{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.036778227289444645, "eval_steps": 9, "global_step": 100, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0003677822728944465, "grad_norm": NaN, "learning_rate": 1e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0003677822728944465, "eval_loss": NaN, "eval_runtime": 270.89, "eval_samples_per_second": 8.454, "eval_steps_per_second": 1.059, "step": 1 }, { "epoch": 0.000735564545788893, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.0011033468186833395, "grad_norm": NaN, "learning_rate": 3e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.001471129091577786, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.0018389113644722325, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 5 }, { "epoch": 0.002206693637366679, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 6 }, { "epoch": 0.0025744759102611253, "grad_norm": NaN, "learning_rate": 7e-05, "loss": 0.0, "step": 7 }, { "epoch": 0.002942258183155572, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 8 }, { "epoch": 0.0033100404560500183, "grad_norm": NaN, "learning_rate": 9e-05, "loss": 0.0, "step": 9 }, { "epoch": 0.0033100404560500183, "eval_loss": NaN, "eval_runtime": 270.6454, "eval_samples_per_second": 8.461, "eval_steps_per_second": 1.06, "step": 9 }, { "epoch": 0.003677822728944465, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 10 }, { "epoch": 0.004045605001838912, "grad_norm": NaN, "learning_rate": 9.99695413509548e-05, "loss": 0.0, "step": 11 }, { "epoch": 0.004413387274733358, "grad_norm": NaN, "learning_rate": 9.987820251299122e-05, "loss": 0.0, "step": 12 }, { "epoch": 0.004781169547627804, "grad_norm": NaN, "learning_rate": 9.972609476841367e-05, "loss": 0.0, "step": 13 }, { "epoch": 0.0051489518205222505, "grad_norm": NaN, "learning_rate": 9.951340343707852e-05, "loss": 0.0, "step": 14 }, { "epoch": 0.005516734093416698, "grad_norm": NaN, "learning_rate": 9.924038765061042e-05, "loss": 0.0, "step": 15 }, { "epoch": 0.005884516366311144, "grad_norm": NaN, "learning_rate": 9.890738003669029e-05, "loss": 0.0, "step": 16 }, { "epoch": 0.00625229863920559, "grad_norm": NaN, "learning_rate": 9.851478631379982e-05, "loss": 0.0, "step": 17 }, { "epoch": 0.0066200809121000365, "grad_norm": NaN, "learning_rate": 9.806308479691595e-05, "loss": 0.0, "step": 18 }, { "epoch": 0.0066200809121000365, "eval_loss": NaN, "eval_runtime": 270.7231, "eval_samples_per_second": 8.459, "eval_steps_per_second": 1.06, "step": 18 }, { "epoch": 0.006987863184994484, "grad_norm": NaN, "learning_rate": 9.755282581475769e-05, "loss": 0.0, "step": 19 }, { "epoch": 0.00735564545788893, "grad_norm": NaN, "learning_rate": 9.698463103929542e-05, "loss": 0.0, "step": 20 }, { "epoch": 0.007723427730783376, "grad_norm": NaN, "learning_rate": 9.635919272833938e-05, "loss": 0.0, "step": 21 }, { "epoch": 0.008091210003677823, "grad_norm": NaN, "learning_rate": 9.567727288213005e-05, "loss": 0.0, "step": 22 }, { "epoch": 0.008458992276572269, "grad_norm": NaN, "learning_rate": 9.493970231495835e-05, "loss": 0.0, "step": 23 }, { "epoch": 0.008826774549466716, "grad_norm": NaN, "learning_rate": 9.414737964294636e-05, "loss": 0.0, "step": 24 }, { "epoch": 0.009194556822361161, "grad_norm": NaN, "learning_rate": 9.330127018922194e-05, "loss": 0.0, "step": 25 }, { "epoch": 0.009562339095255609, "grad_norm": NaN, "learning_rate": 9.24024048078213e-05, "loss": 0.0, "step": 26 }, { "epoch": 0.009930121368150056, "grad_norm": NaN, "learning_rate": 9.145187862775209e-05, "loss": 0.0, "step": 27 }, { "epoch": 0.009930121368150056, "eval_loss": NaN, "eval_runtime": 271.0388, "eval_samples_per_second": 8.449, "eval_steps_per_second": 1.059, "step": 27 }, { "epoch": 0.010297903641044501, "grad_norm": NaN, "learning_rate": 9.045084971874738e-05, "loss": 0.0, "step": 28 }, { "epoch": 0.010665685913938948, "grad_norm": NaN, "learning_rate": 8.940053768033609e-05, "loss": 0.0, "step": 29 }, { "epoch": 0.011033468186833395, "grad_norm": NaN, "learning_rate": 8.83022221559489e-05, "loss": 0.0, "step": 30 }, { "epoch": 0.01140125045972784, "grad_norm": NaN, "learning_rate": 8.715724127386972e-05, "loss": 0.0, "step": 31 }, { "epoch": 0.011769032732622288, "grad_norm": NaN, "learning_rate": 8.596699001693255e-05, "loss": 0.0, "step": 32 }, { "epoch": 0.012136815005516733, "grad_norm": NaN, "learning_rate": 8.473291852294987e-05, "loss": 0.0, "step": 33 }, { "epoch": 0.01250459727841118, "grad_norm": NaN, "learning_rate": 8.345653031794292e-05, "loss": 0.0, "step": 34 }, { "epoch": 0.012872379551305628, "grad_norm": NaN, "learning_rate": 8.213938048432697e-05, "loss": 0.0, "step": 35 }, { "epoch": 0.013240161824200073, "grad_norm": NaN, "learning_rate": 8.07830737662829e-05, "loss": 0.0, "step": 36 }, { "epoch": 0.013240161824200073, "eval_loss": NaN, "eval_runtime": 270.7509, "eval_samples_per_second": 8.458, "eval_steps_per_second": 1.06, "step": 36 }, { "epoch": 0.01360794409709452, "grad_norm": NaN, "learning_rate": 7.938926261462366e-05, "loss": 0.0, "step": 37 }, { "epoch": 0.013975726369988967, "grad_norm": NaN, "learning_rate": 7.795964517353735e-05, "loss": 0.0, "step": 38 }, { "epoch": 0.014343508642883413, "grad_norm": NaN, "learning_rate": 7.649596321166024e-05, "loss": 0.0, "step": 39 }, { "epoch": 0.01471129091577786, "grad_norm": NaN, "learning_rate": 7.500000000000001e-05, "loss": 0.0, "step": 40 }, { "epoch": 0.015079073188672305, "grad_norm": NaN, "learning_rate": 7.347357813929454e-05, "loss": 0.0, "step": 41 }, { "epoch": 0.015446855461566752, "grad_norm": NaN, "learning_rate": 7.191855733945387e-05, "loss": 0.0, "step": 42 }, { "epoch": 0.0158146377344612, "grad_norm": NaN, "learning_rate": 7.033683215379002e-05, "loss": 0.0, "step": 43 }, { "epoch": 0.016182420007355647, "grad_norm": NaN, "learning_rate": 6.873032967079561e-05, "loss": 0.0, "step": 44 }, { "epoch": 0.01655020228025009, "grad_norm": NaN, "learning_rate": 6.710100716628344e-05, "loss": 0.0, "step": 45 }, { "epoch": 0.01655020228025009, "eval_loss": NaN, "eval_runtime": 270.8064, "eval_samples_per_second": 8.456, "eval_steps_per_second": 1.06, "step": 45 }, { "epoch": 0.016917984553144538, "grad_norm": NaN, "learning_rate": 6.545084971874738e-05, "loss": 0.0, "step": 46 }, { "epoch": 0.017285766826038985, "grad_norm": NaN, "learning_rate": 6.378186779084995e-05, "loss": 0.0, "step": 47 }, { "epoch": 0.017653549098933432, "grad_norm": NaN, "learning_rate": 6.209609477998338e-05, "loss": 0.0, "step": 48 }, { "epoch": 0.01802133137182788, "grad_norm": NaN, "learning_rate": 6.0395584540887963e-05, "loss": 0.0, "step": 49 }, { "epoch": 0.018389113644722323, "grad_norm": NaN, "learning_rate": 5.868240888334653e-05, "loss": 0.0, "step": 50 }, { "epoch": 0.01875689591761677, "grad_norm": NaN, "learning_rate": 5.695865504800327e-05, "loss": 0.0, "step": 51 }, { "epoch": 