| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 268, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.018656716417910446, | |
| "grad_norm": 7.992456557616748, | |
| "learning_rate": 1.785714285714286e-05, | |
| "loss": 3.3955, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03731343283582089, | |
| "grad_norm": 3.4968199831167857, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 3.0816, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.055970149253731345, | |
| "grad_norm": 2.968125450447822, | |
| "learning_rate": 4.999827900623038e-05, | |
| "loss": 2.804, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07462686567164178, | |
| "grad_norm": 2.588497606835322, | |
| "learning_rate": 4.993807186343243e-05, | |
| "loss": 2.6908, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09328358208955224, | |
| "grad_norm": 2.549871368666643, | |
| "learning_rate": 4.979207812402531e-05, | |
| "loss": 2.5652, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11194029850746269, | |
| "grad_norm": 1.9738305926810327, | |
| "learning_rate": 4.956085596012407e-05, | |
| "loss": 2.5363, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13059701492537312, | |
| "grad_norm": 2.3251077114713885, | |
| "learning_rate": 4.924528939432311e-05, | |
| "loss": 2.4766, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.14925373134328357, | |
| "grad_norm": 2.764973986868281, | |
| "learning_rate": 4.884658491984735e-05, | |
| "loss": 2.4402, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.16791044776119404, | |
| "grad_norm": 1.9523889288733327, | |
| "learning_rate": 4.8366266887814235e-05, | |
| "loss": 2.4491, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1865671641791045, | |
| "grad_norm": 1.9187589431371008, | |
| "learning_rate": 4.780617167924209e-05, | |
| "loss": 2.3786, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.20522388059701493, | |
| "grad_norm": 1.9304839973674266, | |
| "learning_rate": 4.716844068408693e-05, | |
| "loss": 2.3897, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.22388059701492538, | |
| "grad_norm": 2.8003484835380372, | |
| "learning_rate": 4.6455512114150546e-05, | |
| "loss": 2.3704, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.24253731343283583, | |
| "grad_norm": 1.5013907534892832, | |
| "learning_rate": 4.5670111681161296e-05, | |
| "loss": 2.3343, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.26119402985074625, | |
| "grad_norm": 2.9773909499359377, | |
| "learning_rate": 4.481524217566783e-05, | |
| "loss": 2.3199, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.2798507462686567, | |
| "grad_norm": 4.2665640456752785, | |
| "learning_rate": 4.3894171986588217e-05, | |
| "loss": 2.3193, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.29850746268656714, | |
| "grad_norm": 1.9307726906007678, | |
| "learning_rate": 4.29104226053073e-05, | |
| "loss": 2.322, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.31716417910447764, | |
| "grad_norm": 2.237168079938654, | |
| "learning_rate": 4.186775516209732e-05, | |
| "loss": 2.3077, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.3358208955223881, | |
| "grad_norm": 2.901386689863122, | |
| "learning_rate": 4.077015604633669e-05, | |
| "loss": 2.3101, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.35447761194029853, | |
| "grad_norm": 2.5210971167889245, | |
| "learning_rate": 3.962182166550441e-05, | |
| "loss": 2.3042, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.373134328358209, | |
| "grad_norm": 2.6070376003561933, | |
| "learning_rate": 3.8427142401220634e-05, | |
| "loss": 2.2873, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3917910447761194, | |
| "grad_norm": 2.2004757384840152, | |
| "learning_rate": 3.71906858236735e-05, | |
| "loss": 2.2728, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.41044776119402987, | |
| "grad_norm": 2.1473625420095868, | |
| "learning_rate": 3.591717922860785e-05, | |
| "loss": 2.2999, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.4291044776119403, | |
| "grad_norm": 1.4790945776347835, | |
| "learning_rate": 3.46114915636416e-05, | |
| "loss": 2.2623, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.44776119402985076, | |
| "grad_norm": 1.4602444685381062, | |
| "learning_rate": 3.3278614813010034e-05, | |
| "loss": 2.2668, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.4664179104477612, | |
| "grad_norm": 1.3383920889270082, | |
| "learning_rate": 3.1923644911909e-05, | |
| "loss": 2.2541, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.48507462686567165, | |
| "grad_norm": 1.6295501707411197, | |
| "learning_rate": 3.0551762263406576e-05, | |
| "loss": 2.2505, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.503731343283582, | |
| "grad_norm": 1.5700164012256488, | |
| "learning_rate": 2.9168211932412042e-05, | |
| "loss": 2.2392, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.5223880597014925, | |
| "grad_norm": 1.3183550705568836, | |
| "learning_rate": 2.777828359242567e-05, | |
| "loss": 2.26, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.5410447761194029, | |
| "grad_norm": 1.270837720420853, | |
| "learning_rate": 2.6387291301738377e-05, | |
| "loss": 2.2291, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.5597014925373134, | |
| "grad_norm": 1.2360031288329183, | |
| "learning_rate": 2.50005531864019e-05, | |
| "loss": 2.2191, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.5783582089552238, | |
| "grad_norm": 1.4058327877557197, | |
| "learning_rate": 2.362337110764688e-05, | |
| "loss": 2.2201, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.5970149253731343, | |
| "grad_norm": 1.1447309950598807, | |
| "learning_rate": 2.226101039148557e-05, | |
| "loss": 2.212, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.6156716417910447, | |
| "grad_norm": 1.2920928760986912, | |
| "learning_rate": 2.0918679697998252e-05, | |
| "loss": 2.2068, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.6343283582089553, | |
| "grad_norm": 1.3303686169767341, | |
| "learning_rate": 1.9601511107268255e-05, | |
| "loss": 2.208, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.6529850746268657, | |
| "grad_norm": 1.0982459829577405, | |
| "learning_rate": 1.8314540498102216e-05, | |
| "loss": 2.205, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.6716417910447762, | |
| "grad_norm": 1.2297852411953294, | |
| "learning_rate": 1.7062688294552992e-05, | |
| "loss": 2.1727, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.6902985074626866, | |
| "grad_norm": 1.0412249297641412, | |
| "learning_rate": 1.5850740653856096e-05, | |
| "loss": 2.1852, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.7089552238805971, | |
| "grad_norm": 1.2871807028686466, | |
| "learning_rate": 1.4683331167703218e-05, | |
| "loss": 2.199, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.7276119402985075, | |
| "grad_norm": 1.2102977879839474, | |
| "learning_rate": 1.356492314681356e-05, | |
| "loss": 2.2087, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.746268656716418, | |
| "grad_norm": 0.9891067478501752, | |
| "learning_rate": 1.2499792556533716e-05, | |
| "loss": 2.1852, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.7649253731343284, | |
| "grad_norm": 0.8301326918730746, | |
| "learning_rate": 1.1492011668707753e-05, | |
| "loss": 2.1736, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.7835820895522388, | |
| "grad_norm": 0.7981204348651115, | |
| "learning_rate": 1.0545433492320603e-05, | |
| "loss": 2.1941, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.8022388059701493, | |
| "grad_norm": 0.9338161168132167, | |
| "learning_rate": 9.663677042440537e-06, | |
| "loss": 2.1702, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.8208955223880597, | |
| "grad_norm": 0.8537076459178821, | |
| "learning_rate": 8.850113503781367e-06, | |
| "loss": 2.169, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.8395522388059702, | |
| "grad_norm": 0.8531025855292982, | |
| "learning_rate": 8.107853341784671e-06, | |
| "loss": 2.1934, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.8582089552238806, | |
| "grad_norm": 0.7887299648309287, | |
| "learning_rate": 7.439734410499752e-06, | |
| "loss": 2.1789, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.8768656716417911, | |
| "grad_norm": 0.7325960398919809, | |
| "learning_rate": 6.848311102728011e-06, | |
| "loss": 2.179, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.8955223880597015, | |
| "grad_norm": 0.8564233439601584, | |
| "learning_rate": 6.335844583913515e-06, | |
| "loss": 2.1635, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.914179104477612, | |
| "grad_norm": 0.9533929441227149, | |
| "learning_rate": 5.904294147118193e-06, | |
| "loss": 2.1775, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.9328358208955224, | |
| "grad_norm": 0.713300332791207, | |
| "learning_rate": 5.555309722133842e-06, | |
| "loss": 2.1629, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.9514925373134329, | |
| "grad_norm": 0.7316453284294552, | |
| "learning_rate": 5.290225567370509e-06, | |
| "loss": 2.1478, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.9701492537313433, | |
| "grad_norm": 0.6667774680701307, | |
| "learning_rate": 5.110055168638854e-06, | |
| "loss": 2.1616, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.9888059701492538, | |
| "grad_norm": 0.7087383615740679, | |
| "learning_rate": 5.0154873643297575e-06, | |
| "loss": 2.1761, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 268, | |
| "total_flos": 126040110268416.0, | |
| "train_loss": 2.3174947375681865, | |
| "train_runtime": 34132.5347, | |
| "train_samples_per_second": 1.005, | |
| "train_steps_per_second": 0.008 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 268, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 126040110268416.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |