| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9605263157894737, | |
| "eval_steps": 19, | |
| "global_step": 152, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013157894736842105, | |
| "grad_norm": 0.402255117893219, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 1.641, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013157894736842105, | |
| "eval_loss": 1.6610033512115479, | |
| "eval_runtime": 11.198, | |
| "eval_samples_per_second": 13.217, | |
| "eval_steps_per_second": 1.697, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02631578947368421, | |
| "grad_norm": 0.39817070960998535, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 1.5949, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.039473684210526314, | |
| "grad_norm": 0.40712764859199524, | |
| "learning_rate": 3e-06, | |
| "loss": 1.625, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05263157894736842, | |
| "grad_norm": 0.42735520005226135, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.6878, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06578947368421052, | |
| "grad_norm": 0.3926982879638672, | |
| "learning_rate": 5e-06, | |
| "loss": 1.5266, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07894736842105263, | |
| "grad_norm": 0.4139236807823181, | |
| "learning_rate": 6e-06, | |
| "loss": 1.6492, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09210526315789473, | |
| "grad_norm": 0.3906595706939697, | |
| "learning_rate": 7e-06, | |
| "loss": 1.5571, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.10526315789473684, | |
| "grad_norm": 0.4070392847061157, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 1.5989, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.11842105263157894, | |
| "grad_norm": 0.4086395800113678, | |
| "learning_rate": 9e-06, | |
| "loss": 1.6022, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.13157894736842105, | |
| "grad_norm": 0.42242783308029175, | |
| "learning_rate": 1e-05, | |
| "loss": 1.5348, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14473684210526316, | |
| "grad_norm": 0.43531253933906555, | |
| "learning_rate": 9.998776383426217e-06, | |
| "loss": 1.661, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.15789473684210525, | |
| "grad_norm": 0.44515812397003174, | |
| "learning_rate": 9.995106132599869e-06, | |
| "loss": 1.6782, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.17105263157894737, | |
| "grad_norm": 0.4268193542957306, | |
| "learning_rate": 9.988991043912857e-06, | |
| "loss": 1.6253, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.18421052631578946, | |
| "grad_norm": 0.4616084694862366, | |
| "learning_rate": 9.980434110374725e-06, | |
| "loss": 1.633, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.19736842105263158, | |
| "grad_norm": 0.4059070646762848, | |
| "learning_rate": 9.969439520147754e-06, | |
| "loss": 1.6423, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 0.4180908501148224, | |
| "learning_rate": 9.956012654497073e-06, | |
| "loss": 1.6157, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2236842105263158, | |
| "grad_norm": 0.44470345973968506, | |
| "learning_rate": 9.94016008515682e-06, | |
| "loss": 1.6116, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.23684210526315788, | |
| "grad_norm": 0.4326673150062561, | |
| "learning_rate": 9.921889571113629e-06, | |
| "loss": 1.65, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.44323351979255676, | |
| "learning_rate": 9.901210054809015e-06, | |
| "loss": 1.5857, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 1.6229134798049927, | |
| "eval_runtime": 11.1737, | |
| "eval_samples_per_second": 13.245, | |
| "eval_steps_per_second": 1.7, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2631578947368421, | |
| "grad_norm": 0.4330739378929138, | |
| "learning_rate": 9.878131657762535e-06, | |
| "loss": 1.5456, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.27631578947368424, | |
| "grad_norm": 0.43902918696403503, | |
| "learning_rate": 9.852665675617837e-06, | |
| "loss": 1.6184, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2894736842105263, | |
| "grad_norm": 0.4325895309448242, | |
| "learning_rate": 9.82482457261405e-06, | |
| "loss": 1.5871, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3026315789473684, | |
| "grad_norm": 0.4587506353855133, | |
| "learning_rate": 9.7946219754852e-06, | |
| "loss": 1.5777, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3157894736842105, | |
| "grad_norm": 0.38507089018821716, | |
| "learning_rate": 9.762072666790658e-06, | |
| "loss": 1.4464, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.32894736842105265, | |
| "grad_norm": 0.3887621760368347, | |
| "learning_rate": 9.727192577679852e-06, | |
