + "step": 2029056 + }, + { + "epoch": 1.01, + "learning_rate": 1.6773188946535e-05, + "loss": 3.4123, + "step": 2029568 + }, + { + "epoch": 1.01, + "learning_rate": 1.676480299902448e-05, + "loss": 3.4051, + "step": 2030080 + }, + { + "epoch": 1.02, + "learning_rate": 1.6756433430317692e-05, + "loss": 3.4074, + "step": 2030592 + }, + { + "epoch": 1.02, + "learning_rate": 1.674804748280717e-05, + "loss": 3.4014, + "step": 2031104 + }, + { + "epoch": 1.02, + "learning_rate": 1.673966153529665e-05, + "loss": 3.3975, + "step": 2031616 + }, + { + "epoch": 1.02, + "learning_rate": 1.673127558778613e-05, + "loss": 3.4105, + "step": 2032128 + }, + { + "epoch": 1.02, + "learning_rate": 1.6722906019079344e-05, + "loss": 3.409, + "step": 2032640 + }, + { + "epoch": 1.02, + "learning_rate": 1.671452007156882e-05, + "loss": 3.4078, + "step": 2033152 + }, + { + "epoch": 1.02, + "learning_rate": 1.67061341240583e-05, + "loss": 3.3984, + "step": 2033664 + }, + { + "epoch": 1.02, + "learning_rate": 1.669774817654778e-05, + "loss": 3.3921, + "step": 2034176 + }, + { + "epoch": 1.02, + "learning_rate": 1.668937860784099e-05, + "loss": 3.3997, + "step": 2034688 + }, + { + "epoch": 1.02, + "learning_rate": 1.6680992660330473e-05, + "loss": 3.4141, + "step": 2035200 + }, + { + "epoch": 1.02, + "learning_rate": 1.6672606712819953e-05, + "loss": 3.4023, + "step": 2035712 + }, + { + "epoch": 1.02, + "learning_rate": 1.6664220765309433e-05, + "loss": 3.4058, + "step": 2036224 + }, + { + "epoch": 1.02, + "learning_rate": 1.6655851196602642e-05, + "loss": 3.3972, + "step": 2036736 + }, + { + "epoch": 1.02, + "learning_rate": 1.6647465249092122e-05, + "loss": 3.397, + "step": 2037248 + }, + { + "epoch": 1.02, + "learning_rate": 1.6639079301581602e-05, + "loss": 3.4053, + "step": 2037760 + }, + { + "epoch": 1.02, + "learning_rate": 1.6630693354071082e-05, + "loss": 3.3913, + "step": 2038272 + }, + { + "epoch": 1.02, + "learning_rate": 1.6622323785364295e-05, + "loss": 3.3976, + "step": 2038784 + }, + { + "epoch": 1.02, + "learning_rate": 1.6613937837853775e-05, + "loss": 3.4079, + "step": 2039296 + }, + { + "epoch": 1.02, + "learning_rate": 1.6605551890343255e-05, + "loss": 3.4079, + "step": 2039808 + }, + { + "epoch": 1.02, + "learning_rate": 1.6597165942832735e-05, + "loss": 3.3969, + "step": 2040320 + }, + { + "epoch": 1.02, + "learning_rate": 1.6588796374125944e-05, + "loss": 3.3966, + "step": 2040832 + }, + { + "epoch": 1.02, + "learning_rate": 1.6580410426615424e-05, + "loss": 3.3981, + "step": 2041344 + }, + { + "epoch": 1.02, + "learning_rate": 1.6572024479104907e-05, + "loss": 3.4077, + "step": 2041856 + }, + { + "epoch": 1.02, + "learning_rate": 1.6563638531594387e-05, + "loss": 3.4002, + "step": 2042368 + }, + { + "epoch": 1.02, + "learning_rate": 1.6555268962887596e-05, + "loss": 3.4119, + "step": 2042880 + }, + { + "epoch": 1.02, + "learning_rate": 1.654689939418081e-05, + "loss": 3.4107, + "step": 2043392 + }, + { + "epoch": 1.02, + "learning_rate": 1.653851344667029e-05, + "loss": 3.3999, + "step": 2043904 + }, + { + "epoch": 1.02, + "learning_rate": 1.653012749915977e-05, + "loss": 3.3996, + "step": 2044416 + }, + { + "epoch": 1.02, + "learning_rate": 1.652174155164925e-05, + "loss": 3.4002, + "step": 2044928 + }, + { + "epoch": 1.02, + "learning_rate": 1.651335560413873e-05, + "loss": 3.3986, + "step": 