error577's picture
Training in progress, epoch 0, checkpoint
aa08af1 verified
raw
history blame
18.1 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.03566333808844508,
"eval_steps": 500,
"global_step": 100,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0003566333808844508,
"grad_norm": 9.363040924072266,
"learning_rate": 1e-05,
"loss": 4.3855,
"step": 1
},
{
"epoch": 0.0007132667617689016,
"grad_norm": 6.347451210021973,
"learning_rate": 2e-05,
"loss": 3.1545,
"step": 2
},
{
"epoch": 0.0010699001426533524,
"grad_norm": 6.86058235168457,
"learning_rate": 3e-05,
"loss": 3.3333,
"step": 3
},
{
"epoch": 0.0014265335235378032,
"grad_norm": 6.634664058685303,
"learning_rate": 4e-05,
"loss": 3.1498,
"step": 4
},
{
"epoch": 0.001783166904422254,
"grad_norm": 7.706277370452881,
"learning_rate": 5e-05,
"loss": 3.5972,
"step": 5
},
{
"epoch": 0.0021398002853067048,
"grad_norm": 8.101608276367188,
"learning_rate": 6e-05,
"loss": 3.3785,
"step": 6
},
{
"epoch": 0.0024964336661911554,
"grad_norm": 6.382760524749756,
"learning_rate": 7e-05,
"loss": 2.7591,
"step": 7
},
{
"epoch": 0.0028530670470756064,
"grad_norm": 5.29052209854126,
"learning_rate": 8e-05,
"loss": 2.5879,
"step": 8
},
{
"epoch": 0.003209700427960057,
"grad_norm": 5.6285881996154785,
"learning_rate": 9e-05,
"loss": 2.5621,
"step": 9
},
{
"epoch": 0.003566333808844508,
"grad_norm": 6.152998447418213,
"learning_rate": 0.0001,
"loss": 2.6534,
"step": 10
},
{
"epoch": 0.0039229671897289585,
"grad_norm": 5.639293193817139,
"learning_rate": 9.99695413509548e-05,
"loss": 2.2913,
"step": 11
},
{
"epoch": 0.0042796005706134095,
"grad_norm": 5.765322685241699,
"learning_rate": 9.987820251299122e-05,
"loss": 2.4268,
"step": 12
},
{
"epoch": 0.0046362339514978606,
"grad_norm": 4.234713554382324,
"learning_rate": 9.972609476841367e-05,
"loss": 1.7016,
"step": 13
},
{
"epoch": 0.004992867332382311,
"grad_norm": 3.2637741565704346,
"learning_rate": 9.951340343707852e-05,
"loss": 0.9702,
"step": 14
},
{
"epoch": 0.005349500713266762,
"grad_norm": 4.795892238616943,
"learning_rate": 9.924038765061042e-05,
"loss": 1.6439,
"step": 15
},
{
"epoch": 0.005706134094151213,
"grad_norm": 5.164958477020264,
"learning_rate": 9.890738003669029e-05,
"loss": 1.3666,
"step": 16
},
{
"epoch": 0.006062767475035664,
"grad_norm": 3.871415853500366,
"learning_rate": 9.851478631379982e-05,
"loss": 1.073,
"step": 17
},
{
"epoch": 0.006419400855920114,
"grad_norm": 4.184787750244141,
"learning_rate": 9.806308479691595e-05,
"loss": 0.8661,
"step": 18
},
{
"epoch": 0.006776034236804565,
"grad_norm": 3.906731605529785,
"learning_rate": 9.755282581475769e-05,
"loss": 0.6565,
"step": 19
},
{
"epoch": 0.007132667617689016,
"grad_norm": 3.2300405502319336,
"learning_rate": 9.698463103929542e-05,
"loss": 0.7052,
"step": 20
},
{
"epoch": 0.007489300998573466,
"grad_norm": 4.245668411254883,
"learning_rate": 9.635919272833938e-05,
"loss": 0.7697,
"step": 21
},
{
"epoch": 0.007845934379457917,
"grad_norm": 4.0306291580200195,
"learning_rate": 9.567727288213005e-05,
"loss": 0.8679,
"step": 22
},
{
"epoch": 0.008202567760342368,
"grad_norm": 3.8920738697052,
"learning_rate": 9.493970231495835e-05,
"loss": 0.8939,
"step": 23
},
{
"epoch": 0.008559201141226819,
"grad_norm": 3.2148375511169434,
"learning_rate": 9.414737964294636e-05,
"loss": 0.7285,
"step": 24
},
{
"epoch": 0.00891583452211127,
"grad_norm": 4.372247219085693,
"learning_rate": 9.330127018922194e-05,
"loss": 0.7695,
"step": 25
},
{
