lesso06's picture
Training in progress, step 100, checkpoint
0436ea4 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.006476474207441469,
"eval_steps": 9,
"global_step": 100,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 6.476474207441469e-05,
"grad_norm": NaN,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 1
},
{
"epoch": 6.476474207441469e-05,
"eval_loss": NaN,
"eval_runtime": 2478.3515,
"eval_samples_per_second": 5.247,
"eval_steps_per_second": 0.656,
"step": 1
},
{
"epoch": 0.00012952948414882937,
"grad_norm": NaN,
"learning_rate": 2e-05,
"loss": 0.0,
"step": 2
},
{
"epoch": 0.00019429422622324407,
"grad_norm": NaN,
"learning_rate": 3e-05,
"loss": 0.0,
"step": 3
},
{
"epoch": 0.00025905896829765874,
"grad_norm": NaN,
"learning_rate": 4e-05,
"loss": 0.0,
"step": 4
},
{
"epoch": 0.00032382371037207344,
"grad_norm": NaN,
"learning_rate": 5e-05,
"loss": 0.0,
"step": 5
},
{
"epoch": 0.00038858845244648814,
"grad_norm": NaN,
"learning_rate": 6e-05,
"loss": 0.0,
"step": 6
},
{
"epoch": 0.00045335319452090284,
"grad_norm": NaN,
"learning_rate": 7e-05,
"loss": 0.0,
"step": 7
},
{
"epoch": 0.0005181179365953175,
"grad_norm": NaN,
"learning_rate": 8e-05,
"loss": 0.0,
"step": 8
},
{
"epoch": 0.0005828826786697322,
"grad_norm": NaN,
"learning_rate": 9e-05,
"loss": 0.0,
"step": 9
},
{
"epoch": 0.0005828826786697322,
"eval_loss": NaN,
"eval_runtime": 2478.6563,
"eval_samples_per_second": 5.246,
"eval_steps_per_second": 0.656,
"step": 9
},
{
"epoch": 0.0006476474207441469,
"grad_norm": NaN,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 10
},
{
"epoch": 0.0007124121628185615,
"grad_norm": NaN,
"learning_rate": 9.99695413509548e-05,
"loss": 0.0,
"step": 11
},
{
"epoch": 0.0007771769048929763,
"grad_norm": NaN,
"learning_rate": 9.987820251299122e-05,
"loss": 0.0,
"step": 12
},
{
"epoch": 0.0008419416469673909,
"grad_norm": NaN,
"learning_rate": 9.972609476841367e-05,
"loss": 0.0,
"step": 13
},
{
"epoch": 0.0009067063890418057,
"grad_norm": NaN,
"learning_rate": 9.951340343707852e-05,
"loss": 0.0,
"step": 14
},
{
"epoch": 0.0009714711311162203,
"grad_norm": NaN,
"learning_rate": 9.924038765061042e-05,
"loss": 0.0,
"step": 15
},
{
"epoch": 0.001036235873190635,
"grad_norm": NaN,
"learning_rate": 9.890738003669029e-05,
"loss": 0.0,
"step": 16
},
{
"epoch": 0.0011010006152650496,
"grad_norm": NaN,
"learning_rate": 9.851478631379982e-05,
"loss": 0.0,
"step": 17
},
{
"epoch": 0.0011657653573394645,
"grad_norm": NaN,
"learning_rate": 9.806308479691595e-05,
"loss": 0.0,
"step": 18
},
{
"epoch": 0.0011657653573394645,
"eval_loss": NaN,
"eval_runtime": 2475.9679,
"eval_samples_per_second": 5.252,
"eval_steps_per_second": 0.657,
"step": 18
},
{
"epoch": 0.0012305300994138791,
"grad_norm": NaN,
"learning_rate": 9.755282581475769e-05,
