model_10a8f7e9 / checkpoint-192 /trainer_state.json
ugaoo's picture
Upload folder using huggingface_hub
85a5c1b verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 5.835051546391752,
"eval_steps": 500,
"global_step": 192,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.030927835051546393,
"grad_norm": 31.330896377563477,
"learning_rate": 5.0000000000000004e-08,
"loss": 4.8446,
"step": 1
},
{
"epoch": 0.061855670103092786,
"grad_norm": 31.82550811767578,
"learning_rate": 1.0000000000000001e-07,
"loss": 4.7928,
"step": 2
},
{
"epoch": 0.09278350515463918,
"grad_norm": 30.859010696411133,
"learning_rate": 1.5000000000000002e-07,
"loss": 4.6291,
"step": 3
},
{
"epoch": 0.12371134020618557,
"grad_norm": 31.643869400024414,
"learning_rate": 2.0000000000000002e-07,
"loss": 4.713,
"step": 4
},
{
"epoch": 0.15463917525773196,
"grad_norm": 33.41943359375,
"learning_rate": 2.5000000000000004e-07,
"loss": 4.9265,
"step": 5
},
{
"epoch": 0.18556701030927836,
"grad_norm": 32.8159065246582,
"learning_rate": 3.0000000000000004e-07,
"loss": 4.832,
"step": 6
},
{
"epoch": 0.21649484536082475,
"grad_norm": 31.771827697753906,
"learning_rate": 3.5000000000000004e-07,
"loss": 4.6801,
"step": 7
},
{
"epoch": 0.24742268041237114,
"grad_norm": 33.52857971191406,
"learning_rate": 4.0000000000000003e-07,
"loss": 4.9088,
"step": 8
},
{
"epoch": 0.27835051546391754,
"grad_norm": 31.47663688659668,
"learning_rate": 4.5000000000000003e-07,
"loss": 4.5767,
"step": 9
},
{
"epoch": 0.30927835051546393,
"grad_norm": 34.30753707885742,
"learning_rate": 5.000000000000001e-07,
"loss": 4.961,
"step": 10
},
{
"epoch": 0.3402061855670103,
"grad_norm": 31.3031005859375,
"learning_rate": 5.5e-07,
"loss": 4.7181,
"step": 11
},
{
"epoch": 0.3711340206185567,
"grad_norm": 32.63737106323242,
"learning_rate": 6.000000000000001e-07,
"loss": 4.7796,
"step": 12
},
{
"epoch": 0.4020618556701031,
"grad_norm": 31.14106559753418,
"learning_rate": 6.5e-07,
"loss": 4.5596,
"step": 13
},
{
"epoch": 0.4329896907216495,
"grad_norm": 30.995929718017578,
"learning_rate": 7.000000000000001e-07,
"loss": 4.5709,
"step": 14
},
{
"epoch": 0.4639175257731959,
"grad_norm": 29.113582611083984,
"learning_rate": 7.5e-07,
"loss": 4.4329,
"step": 15
},
{
"epoch": 0.4948453608247423,
"grad_norm": 27.933208465576172,
"learning_rate": 8.000000000000001e-07,
"loss": 4.337,
"step": 16
},
{
"epoch": 0.5257731958762887,
"grad_norm": 27.216915130615234,
"learning_rate": 8.500000000000001e-07,
"loss": 4.3253,
"step": 17
},
{
"epoch": 0.5567010309278351,
"grad_norm": 25.551725387573242,
"learning_rate": 9.000000000000001e-07,
"loss": 4.3318,
"step": 18
},
{
"epoch": 0.5876288659793815,
"grad_norm": 22.587017059326172,
"learning_rate": 9.500000000000001e-07,
"loss": 4.0206,
"step": 19
},
{
"epoch": 0.6185567010309279,
"grad_norm": 21.570398330688477,
"learning_rate": 1.0000000000000002e-06,
"loss": 3.8186,
"step": 20
},
{
"epoch": 0.6494845360824743,
"grad_norm": 20.41568946838379,
"learning_rate": 1.0500000000000001e-06,
"loss": 3.771,
"step": 21
},
{
"epoch": 0.6804123711340206,
"grad_norm": 19.1239070892334,
"learning_rate": 1.1e-06,
"loss": 3.5997,
"step": 22
},
{
"epoch": 0.711340206185567,
"grad_norm": 19.375389099121094,