"epoch": 0.009272467902995721,
"grad_norm": 2.8545451164245605,
"learning_rate": 9.24024048078213e-05,
"loss": 0.5572,
"step": 26
},
{
"epoch": 0.00962910128388017,
"grad_norm": 2.885377883911133,
"learning_rate": 9.145187862775209e-05,
"loss": 0.5268,
"step": 27
},
{
"epoch": 0.009985734664764621,
"grad_norm": 7.588974952697754,
"learning_rate": 9.045084971874738e-05,
"loss": 0.7713,
"step": 28
},
{
"epoch": 0.010342368045649072,
"grad_norm": 2.902350425720215,
"learning_rate": 8.940053768033609e-05,
"loss": 0.5385,
"step": 29
},
{
"epoch": 0.010699001426533523,
"grad_norm": 4.498276233673096,
"learning_rate": 8.83022221559489e-05,
"loss": 0.931,
"step": 30
},
{
"epoch": 0.011055634807417974,
"grad_norm": 4.142467021942139,
"learning_rate": 8.715724127386972e-05,
"loss": 0.8787,
"step": 31
},
{
"epoch": 0.011412268188302425,
"grad_norm": 3.7488930225372314,
"learning_rate": 8.596699001693255e-05,
"loss": 0.6626,
"step": 32
},
{
"epoch": 0.011768901569186876,
"grad_norm": 4.370077610015869,
"learning_rate": 8.473291852294987e-05,
"loss": 0.8969,
"step": 33
},
{
"epoch": 0.012125534950071327,
"grad_norm": 3.818770170211792,
"learning_rate": 8.345653031794292e-05,
"loss": 0.7333,
"step": 34
},
{
"epoch": 0.012482168330955777,
"grad_norm": 4.14440393447876,
"learning_rate": 8.213938048432697e-05,
"loss": 0.6302,
"step": 35
},
{
"epoch": 0.012838801711840228,
"grad_norm": 3.1287050247192383,
"learning_rate": 8.07830737662829e-05,
"loss": 0.6581,
"step": 36
},
{
"epoch": 0.013195435092724679,
"grad_norm": 3.507883071899414,
"learning_rate": 7.938926261462366e-05,
"loss": 0.8353,
"step": 37
},
{
"epoch": 0.01355206847360913,
"grad_norm": 2.537346363067627,
"learning_rate": 7.795964517353735e-05,
"loss": 0.572,
"step": 38
},
{
"epoch": 0.01390870185449358,
"grad_norm": 2.7204527854919434,
"learning_rate": 7.649596321166024e-05,
"loss": 0.6852,
"step": 39
},
{
"epoch": 0.014265335235378032,
"grad_norm": 3.4210116863250732,
"learning_rate": 7.500000000000001e-05,
"loss": 0.892,
"step": 40
},
{
"epoch": 0.014621968616262483,
"grad_norm": 2.5639355182647705,
"learning_rate": 7.347357813929454e-05,
"loss": 0.694,
"step": 41
},
{
"epoch": 0.014978601997146932,
"grad_norm": 1.8123944997787476,
"learning_rate": 7.191855733945387e-05,
"loss": 0.3759,
"step": 42
},
{
"epoch": 0.015335235378031383,
"grad_norm": 2.9636120796203613,
"learning_rate": 7.033683215379002e-05,
"loss": 0.7841,
"step": 43
},
{
"epoch": 0.015691868758915834,
"grad_norm": 2.436626672744751,
"learning_rate": 6.873032967079561e-05,
"loss": 0.5834,
"step": 44
},
{
"epoch": 0.016048502139800285,
"grad_norm": 2.7249507904052734,
"learning_rate": 6.710100716628344e-05,
"loss": 0.4933,
"step": 45
},
{
"epoch": 0.016405135520684736,
"grad_norm": 2.284421920776367,
"learning_rate": 6.545084971874738e-05,
"loss": 0.4192,
"step": 46
},
{
"epoch": 0.016761768901569187,
"grad_norm": 3.8047709465026855,
"learning_rate": 6.378186779084995e-05,
"loss": 0.8853,
"step": 47
},
{
"epoch": 0.017118402282453638,
"grad_norm": 3.018512725830078,
"learning_rate": 6.209609477998338e-05,
"loss": 0.536,
"step": 48
},
{
"epoch": 0.01747503566333809,
"grad_norm": 3.01859974861145,
"learning_rate": 6.0395584540887963e-05,
"loss": 0.729,
"step": 49
},
{
"epoch": 0.01783166904422254,
"grad_norm": 2.6281919479370117,
"learning_rate": 5.868240888334653e-05,
"loss": 0.6991,
"step": 50
},
{
"epoch": 0.01818830242510699,
"grad_norm": 3.3880066871643066,
"learning_rate": 5.695865504800327e-05,
"loss": 0.8231,