2045440 + }, + { + "epoch": 1.02, + "learning_rate": 1.650496965662821e-05, + "loss": 3.4046, + "step": 2045952 + }, + { + "epoch": 1.02, + "learning_rate": 1.6496583709117688e-05, + "loss": 3.3887, + "step": 2046464 + }, + { + "epoch": 1.02, + "learning_rate": 1.6488197761607168e-05, + "loss": 3.3941, + "step": 2046976 + }, + { + "epoch": 1.02, + "learning_rate": 1.6479828192900377e-05, + "loss": 3.4014, + "step": 2047488 + }, + { + "epoch": 1.02, + "learning_rate": 1.647144224538986e-05, + "loss": 3.4048, + "step": 2048000 + }, + { + "epoch": 1.02, + "learning_rate": 1.646307267668307e-05, + "loss": 3.4019, + "step": 2048512 + }, + { + "epoch": 1.02, + "learning_rate": 1.645468672917255e-05, + "loss": 3.3935, + "step": 2049024 + }, + { + "epoch": 1.02, + "learning_rate": 1.644630078166203e-05, + "loss": 3.3971, + "step": 2049536 + }, + { + "epoch": 1.02, + "learning_rate": 1.643791483415151e-05, + "loss": 3.3982, + "step": 2050048 + }, + { + "epoch": 1.02, + "learning_rate": 1.642952888664099e-05, + "loss": 3.4136, + "step": 2050560 + }, + { + "epoch": 1.02, + "learning_rate": 1.642114293913047e-05, + "loss": 3.4009, + "step": 2051072 + }, + { + "epoch": 1.02, + "learning_rate": 1.641275699161995e-05, + "loss": 3.4063, + "step": 2051584 + }, + { + "epoch": 1.02, + "learning_rate": 1.640437104410943e-05, + "loss": 3.392, + "step": 2052096 + }, + { + "epoch": 1.02, + "learning_rate": 1.6396001475402642e-05, + "loss": 3.4115, + "step": 2052608 + }, + { + "epoch": 1.02, + "learning_rate": 1.638761552789212e-05, + "loss": 3.3993, + "step": 2053120 + }, + { + "epoch": 1.02, + "learning_rate": 1.63792295803816e-05, + "loss": 3.4111, + "step": 2053632 + }, + { + "epoch": 1.02, + "learning_rate": 1.6370843632871082e-05, + "loss": 3.4108, + "step": 2054144 + }, + { + "epoch": 1.02, + "learning_rate": 1.6362474064164294e-05, + "loss": 3.4039, + "step": 2054656 + }, + { + "epoch": 1.02, + "learning_rate": 1.635408811665377e-05, + "loss": 3.4025, + "step": 2055168 + }, + { + "epoch": 1.02, + "learning_rate": 1.634570216914325e-05, + "loss": 3.4151, + "step": 2055680 + }, + { + "epoch": 1.02, + "learning_rate": 1.633731622163273e-05, + "loss": 3.3932, + "step": 2056192 + }, + { + "epoch": 1.02, + "learning_rate": 1.6328946652925943e-05, + "loss": 3.408, + "step": 2056704 + }, + { + "epoch": 1.02, + "learning_rate": 1.6320560705415423e-05, + "loss": 3.3977, + "step": 2057216 + }, + { + "epoch": 1.02, + "learning_rate": 1.6312174757904903e-05, + "loss": 3.4004, + "step": 2057728 + }, + { + "epoch": 1.02, + "learning_rate": 1.6303788810394383e-05, + "loss": 3.3959, + "step": 2058240 + }, + { + "epoch": 1.02, + "learning_rate": 1.6295419241687592e-05, + "loss": 3.3956, + "step": 2058752 + }, + { + "epoch": 1.02, + "learning_rate": 1.6287033294177072e-05, + "loss": 3.3992, + "step": 2059264 + }, + { + "epoch": 1.02, + "learning_rate": 1.6278647346666552e-05, + "loss": 3.4058, + "step": 2059776 + }, + { + "epoch": 1.02, + "learning_rate": 1.6270261399156032e-05, + "loss": 3.4035, + "step": 2060288 + }, + { + "epoch": 1.03, + "eval_loss": 3.8581464290618896, + "eval_runtime": 305.2382, + "eval_samples_per_second": 1250.142, + "eval_steps_per_second": 39.068, + "step": 2060640 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.4248983383480402e+18, + "trial_name": null, + "trial_params": null +}