0.019124678190511217, "grad_norm": NaN, "learning_rate": 5.522642316338268e-05, "loss": 0.0, "step": 52 }, { "epoch": 0.019492460463405664, "grad_norm": NaN, "learning_rate": 5.348782368720626e-05, "loss": 0.0, "step": 53 }, { "epoch": 0.01986024273630011, "grad_norm": NaN, "learning_rate": 5.174497483512506e-05, "loss": 0.0, "step": 54 }, { "epoch": 0.01986024273630011, "eval_loss": NaN, "eval_runtime": 270.6755, "eval_samples_per_second": 8.46, "eval_steps_per_second": 1.06, "step": 54 }, { "epoch": 0.02022802500919456, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 55 }, { "epoch": 0.020595807282089002, "grad_norm": NaN, "learning_rate": 4.825502516487497e-05, "loss": 0.0, "step": 56 }, { "epoch": 0.02096358955498345, "grad_norm": NaN, "learning_rate": 4.6512176312793736e-05, "loss": 0.0, "step": 57 }, { "epoch": 0.021331371827877896, "grad_norm": NaN, "learning_rate": 4.477357683661734e-05, "loss": 0.0, "step": 58 }, { "epoch": 0.021699154100772344, "grad_norm": NaN, "learning_rate": 4.3041344951996746e-05, "loss": 0.0, "step": 59 }, { "epoch": 0.02206693637366679, "grad_norm": NaN, "learning_rate": 4.131759111665349e-05, "loss": 0.0, "step": 60 }, { "epoch": 0.022434718646561234, "grad_norm": NaN, "learning_rate": 3.960441545911204e-05, "loss": 0.0, "step": 61 }, { "epoch": 0.02280250091945568, "grad_norm": NaN, "learning_rate": 3.790390522001662e-05, "loss": 0.0, "step": 62 }, { "epoch": 0.02317028319235013, "grad_norm": NaN, "learning_rate": 3.6218132209150045e-05, "loss": 0.0, "step": 63 }, { "epoch": 0.02317028319235013, "eval_loss": NaN, "eval_runtime": 270.6111, "eval_samples_per_second": 8.462, "eval_steps_per_second": 1.061, "step": 63 }, { "epoch": 0.023538065465244576, "grad_norm": NaN, "learning_rate": 3.4549150281252636e-05, "loss": 0.0, "step": 64 }, { "epoch": 0.023905847738139023, "grad_norm": NaN, "learning_rate": 3.289899283371657e-05, "loss": 0.0, "step": 65 }, { "epoch": 0.024273630011033467, "grad_norm": NaN, "learning_rate": 3.12696703292044e-05, "loss": 0.0, "step": 66 }, { "epoch": 0.024641412283927914, "grad_norm": NaN, "learning_rate": 2.9663167846209998e-05, "loss": 0.0, "step": 67 }, { "epoch": 0.02500919455682236, "grad_norm": NaN, "learning_rate": 2.8081442660546125e-05, "loss": 0.0, "step": 68 }, { "epoch": 0.025376976829716808, "grad_norm": NaN, "learning_rate": 2.6526421860705473e-05, "loss": 0.0, "step": 69 }, { "epoch": 0.025744759102611255, "grad_norm": NaN, "learning_rate": 2.500000000000001e-05, "loss": 0.0, "step": 70 }, { "epoch": 0.0261125413755057, "grad_norm": NaN, "learning_rate": 2.350403678833976e-05, "loss": 0.0, "step": 71 }, { "epoch": 0.026480323648400146, "grad_norm": NaN, "learning_rate": 2.2040354826462668e-05, "loss": 0.0, "step": 72 }, { "epoch": 0.026480323648400146, "eval_loss": NaN, "eval_runtime": 270.8675, "eval_samples_per_second": 8.454, "eval_steps_per_second": 1.06, "step": 72 }, { "epoch": 0.026848105921294593, "grad_norm": NaN, "learning_rate": 2.061073738537635e-05, "loss": 0.0, "step": 73 }, { "epoch": 0.02721588819418904, "grad_norm": NaN, "learning_rate": 1.9216926233717085e-05, "loss": 0.0, "step": 74 }, { "epoch": 0.027583670467083488, "grad_norm": NaN, "learning_rate": 1.7860619515673033e-05, "loss": 0.0, "step": 75 }, { "epoch": 0.027951452739977935, "grad_norm": NaN, "learning_rate": 1.6543469682057106e-05, "loss": 0.0, "step": 76 }, { "epoch": 0.02831923501287238, "grad_norm": NaN, "learning_rate": 