"loss": 0.0,
"step": 19
},
{
"epoch": 0.0012952948414882938,
"grad_norm": NaN,
"learning_rate": 9.698463103929542e-05,
"loss": 0.0,
"step": 20
},
{
"epoch": 0.0013600595835627084,
"grad_norm": NaN,
"learning_rate": 9.635919272833938e-05,
"loss": 0.0,
"step": 21
},
{
"epoch": 0.001424824325637123,
"grad_norm": NaN,
"learning_rate": 9.567727288213005e-05,
"loss": 0.0,
"step": 22
},
{
"epoch": 0.001489589067711538,
"grad_norm": NaN,
"learning_rate": 9.493970231495835e-05,
"loss": 0.0,
"step": 23
},
{
"epoch": 0.0015543538097859526,
"grad_norm": NaN,
"learning_rate": 9.414737964294636e-05,
"loss": 0.0,
"step": 24
},
{
"epoch": 0.0016191185518603672,
"grad_norm": NaN,
"learning_rate": 9.330127018922194e-05,
"loss": 0.0,
"step": 25
},
{
"epoch": 0.0016838832939347818,
"grad_norm": NaN,
"learning_rate": 9.24024048078213e-05,
"loss": 0.0,
"step": 26
},
{
"epoch": 0.0017486480360091965,
"grad_norm": NaN,
"learning_rate": 9.145187862775209e-05,
"loss": 0.0,
"step": 27
},
{
"epoch": 0.0017486480360091965,
"eval_loss": NaN,
"eval_runtime": 2474.8974,
"eval_samples_per_second": 5.254,
"eval_steps_per_second": 0.657,
"step": 27
},
{
"epoch": 0.0018134127780836114,
"grad_norm": NaN,
"learning_rate": 9.045084971874738e-05,
"loss": 0.0,
"step": 28
},
{
"epoch": 0.001878177520158026,
"grad_norm": NaN,
"learning_rate": 8.940053768033609e-05,
"loss": 0.0,
"step": 29
},
{
"epoch": 0.0019429422622324406,
"grad_norm": NaN,
"learning_rate": 8.83022221559489e-05,
"loss": 0.0,
"step": 30
},
{
"epoch": 0.0020077070043068553,
"grad_norm": NaN,
"learning_rate": 8.715724127386972e-05,
"loss": 0.0,
"step": 31
},
{
"epoch": 0.00207247174638127,
"grad_norm": NaN,
"learning_rate": 8.596699001693255e-05,
"loss": 0.0,
"step": 32
},
{
"epoch": 0.0021372364884556846,
"grad_norm": NaN,
"learning_rate": 8.473291852294987e-05,
"loss": 0.0,
"step": 33
},
{
"epoch": 0.0022020012305300992,
"grad_norm": NaN,
"learning_rate": 8.345653031794292e-05,
"loss": 0.0,
"step": 34
},
{
"epoch": 0.0022667659726045143,
"grad_norm": NaN,
"learning_rate": 8.213938048432697e-05,
"loss": 0.0,
"step": 35
},
{
"epoch": 0.002331530714678929,
"grad_norm": NaN,
"learning_rate": 8.07830737662829e-05,
"loss": 0.0,
"step": 36
},
{
"epoch": 0.002331530714678929,
"eval_loss": NaN,
"eval_runtime": 2476.0087,
"eval_samples_per_second": 5.252,
"eval_steps_per_second": 0.657,
"step": 36
},
{
"epoch": 0.0023962954567533436,
"grad_norm": NaN,
"learning_rate": 7.938926261462366e-05,
"loss": 0.0,
"step": 37
},
{
"epoch": 0.0024610601988277582,
"grad_norm": NaN,
"learning_rate": 7.795964517353735e-05,
"loss": 0.0,
"step": 38
},
{
"epoch": 0.002525824940902173,
"grad_norm": NaN,
"learning_rate": 7.649596321166024e-05,
"loss": 0.0,
"step": 39
},
{
"epoch": 0.0025905896829765875,
"grad_norm": NaN,