"learning_rate": 1.1500000000000002e-06,
"loss": 3.4865,
"step": 23
},
{
"epoch": 0.7422680412371134,
"grad_norm": 19.06153106689453,
"learning_rate": 1.2000000000000002e-06,
"loss": 3.3836,
"step": 24
},
{
"epoch": 0.7731958762886598,
"grad_norm": 17.918527603149414,
"learning_rate": 1.25e-06,
"loss": 3.141,
"step": 25
},
{
"epoch": 0.8041237113402062,
"grad_norm": 18.42892837524414,
"learning_rate": 1.3e-06,
"loss": 3.0393,
"step": 26
},
{
"epoch": 0.8350515463917526,
"grad_norm": 18.298789978027344,
"learning_rate": 1.3500000000000002e-06,
"loss": 3.0098,
"step": 27
},
{
"epoch": 0.865979381443299,
"grad_norm": 16.423397064208984,
"learning_rate": 1.4000000000000001e-06,
"loss": 2.786,
"step": 28
},
{
"epoch": 0.8969072164948454,
"grad_norm": 14.053132057189941,
"learning_rate": 1.45e-06,
"loss": 2.5791,
"step": 29
},
{
"epoch": 0.9278350515463918,
"grad_norm": 14.001585006713867,
"learning_rate": 1.5e-06,
"loss": 2.5818,
"step": 30
},
{
"epoch": 0.9587628865979382,
"grad_norm": 13.626611709594727,
"learning_rate": 1.5500000000000002e-06,
"loss": 2.3909,
"step": 31
},
{
"epoch": 0.9896907216494846,
"grad_norm": 13.853208541870117,
"learning_rate": 1.6000000000000001e-06,
"loss": 2.2437,
"step": 32
},
{
"epoch": 1.0,
"grad_norm": 13.853208541870117,
"learning_rate": 1.6500000000000003e-06,
"loss": 2.2363,
"step": 33
},
{
"epoch": 1.0309278350515463,
"grad_norm": 24.948280334472656,
"learning_rate": 1.7000000000000002e-06,
"loss": 2.1462,
"step": 34
},
{
"epoch": 1.0618556701030928,
"grad_norm": 15.244880676269531,
"learning_rate": 1.75e-06,
"loss": 1.9498,
"step": 35
},
{
"epoch": 1.0927835051546393,
"grad_norm": 15.106721878051758,
"learning_rate": 1.8000000000000001e-06,
"loss": 1.7473,
"step": 36
},
{
"epoch": 1.1237113402061856,
"grad_norm": 14.083307266235352,
"learning_rate": 1.85e-06,
"loss": 1.6159,
"step": 37
},
{
"epoch": 1.1546391752577319,
"grad_norm": 15.086730003356934,
"learning_rate": 1.9000000000000002e-06,
"loss": 1.4901,
"step": 38
},
{
"epoch": 1.1855670103092784,
"grad_norm": 13.394895553588867,
"learning_rate": 1.9500000000000004e-06,
"loss": 1.2992,
"step": 39
},
{
"epoch": 1.2164948453608249,
"grad_norm": 13.134459495544434,
"learning_rate": 2.0000000000000003e-06,
"loss": 1.1725,
"step": 40
},
{
"epoch": 1.2474226804123711,
"grad_norm": 13.013129234313965,
"learning_rate": 2.05e-06,
"loss": 1.056,
"step": 41
},
{
"epoch": 1.2783505154639174,
"grad_norm": 12.309725761413574,
"learning_rate": 2.1000000000000002e-06,
"loss": 0.8779,
"step": 42
},
{
"epoch": 1.309278350515464,
"grad_norm": 11.717962265014648,
"learning_rate": 2.15e-06,
"loss": 0.7724,
"step": 43
},
{
"epoch": 1.3402061855670104,
"grad_norm": 10.531135559082031,
"learning_rate": 2.2e-06,
"loss": 0.6223,
"step": 44
},
{
"epoch": 1.3711340206185567,
"grad_norm": 9.451440811157227,
"learning_rate": 2.25e-06,
"loss": 0.5095,
"step": 45
},
{
"epoch": 1.402061855670103,
"grad_norm": 7.987078666687012,
"learning_rate": 2.3000000000000004e-06,
"loss": 0.3841,
"step": 46
},
{
"epoch": 1.4329896907216495,
"grad_norm": 6.726036071777344,
"learning_rate": 2.35e-06,
"loss": 0.3333,
"step": 47
},
{
"epoch": 1.463917525773196,
"grad_norm": 4.108280658721924,