1.526708147705013e-05, "loss": 0.0, "step": 77 }, { "epoch": 0.028687017285766826, "grad_norm": NaN, "learning_rate": 1.4033009983067452e-05, "loss": 0.0, "step": 78 }, { "epoch": 0.029054799558661273, "grad_norm": NaN, "learning_rate": 1.2842758726130283e-05, "loss": 0.0, "step": 79 }, { "epoch": 0.02942258183155572, "grad_norm": NaN, "learning_rate": 1.1697777844051105e-05, "loss": 0.0, "step": 80 }, { "epoch": 0.029790364104450167, "grad_norm": NaN, "learning_rate": 1.0599462319663905e-05, "loss": 0.0, "step": 81 }, { "epoch": 0.029790364104450167, "eval_loss": NaN, "eval_runtime": 270.7697, "eval_samples_per_second": 8.457, "eval_steps_per_second": 1.06, "step": 81 }, { "epoch": 0.03015814637734461, "grad_norm": NaN, "learning_rate": 9.549150281252633e-06, "loss": 0.0, "step": 82 }, { "epoch": 0.030525928650239058, "grad_norm": NaN, "learning_rate": 8.548121372247918e-06, "loss": 0.0, "step": 83 }, { "epoch": 0.030893710923133505, "grad_norm": NaN, "learning_rate": 7.597595192178702e-06, "loss": 0.0, "step": 84 }, { "epoch": 0.03126149319602795, "grad_norm": NaN, "learning_rate": 6.698729810778065e-06, "loss": 0.0, "step": 85 }, { "epoch": 0.0316292754689224, "grad_norm": NaN, "learning_rate": 5.852620357053651e-06, "loss": 0.0, "step": 86 }, { "epoch": 0.031997057741816846, "grad_norm": NaN, "learning_rate": 5.060297685041659e-06, "loss": 0.0, "step": 87 }, { "epoch": 0.032364840014711294, "grad_norm": NaN, "learning_rate": 4.322727117869951e-06, "loss": 0.0, "step": 88 }, { "epoch": 0.03273262228760574, "grad_norm": NaN, "learning_rate": 3.6408072716606346e-06, "loss": 0.0, "step": 89 }, { "epoch": 0.03310040456050018, "grad_norm": NaN, "learning_rate": 3.0153689607045845e-06, "loss": 0.0, "step": 90 }, { "epoch": 0.03310040456050018, "eval_loss": NaN, "eval_runtime": 270.6404, "eval_samples_per_second": 8.461, "eval_steps_per_second": 1.06, "step": 90 }, { "epoch": 0.03346818683339463, "grad_norm": NaN, "learning_rate": 2.4471741852423237e-06, "loss": 0.0, "step": 91 }, { "epoch": 0.033835969106289075, "grad_norm": NaN, "learning_rate": 1.9369152030840556e-06, "loss": 0.0, "step": 92 }, { "epoch": 0.03420375137918352, "grad_norm": NaN, "learning_rate": 1.4852136862001764e-06, "loss": 0.0, "step": 93 }, { "epoch": 0.03457153365207797, "grad_norm": NaN, "learning_rate": 1.0926199633097157e-06, "loss": 0.0, "step": 94 }, { "epoch": 0.03493931592497242, "grad_norm": NaN, "learning_rate": 7.596123493895991e-07, "loss": 0.0, "step": 95 }, { "epoch": 0.035307098197866864, "grad_norm": NaN, "learning_rate": 4.865965629214819e-07, "loss": 0.0, "step": 96 }, { "epoch": 0.03567488047076131, "grad_norm": NaN, "learning_rate": 2.7390523158633554e-07, "loss": 0.0, "step": 97 }, { "epoch": 0.03604266274365576, "grad_norm": NaN, "learning_rate": 1.2179748700879012e-07, "loss": 0.0, "step": 98 }, { "epoch": 0.036410445016550205, "grad_norm": NaN, "learning_rate": 3.04586490452119e-08, "loss": 0.0, "step": 99 }, { "epoch": 0.036410445016550205, "eval_loss": NaN, "eval_runtime": 270.6588, "eval_samples_per_second": 8.461, "eval_steps_per_second": 1.06, "step": 99 }, { "epoch": 0.036778227289444645, "grad_norm": NaN, "learning_rate": 0.0, "loss": 0.0, "step": 100 } ], "logging_steps": 1, "max_steps": 100, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 25, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 7.641439020672614e+16, "train_batch_size": 8, "trial_name": null, "trial_params": null }