"learning_rate": 7.500000000000001e-05,
"loss": 0.0,
"step": 40
},
{
"epoch": 0.002655354425051002,
"grad_norm": NaN,
"learning_rate": 7.347357813929454e-05,
"loss": 0.0,
"step": 41
},
{
"epoch": 0.002720119167125417,
"grad_norm": NaN,
"learning_rate": 7.191855733945387e-05,
"loss": 0.0,
"step": 42
},
{
"epoch": 0.0027848839091998315,
"grad_norm": NaN,
"learning_rate": 7.033683215379002e-05,
"loss": 0.0,
"step": 43
},
{
"epoch": 0.002849648651274246,
"grad_norm": NaN,
"learning_rate": 6.873032967079561e-05,
"loss": 0.0,
"step": 44
},
{
"epoch": 0.002914413393348661,
"grad_norm": NaN,
"learning_rate": 6.710100716628344e-05,
"loss": 0.0,
"step": 45
},
{
"epoch": 0.002914413393348661,
"eval_loss": NaN,
"eval_runtime": 2476.225,
"eval_samples_per_second": 5.251,
"eval_steps_per_second": 0.657,
"step": 45
},
{
"epoch": 0.002979178135423076,
"grad_norm": NaN,
"learning_rate": 6.545084971874738e-05,
"loss": 0.0,
"step": 46
},
{
"epoch": 0.0030439428774974905,
"grad_norm": NaN,
"learning_rate": 6.378186779084995e-05,
"loss": 0.0,
"step": 47
},
{
"epoch": 0.003108707619571905,
"grad_norm": NaN,
"learning_rate": 6.209609477998338e-05,
"loss": 0.0,
"step": 48
},
{
"epoch": 0.0031734723616463198,
"grad_norm": NaN,
"learning_rate": 6.0395584540887963e-05,
"loss": 0.0,
"step": 49
},
{
"epoch": 0.0032382371037207344,
"grad_norm": NaN,
"learning_rate": 5.868240888334653e-05,
"loss": 0.0,
"step": 50
},
{
"epoch": 0.003303001845795149,
"grad_norm": NaN,
"learning_rate": 5.695865504800327e-05,
"loss": 0.0,
"step": 51
},
{
"epoch": 0.0033677665878695637,
"grad_norm": NaN,
"learning_rate": 5.522642316338268e-05,
"loss": 0.0,
"step": 52
},
{
"epoch": 0.0034325313299439783,
"grad_norm": NaN,
"learning_rate": 5.348782368720626e-05,
"loss": 0.0,
"step": 53
},
{
"epoch": 0.003497296072018393,
"grad_norm": NaN,
"learning_rate": 5.174497483512506e-05,
"loss": 0.0,
"step": 54
},
{
"epoch": 0.003497296072018393,
"eval_loss": NaN,
"eval_runtime": 2475.6928,
"eval_samples_per_second": 5.252,
"eval_steps_per_second": 0.657,
"step": 54
},
{
"epoch": 0.003562060814092808,
"grad_norm": NaN,
"learning_rate": 5e-05,
"loss": 0.0,
"step": 55
},
{
"epoch": 0.0036268255561672227,
"grad_norm": NaN,
"learning_rate": 4.825502516487497e-05,
"loss": 0.0,
"step": 56
},
{
"epoch": 0.0036915902982416374,
"grad_norm": NaN,
"learning_rate": 4.6512176312793736e-05,
"loss": 0.0,
"step": 57
},
{
"epoch": 0.003756355040316052,
"grad_norm": NaN,
"learning_rate": 4.477357683661734e-05,
"loss": 0.0,
"step": 58
},
{
"epoch": 0.0038211197823904666,
"grad_norm": NaN,
"learning_rate": 4.3041344951996746e-05,
"loss": 0.0,
"step": 59
},
{
"epoch": 0.0038858845244648813,
"grad_norm": NaN,
"learning_rate": 4.131759111665349e-05,
"loss": 0.0,
"step": 60
},
{
"epoch": 0.003950649266539296,
"grad_norm": NaN,
"learning_rate": 3.960441545911204e-05,
"loss": 0.0,
"step": 61
},
{
"epoch": 0.004015414008613711,
"grad_norm": NaN,
"learning_rate": 3.790390522001662e-05,
"loss": 0.0,
"step": 62
},
{
"epoch": 0.004080178750688126,
"grad_norm": NaN,
"learning_rate": 3.6218132209150045e-05,
"loss": 0.0,
"step": 63
},
{
"epoch": 0.004080178750688126,
"eval_loss": NaN,
"eval_runtime": 2477.3204,
"eval_samples_per_second": 5.249,
"eval_steps_per_second": 0.656,
"step": 63
},
{
"epoch": 0.00414494349276254,
"grad_norm": NaN,
"learning_rate": 3.4549150281252636e-05,
"loss": 0.0,
"step": 64
},
{
"epoch": 0.004209708234836955,
"grad_norm": NaN,
"learning_rate": 3.289899283371657e-05,
"loss": 0.0,
"step": 65
},
{
"epoch": 0.004274472976911369,
"grad_norm": NaN,
"learning_rate": 3.12696703292044e-05,
"loss": 0.0,
"step": 66
},
{
"epoch": 0.004339237718985784,
"grad_norm": NaN,
"learning_rate": 2.9663167846209998e-05,
"loss": 0.0,
"step": 67
},
{
"epoch": 0.0044040024610601984,
"grad_norm": NaN,
"learning_rate": 2.8081442660546125e-05,
"loss": 0.0,
"step": 68
},
{
"epoch": 0.0044687672031346135,
"grad_norm": NaN,
"learning_rate": 2.6526421860705473e-05,
"loss": 0.0,
"step": 69
},
{
"epoch": 0.004533531945209029,
"grad_norm": NaN,
"learning_rate": 2.500000000000001e-05,
"loss": 0.0,
"step": 70
},
{
"epoch": 0.004598296687283443,
"grad_norm": NaN,
"learning_rate": 2.350403678833976e-05,
"loss": 0.0,
"step": 71
},
{
"epoch": 0.004663061429357858,
"grad_norm": NaN,
"learning_rate": 2.2040354826462668e-05,
"loss": 0.0,
"step": 72
},
{
"epoch": 0.004663061429357858,
"eval_loss": NaN,
"eval_runtime": 2477.5873,
"eval_samples_per_second": 5.248,
"eval_steps_per_second": 0.656,
"step": 72
},
{
"epoch": 0.004727826171432272,
"grad_norm": NaN,
"learning_rate": 2.061073738537635e-05,
"loss": 0.0,
"step": 73
},
{
"epoch": 0.004792590913506687,
"grad_norm": NaN,
"learning_rate": 1.9216926233717085e-05,
"loss": 0.0,
"step": 74
},
{
"epoch": 0.004857355655581101,
"grad_norm": NaN,
"learning_rate": 1.7860619515673033e-05,
"loss": 0.0,
"step": 75
},
{
"epoch": 0.0049221203976555165,
"grad_norm": NaN,
"learning_rate": 1.6543469682057106e-05,
"loss": 0.0,
"step": 76
},
{
"epoch": 0.004986885139729931,
"grad_norm": NaN,
"learning_rate": 1.526708147705013e-05,
"loss": 0.0,
"step": 77
},
{
"epoch": 0.005051649881804346,
"grad_norm": NaN,
"learning_rate": 1.4033009983067452e-05,
"loss": 0.0,
"step": 78
},
{
"epoch": 0.00511641462387876,
"grad_norm": NaN,
"learning_rate": 1.2842758726130283e-05,
"loss": 0.0,
"step": 79
},
{
"epoch": 0.005181179365953175,
"grad_norm": NaN,
"learning_rate": 1.1697777844051105e-05,
"loss": 0.0,
"step": 80
},
{
"epoch": 0.00524594410802759,
"grad_norm": NaN,
"learning_rate": 1.0599462319663905e-05,
"loss": 0.0,
"step": 81
},
{
"epoch": 0.00524594410802759,
"eval_loss": NaN,
"eval_runtime": 2478.6796,
"eval_samples_per_second": 5.246,
"eval_steps_per_second": 0.656,
"step": 81
},
{
"epoch": 0.005310708850102004,
"grad_norm": NaN,
"learning_rate": 9.549150281252633e-06,
"loss": 0.0,
"step": 82
},
{
"epoch": 0.005375473592176419,
"grad_norm": NaN,
"learning_rate": 8.548121372247918e-06,
"loss": 0.0,
"step": 83
},
{
"epoch": 0.005440238334250834,
"grad_norm": NaN,
"learning_rate": 7.597595192178702e-06,
"loss": 0.0,
"step": 84
},
{
"epoch": 0.005505003076325249,
"grad_norm": NaN,
"learning_rate": 6.698729810778065e-06,
"loss": 0.0,
"step": 85
},
{
"epoch": 0.005569767818399663,
"grad_norm": NaN,
"learning_rate": 5.852620357053651e-06,
"loss": 0.0,
"step": 86
},
{
"epoch": 0.005634532560474078,
"grad_norm": NaN,
"learning_rate": 5.060297685041659e-06,
"loss": 0.0,
"step": 87
},
{
"epoch": 0.005699297302548492,
"grad_norm": NaN,
"learning_rate": 4.322727117869951e-06,
"loss": 0.0,
"step": 88
},
{
"epoch": 0.005764062044622907,
"grad_norm": NaN,
"learning_rate": 3.6408072716606346e-06,
"loss": 0.0,
"step": 89
},
{
"epoch": 0.005828826786697322,
"grad_norm": NaN,
"learning_rate": 3.0153689607045845e-06,
"loss": 0.0,
"step": 90
},
{
"epoch": 0.005828826786697322,
"eval_loss": NaN,
"eval_runtime": 2477.0861,
"eval_samples_per_second": 5.249,
"eval_steps_per_second": 0.656,
"step": 90
},
{
"epoch": 0.005893591528771737,
"grad_norm": NaN,
"learning_rate": 2.4471741852423237e-06,
"loss": 0.0,
"step": 91
},
{
"epoch": 0.005958356270846152,
"grad_norm": NaN,
"learning_rate": 1.9369152030840556e-06,
"loss": 0.0,
"step": 92
},
{
"epoch": 0.006023121012920566,
"grad_norm": NaN,
"learning_rate": 1.4852136862001764e-06,
"loss": 0.0,
"step": 93
},
{
"epoch": 0.006087885754994981,
"grad_norm": NaN,
"learning_rate": 1.0926199633097157e-06,
"loss": 0.0,
"step": 94
},
{
"epoch": 0.006152650497069395,
"grad_norm": NaN,
"learning_rate": 7.596123493895991e-07,
"loss": 0.0,
"step": 95
},
{
"epoch": 0.00621741523914381,
"grad_norm": NaN,
"learning_rate": 4.865965629214819e-07,
"loss": 0.0,
"step": 96
},
{
"epoch": 0.0062821799812182244,
"grad_norm": NaN,
"learning_rate": 2.7390523158633554e-07,
"loss": 0.0,
"step": 97
},
{
"epoch": 0.0063469447232926395,
"grad_norm": NaN,
"learning_rate": 1.2179748700879012e-07,
"loss": 0.0,
"step": 98
},
{
"epoch": 0.006411709465367055,
"grad_norm": NaN,
"learning_rate": 3.04586490452119e-08,
"loss": 0.0,
"step": 99
},
{
"epoch": 0.006411709465367055,
"eval_loss": NaN,
"eval_runtime": 2475.2134,
"eval_samples_per_second": 5.253,
"eval_steps_per_second": 0.657,
"step": 99
},
{
"epoch": 0.006476474207441469,
"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": 1.29905631166464e+17,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}