"learning_rate": 2.4000000000000003e-06,
"loss": 0.2602,
"step": 48
},
{
"epoch": 1.4948453608247423,
"grad_norm": 2.6678011417388916,
"learning_rate": 2.4500000000000003e-06,
"loss": 0.2251,
"step": 49
},
{
"epoch": 1.5257731958762886,
"grad_norm": 2.8046882152557373,
"learning_rate": 2.5e-06,
"loss": 0.1984,
"step": 50
},
{
"epoch": 1.556701030927835,
"grad_norm": 2.6669921875,
"learning_rate": 2.55e-06,
"loss": 0.2084,
"step": 51
},
{
"epoch": 1.5876288659793816,
"grad_norm": 1.8236641883850098,
"learning_rate": 2.6e-06,
"loss": 0.169,
"step": 52
},
{
"epoch": 1.6185567010309279,
"grad_norm": 1.405070185661316,
"learning_rate": 2.6500000000000005e-06,
"loss": 0.1635,
"step": 53
},
{
"epoch": 1.6494845360824741,
"grad_norm": 1.869597315788269,
"learning_rate": 2.7000000000000004e-06,
"loss": 0.1572,
"step": 54
},
{
"epoch": 1.6804123711340206,
"grad_norm": 1.2718607187271118,
"learning_rate": 2.7500000000000004e-06,
"loss": 0.1411,
"step": 55
},
{
"epoch": 1.7113402061855671,
"grad_norm": 0.9617771506309509,
"learning_rate": 2.8000000000000003e-06,
"loss": 0.1427,
"step": 56
},
{
"epoch": 1.7422680412371134,
"grad_norm": 0.6258248090744019,
"learning_rate": 2.85e-06,
"loss": 0.1241,
"step": 57
},
{
"epoch": 1.7731958762886597,
"grad_norm": 0.5329176187515259,
"learning_rate": 2.9e-06,
"loss": 0.1214,
"step": 58
},
{
"epoch": 1.8041237113402062,
"grad_norm": 0.8642020225524902,
"learning_rate": 2.95e-06,
"loss": 0.1336,
"step": 59
},
{
"epoch": 1.8350515463917527,
"grad_norm": 0.627882182598114,
"learning_rate": 3e-06,
"loss": 0.121,
"step": 60
},
{
"epoch": 1.865979381443299,
"grad_norm": 0.7841255068778992,
"learning_rate": 3.05e-06,
"loss": 0.1163,
"step": 61
},
{
"epoch": 1.8969072164948453,
"grad_norm": 0.5962179899215698,
"learning_rate": 3.1000000000000004e-06,
"loss": 0.1117,
"step": 62
},
{
"epoch": 1.9278350515463918,
"grad_norm": 0.5344879627227783,
"learning_rate": 3.1500000000000003e-06,
"loss": 0.1162,
"step": 63
},
{
"epoch": 1.9587628865979383,
"grad_norm": 0.4333738386631012,
"learning_rate": 3.2000000000000003e-06,
"loss": 0.1152,
"step": 64
},
{
"epoch": 1.9896907216494846,
"grad_norm": 0.5866488814353943,
"learning_rate": 3.2500000000000002e-06,
"loss": 0.1171,
"step": 65
},
{
"epoch": 2.0,
"grad_norm": 0.5866488814353943,
"learning_rate": 3.3000000000000006e-06,
"loss": 0.0989,
"step": 66
},
{
"epoch": 2.0309278350515463,
"grad_norm": 0.8926169872283936,
"learning_rate": 3.3500000000000005e-06,
"loss": 0.1101,
"step": 67
},
{
"epoch": 2.0618556701030926,
"grad_norm": 0.4878557622432709,
"learning_rate": 3.4000000000000005e-06,
"loss": 0.1097,
"step": 68
},
{
"epoch": 2.0927835051546393,
"grad_norm": 0.4245884418487549,
"learning_rate": 3.45e-06,
"loss": 0.1089,
"step": 69
},
{
"epoch": 2.1237113402061856,
"grad_norm": 0.46030956506729126,
"learning_rate": 3.5e-06,
"loss": 0.1145,
"step": 70
},
{
"epoch": 2.154639175257732,
"grad_norm": 0.2561495900154114,
"learning_rate": 3.5500000000000003e-06,
"loss": 0.1118,
"step": 71
},
{
"epoch": 2.1855670103092786,
"grad_norm": 0.4041549563407898,
"learning_rate": 3.6000000000000003e-06,
"loss": 0.12,
"step": 72
},
{
"epoch": 2.216494845360825,
"grad_norm": 0.5008761882781982,