"step": 51
},
{
"epoch": 0.018544935805991442,
"grad_norm": 3.1417741775512695,
"learning_rate": 5.522642316338268e-05,
"loss": 0.6593,
"step": 52
},
{
"epoch": 0.018901569186875893,
"grad_norm": 2.7709360122680664,
"learning_rate": 5.348782368720626e-05,
"loss": 0.6594,
"step": 53
},
{
"epoch": 0.01925820256776034,
"grad_norm": 1.8896925449371338,
"learning_rate": 5.174497483512506e-05,
"loss": 0.3743,
"step": 54
},
{
"epoch": 0.019614835948644792,
"grad_norm": 2.332252264022827,
"learning_rate": 5e-05,
"loss": 0.5242,
"step": 55
},
{
"epoch": 0.019971469329529243,
"grad_norm": 2.262308120727539,
"learning_rate": 4.825502516487497e-05,
"loss": 0.4749,
"step": 56
},
{
"epoch": 0.020328102710413694,
"grad_norm": 3.0309510231018066,
"learning_rate": 4.6512176312793736e-05,
"loss": 0.8089,
"step": 57
},
{
"epoch": 0.020684736091298145,
"grad_norm": 2.982093095779419,
"learning_rate": 4.477357683661734e-05,
"loss": 0.7445,
"step": 58
},
{
"epoch": 0.021041369472182596,
"grad_norm": 2.9706778526306152,
"learning_rate": 4.3041344951996746e-05,
"loss": 0.7625,
"step": 59
},
{
"epoch": 0.021398002853067047,
"grad_norm": 3.214873790740967,
"learning_rate": 4.131759111665349e-05,
"loss": 0.7535,
"step": 60
},
{
"epoch": 0.021754636233951498,
"grad_norm": 1.8653569221496582,
"learning_rate": 3.960441545911204e-05,
"loss": 0.2986,
"step": 61
},
{
"epoch": 0.02211126961483595,
"grad_norm": 2.036979913711548,
"learning_rate": 3.790390522001662e-05,
"loss": 0.4829,
"step": 62
},
{
"epoch": 0.0224679029957204,
"grad_norm": 2.363051414489746,
"learning_rate": 3.6218132209150045e-05,
"loss": 0.5076,
"step": 63
},
{
"epoch": 0.02282453637660485,
"grad_norm": 2.7768218517303467,
"learning_rate": 3.4549150281252636e-05,
"loss": 0.6432,
"step": 64
},
{
"epoch": 0.023181169757489302,
"grad_norm": 2.8919661045074463,
"learning_rate": 3.289899283371657e-05,
"loss": 0.841,
"step": 65
},
{
"epoch": 0.023537803138373753,
"grad_norm": 2.0824460983276367,
"learning_rate": 3.12696703292044e-05,
"loss": 0.6802,
"step": 66
},
{
"epoch": 0.023894436519258204,
"grad_norm": 1.9507566690444946,
"learning_rate": 2.9663167846209998e-05,
"loss": 0.4093,
"step": 67
},
{
"epoch": 0.024251069900142655,
"grad_norm": 2.6440842151641846,
"learning_rate": 2.8081442660546125e-05,
"loss": 0.7536,
"step": 68
},
{
"epoch": 0.024607703281027102,
"grad_norm": 2.003270387649536,
"learning_rate": 2.6526421860705473e-05,
"loss": 0.4625,
"step": 69
},
{
"epoch": 0.024964336661911554,
"grad_norm": 1.971593976020813,
"learning_rate": 2.500000000000001e-05,
"loss": 0.4918,
"step": 70
},
{
"epoch": 0.025320970042796005,
"grad_norm": 3.1076760292053223,
"learning_rate": 2.350403678833976e-05,
"loss": 0.6007,
"step": 71
},
{
"epoch": 0.025677603423680456,
"grad_norm": 2.7494683265686035,
"learning_rate": 2.2040354826462668e-05,
"loss": 0.7651,
"step": 72
},
{
"epoch": 0.026034236804564907,
"grad_norm": 2.109565496444702,
"learning_rate": 2.061073738537635e-05,
"loss": 0.5258,
"step": 73
},
{
"epoch": 0.026390870185449358,
"grad_norm": 2.0325872898101807,
"learning_rate": 1.9216926233717085e-05,
"loss": 0.4343,
"step": 74
},
{
"epoch": 0.02674750356633381,
"grad_norm": 2.677518844604492,
"learning_rate": 1.7860619515673033e-05,
"loss": 0.7317,
"step": 75
},
{
"epoch": 0.02710413694721826,
"grad_norm": 1.955473780632019,
"learning_rate": 1.6543469682057106e-05,
"loss": 0.5048,
"step": 76
},
{
"epoch": 0.02746077032810271,
"grad_norm": 2.564527988433838,
"learning_rate": 1.526708147705013e-05,
"loss": 0.5563,
"step": 77
},
{
"epoch": 0.02781740370898716,
"grad_norm": 2.2224435806274414,
"learning_rate": 1.4033009983067452e-05,
"loss": 0.4178,
"step": 78
},
{
"epoch": 0.028174037089871613,
"grad_norm": 2.506559371948242,
"learning_rate": 1.2842758726130283e-05,
"loss": 0.7548,
"step": 79
},
{
"epoch": 0.028530670470756064,
"grad_norm": 2.0382838249206543,
"learning_rate": 1.1697777844051105e-05,
"loss": 0.4553,
"step": 80
},
{
"epoch": 0.028887303851640515,
"grad_norm": 2.390615940093994,
"learning_rate": 1.0599462319663905e-05,
"loss": 0.6142,
"step": 81
},
{
"epoch": 0.029243937232524966,
"grad_norm": 2.520522117614746,
"learning_rate": 9.549150281252633e-06,
"loss": 0.6926,
"step": 82
},
{
"epoch": 0.029600570613409417,
"grad_norm": 2.2115468978881836,
"learning_rate": 8.548121372247918e-06,
"loss": 0.4984,
"step": 83
},
{
"epoch": 0.029957203994293864,
"grad_norm": 1.859317660331726,
"learning_rate": 7.597595192178702e-06,
"loss": 0.414,
"step": 84
},
{
"epoch": 0.030313837375178315,
"grad_norm": 2.4491794109344482,
"learning_rate": 6.698729810778065e-06,
"loss": 0.5051,
"step": 85
},
{
"epoch": 0.030670470756062766,
"grad_norm": 3.001934289932251,
"learning_rate": 5.852620357053651e-06,
"loss": 0.8421,
"step": 86
},
{
"epoch": 0.031027104136947217,
"grad_norm": 2.546048879623413,
"learning_rate": 5.060297685041659e-06,
"loss": 0.6714,
"step": 87
},
{
"epoch": 0.03138373751783167,
"grad_norm": 2.3099381923675537,
"learning_rate": 4.322727117869951e-06,
"loss": 0.5193,
"step": 88
},
{
"epoch": 0.03174037089871612,
"grad_norm": 2.254861831665039,
"learning_rate": 3.6408072716606346e-06,
"loss": 0.5998,
"step": 89
},
{
"epoch": 0.03209700427960057,
"grad_norm": 2.1736197471618652,
"learning_rate": 3.0153689607045845e-06,
"loss": 0.4596,
"step": 90
},
{
"epoch": 0.03245363766048502,
"grad_norm": 2.836841344833374,
"learning_rate": 2.4471741852423237e-06,
"loss": 0.5677,
"step": 91
},
{
"epoch": 0.03281027104136947,
"grad_norm": 2.688999652862549,
"learning_rate": 1.9369152030840556e-06,
"loss": 0.4659,
"step": 92
},
{
"epoch": 0.03316690442225392,
"grad_norm": 1.7395498752593994,
"learning_rate": 1.4852136862001764e-06,
"loss": 0.3645,
"step": 93
},
{
"epoch": 0.033523537803138374,
"grad_norm": 1.8164441585540771,
"learning_rate": 1.0926199633097157e-06,
"loss": 0.5342,
"step": 94
},
{
"epoch": 0.033880171184022825,
"grad_norm": 2.278712034225464,
"learning_rate": 7.596123493895991e-07,
"loss": 0.6005,
"step": 95
},
{
"epoch": 0.034236804564907276,
"grad_norm": 2.416529417037964,
"learning_rate": 4.865965629214819e-07,
"loss": 0.6101,
"step": 96
},
{
"epoch": 0.03459343794579173,
"grad_norm": 2.829819679260254,
"learning_rate": 2.7390523158633554e-07,
"loss": 0.5345,
"step": 97
},
{
"epoch": 0.03495007132667618,
"grad_norm": 2.9469738006591797,
"learning_rate": 1.2179748700879012e-07,
"loss": 0.7436,
"step": 98
},
{
"epoch": 0.03530670470756063,
"grad_norm": 2.819187879562378,
"learning_rate": 3.04586490452119e-08,
"loss": 0.7091,
"step": 99
},
{
"epoch": 0.03566333808844508,
"grad_norm": 1.8256174325942993,
"learning_rate": 0.0,
"loss": 0.3428,
"step": 100
},
{
"epoch": 0.03566333808844508,
"eval_loss": 0.5488497018814087,
"eval_runtime": 68.0904,
"eval_samples_per_second": 6.726,
"eval_steps_per_second": 6.726,
"step": 100
}
],
"logging_steps": 1,
"max_steps": 100,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 5000973307084800.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}