model_32aa9ae6 / checkpoint-234 /trainer_state.json
ugaoo's picture
Upload folder using huggingface_hub
f69e8c7 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.9886363636363638,
"eval_steps": 500,
"global_step": 234,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.008522727272727272,
"grad_norm": 35.49958801269531,
"learning_rate": 5.0000000000000004e-08,
"loss": 4.6143,
"step": 1
},
{
"epoch": 0.017045454545454544,
"grad_norm": 35.543556213378906,
"learning_rate": 1.0000000000000001e-07,
"loss": 4.6719,
"step": 2
},
{
"epoch": 0.02556818181818182,
"grad_norm": 34.12852096557617,
"learning_rate": 1.5000000000000002e-07,
"loss": 4.5546,
"step": 3
},
{
"epoch": 0.03409090909090909,
"grad_norm": 33.610572814941406,
"learning_rate": 2.0000000000000002e-07,
"loss": 4.4919,
"step": 4
},
{
"epoch": 0.04261363636363636,
"grad_norm": 34.532169342041016,
"learning_rate": 2.5000000000000004e-07,
"loss": 4.6095,
"step": 5
},
{
"epoch": 0.05113636363636364,
"grad_norm": 34.2357063293457,
"learning_rate": 3.0000000000000004e-07,
"loss": 4.585,
"step": 6
},
{
"epoch": 0.05965909090909091,
"grad_norm": 34.94609832763672,
"learning_rate": 3.5000000000000004e-07,
"loss": 4.5911,
"step": 7
},
{
"epoch": 0.06818181818181818,
"grad_norm": 34.79508590698242,
"learning_rate": 4.0000000000000003e-07,
"loss": 4.6294,
"step": 8
},
{
"epoch": 0.07670454545454546,
"grad_norm": 35.18478775024414,
"learning_rate": 4.5000000000000003e-07,
"loss": 4.6568,
"step": 9
},
{
"epoch": 0.08522727272727272,
"grad_norm": 33.75633239746094,
"learning_rate": 5.000000000000001e-07,
"loss": 4.4504,
"step": 10
},
{
"epoch": 0.09375,
"grad_norm": 34.20966339111328,
"learning_rate": 5.5e-07,
"loss": 4.5005,
"step": 11
},
{
"epoch": 0.10227272727272728,
"grad_norm": 33.20008087158203,
"learning_rate": 6.000000000000001e-07,
"loss": 4.4297,
"step": 12
},
{
"epoch": 0.11079545454545454,
"grad_norm": 33.53578567504883,
"learning_rate": 6.5e-07,
"loss": 4.4136,
"step": 13
},
{
"epoch": 0.11931818181818182,
"grad_norm": 31.951068878173828,
"learning_rate": 7.000000000000001e-07,
"loss": 4.3065,
"step": 14
},
{
"epoch": 0.1278409090909091,
"grad_norm": 30.890714645385742,
"learning_rate": 7.5e-07,
"loss": 4.2433,
"step": 15
},
{
"epoch": 0.13636363636363635,
"grad_norm": 29.448890686035156,
"learning_rate": 8.000000000000001e-07,
"loss": 4.0981,
"step": 16
},
{
"epoch": 0.14488636363636365,
"grad_norm": 26.769498825073242,
"learning_rate": 8.500000000000001e-07,
"loss": 3.9818,
"step": 17
},
{
"epoch": 0.1534090909090909,
"grad_norm": 25.418458938598633,
"learning_rate": 9.000000000000001e-07,
"loss": 3.8568,
"step": 18
},
{
"epoch": 0.16193181818181818,
"grad_norm": 24.099462509155273,
"learning_rate": 9.500000000000001e-07,
"loss": 3.7139,
"step": 19
},
{
"epoch": 0.17045454545454544,
"grad_norm": 22.487621307373047,
"learning_rate": 1.0000000000000002e-06,
"loss": 3.6967,
"step": 20
},
{
"epoch": 0.17897727272727273,
"grad_norm": 20.72856330871582,
"learning_rate": 1.0500000000000001e-06,
"loss": 3.5031,
"step": 21
},
{
"epoch": 0.1875,
"grad_norm": 19.552040100097656,
"learning_rate": 1.1e-06,
"loss": 3.4201,
"step": 22
},
{
"epoch": 0.19602272727272727,
"grad_norm": 18.033971786499023,
"learning_rate": 1.1500000000000002e-06,
"loss": 3.1842,
"step": 23
},
{
"epoch": 0.20454545454545456,
"grad_norm": 18.865802764892578,
"learning_rate": 1.2000000000000002e-06,
"loss": 3.1982,
"step": 24
},
{
"epoch": 0.21306818181818182,
"grad_norm": 18.849502563476562,
"learning_rate": 1.25e-06,
"loss": 2.9954,
"step": 25
},
{
"epoch": 0.2215909090909091,
"grad_norm": 19.714330673217773,
"learning_rate": 1.3e-06,
"loss": 2.8763,
"step": 26
},
{
"epoch": 0.23011363636363635,
"grad_norm": 20.26412010192871,
"learning_rate": 1.3500000000000002e-06,
"loss": 2.7259,
"step": 27
},
{
"epoch": 0.23863636363636365,
"grad_norm": 19.212318420410156,
"learning_rate": 1.4000000000000001e-06,
"loss": 2.6099,
"step": 28
},
{
"epoch": 0.2471590909090909,
"grad_norm": 16.80523681640625,
"learning_rate": 1.45e-06,
"loss": 2.4482,
"step": 29
},
{
"epoch": 0.2556818181818182,
"grad_norm": 14.624052047729492,
"learning_rate": 1.5e-06,
"loss": 2.2364,
"step": 30
},
{
"epoch": 0.26420454545454547,
"grad_norm": 14.759950637817383,
"learning_rate": 1.5500000000000002e-06,
"loss": 2.2159,
"step": 31
},
{
"epoch": 0.2727272727272727,
"grad_norm": 14.904441833496094,
"learning_rate": 1.6000000000000001e-06,
"loss": 2.0206,
"step": 32
},
{
"epoch": 0.28125,
"grad_norm": 15.03490161895752,
"learning_rate": 1.6500000000000003e-06,
"loss": 1.8725,
"step": 33
},
{
"epoch": 0.2897727272727273,
"grad_norm": 15.70709228515625,
"learning_rate": 1.7000000000000002e-06,
"loss": 1.8046,
"step": 34
},
{
"epoch": 0.29829545454545453,
"grad_norm": 15.637526512145996,
"learning_rate": 1.75e-06,
"loss": 1.6198,
"step": 35
},
{
"epoch": 0.3068181818181818,
"grad_norm": 14.345853805541992,
"learning_rate": 1.8000000000000001e-06,
"loss": 1.4247,
"step": 36
},
{
"epoch": 0.3153409090909091,
"grad_norm": 14.281502723693848,
"learning_rate": 1.85e-06,
"loss": 1.2859,
"step": 37
},
{
"epoch": 0.32386363636363635,
"grad_norm": 13.567434310913086,
"learning_rate": 1.9000000000000002e-06,
"loss": 1.1452,
"step": 38
},
{
"epoch": 0.33238636363636365,
"grad_norm": 13.128920555114746,
"learning_rate": 1.9500000000000004e-06,
"loss": 1.0036,
"step": 39
},
{
"epoch": 0.3409090909090909,
"grad_norm": 12.954020500183105,
"learning_rate": 2.0000000000000003e-06,
"loss": 0.851,
"step": 40
},
{
"epoch": 0.3494318181818182,
"grad_norm": 12.533946990966797,
"learning_rate": 2.05e-06,
"loss": 0.715,
"step": 41
},
{
"epoch": 0.35795454545454547,
"grad_norm": 11.564764022827148,
"learning_rate": 2.1000000000000002e-06,
"loss": 0.5987,
"step": 42
},
{
"epoch": 0.3664772727272727,
"grad_norm": 10.383822441101074,
"learning_rate": 2.15e-06,
"loss": 0.4834,
"step": 43
},
{
"epoch": 0.375,
"grad_norm": 8.901700973510742,
"learning_rate": 2.2e-06,
"loss": 0.3808,
"step": 44
},
{
"epoch": 0.3835227272727273,
"grad_norm": 7.737320423126221,
"learning_rate": 2.25e-06,
"loss": 0.2975,
"step": 45
},
{
"epoch": 0.39204545454545453,
"grad_norm": 5.334733963012695,
"learning_rate": 2.3000000000000004e-06,
"loss": 0.2261,
"step": 46
},
{
"epoch": 0.4005681818181818,
"grad_norm": 3.3499741554260254,
"learning_rate": 2.35e-06,
"loss": 0.1854,
"step": 47
},
{
"epoch": 0.4090909090909091,
"grad_norm": 2.4037742614746094,
"learning_rate": 2.4000000000000003e-06,
"loss": 0.1532,
"step": 48
},
{
"epoch": 0.41761363636363635,
"grad_norm": 1.8914185762405396,
"learning_rate": 2.4500000000000003e-06,
"loss": 0.1372,
"step": 49
},
{
"epoch": 0.42613636363636365,
"grad_norm": 1.7124507427215576,
"learning_rate": 2.5e-06,
"loss": 0.136,
"step": 50
},
{
"epoch": 0.4346590909090909,
"grad_norm": 1.242527961730957,
"learning_rate": 2.55e-06,
"loss": 0.1238,
"step": 51
},
{
"epoch": 0.4431818181818182,
"grad_norm": 0.9835780262947083,
"learning_rate": 2.6e-06,
"loss": 0.1192,
"step": 52
},
{
"epoch": 0.45170454545454547,
"grad_norm": 1.0163497924804688,
"learning_rate": 2.6500000000000005e-06,
"loss": 0.1175,
"step": 53
},
{
"epoch": 0.4602272727272727,
"grad_norm": 0.8837094306945801,
"learning_rate": 2.7000000000000004e-06,
"loss": 0.1104,
"step": 54
},
{
"epoch": 0.46875,
"grad_norm": 0.6102741956710815,
"learning_rate": 2.7500000000000004e-06,
"loss": 0.0986,
"step": 55
},
{
"epoch": 0.4772727272727273,
"grad_norm": 0.85715252161026,
"learning_rate": 2.8000000000000003e-06,
"loss": 0.1083,
"step": 56
},
{
"epoch": 0.48579545454545453,
"grad_norm": 0.9692059755325317,
"learning_rate": 2.85e-06,
"loss": 0.0994,
"step": 57
},
{
"epoch": 0.4943181818181818,
"grad_norm": 0.5620752573013306,
"learning_rate": 2.9e-06,
"loss": 0.0909,
"step": 58
},
{
"epoch": 0.5028409090909091,
"grad_norm": 0.5377550721168518,
"learning_rate": 2.95e-06,
"loss": 0.087,
"step": 59
},
{
"epoch": 0.5113636363636364,
"grad_norm": 0.7260486483573914,
"learning_rate": 3e-06,
"loss": 0.0949,
"step": 60
},
{
"epoch": 0.5198863636363636,
"grad_norm": 0.5636699199676514,
"learning_rate": 3.05e-06,
"loss": 0.0884,
"step": 61
},
{
"epoch": 0.5284090909090909,
"grad_norm": 0.3729614019393921,
"learning_rate": 3.1000000000000004e-06,
"loss": 0.0771,
"step": 62
},
{
"epoch": 0.5369318181818182,
"grad_norm": 0.5472120046615601,
"learning_rate": 3.1500000000000003e-06,
"loss": 0.0887,
"step": 63
},
{
"epoch": 0.5454545454545454,
"grad_norm": 0.4915490448474884,
"learning_rate": 3.2000000000000003e-06,
"loss": 0.0826,
"step": 64
},
{
"epoch": 0.5539772727272727,
"grad_norm": 0.4123076796531677,
"learning_rate": 3.2500000000000002e-06,
"loss": 0.0834,
"step": 65
},
{
"epoch": 0.5625,
"grad_norm": 0.32767826318740845,
"learning_rate": 3.3000000000000006e-06,
"loss": 0.0765,
"step": 66
},
{
"epoch": 0.5710227272727273,
"grad_norm": 0.34970155358314514,
"learning_rate": 3.3500000000000005e-06,
"loss": 0.0832,
"step": 67
},
{
"epoch": 0.5795454545454546,
"grad_norm": 0.38679587841033936,
"learning_rate": 3.4000000000000005e-06,
"loss": 0.0766,
"step": 68
},
{
"epoch": 0.5880681818181818,
"grad_norm": 0.5464550852775574,
"learning_rate": 3.45e-06,
"loss": 0.0748,
"step": 69
},
{
"epoch": 0.5965909090909091,
"grad_norm": 0.3545376658439636,
"learning_rate": 3.5e-06,
"loss": 0.0759,
"step": 70
},
{
"epoch": 0.6051136363636364,
"grad_norm": 0.3532780110836029,
"learning_rate": 3.5500000000000003e-06,
"loss": 0.0728,
"step": 71
},
{
"epoch": 0.6136363636363636,
"grad_norm": 0.5024192929267883,
"learning_rate": 3.6000000000000003e-06,
"loss": 0.081,
"step": 72
},
{
"epoch": 0.6221590909090909,
"grad_norm": 0.3845844268798828,
"learning_rate": 3.65e-06,
"loss": 0.0689,
"step": 73
},
{
"epoch": 0.6306818181818182,
"grad_norm": 0.46010249853134155,
"learning_rate": 3.7e-06,
"loss": 0.0757,
"step": 74
},
{
"epoch": 0.6392045454545454,
"grad_norm": 0.36048972606658936,
"learning_rate": 3.7500000000000005e-06,
"loss": 0.0758,
"step": 75
},
{
"epoch": 0.6477272727272727,
"grad_norm": 0.2978876829147339,
"learning_rate": 3.8000000000000005e-06,
"loss": 0.0747,
"step": 76
},
{
"epoch": 0.65625,
"grad_norm": 0.30899888277053833,
"learning_rate": 3.85e-06,
"loss": 0.0788,
"step": 77
},
{
"epoch": 0.6647727272727273,
"grad_norm": 0.45000651478767395,
"learning_rate": 3.900000000000001e-06,
"loss": 0.0672,
"step": 78
},
{
"epoch": 0.6732954545454546,
"grad_norm": 0.2621772587299347,
"learning_rate": 3.95e-06,
"loss": 0.0719,
"step": 79
},
{
"epoch": 0.6818181818181818,
"grad_norm": 0.28618085384368896,
"learning_rate": 4.000000000000001e-06,
"loss": 0.0744,
"step": 80
},
{
"epoch": 0.6903409090909091,
"grad_norm": 0.40642479062080383,
"learning_rate": 4.05e-06,
"loss": 0.0743,
"step": 81
},
{
"epoch": 0.6988636363636364,
"grad_norm": 0.3514344096183777,
"learning_rate": 4.1e-06,
"loss": 0.0708,
"step": 82
},
{
"epoch": 0.7073863636363636,
"grad_norm": 0.426798939704895,
"learning_rate": 4.15e-06,
"loss": 0.073,
"step": 83
},
{
"epoch": 0.7159090909090909,
"grad_norm": 0.29413217306137085,
"learning_rate": 4.2000000000000004e-06,
"loss": 0.0732,
"step": 84
},
{
"epoch": 0.7244318181818182,
"grad_norm": 0.37668099999427795,
"learning_rate": 4.25e-06,
"loss": 0.0664,
"step": 85
},
{
"epoch": 0.7329545454545454,
"grad_norm": 0.3696061372756958,
"learning_rate": 4.3e-06,
"loss": 0.0649,
"step": 86
},
{
"epoch": 0.7414772727272727,
"grad_norm": 0.311988890171051,
"learning_rate": 4.350000000000001e-06,
"loss": 0.0689,
"step": 87
},
{
"epoch": 0.75,
"grad_norm": 0.3180747628211975,
"learning_rate": 4.4e-06,
"loss": 0.0746,
"step": 88
},
{
"epoch": 0.7585227272727273,
"grad_norm": 0.46045729517936707,
"learning_rate": 4.450000000000001e-06,
"loss": 0.0763,
"step": 89
},
{
"epoch": 0.7670454545454546,
"grad_norm": 0.3566094934940338,
"learning_rate": 4.5e-06,
"loss": 0.0676,
"step": 90
},
{
"epoch": 0.7755681818181818,
"grad_norm": 0.35632985830307007,
"learning_rate": 4.5500000000000005e-06,
"loss": 0.0677,
"step": 91
},
{
"epoch": 0.7840909090909091,
"grad_norm": 0.27962526679039,
"learning_rate": 4.600000000000001e-06,
"loss": 0.0689,
"step": 92
},
{
"epoch": 0.7926136363636364,
"grad_norm": 0.4532427191734314,
"learning_rate": 4.65e-06,
"loss": 0.0724,
"step": 93
},
{
"epoch": 0.8011363636363636,
"grad_norm": 0.363337904214859,
"learning_rate": 4.7e-06,
"loss": 0.0708,
"step": 94
},
{
"epoch": 0.8096590909090909,
"grad_norm": 0.3065521717071533,
"learning_rate": 4.75e-06,
"loss": 0.0713,
"step": 95
},
{
"epoch": 0.8181818181818182,
"grad_norm": 0.24705548584461212,
"learning_rate": 4.800000000000001e-06,
"loss": 0.0683,
"step": 96
},
{
"epoch": 0.8267045454545454,
"grad_norm": 0.5038250684738159,
"learning_rate": 4.85e-06,
"loss": 0.0738,
"step": 97
},
{
"epoch": 0.8352272727272727,
"grad_norm": 0.2972690761089325,
"learning_rate": 4.9000000000000005e-06,
"loss": 0.0684,
"step": 98
},
{
"epoch": 0.84375,
"grad_norm": 0.40811270475387573,
"learning_rate": 4.95e-06,
"loss": 0.066,
"step": 99
},
{
"epoch": 0.8522727272727273,
"grad_norm": 0.3925577998161316,
"learning_rate": 5e-06,
"loss": 0.0692,
"step": 100
},
{
"epoch": 0.8607954545454546,
"grad_norm": 0.32043716311454773,
"learning_rate": 4.999965957943338e-06,
"loss": 0.0652,
"step": 101
},
{
"epoch": 0.8693181818181818,
"grad_norm": 0.26025497913360596,
"learning_rate": 4.999863832700438e-06,
"loss": 0.0634,
"step": 102
},
{
"epoch": 0.8778409090909091,
"grad_norm": 0.5605457425117493,
"learning_rate": 4.999693627052545e-06,
"loss": 0.0686,
"step": 103
},
{
"epoch": 0.8863636363636364,
"grad_norm": 0.48003220558166504,
"learning_rate": 4.9994553456349785e-06,
"loss": 0.0707,
"step": 104
},
{
"epoch": 0.8948863636363636,
"grad_norm": 0.22346197068691254,
"learning_rate": 4.99914899493701e-06,
"loss": 0.067,
"step": 105
},
{
"epoch": 0.9034090909090909,
"grad_norm": 0.45966312289237976,
"learning_rate": 4.998774583301685e-06,
"loss": 0.0663,
"step": 106
},
{
"epoch": 0.9119318181818182,
"grad_norm": 0.38695356249809265,
"learning_rate": 4.998332120925598e-06,
"loss": 0.0714,
"step": 107
},
{
"epoch": 0.9204545454545454,
"grad_norm": 0.35708868503570557,
"learning_rate": 4.997821619858614e-06,
"loss": 0.0632,
"step": 108
},
{
"epoch": 0.9289772727272727,
"grad_norm": 0.2699528932571411,
"learning_rate": 4.9972430940035355e-06,
"loss": 0.0649,
"step": 109
},
{
"epoch": 0.9375,
"grad_norm": 0.5043486952781677,
"learning_rate": 4.9965965591157314e-06,
"loss": 0.0715,
"step": 110
},
{
"epoch": 0.9460227272727273,
"grad_norm": 0.4046338200569153,
"learning_rate": 4.995882032802703e-06,
"loss": 0.0657,
"step": 111
},
{
"epoch": 0.9545454545454546,
"grad_norm": 0.3543775677680969,
"learning_rate": 4.995099534523608e-06,
"loss": 0.0698,
"step": 112
},
{
"epoch": 0.9630681818181818,
"grad_norm": 0.3295219838619232,
"learning_rate": 4.994249085588725e-06,
"loss": 0.0719,
"step": 113
},
{
"epoch": 0.9715909090909091,
"grad_norm": 0.3691340982913971,
"learning_rate": 4.993330709158879e-06,
"loss": 0.0689,
"step": 114
},
{
"epoch": 0.9801136363636364,
"grad_norm": 0.4219862222671509,
"learning_rate": 4.9923444302448095e-06,
"loss": 0.0644,
"step": 115
},
{
"epoch": 0.9886363636363636,
"grad_norm": 0.33437392115592957,
"learning_rate": 4.991290275706486e-06,
"loss": 0.074,
"step": 116
},
{
"epoch": 0.9971590909090909,
"grad_norm": 0.22970478236675262,
"learning_rate": 4.990168274252379e-06,
"loss": 0.0639,
"step": 117
},
{
"epoch": 1.0,
"grad_norm": 0.22970478236675262,
"learning_rate": 4.988978456438678e-06,
"loss": 0.0718,
"step": 118
},
{
"epoch": 1.0085227272727273,
"grad_norm": 0.7316553592681885,
"learning_rate": 4.98772085466846e-06,
"loss": 0.062,
"step": 119
},
{
"epoch": 1.0170454545454546,
"grad_norm": 0.27226850390434265,
"learning_rate": 4.986395503190805e-06,
"loss": 0.0583,
"step": 120
},
{
"epoch": 1.0255681818181819,
"grad_norm": 0.20066767930984497,
"learning_rate": 4.9850024380998655e-06,
"loss": 0.0624,
"step": 121
},
{
"epoch": 1.0340909090909092,
"grad_norm": 0.26274779438972473,
"learning_rate": 4.9835416973338815e-06,
"loss": 0.0641,
"step": 122
},
{
"epoch": 1.0426136363636365,
"grad_norm": 0.3893499970436096,
"learning_rate": 4.982013320674149e-06,
"loss": 0.066,
"step": 123
},
{
"epoch": 1.0511363636363635,
"grad_norm": 0.3454163670539856,
"learning_rate": 4.980417349743936e-06,
"loss": 0.061,
"step": 124
},
{
"epoch": 1.0596590909090908,
"grad_norm": 0.26956701278686523,
"learning_rate": 4.97875382800735e-06,
"loss": 0.0641,
"step": 125
},
{
"epoch": 1.0681818181818181,
"grad_norm": 0.4147774279117584,
"learning_rate": 4.97702280076815e-06,
"loss": 0.0599,
"step": 126
},
{
"epoch": 1.0767045454545454,
"grad_norm": 0.2839421033859253,
"learning_rate": 4.9752243151685185e-06,
"loss": 0.0669,
"step": 127
},
{
"epoch": 1.0852272727272727,
"grad_norm": 0.41760239005088806,
"learning_rate": 4.973358420187776e-06,
"loss": 0.0661,
"step": 128
},
{
"epoch": 1.09375,
"grad_norm": 0.29833659529685974,
"learning_rate": 4.9714251666410426e-06,
"loss": 0.0672,
"step": 129
},
{
"epoch": 1.1022727272727273,
"grad_norm": 0.2806449830532074,
"learning_rate": 4.969424607177861e-06,
"loss": 0.0589,
"step": 130
},
{
"epoch": 1.1107954545454546,
"grad_norm": 0.33876338601112366,
"learning_rate": 4.967356796280756e-06,
"loss": 0.0647,
"step": 131
},
{
"epoch": 1.1193181818181819,
"grad_norm": 0.2331860363483429,
"learning_rate": 4.96522179026376e-06,
"loss": 0.0633,
"step": 132
},
{
"epoch": 1.1278409090909092,
"grad_norm": 0.22244933247566223,
"learning_rate": 4.963019647270866e-06,
"loss": 0.0618,
"step": 133
},
{
"epoch": 1.1363636363636362,
"grad_norm": 0.24649232625961304,
"learning_rate": 4.960750427274458e-06,
"loss": 0.0565,
"step": 134
},
{
"epoch": 1.1448863636363638,
"grad_norm": 0.23454727232456207,
"learning_rate": 4.958414192073665e-06,
"loss": 0.0607,
"step": 135
},
{
"epoch": 1.1534090909090908,
"grad_norm": 0.28441867232322693,
"learning_rate": 4.956011005292693e-06,
"loss": 0.0548,
"step": 136
},
{
"epoch": 1.1619318181818181,
"grad_norm": 0.26571962237358093,
"learning_rate": 4.9535409323790726e-06,
"loss": 0.0596,
"step": 137
},
{
"epoch": 1.1704545454545454,
"grad_norm": 0.2692795991897583,
"learning_rate": 4.951004040601898e-06,
"loss": 0.0572,
"step": 138
},
{
"epoch": 1.1789772727272727,
"grad_norm": 0.35209110379219055,
"learning_rate": 4.9484003990499785e-06,
"loss": 0.0657,
"step": 139
},
{
"epoch": 1.1875,
"grad_norm": 0.2726614773273468,
"learning_rate": 4.945730078629965e-06,
"loss": 0.0561,
"step": 140
},
{
"epoch": 1.1960227272727273,
"grad_norm": 0.2439083456993103,
"learning_rate": 4.942993152064415e-06,
"loss": 0.0594,
"step": 141
},
{
"epoch": 1.2045454545454546,
"grad_norm": 0.23282821476459503,
"learning_rate": 4.940189693889819e-06,
"loss": 0.0598,
"step": 142
},
{
"epoch": 1.2130681818181819,
"grad_norm": 0.22507373988628387,
"learning_rate": 4.937319780454559e-06,
"loss": 0.0632,
"step": 143
},
{
"epoch": 1.2215909090909092,
"grad_norm": 0.35792839527130127,
"learning_rate": 4.934383489916843e-06,
"loss": 0.0626,
"step": 144
},
{
"epoch": 1.2301136363636362,
"grad_norm": 0.3073280453681946,
"learning_rate": 4.931380902242564e-06,
"loss": 0.0558,
"step": 145
},
{
"epoch": 1.2386363636363638,
"grad_norm": 0.2743082642555237,
"learning_rate": 4.928312099203131e-06,
"loss": 0.0638,
"step": 146
},
{
"epoch": 1.2471590909090908,
"grad_norm": 0.2522992491722107,
"learning_rate": 4.925177164373237e-06,
"loss": 0.0599,
"step": 147
},
{
"epoch": 1.2556818181818181,
"grad_norm": 0.25230202078819275,
"learning_rate": 4.921976183128585e-06,
"loss": 0.0579,
"step": 148
},
{
"epoch": 1.2642045454545454,
"grad_norm": 0.24467583000659943,
"learning_rate": 4.918709242643563e-06,
"loss": 0.0607,
"step": 149
},
{
"epoch": 1.2727272727272727,
"grad_norm": 0.2191130518913269,
"learning_rate": 4.915376431888871e-06,
"loss": 0.0622,
"step": 150
},
{
"epoch": 1.28125,
"grad_norm": 0.26959559321403503,
"learning_rate": 4.911977841629092e-06,
"loss": 0.0568,
"step": 151
},
{
"epoch": 1.2897727272727273,
"grad_norm": 0.25139617919921875,
"learning_rate": 4.908513564420231e-06,
"loss": 0.0607,
"step": 152
},
{
"epoch": 1.2982954545454546,
"grad_norm": 0.27705878019332886,
"learning_rate": 4.904983694607183e-06,
"loss": 0.0607,
"step": 153
},
{
"epoch": 1.3068181818181819,
"grad_norm": 0.2860431373119354,
"learning_rate": 4.9013883283211705e-06,
"loss": 0.0572,
"step": 154
},
{
"epoch": 1.3153409090909092,
"grad_norm": 0.27946561574935913,
"learning_rate": 4.897727563477123e-06,
"loss": 0.054,
"step": 155
},
{
"epoch": 1.3238636363636362,
"grad_norm": 0.25392627716064453,
"learning_rate": 4.894001499771015e-06,
"loss": 0.0623,
"step": 156
},
{
"epoch": 1.3323863636363638,
"grad_norm": 0.24209532141685486,
"learning_rate": 4.890210238677141e-06,
"loss": 0.0592,
"step": 157
},
{
"epoch": 1.3409090909090908,
"grad_norm": 0.23799730837345123,
"learning_rate": 4.886353883445363e-06,
"loss": 0.0545,
"step": 158
},
{
"epoch": 1.3494318181818181,
"grad_norm": 0.20330385863780975,
"learning_rate": 4.88243253909829e-06,
"loss": 0.0582,
"step": 159
},
{
"epoch": 1.3579545454545454,
"grad_norm": 0.2390514761209488,
"learning_rate": 4.878446312428424e-06,
"loss": 0.0558,
"step": 160
},
{
"epoch": 1.3664772727272727,
"grad_norm": 0.3132871687412262,
"learning_rate": 4.874395311995248e-06,
"loss": 0.0522,
"step": 161
},
{
"epoch": 1.375,
"grad_norm": 0.2441999763250351,
"learning_rate": 4.870279648122271e-06,
"loss": 0.0632,
"step": 162
},
{
"epoch": 1.3835227272727273,
"grad_norm": 0.3468320369720459,
"learning_rate": 4.866099432894023e-06,
"loss": 0.0544,
"step": 163
},
{
"epoch": 1.3920454545454546,
"grad_norm": 0.2637532949447632,
"learning_rate": 4.8618547801530045e-06,
"loss": 0.0508,
"step": 164
},
{
"epoch": 1.4005681818181819,
"grad_norm": 0.25950244069099426,
"learning_rate": 4.857545805496581e-06,
"loss": 0.0535,
"step": 165
},
{
"epoch": 1.4090909090909092,
"grad_norm": 0.24120447039604187,
"learning_rate": 4.853172626273841e-06,
"loss": 0.0563,
"step": 166
},
{
"epoch": 1.4176136363636362,
"grad_norm": 0.2234521359205246,
"learning_rate": 4.848735361582396e-06,
"loss": 0.0526,
"step": 167
},
{
"epoch": 1.4261363636363638,
"grad_norm": 0.24657292664051056,
"learning_rate": 4.844234132265139e-06,
"loss": 0.0596,
"step": 168
},
{
"epoch": 1.4346590909090908,
"grad_norm": 0.4169978201389313,
"learning_rate": 4.839669060906952e-06,
"loss": 0.0569,
"step": 169
},
{
"epoch": 1.4431818181818181,
"grad_norm": 0.24876588582992554,
"learning_rate": 4.835040271831371e-06,
"loss": 0.0555,
"step": 170
},
{
"epoch": 1.4517045454545454,
"grad_norm": 0.2905561923980713,
"learning_rate": 4.830347891097193e-06,
"loss": 0.0518,
"step": 171
},
{
"epoch": 1.4602272727272727,
"grad_norm": 0.32290127873420715,
"learning_rate": 4.8255920464950545e-06,
"loss": 0.0544,
"step": 172
},
{
"epoch": 1.46875,
"grad_norm": 0.3065219223499298,
"learning_rate": 4.820772867543939e-06,
"loss": 0.0563,
"step": 173
},
{
"epoch": 1.4772727272727273,
"grad_norm": 0.3081221878528595,
"learning_rate": 4.8158904854876555e-06,
"loss": 0.0595,
"step": 174
},
{
"epoch": 1.4857954545454546,
"grad_norm": 0.3171551823616028,
"learning_rate": 4.810945033291267e-06,
"loss": 0.0509,
"step": 175
},
{
"epoch": 1.4943181818181819,
"grad_norm": 0.46660706400871277,
"learning_rate": 4.805936645637463e-06,
"loss": 0.0575,
"step": 176
},
{
"epoch": 1.5028409090909092,
"grad_norm": 0.3173319399356842,
"learning_rate": 4.800865458922899e-06,
"loss": 0.0579,
"step": 177
},
{
"epoch": 1.5113636363636362,
"grad_norm": 0.2553943693637848,
"learning_rate": 4.795731611254473e-06,
"loss": 0.0602,
"step": 178
},
{
"epoch": 1.5198863636363638,
"grad_norm": 0.39231568574905396,
"learning_rate": 4.790535242445573e-06,
"loss": 0.0606,
"step": 179
},
{
"epoch": 1.5284090909090908,
"grad_norm": 0.2721359133720398,
"learning_rate": 4.7852764940122636e-06,
"loss": 0.0545,
"step": 180
},
{
"epoch": 1.5369318181818183,
"grad_norm": 0.2545195519924164,
"learning_rate": 4.779955509169435e-06,
"loss": 0.0546,
"step": 181
},
{
"epoch": 1.5454545454545454,
"grad_norm": 0.3155561685562134,
"learning_rate": 4.7745724328269e-06,
"loss": 0.0543,
"step": 182
},
{
"epoch": 1.5539772727272727,
"grad_norm": 0.24933341145515442,
"learning_rate": 4.769127411585452e-06,
"loss": 0.0571,
"step": 183
},
{
"epoch": 1.5625,
"grad_norm": 0.2886108458042145,
"learning_rate": 4.763620593732867e-06,
"loss": 0.0521,
"step": 184
},
{
"epoch": 1.5710227272727273,
"grad_norm": 0.23579014837741852,
"learning_rate": 4.75805212923987e-06,
"loss": 0.0551,
"step": 185
},
{
"epoch": 1.5795454545454546,
"grad_norm": 0.2821877896785736,
"learning_rate": 4.752422169756048e-06,
"loss": 0.0494,
"step": 186
},
{
"epoch": 1.5880681818181817,
"grad_norm": 0.28472304344177246,
"learning_rate": 4.746730868605721e-06,
"loss": 0.0524,
"step": 187
},
{
"epoch": 1.5965909090909092,
"grad_norm": 0.30284813046455383,
"learning_rate": 4.7409783807837654e-06,
"loss": 0.0519,
"step": 188
},
{
"epoch": 1.6051136363636362,
"grad_norm": 0.2568075656890869,
"learning_rate": 4.735164862951395e-06,
"loss": 0.0532,
"step": 189
},
{
"epoch": 1.6136363636363638,
"grad_norm": 0.28199082612991333,
"learning_rate": 4.729290473431892e-06,
"loss": 0.0578,
"step": 190
},
{
"epoch": 1.6221590909090908,
"grad_norm": 0.3818947970867157,
"learning_rate": 4.723355372206297e-06,
"loss": 0.0552,
"step": 191
},
{
"epoch": 1.6306818181818183,
"grad_norm": 0.26314595341682434,
"learning_rate": 4.717359720909053e-06,
"loss": 0.0505,
"step": 192
},
{
"epoch": 1.6392045454545454,
"grad_norm": 0.2616359293460846,
"learning_rate": 4.7113036828235995e-06,
"loss": 0.0511,
"step": 193
},
{
"epoch": 1.6477272727272727,
"grad_norm": 0.33692309260368347,
"learning_rate": 4.705187422877931e-06,
"loss": 0.0554,
"step": 194
},
{
"epoch": 1.65625,
"grad_norm": 0.30861467123031616,
"learning_rate": 4.6990111076401e-06,
"loss": 0.0485,
"step": 195
},
{
"epoch": 1.6647727272727273,
"grad_norm": 0.251370370388031,
"learning_rate": 4.692774905313687e-06,
"loss": 0.0454,
"step": 196
},
{
"epoch": 1.6732954545454546,
"grad_norm": 0.33005693554878235,
"learning_rate": 4.686478985733212e-06,
"loss": 0.0509,
"step": 197
},
{
"epoch": 1.6818181818181817,
"grad_norm": 0.39172685146331787,
"learning_rate": 4.68012352035952e-06,
"loss": 0.0552,
"step": 198
},
{
"epoch": 1.6903409090909092,
"grad_norm": 0.5113612413406372,
"learning_rate": 4.673708682275097e-06,
"loss": 0.0537,
"step": 199
},
{
"epoch": 1.6988636363636362,
"grad_norm": 0.27660125494003296,
"learning_rate": 4.667234646179368e-06,
"loss": 0.0463,
"step": 200
},
{
"epoch": 1.7073863636363638,
"grad_norm": 0.38760706782341003,
"learning_rate": 4.660701588383939e-06,
"loss": 0.0496,
"step": 201
},
{
"epoch": 1.7159090909090908,
"grad_norm": 0.3487601578235626,
"learning_rate": 4.654109686807787e-06,
"loss": 0.0498,
"step": 202
},
{
"epoch": 1.7244318181818183,
"grad_norm": 0.2964484393596649,
"learning_rate": 4.647459120972422e-06,
"loss": 0.0501,
"step": 203
},
{
"epoch": 1.7329545454545454,
"grad_norm": 0.3318927586078644,
"learning_rate": 4.640750071996995e-06,
"loss": 0.0535,
"step": 204
},
{
"epoch": 1.7414772727272727,
"grad_norm": 0.3152824640274048,
"learning_rate": 4.633982722593367e-06,
"loss": 0.0537,
"step": 205
},
{
"epoch": 1.75,
"grad_norm": 0.3267940878868103,
"learning_rate": 4.62715725706113e-06,
"loss": 0.0434,
"step": 206
},
{
"epoch": 1.7585227272727273,
"grad_norm": 0.32321202754974365,
"learning_rate": 4.620273861282593e-06,
"loss": 0.055,
"step": 207
},
{
"epoch": 1.7670454545454546,
"grad_norm": 0.3501484990119934,
"learning_rate": 4.613332722717714e-06,
"loss": 0.0458,
"step": 208
},
{
"epoch": 1.7755681818181817,
"grad_norm": 0.29107236862182617,
"learning_rate": 4.606334030399e-06,
"loss": 0.0496,
"step": 209
},
{
"epoch": 1.7840909090909092,
"grad_norm": 0.3194922208786011,
"learning_rate": 4.599277974926355e-06,
"loss": 0.0532,
"step": 210
},
{
"epoch": 1.7926136363636362,
"grad_norm": 0.2896871864795685,
"learning_rate": 4.592164748461892e-06,
"loss": 0.0482,
"step": 211
},
{
"epoch": 1.8011363636363638,
"grad_norm": 0.2559587061405182,
"learning_rate": 4.584994544724695e-06,
"loss": 0.0474,
"step": 212
},
{
"epoch": 1.8096590909090908,
"grad_norm": 0.3188915252685547,
"learning_rate": 4.577767558985552e-06,
"loss": 0.0454,
"step": 213
},
{
"epoch": 1.8181818181818183,
"grad_norm": 0.31643223762512207,
"learning_rate": 4.57048398806163e-06,
"loss": 0.0503,
"step": 214
},
{
"epoch": 1.8267045454545454,
"grad_norm": 0.3251838684082031,
"learning_rate": 4.563144030311114e-06,
"loss": 0.0484,
"step": 215
},
{
"epoch": 1.8352272727272727,
"grad_norm": 0.26603975892066956,
"learning_rate": 4.555747885627812e-06,
"loss": 0.0442,
"step": 216
},
{
"epoch": 1.84375,
"grad_norm": 0.4656536877155304,
"learning_rate": 4.548295755435703e-06,
"loss": 0.0428,
"step": 217
},
{
"epoch": 1.8522727272727273,
"grad_norm": 0.32816216349601746,
"learning_rate": 4.540787842683459e-06,
"loss": 0.0455,
"step": 218
},
{
"epoch": 1.8607954545454546,
"grad_norm": 0.31960371136665344,
"learning_rate": 4.533224351838914e-06,
"loss": 0.0454,
"step": 219
},
{
"epoch": 1.8693181818181817,
"grad_norm": 0.33228686451911926,
"learning_rate": 4.525605488883493e-06,
"loss": 0.0413,
"step": 220
},
{
"epoch": 1.8778409090909092,
"grad_norm": 0.271839439868927,
"learning_rate": 4.517931461306609e-06,
"loss": 0.0462,
"step": 221
},
{
"epoch": 1.8863636363636362,
"grad_norm": 0.3333345949649811,
"learning_rate": 4.510202478100008e-06,
"loss": 0.0458,
"step": 222
},
{
"epoch": 1.8948863636363638,
"grad_norm": 0.2923465371131897,
"learning_rate": 4.502418749752076e-06,
"loss": 0.0407,
"step": 223
},
{
"epoch": 1.9034090909090908,
"grad_norm": 0.34088781476020813,
"learning_rate": 4.494580488242109e-06,
"loss": 0.0422,
"step": 224
},
{
"epoch": 1.9119318181818183,
"grad_norm": 0.3535335958003998,
"learning_rate": 4.486687907034544e-06,
"loss": 0.0454,
"step": 225
},
{
"epoch": 1.9204545454545454,
"grad_norm": 0.32973766326904297,
"learning_rate": 4.478741221073136e-06,
"loss": 0.0429,
"step": 226
},
{
"epoch": 1.9289772727272727,
"grad_norm": 0.3509384095668793,
"learning_rate": 4.470740646775113e-06,
"loss": 0.0436,
"step": 227
},
{
"epoch": 1.9375,
"grad_norm": 0.2931392788887024,
"learning_rate": 4.462686402025277e-06,
"loss": 0.0466,
"step": 228
},
{
"epoch": 1.9460227272727273,
"grad_norm": 0.30415666103363037,
"learning_rate": 4.454578706170075e-06,
"loss": 0.0416,
"step": 229
},
{
"epoch": 1.9545454545454546,
"grad_norm": 0.3433127701282501,
"learning_rate": 4.446417780011618e-06,
"loss": 0.0424,
"step": 230
},
{
"epoch": 1.9630681818181817,
"grad_norm": 0.352159708738327,
"learning_rate": 4.4382038458016764e-06,
"loss": 0.0404,
"step": 231
},
{
"epoch": 1.9715909090909092,
"grad_norm": 0.27307572960853577,
"learning_rate": 4.42993712723562e-06,
"loss": 0.0429,
"step": 232
},
{
"epoch": 1.9801136363636362,
"grad_norm": 0.2662625312805176,
"learning_rate": 4.4216178494463305e-06,
"loss": 0.0425,
"step": 233
},
{
"epoch": 1.9886363636363638,
"grad_norm": 0.29612037539482117,
"learning_rate": 4.413246238998069e-06,
"loss": 0.0463,
"step": 234
}
],
"logging_steps": 1,
"max_steps": 702,
"num_input_tokens_seen": 0,
"num_train_epochs": 6,
"save_steps": 117,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 5.225133556849705e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}