bbytxt's picture
Training in progress, step 100, checkpoint
3855f46 verified
{
"best_metric": 2.433537244796753,
"best_model_checkpoint": "miner_id_24/checkpoint-100",
"epoch": 0.03209371364384001,
"eval_steps": 50,
"global_step": 100,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0003209371364384001,
"grad_norm": 29.0620174407959,
"learning_rate": 5.000000000000001e-07,
"loss": 8.3536,
"step": 1
},
{
"epoch": 0.0003209371364384001,
"eval_loss": 9.608317375183105,
"eval_runtime": 114.1452,
"eval_samples_per_second": 45.977,
"eval_steps_per_second": 11.494,
"step": 1
},
{
"epoch": 0.0006418742728768002,
"grad_norm": 27.07642936706543,
"learning_rate": 1.0000000000000002e-06,
"loss": 8.5873,
"step": 2
},
{
"epoch": 0.0009628114093152004,
"grad_norm": 26.89195442199707,
"learning_rate": 1.5e-06,
"loss": 8.5025,
"step": 3
},
{
"epoch": 0.0012837485457536004,
"grad_norm": 28.958402633666992,
"learning_rate": 2.0000000000000003e-06,
"loss": 8.3659,
"step": 4
},
{
"epoch": 0.0016046856821920006,
"grad_norm": 26.5856990814209,
"learning_rate": 2.5e-06,
"loss": 8.6332,
"step": 5
},
{
"epoch": 0.0019256228186304008,
"grad_norm": 26.915088653564453,
"learning_rate": 3e-06,
"loss": 8.7503,
"step": 6
},
{
"epoch": 0.002246559955068801,
"grad_norm": 26.08704376220703,
"learning_rate": 3.5e-06,
"loss": 8.9856,
"step": 7
},
{
"epoch": 0.002567497091507201,
"grad_norm": 25.679841995239258,
"learning_rate": 4.000000000000001e-06,
"loss": 8.2122,
"step": 8
},
{
"epoch": 0.0028884342279456013,
"grad_norm": 26.561437606811523,
"learning_rate": 4.5e-06,
"loss": 8.9559,
"step": 9
},
{
"epoch": 0.003209371364384001,
"grad_norm": 28.039274215698242,
"learning_rate": 5e-06,
"loss": 9.0445,
"step": 10
},
{
"epoch": 0.0035303085008224016,
"grad_norm": 27.321456909179688,
"learning_rate": 4.99847706754774e-06,
"loss": 8.3967,
"step": 11
},
{
"epoch": 0.0038512456372608015,
"grad_norm": 28.633220672607422,
"learning_rate": 4.993910125649561e-06,
"loss": 8.845,
"step": 12
},
{
"epoch": 0.004172182773699202,
"grad_norm": 28.76858139038086,
"learning_rate": 4.986304738420684e-06,
"loss": 9.0155,
"step": 13
},
{
"epoch": 0.004493119910137602,
"grad_norm": 28.05516242980957,
"learning_rate": 4.975670171853926e-06,
"loss": 9.0271,
"step": 14
},
{
"epoch": 0.004814057046576002,
"grad_norm": 30.46915626525879,
"learning_rate": 4.962019382530521e-06,
"loss": 8.8126,
"step": 15
},
{
"epoch": 0.005134994183014402,
"grad_norm": 27.029661178588867,
"learning_rate": 4.9453690018345144e-06,
"loss": 8.6929,
"step": 16
},
{
"epoch": 0.0054559313194528026,
"grad_norm": 25.081933975219727,
"learning_rate": 4.925739315689991e-06,
"loss": 8.638,
"step": 17
},
{
"epoch": 0.0057768684558912025,
"grad_norm": 29.977359771728516,
"learning_rate": 4.903154239845798e-06,
"loss": 8.4378,
"step": 18
},
{
"epoch": 0.0060978055923296024,
"grad_norm": 28.07939910888672,
"learning_rate": 4.8776412907378845e-06,
"loss": 8.5696,
"step": 19
},
{
"epoch": 0.006418742728768002,
"grad_norm": 28.049762725830078,
"learning_rate": 4.849231551964771e-06,
"loss": 8.4232,
"step": 20
},
{
"epoch": 0.006739679865206402,
"grad_norm": 26.482662200927734,
"learning_rate": 4.817959636416969e-06,
"loss": 8.0291,
"step": 21
},
{
"epoch": 0.007060617001644803,
"grad_norm": 26.32106590270996,
"learning_rate": 4.783863644106502e-06,
"loss": 8.2169,
"step": 22
},
{
"epoch": 0.007381554138083203,
"grad_norm": 28.06663703918457,
"learning_rate": 4.746985115747918e-06,
"loss": 7.9846,
"step": 23
},
{
"epoch": 0.007702491274521603,
"grad_norm": 29.093708038330078,
"learning_rate": 4.707368982147318e-06,
"loss": 8.3039,
"step": 24
},
{
"epoch": 0.008023428410960003,
"grad_norm": 26.908905029296875,
"learning_rate": 4.665063509461098e-06,
"loss": 7.842,
"step": 25
},
{
"epoch": 0.008344365547398404,
"grad_norm": 29.075284957885742,
"learning_rate": 4.620120240391065e-06,
"loss": 8.1723,
"step": 26
},
{
"epoch": 0.008665302683836803,
"grad_norm": 27.27924156188965,
"learning_rate": 4.572593931387604e-06,
"loss": 7.5182,
"step": 27
},
{
"epoch": 0.008986239820275204,
"grad_norm": 29.46119499206543,
"learning_rate": 4.522542485937369e-06,
"loss": 7.6367,
"step": 28
},
{
"epoch": 0.009307176956713605,
"grad_norm": 27.407634735107422,
"learning_rate": 4.470026884016805e-06,
"loss": 7.5039,
"step": 29
},
{
"epoch": 0.009628114093152004,
"grad_norm": 29.512258529663086,
"learning_rate": 4.415111107797445e-06,
"loss": 7.571,
"step": 30
},
{
"epoch": 0.009949051229590404,
"grad_norm": 27.04265022277832,
"learning_rate": 4.357862063693486e-06,
"loss": 7.2244,
"step": 31
},
{
"epoch": 0.010269988366028803,
"grad_norm": 28.921262741088867,
"learning_rate": 4.2983495008466285e-06,
"loss": 7.1985,
"step": 32
},
{
"epoch": 0.010590925502467204,
"grad_norm": 28.390796661376953,
"learning_rate": 4.236645926147493e-06,
"loss": 7.1598,
"step": 33
},
{
"epoch": 0.010911862638905605,
"grad_norm": 27.8939266204834,
"learning_rate": 4.172826515897146e-06,
"loss": 7.1128,
"step": 34
},
{
"epoch": 0.011232799775344004,
"grad_norm": 28.097919464111328,
"learning_rate": 4.106969024216348e-06,
"loss": 6.8686,
"step": 35
},
{
"epoch": 0.011553736911782405,
"grad_norm": 27.190977096557617,
"learning_rate": 4.039153688314146e-06,
"loss": 6.4434,
"step": 36
},
{
"epoch": 0.011874674048220804,
"grad_norm": 27.64179039001465,
"learning_rate": 3.969463130731183e-06,
"loss": 6.6498,
"step": 37
},
{
"epoch": 0.012195611184659205,
"grad_norm": 25.73870277404785,
"learning_rate": 3.897982258676867e-06,
"loss": 6.1158,
"step": 38
},
{
"epoch": 0.012516548321097606,
"grad_norm": 27.77838897705078,
"learning_rate": 3.824798160583012e-06,
"loss": 6.0776,
"step": 39
},
{
"epoch": 0.012837485457536005,
"grad_norm": 25.881872177124023,
"learning_rate": 3.7500000000000005e-06,
"loss": 6.4197,
"step": 40
},
{
"epoch": 0.013158422593974406,
"grad_norm": 27.128604888916016,
"learning_rate": 3.6736789069647273e-06,
"loss": 6.0235,
"step": 41
},
{
"epoch": 0.013479359730412805,
"grad_norm": 28.29000473022461,
"learning_rate": 3.595927866972694e-06,
"loss": 6.0427,
"step": 42
},
{
"epoch": 0.013800296866851205,
"grad_norm": 28.178508758544922,
"learning_rate": 3.516841607689501e-06,
"loss": 5.8592,
"step": 43
},
{
"epoch": 0.014121234003289606,
"grad_norm": 27.883281707763672,
"learning_rate": 3.436516483539781e-06,
"loss": 5.881,
"step": 44
},
{
"epoch": 0.014442171139728005,
"grad_norm": 30.232969284057617,
"learning_rate": 3.3550503583141726e-06,
"loss": 5.9248,
"step": 45
},
{
"epoch": 0.014763108276166406,
"grad_norm": 28.135517120361328,
"learning_rate": 3.272542485937369e-06,
"loss": 6.09,
"step": 46
},
{
"epoch": 0.015084045412604805,
"grad_norm": 29.159257888793945,
"learning_rate": 3.189093389542498e-06,
"loss": 5.6698,
"step": 47
},
{
"epoch": 0.015404982549043206,
"grad_norm": 28.084815979003906,
"learning_rate": 3.1048047389991693e-06,
"loss": 5.6638,
"step": 48
},
{
"epoch": 0.015725919685481607,
"grad_norm": 33.78214645385742,
"learning_rate": 3.019779227044398e-06,
"loss": 6.0495,
"step": 49
},
{
"epoch": 0.016046856821920006,
"grad_norm": 33.4984245300293,
"learning_rate": 2.9341204441673267e-06,
"loss": 6.7971,
"step": 50
},
{
"epoch": 0.016046856821920006,
"eval_loss": 4.2570929527282715,
"eval_runtime": 114.8019,
"eval_samples_per_second": 45.714,
"eval_steps_per_second": 11.428,
"step": 50
},
{
"epoch": 0.016367793958358405,
"grad_norm": 25.424381256103516,
"learning_rate": 2.847932752400164e-06,
"loss": 3.7885,
"step": 51
},
{
"epoch": 0.016688731094796808,
"grad_norm": 24.880250930786133,
"learning_rate": 2.761321158169134e-06,
"loss": 3.713,
"step": 52
},
{
"epoch": 0.017009668231235207,
"grad_norm": 24.886323928833008,
"learning_rate": 2.6743911843603134e-06,
"loss": 3.4695,
"step": 53
},
{
"epoch": 0.017330605367673606,
"grad_norm": 24.543724060058594,
"learning_rate": 2.587248741756253e-06,
"loss": 3.5675,
"step": 54
},
{
"epoch": 0.01765154250411201,
"grad_norm": 24.91683578491211,
"learning_rate": 2.5e-06,
"loss": 3.3737,
"step": 55
},
{
"epoch": 0.017972479640550407,
"grad_norm": 24.803110122680664,
"learning_rate": 2.4127512582437486e-06,
"loss": 3.3712,
"step": 56
},
{
"epoch": 0.018293416776988806,
"grad_norm": 23.752742767333984,
"learning_rate": 2.325608815639687e-06,
"loss": 3.2692,
"step": 57
},
{
"epoch": 0.01861435391342721,
"grad_norm": 25.91507339477539,
"learning_rate": 2.238678841830867e-06,
"loss": 3.3837,
"step": 58
},
{
"epoch": 0.018935291049865608,
"grad_norm": 23.929170608520508,
"learning_rate": 2.1520672475998374e-06,
"loss": 3.1364,
"step": 59
},
{
"epoch": 0.019256228186304007,
"grad_norm": 23.347362518310547,
"learning_rate": 2.0658795558326745e-06,
"loss": 3.2312,
"step": 60
},
{
"epoch": 0.019577165322742406,
"grad_norm": 23.763065338134766,
"learning_rate": 1.9802207729556023e-06,
"loss": 2.8907,
"step": 61
},
{
"epoch": 0.01989810245918081,
"grad_norm": 24.44504737854004,
"learning_rate": 1.895195261000831e-06,
"loss": 3.2479,
"step": 62
},
{
"epoch": 0.020219039595619208,
"grad_norm": 22.8721981048584,
"learning_rate": 1.8109066104575023e-06,
"loss": 3.0271,
"step": 63
},
{
"epoch": 0.020539976732057607,
"grad_norm": 22.79950523376465,
"learning_rate": 1.7274575140626318e-06,
"loss": 3.0064,
"step": 64
},
{
"epoch": 0.02086091386849601,
"grad_norm": 23.403169631958008,
"learning_rate": 1.6449496416858285e-06,
"loss": 2.764,
"step": 65
},
{
"epoch": 0.02118185100493441,
"grad_norm": 22.879098892211914,
"learning_rate": 1.56348351646022e-06,
"loss": 2.9624,
"step": 66
},
{
"epoch": 0.021502788141372808,
"grad_norm": 21.32579803466797,
"learning_rate": 1.4831583923105e-06,
"loss": 2.6705,
"step": 67
},
{
"epoch": 0.02182372527781121,
"grad_norm": 22.811050415039062,
"learning_rate": 1.4040721330273063e-06,
"loss": 2.6002,
"step": 68
},
{
"epoch": 0.02214466241424961,
"grad_norm": 22.359167098999023,
"learning_rate": 1.3263210930352737e-06,
"loss": 2.6466,
"step": 69
},
{
"epoch": 0.02246559955068801,
"grad_norm": 22.979188919067383,
"learning_rate": 1.2500000000000007e-06,
"loss": 2.8473,
"step": 70
},
{
"epoch": 0.022786536687126407,
"grad_norm": 20.867158889770508,
"learning_rate": 1.1752018394169882e-06,
"loss": 2.6938,
"step": 71
},
{
"epoch": 0.02310747382356481,
"grad_norm": 20.0809383392334,
"learning_rate": 1.1020177413231334e-06,
"loss": 2.5959,
"step": 72
},
{
"epoch": 0.02342841096000321,
"grad_norm": 21.05283546447754,
"learning_rate": 1.0305368692688175e-06,
"loss": 2.5396,
"step": 73
},
{
"epoch": 0.023749348096441608,
"grad_norm": 20.267318725585938,
"learning_rate": 9.608463116858544e-07,
"loss": 2.6901,
"step": 74
},
{
"epoch": 0.02407028523288001,
"grad_norm": 20.902544021606445,
"learning_rate": 8.930309757836517e-07,
"loss": 2.6968,
"step": 75
},
{
"epoch": 0.02439122236931841,
"grad_norm": 19.689470291137695,
"learning_rate": 8.271734841028553e-07,
"loss": 2.6722,
"step": 76
},
{
"epoch": 0.02471215950575681,
"grad_norm": 19.139225006103516,
"learning_rate": 7.633540738525066e-07,
"loss": 2.5436,
"step": 77
},
{
"epoch": 0.02503309664219521,
"grad_norm": 18.674592971801758,
"learning_rate": 7.016504991533727e-07,
"loss": 2.4693,
"step": 78
},
{
"epoch": 0.02535403377863361,
"grad_norm": 20.122690200805664,
"learning_rate": 6.421379363065142e-07,
"loss": 2.4514,
"step": 79
},
{
"epoch": 0.02567497091507201,
"grad_norm": 19.937786102294922,
"learning_rate": 5.848888922025553e-07,
"loss": 2.8831,
"step": 80
},
{
"epoch": 0.025995908051510412,
"grad_norm": 19.96189308166504,
"learning_rate": 5.299731159831953e-07,
"loss": 2.6644,
"step": 81
},
{
"epoch": 0.02631684518794881,
"grad_norm": 17.768918991088867,
"learning_rate": 4.774575140626317e-07,
"loss": 2.3974,
"step": 82
},
{
"epoch": 0.02663778232438721,
"grad_norm": 18.64786148071289,
"learning_rate": 4.27406068612396e-07,
"loss": 2.5981,
"step": 83
},
{
"epoch": 0.02695871946082561,
"grad_norm": 18.258705139160156,
"learning_rate": 3.798797596089351e-07,
"loss": 2.4503,
"step": 84
},
{
"epoch": 0.027279656597264012,
"grad_norm": 19.37623405456543,
"learning_rate": 3.3493649053890325e-07,
"loss": 2.7219,
"step": 85
},
{
"epoch": 0.02760059373370241,
"grad_norm": 18.341720581054688,
"learning_rate": 2.9263101785268253e-07,
"loss": 2.6573,
"step": 86
},
{
"epoch": 0.02792153087014081,
"grad_norm": 18.695499420166016,
"learning_rate": 2.53014884252083e-07,
"loss": 2.5608,
"step": 87
},
{
"epoch": 0.028242468006579213,
"grad_norm": 18.94692611694336,
"learning_rate": 2.1613635589349756e-07,
"loss": 2.9003,
"step": 88
},
{
"epoch": 0.02856340514301761,
"grad_norm": 19.977092742919922,
"learning_rate": 1.8204036358303173e-07,
"loss": 2.6623,
"step": 89
},
{
"epoch": 0.02888434227945601,
"grad_norm": 20.050983428955078,
"learning_rate": 1.507684480352292e-07,
"loss": 2.837,
"step": 90
},
{
"epoch": 0.029205279415894413,
"grad_norm": 20.20208740234375,
"learning_rate": 1.223587092621162e-07,
"loss": 2.8119,
"step": 91
},
{
"epoch": 0.029526216552332812,
"grad_norm": 19.773828506469727,
"learning_rate": 9.684576015420277e-08,
"loss": 2.6902,
"step": 92
},
{
"epoch": 0.02984715368877121,
"grad_norm": 19.30417823791504,
"learning_rate": 7.426068431000883e-08,
"loss": 3.0893,
"step": 93
},
{
"epoch": 0.03016809082520961,
"grad_norm": 20.463987350463867,
"learning_rate": 5.463099816548578e-08,
"loss": 2.7802,
"step": 94
},
{
"epoch": 0.030489027961648013,
"grad_norm": 21.89801597595215,
"learning_rate": 3.798061746947995e-08,
"loss": 2.8602,
"step": 95
},
{
"epoch": 0.030809965098086412,
"grad_norm": 23.680221557617188,
"learning_rate": 2.4329828146074096e-08,
"loss": 3.0159,
"step": 96
},
{
"epoch": 0.03113090223452481,
"grad_norm": 23.18214988708496,
"learning_rate": 1.3695261579316776e-08,
"loss": 2.9944,
"step": 97
},
{
"epoch": 0.031451839370963214,
"grad_norm": 25.3561954498291,
"learning_rate": 6.089874350439507e-09,
"loss": 3.1602,
"step": 98
},
{
"epoch": 0.03177277650740161,
"grad_norm": 25.77769660949707,
"learning_rate": 1.5229324522605949e-09,
"loss": 3.9821,
"step": 99
},
{
"epoch": 0.03209371364384001,
"grad_norm": 33.58566665649414,
"learning_rate": 0.0,
"loss": 4.7959,
"step": 100
},
{
"epoch": 0.03209371364384001,
"eval_loss": 2.433537244796753,
"eval_runtime": 114.8374,
"eval_samples_per_second": 45.699,
"eval_steps_per_second": 11.425,
"step": 100
}
],
"logging_steps": 1,
"max_steps": 100,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.93544513912832e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}