| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.3956043956043956, |
| "eval_steps": 500, |
| "global_step": 60, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.006593406593406593, |
| "grad_norm": 1.195170283317566, |
| "learning_rate": 0.0, |
| "loss": 1.0821, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.013186813186813187, |
| "grad_norm": 1.0331945419311523, |
| "learning_rate": 9.56e-05, |
| "loss": 1.0763, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.01978021978021978, |
| "grad_norm": 1.1415084600448608, |
| "learning_rate": 0.0001912, |
| "loss": 1.0495, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.026373626373626374, |
| "grad_norm": 1.063579797744751, |
| "learning_rate": 0.0002868, |
| "loss": 0.956, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.03296703296703297, |
| "grad_norm": 0.6625626087188721, |
| "learning_rate": 0.0003824, |
| "loss": 0.8477, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.03956043956043956, |
| "grad_norm": 0.6782878637313843, |
| "learning_rate": 0.000478, |
| "loss": 1.0343, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.046153846153846156, |
| "grad_norm": 0.6161335110664368, |
| "learning_rate": 0.00047694013303769406, |
| "loss": 0.9727, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.05274725274725275, |
| "grad_norm": 0.41984498500823975, |
| "learning_rate": 0.00047588026607538804, |
| "loss": 0.8698, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.05934065934065934, |
| "grad_norm": 0.3116914927959442, |
| "learning_rate": 0.0004748203991130821, |
| "loss": 0.8446, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.06593406593406594, |
| "grad_norm": 0.29025012254714966, |
| "learning_rate": 0.00047376053215077607, |
| "loss": 0.7877, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.07252747252747253, |
| "grad_norm": 0.39959046244621277, |
| "learning_rate": 0.00047270066518847006, |
| "loss": 0.8688, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.07912087912087912, |
| "grad_norm": 0.5689778923988342, |
| "learning_rate": 0.0004716407982261641, |
| "loss": 0.8847, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.08571428571428572, |
| "grad_norm": 0.40798476338386536, |
| "learning_rate": 0.00047058093126385814, |
| "loss": 0.7254, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.09230769230769231, |
| "grad_norm": 0.6968982219696045, |
| "learning_rate": 0.0004695210643015521, |
| "loss": 0.8179, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.0989010989010989, |
| "grad_norm": 0.5194700360298157, |
| "learning_rate": 0.00046846119733924617, |
| "loss": 0.7156, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.1054945054945055, |
| "grad_norm": 0.43927809596061707, |
| "learning_rate": 0.00046740133037694015, |
| "loss": 0.8273, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.11208791208791209, |
| "grad_norm": 0.3979283571243286, |
| "learning_rate": 0.00046634146341463414, |
| "loss": 0.7288, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.11868131868131868, |
| "grad_norm": 0.4314859211444855, |
| "learning_rate": 0.0004652815964523282, |
| "loss": 0.7677, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.12527472527472527, |
| "grad_norm": 0.3548160791397095, |
| "learning_rate": 0.0004642217294900222, |
| "loss": 0.6472, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.13186813186813187, |
| "grad_norm": 0.38769328594207764, |
| "learning_rate": 0.0004631618625277162, |
| "loss": 0.6578, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.13846153846153847, |
| "grad_norm": 0.3017254173755646, |
| "learning_rate": 0.00046210199556541025, |
| "loss": 0.7163, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.14505494505494507, |
| "grad_norm": 0.33315712213516235, |
| "learning_rate": 0.00046104212860310423, |
| "loss": 0.6951, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.15164835164835164, |
| "grad_norm": 0.3334329426288605, |
| "learning_rate": 0.0004599822616407982, |
| "loss": 0.7464, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.15824175824175823, |
| "grad_norm": 0.301981121301651, |
| "learning_rate": 0.00045892239467849226, |
| "loss": 0.667, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.16483516483516483, |
| "grad_norm": 0.3768517076969147, |
| "learning_rate": 0.0004578625277161863, |
| "loss": 0.6719, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.17142857142857143, |
| "grad_norm": 0.3810518980026245, |
| "learning_rate": 0.0004568026607538803, |
| "loss": 0.7687, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.17802197802197803, |
| "grad_norm": 0.4689561128616333, |
| "learning_rate": 0.00045574279379157433, |
| "loss": 0.7114, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.18461538461538463, |
| "grad_norm": 0.3895481824874878, |
| "learning_rate": 0.00045468292682926826, |
| "loss": 0.7328, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.1912087912087912, |
| "grad_norm": 0.44972071051597595, |
| "learning_rate": 0.0004536230598669623, |
| "loss": 0.708, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.1978021978021978, |
| "grad_norm": 0.39502742886543274, |
| "learning_rate": 0.00045256319290465634, |
| "loss": 0.7672, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.2043956043956044, |