| "loss": 1.5026, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.34210526315789475, | |
| "grad_norm": 0.3975026309490204, | |
| "learning_rate": 9.689998780094839e-06, | |
| "loss": 1.5542, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.35526315789473684, | |
| "grad_norm": 0.4168972074985504, | |
| "learning_rate": 9.650509478414483e-06, | |
| "loss": 1.5423, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3684210526315789, | |
| "grad_norm": 0.40937769412994385, | |
| "learning_rate": 9.608744000544392e-06, | |
| "loss": 1.544, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3815789473684211, | |
| "grad_norm": 0.42820680141448975, | |
| "learning_rate": 9.564722788456943e-06, | |
| "loss": 1.5586, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.39473684210526316, | |
| "grad_norm": 0.39091867208480835, | |
| "learning_rate": 9.51846738818602e-06, | |
| "loss": 1.547, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.40789473684210525, | |
| "grad_norm": 0.39774808287620544, | |
| "learning_rate": 9.470000439281379e-06, | |
| "loss": 1.4802, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 0.38609299063682556, | |
| "learning_rate": 9.419345663727805e-06, | |
| "loss": 1.5297, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4342105263157895, | |
| "grad_norm": 0.384609580039978, | |
| "learning_rate": 9.366527854334464e-06, | |
| "loss": 1.4976, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.4473684210526316, | |
| "grad_norm": 0.3664967119693756, | |
| "learning_rate": 9.31157286260014e-06, | |
| "loss": 1.4768, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.4605263157894737, | |
| "grad_norm": 0.4111669063568115, | |
| "learning_rate": 9.25450758606031e-06, | |
| "loss": 1.4819, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.47368421052631576, | |
| "grad_norm": 0.38792452216148376, | |
| "learning_rate": 9.195359955122244e-06, | |
| "loss": 1.4876, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.4868421052631579, | |
| "grad_norm": 0.3711869716644287, | |
| "learning_rate": 9.134158919394545e-06, | |
| "loss": 1.4768, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.37189042568206787, | |
| "learning_rate": 9.070934433517872e-06, | |
| "loss": 1.4426, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 1.4863917827606201, | |
| "eval_runtime": 11.152, | |
| "eval_samples_per_second": 13.271, | |
| "eval_steps_per_second": 1.704, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5131578947368421, | |
| "grad_norm": 0.3438572287559509, | |
| "learning_rate": 9.005717442503741e-06, | |
| "loss": 1.4076, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "grad_norm": 0.36527037620544434, | |
| "learning_rate": 8.938539866588593e-06, | |
| "loss": 1.4656, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5394736842105263, | |
| "grad_norm": 0.36658236384391785, | |
| "learning_rate": 8.869434585610534e-06, | |
| "loss": 1.4152, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5526315789473685, | |
| "grad_norm": 0.3422878682613373, | |
| "learning_rate": 8.798435422916425e-06, | |
| "loss": 1.3725, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5657894736842105, | |
| "grad_norm": 0.3560190498828888, | |
| "learning_rate": 8.725577128807144e-06, | |
| "loss": 1.3982, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5789473684210527, | |
| "grad_norm": 0.3515233099460602, | |
| "learning_rate": 8.650895363529172e-06, | |
| "loss": 1.4798, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5921052631578947, | |
| "grad_norm": 0.35305333137512207, | |
| "learning_rate": 8.574426679820813e-06, | |
| "loss": 1.4064, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6052631578947368, | |
| "grad_norm": 0.3789292871952057, | |
| "learning_rate": 8.496208505021572e-06, | |
| "loss": 1.3732, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.618421052631579, | |
| "grad_norm": 0.33839643001556396, | |
| "learning_rate": 8.416279122753468e-06, | |
| "loss": 1.345, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.631578947368421, | |
| "grad_norm": 0.34697043895721436, | |
| "learning_rate": 8.334677654183254e-06, | |
| "loss": 1.4175, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6447368421052632, | |
| "grad_norm": 0.3513168394565582, | |
| "learning_rate": 8.251444038874685e-06, | |
| "loss": 1.3793, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6578947368421053, | |
| "grad_norm": 0.3464255630970001, | |
| "learning_rate": 8.166619015240236e-06, | |
| "loss": 1.4089, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6710526315789473, | |
| "grad_norm": 0.34775641560554504, | |
| "learning_rate": 8.080244100601822e-06, | |
| "loss": 1.391, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.6842105263157895, | |
| "grad_norm": 0.33794087171554565, | |