"learning_rate": 3.65e-06,
"loss": 0.1205,
"step": 73
},
{
"epoch": 2.247422680412371,
"grad_norm": 0.4233935475349426,
"learning_rate": 3.7e-06,
"loss": 0.1114,
"step": 74
},
{
"epoch": 2.2783505154639174,
"grad_norm": 0.3335970640182495,
"learning_rate": 3.7500000000000005e-06,
"loss": 0.1124,
"step": 75
},
{
"epoch": 2.3092783505154637,
"grad_norm": 0.3707692325115204,
"learning_rate": 3.8000000000000005e-06,
"loss": 0.1128,
"step": 76
},
{
"epoch": 2.3402061855670104,
"grad_norm": 0.3256140649318695,
"learning_rate": 3.85e-06,
"loss": 0.1107,
"step": 77
},
{
"epoch": 2.3711340206185567,
"grad_norm": 0.37325188517570496,
"learning_rate": 3.900000000000001e-06,
"loss": 0.1105,
"step": 78
},
{
"epoch": 2.402061855670103,
"grad_norm": 0.3175105154514313,
"learning_rate": 3.95e-06,
"loss": 0.1012,
"step": 79
},
{
"epoch": 2.4329896907216497,
"grad_norm": 0.2766858637332916,
"learning_rate": 4.000000000000001e-06,
"loss": 0.1107,
"step": 80
},
{
"epoch": 2.463917525773196,
"grad_norm": 0.3836129307746887,
"learning_rate": 4.05e-06,
"loss": 0.1122,
"step": 81
},
{
"epoch": 2.4948453608247423,
"grad_norm": 0.3037668764591217,
"learning_rate": 4.1e-06,
"loss": 0.1086,
"step": 82
},
{
"epoch": 2.5257731958762886,
"grad_norm": 0.2676079571247101,
"learning_rate": 4.15e-06,
"loss": 0.1078,
"step": 83
},
{
"epoch": 2.556701030927835,
"grad_norm": 0.2874029874801636,
"learning_rate": 4.2000000000000004e-06,
"loss": 0.1105,
"step": 84
},
{
"epoch": 2.5876288659793816,
"grad_norm": 0.26905298233032227,
"learning_rate": 4.25e-06,
"loss": 0.1085,
"step": 85
},
{
"epoch": 2.618556701030928,
"grad_norm": 0.29047831892967224,
"learning_rate": 4.3e-06,
"loss": 0.1054,
"step": 86
},
{
"epoch": 2.649484536082474,
"grad_norm": 0.28010866045951843,
"learning_rate": 4.350000000000001e-06,
"loss": 0.1056,
"step": 87
},
{
"epoch": 2.680412371134021,
"grad_norm": 0.2774551510810852,
"learning_rate": 4.4e-06,
"loss": 0.1062,
"step": 88
},
{
"epoch": 2.711340206185567,
"grad_norm": 0.36281612515449524,
"learning_rate": 4.450000000000001e-06,
"loss": 0.1027,
"step": 89
},
{
"epoch": 2.7422680412371134,
"grad_norm": 0.47866588830947876,
"learning_rate": 4.5e-06,
"loss": 0.1095,
"step": 90
},
{
"epoch": 2.7731958762886597,
"grad_norm": 0.35023054480552673,
"learning_rate": 4.5500000000000005e-06,
"loss": 0.1089,
"step": 91
},
{
"epoch": 2.804123711340206,
"grad_norm": 0.24360068142414093,
"learning_rate": 4.600000000000001e-06,
"loss": 0.1046,
"step": 92
},
{
"epoch": 2.8350515463917527,
"grad_norm": 0.6635286211967468,
"learning_rate": 4.65e-06,
"loss": 0.1083,
"step": 93
},
{
"epoch": 2.865979381443299,
"grad_norm": 0.44127148389816284,
"learning_rate": 4.7e-06,
"loss": 0.1082,
"step": 94
},
{
"epoch": 2.8969072164948453,
"grad_norm": 0.37611761689186096,
"learning_rate": 4.75e-06,
"loss": 0.107,
"step": 95
},
{
"epoch": 2.927835051546392,
"grad_norm": 0.29258766770362854,
"learning_rate": 4.800000000000001e-06,
"loss": 0.1079,
"step": 96
},
{
"epoch": 2.9587628865979383,
"grad_norm": 0.19428832828998566,
"learning_rate": 4.85e-06,
"loss": 0.1078,
"step": 97
},
{
"epoch": 2.9896907216494846,
"grad_norm": 0.30616602301597595,
"learning_rate": 4.9000000000000005e-06,
"loss": 0.1065,
"step": 98
},
{
"epoch": 3.0,
"grad_norm": 0.7477559447288513,
"learning_rate": 4.95e-06,
"loss": 0.1055,
"step": 99
},
{
"epoch": 3.0309278350515463,
"grad_norm": 0.250438392162323,
"learning_rate": 5e-06,
"loss": 0.1101,
"step": 100
},
{
"epoch": 3.0618556701030926,
"grad_norm": 0.22634077072143555,
"learning_rate": 4.998542555915435e-06,
"loss": 0.1027,
"step": 101
},
{
"epoch": 3.0927835051546393,
"grad_norm": 0.4120931327342987,
"learning_rate": 4.994171922976349e-06,
"loss": 0.1041,
"step": 102
},
{
"epoch": 3.1237113402061856,
"grad_norm": 0.4830654561519623,
"learning_rate": 4.986893197145238e-06,
"loss": 0.1103,
"step": 103
},
{
"epoch": 3.154639175257732,
"grad_norm": 0.39406684041023254,
"learning_rate": 4.976714865090827e-06,
"loss": 0.1041,
"step": 104
},
{
"epoch": 3.1855670103092786,
"grad_norm": 0.2510586380958557,
"learning_rate": 4.963648794292992e-06,
"loss": 0.1035,
"step": 105
},
{
"epoch": 3.216494845360825,
"grad_norm": 0.3943077027797699,
"learning_rate": 4.947710219205808e-06,
"loss": 0.1013,
"step": 106
},
{
"epoch": 3.247422680412371,
"grad_norm": 0.521105945110321,
"learning_rate": 4.928917723494854e-06,
"loss": 0.1066,
"step": 107
},
{
"epoch": 3.2783505154639174,
"grad_norm": 0.39136141538619995,
"learning_rate": 4.907293218369499e-06,
"loss": 0.1027,
"step": 108
},
{
"epoch": 3.3092783505154637,
"grad_norm": 0.7300665974617004,
"learning_rate": 4.882861917035403e-06,
"loss": 0.1052,
"step": 109
},
{
"epoch": 3.3402061855670104,
"grad_norm": 0.6353471279144287,
"learning_rate": 4.855652305297052e-06,
"loss": 0.1029,
"step": 110
},
{
"epoch": 3.3711340206185567,
"grad_norm": 0.7813745737075806,
"learning_rate": 4.825696108344583e-06,
"loss": 0.1061,
"step": 111
},
{
"epoch": 3.402061855670103,
"grad_norm": 0.35173729062080383,
"learning_rate": 4.793028253763633e-06,
"loss": 0.1087,
"step": 112
},
{
"epoch": 3.4329896907216497,
"grad_norm": 0.40841713547706604,
"learning_rate": 4.757686830811332e-06,
"loss": 0.1024,
"step": 113
},
{
"epoch": 3.463917525773196,
"grad_norm": 0.24630524218082428,
"learning_rate": 4.7197130460059385e-06,
"loss": 0.1071,
"step": 114
},
{
"epoch": 3.4948453608247423,
"grad_norm": 0.2730019986629486,
"learning_rate": 4.679151175081879e-06,
"loss": 0.1059,
"step": 115
},
{
"epoch": 3.5257731958762886,
"grad_norm": 0.4475044906139374,
"learning_rate": 4.636048511366222e-06,
"loss": 0.1055,
"step": 116
},
{
"epoch": 3.556701030927835,
"grad_norm": 0.4198738634586334,
"learning_rate": 4.590455310636778e-06,
"loss": 0.1031,
"step": 117
},
{
"epoch": 3.5876288659793816,
"grad_norm": 0.3596094846725464,
"learning_rate": 4.542424732526105e-06,
"loss": 0.1008,
"step": 118
},
{
"epoch": 3.618556701030928,
"grad_norm": 0.33327534794807434,
"learning_rate": 4.4920127785397615e-06,
"loss": 0.1046,
"step": 119
},
{
"epoch": 3.649484536082474,
"grad_norm": 0.26345059275627136,
"learning_rate": 4.43927822676105e-06,
"loss": 0.1036,
"step": 120
},
{
"epoch": 3.680412371134021,
"grad_norm": 0.4857600927352905,
"learning_rate": 4.384282563318403e-06,
"loss": 0.1059,
"step": 121
},
{
"epoch": 3.711340206185567,
"grad_norm": 0.5701199173927307,
"learning_rate": 4.32708991069531e-06,
"loss": 0.1048,
"step": 122
},
{
"epoch": 3.7422680412371134,
"grad_norm": 0.6222259998321533,
"learning_rate": 4.267766952966369e-06,
"loss": 0.1031,
"step": 123
},
{
"epoch": 3.7731958762886597,
"grad_norm": 0.3183295428752899,
"learning_rate": 4.206382858046636e-06,
"loss": 0.0993,
"step": 124
},
{
"epoch": 3.804123711340206,
"grad_norm": 0.4618447721004486,
"learning_rate": 4.143009197044932e-06,
"loss": 0.1049,
"step": 125
},
{
"epoch": 3.8350515463917527,
"grad_norm": 0.48689910769462585,
"learning_rate": 4.077719860815132e-06,
"loss": 0.1004,
"step": 126
},
{
"epoch": 3.865979381443299,
"grad_norm": 0.5205806493759155,
"learning_rate": 4.010590973802737e-06,
"loss": 0.1044,
"step": 127
},
{
"epoch": 3.8969072164948453,
"grad_norm": 0.29967570304870605,
"learning_rate": 3.941700805287169e-06,
"loss": 0.101,
"step": 128
},
{
"epoch": 3.927835051546392,
"grad_norm": 0.4049663543701172,
"learning_rate": 3.871129678123297e-06,
"loss": 0.1023,
"step": 129
},
{
"epoch": 3.9587628865979383,
"grad_norm": 0.3243454098701477,
"learning_rate": 3.798959875088584e-06,
"loss": 0.0996,
"step": 130
},
{
"epoch": 3.9896907216494846,
"grad_norm": 0.2899306118488312,
"learning_rate": 3.7252755429450437e-06,
"loss": 0.098,
"step": 131
},
{
"epoch": 4.0,
"grad_norm": 0.2899306118488312,
"learning_rate": 3.650162594327881e-06,
"loss": 0.0992,
"step": 132
},
{
"epoch": 4.030927835051546,
"grad_norm": 1.1642309427261353,
"learning_rate": 3.5737086075752054e-06,
"loss": 0.0959,
"step": 133
},
{
"epoch": 4.061855670103093,
"grad_norm": 0.7160468697547913,
"learning_rate": 3.4960027246156043e-06,
"loss": 0.1032,
"step": 134
},
{
"epoch": 4.092783505154639,
"grad_norm": 0.5639675855636597,
"learning_rate": 3.417135547032642e-06,
"loss": 0.0991,
"step": 135
},
{
"epoch": 4.123711340206185,
"grad_norm": 0.4824839234352112,
"learning_rate": 3.3371990304274654e-06,
"loss": 0.0924,
"step": 136
},
{
"epoch": 4.154639175257732,
"grad_norm": 0.47185495495796204,
"learning_rate": 3.25628637720269e-06,
"loss": 0.0965,
"step": 137
},
{
"epoch": 4.185567010309279,
"grad_norm": 0.7727807760238647,
"learning_rate": 3.174491927892561e-06,
"loss": 0.1004,
"step": 138
},
{
"epoch": 4.216494845360825,
"grad_norm": 0.8841911554336548,
"learning_rate": 3.091911051166117e-06,
"loss": 0.1037,
"step": 139
},
{
"epoch": 4.247422680412371,
"grad_norm": 1.0637952089309692,
"learning_rate": 3.0086400326315853e-06,
"loss": 0.0988,
"step": 140
},
{
"epoch": 4.278350515463917,
"grad_norm": 0.8243911266326904,
"learning_rate": 2.924775962571667e-06,
"loss": 0.0973,
"step": 141
},
{
"epoch": 4.309278350515464,
"grad_norm": 0.7223678827285767,
"learning_rate": 2.840416622740617e-06,
"loss": 0.0967,
"step": 142
},
{
"epoch": 4.34020618556701,
"grad_norm": 0.6225246787071228,
"learning_rate": 2.7556603723550855e-06,
"loss": 0.1013,
"step": 143
},
{
"epoch": 4.371134020618557,
"grad_norm": 0.4938095211982727,
"learning_rate": 2.670606033411678e-06,
"loss": 0.0939,
"step": 144
},
{
"epoch": 4.402061855670103,
"grad_norm": 0.521511435508728,
"learning_rate": 2.58535277546492e-06,
"loss": 0.1026,
"step": 145
},
{
"epoch": 4.43298969072165,
"grad_norm": 0.6362576484680176,
"learning_rate": 2.5e-06,
"loss": 0.0977,
"step": 146
},
{
"epoch": 4.463917525773196,
"grad_norm": 0.523650586605072,
"learning_rate": 2.4146472245350804e-06,
"loss": 0.0994,
"step": 147
},
{
"epoch": 4.494845360824742,
"grad_norm": 0.6778432726860046,
"learning_rate": 2.3293939665883233e-06,
"loss": 0.0927,
"step": 148
},
{
"epoch": 4.525773195876289,
"grad_norm": 0.5455223917961121,
"learning_rate": 2.2443396276449145e-06,
"loss": 0.0957,
"step": 149
},
{
"epoch": 4.556701030927835,
"grad_norm": 0.5670258402824402,
"learning_rate": 2.159583377259384e-06,
"loss": 0.0932,
"step": 150
},
{
"epoch": 4.587628865979381,
"grad_norm": 0.6063594818115234,
"learning_rate": 2.0752240374283334e-06,
"loss": 0.097,
"step": 151
},
{
"epoch": 4.618556701030927,
"grad_norm": 0.8716773390769958,
"learning_rate": 1.991359967368416e-06,
"loss": 0.0932,
"step": 152
},
{
"epoch": 4.649484536082475,
"grad_norm": 0.5040673613548279,
"learning_rate": 1.9080889488338833e-06,
"loss": 0.0945,
"step": 153
},
{
"epoch": 4.680412371134021,
"grad_norm": 0.7626310586929321,
"learning_rate": 1.8255080721074391e-06,
"loss": 0.0907,
"step": 154
},
{
"epoch": 4.711340206185567,
"grad_norm": 0.7159733176231384,
"learning_rate": 1.7437136227973108e-06,
"loss": 0.0959,
"step": 155
},
{
"epoch": 4.742268041237113,
"grad_norm": 0.7429032325744629,
"learning_rate": 1.6628009695725348e-06,
"loss": 0.0891,
"step": 156
},
{
"epoch": 4.77319587628866,
"grad_norm": 0.7814318537712097,
"learning_rate": 1.5828644529673592e-06,
"loss": 0.0888,
"step": 157
},
{
"epoch": 4.804123711340206,
"grad_norm": 0.9120146036148071,
"learning_rate": 1.5039972753843966e-06,
"loss": 0.0902,
"step": 158
},
{
"epoch": 4.835051546391752,
"grad_norm": 0.6306695342063904,
"learning_rate": 1.4262913924247956e-06,
"loss": 0.0871,
"step": 159
},
{
"epoch": 4.8659793814432994,
"grad_norm": 0.9792791604995728,
"learning_rate": 1.3498374056721198e-06,
"loss": 0.0943,
"step": 160
},
{
"epoch": 4.896907216494846,
"grad_norm": 1.5480984449386597,
"learning_rate": 1.2747244570549578e-06,
"loss": 0.0978,
"step": 161
},
{
"epoch": 4.927835051546392,
"grad_norm": 0.7049218416213989,
"learning_rate": 1.2010401249114166e-06,
"loss": 0.0879,
"step": 162
},
{
"epoch": 4.958762886597938,
"grad_norm": 1.0587555170059204,
"learning_rate": 1.1288703218767027e-06,
"loss": 0.0868,
"step": 163
},
{
"epoch": 4.989690721649485,
"grad_norm": 0.9614342451095581,
"learning_rate": 1.0582991947128324e-06,
"loss": 0.0921,
"step": 164
},
{
"epoch": 5.0,
"grad_norm": 0.9614342451095581,
"learning_rate": 9.89409026197264e-07,
"loss": 0.0744,
"step": 165
},
{
"epoch": 5.030927835051546,
"grad_norm": 2.484208106994629,
"learning_rate": 9.222801391848688e-07,
"loss": 0.09,
"step": 166
},
{
"epoch": 5.061855670103093,
"grad_norm": 1.0592623949050903,
"learning_rate": 8.569908029550686e-07,
"loss": 0.085,
"step": 167
},
{
"epoch": 5.092783505154639,
"grad_norm": 1.5516217947006226,
"learning_rate": 7.936171419533653e-07,
"loss": 0.0871,
"step": 168
},
{
"epoch": 5.123711340206185,
"grad_norm": 1.048254132270813,
"learning_rate": 7.322330470336314e-07,
"loss": 0.0859,
"step": 169
},
{
"epoch": 5.154639175257732,
"grad_norm": 1.14556086063385,
"learning_rate": 6.729100893046897e-07,
"loss": 0.0895,
"step": 170
},
{
"epoch": 5.185567010309279,
"grad_norm": 0.8058810234069824,
"learning_rate": 6.157174366815979e-07,
"loss": 0.0866,
"step": 171
},
{
"epoch": 5.216494845360825,
"grad_norm": 0.7695685625076294,
"learning_rate": 5.607217732389503e-07,
"loss": 0.0851,
"step": 172
},
{
"epoch": 5.247422680412371,
"grad_norm": 0.9549402594566345,
"learning_rate": 5.079872214602388e-07,
"loss": 0.0866,
"step": 173
},
{
"epoch": 5.278350515463917,
"grad_norm": 1.521871566772461,
"learning_rate": 4.5757526747389506e-07,
"loss": 0.0834,
"step": 174
},
{
"epoch": 5.309278350515464,
"grad_norm": 0.7393187284469604,
"learning_rate": 4.095446893632235e-07,
"loss": 0.0845,
"step": 175
},
{
"epoch": 5.34020618556701,
"grad_norm": 0.7789802551269531,
"learning_rate": 3.639514886337786e-07,
"loss": 0.0821,
"step": 176
},
{
"epoch": 5.371134020618557,
"grad_norm": 0.7179467082023621,
"learning_rate": 3.208488249181216e-07,
"loss": 0.079,
"step": 177
},
{
"epoch": 5.402061855670103,
"grad_norm": 0.7849685549736023,
"learning_rate": 2.80286953994062e-07,
"loss": 0.0829,
"step": 178
},
{
"epoch": 5.43298969072165,
"grad_norm": 1.0993801355361938,
"learning_rate": 2.423131691886682e-07,
"loss": 0.0876,
"step": 179
},
{
"epoch": 5.463917525773196,
"grad_norm": 0.8301159143447876,
"learning_rate": 2.0697174623636795e-07,
"loss": 0.0872,
"step": 180
},
{
"epoch": 5.494845360824742,
"grad_norm": 1.1351754665374756,
"learning_rate": 1.743038916554171e-07,
"loss": 0.0883,
"step": 181
},
{
"epoch": 5.525773195876289,
"grad_norm": 1.0282760858535767,
"learning_rate": 1.44347694702949e-07,
"loss": 0.0785,
"step": 182
},
{
"epoch": 5.556701030927835,
"grad_norm": 0.7519952058792114,
"learning_rate": 1.1713808296459794e-07,
"loss": 0.0862,
"step": 183
},
{
"epoch": 5.587628865979381,
"grad_norm": 0.7985242605209351,
"learning_rate": 9.270678163050218e-08,
"loss": 0.0831,
"step": 184
},
{
"epoch": 5.618556701030927,
"grad_norm": 0.783128559589386,
"learning_rate": 7.108227650514637e-08,
"loss": 0.0766,
"step": 185
},
{
"epoch": 5.649484536082475,
"grad_norm": 0.9066674113273621,
"learning_rate": 5.2289780794192726e-08,
"loss": 0.0812,
"step": 186
},
{
"epoch": 5.680412371134021,
"grad_norm": 1.1403989791870117,
"learning_rate": 3.635120570700784e-08,
"loss": 0.0871,
"step": 187
},
{
"epoch": 5.711340206185567,
"grad_norm": 0.9781270027160645,
"learning_rate": 2.3285134909173113e-08,
"loss": 0.0816,
"step": 188
},
{
"epoch": 5.742268041237113,
"grad_norm": 0.8195537328720093,
"learning_rate": 1.3106802854762901e-08,
"loss": 0.0838,
"step": 189
},
{
"epoch": 5.77319587628866,
"grad_norm": 1.0189077854156494,
"learning_rate": 5.828077023651846e-09,
"loss": 0.0843,
"step": 190
},
{
"epoch": 5.804123711340206,
"grad_norm": 1.030791163444519,
"learning_rate": 1.4574440845649406e-09,
"loss": 0.0847,
"step": 191
},
{
"epoch": 5.835051546391752,
"grad_norm": 1.2187172174453735,
"learning_rate": 0.0,
"loss": 0.0841,
"step": 192
}
],
"logging_steps": 1,
"max_steps": 192,
"num_input_tokens_seen": 0,
"num_train_epochs": 6,
"save_steps": 32,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 4.2077352764217754e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}