| "grad_norm": 0.5479147434234619, |
| "learning_rate": 0.00045150332594235033, |
| "loss": 0.7583, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.210989010989011, |
| "grad_norm": 0.33382317423820496, |
| "learning_rate": 0.00045044345898004437, |
| "loss": 0.7369, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.2175824175824176, |
| "grad_norm": 0.49583446979522705, |
| "learning_rate": 0.0004493835920177384, |
| "loss": 0.8174, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.22417582417582418, |
| "grad_norm": 0.3855836093425751, |
| "learning_rate": 0.00044832372505543234, |
| "loss": 0.7935, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.23076923076923078, |
| "grad_norm": 0.45332643389701843, |
| "learning_rate": 0.0004472638580931264, |
| "loss": 0.7593, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.23736263736263735, |
| "grad_norm": 0.3067397475242615, |
| "learning_rate": 0.0004462039911308204, |
| "loss": 0.6878, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.24395604395604395, |
| "grad_norm": 0.3372962474822998, |
| "learning_rate": 0.0004451441241685144, |
| "loss": 0.7705, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.25054945054945055, |
| "grad_norm": 0.40445494651794434, |
| "learning_rate": 0.00044408425720620845, |
| "loss": 0.7849, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.2571428571428571, |
| "grad_norm": 0.3279916048049927, |
| "learning_rate": 0.0004430243902439025, |
| "loss": 0.715, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.26373626373626374, |
| "grad_norm": 0.31464719772338867, |
| "learning_rate": 0.0004419645232815964, |
| "loss": 0.7322, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.2703296703296703, |
| "grad_norm": 0.27914178371429443, |
| "learning_rate": 0.00044090465631929047, |
| "loss": 0.6922, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.27692307692307694, |
| "grad_norm": 0.27055102586746216, |
| "learning_rate": 0.0004398447893569845, |
| "loss": 0.7071, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.2835164835164835, |
| "grad_norm": 0.30358147621154785, |
| "learning_rate": 0.0004387849223946785, |
| "loss": 0.7257, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.29010989010989013, |
| "grad_norm": 0.3098717927932739, |
| "learning_rate": 0.00043772505543237253, |
| "loss": 0.6871, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.2967032967032967, |
| "grad_norm": 0.32566770911216736, |
| "learning_rate": 0.0004366651884700666, |
| "loss": 0.7264, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.3032967032967033, |
| "grad_norm": 0.3617362082004547, |
| "learning_rate": 0.0004356053215077605, |
| "loss": 0.6902, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.3098901098901099, |
| "grad_norm": 0.43403375148773193, |
| "learning_rate": 0.00043454545454545455, |
| "loss": 0.7037, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.31648351648351647, |
| "grad_norm": 0.33475279808044434, |
| "learning_rate": 0.0004334855875831486, |
| "loss": 0.7261, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.3230769230769231, |
| "grad_norm": 0.34020453691482544, |
| "learning_rate": 0.0004324257206208426, |
| "loss": 0.6361, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.32967032967032966, |
| "grad_norm": 0.29145631194114685, |
| "learning_rate": 0.0004313658536585366, |
| "loss": 0.6797, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.3362637362637363, |
| "grad_norm": 0.35258740186691284, |
| "learning_rate": 0.00043030598669623066, |
| "loss": 0.6811, |
| "step": 51 |
| }, |
| { |
| "epoch": 0.34285714285714286, |
| "grad_norm": 0.31551578640937805, |
| "learning_rate": 0.0004292461197339246, |
| "loss": 0.6662, |
| "step": 52 |
| }, |
| { |
| "epoch": 0.34945054945054943, |
| "grad_norm": 0.40033137798309326, |
| "learning_rate": 0.00042818625277161863, |
| "loss": 0.7066, |
| "step": 53 |
| }, |
| { |
| "epoch": 0.35604395604395606, |
| "grad_norm": 0.34928882122039795, |
| "learning_rate": 0.00042712638580931267, |
| "loss": 0.6704, |
| "step": 54 |
| }, |
| { |
| "epoch": 0.3626373626373626, |
| "grad_norm": 0.3890458345413208, |
| "learning_rate": 0.00042606651884700666, |
| "loss": 0.7074, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.36923076923076925, |
| "grad_norm": 0.34585464000701904, |
| "learning_rate": 0.0004250066518847007, |
| "loss": 0.7147, |
| "step": 56 |
| }, |
| { |
| "epoch": 0.3758241758241758, |
| "grad_norm": 0.2896708548069, |
| "learning_rate": 0.00042394678492239474, |
| "loss": 0.7679, |
| "step": 57 |
| }, |
| { |
| "epoch": 0.3824175824175824, |
| "grad_norm": 0.3353179395198822, |
| "learning_rate": 0.00042288691796008867, |
| "loss": 0.6415, |
| "step": 58 |
| }, |
| { |
| "epoch": 0.389010989010989, |
| "grad_norm": 0.32367175817489624, |
| "learning_rate": 0.0004218270509977827, |
| "loss": 0.7697, |
| "step": 59 |
| }, |
| { |
| "epoch": 0.3956043956043956, |
| "grad_norm": 0.32652848958969116, |
| "learning_rate": 0.00042076718403547675, |
| "loss": 0.6835, |
| "step": 60 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 456, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 15, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.755917642343219e+16, |
| "train_batch_size": 22, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