| "learning_rate": 7.992361570870289e-06, | |
| "loss": 1.4101, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.6973684210526315, | |
| "grad_norm": 0.35401248931884766, | |
| "learning_rate": 7.903014439853605e-06, | |
| "loss": 1.3881, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.7105263157894737, | |
| "grad_norm": 0.32468080520629883, | |
| "learning_rate": 7.812246438203905e-06, | |
| "loss": 1.3629, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.7236842105263158, | |
| "grad_norm": 0.34929484128952026, | |
| "learning_rate": 7.720101992013661e-06, | |
| "loss": 1.3425, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.7368421052631579, | |
| "grad_norm": 0.3399946689605713, | |
| "learning_rate": 7.626626201071494e-06, | |
| "loss": 1.3021, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.31694310903549194, | |
| "learning_rate": 7.53186481678822e-06, | |
| "loss": 1.2782, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 1.375747799873352, | |
| "eval_runtime": 11.2956, | |
| "eval_samples_per_second": 13.102, | |
| "eval_steps_per_second": 1.682, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.7631578947368421, | |
| "grad_norm": 0.34202322363853455, | |
| "learning_rate": 7.4358642198039835e-06, | |
| "loss": 1.338, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.7763157894736842, | |
| "grad_norm": 0.3176383376121521, | |
| "learning_rate": 7.338671397287409e-06, | |
| "loss": 1.3133, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.7894736842105263, | |
| "grad_norm": 0.31007757782936096, | |
| "learning_rate": 7.240333919937893e-06, | |
| "loss": 1.3322, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.8026315789473685, | |
| "grad_norm": 0.31201171875, | |
| "learning_rate": 7.140899918702276e-06, | |
| "loss": 1.2824, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.8157894736842105, | |
| "grad_norm": 0.29208070039749146, | |
| "learning_rate": 7.040418061217325e-06, | |
| "loss": 1.3342, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.8289473684210527, | |
| "grad_norm": 0.29806771874427795, | |
| "learning_rate": 6.938937527989511e-06, | |
| "loss": 1.3021, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 0.30114126205444336, | |
| "learning_rate": 6.836507988323785e-06, | |
| "loss": 1.2985, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.8552631578947368, | |
| "grad_norm": 0.28877463936805725, | |
| "learning_rate": 6.733179576013098e-06, | |
| "loss": 1.2917, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.868421052631579, | |
| "grad_norm": 0.3036439120769501, | |
| "learning_rate": 6.629002864800589e-06, | |
| "loss": 1.336, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.881578947368421, | |
| "grad_norm": 0.29111841320991516, | |
| "learning_rate": 6.524028843626433e-06, | |
| "loss": 1.3284, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.8947368421052632, | |
| "grad_norm": 0.31157442927360535, | |
| "learning_rate": 6.418308891671484e-06, | |
| "loss": 1.298, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.9078947368421053, | |
| "grad_norm": 0.28027617931365967, | |
| "learning_rate": 6.311894753209896e-06, | |
| "loss": 1.3627, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.9210526315789473, | |
| "grad_norm": 0.31063735485076904, | |
| "learning_rate": 6.204838512283073e-06, | |
| "loss": 1.2751, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.9342105263157895, | |
| "grad_norm": 0.27762889862060547, | |
| "learning_rate": 6.097192567207304e-06, | |
| "loss": 1.2646, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.9473684210526315, | |
| "grad_norm": 0.30012503266334534, | |
| "learning_rate": 5.989009604927587e-06, | |
| "loss": 1.2696, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.9605263157894737, | |
| "grad_norm": 0.2858477234840393, | |
| "learning_rate": 5.8803425752301814e-06, | |
| "loss": 1.3184, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.9736842105263158, | |
| "grad_norm": 0.2571242153644562, | |
| "learning_rate": 5.771244664826512e-06, | |
| "loss": 1.1024, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.9868421052631579, | |
| "grad_norm": 0.28689220547676086, | |
| "learning_rate": 5.661769271321113e-06, | |
| "loss": 1.3068, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.27221059799194336, | |
| "learning_rate": 5.55196997707635e-06, | |
| "loss": 1.262, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.3148635625839233, | |
| "eval_runtime": 11.2095, | |
| "eval_samples_per_second": 13.203, | |
| "eval_steps_per_second": 1.695, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.013157894736842, | |
| "grad_norm": 0.2928997278213501, | |
| "learning_rate": 5.441900522986712e-06, | |
| "loss": 1.2916, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 1.0263157894736843, | |
| "grad_norm": 0.28008702397346497, | |
| "learning_rate": 5.33161478217552e-06, | |
| "loss": 1.3139, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.0394736842105263, | |
| "grad_norm": 0.3058090806007385, | |
| "learning_rate": 5.221166733626895e-06, | |
| "loss": 1.1989, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 1.013157894736842, | |
| "grad_norm": 0.27998045086860657, | |
| "learning_rate": 5.110610435765935e-06, | |
| "loss": 1.247, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.0263157894736843, | |
| "grad_norm": 0.2768513560295105, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3229, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.0394736842105263, | |
| "grad_norm": 0.28100040555000305, | |
| "learning_rate": 4.8893895642340665e-06, | |
| "loss": 1.3181, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.0526315789473684, | |
| "grad_norm": 0.29516279697418213, | |
| "learning_rate": 4.778833266373107e-06, | |
| "loss": 1.1794, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 1.0657894736842106, | |
| "grad_norm": 0.266646146774292, | |
| "learning_rate": 4.668385217824482e-06, | |
| "loss": 1.261, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.0789473684210527, | |
| "grad_norm": 0.2927522361278534, | |
| "learning_rate": 4.558099477013288e-06, | |
| "loss": 1.3016, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.0921052631578947, | |
| "grad_norm": 0.2729503810405731, | |
| "learning_rate": 4.4480300229236525e-06, | |
| "loss": 1.2789, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.1052631578947367, | |
| "grad_norm": 0.2716759145259857, | |
| "learning_rate": 4.338230728678888e-06, | |
| "loss": 1.2746, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.118421052631579, | |
| "grad_norm": 0.2987295985221863, | |
| "learning_rate": 4.228755335173488e-06, | |
| "loss": 1.3, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.131578947368421, | |
| "grad_norm": 0.2681940495967865, | |
| "learning_rate": 4.119657424769819e-06, | |
| "loss": 1.2736, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 1.1447368421052633, | |
| "grad_norm": 0.26406219601631165, | |
| "learning_rate": 4.010990395072414e-06, | |
| "loss": 1.2695, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.1578947368421053, | |
| "grad_norm": 0.262295663356781, | |
| "learning_rate": 3.902807432792698e-06, | |
| "loss": 1.2413, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.1710526315789473, | |
| "grad_norm": 0.2757396101951599, | |
| "learning_rate": 3.7951614877169285e-06, | |
| "loss": 1.2272, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.1842105263157894, | |
| "grad_norm": 0.2563100755214691, | |
| "learning_rate": 3.6881052467901056e-06, | |
| "loss": 1.2172, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.1973684210526316, | |
| "grad_norm": 0.27466002106666565, | |
| "learning_rate": 3.5816911083285165e-06, | |
| "loss": 1.2276, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.2105263157894737, | |
| "grad_norm": 0.27229124307632446, | |
| "learning_rate": 3.4759711563735676e-06, | |
| "loss": 1.2384, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.2105263157894737, | |
| "eval_loss": 1.2851184606552124, | |
| "eval_runtime": 11.1818, | |
| "eval_samples_per_second": 13.236, | |
| "eval_steps_per_second": 1.699, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.2236842105263157, | |
| "grad_norm": 0.26436150074005127, | |
| "learning_rate": 3.370997135199413e-06, | |
| "loss": 1.2118, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.236842105263158, | |
| "grad_norm": 0.2642536461353302, | |
| "learning_rate": 3.2668204239869046e-06, | |
| "loss": 1.2411, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 0.3076295256614685, | |
| "learning_rate": 3.1634920116762175e-06, | |
| "loss": 1.1806, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.263157894736842, | |
| "grad_norm": 0.2798045873641968, | |
| "learning_rate": 3.061062472010489e-06, | |
| "loss": 1.231, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.2763157894736843, | |
| "grad_norm": 0.26016712188720703, | |
| "learning_rate": 2.9595819387826753e-06, | |
| "loss": 1.2221, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.2894736842105263, | |
| "grad_norm": 0.27707499265670776, | |
| "learning_rate": 2.8591000812977245e-06, | |
| "loss": 1.2265, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 1.3026315789473684, | |
| "grad_norm": 0.24529437720775604, | |
| "learning_rate": 2.7596660800621076e-06, | |
| "loss": 1.1956, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.3157894736842106, | |
| "grad_norm": 0.2894725799560547, | |
| "learning_rate": 2.661328602712592e-06, | |
| "loss": 1.2519, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 1.3289473684210527, | |
| "grad_norm": 0.259954035282135, | |
| "learning_rate": 2.5641357801960186e-06, | |
| "loss": 1.28, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.3421052631578947, | |
| "grad_norm": 0.28108924627304077, | |
| "learning_rate": 2.4681351832117815e-06, | |
| "loss": 1.1942, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.3552631578947367, | |
| "grad_norm": 0.2708108723163605, | |
| "learning_rate": 2.373373798928507e-06, | |
| "loss": 1.2821, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.368421052631579, | |
| "grad_norm": 0.2668735086917877, | |
| "learning_rate": 2.2798980079863386e-06, | |
| "loss": 1.2289, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 1.381578947368421, | |
| "grad_norm": 0.26546740531921387, | |
| "learning_rate": 2.187753561796097e-06, | |
| "loss": 1.2604, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.3947368421052633, | |
| "grad_norm": 0.262500137090683, | |
| "learning_rate": 2.0969855601463966e-06, | |
| "loss": 1.2243, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 1.4078947368421053, | |
| "grad_norm": 0.24560751020908356, | |
| "learning_rate": 2.0076384291297134e-06, | |
| "loss": 1.2348, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.4210526315789473, | |
| "grad_norm": 0.26329511404037476, | |
| "learning_rate": 1.9197558993981784e-06, | |
| "loss": 1.2551, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.4342105263157894, | |
| "grad_norm": 0.2851774990558624, | |
| "learning_rate": 1.8333809847597644e-06, | |
| "loss": 1.2282, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.4473684210526316, | |
| "grad_norm": 0.26805853843688965, | |
| "learning_rate": 1.748555961125315e-06, | |
| "loss": 1.2531, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 1.4605263157894737, | |
| "grad_norm": 0.2691291272640228, | |
| "learning_rate": 1.665322345816746e-06, | |
| "loss": 1.1451, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.4605263157894737, | |
| "eval_loss": 1.2717276811599731, | |
| "eval_runtime": 11.1773, | |
| "eval_samples_per_second": 13.241, | |
| "eval_steps_per_second": 1.7, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.4736842105263157, | |
| "grad_norm": 0.2724035680294037, | |
| "learning_rate": 1.583720877246533e-06, | |
| "loss": 1.2532, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.486842105263158, | |
| "grad_norm": 0.28526419401168823, | |
| "learning_rate": 1.50379149497843e-06, | |
| "loss": 1.1913, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.29095906019210815, | |
| "learning_rate": 1.4255733201791883e-06, | |
| "loss": 1.1994, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.513157894736842, | |
| "grad_norm": 0.2538934051990509, | |
| "learning_rate": 1.3491046364708294e-06, | |
| "loss": 1.128, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.526315789473684, | |
| "grad_norm": 0.2766117751598358, | |
| "learning_rate": 1.2744228711928585e-06, | |
| "loss": 1.1852, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 1.5394736842105263, | |
| "grad_norm": 0.2569272816181183, | |
| "learning_rate": 1.2015645770835765e-06, | |
| "loss": 1.2415, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.5526315789473686, | |
| "grad_norm": 0.2636973559856415, | |
| "learning_rate": 1.1305654143894674e-06, | |
| "loss": 1.1965, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 1.5657894736842106, | |
| "grad_norm": 0.2750151753425598, | |
| "learning_rate": 1.0614601334114099e-06, | |
| "loss": 1.1965, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 1.5789473684210527, | |
| "grad_norm": 0.27310946583747864, | |
| "learning_rate": 9.942825574962595e-07, | |
| "loss": 1.2491, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 1.5921052631578947, | |
| "grad_norm": 0.30951154232025146, | |
| "learning_rate": 9.290655664821296e-07, | |
| "loss": 1.2388, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 1.6052631578947367, | |
| "grad_norm": 0.2787538170814514, | |
| "learning_rate": 8.658410806054568e-07, | |
| "loss": 1.167, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.618421052631579, | |
| "grad_norm": 0.30251288414001465, | |
| "learning_rate": 8.046400448777575e-07, | |
| "loss": 1.2439, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 1.631578947368421, | |
| "grad_norm": 0.2696026563644409, | |
| "learning_rate": 7.45492413939689e-07, | |
| "loss": 1.2197, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 1.6447368421052633, | |
| "grad_norm": 0.26345524191856384, | |
| "learning_rate": 6.884271373998608e-07, | |
| "loss": 1.2436, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 1.6578947368421053, | |
| "grad_norm": 0.25275254249572754, | |
| "learning_rate": 6.334721456655363e-07, | |
| "loss": 1.2608, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 1.6710526315789473, | |
| "grad_norm": 0.2568216323852539, | |
| "learning_rate": 5.806543362721945e-07, | |
| "loss": 1.2484, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.6842105263157894, | |
| "grad_norm": 0.26159876585006714, | |
| "learning_rate": 5.29999560718622e-07, | |
| "loss": 1.225, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 1.6973684210526314, | |
| "grad_norm": 0.2594353258609772, | |
| "learning_rate": 4.815326118139813e-07, | |
| "loss": 1.2002, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.7105263157894737, | |
| "grad_norm": 0.2540861964225769, | |
| "learning_rate": 4.3527721154305703e-07, | |
| "loss": 1.2273, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 1.7105263157894737, | |
| "eval_loss": 1.2666972875595093, | |
| "eval_runtime": 11.1757, | |
| "eval_samples_per_second": 13.243, | |
| "eval_steps_per_second": 1.7, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 1.723684210526316, | |
| "grad_norm": 0.23720534145832062, | |
| "learning_rate": 3.9125599945560866e-07, | |
| "loss": 1.2512, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 1.736842105263158, | |
| "grad_norm": 0.26305046677589417, | |
| "learning_rate": 3.4949052158551875e-07, | |
| "loss": 1.235, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 0.2618529796600342, | |
| "learning_rate": 3.100012199051627e-07, | |
| "loss": 1.2146, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 1.763157894736842, | |
| "grad_norm": 0.27660179138183594, | |
| "learning_rate": 2.728074223201488e-07, | |
| "loss": 1.2123, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 1.776315789473684, | |
| "grad_norm": 0.2622484266757965, | |
| "learning_rate": 2.3792733320934348e-07, | |
| "loss": 1.2098, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 1.7894736842105263, | |
| "grad_norm": 0.2647554576396942, | |
| "learning_rate": 2.053780245147996e-07, | |
| "loss": 1.1725, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 1.8026315789473686, | |
| "grad_norm": 0.2567311227321625, | |
| "learning_rate": 1.7517542738595071e-07, | |
| "loss": 1.1835, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.8157894736842106, | |
| "grad_norm": 0.2933162450790405, | |
| "learning_rate": 1.47334324382164e-07, | |
| "loss": 1.2196, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 1.8289473684210527, | |
| "grad_norm": 0.2644355595111847, | |
| "learning_rate": 1.2186834223746612e-07, | |
| "loss": 1.1582, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 1.8421052631578947, | |
| "grad_norm": 0.2735837697982788, | |
| "learning_rate": 9.878994519098573e-08, | |
| "loss": 1.2063, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 1.8552631578947367, | |
| "grad_norm": 0.28176724910736084, | |
| "learning_rate": 7.81104288863721e-08, | |
| "loss": 1.254, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 1.868421052631579, | |
| "grad_norm": 0.2595096230506897, | |
| "learning_rate": 5.983991484317997e-08, | |
| "loss": 1.218, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.881578947368421, | |
| "grad_norm": 0.2540487051010132, | |
| "learning_rate": 4.398734550292716e-08, | |
| "loss": 1.197, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 1.8947368421052633, | |
| "grad_norm": 0.2847471833229065, | |
| "learning_rate": 3.0560479852246304e-08, | |
| "loss": 1.1756, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 1.9078947368421053, | |
| "grad_norm": 0.28027528524398804, | |
| "learning_rate": 1.9565889625275945e-08, | |
| "loss": 1.239, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 1.9210526315789473, | |
| "grad_norm": 0.268658310174942, | |
| "learning_rate": 1.1008956087144585e-08, | |
| "loss": 1.2424, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 1.9342105263157894, | |
| "grad_norm": 0.2798985540866852, | |
| "learning_rate": 4.89386740013198e-09, | |
| "loss": 1.2587, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.9473684210526314, | |
| "grad_norm": 0.24452678859233856, | |
| "learning_rate": 1.2236165737850025e-09, | |
| "loss": 1.2067, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 1.9605263157894737, | |
| "grad_norm": 0.26837992668151855, | |
| "learning_rate": 0.0, | |
| "loss": 1.2018, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 1.9605263157894737, | |
| "eval_loss": 1.2660664319992065, | |
| "eval_runtime": 11.23, | |
| "eval_samples_per_second": 13.179, | |
| "eval_steps_per_second": 1.692, | |
| "step": 152 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 152, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 38, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.408145505581793e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |