Files
llama3-8b-full-pretrain-c4-…/trainer_state.json
ModelHub XC fd89aa97b5 初始化项目,由ModelHub XC社区提供模型
Model: shuoxing/llama3-8b-full-pretrain-c4-1m-en
Source: Original Platform
2026-07-15 15:16:11 +08:00

6449 lines
165 KiB
JSON

{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 500,
"global_step": 915,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.003278688524590164,
"grad_norm": 16.89353212095864,
"learning_rate": 0.0,
"loss": 3.0094027519226074,
"step": 1
},
{
"epoch": 0.006557377049180328,
"grad_norm": 16.028943910846195,
"learning_rate": 1.0869565217391305e-07,
"loss": 2.479351758956909,
"step": 2
},
{
"epoch": 0.009836065573770493,
"grad_norm": 17.868457175984453,
"learning_rate": 2.173913043478261e-07,
"loss": 2.557854175567627,
"step": 3
},
{
"epoch": 0.013114754098360656,
"grad_norm": 17.664917096804118,
"learning_rate": 3.2608695652173915e-07,
"loss": 2.84600567817688,
"step": 4
},
{
"epoch": 0.01639344262295082,
"grad_norm": 17.109555608982376,
"learning_rate": 4.347826086956522e-07,
"loss": 2.8910634517669678,
"step": 5
},
{
"epoch": 0.019672131147540985,
"grad_norm": 21.795417097411942,
"learning_rate": 5.434782608695653e-07,
"loss": 3.316324234008789,
"step": 6
},
{
"epoch": 0.022950819672131147,
"grad_norm": 23.206155197624565,
"learning_rate": 6.521739130434783e-07,
"loss": 2.203197717666626,
"step": 7
},
{
"epoch": 0.02622950819672131,
"grad_norm": 16.44869113667813,
"learning_rate": 7.608695652173914e-07,
"loss": 2.2714686393737793,
"step": 8
},
{
"epoch": 0.029508196721311476,
"grad_norm": 21.286553216527384,
"learning_rate": 8.695652173913044e-07,
"loss": 2.418856620788574,
"step": 9
},
{
"epoch": 0.03278688524590164,
"grad_norm": 15.196927017869122,
"learning_rate": 9.782608695652175e-07,
"loss": 2.7377705574035645,
"step": 10
},
{
"epoch": 0.036065573770491806,
"grad_norm": 16.195139191781866,
"learning_rate": 1.0869565217391306e-06,
"loss": 2.68233060836792,
"step": 11
},
{
"epoch": 0.03934426229508197,
"grad_norm": 16.975158613094695,
"learning_rate": 1.1956521739130436e-06,
"loss": 2.3804709911346436,
"step": 12
},
{
"epoch": 0.04262295081967213,
"grad_norm": 16.03747038201197,
"learning_rate": 1.3043478260869566e-06,
"loss": 2.442486047744751,
"step": 13
},
{
"epoch": 0.04590163934426229,
"grad_norm": 13.958818850279027,
"learning_rate": 1.4130434782608697e-06,
"loss": 2.3495070934295654,
"step": 14
},
{
"epoch": 0.04918032786885246,
"grad_norm": 76.12773314030454,
"learning_rate": 1.521739130434783e-06,
"loss": 2.233027696609497,
"step": 15
},
{
"epoch": 0.05245901639344262,
"grad_norm": 12.689587104774729,
"learning_rate": 1.6304347826086957e-06,
"loss": 2.28440523147583,
"step": 16
},
{
"epoch": 0.05573770491803279,
"grad_norm": 11.137011403020724,
"learning_rate": 1.7391304347826088e-06,
"loss": 2.1200904846191406,
"step": 17
},
{
"epoch": 0.05901639344262295,
"grad_norm": 12.795123355445146,
"learning_rate": 1.8478260869565218e-06,
"loss": 2.5397818088531494,
"step": 18
},
{
"epoch": 0.06229508196721312,
"grad_norm": 11.394155718638995,
"learning_rate": 1.956521739130435e-06,
"loss": 2.5477490425109863,
"step": 19
},
{
"epoch": 0.06557377049180328,
"grad_norm": 12.941190800367005,
"learning_rate": 2.065217391304348e-06,
"loss": 2.836233615875244,
"step": 20
},
{
"epoch": 0.06885245901639345,
"grad_norm": 11.046137332938052,
"learning_rate": 2.173913043478261e-06,
"loss": 2.131692409515381,
"step": 21
},
{
"epoch": 0.07213114754098361,
"grad_norm": 17.52625950015947,
"learning_rate": 2.282608695652174e-06,
"loss": 2.54901123046875,
"step": 22
},
{
"epoch": 0.07540983606557378,
"grad_norm": 15.179411936939736,
"learning_rate": 2.391304347826087e-06,
"loss": 2.4161558151245117,
"step": 23
},
{
"epoch": 0.07868852459016394,
"grad_norm": 15.65678400445971,
"learning_rate": 2.5e-06,
"loss": 2.2004499435424805,
"step": 24
},
{
"epoch": 0.08196721311475409,
"grad_norm": 18.087212043190434,
"learning_rate": 2.6086956521739132e-06,
"loss": 2.536360025405884,
"step": 25
},
{
"epoch": 0.08524590163934426,
"grad_norm": 18.926639105563854,
"learning_rate": 2.7173913043478263e-06,
"loss": 2.7464561462402344,
"step": 26
},
{
"epoch": 0.08852459016393442,
"grad_norm": 15.355968795855254,
"learning_rate": 2.8260869565217393e-06,
"loss": 2.894282102584839,
"step": 27
},
{
"epoch": 0.09180327868852459,
"grad_norm": 8.691177279105537,
"learning_rate": 2.9347826086956528e-06,
"loss": 2.3183541297912598,
"step": 28
},
{
"epoch": 0.09508196721311475,
"grad_norm": 15.529231139964732,
"learning_rate": 3.043478260869566e-06,
"loss": 2.283705711364746,
"step": 29
},
{
"epoch": 0.09836065573770492,
"grad_norm": 12.126223168480202,
"learning_rate": 3.152173913043479e-06,
"loss": 1.8977246284484863,
"step": 30
},
{
"epoch": 0.10163934426229508,
"grad_norm": 25.91368694328349,
"learning_rate": 3.2608695652173914e-06,
"loss": 2.572606086730957,
"step": 31
},
{
"epoch": 0.10491803278688525,
"grad_norm": 8.042192706097293,
"learning_rate": 3.3695652173913045e-06,
"loss": 2.369826316833496,
"step": 32
},
{
"epoch": 0.10819672131147541,
"grad_norm": 10.217213708676413,
"learning_rate": 3.4782608695652175e-06,
"loss": 2.0198986530303955,
"step": 33
},
{
"epoch": 0.11147540983606558,
"grad_norm": 16.517414212994996,
"learning_rate": 3.5869565217391305e-06,
"loss": 2.160893201828003,
"step": 34
},
{
"epoch": 0.11475409836065574,
"grad_norm": 11.776543409467024,
"learning_rate": 3.6956521739130436e-06,
"loss": 2.2623419761657715,
"step": 35
},
{
"epoch": 0.1180327868852459,
"grad_norm": 10.027433960634152,
"learning_rate": 3.804347826086957e-06,
"loss": 2.5216753482818604,
"step": 36
},
{
"epoch": 0.12131147540983607,
"grad_norm": 8.337831849962773,
"learning_rate": 3.91304347826087e-06,
"loss": 2.128694772720337,
"step": 37
},
{
"epoch": 0.12459016393442623,
"grad_norm": 9.02353353510628,
"learning_rate": 4.021739130434783e-06,
"loss": 2.4561331272125244,
"step": 38
},
{
"epoch": 0.12786885245901639,
"grad_norm": 9.111603210771797,
"learning_rate": 4.130434782608696e-06,
"loss": 2.297398090362549,
"step": 39
},
{
"epoch": 0.13114754098360656,
"grad_norm": 6.888204153928028,
"learning_rate": 4.239130434782609e-06,
"loss": 2.181044101715088,
"step": 40
},
{
"epoch": 0.13442622950819672,
"grad_norm": 9.729446575014977,
"learning_rate": 4.347826086956522e-06,
"loss": 2.456869602203369,
"step": 41
},
{
"epoch": 0.1377049180327869,
"grad_norm": 9.537377126128062,
"learning_rate": 4.456521739130435e-06,
"loss": 2.583646774291992,
"step": 42
},
{
"epoch": 0.14098360655737704,
"grad_norm": 20.79305394317051,
"learning_rate": 4.565217391304348e-06,
"loss": 2.187347650527954,
"step": 43
},
{
"epoch": 0.14426229508196722,
"grad_norm": 12.029609133743605,
"learning_rate": 4.673913043478261e-06,
"loss": 2.0726521015167236,
"step": 44
},
{
"epoch": 0.14754098360655737,
"grad_norm": 12.83655966367189,
"learning_rate": 4.782608695652174e-06,
"loss": 2.773625135421753,
"step": 45
},
{
"epoch": 0.15081967213114755,
"grad_norm": 9.398980764324769,
"learning_rate": 4.891304347826087e-06,
"loss": 2.6287107467651367,
"step": 46
},
{
"epoch": 0.1540983606557377,
"grad_norm": 11.033254103172723,
"learning_rate": 5e-06,
"loss": 2.549129009246826,
"step": 47
},
{
"epoch": 0.15737704918032788,
"grad_norm": 10.298031451477781,
"learning_rate": 5.108695652173914e-06,
"loss": 2.471952438354492,
"step": 48
},
{
"epoch": 0.16065573770491803,
"grad_norm": 7.840202939559905,
"learning_rate": 5.2173913043478265e-06,
"loss": 2.512025833129883,
"step": 49
},
{
"epoch": 0.16393442622950818,
"grad_norm": 10.10194984633829,
"learning_rate": 5.3260869565217395e-06,
"loss": 2.5505197048187256,
"step": 50
},
{
"epoch": 0.16721311475409836,
"grad_norm": 8.840489916114647,
"learning_rate": 5.4347826086956525e-06,
"loss": 2.4877638816833496,
"step": 51
},
{
"epoch": 0.17049180327868851,
"grad_norm": 6.071904404309473,
"learning_rate": 5.543478260869566e-06,
"loss": 2.514116048812866,
"step": 52
},
{
"epoch": 0.1737704918032787,
"grad_norm": 8.358712110161177,
"learning_rate": 5.652173913043479e-06,
"loss": 2.398836135864258,
"step": 53
},
{
"epoch": 0.17704918032786884,
"grad_norm": 9.148970336356888,
"learning_rate": 5.760869565217392e-06,
"loss": 2.498903751373291,
"step": 54
},
{
"epoch": 0.18032786885245902,
"grad_norm": 8.405179217040024,
"learning_rate": 5.8695652173913055e-06,
"loss": 2.741854190826416,
"step": 55
},
{
"epoch": 0.18360655737704917,
"grad_norm": 36.365983609117684,
"learning_rate": 5.978260869565218e-06,
"loss": 2.234142303466797,
"step": 56
},
{
"epoch": 0.18688524590163935,
"grad_norm": 7.68829577102625,
"learning_rate": 6.086956521739132e-06,
"loss": 2.370748996734619,
"step": 57
},
{
"epoch": 0.1901639344262295,
"grad_norm": 22.381764027626158,
"learning_rate": 6.195652173913044e-06,
"loss": 2.635423421859741,
"step": 58
},
{
"epoch": 0.19344262295081968,
"grad_norm": 7.080805794757332,
"learning_rate": 6.304347826086958e-06,
"loss": 2.5489463806152344,
"step": 59
},
{
"epoch": 0.19672131147540983,
"grad_norm": 10.998453372305452,
"learning_rate": 6.41304347826087e-06,
"loss": 2.6816728115081787,
"step": 60
},
{
"epoch": 0.2,
"grad_norm": 7.34484367857415,
"learning_rate": 6.521739130434783e-06,
"loss": 2.1532349586486816,
"step": 61
},
{
"epoch": 0.20327868852459016,
"grad_norm": 9.768503039892842,
"learning_rate": 6.630434782608696e-06,
"loss": 2.455888271331787,
"step": 62
},
{
"epoch": 0.20655737704918034,
"grad_norm": 18.26030810766118,
"learning_rate": 6.739130434782609e-06,
"loss": 1.318924903869629,
"step": 63
},
{
"epoch": 0.2098360655737705,
"grad_norm": 11.421285434071244,
"learning_rate": 6.847826086956523e-06,
"loss": 2.6968984603881836,
"step": 64
},
{
"epoch": 0.21311475409836064,
"grad_norm": 6.707816680569159,
"learning_rate": 6.956521739130435e-06,
"loss": 2.5202150344848633,
"step": 65
},
{
"epoch": 0.21639344262295082,
"grad_norm": 9.725970026297484,
"learning_rate": 7.065217391304349e-06,
"loss": 3.0976004600524902,
"step": 66
},
{
"epoch": 0.21967213114754097,
"grad_norm": 12.259636136580166,
"learning_rate": 7.173913043478261e-06,
"loss": 2.3197407722473145,
"step": 67
},
{
"epoch": 0.22295081967213115,
"grad_norm": 11.856167783229704,
"learning_rate": 7.282608695652175e-06,
"loss": 2.131117582321167,
"step": 68
},
{
"epoch": 0.2262295081967213,
"grad_norm": 8.301390262803812,
"learning_rate": 7.391304347826087e-06,
"loss": 2.2955703735351562,
"step": 69
},
{
"epoch": 0.22950819672131148,
"grad_norm": 7.257457610803963,
"learning_rate": 7.500000000000001e-06,
"loss": 2.2596120834350586,
"step": 70
},
{
"epoch": 0.23278688524590163,
"grad_norm": 11.841362824519118,
"learning_rate": 7.608695652173914e-06,
"loss": 2.22799015045166,
"step": 71
},
{
"epoch": 0.2360655737704918,
"grad_norm": 11.994180547857127,
"learning_rate": 7.717391304347827e-06,
"loss": 2.3619353771209717,
"step": 72
},
{
"epoch": 0.23934426229508196,
"grad_norm": 18.61903589815759,
"learning_rate": 7.82608695652174e-06,
"loss": 2.276402711868286,
"step": 73
},
{
"epoch": 0.24262295081967214,
"grad_norm": 8.639083747845074,
"learning_rate": 7.934782608695653e-06,
"loss": 2.602898597717285,
"step": 74
},
{
"epoch": 0.2459016393442623,
"grad_norm": 8.441808484395048,
"learning_rate": 8.043478260869566e-06,
"loss": 2.44040846824646,
"step": 75
},
{
"epoch": 0.24918032786885247,
"grad_norm": 11.535106426694751,
"learning_rate": 8.15217391304348e-06,
"loss": 2.365647077560425,
"step": 76
},
{
"epoch": 0.25245901639344265,
"grad_norm": 18.315786566453365,
"learning_rate": 8.260869565217392e-06,
"loss": 2.658693313598633,
"step": 77
},
{
"epoch": 0.25573770491803277,
"grad_norm": 15.855955724429215,
"learning_rate": 8.369565217391305e-06,
"loss": 1.595600962638855,
"step": 78
},
{
"epoch": 0.25901639344262295,
"grad_norm": 8.675987208012433,
"learning_rate": 8.478260869565218e-06,
"loss": 2.3835480213165283,
"step": 79
},
{
"epoch": 0.26229508196721313,
"grad_norm": 13.471802392623209,
"learning_rate": 8.586956521739131e-06,
"loss": 2.095423698425293,
"step": 80
},
{
"epoch": 0.26557377049180325,
"grad_norm": 13.499186101973232,
"learning_rate": 8.695652173913044e-06,
"loss": 2.546840190887451,
"step": 81
},
{
"epoch": 0.26885245901639343,
"grad_norm": 11.293340960759608,
"learning_rate": 8.804347826086957e-06,
"loss": 1.510994791984558,
"step": 82
},
{
"epoch": 0.2721311475409836,
"grad_norm": 9.239083457753898,
"learning_rate": 8.91304347826087e-06,
"loss": 2.1867687702178955,
"step": 83
},
{
"epoch": 0.2754098360655738,
"grad_norm": 9.841087525915807,
"learning_rate": 9.021739130434784e-06,
"loss": 2.436410903930664,
"step": 84
},
{
"epoch": 0.2786885245901639,
"grad_norm": 14.160634901988136,
"learning_rate": 9.130434782608697e-06,
"loss": 2.6772923469543457,
"step": 85
},
{
"epoch": 0.2819672131147541,
"grad_norm": 7.723300697532095,
"learning_rate": 9.23913043478261e-06,
"loss": 2.6738224029541016,
"step": 86
},
{
"epoch": 0.28524590163934427,
"grad_norm": 12.61070856616998,
"learning_rate": 9.347826086956523e-06,
"loss": 2.712817668914795,
"step": 87
},
{
"epoch": 0.28852459016393445,
"grad_norm": 7.189321581499551,
"learning_rate": 9.456521739130436e-06,
"loss": 2.2721221446990967,
"step": 88
},
{
"epoch": 0.29180327868852457,
"grad_norm": 27.343926151075024,
"learning_rate": 9.565217391304349e-06,
"loss": 1.9258663654327393,
"step": 89
},
{
"epoch": 0.29508196721311475,
"grad_norm": 11.406519767474075,
"learning_rate": 9.673913043478262e-06,
"loss": 2.6684117317199707,
"step": 90
},
{
"epoch": 0.2983606557377049,
"grad_norm": 20.51088786538055,
"learning_rate": 9.782608695652175e-06,
"loss": 2.364388942718506,
"step": 91
},
{
"epoch": 0.3016393442622951,
"grad_norm": 8.44528444743607,
"learning_rate": 9.891304347826088e-06,
"loss": 2.722784996032715,
"step": 92
},
{
"epoch": 0.30491803278688523,
"grad_norm": 7.508036366602105,
"learning_rate": 1e-05,
"loss": 2.3887619972229004,
"step": 93
},
{
"epoch": 0.3081967213114754,
"grad_norm": 10.124125411792933,
"learning_rate": 9.999963571645329e-06,
"loss": 2.1840157508850098,
"step": 94
},
{
"epoch": 0.3114754098360656,
"grad_norm": 16.38308252379299,
"learning_rate": 9.999854287112122e-06,
"loss": 2.2762627601623535,
"step": 95
},
{
"epoch": 0.31475409836065577,
"grad_norm": 6.288851667519567,
"learning_rate": 9.999672147992806e-06,
"loss": 2.119352102279663,
"step": 96
},
{
"epoch": 0.3180327868852459,
"grad_norm": 9.47809746312098,
"learning_rate": 9.99941715694139e-06,
"loss": 2.301476240158081,
"step": 97
},
{
"epoch": 0.32131147540983607,
"grad_norm": 13.094257600615272,
"learning_rate": 9.999089317673432e-06,
"loss": 2.5972483158111572,
"step": 98
},
{
"epoch": 0.32459016393442625,
"grad_norm": 10.19048933796723,
"learning_rate": 9.998688634965996e-06,
"loss": 2.779660940170288,
"step": 99
},
{
"epoch": 0.32786885245901637,
"grad_norm": 5.8936834387995845,
"learning_rate": 9.998215114657564e-06,
"loss": 2.2308220863342285,
"step": 100
},
{
"epoch": 0.33114754098360655,
"grad_norm": 10.502710763313692,
"learning_rate": 9.997668763647963e-06,
"loss": 2.8325366973876953,
"step": 101
},
{
"epoch": 0.3344262295081967,
"grad_norm": 7.850898262428381,
"learning_rate": 9.99704958989826e-06,
"loss": 2.3015875816345215,
"step": 102
},
{
"epoch": 0.3377049180327869,
"grad_norm": 7.175846059648616,
"learning_rate": 9.996357602430647e-06,
"loss": 2.083513021469116,
"step": 103
},
{
"epoch": 0.34098360655737703,
"grad_norm": 12.918153921333007,
"learning_rate": 9.99559281132831e-06,
"loss": 1.970626950263977,
"step": 104
},
{
"epoch": 0.3442622950819672,
"grad_norm": 10.831422691089006,
"learning_rate": 9.994755227735284e-06,
"loss": 2.1563878059387207,
"step": 105
},
{
"epoch": 0.3475409836065574,
"grad_norm": 6.825443208154653,
"learning_rate": 9.993844863856281e-06,
"loss": 2.480492353439331,
"step": 106
},
{
"epoch": 0.35081967213114756,
"grad_norm": 21.992403965996946,
"learning_rate": 9.992861732956529e-06,
"loss": 1.792158842086792,
"step": 107
},
{
"epoch": 0.3540983606557377,
"grad_norm": 17.359788849655715,
"learning_rate": 9.991805849361563e-06,
"loss": 1.8844330310821533,
"step": 108
},
{
"epoch": 0.35737704918032787,
"grad_norm": 10.313007387963811,
"learning_rate": 9.990677228457022e-06,
"loss": 2.675395965576172,
"step": 109
},
{
"epoch": 0.36065573770491804,
"grad_norm": 17.684705918346737,
"learning_rate": 9.98947588668843e-06,
"loss": 2.1340208053588867,
"step": 110
},
{
"epoch": 0.3639344262295082,
"grad_norm": 16.22328112769769,
"learning_rate": 9.988201841560945e-06,
"loss": 2.472806453704834,
"step": 111
},
{
"epoch": 0.36721311475409835,
"grad_norm": 8.585998811584894,
"learning_rate": 9.986855111639118e-06,
"loss": 2.2037081718444824,
"step": 112
},
{
"epoch": 0.3704918032786885,
"grad_norm": 10.625503536630955,
"learning_rate": 9.985435716546607e-06,
"loss": 2.8116614818573,
"step": 113
},
{
"epoch": 0.3737704918032787,
"grad_norm": 8.328891017920228,
"learning_rate": 9.983943676965908e-06,
"loss": 2.2937393188476562,
"step": 114
},
{
"epoch": 0.3770491803278688,
"grad_norm": 25.132057060893327,
"learning_rate": 9.982379014638036e-06,
"loss": 2.009312629699707,
"step": 115
},
{
"epoch": 0.380327868852459,
"grad_norm": 17.734057181718484,
"learning_rate": 9.980741752362222e-06,
"loss": 2.4379334449768066,
"step": 116
},
{
"epoch": 0.3836065573770492,
"grad_norm": 8.650433488596095,
"learning_rate": 9.979031913995574e-06,
"loss": 2.6336417198181152,
"step": 117
},
{
"epoch": 0.38688524590163936,
"grad_norm": 10.335901220440789,
"learning_rate": 9.977249524452732e-06,
"loss": 2.6149487495422363,
"step": 118
},
{
"epoch": 0.3901639344262295,
"grad_norm": 12.454276988377098,
"learning_rate": 9.975394609705504e-06,
"loss": 2.3056716918945312,
"step": 119
},
{
"epoch": 0.39344262295081966,
"grad_norm": 11.52674648293092,
"learning_rate": 9.973467196782484e-06,
"loss": 2.3978047370910645,
"step": 120
},
{
"epoch": 0.39672131147540984,
"grad_norm": 11.70854679403386,
"learning_rate": 9.971467313768668e-06,
"loss": 2.4032225608825684,
"step": 121
},
{
"epoch": 0.4,
"grad_norm": 7.244882025846572,
"learning_rate": 9.969394989805035e-06,
"loss": 2.4925785064697266,
"step": 122
},
{
"epoch": 0.40327868852459015,
"grad_norm": 29.631727691106814,
"learning_rate": 9.967250255088121e-06,
"loss": 2.540073871612549,
"step": 123
},
{
"epoch": 0.4065573770491803,
"grad_norm": 16.491791586455538,
"learning_rate": 9.965033140869596e-06,
"loss": 2.562507152557373,
"step": 124
},
{
"epoch": 0.4098360655737705,
"grad_norm": 18.89159517028497,
"learning_rate": 9.962743679455783e-06,
"loss": 1.4019899368286133,
"step": 125
},
{
"epoch": 0.4131147540983607,
"grad_norm": 11.08365886362951,
"learning_rate": 9.96038190420721e-06,
"loss": 2.470672130584717,
"step": 126
},
{
"epoch": 0.4163934426229508,
"grad_norm": 13.931169642100365,
"learning_rate": 9.957947849538112e-06,
"loss": 2.5515592098236084,
"step": 127
},
{
"epoch": 0.419672131147541,
"grad_norm": 10.48096677220992,
"learning_rate": 9.95544155091593e-06,
"loss": 1.8564338684082031,
"step": 128
},
{
"epoch": 0.42295081967213116,
"grad_norm": 22.085697247990158,
"learning_rate": 9.9528630448608e-06,
"loss": 2.4436991214752197,
"step": 129
},
{
"epoch": 0.4262295081967213,
"grad_norm": 41.05766088686945,
"learning_rate": 9.950212368945013e-06,
"loss": 2.011152982711792,
"step": 130
},
{
"epoch": 0.42950819672131146,
"grad_norm": 7.332867185902429,
"learning_rate": 9.947489561792475e-06,
"loss": 2.3709192276000977,
"step": 131
},
{
"epoch": 0.43278688524590164,
"grad_norm": 7.067784534663912,
"learning_rate": 9.94469466307814e-06,
"loss": 2.4364941120147705,
"step": 132
},
{
"epoch": 0.4360655737704918,
"grad_norm": 6.796150590529943,
"learning_rate": 9.941827713527435e-06,
"loss": 2.605982780456543,
"step": 133
},
{
"epoch": 0.43934426229508194,
"grad_norm": 17.847218467637784,
"learning_rate": 9.938888754915657e-06,
"loss": 1.9951808452606201,
"step": 134
},
{
"epoch": 0.4426229508196721,
"grad_norm": 9.637940265765115,
"learning_rate": 9.93587783006738e-06,
"loss": 2.514698028564453,
"step": 135
},
{
"epoch": 0.4459016393442623,
"grad_norm": 14.025044375098688,
"learning_rate": 9.932794982855818e-06,
"loss": 2.6266212463378906,
"step": 136
},
{
"epoch": 0.4491803278688525,
"grad_norm": 7.742628932780814,
"learning_rate": 9.929640258202193e-06,
"loss": 2.694523811340332,
"step": 137
},
{
"epoch": 0.4524590163934426,
"grad_norm": 9.420409137736808,
"learning_rate": 9.926413702075075e-06,
"loss": 2.3812270164489746,
"step": 138
},
{
"epoch": 0.4557377049180328,
"grad_norm": 25.357762811620063,
"learning_rate": 9.923115361489719e-06,
"loss": 1.8413501977920532,
"step": 139
},
{
"epoch": 0.45901639344262296,
"grad_norm": 9.23668319901442,
"learning_rate": 9.91974528450737e-06,
"loss": 2.681863307952881,
"step": 140
},
{
"epoch": 0.46229508196721314,
"grad_norm": 13.91154278046453,
"learning_rate": 9.916303520234573e-06,
"loss": 1.9020752906799316,
"step": 141
},
{
"epoch": 0.46557377049180326,
"grad_norm": 9.735454722376808,
"learning_rate": 9.912790118822451e-06,
"loss": 2.2685928344726562,
"step": 142
},
{
"epoch": 0.46885245901639344,
"grad_norm": 6.307393100595144,
"learning_rate": 9.90920513146598e-06,
"loss": 2.6260900497436523,
"step": 143
},
{
"epoch": 0.4721311475409836,
"grad_norm": 10.256520667204969,
"learning_rate": 9.905548610403234e-06,
"loss": 2.425342082977295,
"step": 144
},
{
"epoch": 0.47540983606557374,
"grad_norm": 5.736311053584111,
"learning_rate": 9.901820608914632e-06,
"loss": 2.357337713241577,
"step": 145
},
{
"epoch": 0.4786885245901639,
"grad_norm": 8.807246568465844,
"learning_rate": 9.898021181322158e-06,
"loss": 2.2193427085876465,
"step": 146
},
{
"epoch": 0.4819672131147541,
"grad_norm": 12.42413884634667,
"learning_rate": 9.89415038298857e-06,
"loss": 2.517714262008667,
"step": 147
},
{
"epoch": 0.4852459016393443,
"grad_norm": 13.402793074301506,
"learning_rate": 9.890208270316595e-06,
"loss": 2.0575406551361084,
"step": 148
},
{
"epoch": 0.4885245901639344,
"grad_norm": 6.023414807948633,
"learning_rate": 9.886194900748103e-06,
"loss": 2.6296324729919434,
"step": 149
},
{
"epoch": 0.4918032786885246,
"grad_norm": 7.715805841847776,
"learning_rate": 9.882110332763275e-06,
"loss": 2.4448821544647217,
"step": 150
},
{
"epoch": 0.49508196721311476,
"grad_norm": 9.118773545041579,
"learning_rate": 9.877954625879746e-06,
"loss": 2.2841904163360596,
"step": 151
},
{
"epoch": 0.49836065573770494,
"grad_norm": 6.177286913705299,
"learning_rate": 9.873727840651745e-06,
"loss": 2.2682907581329346,
"step": 152
},
{
"epoch": 0.5016393442622951,
"grad_norm": 10.286512937930272,
"learning_rate": 9.869430038669202e-06,
"loss": 2.8492913246154785,
"step": 153
},
{
"epoch": 0.5049180327868853,
"grad_norm": 8.902132907191097,
"learning_rate": 9.865061282556859e-06,
"loss": 2.546908140182495,
"step": 154
},
{
"epoch": 0.5081967213114754,
"grad_norm": 12.932184915529149,
"learning_rate": 9.860621635973356e-06,
"loss": 2.2108309268951416,
"step": 155
},
{
"epoch": 0.5114754098360655,
"grad_norm": 21.722529791173507,
"learning_rate": 9.8561111636103e-06,
"loss": 2.1323680877685547,
"step": 156
},
{
"epoch": 0.5147540983606558,
"grad_norm": 8.54995237341061,
"learning_rate": 9.851529931191325e-06,
"loss": 2.3354313373565674,
"step": 157
},
{
"epoch": 0.5180327868852459,
"grad_norm": 11.778806941155413,
"learning_rate": 9.846878005471139e-06,
"loss": 2.489478826522827,
"step": 158
},
{
"epoch": 0.521311475409836,
"grad_norm": 18.453791625427396,
"learning_rate": 9.842155454234537e-06,
"loss": 2.464871406555176,
"step": 159
},
{
"epoch": 0.5245901639344263,
"grad_norm": 13.977349143338607,
"learning_rate": 9.83736234629543e-06,
"loss": 2.521759271621704,
"step": 160
},
{
"epoch": 0.5278688524590164,
"grad_norm": 14.843078406057481,
"learning_rate": 9.832498751495832e-06,
"loss": 2.189639091491699,
"step": 161
},
{
"epoch": 0.5311475409836065,
"grad_norm": 11.805763820117145,
"learning_rate": 9.827564740704848e-06,
"loss": 2.3668131828308105,
"step": 162
},
{
"epoch": 0.5344262295081967,
"grad_norm": 11.317160406796951,
"learning_rate": 9.82256038581763e-06,
"loss": 2.697373151779175,
"step": 163
},
{
"epoch": 0.5377049180327869,
"grad_norm": 10.207489785694769,
"learning_rate": 9.817485759754348e-06,
"loss": 2.1023507118225098,
"step": 164
},
{
"epoch": 0.5409836065573771,
"grad_norm": 10.180641561578351,
"learning_rate": 9.812340936459113e-06,
"loss": 2.5591394901275635,
"step": 165
},
{
"epoch": 0.5442622950819672,
"grad_norm": 12.41560054529337,
"learning_rate": 9.807125990898905e-06,
"loss": 2.2220029830932617,
"step": 166
},
{
"epoch": 0.5475409836065573,
"grad_norm": 8.647737868553188,
"learning_rate": 9.801840999062476e-06,
"loss": 2.7247979640960693,
"step": 167
},
{
"epoch": 0.5508196721311476,
"grad_norm": 11.273589344567679,
"learning_rate": 9.796486037959251e-06,
"loss": 2.238039493560791,
"step": 168
},
{
"epoch": 0.5540983606557377,
"grad_norm": 7.067412937489566,
"learning_rate": 9.791061185618199e-06,
"loss": 2.407823085784912,
"step": 169
},
{
"epoch": 0.5573770491803278,
"grad_norm": 13.730271908177464,
"learning_rate": 9.785566521086695e-06,
"loss": 2.2689170837402344,
"step": 170
},
{
"epoch": 0.5606557377049181,
"grad_norm": 13.635709240955189,
"learning_rate": 9.780002124429377e-06,
"loss": 2.018502712249756,
"step": 171
},
{
"epoch": 0.5639344262295082,
"grad_norm": 14.612861839376295,
"learning_rate": 9.774368076726972e-06,
"loss": 2.2665579319000244,
"step": 172
},
{
"epoch": 0.5672131147540984,
"grad_norm": 41.96415343388753,
"learning_rate": 9.768664460075112e-06,
"loss": 2.3035991191864014,
"step": 173
},
{
"epoch": 0.5704918032786885,
"grad_norm": 19.63165274562379,
"learning_rate": 9.76289135758315e-06,
"loss": 2.5324723720550537,
"step": 174
},
{
"epoch": 0.5737704918032787,
"grad_norm": 6.610337445226602,
"learning_rate": 9.757048853372927e-06,
"loss": 2.565101146697998,
"step": 175
},
{
"epoch": 0.5770491803278689,
"grad_norm": 11.189423195267334,
"learning_rate": 9.75113703257758e-06,
"loss": 2.298004150390625,
"step": 176
},
{
"epoch": 0.580327868852459,
"grad_norm": 11.685516338819953,
"learning_rate": 9.745155981340265e-06,
"loss": 2.463772773742676,
"step": 177
},
{
"epoch": 0.5836065573770491,
"grad_norm": 9.299439842875548,
"learning_rate": 9.739105786812923e-06,
"loss": 2.5719070434570312,
"step": 178
},
{
"epoch": 0.5868852459016394,
"grad_norm": 5.816867653870291,
"learning_rate": 9.732986537155012e-06,
"loss": 2.4491379261016846,
"step": 179
},
{
"epoch": 0.5901639344262295,
"grad_norm": 8.912746736929753,
"learning_rate": 9.726798321532205e-06,
"loss": 2.3815207481384277,
"step": 180
},
{
"epoch": 0.5934426229508196,
"grad_norm": 11.523154847243013,
"learning_rate": 9.720541230115113e-06,
"loss": 2.3223185539245605,
"step": 181
},
{
"epoch": 0.5967213114754099,
"grad_norm": 6.379908315597364,
"learning_rate": 9.71421535407795e-06,
"loss": 2.4502346515655518,
"step": 182
},
{
"epoch": 0.6,
"grad_norm": 13.763467803769869,
"learning_rate": 9.70782078559722e-06,
"loss": 2.5693788528442383,
"step": 183
},
{
"epoch": 0.6032786885245902,
"grad_norm": 6.8455322733799004,
"learning_rate": 9.701357617850364e-06,
"loss": 2.2750675678253174,
"step": 184
},
{
"epoch": 0.6065573770491803,
"grad_norm": 10.904041161242418,
"learning_rate": 9.694825945014414e-06,
"loss": 2.4306750297546387,
"step": 185
},
{
"epoch": 0.6098360655737705,
"grad_norm": 8.736445176506262,
"learning_rate": 9.688225862264604e-06,
"loss": 2.4892170429229736,
"step": 186
},
{
"epoch": 0.6131147540983607,
"grad_norm": 13.71647922858585,
"learning_rate": 9.681557465772995e-06,
"loss": 2.5634660720825195,
"step": 187
},
{
"epoch": 0.6163934426229508,
"grad_norm": 12.108203455114717,
"learning_rate": 9.674820852707076e-06,
"loss": 2.3774335384368896,
"step": 188
},
{
"epoch": 0.6196721311475409,
"grad_norm": 10.149287498094273,
"learning_rate": 9.668016121228338e-06,
"loss": 2.4913172721862793,
"step": 189
},
{
"epoch": 0.6229508196721312,
"grad_norm": 10.196856373881207,
"learning_rate": 9.661143370490846e-06,
"loss": 2.7339348793029785,
"step": 190
},
{
"epoch": 0.6262295081967213,
"grad_norm": 9.333771245553299,
"learning_rate": 9.654202700639805e-06,
"loss": 2.2505457401275635,
"step": 191
},
{
"epoch": 0.6295081967213115,
"grad_norm": 8.148903296375927,
"learning_rate": 9.647194212810086e-06,
"loss": 2.695054054260254,
"step": 192
},
{
"epoch": 0.6327868852459017,
"grad_norm": 12.557400841371972,
"learning_rate": 9.640118009124761e-06,
"loss": 2.382502555847168,
"step": 193
},
{
"epoch": 0.6360655737704918,
"grad_norm": 9.145946209661751,
"learning_rate": 9.632974192693614e-06,
"loss": 2.34623384475708,
"step": 194
},
{
"epoch": 0.639344262295082,
"grad_norm": 8.542659802114223,
"learning_rate": 9.625762867611636e-06,
"loss": 2.1379222869873047,
"step": 195
},
{
"epoch": 0.6426229508196721,
"grad_norm": 12.326902118073734,
"learning_rate": 9.61848413895751e-06,
"loss": 1.9921382665634155,
"step": 196
},
{
"epoch": 0.6459016393442623,
"grad_norm": 14.271821865211999,
"learning_rate": 9.61113811279208e-06,
"loss": 2.4724960327148438,
"step": 197
},
{
"epoch": 0.6491803278688525,
"grad_norm": 11.47655091808735,
"learning_rate": 9.603724896156806e-06,
"loss": 2.3870677947998047,
"step": 198
},
{
"epoch": 0.6524590163934426,
"grad_norm": 7.323447004522844,
"learning_rate": 9.596244597072198e-06,
"loss": 2.391430616378784,
"step": 199
},
{
"epoch": 0.6557377049180327,
"grad_norm": 10.095709097095108,
"learning_rate": 9.588697324536254e-06,
"loss": 2.2718007564544678,
"step": 200
},
{
"epoch": 0.659016393442623,
"grad_norm": 13.52756110555734,
"learning_rate": 9.581083188522862e-06,
"loss": 2.454087018966675,
"step": 201
},
{
"epoch": 0.6622950819672131,
"grad_norm": 16.735232835265577,
"learning_rate": 9.5734022999802e-06,
"loss": 2.7983779907226562,
"step": 202
},
{
"epoch": 0.6655737704918033,
"grad_norm": 9.118893537948745,
"learning_rate": 9.565654770829123e-06,
"loss": 2.388134479522705,
"step": 203
},
{
"epoch": 0.6688524590163935,
"grad_norm": 8.372558203314588,
"learning_rate": 9.557840713961526e-06,
"loss": 2.368241548538208,
"step": 204
},
{
"epoch": 0.6721311475409836,
"grad_norm": 7.867813978162408,
"learning_rate": 9.549960243238701e-06,
"loss": 2.33974552154541,
"step": 205
},
{
"epoch": 0.6754098360655738,
"grad_norm": 15.063066709550244,
"learning_rate": 9.542013473489683e-06,
"loss": 2.649343252182007,
"step": 206
},
{
"epoch": 0.6786885245901639,
"grad_norm": 7.047401029645536,
"learning_rate": 9.53400052050957e-06,
"loss": 2.560885429382324,
"step": 207
},
{
"epoch": 0.6819672131147541,
"grad_norm": 8.907822727514814,
"learning_rate": 9.52592150105784e-06,
"loss": 2.412108898162842,
"step": 208
},
{
"epoch": 0.6852459016393443,
"grad_norm": 5.170484841596506,
"learning_rate": 9.517776532856647e-06,
"loss": 2.0627474784851074,
"step": 209
},
{
"epoch": 0.6885245901639344,
"grad_norm": 8.088836029721898,
"learning_rate": 9.509565734589105e-06,
"loss": 2.5947265625,
"step": 210
},
{
"epoch": 0.6918032786885245,
"grad_norm": 31.641619526555406,
"learning_rate": 9.501289225897566e-06,
"loss": 2.513089418411255,
"step": 211
},
{
"epoch": 0.6950819672131148,
"grad_norm": 13.679037779223505,
"learning_rate": 9.492947127381867e-06,
"loss": 2.400226593017578,
"step": 212
},
{
"epoch": 0.6983606557377049,
"grad_norm": 10.43977237624282,
"learning_rate": 9.484539560597576e-06,
"loss": 2.286137580871582,
"step": 213
},
{
"epoch": 0.7016393442622951,
"grad_norm": 10.141075367022605,
"learning_rate": 9.476066648054223e-06,
"loss": 2.7649638652801514,
"step": 214
},
{
"epoch": 0.7049180327868853,
"grad_norm": 8.474472872601897,
"learning_rate": 9.467528513213514e-06,
"loss": 2.317016124725342,
"step": 215
},
{
"epoch": 0.7081967213114754,
"grad_norm": 16.498421555513367,
"learning_rate": 9.458925280487532e-06,
"loss": 2.233351945877075,
"step": 216
},
{
"epoch": 0.7114754098360656,
"grad_norm": 11.493606098576603,
"learning_rate": 9.45025707523692e-06,
"loss": 2.2825753688812256,
"step": 217
},
{
"epoch": 0.7147540983606557,
"grad_norm": 13.65050204569431,
"learning_rate": 9.441524023769059e-06,
"loss": 2.168769598007202,
"step": 218
},
{
"epoch": 0.7180327868852459,
"grad_norm": 8.983713618349288,
"learning_rate": 9.432726253336231e-06,
"loss": 2.559760808944702,
"step": 219
},
{
"epoch": 0.7213114754098361,
"grad_norm": 15.583644405048908,
"learning_rate": 9.423863892133754e-06,
"loss": 1.7594213485717773,
"step": 220
},
{
"epoch": 0.7245901639344262,
"grad_norm": 8.73686355390609,
"learning_rate": 9.414937069298125e-06,
"loss": 2.4652814865112305,
"step": 221
},
{
"epoch": 0.7278688524590164,
"grad_norm": 11.495894245929948,
"learning_rate": 9.405945914905129e-06,
"loss": 2.5217018127441406,
"step": 222
},
{
"epoch": 0.7311475409836066,
"grad_norm": 4.726521302535209,
"learning_rate": 9.396890559967951e-06,
"loss": 2.0314042568206787,
"step": 223
},
{
"epoch": 0.7344262295081967,
"grad_norm": 7.298626143624748,
"learning_rate": 9.387771136435267e-06,
"loss": 2.8855409622192383,
"step": 224
},
{
"epoch": 0.7377049180327869,
"grad_norm": 9.260856152886753,
"learning_rate": 9.37858777718931e-06,
"loss": 2.125582218170166,
"step": 225
},
{
"epoch": 0.740983606557377,
"grad_norm": 6.911659227229308,
"learning_rate": 9.369340616043948e-06,
"loss": 2.481126546859741,
"step": 226
},
{
"epoch": 0.7442622950819672,
"grad_norm": 9.776776699911634,
"learning_rate": 9.360029787742731e-06,
"loss": 2.098676919937134,
"step": 227
},
{
"epoch": 0.7475409836065574,
"grad_norm": 20.38163371355876,
"learning_rate": 9.350655427956919e-06,
"loss": 2.2835912704467773,
"step": 228
},
{
"epoch": 0.7508196721311475,
"grad_norm": 9.237053047118033,
"learning_rate": 9.341217673283511e-06,
"loss": 2.5307552814483643,
"step": 229
},
{
"epoch": 0.7540983606557377,
"grad_norm": 9.562449590605533,
"learning_rate": 9.33171666124326e-06,
"loss": 2.6956987380981445,
"step": 230
},
{
"epoch": 0.7573770491803279,
"grad_norm": 17.292398769655275,
"learning_rate": 9.322152530278658e-06,
"loss": 3.334162712097168,
"step": 231
},
{
"epoch": 0.760655737704918,
"grad_norm": 9.403803835297106,
"learning_rate": 9.31252541975193e-06,
"loss": 2.7605435848236084,
"step": 232
},
{
"epoch": 0.7639344262295082,
"grad_norm": 51.211138872525396,
"learning_rate": 9.302835469942992e-06,
"loss": 2.3734195232391357,
"step": 233
},
{
"epoch": 0.7672131147540984,
"grad_norm": 8.173897381472578,
"learning_rate": 9.293082822047417e-06,
"loss": 2.561389446258545,
"step": 234
},
{
"epoch": 0.7704918032786885,
"grad_norm": 8.124812115012821,
"learning_rate": 9.28326761817437e-06,
"loss": 2.2314820289611816,
"step": 235
},
{
"epoch": 0.7737704918032787,
"grad_norm": 9.308271437225219,
"learning_rate": 9.273390001344544e-06,
"loss": 2.5885002613067627,
"step": 236
},
{
"epoch": 0.7770491803278688,
"grad_norm": 7.493760191845912,
"learning_rate": 9.26345011548807e-06,
"loss": 2.5269150733947754,
"step": 237
},
{
"epoch": 0.780327868852459,
"grad_norm": 10.292634344489139,
"learning_rate": 9.253448105442422e-06,
"loss": 2.344486951828003,
"step": 238
},
{
"epoch": 0.7836065573770492,
"grad_norm": 10.65215597438691,
"learning_rate": 9.24338411695031e-06,
"loss": 2.264143943786621,
"step": 239
},
{
"epoch": 0.7868852459016393,
"grad_norm": 64.63764925427373,
"learning_rate": 9.233258296657547e-06,
"loss": 2.584000825881958,
"step": 240
},
{
"epoch": 0.7901639344262295,
"grad_norm": 11.661794732114105,
"learning_rate": 9.223070792110927e-06,
"loss": 2.1990528106689453,
"step": 241
},
{
"epoch": 0.7934426229508197,
"grad_norm": 7.8236955368941405,
"learning_rate": 9.212821751756057e-06,
"loss": 2.6869657039642334,
"step": 242
},
{
"epoch": 0.7967213114754098,
"grad_norm": 6.138447198486987,
"learning_rate": 9.202511324935212e-06,
"loss": 2.709324598312378,
"step": 243
},
{
"epoch": 0.8,
"grad_norm": 5.161893914940263,
"learning_rate": 9.192139661885143e-06,
"loss": 2.1860909461975098,
"step": 244
},
{
"epoch": 0.8032786885245902,
"grad_norm": 13.2826975259407,
"learning_rate": 9.1817069137349e-06,
"loss": 2.87062406539917,
"step": 245
},
{
"epoch": 0.8065573770491803,
"grad_norm": 8.223008650713565,
"learning_rate": 9.17121323250362e-06,
"loss": 2.6421830654144287,
"step": 246
},
{
"epoch": 0.8098360655737705,
"grad_norm": 7.209232784999499,
"learning_rate": 9.160658771098323e-06,
"loss": 1.1461129188537598,
"step": 247
},
{
"epoch": 0.8131147540983606,
"grad_norm": 5.807632898905771,
"learning_rate": 9.150043683311673e-06,
"loss": 2.4757280349731445,
"step": 248
},
{
"epoch": 0.8163934426229508,
"grad_norm": 11.703476641956268,
"learning_rate": 9.139368123819742e-06,
"loss": 2.5260419845581055,
"step": 249
},
{
"epoch": 0.819672131147541,
"grad_norm": 17.15084273614192,
"learning_rate": 9.128632248179761e-06,
"loss": 2.451849937438965,
"step": 250
},
{
"epoch": 0.8229508196721311,
"grad_norm": 7.708323928439153,
"learning_rate": 9.117836212827839e-06,
"loss": 2.810560941696167,
"step": 251
},
{
"epoch": 0.8262295081967214,
"grad_norm": 7.844205619738867,
"learning_rate": 9.1069801750767e-06,
"loss": 2.397233724594116,
"step": 252
},
{
"epoch": 0.8295081967213115,
"grad_norm": 11.411056209891902,
"learning_rate": 9.096064293113382e-06,
"loss": 2.5832808017730713,
"step": 253
},
{
"epoch": 0.8327868852459016,
"grad_norm": 6.206045042941081,
"learning_rate": 9.085088725996934e-06,
"loss": 1.8659820556640625,
"step": 254
},
{
"epoch": 0.8360655737704918,
"grad_norm": 16.623703379667013,
"learning_rate": 9.074053633656095e-06,
"loss": 2.41814923286438,
"step": 255
},
{
"epoch": 0.839344262295082,
"grad_norm": 7.528315129785465,
"learning_rate": 9.062959176886967e-06,
"loss": 2.8099145889282227,
"step": 256
},
{
"epoch": 0.8426229508196721,
"grad_norm": 12.354232937337795,
"learning_rate": 9.051805517350674e-06,
"loss": 2.538529872894287,
"step": 257
},
{
"epoch": 0.8459016393442623,
"grad_norm": 7.315324736289917,
"learning_rate": 9.040592817571001e-06,
"loss": 2.3083245754241943,
"step": 258
},
{
"epoch": 0.8491803278688524,
"grad_norm": 9.003434584265575,
"learning_rate": 9.029321240932033e-06,
"loss": 2.702756881713867,
"step": 259
},
{
"epoch": 0.8524590163934426,
"grad_norm": 7.755118334347247,
"learning_rate": 9.017990951675764e-06,
"loss": 2.3455848693847656,
"step": 260
},
{
"epoch": 0.8557377049180328,
"grad_norm": 7.720868789254746,
"learning_rate": 9.006602114899711e-06,
"loss": 2.678722381591797,
"step": 261
},
{
"epoch": 0.8590163934426229,
"grad_norm": 9.399180691270317,
"learning_rate": 8.99515489655451e-06,
"loss": 2.4393181800842285,
"step": 262
},
{
"epoch": 0.8622950819672132,
"grad_norm": 6.426704931421514,
"learning_rate": 8.983649463441492e-06,
"loss": 2.7876553535461426,
"step": 263
},
{
"epoch": 0.8655737704918033,
"grad_norm": 10.514349476379792,
"learning_rate": 8.972085983210259e-06,
"loss": 2.637355089187622,
"step": 264
},
{
"epoch": 0.8688524590163934,
"grad_norm": 23.26412353621198,
"learning_rate": 8.96046462435623e-06,
"loss": 2.2888271808624268,
"step": 265
},
{
"epoch": 0.8721311475409836,
"grad_norm": 9.109489526446593,
"learning_rate": 8.948785556218202e-06,
"loss": 2.07401180267334,
"step": 266
},
{
"epoch": 0.8754098360655738,
"grad_norm": 17.55056638792198,
"learning_rate": 8.937048948975869e-06,
"loss": 2.2682414054870605,
"step": 267
},
{
"epoch": 0.8786885245901639,
"grad_norm": 10.78861045705446,
"learning_rate": 8.925254973647344e-06,
"loss": 2.2851309776306152,
"step": 268
},
{
"epoch": 0.8819672131147541,
"grad_norm": 7.54314016455574,
"learning_rate": 8.913403802086677e-06,
"loss": 2.6696438789367676,
"step": 269
},
{
"epoch": 0.8852459016393442,
"grad_norm": 5.9903088070059916,
"learning_rate": 8.901495606981339e-06,
"loss": 2.483783721923828,
"step": 270
},
{
"epoch": 0.8885245901639345,
"grad_norm": 10.060788671745378,
"learning_rate": 8.88953056184971e-06,
"loss": 2.673245906829834,
"step": 271
},
{
"epoch": 0.8918032786885246,
"grad_norm": 7.034335058403492,
"learning_rate": 8.877508841038559e-06,
"loss": 2.4660322666168213,
"step": 272
},
{
"epoch": 0.8950819672131147,
"grad_norm": 8.55853434508635,
"learning_rate": 8.865430619720484e-06,
"loss": 2.471275568008423,
"step": 273
},
{
"epoch": 0.898360655737705,
"grad_norm": 14.342195703865347,
"learning_rate": 8.85329607389138e-06,
"loss": 2.7636022567749023,
"step": 274
},
{
"epoch": 0.9016393442622951,
"grad_norm": 7.082393678085795,
"learning_rate": 8.841105380367861e-06,
"loss": 2.4044272899627686,
"step": 275
},
{
"epoch": 0.9049180327868852,
"grad_norm": 11.224019201335379,
"learning_rate": 8.828858716784692e-06,
"loss": 2.3502447605133057,
"step": 276
},
{
"epoch": 0.9081967213114754,
"grad_norm": 10.7822481689718,
"learning_rate": 8.816556261592191e-06,
"loss": 2.407078266143799,
"step": 277
},
{
"epoch": 0.9114754098360656,
"grad_norm": 6.128814880041577,
"learning_rate": 8.804198194053643e-06,
"loss": 2.4198107719421387,
"step": 278
},
{
"epoch": 0.9147540983606557,
"grad_norm": 8.787476845180032,
"learning_rate": 8.791784694242672e-06,
"loss": 2.318711280822754,
"step": 279
},
{
"epoch": 0.9180327868852459,
"grad_norm": 6.481119402062166,
"learning_rate": 8.779315943040629e-06,
"loss": 2.7764549255371094,
"step": 280
},
{
"epoch": 0.921311475409836,
"grad_norm": 8.880159064541218,
"learning_rate": 8.766792122133949e-06,
"loss": 2.4250147342681885,
"step": 281
},
{
"epoch": 0.9245901639344263,
"grad_norm": 8.644229718563109,
"learning_rate": 8.75421341401151e-06,
"loss": 2.468935966491699,
"step": 282
},
{
"epoch": 0.9278688524590164,
"grad_norm": 13.744531085798844,
"learning_rate": 8.741580001961967e-06,
"loss": 2.169853448867798,
"step": 283
},
{
"epoch": 0.9311475409836065,
"grad_norm": 6.308357979610343,
"learning_rate": 8.728892070071084e-06,
"loss": 2.5795698165893555,
"step": 284
},
{
"epoch": 0.9344262295081968,
"grad_norm": 10.052189974383634,
"learning_rate": 8.716149803219059e-06,
"loss": 2.66308856010437,
"step": 285
},
{
"epoch": 0.9377049180327869,
"grad_norm": 9.123034526965936,
"learning_rate": 8.703353387077813e-06,
"loss": 2.4960551261901855,
"step": 286
},
{
"epoch": 0.940983606557377,
"grad_norm": 22.423904585097915,
"learning_rate": 8.690503008108305e-06,
"loss": 2.661004066467285,
"step": 287
},
{
"epoch": 0.9442622950819672,
"grad_norm": 8.232659723073683,
"learning_rate": 8.677598853557799e-06,
"loss": 2.5189502239227295,
"step": 288
},
{
"epoch": 0.9475409836065574,
"grad_norm": 7.4821803316082915,
"learning_rate": 8.66464111145714e-06,
"loss": 2.6756224632263184,
"step": 289
},
{
"epoch": 0.9508196721311475,
"grad_norm": 9.585079589620893,
"learning_rate": 8.65162997061802e-06,
"loss": 2.1756176948547363,
"step": 290
},
{
"epoch": 0.9540983606557377,
"grad_norm": 7.537583231538749,
"learning_rate": 8.638565620630219e-06,
"loss": 2.4570674896240234,
"step": 291
},
{
"epoch": 0.9573770491803278,
"grad_norm": 6.694511150349457,
"learning_rate": 8.625448251858848e-06,
"loss": 2.3054912090301514,
"step": 292
},
{
"epoch": 0.9606557377049181,
"grad_norm": 7.917760682682373,
"learning_rate": 8.612278055441573e-06,
"loss": 2.393439769744873,
"step": 293
},
{
"epoch": 0.9639344262295082,
"grad_norm": 7.85388740220168,
"learning_rate": 8.599055223285826e-06,
"loss": 2.5273613929748535,
"step": 294
},
{
"epoch": 0.9672131147540983,
"grad_norm": 5.352436129387882,
"learning_rate": 8.585779948066015e-06,
"loss": 2.446168899536133,
"step": 295
},
{
"epoch": 0.9704918032786886,
"grad_norm": 9.580657348379491,
"learning_rate": 8.572452423220717e-06,
"loss": 2.432976484298706,
"step": 296
},
{
"epoch": 0.9737704918032787,
"grad_norm": 6.172511361863051,
"learning_rate": 8.55907284294985e-06,
"loss": 2.350724220275879,
"step": 297
},
{
"epoch": 0.9770491803278688,
"grad_norm": 6.254807576902956,
"learning_rate": 8.54564140221185e-06,
"loss": 2.5221989154815674,
"step": 298
},
{
"epoch": 0.980327868852459,
"grad_norm": 11.45397684624707,
"learning_rate": 8.532158296720837e-06,
"loss": 2.512618064880371,
"step": 299
},
{
"epoch": 0.9836065573770492,
"grad_norm": 10.234003050662777,
"learning_rate": 8.518623722943747e-06,
"loss": 2.108579397201538,
"step": 300
},
{
"epoch": 0.9868852459016394,
"grad_norm": 9.720088231567928,
"learning_rate": 8.505037878097481e-06,
"loss": 2.637286901473999,
"step": 301
},
{
"epoch": 0.9901639344262295,
"grad_norm": 15.219136970853816,
"learning_rate": 8.491400960146032e-06,
"loss": 2.0853002071380615,
"step": 302
},
{
"epoch": 0.9934426229508196,
"grad_norm": 9.635171729082114,
"learning_rate": 8.477713167797592e-06,
"loss": 2.340456008911133,
"step": 303
},
{
"epoch": 0.9967213114754099,
"grad_norm": 6.87333560177396,
"learning_rate": 8.463974700501661e-06,
"loss": 2.3672666549682617,
"step": 304
},
{
"epoch": 1.0,
"grad_norm": 10.462621042015464,
"learning_rate": 8.450185758446145e-06,
"loss": 2.800326347351074,
"step": 305
},
{
"epoch": 1.0032786885245901,
"grad_norm": 14.533639373938543,
"learning_rate": 8.436346542554432e-06,
"loss": 1.219738245010376,
"step": 306
},
{
"epoch": 1.0065573770491802,
"grad_norm": 14.88360903001493,
"learning_rate": 8.422457254482469e-06,
"loss": 1.4494341611862183,
"step": 307
},
{
"epoch": 1.0098360655737706,
"grad_norm": 12.15977366188915,
"learning_rate": 8.408518096615817e-06,
"loss": 1.4818754196166992,
"step": 308
},
{
"epoch": 1.0131147540983607,
"grad_norm": 11.988406204921171,
"learning_rate": 8.394529272066715e-06,
"loss": 1.8539477586746216,
"step": 309
},
{
"epoch": 1.0163934426229508,
"grad_norm": 8.439921492481496,
"learning_rate": 8.380490984671105e-06,
"loss": 1.4613733291625977,
"step": 310
},
{
"epoch": 1.019672131147541,
"grad_norm": 7.084191580276859,
"learning_rate": 8.366403438985675e-06,
"loss": 1.5455926656723022,
"step": 311
},
{
"epoch": 1.022950819672131,
"grad_norm": 6.423762559791681,
"learning_rate": 8.352266840284866e-06,
"loss": 1.4449374675750732,
"step": 312
},
{
"epoch": 1.0262295081967212,
"grad_norm": 8.188558452199691,
"learning_rate": 8.338081394557891e-06,
"loss": 1.2924364805221558,
"step": 313
},
{
"epoch": 1.0295081967213116,
"grad_norm": 8.728713037991858,
"learning_rate": 8.323847308505732e-06,
"loss": 1.5841925144195557,
"step": 314
},
{
"epoch": 1.0327868852459017,
"grad_norm": 13.070036453280155,
"learning_rate": 8.30956478953812e-06,
"loss": 1.3826817274093628,
"step": 315
},
{
"epoch": 1.0360655737704918,
"grad_norm": 9.235731930061215,
"learning_rate": 8.295234045770524e-06,
"loss": 1.4997901916503906,
"step": 316
},
{
"epoch": 1.039344262295082,
"grad_norm": 13.174420813084796,
"learning_rate": 8.28085528602111e-06,
"loss": 1.5066428184509277,
"step": 317
},
{
"epoch": 1.042622950819672,
"grad_norm": 10.14182980143544,
"learning_rate": 8.2664287198077e-06,
"loss": 1.4239689111709595,
"step": 318
},
{
"epoch": 1.0459016393442624,
"grad_norm": 16.151021644287574,
"learning_rate": 8.251954557344724e-06,
"loss": 1.4513654708862305,
"step": 319
},
{
"epoch": 1.0491803278688525,
"grad_norm": 15.98731534303969,
"learning_rate": 8.23743300954015e-06,
"loss": 1.5789086818695068,
"step": 320
},
{
"epoch": 1.0524590163934426,
"grad_norm": 9.928640139556784,
"learning_rate": 8.222864287992419e-06,
"loss": 1.6258488893508911,
"step": 321
},
{
"epoch": 1.0557377049180328,
"grad_norm": 7.190541527762004,
"learning_rate": 8.208248604987348e-06,
"loss": 1.4359124898910522,
"step": 322
},
{
"epoch": 1.0590163934426229,
"grad_norm": 7.782232053710492,
"learning_rate": 8.193586173495056e-06,
"loss": 1.6550524234771729,
"step": 323
},
{
"epoch": 1.0622950819672132,
"grad_norm": 13.11681490593238,
"learning_rate": 8.178877207166842e-06,
"loss": 1.2745180130004883,
"step": 324
},
{
"epoch": 1.0655737704918034,
"grad_norm": 15.294585724645694,
"learning_rate": 8.164121920332085e-06,
"loss": 1.411191463470459,
"step": 325
},
{
"epoch": 1.0688524590163935,
"grad_norm": 7.96799571943578,
"learning_rate": 8.149320527995111e-06,
"loss": 1.6015852689743042,
"step": 326
},
{
"epoch": 1.0721311475409836,
"grad_norm": 7.333251448915382,
"learning_rate": 8.13447324583207e-06,
"loss": 1.2892570495605469,
"step": 327
},
{
"epoch": 1.0754098360655737,
"grad_norm": 8.53552004919549,
"learning_rate": 8.119580290187783e-06,
"loss": 1.3905184268951416,
"step": 328
},
{
"epoch": 1.0786885245901638,
"grad_norm": 10.797771056593009,
"learning_rate": 8.104641878072603e-06,
"loss": 1.366774559020996,
"step": 329
},
{
"epoch": 1.0819672131147542,
"grad_norm": 5.181145611428843,
"learning_rate": 8.089658227159239e-06,
"loss": 1.0951892137527466,
"step": 330
},
{
"epoch": 1.0852459016393443,
"grad_norm": 8.289032879258805,
"learning_rate": 8.074629555779586e-06,
"loss": 1.5894650220870972,
"step": 331
},
{
"epoch": 1.0885245901639344,
"grad_norm": 6.9196900995086645,
"learning_rate": 8.059556082921557e-06,
"loss": 2.0638175010681152,
"step": 332
},
{
"epoch": 1.0918032786885246,
"grad_norm": 8.059026065369947,
"learning_rate": 8.044438028225878e-06,
"loss": 1.4300751686096191,
"step": 333
},
{
"epoch": 1.0950819672131147,
"grad_norm": 9.730961807383812,
"learning_rate": 8.02927561198289e-06,
"loss": 1.6003992557525635,
"step": 334
},
{
"epoch": 1.098360655737705,
"grad_norm": 8.296955967033988,
"learning_rate": 8.014069055129345e-06,
"loss": 1.5709595680236816,
"step": 335
},
{
"epoch": 1.1016393442622952,
"grad_norm": 8.809665246351774,
"learning_rate": 7.998818579245183e-06,
"loss": 1.8245192766189575,
"step": 336
},
{
"epoch": 1.1049180327868853,
"grad_norm": 7.96484738715982,
"learning_rate": 7.9835244065503e-06,
"loss": 1.368034839630127,
"step": 337
},
{
"epoch": 1.1081967213114754,
"grad_norm": 7.056947687170356,
"learning_rate": 7.968186759901315e-06,
"loss": 1.4263694286346436,
"step": 338
},
{
"epoch": 1.1114754098360655,
"grad_norm": 8.897554028630147,
"learning_rate": 7.952805862788322e-06,
"loss": 1.8532183170318604,
"step": 339
},
{
"epoch": 1.1147540983606556,
"grad_norm": 12.708467273377865,
"learning_rate": 7.937381939331628e-06,
"loss": 1.4250767230987549,
"step": 340
},
{
"epoch": 1.118032786885246,
"grad_norm": 8.2827556480665,
"learning_rate": 7.9219152142785e-06,
"loss": 1.4702391624450684,
"step": 341
},
{
"epoch": 1.1213114754098361,
"grad_norm": 31.419584705515167,
"learning_rate": 7.906405912999871e-06,
"loss": 1.59003484249115,
"step": 342
},
{
"epoch": 1.1245901639344262,
"grad_norm": 8.593861875038188,
"learning_rate": 7.890854261487074e-06,
"loss": 1.5017095804214478,
"step": 343
},
{
"epoch": 1.1278688524590164,
"grad_norm": 8.476156978391113,
"learning_rate": 7.875260486348542e-06,
"loss": 1.3351414203643799,
"step": 344
},
{
"epoch": 1.1311475409836065,
"grad_norm": 7.431587054521972,
"learning_rate": 7.8596248148065e-06,
"loss": 1.2222039699554443,
"step": 345
},
{
"epoch": 1.1344262295081968,
"grad_norm": 10.172410177178598,
"learning_rate": 7.843947474693665e-06,
"loss": 1.833259105682373,
"step": 346
},
{
"epoch": 1.137704918032787,
"grad_norm": 9.695236509446838,
"learning_rate": 7.82822869444992e-06,
"loss": 1.554382085800171,
"step": 347
},
{
"epoch": 1.140983606557377,
"grad_norm": 8.75471707105222,
"learning_rate": 7.812468703118984e-06,
"loss": 1.4548015594482422,
"step": 348
},
{
"epoch": 1.1442622950819672,
"grad_norm": 8.57064855290684,
"learning_rate": 7.796667730345083e-06,
"loss": 1.3063480854034424,
"step": 349
},
{
"epoch": 1.1475409836065573,
"grad_norm": 11.662681153860305,
"learning_rate": 7.780826006369586e-06,
"loss": 0.8981505632400513,
"step": 350
},
{
"epoch": 1.1508196721311474,
"grad_norm": 8.8045560064301,
"learning_rate": 7.764943762027675e-06,
"loss": 1.2321419715881348,
"step": 351
},
{
"epoch": 1.1540983606557378,
"grad_norm": 7.398693309255406,
"learning_rate": 7.749021228744958e-06,
"loss": 1.6639280319213867,
"step": 352
},
{
"epoch": 1.157377049180328,
"grad_norm": 12.812324275485885,
"learning_rate": 7.733058638534113e-06,
"loss": 1.4588600397109985,
"step": 353
},
{
"epoch": 1.160655737704918,
"grad_norm": 11.700942854663293,
"learning_rate": 7.717056223991499e-06,
"loss": 1.7766895294189453,
"step": 354
},
{
"epoch": 1.1639344262295082,
"grad_norm": 8.096809191195872,
"learning_rate": 7.701014218293768e-06,
"loss": 1.545503854751587,
"step": 355
},
{
"epoch": 1.1672131147540983,
"grad_norm": 10.15781291965153,
"learning_rate": 7.68493285519447e-06,
"loss": 1.5841809511184692,
"step": 356
},
{
"epoch": 1.1704918032786886,
"grad_norm": 6.956266551234813,
"learning_rate": 7.668812369020645e-06,
"loss": 1.3549474477767944,
"step": 357
},
{
"epoch": 1.1737704918032787,
"grad_norm": 8.697874364844058,
"learning_rate": 7.652652994669407e-06,
"loss": 1.6333961486816406,
"step": 358
},
{
"epoch": 1.1770491803278689,
"grad_norm": 8.247562789586302,
"learning_rate": 7.636454967604524e-06,
"loss": 1.0479097366333008,
"step": 359
},
{
"epoch": 1.180327868852459,
"grad_norm": 14.220261949793006,
"learning_rate": 7.620218523852987e-06,
"loss": 1.8211294412612915,
"step": 360
},
{
"epoch": 1.1836065573770491,
"grad_norm": 9.624626520315642,
"learning_rate": 7.603943900001567e-06,
"loss": 1.1971122026443481,
"step": 361
},
{
"epoch": 1.1868852459016392,
"grad_norm": 6.02279814672322,
"learning_rate": 7.587631333193373e-06,
"loss": 1.3711479902267456,
"step": 362
},
{
"epoch": 1.1901639344262296,
"grad_norm": 7.494490493136151,
"learning_rate": 7.571281061124394e-06,
"loss": 1.4267476797103882,
"step": 363
},
{
"epoch": 1.1934426229508197,
"grad_norm": 11.27806543340223,
"learning_rate": 7.554893322040032e-06,
"loss": 1.758327603340149,
"step": 364
},
{
"epoch": 1.1967213114754098,
"grad_norm": 8.013835367423333,
"learning_rate": 7.538468354731636e-06,
"loss": 1.5538535118103027,
"step": 365
},
{
"epoch": 1.2,
"grad_norm": 8.361421150521341,
"learning_rate": 7.522006398533022e-06,
"loss": 1.1149446964263916,
"step": 366
},
{
"epoch": 1.20327868852459,
"grad_norm": 9.229788704559793,
"learning_rate": 7.505507693316977e-06,
"loss": 1.764215111732483,
"step": 367
},
{
"epoch": 1.2065573770491804,
"grad_norm": 9.763541518847278,
"learning_rate": 7.4889724794917784e-06,
"loss": 1.3411585092544556,
"step": 368
},
{
"epoch": 1.2098360655737705,
"grad_norm": 8.781910763604646,
"learning_rate": 7.472400997997679e-06,
"loss": 1.4444241523742676,
"step": 369
},
{
"epoch": 1.2131147540983607,
"grad_norm": 9.881713464429248,
"learning_rate": 7.4557934903034035e-06,
"loss": 1.1535298824310303,
"step": 370
},
{
"epoch": 1.2163934426229508,
"grad_norm": 16.038401168578606,
"learning_rate": 7.439150198402619e-06,
"loss": 1.7464418411254883,
"step": 371
},
{
"epoch": 1.219672131147541,
"grad_norm": 12.51653188258912,
"learning_rate": 7.422471364810426e-06,
"loss": 1.3906786441802979,
"step": 372
},
{
"epoch": 1.222950819672131,
"grad_norm": 10.458359682213914,
"learning_rate": 7.4057572325598085e-06,
"loss": 1.3982175588607788,
"step": 373
},
{
"epoch": 1.2262295081967214,
"grad_norm": 7.522798397841898,
"learning_rate": 7.3890080451981025e-06,
"loss": 1.4276384115219116,
"step": 374
},
{
"epoch": 1.2295081967213115,
"grad_norm": 13.462837303199894,
"learning_rate": 7.372224046783442e-06,
"loss": 1.682824730873108,
"step": 375
},
{
"epoch": 1.2327868852459016,
"grad_norm": 10.34107419440432,
"learning_rate": 7.355405481881207e-06,
"loss": 1.6824283599853516,
"step": 376
},
{
"epoch": 1.2360655737704918,
"grad_norm": 8.639419387471962,
"learning_rate": 7.338552595560455e-06,
"loss": 1.3464815616607666,
"step": 377
},
{
"epoch": 1.2393442622950819,
"grad_norm": 8.96788308439072,
"learning_rate": 7.321665633390356e-06,
"loss": 2.129988670349121,
"step": 378
},
{
"epoch": 1.2426229508196722,
"grad_norm": 7.205928497540528,
"learning_rate": 7.3047448414366066e-06,
"loss": 1.6468236446380615,
"step": 379
},
{
"epoch": 1.2459016393442623,
"grad_norm": 12.241056010722936,
"learning_rate": 7.287790466257854e-06,
"loss": 1.4744781255722046,
"step": 380
},
{
"epoch": 1.2491803278688525,
"grad_norm": 8.848740093248512,
"learning_rate": 7.270802754902092e-06,
"loss": 1.6379506587982178,
"step": 381
},
{
"epoch": 1.2524590163934426,
"grad_norm": 8.254402118879579,
"learning_rate": 7.253781954903073e-06,
"loss": 1.2095084190368652,
"step": 382
},
{
"epoch": 1.2557377049180327,
"grad_norm": 8.75654117126329,
"learning_rate": 7.236728314276692e-06,
"loss": 1.320736289024353,
"step": 383
},
{
"epoch": 1.2590163934426228,
"grad_norm": 16.148893866749482,
"learning_rate": 7.219642081517374e-06,
"loss": 1.2354371547698975,
"step": 384
},
{
"epoch": 1.2622950819672132,
"grad_norm": 8.876266665665618,
"learning_rate": 7.2025235055944605e-06,
"loss": 1.9609148502349854,
"step": 385
},
{
"epoch": 1.2655737704918033,
"grad_norm": 10.212145685917541,
"learning_rate": 7.185372835948574e-06,
"loss": 1.4914538860321045,
"step": 386
},
{
"epoch": 1.2688524590163934,
"grad_norm": 9.875822539195672,
"learning_rate": 7.168190322487982e-06,
"loss": 1.4521596431732178,
"step": 387
},
{
"epoch": 1.2721311475409836,
"grad_norm": 13.94574516279124,
"learning_rate": 7.150976215584967e-06,
"loss": 1.3369953632354736,
"step": 388
},
{
"epoch": 1.275409836065574,
"grad_norm": 6.555822273720464,
"learning_rate": 7.133730766072163e-06,
"loss": 1.5519535541534424,
"step": 389
},
{
"epoch": 1.278688524590164,
"grad_norm": 12.541244651564327,
"learning_rate": 7.116454225238909e-06,
"loss": 1.866693139076233,
"step": 390
},
{
"epoch": 1.2819672131147541,
"grad_norm": 6.555318810127099,
"learning_rate": 7.0991468448275914e-06,
"loss": 1.2162957191467285,
"step": 391
},
{
"epoch": 1.2852459016393443,
"grad_norm": 16.63261347947183,
"learning_rate": 7.081808877029963e-06,
"loss": 1.3007960319519043,
"step": 392
},
{
"epoch": 1.2885245901639344,
"grad_norm": 18.536839858396142,
"learning_rate": 7.064440574483482e-06,
"loss": 1.2612102031707764,
"step": 393
},
{
"epoch": 1.2918032786885245,
"grad_norm": 11.05091421652279,
"learning_rate": 7.047042190267625e-06,
"loss": 1.6232455968856812,
"step": 394
},
{
"epoch": 1.2950819672131146,
"grad_norm": 8.081221167653263,
"learning_rate": 7.029613977900192e-06,
"loss": 1.725204586982727,
"step": 395
},
{
"epoch": 1.298360655737705,
"grad_norm": 21.723286214553717,
"learning_rate": 7.0121561913336255e-06,
"loss": 1.5390952825546265,
"step": 396
},
{
"epoch": 1.301639344262295,
"grad_norm": 7.711430606948905,
"learning_rate": 6.994669084951302e-06,
"loss": 1.5362415313720703,
"step": 397
},
{
"epoch": 1.3049180327868852,
"grad_norm": 8.485307706298222,
"learning_rate": 6.977152913563825e-06,
"loss": 1.7464603185653687,
"step": 398
},
{
"epoch": 1.3081967213114754,
"grad_norm": 9.365897332142001,
"learning_rate": 6.95960793240532e-06,
"loss": 1.7053837776184082,
"step": 399
},
{
"epoch": 1.3114754098360657,
"grad_norm": 6.623017337472723,
"learning_rate": 6.942034397129702e-06,
"loss": 1.4123156070709229,
"step": 400
},
{
"epoch": 1.3147540983606558,
"grad_norm": 9.182015994009502,
"learning_rate": 6.924432563806962e-06,
"loss": 2.156587600708008,
"step": 401
},
{
"epoch": 1.318032786885246,
"grad_norm": 9.929028759710313,
"learning_rate": 6.906802688919433e-06,
"loss": 1.3962024450302124,
"step": 402
},
{
"epoch": 1.321311475409836,
"grad_norm": 19.518335593135163,
"learning_rate": 6.889145029358046e-06,
"loss": 1.622226357460022,
"step": 403
},
{
"epoch": 1.3245901639344262,
"grad_norm": 15.124312146579202,
"learning_rate": 6.871459842418596e-06,
"loss": 2.099233388900757,
"step": 404
},
{
"epoch": 1.3278688524590163,
"grad_norm": 12.883770096506646,
"learning_rate": 6.853747385797991e-06,
"loss": 1.523669958114624,
"step": 405
},
{
"epoch": 1.3311475409836064,
"grad_norm": 8.441778137156883,
"learning_rate": 6.836007917590487e-06,
"loss": 1.1277689933776855,
"step": 406
},
{
"epoch": 1.3344262295081968,
"grad_norm": 10.523480974653184,
"learning_rate": 6.818241696283942e-06,
"loss": 1.0837914943695068,
"step": 407
},
{
"epoch": 1.337704918032787,
"grad_norm": 10.574109469392138,
"learning_rate": 6.8004489807560425e-06,
"loss": 1.6207302808761597,
"step": 408
},
{
"epoch": 1.340983606557377,
"grad_norm": 10.926404659494368,
"learning_rate": 6.782630030270525e-06,
"loss": 1.2583204507827759,
"step": 409
},
{
"epoch": 1.3442622950819672,
"grad_norm": 9.862008543326159,
"learning_rate": 6.764785104473411e-06,
"loss": 1.4810888767242432,
"step": 410
},
{
"epoch": 1.3475409836065575,
"grad_norm": 10.24878361683331,
"learning_rate": 6.746914463389216e-06,
"loss": 1.3578720092773438,
"step": 411
},
{
"epoch": 1.3508196721311476,
"grad_norm": 13.251903662824025,
"learning_rate": 6.729018367417158e-06,
"loss": 1.9914039373397827,
"step": 412
},
{
"epoch": 1.3540983606557377,
"grad_norm": 9.328090099153702,
"learning_rate": 6.7110970773273735e-06,
"loss": 1.8492844104766846,
"step": 413
},
{
"epoch": 1.3573770491803279,
"grad_norm": 11.488647842266868,
"learning_rate": 6.693150854257102e-06,
"loss": 1.6561657190322876,
"step": 414
},
{
"epoch": 1.360655737704918,
"grad_norm": 7.343608128825276,
"learning_rate": 6.675179959706899e-06,
"loss": 1.4760901927947998,
"step": 415
},
{
"epoch": 1.3639344262295081,
"grad_norm": 8.579920022541033,
"learning_rate": 6.65718465553681e-06,
"loss": 1.6962871551513672,
"step": 416
},
{
"epoch": 1.3672131147540982,
"grad_norm": 9.646239986624149,
"learning_rate": 6.639165203962567e-06,
"loss": 1.500190258026123,
"step": 417
},
{
"epoch": 1.3704918032786886,
"grad_norm": 11.723227819136099,
"learning_rate": 6.621121867551759e-06,
"loss": 1.067988634109497,
"step": 418
},
{
"epoch": 1.3737704918032787,
"grad_norm": 11.510256977384001,
"learning_rate": 6.603054909220005e-06,
"loss": 1.4429908990859985,
"step": 419
},
{
"epoch": 1.3770491803278688,
"grad_norm": 11.782974259408602,
"learning_rate": 6.584964592227135e-06,
"loss": 1.4444313049316406,
"step": 420
},
{
"epoch": 1.380327868852459,
"grad_norm": 8.127425704413369,
"learning_rate": 6.566851180173344e-06,
"loss": 1.5946853160858154,
"step": 421
},
{
"epoch": 1.3836065573770493,
"grad_norm": 11.834837231806146,
"learning_rate": 6.548714936995346e-06,
"loss": 1.435799479484558,
"step": 422
},
{
"epoch": 1.3868852459016394,
"grad_norm": 6.449784907628745,
"learning_rate": 6.5305561269625455e-06,
"loss": 1.7013428211212158,
"step": 423
},
{
"epoch": 1.3901639344262295,
"grad_norm": 10.583301597719005,
"learning_rate": 6.51237501467317e-06,
"loss": 1.377068281173706,
"step": 424
},
{
"epoch": 1.3934426229508197,
"grad_norm": 8.157704440106766,
"learning_rate": 6.494171865050421e-06,
"loss": 1.9748648405075073,
"step": 425
},
{
"epoch": 1.3967213114754098,
"grad_norm": 6.554016476355135,
"learning_rate": 6.475946943338616e-06,
"loss": 1.2935904264450073,
"step": 426
},
{
"epoch": 1.4,
"grad_norm": 22.578016627767845,
"learning_rate": 6.45770051509932e-06,
"loss": 1.9697861671447754,
"step": 427
},
{
"epoch": 1.40327868852459,
"grad_norm": 9.228555178608955,
"learning_rate": 6.439432846207475e-06,
"loss": 1.069584846496582,
"step": 428
},
{
"epoch": 1.4065573770491804,
"grad_norm": 8.24983523057297,
"learning_rate": 6.421144202847531e-06,
"loss": 1.6482625007629395,
"step": 429
},
{
"epoch": 1.4098360655737705,
"grad_norm": 7.385866395546861,
"learning_rate": 6.402834851509564e-06,
"loss": 1.5046641826629639,
"step": 430
},
{
"epoch": 1.4131147540983606,
"grad_norm": 8.637935153514332,
"learning_rate": 6.384505058985388e-06,
"loss": 1.5675042867660522,
"step": 431
},
{
"epoch": 1.4163934426229507,
"grad_norm": 9.79023497333411,
"learning_rate": 6.366155092364681e-06,
"loss": 1.3445487022399902,
"step": 432
},
{
"epoch": 1.419672131147541,
"grad_norm": 6.8547486886474935,
"learning_rate": 6.347785219031076e-06,
"loss": 1.289559245109558,
"step": 433
},
{
"epoch": 1.4229508196721312,
"grad_norm": 10.584428259104762,
"learning_rate": 6.329395706658278e-06,
"loss": 1.3962552547454834,
"step": 434
},
{
"epoch": 1.4262295081967213,
"grad_norm": 9.55282934543838,
"learning_rate": 6.31098682320616e-06,
"loss": 1.2521915435791016,
"step": 435
},
{
"epoch": 1.4295081967213115,
"grad_norm": 12.901326350437573,
"learning_rate": 6.292558836916856e-06,
"loss": 1.2058460712432861,
"step": 436
},
{
"epoch": 1.4327868852459016,
"grad_norm": 9.737585592985,
"learning_rate": 6.274112016310854e-06,
"loss": 1.413370132446289,
"step": 437
},
{
"epoch": 1.4360655737704917,
"grad_norm": 6.485759737574068,
"learning_rate": 6.2556466301830835e-06,
"loss": 1.2930845022201538,
"step": 438
},
{
"epoch": 1.4393442622950818,
"grad_norm": 11.64974070881728,
"learning_rate": 6.237162947598998e-06,
"loss": 1.328700065612793,
"step": 439
},
{
"epoch": 1.4426229508196722,
"grad_norm": 7.07603611397449,
"learning_rate": 6.2186612378906545e-06,
"loss": 1.4033368825912476,
"step": 440
},
{
"epoch": 1.4459016393442623,
"grad_norm": 13.822104214327695,
"learning_rate": 6.200141770652791e-06,
"loss": 1.4624767303466797,
"step": 441
},
{
"epoch": 1.4491803278688524,
"grad_norm": 7.361221857860456,
"learning_rate": 6.181604815738899e-06,
"loss": 1.576357364654541,
"step": 442
},
{
"epoch": 1.4524590163934425,
"grad_norm": 9.456106131000285,
"learning_rate": 6.163050643257282e-06,
"loss": 1.532828450202942,
"step": 443
},
{
"epoch": 1.455737704918033,
"grad_norm": 7.632015314506418,
"learning_rate": 6.144479523567131e-06,
"loss": 1.856471300125122,
"step": 444
},
{
"epoch": 1.459016393442623,
"grad_norm": 10.258556155564422,
"learning_rate": 6.1258917272745795e-06,
"loss": 1.2253443002700806,
"step": 445
},
{
"epoch": 1.4622950819672131,
"grad_norm": 13.801749921871817,
"learning_rate": 6.107287525228764e-06,
"loss": 1.8214157819747925,
"step": 446
},
{
"epoch": 1.4655737704918033,
"grad_norm": 12.95500964912237,
"learning_rate": 6.08866718851787e-06,
"loss": 1.2344238758087158,
"step": 447
},
{
"epoch": 1.4688524590163934,
"grad_norm": 8.114059630664892,
"learning_rate": 6.070030988465192e-06,
"loss": 1.3586925268173218,
"step": 448
},
{
"epoch": 1.4721311475409835,
"grad_norm": 8.302997593912952,
"learning_rate": 6.051379196625171e-06,
"loss": 1.323337197303772,
"step": 449
},
{
"epoch": 1.4754098360655736,
"grad_norm": 9.165565749301205,
"learning_rate": 6.0327120847794415e-06,
"loss": 1.3031678199768066,
"step": 450
},
{
"epoch": 1.478688524590164,
"grad_norm": 11.039958256486253,
"learning_rate": 6.014029924932874e-06,
"loss": 1.7454357147216797,
"step": 451
},
{
"epoch": 1.481967213114754,
"grad_norm": 5.8665691715667165,
"learning_rate": 5.995332989309603e-06,
"loss": 1.4284415245056152,
"step": 452
},
{
"epoch": 1.4852459016393442,
"grad_norm": 9.738643550562717,
"learning_rate": 5.976621550349072e-06,
"loss": 1.5822160243988037,
"step": 453
},
{
"epoch": 1.4885245901639343,
"grad_norm": 9.105911760512909,
"learning_rate": 5.957895880702056e-06,
"loss": 1.207653284072876,
"step": 454
},
{
"epoch": 1.4918032786885247,
"grad_norm": 8.94493900334316,
"learning_rate": 5.9391562532266875e-06,
"loss": 1.18796968460083,
"step": 455
},
{
"epoch": 1.4950819672131148,
"grad_norm": 7.253259219911815,
"learning_rate": 5.920402940984483e-06,
"loss": 1.4249799251556396,
"step": 456
},
{
"epoch": 1.498360655737705,
"grad_norm": 6.0428545997211325,
"learning_rate": 5.90163621723637e-06,
"loss": 1.2148387432098389,
"step": 457
},
{
"epoch": 1.501639344262295,
"grad_norm": 10.68293773211332,
"learning_rate": 5.8828563554386955e-06,
"loss": 1.2648682594299316,
"step": 458
},
{
"epoch": 1.5049180327868852,
"grad_norm": 8.198841450906707,
"learning_rate": 5.864063629239243e-06,
"loss": 1.2296135425567627,
"step": 459
},
{
"epoch": 1.5081967213114753,
"grad_norm": 13.518888318228889,
"learning_rate": 5.845258312473252e-06,
"loss": 1.476584553718567,
"step": 460
},
{
"epoch": 1.5114754098360654,
"grad_norm": 12.120554378871548,
"learning_rate": 5.826440679159424e-06,
"loss": 1.1283669471740723,
"step": 461
},
{
"epoch": 1.5147540983606558,
"grad_norm": 6.670816048809034,
"learning_rate": 5.807611003495925e-06,
"loss": 1.3941131830215454,
"step": 462
},
{
"epoch": 1.518032786885246,
"grad_norm": 9.599762640935925,
"learning_rate": 5.7887695598563975e-06,
"loss": 1.4467484951019287,
"step": 463
},
{
"epoch": 1.521311475409836,
"grad_norm": 8.945489686049422,
"learning_rate": 5.769916622785957e-06,
"loss": 1.5565500259399414,
"step": 464
},
{
"epoch": 1.5245901639344264,
"grad_norm": 9.953206067871495,
"learning_rate": 5.751052466997196e-06,
"loss": 1.19337797164917,
"step": 465
},
{
"epoch": 1.5278688524590165,
"grad_norm": 14.727031659772624,
"learning_rate": 5.732177367366176e-06,
"loss": 1.8662505149841309,
"step": 466
},
{
"epoch": 1.5311475409836066,
"grad_norm": 10.509488558706542,
"learning_rate": 5.713291598928429e-06,
"loss": 1.449589729309082,
"step": 467
},
{
"epoch": 1.5344262295081967,
"grad_norm": 10.923305385782259,
"learning_rate": 5.694395436874942e-06,
"loss": 1.6893059015274048,
"step": 468
},
{
"epoch": 1.5377049180327869,
"grad_norm": 8.286311693216856,
"learning_rate": 5.675489156548151e-06,
"loss": 1.3428866863250732,
"step": 469
},
{
"epoch": 1.540983606557377,
"grad_norm": 6.173067699163104,
"learning_rate": 5.656573033437932e-06,
"loss": 1.805051326751709,
"step": 470
},
{
"epoch": 1.544262295081967,
"grad_norm": 11.536799759656052,
"learning_rate": 5.63764734317758e-06,
"loss": 1.928034782409668,
"step": 471
},
{
"epoch": 1.5475409836065572,
"grad_norm": 7.209559234784469,
"learning_rate": 5.618712361539798e-06,
"loss": 1.2544653415679932,
"step": 472
},
{
"epoch": 1.5508196721311476,
"grad_norm": 7.0947337002847615,
"learning_rate": 5.599768364432681e-06,
"loss": 1.4806904792785645,
"step": 473
},
{
"epoch": 1.5540983606557377,
"grad_norm": 6.378225592429903,
"learning_rate": 5.5808156278956815e-06,
"loss": 1.6040301322937012,
"step": 474
},
{
"epoch": 1.5573770491803278,
"grad_norm": 13.001532433243089,
"learning_rate": 5.561854428095606e-06,
"loss": 1.6910431385040283,
"step": 475
},
{
"epoch": 1.5606557377049182,
"grad_norm": 7.237899730893004,
"learning_rate": 5.542885041322577e-06,
"loss": 1.3757598400115967,
"step": 476
},
{
"epoch": 1.5639344262295083,
"grad_norm": 6.703931743993996,
"learning_rate": 5.523907743986017e-06,
"loss": 1.345323920249939,
"step": 477
},
{
"epoch": 1.5672131147540984,
"grad_norm": 17.92880345014065,
"learning_rate": 5.5049228126106106e-06,
"loss": 1.7451939582824707,
"step": 478
},
{
"epoch": 1.5704918032786885,
"grad_norm": 25.47716013520683,
"learning_rate": 5.4859305238322846e-06,
"loss": 1.5801379680633545,
"step": 479
},
{
"epoch": 1.5737704918032787,
"grad_norm": 9.78005871327646,
"learning_rate": 5.466931154394171e-06,
"loss": 1.4417543411254883,
"step": 480
},
{
"epoch": 1.5770491803278688,
"grad_norm": 7.845555178426862,
"learning_rate": 5.447924981142578e-06,
"loss": 1.4756526947021484,
"step": 481
},
{
"epoch": 1.580327868852459,
"grad_norm": 6.508529323042152,
"learning_rate": 5.4289122810229535e-06,
"loss": 1.8134113550186157,
"step": 482
},
{
"epoch": 1.583606557377049,
"grad_norm": 7.2399856783936665,
"learning_rate": 5.40989333107585e-06,
"loss": 1.4654526710510254,
"step": 483
},
{
"epoch": 1.5868852459016394,
"grad_norm": 10.055481248084142,
"learning_rate": 5.39086840843289e-06,
"loss": 1.3508714437484741,
"step": 484
},
{
"epoch": 1.5901639344262295,
"grad_norm": 7.055143216570921,
"learning_rate": 5.371837790312725e-06,
"loss": 1.373887300491333,
"step": 485
},
{
"epoch": 1.5934426229508196,
"grad_norm": 9.636116824048985,
"learning_rate": 5.3528017540169974e-06,
"loss": 1.344774842262268,
"step": 486
},
{
"epoch": 1.59672131147541,
"grad_norm": 12.33974858592215,
"learning_rate": 5.3337605769263015e-06,
"loss": 1.9978229999542236,
"step": 487
},
{
"epoch": 1.6,
"grad_norm": 9.710433403844894,
"learning_rate": 5.314714536496135e-06,
"loss": 1.7118706703186035,
"step": 488
},
{
"epoch": 1.6032786885245902,
"grad_norm": 7.498696507906713,
"learning_rate": 5.295663910252867e-06,
"loss": 1.1946070194244385,
"step": 489
},
{
"epoch": 1.6065573770491803,
"grad_norm": 6.3253658386979374,
"learning_rate": 5.276608975789683e-06,
"loss": 1.4657094478607178,
"step": 490
},
{
"epoch": 1.6098360655737705,
"grad_norm": 7.608212656330091,
"learning_rate": 5.25755001076255e-06,
"loss": 1.4694055318832397,
"step": 491
},
{
"epoch": 1.6131147540983606,
"grad_norm": 10.266284962007779,
"learning_rate": 5.238487292886162e-06,
"loss": 1.0663282871246338,
"step": 492
},
{
"epoch": 1.6163934426229507,
"grad_norm": 11.315157373411498,
"learning_rate": 5.219421099929899e-06,
"loss": 1.6470210552215576,
"step": 493
},
{
"epoch": 1.6196721311475408,
"grad_norm": 10.658486832627354,
"learning_rate": 5.200351709713774e-06,
"loss": 1.4890694618225098,
"step": 494
},
{
"epoch": 1.6229508196721312,
"grad_norm": 8.705183945598245,
"learning_rate": 5.181279400104393e-06,
"loss": 1.194528341293335,
"step": 495
},
{
"epoch": 1.6262295081967213,
"grad_norm": 12.287684290665057,
"learning_rate": 5.1622044490108994e-06,
"loss": 1.1717027425765991,
"step": 496
},
{
"epoch": 1.6295081967213116,
"grad_norm": 6.852835561152611,
"learning_rate": 5.143127134380926e-06,
"loss": 1.3001526594161987,
"step": 497
},
{
"epoch": 1.6327868852459018,
"grad_norm": 10.434751231193086,
"learning_rate": 5.124047734196549e-06,
"loss": 2.141303062438965,
"step": 498
},
{
"epoch": 1.6360655737704919,
"grad_norm": 9.796651343186152,
"learning_rate": 5.104966526470227e-06,
"loss": 1.7574173212051392,
"step": 499
},
{
"epoch": 1.639344262295082,
"grad_norm": 7.9300937657173955,
"learning_rate": 5.085883789240764e-06,
"loss": 1.4474475383758545,
"step": 500
},
{
"epoch": 1.6426229508196721,
"grad_norm": 7.532558940104923,
"learning_rate": 5.066799800569247e-06,
"loss": 1.5207959413528442,
"step": 501
},
{
"epoch": 1.6459016393442623,
"grad_norm": 6.3818911891780195,
"learning_rate": 5.0477148385349985e-06,
"loss": 1.4381382465362549,
"step": 502
},
{
"epoch": 1.6491803278688524,
"grad_norm": 9.164865769377675,
"learning_rate": 5.028629181231526e-06,
"loss": 1.7102932929992676,
"step": 503
},
{
"epoch": 1.6524590163934425,
"grad_norm": 10.089200649938695,
"learning_rate": 5.0095431067624655e-06,
"loss": 1.3638228178024292,
"step": 504
},
{
"epoch": 1.6557377049180326,
"grad_norm": 9.28966329247032,
"learning_rate": 4.9904568932375344e-06,
"loss": 1.3798298835754395,
"step": 505
},
{
"epoch": 1.659016393442623,
"grad_norm": 7.574242480850614,
"learning_rate": 4.971370818768475e-06,
"loss": 1.4695639610290527,
"step": 506
},
{
"epoch": 1.662295081967213,
"grad_norm": 8.901720684229767,
"learning_rate": 4.952285161465003e-06,
"loss": 1.3713805675506592,
"step": 507
},
{
"epoch": 1.6655737704918034,
"grad_norm": 9.490445406232086,
"learning_rate": 4.933200199430754e-06,
"loss": 1.6947979927062988,
"step": 508
},
{
"epoch": 1.6688524590163936,
"grad_norm": 8.09980845418294,
"learning_rate": 4.914116210759237e-06,
"loss": 2.0679752826690674,
"step": 509
},
{
"epoch": 1.6721311475409837,
"grad_norm": 7.75123899004764,
"learning_rate": 4.8950334735297746e-06,
"loss": 1.7710498571395874,
"step": 510
},
{
"epoch": 1.6754098360655738,
"grad_norm": 8.246679834300911,
"learning_rate": 4.875952265803452e-06,
"loss": 1.4090079069137573,
"step": 511
},
{
"epoch": 1.678688524590164,
"grad_norm": 24.566367864116824,
"learning_rate": 4.856872865619074e-06,
"loss": 1.2892216444015503,
"step": 512
},
{
"epoch": 1.681967213114754,
"grad_norm": 9.154282919956307,
"learning_rate": 4.837795550989101e-06,
"loss": 1.6451359987258911,
"step": 513
},
{
"epoch": 1.6852459016393442,
"grad_norm": 10.472618479029203,
"learning_rate": 4.818720599895608e-06,
"loss": 1.6292381286621094,
"step": 514
},
{
"epoch": 1.6885245901639343,
"grad_norm": 7.052090572598493,
"learning_rate": 4.799648290286228e-06,
"loss": 1.4105167388916016,
"step": 515
},
{
"epoch": 1.6918032786885244,
"grad_norm": 9.991877315968562,
"learning_rate": 4.780578900070104e-06,
"loss": 1.5266077518463135,
"step": 516
},
{
"epoch": 1.6950819672131148,
"grad_norm": 7.192264305713691,
"learning_rate": 4.76151270711384e-06,
"loss": 1.401094913482666,
"step": 517
},
{
"epoch": 1.698360655737705,
"grad_norm": 8.346845526705799,
"learning_rate": 4.74244998923745e-06,
"loss": 1.3493717908859253,
"step": 518
},
{
"epoch": 1.7016393442622952,
"grad_norm": 6.629577551219913,
"learning_rate": 4.723391024210318e-06,
"loss": 1.8160909414291382,
"step": 519
},
{
"epoch": 1.7049180327868854,
"grad_norm": 11.487830630303534,
"learning_rate": 4.704336089747135e-06,
"loss": 1.4186710119247437,
"step": 520
},
{
"epoch": 1.7081967213114755,
"grad_norm": 6.750650905528032,
"learning_rate": 4.685285463503867e-06,
"loss": 1.6921336650848389,
"step": 521
},
{
"epoch": 1.7114754098360656,
"grad_norm": 8.75830088082367,
"learning_rate": 4.666239423073702e-06,
"loss": 1.0855233669281006,
"step": 522
},
{
"epoch": 1.7147540983606557,
"grad_norm": 12.783655428922271,
"learning_rate": 4.647198245983005e-06,
"loss": 1.4159142971038818,
"step": 523
},
{
"epoch": 1.7180327868852459,
"grad_norm": 11.855373216443706,
"learning_rate": 4.628162209687276e-06,
"loss": 1.6099746227264404,
"step": 524
},
{
"epoch": 1.721311475409836,
"grad_norm": 16.09290536501777,
"learning_rate": 4.609131591567111e-06,
"loss": 1.6052772998809814,
"step": 525
},
{
"epoch": 1.724590163934426,
"grad_norm": 9.249385137520209,
"learning_rate": 4.5901066689241514e-06,
"loss": 1.6209545135498047,
"step": 526
},
{
"epoch": 1.7278688524590164,
"grad_norm": 55.487694533164195,
"learning_rate": 4.571087718977047e-06,
"loss": 2.792712688446045,
"step": 527
},
{
"epoch": 1.7311475409836066,
"grad_norm": 7.426791606702041,
"learning_rate": 4.552075018857423e-06,
"loss": 1.5465900897979736,
"step": 528
},
{
"epoch": 1.7344262295081967,
"grad_norm": 9.15211592940861,
"learning_rate": 4.533068845605831e-06,
"loss": 1.601561188697815,
"step": 529
},
{
"epoch": 1.737704918032787,
"grad_norm": 8.177876480364937,
"learning_rate": 4.514069476167716e-06,
"loss": 1.5934646129608154,
"step": 530
},
{
"epoch": 1.7409836065573772,
"grad_norm": 74.16329164060816,
"learning_rate": 4.49507718738939e-06,
"loss": 2.185462713241577,
"step": 531
},
{
"epoch": 1.7442622950819673,
"grad_norm": 10.97624327347011,
"learning_rate": 4.4760922560139854e-06,
"loss": 1.2236711978912354,
"step": 532
},
{
"epoch": 1.7475409836065574,
"grad_norm": 9.806550239570528,
"learning_rate": 4.457114958677423e-06,
"loss": 1.389749526977539,
"step": 533
},
{
"epoch": 1.7508196721311475,
"grad_norm": 7.235080058556069,
"learning_rate": 4.438145571904396e-06,
"loss": 1.4698362350463867,
"step": 534
},
{
"epoch": 1.7540983606557377,
"grad_norm": 8.352056869428369,
"learning_rate": 4.41918437210432e-06,
"loss": 1.1259835958480835,
"step": 535
},
{
"epoch": 1.7573770491803278,
"grad_norm": 8.223586404616016,
"learning_rate": 4.400231635567319e-06,
"loss": 1.4079432487487793,
"step": 536
},
{
"epoch": 1.760655737704918,
"grad_norm": 9.696589268397148,
"learning_rate": 4.381287638460202e-06,
"loss": 1.5803723335266113,
"step": 537
},
{
"epoch": 1.7639344262295082,
"grad_norm": 8.631613071998114,
"learning_rate": 4.362352656822422e-06,
"loss": 1.783247470855713,
"step": 538
},
{
"epoch": 1.7672131147540984,
"grad_norm": 6.769387598626242,
"learning_rate": 4.3434269665620694e-06,
"loss": 1.3596124649047852,
"step": 539
},
{
"epoch": 1.7704918032786885,
"grad_norm": 12.700446025136257,
"learning_rate": 4.324510843451851e-06,
"loss": 1.2757470607757568,
"step": 540
},
{
"epoch": 1.7737704918032788,
"grad_norm": 10.97349445647978,
"learning_rate": 4.305604563125061e-06,
"loss": 1.4117778539657593,
"step": 541
},
{
"epoch": 1.777049180327869,
"grad_norm": 8.448231811716006,
"learning_rate": 4.286708401071574e-06,
"loss": 1.6345001459121704,
"step": 542
},
{
"epoch": 1.780327868852459,
"grad_norm": 5.977930323371188,
"learning_rate": 4.2678226326338246e-06,
"loss": 1.464469075202942,
"step": 543
},
{
"epoch": 1.7836065573770492,
"grad_norm": 10.488070983730596,
"learning_rate": 4.248947533002806e-06,
"loss": 0.8534256219863892,
"step": 544
},
{
"epoch": 1.7868852459016393,
"grad_norm": 12.073744191960243,
"learning_rate": 4.230083377214044e-06,
"loss": 1.5764466524124146,
"step": 545
},
{
"epoch": 1.7901639344262295,
"grad_norm": 10.116747302655472,
"learning_rate": 4.211230440143604e-06,
"loss": 1.5294190645217896,
"step": 546
},
{
"epoch": 1.7934426229508196,
"grad_norm": 6.947385827026429,
"learning_rate": 4.192388996504077e-06,
"loss": 1.4170427322387695,
"step": 547
},
{
"epoch": 1.7967213114754097,
"grad_norm": 8.673815099532291,
"learning_rate": 4.1735593208405785e-06,
"loss": 1.6583044528961182,
"step": 548
},
{
"epoch": 1.8,
"grad_norm": 7.8084373215499845,
"learning_rate": 4.154741687526749e-06,
"loss": 1.4119561910629272,
"step": 549
},
{
"epoch": 1.8032786885245902,
"grad_norm": 11.6505598659139,
"learning_rate": 4.135936370760759e-06,
"loss": 1.18519926071167,
"step": 550
},
{
"epoch": 1.8065573770491803,
"grad_norm": 7.206435414152386,
"learning_rate": 4.117143644561306e-06,
"loss": 1.283574104309082,
"step": 551
},
{
"epoch": 1.8098360655737706,
"grad_norm": 6.586238801855751,
"learning_rate": 4.09836378276363e-06,
"loss": 1.3717527389526367,
"step": 552
},
{
"epoch": 1.8131147540983608,
"grad_norm": 11.243675301529752,
"learning_rate": 4.079597059015518e-06,
"loss": 1.7565321922302246,
"step": 553
},
{
"epoch": 1.8163934426229509,
"grad_norm": 12.091978383833098,
"learning_rate": 4.060843746773315e-06,
"loss": 1.6233265399932861,
"step": 554
},
{
"epoch": 1.819672131147541,
"grad_norm": 11.53599375292441,
"learning_rate": 4.042104119297945e-06,
"loss": 1.6700351238250732,
"step": 555
},
{
"epoch": 1.8229508196721311,
"grad_norm": 11.681108367045207,
"learning_rate": 4.023378449650928e-06,
"loss": 1.7181103229522705,
"step": 556
},
{
"epoch": 1.8262295081967213,
"grad_norm": 9.081769748597901,
"learning_rate": 4.004667010690398e-06,
"loss": 1.4881409406661987,
"step": 557
},
{
"epoch": 1.8295081967213114,
"grad_norm": 10.069568358332267,
"learning_rate": 3.985970075067128e-06,
"loss": 1.3073152303695679,
"step": 558
},
{
"epoch": 1.8327868852459015,
"grad_norm": 6.18422898732813,
"learning_rate": 3.96728791522056e-06,
"loss": 1.7904932498931885,
"step": 559
},
{
"epoch": 1.8360655737704918,
"grad_norm": 18.088444221423824,
"learning_rate": 3.9486208033748315e-06,
"loss": 1.884446382522583,
"step": 560
},
{
"epoch": 1.839344262295082,
"grad_norm": 5.751334007919857,
"learning_rate": 3.929969011534811e-06,
"loss": 1.5616281032562256,
"step": 561
},
{
"epoch": 1.842622950819672,
"grad_norm": 7.8316844091562565,
"learning_rate": 3.91133281148213e-06,
"loss": 1.4229798316955566,
"step": 562
},
{
"epoch": 1.8459016393442624,
"grad_norm": 8.142206278555301,
"learning_rate": 3.892712474771237e-06,
"loss": 1.3973615169525146,
"step": 563
},
{
"epoch": 1.8491803278688526,
"grad_norm": 11.51994080215916,
"learning_rate": 3.874108272725421e-06,
"loss": 1.4394562244415283,
"step": 564
},
{
"epoch": 1.8524590163934427,
"grad_norm": 7.031408743840362,
"learning_rate": 3.855520476432871e-06,
"loss": 1.8910778760910034,
"step": 565
},
{
"epoch": 1.8557377049180328,
"grad_norm": 14.859145590342383,
"learning_rate": 3.83694935674272e-06,
"loss": 1.8477580547332764,
"step": 566
},
{
"epoch": 1.859016393442623,
"grad_norm": 8.615394904677078,
"learning_rate": 3.818395184261104e-06,
"loss": 1.6715424060821533,
"step": 567
},
{
"epoch": 1.862295081967213,
"grad_norm": 7.494768071817523,
"learning_rate": 3.7998582293472088e-06,
"loss": 1.2757171392440796,
"step": 568
},
{
"epoch": 1.8655737704918032,
"grad_norm": 7.594052894821273,
"learning_rate": 3.781338762109347e-06,
"loss": 1.2033525705337524,
"step": 569
},
{
"epoch": 1.8688524590163933,
"grad_norm": 7.547056826346777,
"learning_rate": 3.762837052401004e-06,
"loss": 1.6481246948242188,
"step": 570
},
{
"epoch": 1.8721311475409836,
"grad_norm": 7.436931179017303,
"learning_rate": 3.7443533698169186e-06,
"loss": 1.2988598346710205,
"step": 571
},
{
"epoch": 1.8754098360655738,
"grad_norm": 12.152906412174815,
"learning_rate": 3.725887983689148e-06,
"loss": 1.3220934867858887,
"step": 572
},
{
"epoch": 1.8786885245901639,
"grad_norm": 8.888061965475663,
"learning_rate": 3.7074411630831462e-06,
"loss": 1.3513283729553223,
"step": 573
},
{
"epoch": 1.8819672131147542,
"grad_norm": 6.297143314045074,
"learning_rate": 3.6890131767938402e-06,
"loss": 1.208467721939087,
"step": 574
},
{
"epoch": 1.8852459016393444,
"grad_norm": 8.324756033243434,
"learning_rate": 3.670604293341723e-06,
"loss": 1.4959217309951782,
"step": 575
},
{
"epoch": 1.8885245901639345,
"grad_norm": 6.671533588498681,
"learning_rate": 3.652214780968926e-06,
"loss": 1.284533143043518,
"step": 576
},
{
"epoch": 1.8918032786885246,
"grad_norm": 7.555092020319121,
"learning_rate": 3.633844907635321e-06,
"loss": 1.2508797645568848,
"step": 577
},
{
"epoch": 1.8950819672131147,
"grad_norm": 8.43412034405742,
"learning_rate": 3.6154949410146136e-06,
"loss": 1.2697298526763916,
"step": 578
},
{
"epoch": 1.8983606557377048,
"grad_norm": 9.003353875048909,
"learning_rate": 3.597165148490439e-06,
"loss": 1.382217288017273,
"step": 579
},
{
"epoch": 1.901639344262295,
"grad_norm": 9.27098796032901,
"learning_rate": 3.5788557971524695e-06,
"loss": 1.6072741746902466,
"step": 580
},
{
"epoch": 1.904918032786885,
"grad_norm": 5.5253341744418485,
"learning_rate": 3.5605671537925264e-06,
"loss": 1.3846685886383057,
"step": 581
},
{
"epoch": 1.9081967213114754,
"grad_norm": 10.22222113080044,
"learning_rate": 3.542299484900681e-06,
"loss": 1.73702871799469,
"step": 582
},
{
"epoch": 1.9114754098360656,
"grad_norm": 11.47077324018453,
"learning_rate": 3.524053056661385e-06,
"loss": 1.8521015644073486,
"step": 583
},
{
"epoch": 1.9147540983606557,
"grad_norm": 14.70885803418104,
"learning_rate": 3.5058281349495804e-06,
"loss": 1.679369330406189,
"step": 584
},
{
"epoch": 1.918032786885246,
"grad_norm": 9.79227306739351,
"learning_rate": 3.487624985326833e-06,
"loss": 1.4347236156463623,
"step": 585
},
{
"epoch": 1.9213114754098362,
"grad_norm": 7.895368432371944,
"learning_rate": 3.469443873037457e-06,
"loss": 1.6367138624191284,
"step": 586
},
{
"epoch": 1.9245901639344263,
"grad_norm": 9.86171941668043,
"learning_rate": 3.4512850630046545e-06,
"loss": 1.987825632095337,
"step": 587
},
{
"epoch": 1.9278688524590164,
"grad_norm": 10.69693870131734,
"learning_rate": 3.4331488198266575e-06,
"loss": 1.4333100318908691,
"step": 588
},
{
"epoch": 1.9311475409836065,
"grad_norm": 9.58303495289985,
"learning_rate": 3.415035407772865e-06,
"loss": 1.811872959136963,
"step": 589
},
{
"epoch": 1.9344262295081966,
"grad_norm": 9.991867112663671,
"learning_rate": 3.3969450907799966e-06,
"loss": 1.4560937881469727,
"step": 590
},
{
"epoch": 1.9377049180327868,
"grad_norm": 8.108964428953943,
"learning_rate": 3.3788781324482446e-06,
"loss": 1.4396641254425049,
"step": 591
},
{
"epoch": 1.940983606557377,
"grad_norm": 9.589154621854519,
"learning_rate": 3.3608347960374347e-06,
"loss": 1.809628963470459,
"step": 592
},
{
"epoch": 1.9442622950819672,
"grad_norm": 8.08333948546386,
"learning_rate": 3.34281534446319e-06,
"loss": 1.5539662837982178,
"step": 593
},
{
"epoch": 1.9475409836065574,
"grad_norm": 12.574619755000336,
"learning_rate": 3.3248200402931024e-06,
"loss": 1.2026546001434326,
"step": 594
},
{
"epoch": 1.9508196721311475,
"grad_norm": 16.902985823344192,
"learning_rate": 3.3068491457428984e-06,
"loss": 1.0881797075271606,
"step": 595
},
{
"epoch": 1.9540983606557378,
"grad_norm": 8.356842538208136,
"learning_rate": 3.2889029226726286e-06,
"loss": 1.695966362953186,
"step": 596
},
{
"epoch": 1.957377049180328,
"grad_norm": 8.41169408094449,
"learning_rate": 3.270981632582843e-06,
"loss": 1.4734704494476318,
"step": 597
},
{
"epoch": 1.960655737704918,
"grad_norm": 5.906317987561819,
"learning_rate": 3.253085536610786e-06,
"loss": 1.108353614807129,
"step": 598
},
{
"epoch": 1.9639344262295082,
"grad_norm": 8.465425955671048,
"learning_rate": 3.2352148955265893e-06,
"loss": 1.5087281465530396,
"step": 599
},
{
"epoch": 1.9672131147540983,
"grad_norm": 8.352824374400317,
"learning_rate": 3.217369969729476e-06,
"loss": 1.3761603832244873,
"step": 600
},
{
"epoch": 1.9704918032786884,
"grad_norm": 5.615486549740408,
"learning_rate": 3.1995510192439587e-06,
"loss": 0.8662180304527283,
"step": 601
},
{
"epoch": 1.9737704918032786,
"grad_norm": 8.217362775403338,
"learning_rate": 3.181758303716058e-06,
"loss": 1.1148695945739746,
"step": 602
},
{
"epoch": 1.9770491803278687,
"grad_norm": 26.703857759821094,
"learning_rate": 3.163992082409515e-06,
"loss": 1.6514984369277954,
"step": 603
},
{
"epoch": 1.980327868852459,
"grad_norm": 9.250896223229718,
"learning_rate": 3.1462526142020115e-06,
"loss": 1.6147348880767822,
"step": 604
},
{
"epoch": 1.9836065573770492,
"grad_norm": 17.31517028770501,
"learning_rate": 3.1285401575814043e-06,
"loss": 1.0211924314498901,
"step": 605
},
{
"epoch": 1.9868852459016395,
"grad_norm": 11.745081110726778,
"learning_rate": 3.1108549706419553e-06,
"loss": 1.4241924285888672,
"step": 606
},
{
"epoch": 1.9901639344262296,
"grad_norm": 11.388120688396235,
"learning_rate": 3.093197311080568e-06,
"loss": 1.7059409618377686,
"step": 607
},
{
"epoch": 1.9934426229508198,
"grad_norm": 10.203359159576197,
"learning_rate": 3.0755674361930387e-06,
"loss": 1.3052058219909668,
"step": 608
},
{
"epoch": 1.9967213114754099,
"grad_norm": 12.66929230024026,
"learning_rate": 3.0579656028703e-06,
"loss": 1.6413627862930298,
"step": 609
},
{
"epoch": 2.0,
"grad_norm": 9.901860094629342,
"learning_rate": 3.0403920675946826e-06,
"loss": 0.7727410793304443,
"step": 610
},
{
"epoch": 2.00327868852459,
"grad_norm": 6.80522504918782,
"learning_rate": 3.022847086436176e-06,
"loss": 0.5204824209213257,
"step": 611
},
{
"epoch": 2.0065573770491802,
"grad_norm": 10.370094518601123,
"learning_rate": 3.0053309150486996e-06,
"loss": 0.7960829138755798,
"step": 612
},
{
"epoch": 2.0098360655737704,
"grad_norm": 11.631077275085174,
"learning_rate": 2.9878438086663753e-06,
"loss": 0.6627193689346313,
"step": 613
},
{
"epoch": 2.0131147540983605,
"grad_norm": 8.269501072426324,
"learning_rate": 2.970386022099809e-06,
"loss": 0.8483942747116089,
"step": 614
},
{
"epoch": 2.0163934426229506,
"grad_norm": 11.433034909968399,
"learning_rate": 2.952957809732377e-06,
"loss": 1.0915180444717407,
"step": 615
},
{
"epoch": 2.019672131147541,
"grad_norm": 11.029984955450137,
"learning_rate": 2.9355594255165186e-06,
"loss": 0.7344239950180054,
"step": 616
},
{
"epoch": 2.0229508196721313,
"grad_norm": 6.538446171100794,
"learning_rate": 2.9181911229700383e-06,
"loss": 0.557336688041687,
"step": 617
},
{
"epoch": 2.0262295081967214,
"grad_norm": 10.390688726074252,
"learning_rate": 2.9008531551724094e-06,
"loss": 0.6669437885284424,
"step": 618
},
{
"epoch": 2.0295081967213116,
"grad_norm": 9.199661937117229,
"learning_rate": 2.8835457747610907e-06,
"loss": 0.6179019212722778,
"step": 619
},
{
"epoch": 2.0327868852459017,
"grad_norm": 7.615029287636688,
"learning_rate": 2.8662692339278387e-06,
"loss": 0.520706295967102,
"step": 620
},
{
"epoch": 2.036065573770492,
"grad_norm": 14.874804480624977,
"learning_rate": 2.8490237844150335e-06,
"loss": 0.6297595500946045,
"step": 621
},
{
"epoch": 2.039344262295082,
"grad_norm": 13.985425134800286,
"learning_rate": 2.8318096775120187e-06,
"loss": 0.8497211337089539,
"step": 622
},
{
"epoch": 2.042622950819672,
"grad_norm": 13.111853605082757,
"learning_rate": 2.814627164051429e-06,
"loss": 0.979051947593689,
"step": 623
},
{
"epoch": 2.045901639344262,
"grad_norm": 11.09422268561705,
"learning_rate": 2.79747649440554e-06,
"loss": 0.5062299966812134,
"step": 624
},
{
"epoch": 2.0491803278688523,
"grad_norm": 12.496707541331265,
"learning_rate": 2.780357918482627e-06,
"loss": 0.7015146017074585,
"step": 625
},
{
"epoch": 2.0524590163934424,
"grad_norm": 10.905413013212424,
"learning_rate": 2.763271685723311e-06,
"loss": 0.610783040523529,
"step": 626
},
{
"epoch": 2.055737704918033,
"grad_norm": 8.781941546714954,
"learning_rate": 2.7462180450969287e-06,
"loss": 0.5132089853286743,
"step": 627
},
{
"epoch": 2.059016393442623,
"grad_norm": 10.673103616850808,
"learning_rate": 2.7291972450979082e-06,
"loss": 0.777117133140564,
"step": 628
},
{
"epoch": 2.0622950819672132,
"grad_norm": 10.202783498286214,
"learning_rate": 2.712209533742147e-06,
"loss": 0.7694088220596313,
"step": 629
},
{
"epoch": 2.0655737704918034,
"grad_norm": 20.49043324223074,
"learning_rate": 2.6952551585633947e-06,
"loss": 1.1913038492202759,
"step": 630
},
{
"epoch": 2.0688524590163935,
"grad_norm": 7.644454615493383,
"learning_rate": 2.6783343666096445e-06,
"loss": 0.5829485654830933,
"step": 631
},
{
"epoch": 2.0721311475409836,
"grad_norm": 9.065091705244212,
"learning_rate": 2.6614474044395454e-06,
"loss": 0.41709184646606445,
"step": 632
},
{
"epoch": 2.0754098360655737,
"grad_norm": 8.021391962895821,
"learning_rate": 2.644594518118795e-06,
"loss": 0.5522010326385498,
"step": 633
},
{
"epoch": 2.078688524590164,
"grad_norm": 8.33270176581632,
"learning_rate": 2.6277759532165596e-06,
"loss": 0.5892815589904785,
"step": 634
},
{
"epoch": 2.081967213114754,
"grad_norm": 11.181774266781076,
"learning_rate": 2.6109919548019004e-06,
"loss": 0.6555030345916748,
"step": 635
},
{
"epoch": 2.085245901639344,
"grad_norm": 6.1243937926273135,
"learning_rate": 2.5942427674401936e-06,
"loss": 0.6386077404022217,
"step": 636
},
{
"epoch": 2.088524590163934,
"grad_norm": 11.051666301631604,
"learning_rate": 2.5775286351895745e-06,
"loss": 0.5038043856620789,
"step": 637
},
{
"epoch": 2.091803278688525,
"grad_norm": 8.95985517236454,
"learning_rate": 2.5608498015973817e-06,
"loss": 0.5079100131988525,
"step": 638
},
{
"epoch": 2.095081967213115,
"grad_norm": 7.70565789530436,
"learning_rate": 2.5442065096965986e-06,
"loss": 0.6524150371551514,
"step": 639
},
{
"epoch": 2.098360655737705,
"grad_norm": 7.298451254709435,
"learning_rate": 2.52759900200232e-06,
"loss": 0.6000703573226929,
"step": 640
},
{
"epoch": 2.101639344262295,
"grad_norm": 9.184883410922703,
"learning_rate": 2.5110275205082224e-06,
"loss": 0.4635947346687317,
"step": 641
},
{
"epoch": 2.1049180327868853,
"grad_norm": 12.306589964555906,
"learning_rate": 2.4944923066830248e-06,
"loss": 0.4841459393501282,
"step": 642
},
{
"epoch": 2.1081967213114754,
"grad_norm": 12.120814433124611,
"learning_rate": 2.4779936014669792e-06,
"loss": 0.9178411364555359,
"step": 643
},
{
"epoch": 2.1114754098360655,
"grad_norm": 6.975255854992642,
"learning_rate": 2.461531645268364e-06,
"loss": 0.5847235918045044,
"step": 644
},
{
"epoch": 2.1147540983606556,
"grad_norm": 9.733219268130398,
"learning_rate": 2.445106677959969e-06,
"loss": 0.4724552631378174,
"step": 645
},
{
"epoch": 2.1180327868852458,
"grad_norm": 63.124414385253765,
"learning_rate": 2.428718938875607e-06,
"loss": 1.7704694271087646,
"step": 646
},
{
"epoch": 2.121311475409836,
"grad_norm": 9.755450303526732,
"learning_rate": 2.4123686668066282e-06,
"loss": 0.9343034625053406,
"step": 647
},
{
"epoch": 2.1245901639344265,
"grad_norm": 10.195056393393118,
"learning_rate": 2.396056099998435e-06,
"loss": 0.8475706577301025,
"step": 648
},
{
"epoch": 2.1278688524590166,
"grad_norm": 8.567217632834149,
"learning_rate": 2.3797814761470146e-06,
"loss": 0.6202654838562012,
"step": 649
},
{
"epoch": 2.1311475409836067,
"grad_norm": 11.00797895411823,
"learning_rate": 2.3635450323954773e-06,
"loss": 0.898897111415863,
"step": 650
},
{
"epoch": 2.134426229508197,
"grad_norm": 13.34250594487987,
"learning_rate": 2.3473470053305954e-06,
"loss": 0.7017407417297363,
"step": 651
},
{
"epoch": 2.137704918032787,
"grad_norm": 8.059320484016075,
"learning_rate": 2.331187630979355e-06,
"loss": 0.7722477912902832,
"step": 652
},
{
"epoch": 2.140983606557377,
"grad_norm": 9.114403557028968,
"learning_rate": 2.31506714480553e-06,
"loss": 0.7707144021987915,
"step": 653
},
{
"epoch": 2.144262295081967,
"grad_norm": 10.259054525344466,
"learning_rate": 2.2989857817062327e-06,
"loss": 0.743545413017273,
"step": 654
},
{
"epoch": 2.1475409836065573,
"grad_norm": 8.85035133631966,
"learning_rate": 2.2829437760085023e-06,
"loss": 0.883000910282135,
"step": 655
},
{
"epoch": 2.1508196721311474,
"grad_norm": 11.51414308889685,
"learning_rate": 2.266941361465886e-06,
"loss": 0.8990451097488403,
"step": 656
},
{
"epoch": 2.1540983606557376,
"grad_norm": 9.33157197460147,
"learning_rate": 2.2509787712550424e-06,
"loss": 0.6484037637710571,
"step": 657
},
{
"epoch": 2.1573770491803277,
"grad_norm": 9.966960196418873,
"learning_rate": 2.235056237972326e-06,
"loss": 0.5184581875801086,
"step": 658
},
{
"epoch": 2.160655737704918,
"grad_norm": 12.062273294093876,
"learning_rate": 2.2191739936304147e-06,
"loss": 0.5672429800033569,
"step": 659
},
{
"epoch": 2.1639344262295084,
"grad_norm": 11.578066861830251,
"learning_rate": 2.2033322696549197e-06,
"loss": 0.426275372505188,
"step": 660
},
{
"epoch": 2.1672131147540985,
"grad_norm": 7.799563330500566,
"learning_rate": 2.187531296881017e-06,
"loss": 0.5644603371620178,
"step": 661
},
{
"epoch": 2.1704918032786886,
"grad_norm": 12.692062832535653,
"learning_rate": 2.1717713055500807e-06,
"loss": 0.7381806373596191,
"step": 662
},
{
"epoch": 2.1737704918032787,
"grad_norm": 10.328717808626742,
"learning_rate": 2.156052525306336e-06,
"loss": 1.1425390243530273,
"step": 663
},
{
"epoch": 2.177049180327869,
"grad_norm": 10.328663124547331,
"learning_rate": 2.140375185193502e-06,
"loss": 0.5078897476196289,
"step": 664
},
{
"epoch": 2.180327868852459,
"grad_norm": 11.760695188291958,
"learning_rate": 2.1247395136514592e-06,
"loss": 0.6729401350021362,
"step": 665
},
{
"epoch": 2.183606557377049,
"grad_norm": 11.553087048317673,
"learning_rate": 2.1091457385129267e-06,
"loss": 0.40105968713760376,
"step": 666
},
{
"epoch": 2.1868852459016392,
"grad_norm": 7.385212696869419,
"learning_rate": 2.093594087000131e-06,
"loss": 0.7621872425079346,
"step": 667
},
{
"epoch": 2.1901639344262294,
"grad_norm": 8.170651600457456,
"learning_rate": 2.078084785721501e-06,
"loss": 0.6865527629852295,
"step": 668
},
{
"epoch": 2.1934426229508195,
"grad_norm": 9.966802021569556,
"learning_rate": 2.0626180606683715e-06,
"loss": 0.5401767492294312,
"step": 669
},
{
"epoch": 2.19672131147541,
"grad_norm": 7.692541035567487,
"learning_rate": 2.0471941372116793e-06,
"loss": 0.8780995011329651,
"step": 670
},
{
"epoch": 2.2,
"grad_norm": 7.06726992148381,
"learning_rate": 2.031813240098686e-06,
"loss": 0.8158024549484253,
"step": 671
},
{
"epoch": 2.2032786885245903,
"grad_norm": 13.10476850738305,
"learning_rate": 2.016475593449702e-06,
"loss": 0.6709092855453491,
"step": 672
},
{
"epoch": 2.2065573770491804,
"grad_norm": 10.115353928008695,
"learning_rate": 2.001181420754819e-06,
"loss": 0.5526499152183533,
"step": 673
},
{
"epoch": 2.2098360655737705,
"grad_norm": 7.1356315930848675,
"learning_rate": 1.985930944870657e-06,
"loss": 0.5387853384017944,
"step": 674
},
{
"epoch": 2.2131147540983607,
"grad_norm": 10.24212597241438,
"learning_rate": 1.9707243880171117e-06,
"loss": 0.5927190184593201,
"step": 675
},
{
"epoch": 2.216393442622951,
"grad_norm": 13.544315136826267,
"learning_rate": 1.9555619717741248e-06,
"loss": 0.8063439726829529,
"step": 676
},
{
"epoch": 2.219672131147541,
"grad_norm": 7.7043095829823764,
"learning_rate": 1.9404439170784438e-06,
"loss": 0.8656831979751587,
"step": 677
},
{
"epoch": 2.222950819672131,
"grad_norm": 8.221101482965668,
"learning_rate": 1.925370444220415e-06,
"loss": 0.5712820291519165,
"step": 678
},
{
"epoch": 2.226229508196721,
"grad_norm": 8.461774526575825,
"learning_rate": 1.910341772840764e-06,
"loss": 0.5832774639129639,
"step": 679
},
{
"epoch": 2.2295081967213113,
"grad_norm": 12.262436150282866,
"learning_rate": 1.8953581219273987e-06,
"loss": 0.819401741027832,
"step": 680
},
{
"epoch": 2.2327868852459014,
"grad_norm": 10.381156704851467,
"learning_rate": 1.8804197098122168e-06,
"loss": 0.6590138673782349,
"step": 681
},
{
"epoch": 2.236065573770492,
"grad_norm": 8.175338805924074,
"learning_rate": 1.8655267541679317e-06,
"loss": 0.6401422619819641,
"step": 682
},
{
"epoch": 2.239344262295082,
"grad_norm": 9.489907336274296,
"learning_rate": 1.8506794720048903e-06,
"loss": 0.4747089445590973,
"step": 683
},
{
"epoch": 2.2426229508196722,
"grad_norm": 9.836175039066868,
"learning_rate": 1.835878079667917e-06,
"loss": 0.6246740221977234,
"step": 684
},
{
"epoch": 2.2459016393442623,
"grad_norm": 9.63657985434297,
"learning_rate": 1.8211227928331593e-06,
"loss": 0.6933366656303406,
"step": 685
},
{
"epoch": 2.2491803278688525,
"grad_norm": 10.780295041100512,
"learning_rate": 1.8064138265049457e-06,
"loss": 0.5234163403511047,
"step": 686
},
{
"epoch": 2.2524590163934426,
"grad_norm": 7.528495114867664,
"learning_rate": 1.791751395012652e-06,
"loss": 0.5458259582519531,
"step": 687
},
{
"epoch": 2.2557377049180327,
"grad_norm": 10.233022990604935,
"learning_rate": 1.7771357120075833e-06,
"loss": 0.7600114941596985,
"step": 688
},
{
"epoch": 2.259016393442623,
"grad_norm": 7.003428652762557,
"learning_rate": 1.7625669904598518e-06,
"loss": 0.6699049472808838,
"step": 689
},
{
"epoch": 2.262295081967213,
"grad_norm": 8.533036929885279,
"learning_rate": 1.7480454426552773e-06,
"loss": 0.30874204635620117,
"step": 690
},
{
"epoch": 2.265573770491803,
"grad_norm": 8.307348267058222,
"learning_rate": 1.7335712801923015e-06,
"loss": 0.6455368399620056,
"step": 691
},
{
"epoch": 2.2688524590163937,
"grad_norm": 8.87257195216342,
"learning_rate": 1.7191447139788925e-06,
"loss": 0.5174970030784607,
"step": 692
},
{
"epoch": 2.2721311475409838,
"grad_norm": 11.099583735402225,
"learning_rate": 1.704765954229476e-06,
"loss": 0.8222718238830566,
"step": 693
},
{
"epoch": 2.275409836065574,
"grad_norm": 12.205907598307611,
"learning_rate": 1.6904352104618792e-06,
"loss": 0.5776864290237427,
"step": 694
},
{
"epoch": 2.278688524590164,
"grad_norm": 11.139054961537802,
"learning_rate": 1.6761526914942682e-06,
"loss": 0.9057301878929138,
"step": 695
},
{
"epoch": 2.281967213114754,
"grad_norm": 8.630583590372039,
"learning_rate": 1.6619186054421088e-06,
"loss": 0.7172201871871948,
"step": 696
},
{
"epoch": 2.2852459016393443,
"grad_norm": 8.4758541473458,
"learning_rate": 1.6477331597151358e-06,
"loss": 0.31603288650512695,
"step": 697
},
{
"epoch": 2.2885245901639344,
"grad_norm": 10.045963692358674,
"learning_rate": 1.6335965610143274e-06,
"loss": 0.8781267404556274,
"step": 698
},
{
"epoch": 2.2918032786885245,
"grad_norm": 10.152642496499004,
"learning_rate": 1.6195090153288966e-06,
"loss": 0.9591543078422546,
"step": 699
},
{
"epoch": 2.2950819672131146,
"grad_norm": 8.402047010935645,
"learning_rate": 1.6054707279332865e-06,
"loss": 0.6470961570739746,
"step": 700
},
{
"epoch": 2.2983606557377048,
"grad_norm": 8.029043754391878,
"learning_rate": 1.5914819033841843e-06,
"loss": 0.390561580657959,
"step": 701
},
{
"epoch": 2.301639344262295,
"grad_norm": 11.728947987690505,
"learning_rate": 1.577542745517533e-06,
"loss": 0.41876158118247986,
"step": 702
},
{
"epoch": 2.304918032786885,
"grad_norm": 12.487271261788218,
"learning_rate": 1.5636534574455685e-06,
"loss": 0.5718614459037781,
"step": 703
},
{
"epoch": 2.3081967213114756,
"grad_norm": 8.530606852831838,
"learning_rate": 1.5498142415538558e-06,
"loss": 0.5597206354141235,
"step": 704
},
{
"epoch": 2.3114754098360657,
"grad_norm": 7.30654157846341,
"learning_rate": 1.5360252994983404e-06,
"loss": 0.6952862739562988,
"step": 705
},
{
"epoch": 2.314754098360656,
"grad_norm": 12.716366766516995,
"learning_rate": 1.5222868322024092e-06,
"loss": 0.6790463924407959,
"step": 706
},
{
"epoch": 2.318032786885246,
"grad_norm": 8.298754960677092,
"learning_rate": 1.5085990398539685e-06,
"loss": 0.40630030632019043,
"step": 707
},
{
"epoch": 2.321311475409836,
"grad_norm": 11.061103699867397,
"learning_rate": 1.4949621219025195e-06,
"loss": 0.5404191613197327,
"step": 708
},
{
"epoch": 2.324590163934426,
"grad_norm": 9.194041350216061,
"learning_rate": 1.481376277056255e-06,
"loss": 0.7214863896369934,
"step": 709
},
{
"epoch": 2.3278688524590163,
"grad_norm": 10.513164873740623,
"learning_rate": 1.4678417032791653e-06,
"loss": 0.5778199434280396,
"step": 710
},
{
"epoch": 2.3311475409836064,
"grad_norm": 10.38932118339124,
"learning_rate": 1.4543585977881513e-06,
"loss": 0.3441578447818756,
"step": 711
},
{
"epoch": 2.3344262295081966,
"grad_norm": 8.829864894944937,
"learning_rate": 1.4409271570501522e-06,
"loss": 0.3943712115287781,
"step": 712
},
{
"epoch": 2.337704918032787,
"grad_norm": 9.713700776767412,
"learning_rate": 1.4275475767792846e-06,
"loss": 1.0443286895751953,
"step": 713
},
{
"epoch": 2.3409836065573773,
"grad_norm": 10.887915798399776,
"learning_rate": 1.4142200519339844e-06,
"loss": 0.6791509389877319,
"step": 714
},
{
"epoch": 2.3442622950819674,
"grad_norm": 15.166319282939247,
"learning_rate": 1.4009447767141748e-06,
"loss": 0.576408863067627,
"step": 715
},
{
"epoch": 2.3475409836065575,
"grad_norm": 10.490720645593324,
"learning_rate": 1.3877219445584283e-06,
"loss": 0.6661597490310669,
"step": 716
},
{
"epoch": 2.3508196721311476,
"grad_norm": 16.842580120876438,
"learning_rate": 1.374551748141153e-06,
"loss": 0.6657031774520874,
"step": 717
},
{
"epoch": 2.3540983606557377,
"grad_norm": 8.450377996205953,
"learning_rate": 1.3614343793697831e-06,
"loss": 0.446186900138855,
"step": 718
},
{
"epoch": 2.357377049180328,
"grad_norm": 9.066748448453154,
"learning_rate": 1.3483700293819819e-06,
"loss": 0.651573657989502,
"step": 719
},
{
"epoch": 2.360655737704918,
"grad_norm": 7.966917702107941,
"learning_rate": 1.335358888542862e-06,
"loss": 0.5286246538162231,
"step": 720
},
{
"epoch": 2.363934426229508,
"grad_norm": 12.158588190010066,
"learning_rate": 1.3224011464422032e-06,
"loss": 0.5317904949188232,
"step": 721
},
{
"epoch": 2.3672131147540982,
"grad_norm": 12.593517655534825,
"learning_rate": 1.3094969918916967e-06,
"loss": 0.7954739332199097,
"step": 722
},
{
"epoch": 2.3704918032786884,
"grad_norm": 17.533385513483815,
"learning_rate": 1.2966466129221884e-06,
"loss": 1.2486153841018677,
"step": 723
},
{
"epoch": 2.3737704918032785,
"grad_norm": 10.864571046821904,
"learning_rate": 1.2838501967809441e-06,
"loss": 0.6230376362800598,
"step": 724
},
{
"epoch": 2.3770491803278686,
"grad_norm": 12.188863850756452,
"learning_rate": 1.271107929928917e-06,
"loss": 0.44286614656448364,
"step": 725
},
{
"epoch": 2.380327868852459,
"grad_norm": 8.72028998175659,
"learning_rate": 1.2584199980380358e-06,
"loss": 0.5746725797653198,
"step": 726
},
{
"epoch": 2.3836065573770493,
"grad_norm": 7.8720208021252445,
"learning_rate": 1.245786585988491e-06,
"loss": 0.4517443776130676,
"step": 727
},
{
"epoch": 2.3868852459016394,
"grad_norm": 10.205696041068311,
"learning_rate": 1.2332078778660516e-06,
"loss": 0.6351556777954102,
"step": 728
},
{
"epoch": 2.3901639344262295,
"grad_norm": 13.683034808215892,
"learning_rate": 1.2206840569593726e-06,
"loss": 1.1598081588745117,
"step": 729
},
{
"epoch": 2.3934426229508197,
"grad_norm": 9.488511387047744,
"learning_rate": 1.20821530575733e-06,
"loss": 0.35358521342277527,
"step": 730
},
{
"epoch": 2.39672131147541,
"grad_norm": 13.620783929275827,
"learning_rate": 1.1958018059463577e-06,
"loss": 0.5249242186546326,
"step": 731
},
{
"epoch": 2.4,
"grad_norm": 10.152861508734686,
"learning_rate": 1.1834437384078095e-06,
"loss": 0.7835702896118164,
"step": 732
},
{
"epoch": 2.40327868852459,
"grad_norm": 10.88129657997722,
"learning_rate": 1.17114128321531e-06,
"loss": 0.5754145383834839,
"step": 733
},
{
"epoch": 2.40655737704918,
"grad_norm": 8.675946801194728,
"learning_rate": 1.1588946196321404e-06,
"loss": 0.6827773451805115,
"step": 734
},
{
"epoch": 2.4098360655737707,
"grad_norm": 8.990521692307496,
"learning_rate": 1.146703926108622e-06,
"loss": 0.5709261894226074,
"step": 735
},
{
"epoch": 2.413114754098361,
"grad_norm": 8.612314148456155,
"learning_rate": 1.1345693802795177e-06,
"loss": 0.6407266855239868,
"step": 736
},
{
"epoch": 2.416393442622951,
"grad_norm": 9.810861911468454,
"learning_rate": 1.1224911589614423e-06,
"loss": 0.577508807182312,
"step": 737
},
{
"epoch": 2.419672131147541,
"grad_norm": 10.21022852976877,
"learning_rate": 1.11046943815029e-06,
"loss": 0.633446455001831,
"step": 738
},
{
"epoch": 2.422950819672131,
"grad_norm": 10.433822312317895,
"learning_rate": 1.0985043930186624e-06,
"loss": 0.7005766034126282,
"step": 739
},
{
"epoch": 2.4262295081967213,
"grad_norm": 8.374240128659636,
"learning_rate": 1.0865961979133245e-06,
"loss": 0.8112733364105225,
"step": 740
},
{
"epoch": 2.4295081967213115,
"grad_norm": 9.62795967906854,
"learning_rate": 1.0747450263526576e-06,
"loss": 0.37373289465904236,
"step": 741
},
{
"epoch": 2.4327868852459016,
"grad_norm": 13.753819659963641,
"learning_rate": 1.0629510510241337e-06,
"loss": 0.8246908187866211,
"step": 742
},
{
"epoch": 2.4360655737704917,
"grad_norm": 7.72190068820331,
"learning_rate": 1.0512144437817995e-06,
"loss": 0.356155663728714,
"step": 743
},
{
"epoch": 2.439344262295082,
"grad_norm": 11.709296853156587,
"learning_rate": 1.0395353756437699e-06,
"loss": 0.5895639657974243,
"step": 744
},
{
"epoch": 2.442622950819672,
"grad_norm": 9.206168440632947,
"learning_rate": 1.0279140167897428e-06,
"loss": 0.7546871900558472,
"step": 745
},
{
"epoch": 2.445901639344262,
"grad_norm": 8.050461363390497,
"learning_rate": 1.0163505365585086e-06,
"loss": 0.8311668634414673,
"step": 746
},
{
"epoch": 2.4491803278688526,
"grad_norm": 8.643106973190003,
"learning_rate": 1.004845103445492e-06,
"loss": 0.5180816054344177,
"step": 747
},
{
"epoch": 2.4524590163934428,
"grad_norm": 14.400475668772438,
"learning_rate": 9.933978851002912e-07,
"loss": 0.7587926387786865,
"step": 748
},
{
"epoch": 2.455737704918033,
"grad_norm": 8.67852546917449,
"learning_rate": 9.820090483242394e-07,
"loss": 0.6491926908493042,
"step": 749
},
{
"epoch": 2.459016393442623,
"grad_norm": 9.17651190753313,
"learning_rate": 9.706787590679685e-07,
"loss": 0.6185643672943115,
"step": 750
},
{
"epoch": 2.462295081967213,
"grad_norm": 7.405114789282885,
"learning_rate": 9.594071824289986e-07,
"loss": 0.564989447593689,
"step": 751
},
{
"epoch": 2.4655737704918033,
"grad_norm": 9.972905853881517,
"learning_rate": 9.481944826493266e-07,
"loss": 0.6626894474029541,
"step": 752
},
{
"epoch": 2.4688524590163934,
"grad_norm": 7.094573408783286,
"learning_rate": 9.370408231130346e-07,
"loss": 0.7726181745529175,
"step": 753
},
{
"epoch": 2.4721311475409835,
"grad_norm": 11.077713933639133,
"learning_rate": 9.259463663439072e-07,
"loss": 0.7983223795890808,
"step": 754
},
{
"epoch": 2.4754098360655736,
"grad_norm": 9.884726507627212,
"learning_rate": 9.149112740030675e-07,
"loss": 1.0112802982330322,
"step": 755
},
{
"epoch": 2.4786885245901638,
"grad_norm": 9.905643131452015,
"learning_rate": 9.039357068866178e-07,
"loss": 0.71968013048172,
"step": 756
},
{
"epoch": 2.4819672131147543,
"grad_norm": 14.849954217948104,
"learning_rate": 8.930198249233002e-07,
"loss": 0.5837727785110474,
"step": 757
},
{
"epoch": 2.4852459016393444,
"grad_norm": 9.0944822899666,
"learning_rate": 8.821637871721622e-07,
"loss": 0.5900105237960815,
"step": 758
},
{
"epoch": 2.4885245901639346,
"grad_norm": 7.990941095589427,
"learning_rate": 8.713677518202412e-07,
"loss": 0.5894654989242554,
"step": 759
},
{
"epoch": 2.4918032786885247,
"grad_norm": 8.908684981251513,
"learning_rate": 8.606318761802584e-07,
"loss": 0.6155968904495239,
"step": 760
},
{
"epoch": 2.495081967213115,
"grad_norm": 8.970711386254106,
"learning_rate": 8.49956316688329e-07,
"loss": 0.4901209771633148,
"step": 761
},
{
"epoch": 2.498360655737705,
"grad_norm": 8.359378324244565,
"learning_rate": 8.393412289016778e-07,
"loss": 0.9492852687835693,
"step": 762
},
{
"epoch": 2.501639344262295,
"grad_norm": 9.093256052787806,
"learning_rate": 8.287867674963807e-07,
"loss": 0.8427372574806213,
"step": 763
},
{
"epoch": 2.504918032786885,
"grad_norm": 10.255826071241534,
"learning_rate": 8.182930862651012e-07,
"loss": 0.8181349039077759,
"step": 764
},
{
"epoch": 2.5081967213114753,
"grad_norm": 8.812866421103134,
"learning_rate": 8.078603381148575e-07,
"loss": 0.6845513582229614,
"step": 765
},
{
"epoch": 2.5114754098360654,
"grad_norm": 10.148883137978496,
"learning_rate": 7.974886750647887e-07,
"loss": 0.62053382396698,
"step": 766
},
{
"epoch": 2.5147540983606556,
"grad_norm": 12.940359607584073,
"learning_rate": 7.871782482439433e-07,
"loss": 0.6365728378295898,
"step": 767
},
{
"epoch": 2.5180327868852457,
"grad_norm": 8.122511797596042,
"learning_rate": 7.769292078890745e-07,
"loss": 0.4968264102935791,
"step": 768
},
{
"epoch": 2.521311475409836,
"grad_norm": 13.79917919525515,
"learning_rate": 7.667417033424529e-07,
"loss": 1.1382057666778564,
"step": 769
},
{
"epoch": 2.5245901639344264,
"grad_norm": 10.122757583662537,
"learning_rate": 7.566158830496917e-07,
"loss": 0.6581559777259827,
"step": 770
},
{
"epoch": 2.5278688524590165,
"grad_norm": 7.816258634706478,
"learning_rate": 7.465518945575789e-07,
"loss": 0.43607428669929504,
"step": 771
},
{
"epoch": 2.5311475409836066,
"grad_norm": 10.297048441436818,
"learning_rate": 7.365498845119317e-07,
"loss": 0.6695338487625122,
"step": 772
},
{
"epoch": 2.5344262295081967,
"grad_norm": 8.244938512310734,
"learning_rate": 7.266099986554576e-07,
"loss": 0.595778226852417,
"step": 773
},
{
"epoch": 2.537704918032787,
"grad_norm": 11.687587004973341,
"learning_rate": 7.167323818256305e-07,
"loss": 0.5753973722457886,
"step": 774
},
{
"epoch": 2.540983606557377,
"grad_norm": 8.284695869426658,
"learning_rate": 7.069171779525846e-07,
"loss": 0.5516860485076904,
"step": 775
},
{
"epoch": 2.544262295081967,
"grad_norm": 12.565729777623124,
"learning_rate": 6.971645300570084e-07,
"loss": 1.1838195323944092,
"step": 776
},
{
"epoch": 2.5475409836065572,
"grad_norm": 13.429622305460638,
"learning_rate": 6.874745802480715e-07,
"loss": 0.4558683931827545,
"step": 777
},
{
"epoch": 2.550819672131148,
"grad_norm": 14.212286309934173,
"learning_rate": 6.778474697213427e-07,
"loss": 0.9987090826034546,
"step": 778
},
{
"epoch": 2.554098360655738,
"grad_norm": 7.8958963121132815,
"learning_rate": 6.682833387567422e-07,
"loss": 0.7573103904724121,
"step": 779
},
{
"epoch": 2.557377049180328,
"grad_norm": 7.383146372881519,
"learning_rate": 6.587823267164911e-07,
"loss": 0.517373263835907,
"step": 780
},
{
"epoch": 2.560655737704918,
"grad_norm": 11.652813079038612,
"learning_rate": 6.49344572043083e-07,
"loss": 0.6053184270858765,
"step": 781
},
{
"epoch": 2.5639344262295083,
"grad_norm": 14.01748420884827,
"learning_rate": 6.399702122572698e-07,
"loss": 0.6553714275360107,
"step": 782
},
{
"epoch": 2.5672131147540984,
"grad_norm": 12.627499359642803,
"learning_rate": 6.306593839560521e-07,
"loss": 1.0168967247009277,
"step": 783
},
{
"epoch": 2.5704918032786885,
"grad_norm": 14.045539369184889,
"learning_rate": 6.214122228106917e-07,
"loss": 0.9201576709747314,
"step": 784
},
{
"epoch": 2.5737704918032787,
"grad_norm": 29.59616670098063,
"learning_rate": 6.122288635647355e-07,
"loss": 0.8917211890220642,
"step": 785
},
{
"epoch": 2.577049180327869,
"grad_norm": 12.522181650549864,
"learning_rate": 6.031094400320498e-07,
"loss": 0.4954626262187958,
"step": 786
},
{
"epoch": 2.580327868852459,
"grad_norm": 11.901743267361088,
"learning_rate": 5.940540850948723e-07,
"loss": 0.7444179654121399,
"step": 787
},
{
"epoch": 2.583606557377049,
"grad_norm": 9.144057514766333,
"learning_rate": 5.850629307018768e-07,
"loss": 0.5142679810523987,
"step": 788
},
{
"epoch": 2.586885245901639,
"grad_norm": 14.007018710528909,
"learning_rate": 5.761361078662464e-07,
"loss": 0.3713076114654541,
"step": 789
},
{
"epoch": 2.5901639344262293,
"grad_norm": 9.35544797735101,
"learning_rate": 5.672737466637701e-07,
"loss": 0.6729528903961182,
"step": 790
},
{
"epoch": 2.5934426229508194,
"grad_norm": 12.9010466913571,
"learning_rate": 5.584759762309422e-07,
"loss": 0.5998413562774658,
"step": 791
},
{
"epoch": 2.59672131147541,
"grad_norm": 8.789323608491406,
"learning_rate": 5.497429247630825e-07,
"loss": 0.6380819082260132,
"step": 792
},
{
"epoch": 2.6,
"grad_norm": 9.178527788685045,
"learning_rate": 5.410747195124705e-07,
"loss": 0.5965032577514648,
"step": 793
},
{
"epoch": 2.60327868852459,
"grad_norm": 8.748138258537878,
"learning_rate": 5.324714867864861e-07,
"loss": 0.530613899230957,
"step": 794
},
{
"epoch": 2.6065573770491803,
"grad_norm": 13.13669915079173,
"learning_rate": 5.239333519457779e-07,
"loss": 0.7559823989868164,
"step": 795
},
{
"epoch": 2.6098360655737705,
"grad_norm": 9.102444180885925,
"learning_rate": 5.154604394024254e-07,
"loss": 0.3219029903411865,
"step": 796
},
{
"epoch": 2.6131147540983606,
"grad_norm": 11.17181461481391,
"learning_rate": 5.070528726181345e-07,
"loss": 0.7130431532859802,
"step": 797
},
{
"epoch": 2.6163934426229507,
"grad_norm": 12.394950008370559,
"learning_rate": 4.98710774102435e-07,
"loss": 0.7524692416191101,
"step": 798
},
{
"epoch": 2.619672131147541,
"grad_norm": 10.267399593456043,
"learning_rate": 4.904342654108957e-07,
"loss": 0.49988648295402527,
"step": 799
},
{
"epoch": 2.6229508196721314,
"grad_norm": 13.65861670782972,
"learning_rate": 4.822234671433552e-07,
"loss": 0.82187819480896,
"step": 800
},
{
"epoch": 2.6262295081967215,
"grad_norm": 9.100489214671041,
"learning_rate": 4.7407849894216097e-07,
"loss": 0.6017215251922607,
"step": 801
},
{
"epoch": 2.6295081967213116,
"grad_norm": 8.281691235042029,
"learning_rate": 4.65999479490431e-07,
"loss": 0.5520101189613342,
"step": 802
},
{
"epoch": 2.6327868852459018,
"grad_norm": 8.22441534867937,
"learning_rate": 4.579865265103184e-07,
"loss": 0.5308873653411865,
"step": 803
},
{
"epoch": 2.636065573770492,
"grad_norm": 8.949030474805165,
"learning_rate": 4.500397567613002e-07,
"loss": 0.7142630815505981,
"step": 804
},
{
"epoch": 2.639344262295082,
"grad_norm": 9.435174739342594,
"learning_rate": 4.4215928603847604e-07,
"loss": 0.39907175302505493,
"step": 805
},
{
"epoch": 2.642622950819672,
"grad_norm": 8.377391490056,
"learning_rate": 4.343452291708783e-07,
"loss": 0.6312208771705627,
"step": 806
},
{
"epoch": 2.6459016393442623,
"grad_norm": 7.545619479707925,
"learning_rate": 4.265977000197996e-07,
"loss": 0.5526963472366333,
"step": 807
},
{
"epoch": 2.6491803278688524,
"grad_norm": 10.18998282908331,
"learning_rate": 4.1891681147713913e-07,
"loss": 0.8185096979141235,
"step": 808
},
{
"epoch": 2.6524590163934425,
"grad_norm": 9.368250311381187,
"learning_rate": 4.1130267546374726e-07,
"loss": 0.5902255177497864,
"step": 809
},
{
"epoch": 2.6557377049180326,
"grad_norm": 5.871289073432532,
"learning_rate": 4.03755402927804e-07,
"loss": 0.4009667634963989,
"step": 810
},
{
"epoch": 2.6590163934426227,
"grad_norm": 12.79240864242054,
"learning_rate": 3.962751038431961e-07,
"loss": 0.715050995349884,
"step": 811
},
{
"epoch": 2.662295081967213,
"grad_norm": 10.594262698608302,
"learning_rate": 3.888618872079203e-07,
"loss": 0.5971469879150391,
"step": 812
},
{
"epoch": 2.6655737704918034,
"grad_norm": 15.877999197939989,
"learning_rate": 3.815158610424896e-07,
"loss": 0.8317169547080994,
"step": 813
},
{
"epoch": 2.6688524590163936,
"grad_norm": 8.943100209291494,
"learning_rate": 3.7423713238836426e-07,
"loss": 0.4437413513660431,
"step": 814
},
{
"epoch": 2.6721311475409837,
"grad_norm": 16.895162995871228,
"learning_rate": 3.670258073063865e-07,
"loss": 0.7190691232681274,
"step": 815
},
{
"epoch": 2.675409836065574,
"grad_norm": 9.21012516020575,
"learning_rate": 3.5988199087523987e-07,
"loss": 0.46982142329216003,
"step": 816
},
{
"epoch": 2.678688524590164,
"grad_norm": 7.639609447418553,
"learning_rate": 3.5280578718991544e-07,
"loss": 0.6563073396682739,
"step": 817
},
{
"epoch": 2.681967213114754,
"grad_norm": 6.960564005126012,
"learning_rate": 3.4579729936019656e-07,
"loss": 0.5035058856010437,
"step": 818
},
{
"epoch": 2.685245901639344,
"grad_norm": 9.078968262602558,
"learning_rate": 3.388566295091544e-07,
"loss": 0.7727448344230652,
"step": 819
},
{
"epoch": 2.6885245901639343,
"grad_norm": 7.490814127324463,
"learning_rate": 3.319838787716634e-07,
"loss": 0.6857200860977173,
"step": 820
},
{
"epoch": 2.6918032786885244,
"grad_norm": 13.81275808222043,
"learning_rate": 3.2517914729292446e-07,
"loss": 0.855427622795105,
"step": 821
},
{
"epoch": 2.695081967213115,
"grad_norm": 12.446870332625844,
"learning_rate": 3.184425342270053e-07,
"loss": 0.9690858721733093,
"step": 822
},
{
"epoch": 2.698360655737705,
"grad_norm": 7.558078474486006,
"learning_rate": 3.117741377353978e-07,
"loss": 0.4048570990562439,
"step": 823
},
{
"epoch": 2.7016393442622952,
"grad_norm": 9.428513773870677,
"learning_rate": 3.0517405498558696e-07,
"loss": 0.44000768661499023,
"step": 824
},
{
"epoch": 2.7049180327868854,
"grad_norm": 9.110846542542461,
"learning_rate": 2.9864238214963593e-07,
"loss": 0.6617041230201721,
"step": 825
},
{
"epoch": 2.7081967213114755,
"grad_norm": 9.143156959782054,
"learning_rate": 2.921792144027813e-07,
"loss": 0.5910684466362,
"step": 826
},
{
"epoch": 2.7114754098360656,
"grad_norm": 7.058912049109526,
"learning_rate": 2.8578464592205145e-07,
"loss": 0.7246738076210022,
"step": 827
},
{
"epoch": 2.7147540983606557,
"grad_norm": 12.730471796684768,
"learning_rate": 2.7945876988488883e-07,
"loss": 0.8969898223876953,
"step": 828
},
{
"epoch": 2.718032786885246,
"grad_norm": 8.779816711328683,
"learning_rate": 2.732016784677954e-07,
"loss": 0.5854172110557556,
"step": 829
},
{
"epoch": 2.721311475409836,
"grad_norm": 9.647809268687485,
"learning_rate": 2.6701346284499e-07,
"loss": 0.7470331192016602,
"step": 830
},
{
"epoch": 2.724590163934426,
"grad_norm": 11.088068159529023,
"learning_rate": 2.6089421318707785e-07,
"loss": 1.2475409507751465,
"step": 831
},
{
"epoch": 2.7278688524590162,
"grad_norm": 8.4828159011528,
"learning_rate": 2.548440186597373e-07,
"loss": 0.49615880846977234,
"step": 832
},
{
"epoch": 2.7311475409836063,
"grad_norm": 11.215374424741396,
"learning_rate": 2.4886296742242135e-07,
"loss": 0.6099059581756592,
"step": 833
},
{
"epoch": 2.7344262295081965,
"grad_norm": 10.181385949403362,
"learning_rate": 2.4295114662707285e-07,
"loss": 0.34299445152282715,
"step": 834
},
{
"epoch": 2.737704918032787,
"grad_norm": 11.481712576102744,
"learning_rate": 2.3710864241685338e-07,
"loss": 0.7269039154052734,
"step": 835
},
{
"epoch": 2.740983606557377,
"grad_norm": 7.476213087173758,
"learning_rate": 2.3133553992488845e-07,
"loss": 0.46271950006484985,
"step": 836
},
{
"epoch": 2.7442622950819673,
"grad_norm": 8.16069580105883,
"learning_rate": 2.256319232730292e-07,
"loss": 0.4534473419189453,
"step": 837
},
{
"epoch": 2.7475409836065574,
"grad_norm": 10.878256120702252,
"learning_rate": 2.199978755706228e-07,
"loss": 0.4390193819999695,
"step": 838
},
{
"epoch": 2.7508196721311475,
"grad_norm": 9.083116566307146,
"learning_rate": 2.144334789133057e-07,
"loss": 0.4008505344390869,
"step": 839
},
{
"epoch": 2.7540983606557377,
"grad_norm": 6.43431312570963,
"learning_rate": 2.0893881438180275e-07,
"loss": 0.6122070550918579,
"step": 840
},
{
"epoch": 2.7573770491803278,
"grad_norm": 10.622872262629405,
"learning_rate": 2.0351396204074946e-07,
"loss": 0.7235456705093384,
"step": 841
},
{
"epoch": 2.760655737704918,
"grad_norm": 7.213619311132858,
"learning_rate": 1.981590009375245e-07,
"loss": 0.5202394127845764,
"step": 842
},
{
"epoch": 2.7639344262295085,
"grad_norm": 10.161880372184976,
"learning_rate": 1.928740091010961e-07,
"loss": 0.6245577931404114,
"step": 843
},
{
"epoch": 2.7672131147540986,
"grad_norm": 6.758018946519213,
"learning_rate": 1.8765906354088704e-07,
"loss": 0.8134009838104248,
"step": 844
},
{
"epoch": 2.7704918032786887,
"grad_norm": 9.53893785483641,
"learning_rate": 1.8251424024565256e-07,
"loss": 0.6723477244377136,
"step": 845
},
{
"epoch": 2.773770491803279,
"grad_norm": 7.95046391349502,
"learning_rate": 1.7743961418237144e-07,
"loss": 0.4486456513404846,
"step": 846
},
{
"epoch": 2.777049180327869,
"grad_norm": 7.591058667301265,
"learning_rate": 1.7243525929515504e-07,
"loss": 0.8112704157829285,
"step": 847
},
{
"epoch": 2.780327868852459,
"grad_norm": 9.930607310114755,
"learning_rate": 1.6750124850416826e-07,
"loss": 0.682133674621582,
"step": 848
},
{
"epoch": 2.783606557377049,
"grad_norm": 8.813766989992272,
"learning_rate": 1.626376537045704e-07,
"loss": 0.6443338394165039,
"step": 849
},
{
"epoch": 2.7868852459016393,
"grad_norm": 7.094646177322405,
"learning_rate": 1.578445457654637e-07,
"loss": 0.6525646448135376,
"step": 850
},
{
"epoch": 2.7901639344262295,
"grad_norm": 11.626296711626333,
"learning_rate": 1.5312199452886145e-07,
"loss": 0.9580066800117493,
"step": 851
},
{
"epoch": 2.7934426229508196,
"grad_norm": 9.210254341369163,
"learning_rate": 1.484700688086743e-07,
"loss": 0.6437457799911499,
"step": 852
},
{
"epoch": 2.7967213114754097,
"grad_norm": 8.601088161825224,
"learning_rate": 1.4388883638970063e-07,
"loss": 0.42306095361709595,
"step": 853
},
{
"epoch": 2.8,
"grad_norm": 7.324300334125709,
"learning_rate": 1.3937836402664495e-07,
"loss": 0.6748613119125366,
"step": 854
},
{
"epoch": 2.80327868852459,
"grad_norm": 10.547086935821094,
"learning_rate": 1.3493871744314214e-07,
"loss": 0.3418477177619934,
"step": 855
},
{
"epoch": 2.80655737704918,
"grad_norm": 6.969955887076789,
"learning_rate": 1.3056996133079924e-07,
"loss": 0.5980502367019653,
"step": 856
},
{
"epoch": 2.8098360655737706,
"grad_norm": 7.294833640866651,
"learning_rate": 1.2627215934825577e-07,
"loss": 0.42744672298431396,
"step": 857
},
{
"epoch": 2.8131147540983608,
"grad_norm": 10.37042590987861,
"learning_rate": 1.220453741202543e-07,
"loss": 0.9779307842254639,
"step": 858
},
{
"epoch": 2.816393442622951,
"grad_norm": 12.272481933406535,
"learning_rate": 1.1788966723672635e-07,
"loss": 0.9996778964996338,
"step": 859
},
{
"epoch": 2.819672131147541,
"grad_norm": 17.305538683658135,
"learning_rate": 1.1380509925189853e-07,
"loss": 1.1473438739776611,
"step": 860
},
{
"epoch": 2.822950819672131,
"grad_norm": 8.705145620927263,
"learning_rate": 1.0979172968340667e-07,
"loss": 0.5649204254150391,
"step": 861
},
{
"epoch": 2.8262295081967213,
"grad_norm": 14.32991090724013,
"learning_rate": 1.0584961701143149e-07,
"loss": 0.8015550971031189,
"step": 862
},
{
"epoch": 2.8295081967213114,
"grad_norm": 8.804270867003007,
"learning_rate": 1.0197881867784365e-07,
"loss": 0.33222225308418274,
"step": 863
},
{
"epoch": 2.8327868852459015,
"grad_norm": 10.805115340890156,
"learning_rate": 9.817939108536956e-08,
"loss": 0.706474244594574,
"step": 864
},
{
"epoch": 2.836065573770492,
"grad_norm": 10.402005795094361,
"learning_rate": 9.445138959676692e-08,
"loss": 0.5427497625350952,
"step": 865
},
{
"epoch": 2.839344262295082,
"grad_norm": 8.197074456008247,
"learning_rate": 9.079486853402097e-08,
"loss": 0.6840100288391113,
"step": 866
},
{
"epoch": 2.8426229508196723,
"grad_norm": 9.319086353566995,
"learning_rate": 8.720988117754958e-08,
"loss": 0.6404067277908325,
"step": 867
},
{
"epoch": 2.8459016393442624,
"grad_norm": 8.310362206317706,
"learning_rate": 8.369647976542883e-08,
"loss": 0.556831955909729,
"step": 868
},
{
"epoch": 2.8491803278688526,
"grad_norm": 11.916371174895799,
"learning_rate": 8.025471549263142e-08,
"loss": 0.800558865070343,
"step": 869
},
{
"epoch": 2.8524590163934427,
"grad_norm": 11.724735875015957,
"learning_rate": 7.688463851028227e-08,
"loss": 0.7638567686080933,
"step": 870
},
{
"epoch": 2.855737704918033,
"grad_norm": 9.237960315010103,
"learning_rate": 7.358629792492522e-08,
"loss": 0.5945174694061279,
"step": 871
},
{
"epoch": 2.859016393442623,
"grad_norm": 16.973787019570754,
"learning_rate": 7.035974179780803e-08,
"loss": 0.5800426602363586,
"step": 872
},
{
"epoch": 2.862295081967213,
"grad_norm": 11.379259939969558,
"learning_rate": 6.720501714418237e-08,
"loss": 0.7505283355712891,
"step": 873
},
{
"epoch": 2.865573770491803,
"grad_norm": 9.656225233728003,
"learning_rate": 6.41221699326211e-08,
"loss": 0.999565839767456,
"step": 874
},
{
"epoch": 2.8688524590163933,
"grad_norm": 7.971622495757984,
"learning_rate": 6.11112450843443e-08,
"loss": 0.593449592590332,
"step": 875
},
{
"epoch": 2.8721311475409834,
"grad_norm": 8.980449631620504,
"learning_rate": 5.8172286472566456e-08,
"loss": 0.5593907833099365,
"step": 876
},
{
"epoch": 2.8754098360655735,
"grad_norm": 9.529195014273123,
"learning_rate": 5.53053369218598e-08,
"loss": 0.59034264087677,
"step": 877
},
{
"epoch": 2.8786885245901637,
"grad_norm": 8.883154573445223,
"learning_rate": 5.251043820752533e-08,
"loss": 0.6159124374389648,
"step": 878
},
{
"epoch": 2.8819672131147542,
"grad_norm": 10.015292813404121,
"learning_rate": 4.978763105498774e-08,
"loss": 0.564907968044281,
"step": 879
},
{
"epoch": 2.8852459016393444,
"grad_norm": 8.877025904067645,
"learning_rate": 4.713695513920147e-08,
"loss": 0.6092976331710815,
"step": 880
},
{
"epoch": 2.8885245901639345,
"grad_norm": 13.087425563399531,
"learning_rate": 4.455844908407059e-08,
"loss": 0.45290064811706543,
"step": 881
},
{
"epoch": 2.8918032786885246,
"grad_norm": 7.493274122506968,
"learning_rate": 4.205215046188926e-08,
"loss": 0.5094927549362183,
"step": 882
},
{
"epoch": 2.8950819672131147,
"grad_norm": 10.418940699294136,
"learning_rate": 3.9618095792790524e-08,
"loss": 0.6270198822021484,
"step": 883
},
{
"epoch": 2.898360655737705,
"grad_norm": 8.885371305625478,
"learning_rate": 3.7256320544218347e-08,
"loss": 0.7956331968307495,
"step": 884
},
{
"epoch": 2.901639344262295,
"grad_norm": 8.244563536045693,
"learning_rate": 3.4966859130405873e-08,
"loss": 0.7026015520095825,
"step": 885
},
{
"epoch": 2.904918032786885,
"grad_norm": 10.467424802431355,
"learning_rate": 3.27497449118791e-08,
"loss": 0.7262118458747864,
"step": 886
},
{
"epoch": 2.9081967213114757,
"grad_norm": 9.0119192158647,
"learning_rate": 3.060501019496675e-08,
"loss": 0.6786316633224487,
"step": 887
},
{
"epoch": 2.911475409836066,
"grad_norm": 8.287242668225502,
"learning_rate": 2.853268623133232e-08,
"loss": 0.7014474868774414,
"step": 888
},
{
"epoch": 2.914754098360656,
"grad_norm": 9.449835059250328,
"learning_rate": 2.65328032175155e-08,
"loss": 0.9751036167144775,
"step": 889
},
{
"epoch": 2.918032786885246,
"grad_norm": 11.90492447078595,
"learning_rate": 2.4605390294497043e-08,
"loss": 0.7350157499313354,
"step": 890
},
{
"epoch": 2.921311475409836,
"grad_norm": 7.443321940718876,
"learning_rate": 2.275047554726795e-08,
"loss": 0.6686207056045532,
"step": 891
},
{
"epoch": 2.9245901639344263,
"grad_norm": 7.92371234212105,
"learning_rate": 2.0968086004425903e-08,
"loss": 0.7841460704803467,
"step": 892
},
{
"epoch": 2.9278688524590164,
"grad_norm": 7.081271964048332,
"learning_rate": 1.9258247637778393e-08,
"loss": 0.6987062096595764,
"step": 893
},
{
"epoch": 2.9311475409836065,
"grad_norm": 13.436496778674424,
"learning_rate": 1.762098536196466e-08,
"loss": 0.7867368459701538,
"step": 894
},
{
"epoch": 2.9344262295081966,
"grad_norm": 8.25269515028753,
"learning_rate": 1.6056323034092658e-08,
"loss": 0.7751071453094482,
"step": 895
},
{
"epoch": 2.9377049180327868,
"grad_norm": 8.665161960356096,
"learning_rate": 1.4564283453392669e-08,
"loss": 0.7448148727416992,
"step": 896
},
{
"epoch": 2.940983606557377,
"grad_norm": 10.787329953761654,
"learning_rate": 1.3144888360883678e-08,
"loss": 0.5395925045013428,
"step": 897
},
{
"epoch": 2.944262295081967,
"grad_norm": 10.978042105561899,
"learning_rate": 1.179815843905585e-08,
"loss": 0.6888113021850586,
"step": 898
},
{
"epoch": 2.947540983606557,
"grad_norm": 11.553965534322028,
"learning_rate": 1.0524113311571881e-08,
"loss": 0.5078659653663635,
"step": 899
},
{
"epoch": 2.9508196721311473,
"grad_norm": 13.043459685630678,
"learning_rate": 9.322771542978892e-09,
"loss": 0.6531692743301392,
"step": 900
},
{
"epoch": 2.954098360655738,
"grad_norm": 10.89031227513574,
"learning_rate": 8.194150638438093e-09,
"loss": 0.888818621635437,
"step": 901
},
{
"epoch": 2.957377049180328,
"grad_norm": 9.766839312076108,
"learning_rate": 7.138267043471647e-09,
"loss": 0.49958160519599915,
"step": 902
},
{
"epoch": 2.960655737704918,
"grad_norm": 10.40192268687688,
"learning_rate": 6.1551361437189876e-09,
"loss": 0.8164390325546265,
"step": 903
},
{
"epoch": 2.963934426229508,
"grad_norm": 9.020802587654194,
"learning_rate": 5.244772264717535e-09,
"loss": 0.5776973962783813,
"step": 904
},
{
"epoch": 2.9672131147540983,
"grad_norm": 74.88350948695356,
"learning_rate": 4.407188671690099e-09,
"loss": 0.6302528381347656,
"step": 905
},
{
"epoch": 2.9704918032786884,
"grad_norm": 10.291708081506558,
"learning_rate": 3.6423975693533618e-09,
"loss": 0.7293718457221985,
"step": 906
},
{
"epoch": 2.9737704918032786,
"grad_norm": 8.433209135811323,
"learning_rate": 2.950410101740797e-09,
"loss": 0.6107383370399475,
"step": 907
},
{
"epoch": 2.9770491803278687,
"grad_norm": 16.156426054367216,
"learning_rate": 2.3312363520378024e-09,
"loss": 0.670303225517273,
"step": 908
},
{
"epoch": 2.9803278688524593,
"grad_norm": 9.841217655731743,
"learning_rate": 1.78488534243626e-09,
"loss": 0.647737979888916,
"step": 909
},
{
"epoch": 2.9836065573770494,
"grad_norm": 9.672450498610333,
"learning_rate": 1.3113650340046413e-09,
"loss": 0.6792494654655457,
"step": 910
},
{
"epoch": 2.9868852459016395,
"grad_norm": 10.753013068423641,
"learning_rate": 9.106823265681019e-10,
"loss": 0.5941249132156372,
"step": 911
},
{
"epoch": 2.9901639344262296,
"grad_norm": 7.871527643095715,
"learning_rate": 5.828430586124479e-10,
"loss": 0.3177376985549927,
"step": 912
},
{
"epoch": 2.9934426229508198,
"grad_norm": 12.358592647358588,
"learning_rate": 3.278520071947622e-10,
"loss": 0.6548700928688049,
"step": 913
},
{
"epoch": 2.99672131147541,
"grad_norm": 13.09126561142478,
"learning_rate": 1.457128878779024e-10,
"loss": 0.7156137228012085,
"step": 914
},
{
"epoch": 3.0,
"grad_norm": 11.504680357991957,
"learning_rate": 3.6428354671658176e-11,
"loss": 0.42233142256736755,
"step": 915
},
{
"epoch": 3.0,
"step": 915,
"total_flos": 4888573747200.0,
"train_loss": 1.5217517310478648,
"train_runtime": 2117.074,
"train_samples_per_second": 3.452,
"train_steps_per_second": 0.432
}
],
"logging_steps": 1,
"max_steps": 915,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"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": 4888573747200.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}