MS-24B-Mullein-v0-ep1-lora / trainer_state.json
Hasnonname's picture
Upload folder using huggingface_hub
26f0ff3 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0017097670442403,
"eval_steps": 293,
"global_step": 1172,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0008548835221201111,
"grad_norm": 14.855524063110352,
"learning_rate": 8.547008547008549e-08,
"loss": 1.7846,
"step": 1
},
{
"epoch": 0.0008548835221201111,
"eval_loss": 1.7640409469604492,
"eval_runtime": 533.0927,
"eval_samples_per_second": 7.421,
"eval_steps_per_second": 3.71,
"step": 1
},
{
"epoch": 0.0017097670442402222,
"grad_norm": 11.91721248626709,
"learning_rate": 1.7094017094017097e-07,
"loss": 1.6794,
"step": 2
},
{
"epoch": 0.0025646505663603335,
"grad_norm": 15.487826347351074,
"learning_rate": 2.564102564102564e-07,
"loss": 1.7593,
"step": 3
},
{
"epoch": 0.0034195340884804444,
"grad_norm": 11.996491432189941,
"learning_rate": 3.4188034188034194e-07,
"loss": 1.7245,
"step": 4
},
{
"epoch": 0.004274417610600555,
"grad_norm": 30.804367065429688,
"learning_rate": 4.273504273504274e-07,
"loss": 1.771,
"step": 5
},
{
"epoch": 0.005129301132720667,
"grad_norm": 19.530527114868164,
"learning_rate": 5.128205128205128e-07,
"loss": 1.7888,
"step": 6
},
{
"epoch": 0.005984184654840778,
"grad_norm": 31.70332145690918,
"learning_rate": 5.982905982905984e-07,
"loss": 1.5394,
"step": 7
},
{
"epoch": 0.006839068176960889,
"grad_norm": 11.850404739379883,
"learning_rate": 6.837606837606839e-07,
"loss": 1.7094,
"step": 8
},
{
"epoch": 0.007693951699081001,
"grad_norm": 24.769758224487305,
"learning_rate": 7.692307692307694e-07,
"loss": 1.5411,
"step": 9
},
{
"epoch": 0.00854883522120111,
"grad_norm": 15.908349990844727,
"learning_rate": 8.547008547008548e-07,
"loss": 1.8037,
"step": 10
},
{
"epoch": 0.009403718743321222,
"grad_norm": 6.722436428070068,
"learning_rate": 9.401709401709402e-07,
"loss": 1.7905,
"step": 11
},
{
"epoch": 0.010258602265441334,
"grad_norm": 4.48321008682251,
"learning_rate": 1.0256410256410257e-06,
"loss": 1.6772,
"step": 12
},
{
"epoch": 0.011113485787561444,
"grad_norm": 4.574745178222656,
"learning_rate": 1.111111111111111e-06,
"loss": 1.8258,
"step": 13
},
{
"epoch": 0.011968369309681556,
"grad_norm": 4.0335516929626465,
"learning_rate": 1.1965811965811968e-06,
"loss": 1.8022,
"step": 14
},
{
"epoch": 0.012823252831801668,
"grad_norm": 39.62892532348633,
"learning_rate": 1.282051282051282e-06,
"loss": 1.643,
"step": 15
},
{
"epoch": 0.013678136353921778,
"grad_norm": 7.48787784576416,
"learning_rate": 1.3675213675213678e-06,
"loss": 1.7202,
"step": 16
},
{
"epoch": 0.01453301987604189,
"grad_norm": 4.110783576965332,
"learning_rate": 1.4529914529914531e-06,
"loss": 1.7974,
"step": 17
},
{
"epoch": 0.015387903398162001,
"grad_norm": 3.7065269947052,
"learning_rate": 1.5384615384615387e-06,
"loss": 1.765,
"step": 18
},
{
"epoch": 0.016242786920282113,
"grad_norm": 6.430235862731934,
"learning_rate": 1.623931623931624e-06,
"loss": 1.5331,
"step": 19
},
{
"epoch": 0.01709767044240222,
"grad_norm": 21.641319274902344,
"learning_rate": 1.7094017094017097e-06,
"loss": 1.8761,
"step": 20
},
{
"epoch": 0.017952553964522333,
"grad_norm": 3.3955209255218506,
"learning_rate": 1.794871794871795e-06,
"loss": 1.7766,
"step": 21
},
{
"epoch": 0.018807437486642445,
"grad_norm": 3.9773988723754883,
"learning_rate": 1.8803418803418804e-06,
"loss": 1.7743,
"step": 22
},
{
"epoch": 0.019662321008762557,
"grad_norm": 5.062834739685059,
"learning_rate": 1.9658119658119658e-06,
"loss": 1.769,
"step": 23
},
{
"epoch": 0.02051720453088267,
"grad_norm": 4.090948104858398,
"learning_rate": 2.0512820512820513e-06,
"loss": 1.6356,
"step": 24
},
{
"epoch": 0.021372088053002777,
"grad_norm": 4.175969123840332,
"learning_rate": 2.136752136752137e-06,
"loss": 1.4285,
"step": 25
},
{
"epoch": 0.02222697157512289,
"grad_norm": 2.989772319793701,
"learning_rate": 2.222222222222222e-06,
"loss": 1.5791,
"step": 26
},
{
"epoch": 0.023081855097243,
"grad_norm": 2.7935218811035156,
"learning_rate": 2.307692307692308e-06,
"loss": 1.7335,
"step": 27
},
{
"epoch": 0.023936738619363112,
"grad_norm": 2.8618392944335938,
"learning_rate": 2.3931623931623937e-06,
"loss": 1.8338,
"step": 28
},
{
"epoch": 0.024791622141483224,
"grad_norm": 2.662318229675293,
"learning_rate": 2.478632478632479e-06,
"loss": 1.7555,
"step": 29
},
{
"epoch": 0.025646505663603335,
"grad_norm": 3.7374916076660156,
"learning_rate": 2.564102564102564e-06,
"loss": 1.4183,
"step": 30
},
{
"epoch": 0.026501389185723444,
"grad_norm": 4.106424331665039,
"learning_rate": 2.64957264957265e-06,
"loss": 1.7026,
"step": 31
},
{
"epoch": 0.027356272707843556,
"grad_norm": 2.8097198009490967,
"learning_rate": 2.7350427350427355e-06,
"loss": 1.5934,
"step": 32
},
{
"epoch": 0.028211156229963667,
"grad_norm": 2.798865795135498,
"learning_rate": 2.8205128205128207e-06,
"loss": 1.8201,
"step": 33
},
{
"epoch": 0.02906603975208378,
"grad_norm": 2.733314037322998,
"learning_rate": 2.9059829059829063e-06,
"loss": 1.7498,
"step": 34
},
{
"epoch": 0.02992092327420389,
"grad_norm": 3.037261962890625,
"learning_rate": 2.9914529914529914e-06,
"loss": 1.6768,
"step": 35
},
{
"epoch": 0.030775806796324003,
"grad_norm": 2.6975414752960205,
"learning_rate": 3.0769230769230774e-06,
"loss": 1.7676,
"step": 36
},
{
"epoch": 0.031630690318444114,
"grad_norm": 3.185695171356201,
"learning_rate": 3.1623931623931626e-06,
"loss": 1.719,
"step": 37
},
{
"epoch": 0.032485573840564226,
"grad_norm": 2.5215115547180176,
"learning_rate": 3.247863247863248e-06,
"loss": 1.7738,
"step": 38
},
{
"epoch": 0.03334045736268433,
"grad_norm": 2.78493332862854,
"learning_rate": 3.3333333333333333e-06,
"loss": 1.6016,
"step": 39
},
{
"epoch": 0.03419534088480444,
"grad_norm": 2.629739999771118,
"learning_rate": 3.4188034188034193e-06,
"loss": 1.6574,
"step": 40
},
{
"epoch": 0.035050224406924554,
"grad_norm": 3.270066976547241,
"learning_rate": 3.5042735042735045e-06,
"loss": 1.7667,
"step": 41
},
{
"epoch": 0.035905107929044666,
"grad_norm": 2.714362859725952,
"learning_rate": 3.58974358974359e-06,
"loss": 1.5054,
"step": 42
},
{
"epoch": 0.03675999145116478,
"grad_norm": 3.978623151779175,
"learning_rate": 3.6752136752136756e-06,
"loss": 1.6212,
"step": 43
},
{
"epoch": 0.03761487497328489,
"grad_norm": 2.5128977298736572,
"learning_rate": 3.760683760683761e-06,
"loss": 1.4326,
"step": 44
},
{
"epoch": 0.038469758495405,
"grad_norm": 2.9654622077941895,
"learning_rate": 3.846153846153847e-06,
"loss": 1.7595,
"step": 45
},
{
"epoch": 0.03932464201752511,
"grad_norm": 3.1219539642333984,
"learning_rate": 3.9316239316239315e-06,
"loss": 1.9805,
"step": 46
},
{
"epoch": 0.040179525539645225,
"grad_norm": 2.5867958068847656,
"learning_rate": 4.017094017094018e-06,
"loss": 1.8051,
"step": 47
},
{
"epoch": 0.04103440906176534,
"grad_norm": 2.4655587673187256,
"learning_rate": 4.102564102564103e-06,
"loss": 1.6707,
"step": 48
},
{
"epoch": 0.04188929258388545,
"grad_norm": 3.301828384399414,
"learning_rate": 4.188034188034188e-06,
"loss": 1.4957,
"step": 49
},
{
"epoch": 0.04274417610600555,
"grad_norm": 3.0518338680267334,
"learning_rate": 4.273504273504274e-06,
"loss": 1.623,
"step": 50
},
{
"epoch": 0.043599059628125665,
"grad_norm": 2.4164023399353027,
"learning_rate": 4.358974358974359e-06,
"loss": 1.694,
"step": 51
},
{
"epoch": 0.04445394315024578,
"grad_norm": 2.7269129753112793,
"learning_rate": 4.444444444444444e-06,
"loss": 1.571,
"step": 52
},
{
"epoch": 0.04530882667236589,
"grad_norm": 2.5209498405456543,
"learning_rate": 4.5299145299145306e-06,
"loss": 1.7713,
"step": 53
},
{
"epoch": 0.046163710194486,
"grad_norm": 2.6886680126190186,
"learning_rate": 4.615384615384616e-06,
"loss": 1.6275,
"step": 54
},
{
"epoch": 0.04701859371660611,
"grad_norm": 2.4499754905700684,
"learning_rate": 4.700854700854701e-06,
"loss": 1.6943,
"step": 55
},
{
"epoch": 0.047873477238726224,
"grad_norm": 2.6294198036193848,
"learning_rate": 4.786324786324787e-06,
"loss": 1.6578,
"step": 56
},
{
"epoch": 0.048728360760846336,
"grad_norm": 2.2285401821136475,
"learning_rate": 4.871794871794872e-06,
"loss": 1.5894,
"step": 57
},
{
"epoch": 0.04958324428296645,
"grad_norm": 2.875617027282715,
"learning_rate": 4.957264957264958e-06,
"loss": 1.57,
"step": 58
},
{
"epoch": 0.05043812780508656,
"grad_norm": 6.192116737365723,
"learning_rate": 5.042735042735043e-06,
"loss": 1.5363,
"step": 59
},
{
"epoch": 0.05129301132720667,
"grad_norm": 5.477021217346191,
"learning_rate": 5.128205128205128e-06,
"loss": 1.5987,
"step": 60
},
{
"epoch": 0.052147894849326776,
"grad_norm": 3.1479716300964355,
"learning_rate": 5.213675213675214e-06,
"loss": 1.578,
"step": 61
},
{
"epoch": 0.05300277837144689,
"grad_norm": 2.7842800617218018,
"learning_rate": 5.2991452991453e-06,
"loss": 1.6855,
"step": 62
},
{
"epoch": 0.053857661893567,
"grad_norm": 2.487064838409424,
"learning_rate": 5.384615384615385e-06,
"loss": 1.7421,
"step": 63
},
{
"epoch": 0.05471254541568711,
"grad_norm": 2.895413875579834,
"learning_rate": 5.470085470085471e-06,
"loss": 1.4335,
"step": 64
},
{
"epoch": 0.05556742893780722,
"grad_norm": 2.683014154434204,
"learning_rate": 5.555555555555557e-06,
"loss": 1.5071,
"step": 65
},
{
"epoch": 0.056422312459927335,
"grad_norm": 2.4958949089050293,
"learning_rate": 5.641025641025641e-06,
"loss": 1.594,
"step": 66
},
{
"epoch": 0.057277195982047446,
"grad_norm": 2.551091432571411,
"learning_rate": 5.726495726495727e-06,
"loss": 1.5684,
"step": 67
},
{
"epoch": 0.05813207950416756,
"grad_norm": 2.249833106994629,
"learning_rate": 5.8119658119658126e-06,
"loss": 1.5948,
"step": 68
},
{
"epoch": 0.05898696302628767,
"grad_norm": 2.3720970153808594,
"learning_rate": 5.897435897435898e-06,
"loss": 1.7099,
"step": 69
},
{
"epoch": 0.05984184654840778,
"grad_norm": 2.520702600479126,
"learning_rate": 5.982905982905983e-06,
"loss": 1.4667,
"step": 70
},
{
"epoch": 0.06069673007052789,
"grad_norm": 2.6141464710235596,
"learning_rate": 6.0683760683760684e-06,
"loss": 1.4677,
"step": 71
},
{
"epoch": 0.061551613592648005,
"grad_norm": 2.9519152641296387,
"learning_rate": 6.153846153846155e-06,
"loss": 1.6429,
"step": 72
},
{
"epoch": 0.06240649711476811,
"grad_norm": 3.462202787399292,
"learning_rate": 6.23931623931624e-06,
"loss": 1.495,
"step": 73
},
{
"epoch": 0.06326138063688823,
"grad_norm": 2.5748167037963867,
"learning_rate": 6.324786324786325e-06,
"loss": 1.7717,
"step": 74
},
{
"epoch": 0.06411626415900834,
"grad_norm": 3.142380475997925,
"learning_rate": 6.410256410256412e-06,
"loss": 1.6701,
"step": 75
},
{
"epoch": 0.06497114768112845,
"grad_norm": 2.6841933727264404,
"learning_rate": 6.495726495726496e-06,
"loss": 1.722,
"step": 76
},
{
"epoch": 0.06582603120324856,
"grad_norm": 2.4726481437683105,
"learning_rate": 6.581196581196582e-06,
"loss": 1.7228,
"step": 77
},
{
"epoch": 0.06668091472536866,
"grad_norm": 2.7335448265075684,
"learning_rate": 6.666666666666667e-06,
"loss": 1.5682,
"step": 78
},
{
"epoch": 0.06753579824748877,
"grad_norm": 2.577003002166748,
"learning_rate": 6.752136752136753e-06,
"loss": 1.7154,
"step": 79
},
{
"epoch": 0.06839068176960889,
"grad_norm": 2.7609519958496094,
"learning_rate": 6.837606837606839e-06,
"loss": 1.4844,
"step": 80
},
{
"epoch": 0.069245565291729,
"grad_norm": 3.498229503631592,
"learning_rate": 6.923076923076923e-06,
"loss": 1.4114,
"step": 81
},
{
"epoch": 0.07010044881384911,
"grad_norm": 2.5216593742370605,
"learning_rate": 7.008547008547009e-06,
"loss": 1.5511,
"step": 82
},
{
"epoch": 0.07095533233596922,
"grad_norm": 2.2648119926452637,
"learning_rate": 7.0940170940170945e-06,
"loss": 1.8513,
"step": 83
},
{
"epoch": 0.07181021585808933,
"grad_norm": 2.869992256164551,
"learning_rate": 7.17948717948718e-06,
"loss": 1.4821,
"step": 84
},
{
"epoch": 0.07266509938020944,
"grad_norm": 4.656053066253662,
"learning_rate": 7.264957264957266e-06,
"loss": 1.621,
"step": 85
},
{
"epoch": 0.07351998290232956,
"grad_norm": 2.4541072845458984,
"learning_rate": 7.350427350427351e-06,
"loss": 1.5993,
"step": 86
},
{
"epoch": 0.07437486642444967,
"grad_norm": 2.7510995864868164,
"learning_rate": 7.435897435897437e-06,
"loss": 1.649,
"step": 87
},
{
"epoch": 0.07522974994656978,
"grad_norm": 2.552407741546631,
"learning_rate": 7.521367521367522e-06,
"loss": 1.605,
"step": 88
},
{
"epoch": 0.07608463346868989,
"grad_norm": 2.482236862182617,
"learning_rate": 7.606837606837607e-06,
"loss": 1.4649,
"step": 89
},
{
"epoch": 0.07693951699081,
"grad_norm": 2.5153439044952393,
"learning_rate": 7.692307692307694e-06,
"loss": 1.6409,
"step": 90
},
{
"epoch": 0.07779440051293011,
"grad_norm": 2.774604082107544,
"learning_rate": 7.77777777777778e-06,
"loss": 1.771,
"step": 91
},
{
"epoch": 0.07864928403505023,
"grad_norm": 2.6241939067840576,
"learning_rate": 7.863247863247863e-06,
"loss": 1.5099,
"step": 92
},
{
"epoch": 0.07950416755717034,
"grad_norm": 2.3177523612976074,
"learning_rate": 7.948717948717949e-06,
"loss": 1.6473,
"step": 93
},
{
"epoch": 0.08035905107929045,
"grad_norm": 3.034937620162964,
"learning_rate": 8.034188034188036e-06,
"loss": 1.7484,
"step": 94
},
{
"epoch": 0.08121393460141056,
"grad_norm": 2.1960113048553467,
"learning_rate": 8.11965811965812e-06,
"loss": 1.7495,
"step": 95
},
{
"epoch": 0.08206881812353067,
"grad_norm": 2.538083791732788,
"learning_rate": 8.205128205128205e-06,
"loss": 1.6463,
"step": 96
},
{
"epoch": 0.08292370164565079,
"grad_norm": 2.5417184829711914,
"learning_rate": 8.290598290598293e-06,
"loss": 1.7242,
"step": 97
},
{
"epoch": 0.0837785851677709,
"grad_norm": 2.7011282444000244,
"learning_rate": 8.376068376068377e-06,
"loss": 1.4753,
"step": 98
},
{
"epoch": 0.08463346868989101,
"grad_norm": 2.4932761192321777,
"learning_rate": 8.461538461538462e-06,
"loss": 1.6388,
"step": 99
},
{
"epoch": 0.0854883522120111,
"grad_norm": 3.0729198455810547,
"learning_rate": 8.547008547008548e-06,
"loss": 1.6646,
"step": 100
},
{
"epoch": 0.08634323573413122,
"grad_norm": 3.0038278102874756,
"learning_rate": 8.632478632478633e-06,
"loss": 1.5641,
"step": 101
},
{
"epoch": 0.08719811925625133,
"grad_norm": 2.3090646266937256,
"learning_rate": 8.717948717948719e-06,
"loss": 1.7689,
"step": 102
},
{
"epoch": 0.08805300277837144,
"grad_norm": 2.393385171890259,
"learning_rate": 8.803418803418804e-06,
"loss": 1.667,
"step": 103
},
{
"epoch": 0.08890788630049155,
"grad_norm": 2.366182565689087,
"learning_rate": 8.888888888888888e-06,
"loss": 1.6058,
"step": 104
},
{
"epoch": 0.08976276982261167,
"grad_norm": 2.586094617843628,
"learning_rate": 8.974358974358976e-06,
"loss": 1.4245,
"step": 105
},
{
"epoch": 0.09061765334473178,
"grad_norm": 2.889852285385132,
"learning_rate": 9.059829059829061e-06,
"loss": 1.4404,
"step": 106
},
{
"epoch": 0.09147253686685189,
"grad_norm": 2.264047622680664,
"learning_rate": 9.145299145299145e-06,
"loss": 1.6835,
"step": 107
},
{
"epoch": 0.092327420388972,
"grad_norm": 2.287929058074951,
"learning_rate": 9.230769230769232e-06,
"loss": 1.659,
"step": 108
},
{
"epoch": 0.09318230391109211,
"grad_norm": 2.4839229583740234,
"learning_rate": 9.316239316239318e-06,
"loss": 1.6764,
"step": 109
},
{
"epoch": 0.09403718743321222,
"grad_norm": 2.53434419631958,
"learning_rate": 9.401709401709402e-06,
"loss": 1.5596,
"step": 110
},
{
"epoch": 0.09489207095533234,
"grad_norm": 2.017806053161621,
"learning_rate": 9.487179487179487e-06,
"loss": 1.5227,
"step": 111
},
{
"epoch": 0.09574695447745245,
"grad_norm": 2.4538073539733887,
"learning_rate": 9.572649572649575e-06,
"loss": 1.6464,
"step": 112
},
{
"epoch": 0.09660183799957256,
"grad_norm": 2.4926862716674805,
"learning_rate": 9.658119658119659e-06,
"loss": 1.6442,
"step": 113
},
{
"epoch": 0.09745672152169267,
"grad_norm": 3.169382095336914,
"learning_rate": 9.743589743589744e-06,
"loss": 1.3884,
"step": 114
},
{
"epoch": 0.09831160504381278,
"grad_norm": 3.1526899337768555,
"learning_rate": 9.82905982905983e-06,
"loss": 1.802,
"step": 115
},
{
"epoch": 0.0991664885659329,
"grad_norm": 2.323765754699707,
"learning_rate": 9.914529914529915e-06,
"loss": 1.4209,
"step": 116
},
{
"epoch": 0.100021372088053,
"grad_norm": 2.223529815673828,
"learning_rate": 1e-05,
"loss": 1.6514,
"step": 117
},
{
"epoch": 0.10087625561017312,
"grad_norm": 2.611987590789795,
"learning_rate": 9.999994998012932e-06,
"loss": 1.4056,
"step": 118
},
{
"epoch": 0.10173113913229323,
"grad_norm": 2.104203939437866,
"learning_rate": 9.999979992061739e-06,
"loss": 1.5361,
"step": 119
},
{
"epoch": 0.10258602265441334,
"grad_norm": 2.0273749828338623,
"learning_rate": 9.999954982176439e-06,
"loss": 1.7908,
"step": 120
},
{
"epoch": 0.10344090617653345,
"grad_norm": 2.2206482887268066,
"learning_rate": 9.999919968407077e-06,
"loss": 1.5552,
"step": 121
},
{
"epoch": 0.10429578969865355,
"grad_norm": 2.1885461807250977,
"learning_rate": 9.999874950823707e-06,
"loss": 1.8227,
"step": 122
},
{
"epoch": 0.10515067322077366,
"grad_norm": 2.532996892929077,
"learning_rate": 9.999819929516398e-06,
"loss": 1.7544,
"step": 123
},
{
"epoch": 0.10600555674289378,
"grad_norm": 2.10715913772583,
"learning_rate": 9.999754904595237e-06,
"loss": 1.6595,
"step": 124
},
{
"epoch": 0.10686044026501389,
"grad_norm": 2.810800790786743,
"learning_rate": 9.99967987619033e-06,
"loss": 1.5268,
"step": 125
},
{
"epoch": 0.107715323787134,
"grad_norm": 2.2151639461517334,
"learning_rate": 9.999594844451787e-06,
"loss": 1.6595,
"step": 126
},
{
"epoch": 0.10857020730925411,
"grad_norm": 3.241767168045044,
"learning_rate": 9.999499809549742e-06,
"loss": 1.5238,
"step": 127
},
{
"epoch": 0.10942509083137422,
"grad_norm": 2.3466122150421143,
"learning_rate": 9.99939477167434e-06,
"loss": 1.7066,
"step": 128
},
{
"epoch": 0.11027997435349433,
"grad_norm": 2.006361246109009,
"learning_rate": 9.999279731035741e-06,
"loss": 1.7432,
"step": 129
},
{
"epoch": 0.11113485787561445,
"grad_norm": 2.3450944423675537,
"learning_rate": 9.999154687864118e-06,
"loss": 1.5009,
"step": 130
},
{
"epoch": 0.11198974139773456,
"grad_norm": 2.390202522277832,
"learning_rate": 9.999019642409654e-06,
"loss": 1.6976,
"step": 131
},
{
"epoch": 0.11284462491985467,
"grad_norm": 3.701263189315796,
"learning_rate": 9.99887459494255e-06,
"loss": 1.6372,
"step": 132
},
{
"epoch": 0.11369950844197478,
"grad_norm": 2.3453369140625,
"learning_rate": 9.998719545753015e-06,
"loss": 1.6543,
"step": 133
},
{
"epoch": 0.11455439196409489,
"grad_norm": 2.018839120864868,
"learning_rate": 9.998554495151272e-06,
"loss": 1.7406,
"step": 134
},
{
"epoch": 0.115409275486215,
"grad_norm": 2.201392889022827,
"learning_rate": 9.998379443467552e-06,
"loss": 1.6153,
"step": 135
},
{
"epoch": 0.11626415900833512,
"grad_norm": 2.081862449645996,
"learning_rate": 9.998194391052097e-06,
"loss": 1.6368,
"step": 136
},
{
"epoch": 0.11711904253045523,
"grad_norm": 2.114025592803955,
"learning_rate": 9.99799933827516e-06,
"loss": 1.5724,
"step": 137
},
{
"epoch": 0.11797392605257534,
"grad_norm": 2.1307966709136963,
"learning_rate": 9.997794285527002e-06,
"loss": 1.6064,
"step": 138
},
{
"epoch": 0.11882880957469545,
"grad_norm": 2.265519142150879,
"learning_rate": 9.99757923321789e-06,
"loss": 1.6883,
"step": 139
},
{
"epoch": 0.11968369309681556,
"grad_norm": 2.3927133083343506,
"learning_rate": 9.997354181778101e-06,
"loss": 1.4476,
"step": 140
},
{
"epoch": 0.12053857661893567,
"grad_norm": 2.2618932723999023,
"learning_rate": 9.997119131657915e-06,
"loss": 1.3637,
"step": 141
},
{
"epoch": 0.12139346014105579,
"grad_norm": 2.382002353668213,
"learning_rate": 9.996874083327621e-06,
"loss": 1.4367,
"step": 142
},
{
"epoch": 0.1222483436631759,
"grad_norm": 2.655059337615967,
"learning_rate": 9.99661903727751e-06,
"loss": 1.7059,
"step": 143
},
{
"epoch": 0.12310322718529601,
"grad_norm": 1.9572539329528809,
"learning_rate": 9.996353994017876e-06,
"loss": 1.697,
"step": 144
},
{
"epoch": 0.12395811070741611,
"grad_norm": 2.7208900451660156,
"learning_rate": 9.996078954079017e-06,
"loss": 1.6188,
"step": 145
},
{
"epoch": 0.12481299422953622,
"grad_norm": 2.2011163234710693,
"learning_rate": 9.995793918011231e-06,
"loss": 1.4557,
"step": 146
},
{
"epoch": 0.12566787775165633,
"grad_norm": 2.1749141216278076,
"learning_rate": 9.995498886384816e-06,
"loss": 1.701,
"step": 147
},
{
"epoch": 0.12652276127377646,
"grad_norm": 2.7541191577911377,
"learning_rate": 9.995193859790071e-06,
"loss": 1.7045,
"step": 148
},
{
"epoch": 0.12737764479589656,
"grad_norm": 2.489243984222412,
"learning_rate": 9.994878838837292e-06,
"loss": 1.5494,
"step": 149
},
{
"epoch": 0.12823252831801668,
"grad_norm": 2.1933681964874268,
"learning_rate": 9.99455382415677e-06,
"loss": 1.6329,
"step": 150
},
{
"epoch": 0.12908741184013678,
"grad_norm": 2.036159038543701,
"learning_rate": 9.994218816398794e-06,
"loss": 1.6208,
"step": 151
},
{
"epoch": 0.1299422953622569,
"grad_norm": 2.751338005065918,
"learning_rate": 9.993873816233642e-06,
"loss": 1.593,
"step": 152
},
{
"epoch": 0.130797178884377,
"grad_norm": 3.4958271980285645,
"learning_rate": 9.993518824351593e-06,
"loss": 1.4269,
"step": 153
},
{
"epoch": 0.13165206240649713,
"grad_norm": 3.862670421600342,
"learning_rate": 9.993153841462912e-06,
"loss": 1.5538,
"step": 154
},
{
"epoch": 0.13250694592861723,
"grad_norm": 3.251422166824341,
"learning_rate": 9.992778868297855e-06,
"loss": 1.5283,
"step": 155
},
{
"epoch": 0.13336182945073732,
"grad_norm": 2.1368870735168457,
"learning_rate": 9.992393905606665e-06,
"loss": 1.7056,
"step": 156
},
{
"epoch": 0.13421671297285745,
"grad_norm": 2.3016269207000732,
"learning_rate": 9.991998954159574e-06,
"loss": 1.6743,
"step": 157
},
{
"epoch": 0.13507159649497755,
"grad_norm": 2.4640464782714844,
"learning_rate": 9.991594014746797e-06,
"loss": 1.6553,
"step": 158
},
{
"epoch": 0.13592648001709767,
"grad_norm": 2.2740697860717773,
"learning_rate": 9.991179088178538e-06,
"loss": 1.9916,
"step": 159
},
{
"epoch": 0.13678136353921777,
"grad_norm": 2.08636736869812,
"learning_rate": 9.99075417528498e-06,
"loss": 1.8245,
"step": 160
},
{
"epoch": 0.1376362470613379,
"grad_norm": 2.2464828491210938,
"learning_rate": 9.990319276916282e-06,
"loss": 1.4567,
"step": 161
},
{
"epoch": 0.138491130583458,
"grad_norm": 1.9842820167541504,
"learning_rate": 9.98987439394259e-06,
"loss": 1.7119,
"step": 162
},
{
"epoch": 0.13934601410557812,
"grad_norm": 2.2388288974761963,
"learning_rate": 9.989419527254025e-06,
"loss": 1.5563,
"step": 163
},
{
"epoch": 0.14020089762769822,
"grad_norm": 2.1352884769439697,
"learning_rate": 9.98895467776068e-06,
"loss": 1.7504,
"step": 164
},
{
"epoch": 0.14105578114981834,
"grad_norm": 2.172581672668457,
"learning_rate": 9.988479846392621e-06,
"loss": 1.6671,
"step": 165
},
{
"epoch": 0.14191066467193844,
"grad_norm": 2.1291165351867676,
"learning_rate": 9.987995034099891e-06,
"loss": 1.6297,
"step": 166
},
{
"epoch": 0.14276554819405857,
"grad_norm": 2.3043532371520996,
"learning_rate": 9.987500241852501e-06,
"loss": 1.4487,
"step": 167
},
{
"epoch": 0.14362043171617866,
"grad_norm": 2.1369128227233887,
"learning_rate": 9.986995470640426e-06,
"loss": 1.536,
"step": 168
},
{
"epoch": 0.1444753152382988,
"grad_norm": 2.52339768409729,
"learning_rate": 9.98648072147361e-06,
"loss": 1.651,
"step": 169
},
{
"epoch": 0.1453301987604189,
"grad_norm": 2.230353832244873,
"learning_rate": 9.985955995381961e-06,
"loss": 1.6593,
"step": 170
},
{
"epoch": 0.14618508228253901,
"grad_norm": 1.9805208444595337,
"learning_rate": 9.985421293415352e-06,
"loss": 1.6041,
"step": 171
},
{
"epoch": 0.1470399658046591,
"grad_norm": 2.5390121936798096,
"learning_rate": 9.984876616643605e-06,
"loss": 1.6453,
"step": 172
},
{
"epoch": 0.14789484932677924,
"grad_norm": 2.267672538757324,
"learning_rate": 9.984321966156511e-06,
"loss": 1.4635,
"step": 173
},
{
"epoch": 0.14874973284889934,
"grad_norm": 2.2240028381347656,
"learning_rate": 9.98375734306381e-06,
"loss": 1.5787,
"step": 174
},
{
"epoch": 0.14960461637101946,
"grad_norm": 2.0597617626190186,
"learning_rate": 9.9831827484952e-06,
"loss": 1.8143,
"step": 175
},
{
"epoch": 0.15045949989313956,
"grad_norm": 2.1702632904052734,
"learning_rate": 9.98259818360032e-06,
"loss": 1.3521,
"step": 176
},
{
"epoch": 0.15131438341525968,
"grad_norm": 2.1068551540374756,
"learning_rate": 9.982003649548773e-06,
"loss": 1.642,
"step": 177
},
{
"epoch": 0.15216926693737978,
"grad_norm": 2.5010616779327393,
"learning_rate": 9.981399147530095e-06,
"loss": 1.7123,
"step": 178
},
{
"epoch": 0.15302415045949988,
"grad_norm": 2.073054790496826,
"learning_rate": 9.98078467875377e-06,
"loss": 1.6237,
"step": 179
},
{
"epoch": 0.15387903398162,
"grad_norm": 2.0609512329101562,
"learning_rate": 9.980160244449225e-06,
"loss": 1.6043,
"step": 180
},
{
"epoch": 0.1547339175037401,
"grad_norm": 2.184964418411255,
"learning_rate": 9.979525845865826e-06,
"loss": 1.7787,
"step": 181
},
{
"epoch": 0.15558880102586023,
"grad_norm": 1.9945862293243408,
"learning_rate": 9.978881484272873e-06,
"loss": 1.573,
"step": 182
},
{
"epoch": 0.15644368454798033,
"grad_norm": 2.4625461101531982,
"learning_rate": 9.978227160959602e-06,
"loss": 1.486,
"step": 183
},
{
"epoch": 0.15729856807010045,
"grad_norm": 2.747724771499634,
"learning_rate": 9.977562877235178e-06,
"loss": 1.8208,
"step": 184
},
{
"epoch": 0.15815345159222055,
"grad_norm": 2.442047357559204,
"learning_rate": 9.976888634428699e-06,
"loss": 1.519,
"step": 185
},
{
"epoch": 0.15900833511434068,
"grad_norm": 2.035658836364746,
"learning_rate": 9.976204433889185e-06,
"loss": 1.7189,
"step": 186
},
{
"epoch": 0.15986321863646077,
"grad_norm": 1.9837456941604614,
"learning_rate": 9.975510276985581e-06,
"loss": 1.6247,
"step": 187
},
{
"epoch": 0.1607181021585809,
"grad_norm": 2.1273021697998047,
"learning_rate": 9.974806165106753e-06,
"loss": 1.588,
"step": 188
},
{
"epoch": 0.161572985680701,
"grad_norm": 2.254690647125244,
"learning_rate": 9.974092099661485e-06,
"loss": 1.4978,
"step": 189
},
{
"epoch": 0.16242786920282112,
"grad_norm": 2.070093870162964,
"learning_rate": 9.973368082078474e-06,
"loss": 1.5023,
"step": 190
},
{
"epoch": 0.16328275272494122,
"grad_norm": 2.2594425678253174,
"learning_rate": 9.972634113806332e-06,
"loss": 1.3271,
"step": 191
},
{
"epoch": 0.16413763624706135,
"grad_norm": 2.137816905975342,
"learning_rate": 9.971890196313578e-06,
"loss": 1.6029,
"step": 192
},
{
"epoch": 0.16499251976918144,
"grad_norm": 2.150294542312622,
"learning_rate": 9.971136331088638e-06,
"loss": 1.5479,
"step": 193
},
{
"epoch": 0.16584740329130157,
"grad_norm": 2.0613577365875244,
"learning_rate": 9.970372519639843e-06,
"loss": 1.6085,
"step": 194
},
{
"epoch": 0.16670228681342167,
"grad_norm": 2.489182233810425,
"learning_rate": 9.969598763495422e-06,
"loss": 1.5447,
"step": 195
},
{
"epoch": 0.1675571703355418,
"grad_norm": 1.9882975816726685,
"learning_rate": 9.968815064203503e-06,
"loss": 1.6983,
"step": 196
},
{
"epoch": 0.1684120538576619,
"grad_norm": 2.307633638381958,
"learning_rate": 9.968021423332106e-06,
"loss": 1.3364,
"step": 197
},
{
"epoch": 0.16926693737978202,
"grad_norm": 2.16860032081604,
"learning_rate": 9.967217842469144e-06,
"loss": 1.4998,
"step": 198
},
{
"epoch": 0.17012182090190212,
"grad_norm": 2.1140408515930176,
"learning_rate": 9.966404323222419e-06,
"loss": 1.7047,
"step": 199
},
{
"epoch": 0.1709767044240222,
"grad_norm": 2.0061354637145996,
"learning_rate": 9.965580867219615e-06,
"loss": 1.6829,
"step": 200
},
{
"epoch": 0.17183158794614234,
"grad_norm": 2.1682636737823486,
"learning_rate": 9.964747476108297e-06,
"loss": 1.599,
"step": 201
},
{
"epoch": 0.17268647146826244,
"grad_norm": 2.050809144973755,
"learning_rate": 9.963904151555913e-06,
"loss": 1.6234,
"step": 202
},
{
"epoch": 0.17354135499038256,
"grad_norm": 2.009514331817627,
"learning_rate": 9.963050895249779e-06,
"loss": 1.6771,
"step": 203
},
{
"epoch": 0.17439623851250266,
"grad_norm": 2.012481689453125,
"learning_rate": 9.962187708897088e-06,
"loss": 1.5752,
"step": 204
},
{
"epoch": 0.17525112203462279,
"grad_norm": 2.2250049114227295,
"learning_rate": 9.961314594224897e-06,
"loss": 1.6165,
"step": 205
},
{
"epoch": 0.17610600555674288,
"grad_norm": 2.289846658706665,
"learning_rate": 9.960431552980132e-06,
"loss": 1.5527,
"step": 206
},
{
"epoch": 0.176960889078863,
"grad_norm": 2.110806703567505,
"learning_rate": 9.959538586929576e-06,
"loss": 1.5558,
"step": 207
},
{
"epoch": 0.1778157726009831,
"grad_norm": 1.9617878198623657,
"learning_rate": 9.958635697859871e-06,
"loss": 1.6633,
"step": 208
},
{
"epoch": 0.17867065612310323,
"grad_norm": 2.2823057174682617,
"learning_rate": 9.95772288757751e-06,
"loss": 1.6224,
"step": 209
},
{
"epoch": 0.17952553964522333,
"grad_norm": 1.9670095443725586,
"learning_rate": 9.956800157908843e-06,
"loss": 1.8749,
"step": 210
},
{
"epoch": 0.18038042316734346,
"grad_norm": 2.7742271423339844,
"learning_rate": 9.955867510700064e-06,
"loss": 1.486,
"step": 211
},
{
"epoch": 0.18123530668946355,
"grad_norm": 2.0588271617889404,
"learning_rate": 9.954924947817202e-06,
"loss": 1.5673,
"step": 212
},
{
"epoch": 0.18209019021158368,
"grad_norm": 1.9455853700637817,
"learning_rate": 9.953972471146139e-06,
"loss": 1.5381,
"step": 213
},
{
"epoch": 0.18294507373370378,
"grad_norm": 2.869638442993164,
"learning_rate": 9.95301008259258e-06,
"loss": 1.5812,
"step": 214
},
{
"epoch": 0.1837999572558239,
"grad_norm": 2.755342960357666,
"learning_rate": 9.952037784082069e-06,
"loss": 1.7378,
"step": 215
},
{
"epoch": 0.184654840777944,
"grad_norm": 2.0044925212860107,
"learning_rate": 9.951055577559978e-06,
"loss": 1.6928,
"step": 216
},
{
"epoch": 0.18550972430006413,
"grad_norm": 1.9753495454788208,
"learning_rate": 9.950063464991498e-06,
"loss": 1.6793,
"step": 217
},
{
"epoch": 0.18636460782218423,
"grad_norm": 2.6321005821228027,
"learning_rate": 9.949061448361645e-06,
"loss": 1.8052,
"step": 218
},
{
"epoch": 0.18721949134430435,
"grad_norm": 1.9599953889846802,
"learning_rate": 9.948049529675246e-06,
"loss": 1.6699,
"step": 219
},
{
"epoch": 0.18807437486642445,
"grad_norm": 2.058579444885254,
"learning_rate": 9.947027710956944e-06,
"loss": 1.5779,
"step": 220
},
{
"epoch": 0.18892925838854457,
"grad_norm": 1.9399949312210083,
"learning_rate": 9.945995994251189e-06,
"loss": 1.7076,
"step": 221
},
{
"epoch": 0.18978414191066467,
"grad_norm": 2.8098912239074707,
"learning_rate": 9.944954381622234e-06,
"loss": 1.5293,
"step": 222
},
{
"epoch": 0.19063902543278477,
"grad_norm": 2.3304898738861084,
"learning_rate": 9.943902875154133e-06,
"loss": 1.5303,
"step": 223
},
{
"epoch": 0.1914939089549049,
"grad_norm": 1.800581693649292,
"learning_rate": 9.94284147695073e-06,
"loss": 1.871,
"step": 224
},
{
"epoch": 0.192348792477025,
"grad_norm": 1.8096035718917847,
"learning_rate": 9.941770189135674e-06,
"loss": 1.6497,
"step": 225
},
{
"epoch": 0.19320367599914512,
"grad_norm": 2.4061684608459473,
"learning_rate": 9.940689013852385e-06,
"loss": 1.3758,
"step": 226
},
{
"epoch": 0.19405855952126522,
"grad_norm": 2.075972557067871,
"learning_rate": 9.939597953264075e-06,
"loss": 1.6361,
"step": 227
},
{
"epoch": 0.19491344304338534,
"grad_norm": 1.9757728576660156,
"learning_rate": 9.938497009553732e-06,
"loss": 1.6045,
"step": 228
},
{
"epoch": 0.19576832656550544,
"grad_norm": 2.0147316455841064,
"learning_rate": 9.937386184924119e-06,
"loss": 1.718,
"step": 229
},
{
"epoch": 0.19662321008762557,
"grad_norm": 4.8961334228515625,
"learning_rate": 9.93626548159777e-06,
"loss": 1.8579,
"step": 230
},
{
"epoch": 0.19747809360974566,
"grad_norm": 3.387730836868286,
"learning_rate": 9.935134901816977e-06,
"loss": 1.4704,
"step": 231
},
{
"epoch": 0.1983329771318658,
"grad_norm": 3.4209892749786377,
"learning_rate": 9.933994447843804e-06,
"loss": 1.7328,
"step": 232
},
{
"epoch": 0.1991878606539859,
"grad_norm": 2.224865436553955,
"learning_rate": 9.932844121960062e-06,
"loss": 1.5973,
"step": 233
},
{
"epoch": 0.200042744176106,
"grad_norm": 2.7523677349090576,
"learning_rate": 9.931683926467318e-06,
"loss": 1.4736,
"step": 234
},
{
"epoch": 0.2008976276982261,
"grad_norm": 2.1172382831573486,
"learning_rate": 9.930513863686885e-06,
"loss": 1.5492,
"step": 235
},
{
"epoch": 0.20175251122034624,
"grad_norm": 2.0145204067230225,
"learning_rate": 9.92933393595982e-06,
"loss": 1.7651,
"step": 236
},
{
"epoch": 0.20260739474246633,
"grad_norm": 1.7892417907714844,
"learning_rate": 9.928144145646915e-06,
"loss": 1.8183,
"step": 237
},
{
"epoch": 0.20346227826458646,
"grad_norm": 2.0646109580993652,
"learning_rate": 9.926944495128696e-06,
"loss": 1.6102,
"step": 238
},
{
"epoch": 0.20431716178670656,
"grad_norm": 2.2819433212280273,
"learning_rate": 9.925734986805418e-06,
"loss": 1.7732,
"step": 239
},
{
"epoch": 0.20517204530882668,
"grad_norm": 1.963572382926941,
"learning_rate": 9.924515623097059e-06,
"loss": 1.786,
"step": 240
},
{
"epoch": 0.20602692883094678,
"grad_norm": 2.0390403270721436,
"learning_rate": 9.923286406443315e-06,
"loss": 1.6186,
"step": 241
},
{
"epoch": 0.2068818123530669,
"grad_norm": 2.267930507659912,
"learning_rate": 9.922047339303597e-06,
"loss": 1.5218,
"step": 242
},
{
"epoch": 0.207736695875187,
"grad_norm": 1.9752867221832275,
"learning_rate": 9.920798424157025e-06,
"loss": 1.874,
"step": 243
},
{
"epoch": 0.2085915793973071,
"grad_norm": 2.595473289489746,
"learning_rate": 9.91953966350242e-06,
"loss": 1.6422,
"step": 244
},
{
"epoch": 0.20944646291942723,
"grad_norm": 2.4579105377197266,
"learning_rate": 9.918271059858304e-06,
"loss": 1.539,
"step": 245
},
{
"epoch": 0.21030134644154733,
"grad_norm": 2.0564873218536377,
"learning_rate": 9.916992615762895e-06,
"loss": 1.5645,
"step": 246
},
{
"epoch": 0.21115622996366745,
"grad_norm": 2.313728094100952,
"learning_rate": 9.915704333774095e-06,
"loss": 1.5913,
"step": 247
},
{
"epoch": 0.21201111348578755,
"grad_norm": 2.0686261653900146,
"learning_rate": 9.914406216469493e-06,
"loss": 1.6991,
"step": 248
},
{
"epoch": 0.21286599700790768,
"grad_norm": 1.7527450323104858,
"learning_rate": 9.913098266446354e-06,
"loss": 1.5427,
"step": 249
},
{
"epoch": 0.21372088053002777,
"grad_norm": 1.9648592472076416,
"learning_rate": 9.911780486321618e-06,
"loss": 1.5907,
"step": 250
},
{
"epoch": 0.2145757640521479,
"grad_norm": 2.190805196762085,
"learning_rate": 9.910452878731895e-06,
"loss": 1.5391,
"step": 251
},
{
"epoch": 0.215430647574268,
"grad_norm": 2.548785924911499,
"learning_rate": 9.909115446333453e-06,
"loss": 1.823,
"step": 252
},
{
"epoch": 0.21628553109638812,
"grad_norm": 2.668999671936035,
"learning_rate": 9.907768191802221e-06,
"loss": 1.4534,
"step": 253
},
{
"epoch": 0.21714041461850822,
"grad_norm": 1.8880456686019897,
"learning_rate": 9.906411117833778e-06,
"loss": 1.9095,
"step": 254
},
{
"epoch": 0.21799529814062835,
"grad_norm": 2.0296988487243652,
"learning_rate": 9.905044227143351e-06,
"loss": 1.5362,
"step": 255
},
{
"epoch": 0.21885018166274844,
"grad_norm": 1.850406289100647,
"learning_rate": 9.90366752246581e-06,
"loss": 1.5792,
"step": 256
},
{
"epoch": 0.21970506518486857,
"grad_norm": 2.1268975734710693,
"learning_rate": 9.902281006555654e-06,
"loss": 1.732,
"step": 257
},
{
"epoch": 0.22055994870698867,
"grad_norm": 2.0648953914642334,
"learning_rate": 9.90088468218702e-06,
"loss": 1.5056,
"step": 258
},
{
"epoch": 0.2214148322291088,
"grad_norm": 2.415849447250366,
"learning_rate": 9.899478552153665e-06,
"loss": 1.5931,
"step": 259
},
{
"epoch": 0.2222697157512289,
"grad_norm": 2.0099523067474365,
"learning_rate": 9.89806261926897e-06,
"loss": 1.6716,
"step": 260
},
{
"epoch": 0.22312459927334902,
"grad_norm": 2.1277308464050293,
"learning_rate": 9.896636886365921e-06,
"loss": 1.5538,
"step": 261
},
{
"epoch": 0.22397948279546911,
"grad_norm": 1.9735395908355713,
"learning_rate": 9.895201356297122e-06,
"loss": 1.6561,
"step": 262
},
{
"epoch": 0.22483436631758924,
"grad_norm": 2.20600962638855,
"learning_rate": 9.89375603193477e-06,
"loss": 1.7162,
"step": 263
},
{
"epoch": 0.22568924983970934,
"grad_norm": 2.5070505142211914,
"learning_rate": 9.892300916170665e-06,
"loss": 1.5809,
"step": 264
},
{
"epoch": 0.22654413336182946,
"grad_norm": 2.2711572647094727,
"learning_rate": 9.890836011916194e-06,
"loss": 1.5735,
"step": 265
},
{
"epoch": 0.22739901688394956,
"grad_norm": 2.1966934204101562,
"learning_rate": 9.88936132210233e-06,
"loss": 1.7117,
"step": 266
},
{
"epoch": 0.22825390040606966,
"grad_norm": 2.4135377407073975,
"learning_rate": 9.887876849679627e-06,
"loss": 1.4651,
"step": 267
},
{
"epoch": 0.22910878392818979,
"grad_norm": 1.9522583484649658,
"learning_rate": 9.886382597618207e-06,
"loss": 1.6792,
"step": 268
},
{
"epoch": 0.22996366745030988,
"grad_norm": 2.727830171585083,
"learning_rate": 9.884878568907764e-06,
"loss": 1.5722,
"step": 269
},
{
"epoch": 0.23081855097243,
"grad_norm": 2.306396245956421,
"learning_rate": 9.883364766557549e-06,
"loss": 1.6057,
"step": 270
},
{
"epoch": 0.2316734344945501,
"grad_norm": 2.0543172359466553,
"learning_rate": 9.88184119359637e-06,
"loss": 1.5904,
"step": 271
},
{
"epoch": 0.23252831801667023,
"grad_norm": 1.944240927696228,
"learning_rate": 9.880307853072582e-06,
"loss": 1.5547,
"step": 272
},
{
"epoch": 0.23338320153879033,
"grad_norm": 1.8696750402450562,
"learning_rate": 9.878764748054089e-06,
"loss": 1.611,
"step": 273
},
{
"epoch": 0.23423808506091046,
"grad_norm": 1.9814125299453735,
"learning_rate": 9.877211881628325e-06,
"loss": 1.5352,
"step": 274
},
{
"epoch": 0.23509296858303055,
"grad_norm": 4.211121559143066,
"learning_rate": 9.87564925690226e-06,
"loss": 1.6153,
"step": 275
},
{
"epoch": 0.23594785210515068,
"grad_norm": 3.5215139389038086,
"learning_rate": 9.874076877002381e-06,
"loss": 1.4883,
"step": 276
},
{
"epoch": 0.23680273562727078,
"grad_norm": 2.044966459274292,
"learning_rate": 9.872494745074701e-06,
"loss": 1.5476,
"step": 277
},
{
"epoch": 0.2376576191493909,
"grad_norm": 2.230739116668701,
"learning_rate": 9.87090286428474e-06,
"loss": 1.5347,
"step": 278
},
{
"epoch": 0.238512502671511,
"grad_norm": 7.256809234619141,
"learning_rate": 9.869301237817524e-06,
"loss": 1.7037,
"step": 279
},
{
"epoch": 0.23936738619363113,
"grad_norm": 2.069016218185425,
"learning_rate": 9.867689868877582e-06,
"loss": 1.6771,
"step": 280
},
{
"epoch": 0.24022226971575122,
"grad_norm": 2.5683460235595703,
"learning_rate": 9.866068760688929e-06,
"loss": 1.5833,
"step": 281
},
{
"epoch": 0.24107715323787135,
"grad_norm": 2.004464864730835,
"learning_rate": 9.864437916495073e-06,
"loss": 1.6213,
"step": 282
},
{
"epoch": 0.24193203675999145,
"grad_norm": 2.210275411605835,
"learning_rate": 9.862797339558995e-06,
"loss": 1.5354,
"step": 283
},
{
"epoch": 0.24278692028211157,
"grad_norm": 2.1438090801239014,
"learning_rate": 9.861147033163156e-06,
"loss": 1.6764,
"step": 284
},
{
"epoch": 0.24364180380423167,
"grad_norm": 1.9565024375915527,
"learning_rate": 9.85948700060948e-06,
"loss": 1.6768,
"step": 285
},
{
"epoch": 0.2444966873263518,
"grad_norm": 2.793376922607422,
"learning_rate": 9.85781724521935e-06,
"loss": 1.5542,
"step": 286
},
{
"epoch": 0.2453515708484719,
"grad_norm": 2.833108425140381,
"learning_rate": 9.856137770333606e-06,
"loss": 1.6302,
"step": 287
},
{
"epoch": 0.24620645437059202,
"grad_norm": 2.1430552005767822,
"learning_rate": 9.85444857931253e-06,
"loss": 1.6496,
"step": 288
},
{
"epoch": 0.24706133789271212,
"grad_norm": 1.821040153503418,
"learning_rate": 9.85274967553585e-06,
"loss": 1.6246,
"step": 289
},
{
"epoch": 0.24791622141483222,
"grad_norm": 2.6233530044555664,
"learning_rate": 9.851041062402721e-06,
"loss": 1.4109,
"step": 290
},
{
"epoch": 0.24877110493695234,
"grad_norm": 1.9718334674835205,
"learning_rate": 9.849322743331731e-06,
"loss": 1.6219,
"step": 291
},
{
"epoch": 0.24962598845907244,
"grad_norm": 1.8950848579406738,
"learning_rate": 9.847594721760878e-06,
"loss": 1.6511,
"step": 292
},
{
"epoch": 0.25048087198119257,
"grad_norm": 2.438082218170166,
"learning_rate": 9.845857001147585e-06,
"loss": 1.5432,
"step": 293
},
{
"epoch": 0.25048087198119257,
"eval_loss": 1.6429485082626343,
"eval_runtime": 535.3503,
"eval_samples_per_second": 7.39,
"eval_steps_per_second": 3.695,
"step": 293
},
{
"epoch": 0.25133575550331266,
"grad_norm": 2.273573398590088,
"learning_rate": 9.844109584968669e-06,
"loss": 1.5812,
"step": 294
},
{
"epoch": 0.25219063902543276,
"grad_norm": 1.8384723663330078,
"learning_rate": 9.842352476720354e-06,
"loss": 1.6735,
"step": 295
},
{
"epoch": 0.2530455225475529,
"grad_norm": 1.9818137884140015,
"learning_rate": 9.840585679918254e-06,
"loss": 1.7463,
"step": 296
},
{
"epoch": 0.253900406069673,
"grad_norm": 2.039534568786621,
"learning_rate": 9.838809198097365e-06,
"loss": 1.6754,
"step": 297
},
{
"epoch": 0.2547552895917931,
"grad_norm": 3.1951630115509033,
"learning_rate": 9.837023034812064e-06,
"loss": 1.5875,
"step": 298
},
{
"epoch": 0.2556101731139132,
"grad_norm": 2.5072474479675293,
"learning_rate": 9.835227193636096e-06,
"loss": 1.4731,
"step": 299
},
{
"epoch": 0.25646505663603336,
"grad_norm": 1.7682746648788452,
"learning_rate": 9.83342167816257e-06,
"loss": 1.6874,
"step": 300
},
{
"epoch": 0.25731994015815346,
"grad_norm": 2.0054051876068115,
"learning_rate": 9.831606492003955e-06,
"loss": 1.7077,
"step": 301
},
{
"epoch": 0.25817482368027356,
"grad_norm": 1.800396203994751,
"learning_rate": 9.829781638792064e-06,
"loss": 1.714,
"step": 302
},
{
"epoch": 0.25902970720239366,
"grad_norm": 2.194918394088745,
"learning_rate": 9.827947122178055e-06,
"loss": 1.6603,
"step": 303
},
{
"epoch": 0.2598845907245138,
"grad_norm": 2.0959277153015137,
"learning_rate": 9.826102945832418e-06,
"loss": 1.6439,
"step": 304
},
{
"epoch": 0.2607394742466339,
"grad_norm": 2.1359193325042725,
"learning_rate": 9.824249113444973e-06,
"loss": 1.6057,
"step": 305
},
{
"epoch": 0.261594357768754,
"grad_norm": 1.9840806722640991,
"learning_rate": 9.822385628724855e-06,
"loss": 1.5768,
"step": 306
},
{
"epoch": 0.2624492412908741,
"grad_norm": 1.8947420120239258,
"learning_rate": 9.82051249540052e-06,
"loss": 1.6567,
"step": 307
},
{
"epoch": 0.26330412481299426,
"grad_norm": 1.949657678604126,
"learning_rate": 9.818629717219719e-06,
"loss": 1.6144,
"step": 308
},
{
"epoch": 0.26415900833511435,
"grad_norm": 2.000495195388794,
"learning_rate": 9.816737297949506e-06,
"loss": 1.671,
"step": 309
},
{
"epoch": 0.26501389185723445,
"grad_norm": 2.1426568031311035,
"learning_rate": 9.814835241376223e-06,
"loss": 1.7611,
"step": 310
},
{
"epoch": 0.26586877537935455,
"grad_norm": 1.849526047706604,
"learning_rate": 9.812923551305497e-06,
"loss": 1.67,
"step": 311
},
{
"epoch": 0.26672365890147465,
"grad_norm": 1.818123459815979,
"learning_rate": 9.811002231562228e-06,
"loss": 1.5275,
"step": 312
},
{
"epoch": 0.2675785424235948,
"grad_norm": 2.141369104385376,
"learning_rate": 9.80907128599058e-06,
"loss": 1.4483,
"step": 313
},
{
"epoch": 0.2684334259457149,
"grad_norm": 1.8215101957321167,
"learning_rate": 9.80713071845398e-06,
"loss": 1.4223,
"step": 314
},
{
"epoch": 0.269288309467835,
"grad_norm": 1.7793519496917725,
"learning_rate": 9.805180532835104e-06,
"loss": 1.8701,
"step": 315
},
{
"epoch": 0.2701431929899551,
"grad_norm": 2.3831069469451904,
"learning_rate": 9.803220733035876e-06,
"loss": 1.5475,
"step": 316
},
{
"epoch": 0.27099807651207525,
"grad_norm": 2.3979852199554443,
"learning_rate": 9.801251322977454e-06,
"loss": 1.7673,
"step": 317
},
{
"epoch": 0.27185296003419535,
"grad_norm": 2.326536178588867,
"learning_rate": 9.799272306600219e-06,
"loss": 1.776,
"step": 318
},
{
"epoch": 0.27270784355631544,
"grad_norm": 2.0572667121887207,
"learning_rate": 9.79728368786378e-06,
"loss": 1.597,
"step": 319
},
{
"epoch": 0.27356272707843554,
"grad_norm": 2.6097846031188965,
"learning_rate": 9.795285470746954e-06,
"loss": 1.5121,
"step": 320
},
{
"epoch": 0.2744176106005557,
"grad_norm": 2.138073682785034,
"learning_rate": 9.793277659247764e-06,
"loss": 1.5842,
"step": 321
},
{
"epoch": 0.2752724941226758,
"grad_norm": 1.9335135221481323,
"learning_rate": 9.79126025738343e-06,
"loss": 1.678,
"step": 322
},
{
"epoch": 0.2761273776447959,
"grad_norm": 1.9786878824234009,
"learning_rate": 9.789233269190357e-06,
"loss": 1.634,
"step": 323
},
{
"epoch": 0.276982261166916,
"grad_norm": 1.932175636291504,
"learning_rate": 9.787196698724133e-06,
"loss": 1.6037,
"step": 324
},
{
"epoch": 0.27783714468903614,
"grad_norm": 2.077538013458252,
"learning_rate": 9.785150550059519e-06,
"loss": 1.5051,
"step": 325
},
{
"epoch": 0.27869202821115624,
"grad_norm": 1.9720157384872437,
"learning_rate": 9.783094827290439e-06,
"loss": 1.5322,
"step": 326
},
{
"epoch": 0.27954691173327634,
"grad_norm": 1.9299103021621704,
"learning_rate": 9.781029534529968e-06,
"loss": 1.6145,
"step": 327
},
{
"epoch": 0.28040179525539644,
"grad_norm": 2.12306547164917,
"learning_rate": 9.778954675910337e-06,
"loss": 1.6878,
"step": 328
},
{
"epoch": 0.2812566787775166,
"grad_norm": 1.9829449653625488,
"learning_rate": 9.776870255582913e-06,
"loss": 1.7578,
"step": 329
},
{
"epoch": 0.2821115622996367,
"grad_norm": 2.2889063358306885,
"learning_rate": 9.774776277718193e-06,
"loss": 1.4426,
"step": 330
},
{
"epoch": 0.2829664458217568,
"grad_norm": 2.5552847385406494,
"learning_rate": 9.772672746505794e-06,
"loss": 1.8471,
"step": 331
},
{
"epoch": 0.2838213293438769,
"grad_norm": 2.1380834579467773,
"learning_rate": 9.770559666154454e-06,
"loss": 1.5864,
"step": 332
},
{
"epoch": 0.284676212865997,
"grad_norm": 2.1155436038970947,
"learning_rate": 9.76843704089201e-06,
"loss": 1.6244,
"step": 333
},
{
"epoch": 0.28553109638811713,
"grad_norm": 1.8792701959609985,
"learning_rate": 9.766304874965403e-06,
"loss": 1.7114,
"step": 334
},
{
"epoch": 0.28638597991023723,
"grad_norm": 2.630060911178589,
"learning_rate": 9.764163172640657e-06,
"loss": 1.704,
"step": 335
},
{
"epoch": 0.28724086343235733,
"grad_norm": 2.6928205490112305,
"learning_rate": 9.76201193820288e-06,
"loss": 1.4833,
"step": 336
},
{
"epoch": 0.2880957469544774,
"grad_norm": 1.9738703966140747,
"learning_rate": 9.759851175956252e-06,
"loss": 1.7405,
"step": 337
},
{
"epoch": 0.2889506304765976,
"grad_norm": 1.8967580795288086,
"learning_rate": 9.757680890224013e-06,
"loss": 1.6763,
"step": 338
},
{
"epoch": 0.2898055139987177,
"grad_norm": 1.9165318012237549,
"learning_rate": 9.75550108534846e-06,
"loss": 1.6598,
"step": 339
},
{
"epoch": 0.2906603975208378,
"grad_norm": 1.984978437423706,
"learning_rate": 9.753311765690935e-06,
"loss": 1.5119,
"step": 340
},
{
"epoch": 0.2915152810429579,
"grad_norm": 1.8836838006973267,
"learning_rate": 9.751112935631816e-06,
"loss": 1.6941,
"step": 341
},
{
"epoch": 0.29237016456507803,
"grad_norm": 1.778017520904541,
"learning_rate": 9.748904599570517e-06,
"loss": 1.6655,
"step": 342
},
{
"epoch": 0.2932250480871981,
"grad_norm": 2.1019034385681152,
"learning_rate": 9.746686761925456e-06,
"loss": 1.6087,
"step": 343
},
{
"epoch": 0.2940799316093182,
"grad_norm": 2.2590184211730957,
"learning_rate": 9.744459427134081e-06,
"loss": 1.3935,
"step": 344
},
{
"epoch": 0.2949348151314383,
"grad_norm": 1.9555338621139526,
"learning_rate": 9.742222599652824e-06,
"loss": 1.6565,
"step": 345
},
{
"epoch": 0.2957896986535585,
"grad_norm": 1.791080355644226,
"learning_rate": 9.739976283957122e-06,
"loss": 1.7648,
"step": 346
},
{
"epoch": 0.2966445821756786,
"grad_norm": 2.701005697250366,
"learning_rate": 9.737720484541389e-06,
"loss": 1.6442,
"step": 347
},
{
"epoch": 0.29749946569779867,
"grad_norm": 2.1853907108306885,
"learning_rate": 9.735455205919019e-06,
"loss": 1.5882,
"step": 348
},
{
"epoch": 0.29835434921991877,
"grad_norm": 2.8202414512634277,
"learning_rate": 9.733180452622371e-06,
"loss": 1.6558,
"step": 349
},
{
"epoch": 0.2992092327420389,
"grad_norm": 1.9966498613357544,
"learning_rate": 9.730896229202756e-06,
"loss": 1.5792,
"step": 350
},
{
"epoch": 0.300064116264159,
"grad_norm": 1.8057630062103271,
"learning_rate": 9.72860254023044e-06,
"loss": 1.8001,
"step": 351
},
{
"epoch": 0.3009189997862791,
"grad_norm": 1.988755702972412,
"learning_rate": 9.726299390294621e-06,
"loss": 1.8377,
"step": 352
},
{
"epoch": 0.3017738833083992,
"grad_norm": 1.7807461023330688,
"learning_rate": 9.72398678400343e-06,
"loss": 1.6874,
"step": 353
},
{
"epoch": 0.30262876683051937,
"grad_norm": 2.122286081314087,
"learning_rate": 9.72166472598392e-06,
"loss": 1.4228,
"step": 354
},
{
"epoch": 0.30348365035263947,
"grad_norm": 2.2886228561401367,
"learning_rate": 9.719333220882051e-06,
"loss": 1.7398,
"step": 355
},
{
"epoch": 0.30433853387475956,
"grad_norm": 1.948338270187378,
"learning_rate": 9.716992273362686e-06,
"loss": 1.5523,
"step": 356
},
{
"epoch": 0.30519341739687966,
"grad_norm": 1.9473958015441895,
"learning_rate": 9.714641888109582e-06,
"loss": 1.7423,
"step": 357
},
{
"epoch": 0.30604830091899976,
"grad_norm": 2.157661199569702,
"learning_rate": 9.712282069825375e-06,
"loss": 1.3287,
"step": 358
},
{
"epoch": 0.3069031844411199,
"grad_norm": 3.0535852909088135,
"learning_rate": 9.70991282323158e-06,
"loss": 1.5311,
"step": 359
},
{
"epoch": 0.30775806796324,
"grad_norm": 1.8765023946762085,
"learning_rate": 9.707534153068574e-06,
"loss": 1.7105,
"step": 360
},
{
"epoch": 0.3086129514853601,
"grad_norm": 2.0064175128936768,
"learning_rate": 9.705146064095585e-06,
"loss": 1.6531,
"step": 361
},
{
"epoch": 0.3094678350074802,
"grad_norm": 1.9886373281478882,
"learning_rate": 9.70274856109069e-06,
"loss": 1.4997,
"step": 362
},
{
"epoch": 0.31032271852960036,
"grad_norm": 1.990229606628418,
"learning_rate": 9.700341648850802e-06,
"loss": 1.5256,
"step": 363
},
{
"epoch": 0.31117760205172046,
"grad_norm": 2.106940507888794,
"learning_rate": 9.697925332191656e-06,
"loss": 1.7129,
"step": 364
},
{
"epoch": 0.31203248557384056,
"grad_norm": 1.7736214399337769,
"learning_rate": 9.695499615947808e-06,
"loss": 1.6478,
"step": 365
},
{
"epoch": 0.31288736909596065,
"grad_norm": 2.1179401874542236,
"learning_rate": 9.693064504972619e-06,
"loss": 1.5524,
"step": 366
},
{
"epoch": 0.3137422526180808,
"grad_norm": 1.916581392288208,
"learning_rate": 9.690620004138245e-06,
"loss": 1.6106,
"step": 367
},
{
"epoch": 0.3145971361402009,
"grad_norm": 1.9544050693511963,
"learning_rate": 9.68816611833563e-06,
"loss": 1.4856,
"step": 368
},
{
"epoch": 0.315452019662321,
"grad_norm": 1.9140318632125854,
"learning_rate": 9.685702852474499e-06,
"loss": 1.5316,
"step": 369
},
{
"epoch": 0.3163069031844411,
"grad_norm": 2.6337473392486572,
"learning_rate": 9.683230211483337e-06,
"loss": 1.6554,
"step": 370
},
{
"epoch": 0.31716178670656126,
"grad_norm": 4.639531135559082,
"learning_rate": 9.680748200309396e-06,
"loss": 1.6353,
"step": 371
},
{
"epoch": 0.31801667022868135,
"grad_norm": 2.012089967727661,
"learning_rate": 9.678256823918668e-06,
"loss": 1.5873,
"step": 372
},
{
"epoch": 0.31887155375080145,
"grad_norm": 2.249965190887451,
"learning_rate": 9.67575608729589e-06,
"loss": 1.5251,
"step": 373
},
{
"epoch": 0.31972643727292155,
"grad_norm": 2.2432241439819336,
"learning_rate": 9.673245995444516e-06,
"loss": 1.5292,
"step": 374
},
{
"epoch": 0.3205813207950417,
"grad_norm": 1.8957768678665161,
"learning_rate": 9.67072655338673e-06,
"loss": 1.542,
"step": 375
},
{
"epoch": 0.3214362043171618,
"grad_norm": 2.318333148956299,
"learning_rate": 9.668197766163417e-06,
"loss": 1.6483,
"step": 376
},
{
"epoch": 0.3222910878392819,
"grad_norm": 1.8972350358963013,
"learning_rate": 9.665659638834162e-06,
"loss": 1.7009,
"step": 377
},
{
"epoch": 0.323145971361402,
"grad_norm": 1.7293806076049805,
"learning_rate": 9.663112176477238e-06,
"loss": 1.7716,
"step": 378
},
{
"epoch": 0.3240008548835221,
"grad_norm": 1.9904060363769531,
"learning_rate": 9.660555384189592e-06,
"loss": 1.6335,
"step": 379
},
{
"epoch": 0.32485573840564225,
"grad_norm": 1.9652825593948364,
"learning_rate": 9.657989267086842e-06,
"loss": 1.5519,
"step": 380
},
{
"epoch": 0.32571062192776234,
"grad_norm": 2.0220279693603516,
"learning_rate": 9.655413830303264e-06,
"loss": 1.5513,
"step": 381
},
{
"epoch": 0.32656550544988244,
"grad_norm": 1.9460409879684448,
"learning_rate": 9.652829078991775e-06,
"loss": 1.4417,
"step": 382
},
{
"epoch": 0.32742038897200254,
"grad_norm": 1.9341466426849365,
"learning_rate": 9.650235018323932e-06,
"loss": 1.5433,
"step": 383
},
{
"epoch": 0.3282752724941227,
"grad_norm": 1.7564873695373535,
"learning_rate": 9.647631653489922e-06,
"loss": 1.7237,
"step": 384
},
{
"epoch": 0.3291301560162428,
"grad_norm": 1.9628024101257324,
"learning_rate": 9.645018989698541e-06,
"loss": 1.7277,
"step": 385
},
{
"epoch": 0.3299850395383629,
"grad_norm": 2.3082334995269775,
"learning_rate": 9.642397032177194e-06,
"loss": 1.5495,
"step": 386
},
{
"epoch": 0.330839923060483,
"grad_norm": 1.866422414779663,
"learning_rate": 9.63976578617188e-06,
"loss": 1.7534,
"step": 387
},
{
"epoch": 0.33169480658260314,
"grad_norm": 2.317007541656494,
"learning_rate": 9.637125256947182e-06,
"loss": 1.5052,
"step": 388
},
{
"epoch": 0.33254969010472324,
"grad_norm": 1.8729028701782227,
"learning_rate": 9.634475449786256e-06,
"loss": 1.8099,
"step": 389
},
{
"epoch": 0.33340457362684334,
"grad_norm": 2.69675874710083,
"learning_rate": 9.631816369990826e-06,
"loss": 1.7547,
"step": 390
},
{
"epoch": 0.33425945714896343,
"grad_norm": 1.989051103591919,
"learning_rate": 9.629148022881162e-06,
"loss": 1.3242,
"step": 391
},
{
"epoch": 0.3351143406710836,
"grad_norm": 1.821259617805481,
"learning_rate": 9.62647041379608e-06,
"loss": 1.7114,
"step": 392
},
{
"epoch": 0.3359692241932037,
"grad_norm": 2.20082688331604,
"learning_rate": 9.623783548092927e-06,
"loss": 1.6421,
"step": 393
},
{
"epoch": 0.3368241077153238,
"grad_norm": 2.1007845401763916,
"learning_rate": 9.621087431147571e-06,
"loss": 1.5982,
"step": 394
},
{
"epoch": 0.3376789912374439,
"grad_norm": 1.973475456237793,
"learning_rate": 9.618382068354385e-06,
"loss": 1.4475,
"step": 395
},
{
"epoch": 0.33853387475956404,
"grad_norm": 2.067143201828003,
"learning_rate": 9.615667465126249e-06,
"loss": 1.5659,
"step": 396
},
{
"epoch": 0.33938875828168413,
"grad_norm": 4.515519142150879,
"learning_rate": 9.612943626894524e-06,
"loss": 1.5314,
"step": 397
},
{
"epoch": 0.34024364180380423,
"grad_norm": 2.152055501937866,
"learning_rate": 9.610210559109053e-06,
"loss": 1.6649,
"step": 398
},
{
"epoch": 0.34109852532592433,
"grad_norm": 1.7932733297348022,
"learning_rate": 9.607468267238144e-06,
"loss": 1.623,
"step": 399
},
{
"epoch": 0.3419534088480444,
"grad_norm": 2.0391805171966553,
"learning_rate": 9.60471675676856e-06,
"loss": 1.3268,
"step": 400
},
{
"epoch": 0.3428082923701646,
"grad_norm": 1.702877163887024,
"learning_rate": 9.60195603320551e-06,
"loss": 1.7459,
"step": 401
},
{
"epoch": 0.3436631758922847,
"grad_norm": 2.219301700592041,
"learning_rate": 9.599186102072633e-06,
"loss": 1.4155,
"step": 402
},
{
"epoch": 0.3445180594144048,
"grad_norm": 2.3838083744049072,
"learning_rate": 9.596406968911994e-06,
"loss": 1.6431,
"step": 403
},
{
"epoch": 0.3453729429365249,
"grad_norm": 1.8397514820098877,
"learning_rate": 9.59361863928407e-06,
"loss": 1.6565,
"step": 404
},
{
"epoch": 0.346227826458645,
"grad_norm": 1.9715574979782104,
"learning_rate": 9.590821118767735e-06,
"loss": 1.5712,
"step": 405
},
{
"epoch": 0.3470827099807651,
"grad_norm": 1.8566009998321533,
"learning_rate": 9.588014412960251e-06,
"loss": 1.4365,
"step": 406
},
{
"epoch": 0.3479375935028852,
"grad_norm": 2.3083534240722656,
"learning_rate": 9.585198527477266e-06,
"loss": 1.6871,
"step": 407
},
{
"epoch": 0.3487924770250053,
"grad_norm": 2.463879346847534,
"learning_rate": 9.582373467952785e-06,
"loss": 1.347,
"step": 408
},
{
"epoch": 0.3496473605471255,
"grad_norm": 1.7422118186950684,
"learning_rate": 9.579539240039175e-06,
"loss": 1.6822,
"step": 409
},
{
"epoch": 0.35050224406924557,
"grad_norm": 3.396388292312622,
"learning_rate": 9.576695849407142e-06,
"loss": 1.4162,
"step": 410
},
{
"epoch": 0.35135712759136567,
"grad_norm": 1.8444187641143799,
"learning_rate": 9.573843301745729e-06,
"loss": 1.49,
"step": 411
},
{
"epoch": 0.35221201111348577,
"grad_norm": 1.8690928220748901,
"learning_rate": 9.570981602762298e-06,
"loss": 1.677,
"step": 412
},
{
"epoch": 0.3530668946356059,
"grad_norm": 1.8715145587921143,
"learning_rate": 9.568110758182521e-06,
"loss": 1.5221,
"step": 413
},
{
"epoch": 0.353921778157726,
"grad_norm": 2.1251678466796875,
"learning_rate": 9.565230773750369e-06,
"loss": 1.4464,
"step": 414
},
{
"epoch": 0.3547766616798461,
"grad_norm": 1.9180314540863037,
"learning_rate": 9.562341655228102e-06,
"loss": 1.5082,
"step": 415
},
{
"epoch": 0.3556315452019662,
"grad_norm": 2.0336544513702393,
"learning_rate": 9.559443408396252e-06,
"loss": 1.6297,
"step": 416
},
{
"epoch": 0.35648642872408637,
"grad_norm": 1.9119011163711548,
"learning_rate": 9.556536039053614e-06,
"loss": 1.5721,
"step": 417
},
{
"epoch": 0.35734131224620647,
"grad_norm": 2.0506341457366943,
"learning_rate": 9.553619553017242e-06,
"loss": 1.5863,
"step": 418
},
{
"epoch": 0.35819619576832656,
"grad_norm": 2.2243218421936035,
"learning_rate": 9.550693956122423e-06,
"loss": 1.6749,
"step": 419
},
{
"epoch": 0.35905107929044666,
"grad_norm": 2.0671815872192383,
"learning_rate": 9.547759254222677e-06,
"loss": 1.5347,
"step": 420
},
{
"epoch": 0.3599059628125668,
"grad_norm": 2.6808528900146484,
"learning_rate": 9.544815453189742e-06,
"loss": 1.5961,
"step": 421
},
{
"epoch": 0.3607608463346869,
"grad_norm": 2.706782102584839,
"learning_rate": 9.541862558913557e-06,
"loss": 1.7542,
"step": 422
},
{
"epoch": 0.361615729856807,
"grad_norm": 1.9116767644882202,
"learning_rate": 9.538900577302259e-06,
"loss": 1.5888,
"step": 423
},
{
"epoch": 0.3624706133789271,
"grad_norm": 1.8376832008361816,
"learning_rate": 9.535929514282165e-06,
"loss": 1.7108,
"step": 424
},
{
"epoch": 0.3633254969010472,
"grad_norm": 2.479327917098999,
"learning_rate": 9.532949375797763e-06,
"loss": 1.6665,
"step": 425
},
{
"epoch": 0.36418038042316736,
"grad_norm": 2.165562629699707,
"learning_rate": 9.5299601678117e-06,
"loss": 1.6313,
"step": 426
},
{
"epoch": 0.36503526394528746,
"grad_norm": 2.4955830574035645,
"learning_rate": 9.526961896304764e-06,
"loss": 1.392,
"step": 427
},
{
"epoch": 0.36589014746740756,
"grad_norm": 2.231637477874756,
"learning_rate": 9.523954567275886e-06,
"loss": 1.6392,
"step": 428
},
{
"epoch": 0.36674503098952765,
"grad_norm": 1.9232414960861206,
"learning_rate": 9.520938186742111e-06,
"loss": 1.6145,
"step": 429
},
{
"epoch": 0.3675999145116478,
"grad_norm": 1.8367480039596558,
"learning_rate": 9.5179127607386e-06,
"loss": 1.6133,
"step": 430
},
{
"epoch": 0.3684547980337679,
"grad_norm": 1.8861103057861328,
"learning_rate": 9.514878295318605e-06,
"loss": 1.5945,
"step": 431
},
{
"epoch": 0.369309681555888,
"grad_norm": 2.045668601989746,
"learning_rate": 9.511834796553474e-06,
"loss": 1.7027,
"step": 432
},
{
"epoch": 0.3701645650780081,
"grad_norm": 1.8058552742004395,
"learning_rate": 9.508782270532622e-06,
"loss": 1.5022,
"step": 433
},
{
"epoch": 0.37101944860012825,
"grad_norm": 2.5390875339508057,
"learning_rate": 9.505720723363526e-06,
"loss": 1.5491,
"step": 434
},
{
"epoch": 0.37187433212224835,
"grad_norm": 1.892199158668518,
"learning_rate": 9.502650161171714e-06,
"loss": 1.5664,
"step": 435
},
{
"epoch": 0.37272921564436845,
"grad_norm": 1.891270399093628,
"learning_rate": 9.49957059010075e-06,
"loss": 1.6434,
"step": 436
},
{
"epoch": 0.37358409916648855,
"grad_norm": 1.884423851966858,
"learning_rate": 9.49648201631223e-06,
"loss": 1.6827,
"step": 437
},
{
"epoch": 0.3744389826886087,
"grad_norm": 1.9029580354690552,
"learning_rate": 9.493384445985748e-06,
"loss": 1.7887,
"step": 438
},
{
"epoch": 0.3752938662107288,
"grad_norm": 2.3171463012695312,
"learning_rate": 9.490277885318911e-06,
"loss": 1.6336,
"step": 439
},
{
"epoch": 0.3761487497328489,
"grad_norm": 1.94197416305542,
"learning_rate": 9.48716234052731e-06,
"loss": 1.5117,
"step": 440
},
{
"epoch": 0.377003633254969,
"grad_norm": 2.3445913791656494,
"learning_rate": 9.48403781784451e-06,
"loss": 1.6445,
"step": 441
},
{
"epoch": 0.37785851677708915,
"grad_norm": 1.9795849323272705,
"learning_rate": 9.480904323522039e-06,
"loss": 1.6885,
"step": 442
},
{
"epoch": 0.37871340029920925,
"grad_norm": 1.7723476886749268,
"learning_rate": 9.477761863829376e-06,
"loss": 1.545,
"step": 443
},
{
"epoch": 0.37956828382132934,
"grad_norm": 1.9953805208206177,
"learning_rate": 9.474610445053941e-06,
"loss": 1.6542,
"step": 444
},
{
"epoch": 0.38042316734344944,
"grad_norm": 2.2689387798309326,
"learning_rate": 9.471450073501075e-06,
"loss": 1.6453,
"step": 445
},
{
"epoch": 0.38127805086556954,
"grad_norm": 2.2516140937805176,
"learning_rate": 9.46828075549403e-06,
"loss": 1.5717,
"step": 446
},
{
"epoch": 0.3821329343876897,
"grad_norm": 1.8665640354156494,
"learning_rate": 9.465102497373964e-06,
"loss": 1.5351,
"step": 447
},
{
"epoch": 0.3829878179098098,
"grad_norm": 1.901228904724121,
"learning_rate": 9.46191530549992e-06,
"loss": 1.8935,
"step": 448
},
{
"epoch": 0.3838427014319299,
"grad_norm": 2.023531436920166,
"learning_rate": 9.458719186248813e-06,
"loss": 1.4649,
"step": 449
},
{
"epoch": 0.38469758495405,
"grad_norm": 2.481318950653076,
"learning_rate": 9.455514146015425e-06,
"loss": 1.205,
"step": 450
},
{
"epoch": 0.38555246847617014,
"grad_norm": 2.31809401512146,
"learning_rate": 9.45230019121238e-06,
"loss": 1.6223,
"step": 451
},
{
"epoch": 0.38640735199829024,
"grad_norm": 2.2454018592834473,
"learning_rate": 9.449077328270144e-06,
"loss": 1.747,
"step": 452
},
{
"epoch": 0.38726223552041034,
"grad_norm": 2.1338086128234863,
"learning_rate": 9.445845563637004e-06,
"loss": 1.6782,
"step": 453
},
{
"epoch": 0.38811711904253043,
"grad_norm": 1.8717645406723022,
"learning_rate": 9.442604903779058e-06,
"loss": 1.6059,
"step": 454
},
{
"epoch": 0.3889720025646506,
"grad_norm": 2.139616012573242,
"learning_rate": 9.439355355180203e-06,
"loss": 1.5604,
"step": 455
},
{
"epoch": 0.3898268860867707,
"grad_norm": 3.311588764190674,
"learning_rate": 9.436096924342119e-06,
"loss": 1.5347,
"step": 456
},
{
"epoch": 0.3906817696088908,
"grad_norm": 2.202603578567505,
"learning_rate": 9.432829617784254e-06,
"loss": 1.4768,
"step": 457
},
{
"epoch": 0.3915366531310109,
"grad_norm": 2.028428554534912,
"learning_rate": 9.429553442043822e-06,
"loss": 1.5481,
"step": 458
},
{
"epoch": 0.39239153665313103,
"grad_norm": 1.914510726928711,
"learning_rate": 9.426268403675776e-06,
"loss": 1.5443,
"step": 459
},
{
"epoch": 0.39324642017525113,
"grad_norm": 1.7629053592681885,
"learning_rate": 9.422974509252806e-06,
"loss": 1.7737,
"step": 460
},
{
"epoch": 0.39410130369737123,
"grad_norm": 1.8821051120758057,
"learning_rate": 9.419671765365317e-06,
"loss": 1.6567,
"step": 461
},
{
"epoch": 0.39495618721949133,
"grad_norm": 1.9063416719436646,
"learning_rate": 9.416360178621423e-06,
"loss": 1.5636,
"step": 462
},
{
"epoch": 0.3958110707416115,
"grad_norm": 2.077802896499634,
"learning_rate": 9.413039755646928e-06,
"loss": 1.726,
"step": 463
},
{
"epoch": 0.3966659542637316,
"grad_norm": 2.192138433456421,
"learning_rate": 9.40971050308532e-06,
"loss": 1.6637,
"step": 464
},
{
"epoch": 0.3975208377858517,
"grad_norm": 1.9042564630508423,
"learning_rate": 9.406372427597748e-06,
"loss": 1.7897,
"step": 465
},
{
"epoch": 0.3983757213079718,
"grad_norm": 55.77303695678711,
"learning_rate": 9.403025535863017e-06,
"loss": 1.6107,
"step": 466
},
{
"epoch": 0.3992306048300919,
"grad_norm": 1.9976872205734253,
"learning_rate": 9.39966983457757e-06,
"loss": 1.4734,
"step": 467
},
{
"epoch": 0.400085488352212,
"grad_norm": 2.049694299697876,
"learning_rate": 9.396305330455477e-06,
"loss": 1.5076,
"step": 468
},
{
"epoch": 0.4009403718743321,
"grad_norm": 1.9261916875839233,
"learning_rate": 9.39293203022842e-06,
"loss": 1.7984,
"step": 469
},
{
"epoch": 0.4017952553964522,
"grad_norm": 1.9258121252059937,
"learning_rate": 9.389549940645681e-06,
"loss": 1.4655,
"step": 470
},
{
"epoch": 0.4026501389185723,
"grad_norm": 1.7797189950942993,
"learning_rate": 9.38615906847413e-06,
"loss": 1.6192,
"step": 471
},
{
"epoch": 0.4035050224406925,
"grad_norm": 1.9286493062973022,
"learning_rate": 9.382759420498203e-06,
"loss": 1.7695,
"step": 472
},
{
"epoch": 0.40435990596281257,
"grad_norm": 2.3398804664611816,
"learning_rate": 9.3793510035199e-06,
"loss": 1.4717,
"step": 473
},
{
"epoch": 0.40521478948493267,
"grad_norm": 1.9439282417297363,
"learning_rate": 9.375933824358761e-06,
"loss": 1.4579,
"step": 474
},
{
"epoch": 0.40606967300705277,
"grad_norm": 1.8554619550704956,
"learning_rate": 9.372507889851863e-06,
"loss": 1.6733,
"step": 475
},
{
"epoch": 0.4069245565291729,
"grad_norm": 2.129397392272949,
"learning_rate": 9.3690732068538e-06,
"loss": 1.7154,
"step": 476
},
{
"epoch": 0.407779440051293,
"grad_norm": 2.1848104000091553,
"learning_rate": 9.365629782236665e-06,
"loss": 1.7401,
"step": 477
},
{
"epoch": 0.4086343235734131,
"grad_norm": 2.366959810256958,
"learning_rate": 9.362177622890042e-06,
"loss": 1.4182,
"step": 478
},
{
"epoch": 0.4094892070955332,
"grad_norm": 2.0443150997161865,
"learning_rate": 9.358716735721001e-06,
"loss": 1.6127,
"step": 479
},
{
"epoch": 0.41034409061765337,
"grad_norm": 1.9910573959350586,
"learning_rate": 9.355247127654059e-06,
"loss": 1.6025,
"step": 480
},
{
"epoch": 0.41119897413977347,
"grad_norm": 1.7490131855010986,
"learning_rate": 9.351768805631195e-06,
"loss": 1.636,
"step": 481
},
{
"epoch": 0.41205385766189356,
"grad_norm": 1.9974701404571533,
"learning_rate": 9.348281776611817e-06,
"loss": 1.7417,
"step": 482
},
{
"epoch": 0.41290874118401366,
"grad_norm": 2.488692283630371,
"learning_rate": 9.34478604757275e-06,
"loss": 1.4733,
"step": 483
},
{
"epoch": 0.4137636247061338,
"grad_norm": 2.012645959854126,
"learning_rate": 9.341281625508239e-06,
"loss": 1.6016,
"step": 484
},
{
"epoch": 0.4146185082282539,
"grad_norm": 1.7562576532363892,
"learning_rate": 9.337768517429906e-06,
"loss": 1.6269,
"step": 485
},
{
"epoch": 0.415473391750374,
"grad_norm": 3.038557291030884,
"learning_rate": 9.334246730366763e-06,
"loss": 1.7471,
"step": 486
},
{
"epoch": 0.4163282752724941,
"grad_norm": 1.993278980255127,
"learning_rate": 9.330716271365183e-06,
"loss": 1.5104,
"step": 487
},
{
"epoch": 0.4171831587946142,
"grad_norm": 2.662400007247925,
"learning_rate": 9.32717714748889e-06,
"loss": 1.5185,
"step": 488
},
{
"epoch": 0.41803804231673436,
"grad_norm": 2.5048787593841553,
"learning_rate": 9.323629365818945e-06,
"loss": 1.6455,
"step": 489
},
{
"epoch": 0.41889292583885446,
"grad_norm": 1.7933145761489868,
"learning_rate": 9.32007293345373e-06,
"loss": 1.6,
"step": 490
},
{
"epoch": 0.41974780936097456,
"grad_norm": 1.6806269884109497,
"learning_rate": 9.316507857508936e-06,
"loss": 1.6584,
"step": 491
},
{
"epoch": 0.42060269288309465,
"grad_norm": 2.03226375579834,
"learning_rate": 9.312934145117552e-06,
"loss": 1.7171,
"step": 492
},
{
"epoch": 0.4214575764052148,
"grad_norm": 1.8401916027069092,
"learning_rate": 9.30935180342984e-06,
"loss": 1.5444,
"step": 493
},
{
"epoch": 0.4223124599273349,
"grad_norm": 1.91862154006958,
"learning_rate": 9.305760839613332e-06,
"loss": 1.5491,
"step": 494
},
{
"epoch": 0.423167343449455,
"grad_norm": 2.2723190784454346,
"learning_rate": 9.302161260852809e-06,
"loss": 1.7911,
"step": 495
},
{
"epoch": 0.4240222269715751,
"grad_norm": 2.3843624591827393,
"learning_rate": 9.29855307435029e-06,
"loss": 1.4825,
"step": 496
},
{
"epoch": 0.42487711049369525,
"grad_norm": 13.173310279846191,
"learning_rate": 9.294936287325016e-06,
"loss": 1.6597,
"step": 497
},
{
"epoch": 0.42573199401581535,
"grad_norm": 1.7834957838058472,
"learning_rate": 9.291310907013435e-06,
"loss": 1.6817,
"step": 498
},
{
"epoch": 0.42658687753793545,
"grad_norm": 2.1975371837615967,
"learning_rate": 9.287676940669192e-06,
"loss": 1.6483,
"step": 499
},
{
"epoch": 0.42744176106005555,
"grad_norm": 1.8264548778533936,
"learning_rate": 9.284034395563105e-06,
"loss": 1.5933,
"step": 500
},
{
"epoch": 0.4282966445821757,
"grad_norm": 1.8206008672714233,
"learning_rate": 9.280383278983161e-06,
"loss": 1.5615,
"step": 501
},
{
"epoch": 0.4291515281042958,
"grad_norm": 2.0878608226776123,
"learning_rate": 9.276723598234493e-06,
"loss": 1.5504,
"step": 502
},
{
"epoch": 0.4300064116264159,
"grad_norm": 1.9497365951538086,
"learning_rate": 9.273055360639374e-06,
"loss": 1.5884,
"step": 503
},
{
"epoch": 0.430861295148536,
"grad_norm": 2.368556022644043,
"learning_rate": 9.269378573537194e-06,
"loss": 1.3559,
"step": 504
},
{
"epoch": 0.43171617867065615,
"grad_norm": 1.90982186794281,
"learning_rate": 9.265693244284449e-06,
"loss": 1.6106,
"step": 505
},
{
"epoch": 0.43257106219277625,
"grad_norm": 2.013579845428467,
"learning_rate": 9.261999380254728e-06,
"loss": 1.5972,
"step": 506
},
{
"epoch": 0.43342594571489634,
"grad_norm": 1.9895778894424438,
"learning_rate": 9.258296988838692e-06,
"loss": 1.6102,
"step": 507
},
{
"epoch": 0.43428082923701644,
"grad_norm": 1.9256671667099,
"learning_rate": 9.25458607744407e-06,
"loss": 1.5448,
"step": 508
},
{
"epoch": 0.4351357127591366,
"grad_norm": 1.9200236797332764,
"learning_rate": 9.250866653495631e-06,
"loss": 1.6368,
"step": 509
},
{
"epoch": 0.4359905962812567,
"grad_norm": 2.1511929035186768,
"learning_rate": 9.247138724435185e-06,
"loss": 1.6384,
"step": 510
},
{
"epoch": 0.4368454798033768,
"grad_norm": 2.1603779792785645,
"learning_rate": 9.243402297721546e-06,
"loss": 1.4907,
"step": 511
},
{
"epoch": 0.4377003633254969,
"grad_norm": 1.9871954917907715,
"learning_rate": 9.239657380830543e-06,
"loss": 1.6423,
"step": 512
},
{
"epoch": 0.438555246847617,
"grad_norm": 1.997007131576538,
"learning_rate": 9.235903981254981e-06,
"loss": 1.5842,
"step": 513
},
{
"epoch": 0.43941013036973714,
"grad_norm": 1.8282665014266968,
"learning_rate": 9.232142106504648e-06,
"loss": 1.5855,
"step": 514
},
{
"epoch": 0.44026501389185724,
"grad_norm": 2.0519628524780273,
"learning_rate": 9.228371764106279e-06,
"loss": 1.7629,
"step": 515
},
{
"epoch": 0.44111989741397734,
"grad_norm": 1.9096105098724365,
"learning_rate": 9.224592961603558e-06,
"loss": 1.6367,
"step": 516
},
{
"epoch": 0.44197478093609743,
"grad_norm": 2.1138973236083984,
"learning_rate": 9.220805706557094e-06,
"loss": 1.5607,
"step": 517
},
{
"epoch": 0.4428296644582176,
"grad_norm": 1.8094953298568726,
"learning_rate": 9.217010006544406e-06,
"loss": 1.6805,
"step": 518
},
{
"epoch": 0.4436845479803377,
"grad_norm": 1.847633957862854,
"learning_rate": 9.213205869159912e-06,
"loss": 1.6118,
"step": 519
},
{
"epoch": 0.4445394315024578,
"grad_norm": 2.2239439487457275,
"learning_rate": 9.209393302014908e-06,
"loss": 1.4869,
"step": 520
},
{
"epoch": 0.4453943150245779,
"grad_norm": 1.8056226968765259,
"learning_rate": 9.205572312737562e-06,
"loss": 1.52,
"step": 521
},
{
"epoch": 0.44624919854669803,
"grad_norm": 2.1382007598876953,
"learning_rate": 9.201742908972886e-06,
"loss": 1.4253,
"step": 522
},
{
"epoch": 0.44710408206881813,
"grad_norm": 2.0205068588256836,
"learning_rate": 9.197905098382734e-06,
"loss": 1.577,
"step": 523
},
{
"epoch": 0.44795896559093823,
"grad_norm": 1.8336679935455322,
"learning_rate": 9.194058888645776e-06,
"loss": 1.5969,
"step": 524
},
{
"epoch": 0.4488138491130583,
"grad_norm": 1.958166241645813,
"learning_rate": 9.19020428745749e-06,
"loss": 1.5589,
"step": 525
},
{
"epoch": 0.4496687326351785,
"grad_norm": 1.8487937450408936,
"learning_rate": 9.186341302530142e-06,
"loss": 1.8666,
"step": 526
},
{
"epoch": 0.4505236161572986,
"grad_norm": 1.940935492515564,
"learning_rate": 9.18246994159277e-06,
"loss": 1.7236,
"step": 527
},
{
"epoch": 0.4513784996794187,
"grad_norm": 1.7989500761032104,
"learning_rate": 9.178590212391177e-06,
"loss": 1.3875,
"step": 528
},
{
"epoch": 0.4522333832015388,
"grad_norm": 2.0304832458496094,
"learning_rate": 9.1747021226879e-06,
"loss": 1.7533,
"step": 529
},
{
"epoch": 0.45308826672365893,
"grad_norm": 1.8041130304336548,
"learning_rate": 9.170805680262212e-06,
"loss": 1.6563,
"step": 530
},
{
"epoch": 0.453943150245779,
"grad_norm": 1.8609191179275513,
"learning_rate": 9.166900892910095e-06,
"loss": 1.6209,
"step": 531
},
{
"epoch": 0.4547980337678991,
"grad_norm": 1.9766689538955688,
"learning_rate": 9.162987768444225e-06,
"loss": 1.6673,
"step": 532
},
{
"epoch": 0.4556529172900192,
"grad_norm": 1.8203067779541016,
"learning_rate": 9.159066314693965e-06,
"loss": 1.5735,
"step": 533
},
{
"epoch": 0.4565078008121393,
"grad_norm": 1.907524824142456,
"learning_rate": 9.155136539505337e-06,
"loss": 1.7929,
"step": 534
},
{
"epoch": 0.4573626843342595,
"grad_norm": 2.2627012729644775,
"learning_rate": 9.151198450741013e-06,
"loss": 1.4976,
"step": 535
},
{
"epoch": 0.45821756785637957,
"grad_norm": 2.3210504055023193,
"learning_rate": 9.147252056280305e-06,
"loss": 1.6316,
"step": 536
},
{
"epoch": 0.45907245137849967,
"grad_norm": 1.8242363929748535,
"learning_rate": 9.143297364019134e-06,
"loss": 1.5303,
"step": 537
},
{
"epoch": 0.45992733490061977,
"grad_norm": 2.0939862728118896,
"learning_rate": 9.139334381870032e-06,
"loss": 1.6881,
"step": 538
},
{
"epoch": 0.4607822184227399,
"grad_norm": 2.001176595687866,
"learning_rate": 9.135363117762111e-06,
"loss": 1.7572,
"step": 539
},
{
"epoch": 0.46163710194486,
"grad_norm": 1.824602484703064,
"learning_rate": 9.131383579641055e-06,
"loss": 1.6849,
"step": 540
},
{
"epoch": 0.4624919854669801,
"grad_norm": 1.765763521194458,
"learning_rate": 9.127395775469105e-06,
"loss": 1.6392,
"step": 541
},
{
"epoch": 0.4633468689891002,
"grad_norm": 2.4184436798095703,
"learning_rate": 9.123399713225039e-06,
"loss": 1.496,
"step": 542
},
{
"epoch": 0.46420175251122037,
"grad_norm": 1.7558503150939941,
"learning_rate": 9.119395400904154e-06,
"loss": 1.7759,
"step": 543
},
{
"epoch": 0.46505663603334046,
"grad_norm": 2.245574474334717,
"learning_rate": 9.115382846518263e-06,
"loss": 1.6061,
"step": 544
},
{
"epoch": 0.46591151955546056,
"grad_norm": 2.0234146118164062,
"learning_rate": 9.11136205809566e-06,
"loss": 1.4992,
"step": 545
},
{
"epoch": 0.46676640307758066,
"grad_norm": 1.8050514459609985,
"learning_rate": 9.10733304368112e-06,
"loss": 1.6266,
"step": 546
},
{
"epoch": 0.4676212865997008,
"grad_norm": 1.7917343378067017,
"learning_rate": 9.103295811335873e-06,
"loss": 1.8325,
"step": 547
},
{
"epoch": 0.4684761701218209,
"grad_norm": 1.9059429168701172,
"learning_rate": 9.099250369137593e-06,
"loss": 1.7297,
"step": 548
},
{
"epoch": 0.469331053643941,
"grad_norm": 1.9517232179641724,
"learning_rate": 9.095196725180378e-06,
"loss": 1.7357,
"step": 549
},
{
"epoch": 0.4701859371660611,
"grad_norm": 2.318387985229492,
"learning_rate": 9.09113488757474e-06,
"loss": 1.5877,
"step": 550
},
{
"epoch": 0.47104082068818126,
"grad_norm": 1.796807885169983,
"learning_rate": 9.087064864447583e-06,
"loss": 1.5986,
"step": 551
},
{
"epoch": 0.47189570421030136,
"grad_norm": 1.8475953340530396,
"learning_rate": 9.082986663942187e-06,
"loss": 1.6098,
"step": 552
},
{
"epoch": 0.47275058773242146,
"grad_norm": 1.9878709316253662,
"learning_rate": 9.078900294218196e-06,
"loss": 1.7224,
"step": 553
},
{
"epoch": 0.47360547125454155,
"grad_norm": 1.9042646884918213,
"learning_rate": 9.074805763451595e-06,
"loss": 1.5801,
"step": 554
},
{
"epoch": 0.47446035477666165,
"grad_norm": 2.0457966327667236,
"learning_rate": 9.070703079834701e-06,
"loss": 1.4993,
"step": 555
},
{
"epoch": 0.4753152382987818,
"grad_norm": 1.8046479225158691,
"learning_rate": 9.066592251576143e-06,
"loss": 1.7765,
"step": 556
},
{
"epoch": 0.4761701218209019,
"grad_norm": 1.9781793355941772,
"learning_rate": 9.062473286900843e-06,
"loss": 1.4311,
"step": 557
},
{
"epoch": 0.477025005343022,
"grad_norm": 2.416982889175415,
"learning_rate": 9.058346194050007e-06,
"loss": 1.5628,
"step": 558
},
{
"epoch": 0.4778798888651421,
"grad_norm": 2.044501781463623,
"learning_rate": 9.0542109812811e-06,
"loss": 1.5452,
"step": 559
},
{
"epoch": 0.47873477238726225,
"grad_norm": 1.9374364614486694,
"learning_rate": 9.050067656867833e-06,
"loss": 1.7013,
"step": 560
},
{
"epoch": 0.47958965590938235,
"grad_norm": 1.9821714162826538,
"learning_rate": 9.045916229100148e-06,
"loss": 1.5827,
"step": 561
},
{
"epoch": 0.48044453943150245,
"grad_norm": 1.80966055393219,
"learning_rate": 9.041756706284201e-06,
"loss": 1.5384,
"step": 562
},
{
"epoch": 0.48129942295362255,
"grad_norm": 1.874300241470337,
"learning_rate": 9.037589096742346e-06,
"loss": 1.9239,
"step": 563
},
{
"epoch": 0.4821543064757427,
"grad_norm": 2.0358619689941406,
"learning_rate": 9.033413408813113e-06,
"loss": 1.4334,
"step": 564
},
{
"epoch": 0.4830091899978628,
"grad_norm": 2.362205982208252,
"learning_rate": 9.029229650851192e-06,
"loss": 1.4202,
"step": 565
},
{
"epoch": 0.4838640735199829,
"grad_norm": 2.374218225479126,
"learning_rate": 9.025037831227433e-06,
"loss": 1.4886,
"step": 566
},
{
"epoch": 0.484718957042103,
"grad_norm": 2.0200891494750977,
"learning_rate": 9.020837958328799e-06,
"loss": 1.5932,
"step": 567
},
{
"epoch": 0.48557384056422315,
"grad_norm": 1.9744147062301636,
"learning_rate": 9.01663004055838e-06,
"loss": 1.4954,
"step": 568
},
{
"epoch": 0.48642872408634324,
"grad_norm": 1.8265093564987183,
"learning_rate": 9.012414086335353e-06,
"loss": 1.7541,
"step": 569
},
{
"epoch": 0.48728360760846334,
"grad_norm": 2.042421340942383,
"learning_rate": 9.008190104094978e-06,
"loss": 1.5381,
"step": 570
},
{
"epoch": 0.48813849113058344,
"grad_norm": 1.9857375621795654,
"learning_rate": 9.003958102288575e-06,
"loss": 1.3851,
"step": 571
},
{
"epoch": 0.4889933746527036,
"grad_norm": 1.9522275924682617,
"learning_rate": 8.999718089383516e-06,
"loss": 1.5013,
"step": 572
},
{
"epoch": 0.4898482581748237,
"grad_norm": 2.621446371078491,
"learning_rate": 8.995470073863192e-06,
"loss": 1.5064,
"step": 573
},
{
"epoch": 0.4907031416969438,
"grad_norm": 1.8776718378067017,
"learning_rate": 8.991214064227015e-06,
"loss": 1.4914,
"step": 574
},
{
"epoch": 0.4915580252190639,
"grad_norm": 2.4339656829833984,
"learning_rate": 8.986950068990382e-06,
"loss": 1.4783,
"step": 575
},
{
"epoch": 0.49241290874118404,
"grad_norm": 1.8802049160003662,
"learning_rate": 8.982678096684677e-06,
"loss": 1.5207,
"step": 576
},
{
"epoch": 0.49326779226330414,
"grad_norm": 1.9528294801712036,
"learning_rate": 8.978398155857237e-06,
"loss": 1.4501,
"step": 577
},
{
"epoch": 0.49412267578542424,
"grad_norm": 4.20005464553833,
"learning_rate": 8.974110255071346e-06,
"loss": 1.6392,
"step": 578
},
{
"epoch": 0.49497755930754433,
"grad_norm": 2.0071566104888916,
"learning_rate": 8.969814402906217e-06,
"loss": 1.6073,
"step": 579
},
{
"epoch": 0.49583244282966443,
"grad_norm": 1.8972854614257812,
"learning_rate": 8.965510607956966e-06,
"loss": 1.4545,
"step": 580
},
{
"epoch": 0.4966873263517846,
"grad_norm": 1.9058289527893066,
"learning_rate": 8.961198878834602e-06,
"loss": 1.4867,
"step": 581
},
{
"epoch": 0.4975422098739047,
"grad_norm": 1.9958810806274414,
"learning_rate": 8.956879224166014e-06,
"loss": 1.8224,
"step": 582
},
{
"epoch": 0.4983970933960248,
"grad_norm": 1.8081709146499634,
"learning_rate": 8.952551652593943e-06,
"loss": 1.7404,
"step": 583
},
{
"epoch": 0.4992519769181449,
"grad_norm": 2.774141550064087,
"learning_rate": 8.948216172776971e-06,
"loss": 1.7241,
"step": 584
},
{
"epoch": 0.500106860440265,
"grad_norm": 2.1106200218200684,
"learning_rate": 8.943872793389505e-06,
"loss": 1.5724,
"step": 585
},
{
"epoch": 0.5009617439623851,
"grad_norm": 2.0356194972991943,
"learning_rate": 8.939521523121755e-06,
"loss": 1.6468,
"step": 586
},
{
"epoch": 0.5009617439623851,
"eval_loss": 1.6289023160934448,
"eval_runtime": 534.394,
"eval_samples_per_second": 7.403,
"eval_steps_per_second": 3.701,
"step": 586
},
{
"epoch": 0.5018166274845053,
"grad_norm": 1.933261513710022,
"learning_rate": 8.93516237067972e-06,
"loss": 1.657,
"step": 587
},
{
"epoch": 0.5026715110066253,
"grad_norm": 2.1306746006011963,
"learning_rate": 8.93079534478517e-06,
"loss": 1.6718,
"step": 588
},
{
"epoch": 0.5035263945287455,
"grad_norm": 1.6752455234527588,
"learning_rate": 8.92642045417563e-06,
"loss": 1.7148,
"step": 589
},
{
"epoch": 0.5043812780508655,
"grad_norm": 1.8051491975784302,
"learning_rate": 8.922037707604355e-06,
"loss": 1.6413,
"step": 590
},
{
"epoch": 0.5052361615729857,
"grad_norm": 1.8917031288146973,
"learning_rate": 8.917647113840323e-06,
"loss": 1.5288,
"step": 591
},
{
"epoch": 0.5060910450951058,
"grad_norm": 2.0400190353393555,
"learning_rate": 8.91324868166821e-06,
"loss": 1.4745,
"step": 592
},
{
"epoch": 0.5069459286172259,
"grad_norm": 2.0113611221313477,
"learning_rate": 8.908842419888379e-06,
"loss": 1.6355,
"step": 593
},
{
"epoch": 0.507800812139346,
"grad_norm": 1.8284205198287964,
"learning_rate": 8.904428337316855e-06,
"loss": 1.5299,
"step": 594
},
{
"epoch": 0.5086556956614662,
"grad_norm": 1.8652138710021973,
"learning_rate": 8.900006442785312e-06,
"loss": 1.7343,
"step": 595
},
{
"epoch": 0.5095105791835862,
"grad_norm": 1.8095743656158447,
"learning_rate": 8.89557674514105e-06,
"loss": 1.7715,
"step": 596
},
{
"epoch": 0.5103654627057064,
"grad_norm": 2.018333911895752,
"learning_rate": 8.89113925324699e-06,
"loss": 1.6964,
"step": 597
},
{
"epoch": 0.5112203462278264,
"grad_norm": 2.0537750720977783,
"learning_rate": 8.88669397598164e-06,
"loss": 1.4207,
"step": 598
},
{
"epoch": 0.5120752297499466,
"grad_norm": 1.9517449140548706,
"learning_rate": 8.882240922239089e-06,
"loss": 1.6236,
"step": 599
},
{
"epoch": 0.5129301132720667,
"grad_norm": 1.8960734605789185,
"learning_rate": 8.877780100928984e-06,
"loss": 1.6692,
"step": 600
},
{
"epoch": 0.5137849967941868,
"grad_norm": 2.1357903480529785,
"learning_rate": 8.87331152097651e-06,
"loss": 1.9005,
"step": 601
},
{
"epoch": 0.5146398803163069,
"grad_norm": 2.6492884159088135,
"learning_rate": 8.868835191322384e-06,
"loss": 1.5357,
"step": 602
},
{
"epoch": 0.515494763838427,
"grad_norm": 3.4608476161956787,
"learning_rate": 8.864351120922819e-06,
"loss": 1.6542,
"step": 603
},
{
"epoch": 0.5163496473605471,
"grad_norm": 2.1841821670532227,
"learning_rate": 8.859859318749522e-06,
"loss": 1.6261,
"step": 604
},
{
"epoch": 0.5172045308826673,
"grad_norm": 1.922024130821228,
"learning_rate": 8.855359793789667e-06,
"loss": 1.7292,
"step": 605
},
{
"epoch": 0.5180594144047873,
"grad_norm": 1.988054633140564,
"learning_rate": 8.85085255504588e-06,
"loss": 1.7862,
"step": 606
},
{
"epoch": 0.5189142979269075,
"grad_norm": 1.9861512184143066,
"learning_rate": 8.84633761153622e-06,
"loss": 1.6567,
"step": 607
},
{
"epoch": 0.5197691814490276,
"grad_norm": 2.0631234645843506,
"learning_rate": 8.841814972294166e-06,
"loss": 1.3969,
"step": 608
},
{
"epoch": 0.5206240649711477,
"grad_norm": 1.9361271858215332,
"learning_rate": 8.837284646368586e-06,
"loss": 1.4913,
"step": 609
},
{
"epoch": 0.5214789484932678,
"grad_norm": 2.061472177505493,
"learning_rate": 8.832746642823738e-06,
"loss": 1.6651,
"step": 610
},
{
"epoch": 0.5223338320153879,
"grad_norm": 2.5141899585723877,
"learning_rate": 8.82820097073923e-06,
"loss": 1.6464,
"step": 611
},
{
"epoch": 0.523188715537508,
"grad_norm": 2.2343900203704834,
"learning_rate": 8.823647639210027e-06,
"loss": 1.3821,
"step": 612
},
{
"epoch": 0.5240435990596282,
"grad_norm": 1.7745505571365356,
"learning_rate": 8.819086657346405e-06,
"loss": 1.562,
"step": 613
},
{
"epoch": 0.5248984825817482,
"grad_norm": 1.795174241065979,
"learning_rate": 8.814518034273956e-06,
"loss": 1.7203,
"step": 614
},
{
"epoch": 0.5257533661038684,
"grad_norm": 1.829896330833435,
"learning_rate": 8.809941779133555e-06,
"loss": 1.6731,
"step": 615
},
{
"epoch": 0.5266082496259885,
"grad_norm": 1.787853479385376,
"learning_rate": 8.805357901081352e-06,
"loss": 1.5737,
"step": 616
},
{
"epoch": 0.5274631331481086,
"grad_norm": 1.8447085618972778,
"learning_rate": 8.800766409288745e-06,
"loss": 1.7847,
"step": 617
},
{
"epoch": 0.5283180166702287,
"grad_norm": 2.183621644973755,
"learning_rate": 8.796167312942367e-06,
"loss": 1.3627,
"step": 618
},
{
"epoch": 0.5291729001923487,
"grad_norm": 1.943145513534546,
"learning_rate": 8.791560621244067e-06,
"loss": 1.6397,
"step": 619
},
{
"epoch": 0.5300277837144689,
"grad_norm": 3.3538787364959717,
"learning_rate": 8.786946343410889e-06,
"loss": 1.8127,
"step": 620
},
{
"epoch": 0.5308826672365891,
"grad_norm": 1.7246778011322021,
"learning_rate": 8.782324488675059e-06,
"loss": 1.5005,
"step": 621
},
{
"epoch": 0.5317375507587091,
"grad_norm": 2.007582187652588,
"learning_rate": 8.777695066283955e-06,
"loss": 1.4858,
"step": 622
},
{
"epoch": 0.5325924342808293,
"grad_norm": 1.7573378086090088,
"learning_rate": 8.773058085500106e-06,
"loss": 1.5858,
"step": 623
},
{
"epoch": 0.5334473178029493,
"grad_norm": 2.4984254837036133,
"learning_rate": 8.768413555601156e-06,
"loss": 1.6391,
"step": 624
},
{
"epoch": 0.5343022013250694,
"grad_norm": 2.0162014961242676,
"learning_rate": 8.763761485879858e-06,
"loss": 1.622,
"step": 625
},
{
"epoch": 0.5351570848471896,
"grad_norm": 2.1535332202911377,
"learning_rate": 8.75910188564405e-06,
"loss": 1.6092,
"step": 626
},
{
"epoch": 0.5360119683693096,
"grad_norm": 2.0587708950042725,
"learning_rate": 8.754434764216632e-06,
"loss": 1.6507,
"step": 627
},
{
"epoch": 0.5368668518914298,
"grad_norm": 2.0657832622528076,
"learning_rate": 8.749760130935564e-06,
"loss": 1.5106,
"step": 628
},
{
"epoch": 0.53772173541355,
"grad_norm": 3.3556106090545654,
"learning_rate": 8.74507799515382e-06,
"loss": 1.6122,
"step": 629
},
{
"epoch": 0.53857661893567,
"grad_norm": 1.8298861980438232,
"learning_rate": 8.740388366239397e-06,
"loss": 1.7357,
"step": 630
},
{
"epoch": 0.5394315024577901,
"grad_norm": 2.4920873641967773,
"learning_rate": 8.735691253575278e-06,
"loss": 1.5525,
"step": 631
},
{
"epoch": 0.5402863859799102,
"grad_norm": 1.8337547779083252,
"learning_rate": 8.730986666559425e-06,
"loss": 1.6677,
"step": 632
},
{
"epoch": 0.5411412695020303,
"grad_norm": 2.205390453338623,
"learning_rate": 8.726274614604749e-06,
"loss": 1.7129,
"step": 633
},
{
"epoch": 0.5419961530241505,
"grad_norm": 1.8543306589126587,
"learning_rate": 8.721555107139102e-06,
"loss": 1.4831,
"step": 634
},
{
"epoch": 0.5428510365462705,
"grad_norm": 1.7591562271118164,
"learning_rate": 8.716828153605245e-06,
"loss": 1.6421,
"step": 635
},
{
"epoch": 0.5437059200683907,
"grad_norm": 2.9822521209716797,
"learning_rate": 8.712093763460846e-06,
"loss": 1.4437,
"step": 636
},
{
"epoch": 0.5445608035905108,
"grad_norm": 1.7901097536087036,
"learning_rate": 8.70735194617845e-06,
"loss": 1.6315,
"step": 637
},
{
"epoch": 0.5454156871126309,
"grad_norm": 2.0111300945281982,
"learning_rate": 8.702602711245455e-06,
"loss": 1.5924,
"step": 638
},
{
"epoch": 0.546270570634751,
"grad_norm": 2.0748534202575684,
"learning_rate": 8.697846068164112e-06,
"loss": 1.4713,
"step": 639
},
{
"epoch": 0.5471254541568711,
"grad_norm": 1.9600063562393188,
"learning_rate": 8.693082026451481e-06,
"loss": 1.7141,
"step": 640
},
{
"epoch": 0.5479803376789912,
"grad_norm": 2.1216888427734375,
"learning_rate": 8.688310595639437e-06,
"loss": 1.5694,
"step": 641
},
{
"epoch": 0.5488352212011114,
"grad_norm": 1.7273600101470947,
"learning_rate": 8.683531785274632e-06,
"loss": 1.7303,
"step": 642
},
{
"epoch": 0.5496901047232314,
"grad_norm": 2.0742030143737793,
"learning_rate": 8.678745604918486e-06,
"loss": 1.6376,
"step": 643
},
{
"epoch": 0.5505449882453516,
"grad_norm": 1.9716432094573975,
"learning_rate": 8.673952064147166e-06,
"loss": 1.4841,
"step": 644
},
{
"epoch": 0.5513998717674716,
"grad_norm": 2.9787380695343018,
"learning_rate": 8.669151172551558e-06,
"loss": 1.6401,
"step": 645
},
{
"epoch": 0.5522547552895918,
"grad_norm": 2.2232494354248047,
"learning_rate": 8.664342939737265e-06,
"loss": 1.4223,
"step": 646
},
{
"epoch": 0.5531096388117119,
"grad_norm": 2.1428375244140625,
"learning_rate": 8.659527375324574e-06,
"loss": 1.7418,
"step": 647
},
{
"epoch": 0.553964522333832,
"grad_norm": 1.9772781133651733,
"learning_rate": 8.654704488948442e-06,
"loss": 1.7229,
"step": 648
},
{
"epoch": 0.5548194058559521,
"grad_norm": 2.106757164001465,
"learning_rate": 8.649874290258473e-06,
"loss": 1.567,
"step": 649
},
{
"epoch": 0.5556742893780723,
"grad_norm": 2.3366143703460693,
"learning_rate": 8.645036788918904e-06,
"loss": 1.2882,
"step": 650
},
{
"epoch": 0.5565291729001923,
"grad_norm": 2.5621304512023926,
"learning_rate": 8.640191994608585e-06,
"loss": 1.6807,
"step": 651
},
{
"epoch": 0.5573840564223125,
"grad_norm": 1.8327507972717285,
"learning_rate": 8.635339917020952e-06,
"loss": 1.5425,
"step": 652
},
{
"epoch": 0.5582389399444325,
"grad_norm": 1.9729241132736206,
"learning_rate": 8.63048056586402e-06,
"loss": 1.6851,
"step": 653
},
{
"epoch": 0.5590938234665527,
"grad_norm": 2.0836198329925537,
"learning_rate": 8.625613950860352e-06,
"loss": 1.4055,
"step": 654
},
{
"epoch": 0.5599487069886728,
"grad_norm": 1.7130488157272339,
"learning_rate": 8.620740081747044e-06,
"loss": 1.7865,
"step": 655
},
{
"epoch": 0.5608035905107929,
"grad_norm": 2.0575125217437744,
"learning_rate": 8.615858968275712e-06,
"loss": 1.6653,
"step": 656
},
{
"epoch": 0.561658474032913,
"grad_norm": 1.9657676219940186,
"learning_rate": 8.610970620212461e-06,
"loss": 1.5761,
"step": 657
},
{
"epoch": 0.5625133575550332,
"grad_norm": 1.7400262355804443,
"learning_rate": 8.606075047337872e-06,
"loss": 1.7633,
"step": 658
},
{
"epoch": 0.5633682410771532,
"grad_norm": 1.8632696866989136,
"learning_rate": 8.601172259446981e-06,
"loss": 1.5333,
"step": 659
},
{
"epoch": 0.5642231245992734,
"grad_norm": 2.7947065830230713,
"learning_rate": 8.596262266349265e-06,
"loss": 1.5627,
"step": 660
},
{
"epoch": 0.5650780081213934,
"grad_norm": 2.0627810955047607,
"learning_rate": 8.591345077868606e-06,
"loss": 1.71,
"step": 661
},
{
"epoch": 0.5659328916435136,
"grad_norm": 2.519284725189209,
"learning_rate": 8.586420703843297e-06,
"loss": 1.7696,
"step": 662
},
{
"epoch": 0.5667877751656337,
"grad_norm": 2.0818934440612793,
"learning_rate": 8.581489154125995e-06,
"loss": 1.4629,
"step": 663
},
{
"epoch": 0.5676426586877538,
"grad_norm": 1.8783445358276367,
"learning_rate": 8.57655043858372e-06,
"loss": 1.3525,
"step": 664
},
{
"epoch": 0.5684975422098739,
"grad_norm": 2.1661863327026367,
"learning_rate": 8.571604567097827e-06,
"loss": 1.6119,
"step": 665
},
{
"epoch": 0.569352425731994,
"grad_norm": 1.9182928800582886,
"learning_rate": 8.566651549563993e-06,
"loss": 1.7566,
"step": 666
},
{
"epoch": 0.5702073092541141,
"grad_norm": 1.9936716556549072,
"learning_rate": 8.561691395892188e-06,
"loss": 1.4571,
"step": 667
},
{
"epoch": 0.5710621927762343,
"grad_norm": 1.8677414655685425,
"learning_rate": 8.556724116006664e-06,
"loss": 1.5713,
"step": 668
},
{
"epoch": 0.5719170762983543,
"grad_norm": 1.9004077911376953,
"learning_rate": 8.551749719845928e-06,
"loss": 1.6697,
"step": 669
},
{
"epoch": 0.5727719598204745,
"grad_norm": 2.03224515914917,
"learning_rate": 8.546768217362724e-06,
"loss": 1.5405,
"step": 670
},
{
"epoch": 0.5736268433425946,
"grad_norm": 1.912906527519226,
"learning_rate": 8.541779618524018e-06,
"loss": 1.5431,
"step": 671
},
{
"epoch": 0.5744817268647147,
"grad_norm": 1.7738916873931885,
"learning_rate": 8.536783933310972e-06,
"loss": 1.7385,
"step": 672
},
{
"epoch": 0.5753366103868348,
"grad_norm": 1.7471853494644165,
"learning_rate": 8.53178117171893e-06,
"loss": 1.7176,
"step": 673
},
{
"epoch": 0.5761914939089549,
"grad_norm": 2.7117345333099365,
"learning_rate": 8.526771343757387e-06,
"loss": 1.6298,
"step": 674
},
{
"epoch": 0.577046377431075,
"grad_norm": 1.8789851665496826,
"learning_rate": 8.521754459449984e-06,
"loss": 1.6023,
"step": 675
},
{
"epoch": 0.5779012609531952,
"grad_norm": 1.9868645668029785,
"learning_rate": 8.516730528834476e-06,
"loss": 1.7187,
"step": 676
},
{
"epoch": 0.5787561444753152,
"grad_norm": 1.7088147401809692,
"learning_rate": 8.511699561962719e-06,
"loss": 1.5902,
"step": 677
},
{
"epoch": 0.5796110279974354,
"grad_norm": 1.722632884979248,
"learning_rate": 8.506661568900644e-06,
"loss": 1.6701,
"step": 678
},
{
"epoch": 0.5804659115195555,
"grad_norm": 1.8633525371551514,
"learning_rate": 8.50161655972824e-06,
"loss": 1.6822,
"step": 679
},
{
"epoch": 0.5813207950416756,
"grad_norm": 1.9083114862442017,
"learning_rate": 8.496564544539539e-06,
"loss": 1.5115,
"step": 680
},
{
"epoch": 0.5821756785637957,
"grad_norm": 1.9144874811172485,
"learning_rate": 8.491505533442584e-06,
"loss": 1.6048,
"step": 681
},
{
"epoch": 0.5830305620859157,
"grad_norm": 1.8423601388931274,
"learning_rate": 8.48643953655942e-06,
"loss": 1.627,
"step": 682
},
{
"epoch": 0.5838854456080359,
"grad_norm": 1.9638283252716064,
"learning_rate": 8.481366564026065e-06,
"loss": 1.6544,
"step": 683
},
{
"epoch": 0.5847403291301561,
"grad_norm": 2.422207832336426,
"learning_rate": 8.476286625992499e-06,
"loss": 1.7425,
"step": 684
},
{
"epoch": 0.5855952126522761,
"grad_norm": 3.2921395301818848,
"learning_rate": 8.471199732622633e-06,
"loss": 1.598,
"step": 685
},
{
"epoch": 0.5864500961743963,
"grad_norm": 1.8565130233764648,
"learning_rate": 8.466105894094298e-06,
"loss": 1.4855,
"step": 686
},
{
"epoch": 0.5873049796965164,
"grad_norm": 2.0620574951171875,
"learning_rate": 8.461005120599222e-06,
"loss": 1.5109,
"step": 687
},
{
"epoch": 0.5881598632186364,
"grad_norm": 1.9637583494186401,
"learning_rate": 8.455897422343003e-06,
"loss": 1.6503,
"step": 688
},
{
"epoch": 0.5890147467407566,
"grad_norm": 7.110237121582031,
"learning_rate": 8.450782809545096e-06,
"loss": 1.6213,
"step": 689
},
{
"epoch": 0.5898696302628766,
"grad_norm": 2.607851505279541,
"learning_rate": 8.445661292438799e-06,
"loss": 1.7967,
"step": 690
},
{
"epoch": 0.5907245137849968,
"grad_norm": 1.8419544696807861,
"learning_rate": 8.440532881271209e-06,
"loss": 1.6102,
"step": 691
},
{
"epoch": 0.591579397307117,
"grad_norm": 1.9284480810165405,
"learning_rate": 8.435397586303229e-06,
"loss": 1.5749,
"step": 692
},
{
"epoch": 0.592434280829237,
"grad_norm": 2.60127854347229,
"learning_rate": 8.43025541780953e-06,
"loss": 1.6948,
"step": 693
},
{
"epoch": 0.5932891643513571,
"grad_norm": 1.9099665880203247,
"learning_rate": 8.425106386078535e-06,
"loss": 1.614,
"step": 694
},
{
"epoch": 0.5941440478734772,
"grad_norm": 3.712435245513916,
"learning_rate": 8.419950501412402e-06,
"loss": 1.7601,
"step": 695
},
{
"epoch": 0.5949989313955973,
"grad_norm": 2.350602149963379,
"learning_rate": 8.414787774126994e-06,
"loss": 1.4524,
"step": 696
},
{
"epoch": 0.5958538149177175,
"grad_norm": 1.8215548992156982,
"learning_rate": 8.409618214551874e-06,
"loss": 1.7657,
"step": 697
},
{
"epoch": 0.5967086984398375,
"grad_norm": 1.7211189270019531,
"learning_rate": 8.404441833030269e-06,
"loss": 1.5622,
"step": 698
},
{
"epoch": 0.5975635819619577,
"grad_norm": 1.90372896194458,
"learning_rate": 8.399258639919053e-06,
"loss": 1.6278,
"step": 699
},
{
"epoch": 0.5984184654840778,
"grad_norm": 2.5654449462890625,
"learning_rate": 8.394068645588735e-06,
"loss": 1.3127,
"step": 700
},
{
"epoch": 0.5992733490061979,
"grad_norm": 1.8627386093139648,
"learning_rate": 8.38887186042343e-06,
"loss": 1.6181,
"step": 701
},
{
"epoch": 0.600128232528318,
"grad_norm": 2.154141426086426,
"learning_rate": 8.383668294820835e-06,
"loss": 1.6831,
"step": 702
},
{
"epoch": 0.6009831160504381,
"grad_norm": 2.0848171710968018,
"learning_rate": 8.37845795919222e-06,
"loss": 1.513,
"step": 703
},
{
"epoch": 0.6018379995725582,
"grad_norm": 2.3841915130615234,
"learning_rate": 8.373240863962397e-06,
"loss": 1.7102,
"step": 704
},
{
"epoch": 0.6026928830946784,
"grad_norm": 1.8190158605575562,
"learning_rate": 8.368017019569704e-06,
"loss": 1.7375,
"step": 705
},
{
"epoch": 0.6035477666167984,
"grad_norm": 1.9176008701324463,
"learning_rate": 8.36278643646598e-06,
"loss": 1.6402,
"step": 706
},
{
"epoch": 0.6044026501389186,
"grad_norm": 1.7704726457595825,
"learning_rate": 8.357549125116548e-06,
"loss": 1.7303,
"step": 707
},
{
"epoch": 0.6052575336610387,
"grad_norm": 2.164355993270874,
"learning_rate": 8.352305096000197e-06,
"loss": 1.6992,
"step": 708
},
{
"epoch": 0.6061124171831588,
"grad_norm": 1.8429981470108032,
"learning_rate": 8.34705435960915e-06,
"loss": 1.492,
"step": 709
},
{
"epoch": 0.6069673007052789,
"grad_norm": 2.5694799423217773,
"learning_rate": 8.341796926449053e-06,
"loss": 1.4145,
"step": 710
},
{
"epoch": 0.607822184227399,
"grad_norm": 1.7566078901290894,
"learning_rate": 8.336532807038955e-06,
"loss": 1.5889,
"step": 711
},
{
"epoch": 0.6086770677495191,
"grad_norm": 1.7982147932052612,
"learning_rate": 8.331262011911276e-06,
"loss": 1.4725,
"step": 712
},
{
"epoch": 0.6095319512716393,
"grad_norm": 2.6575653553009033,
"learning_rate": 8.325984551611795e-06,
"loss": 1.3907,
"step": 713
},
{
"epoch": 0.6103868347937593,
"grad_norm": 1.905247688293457,
"learning_rate": 8.32070043669963e-06,
"loss": 1.4379,
"step": 714
},
{
"epoch": 0.6112417183158795,
"grad_norm": 2.1292531490325928,
"learning_rate": 8.315409677747207e-06,
"loss": 1.5796,
"step": 715
},
{
"epoch": 0.6120966018379995,
"grad_norm": 2.0380868911743164,
"learning_rate": 8.310112285340253e-06,
"loss": 1.5329,
"step": 716
},
{
"epoch": 0.6129514853601197,
"grad_norm": 2.1652815341949463,
"learning_rate": 8.30480827007776e-06,
"loss": 1.5661,
"step": 717
},
{
"epoch": 0.6138063688822398,
"grad_norm": 1.880020260810852,
"learning_rate": 8.299497642571976e-06,
"loss": 1.4771,
"step": 718
},
{
"epoch": 0.6146612524043599,
"grad_norm": 2.5005481243133545,
"learning_rate": 8.294180413448375e-06,
"loss": 1.559,
"step": 719
},
{
"epoch": 0.61551613592648,
"grad_norm": 2.4894957542419434,
"learning_rate": 8.288856593345647e-06,
"loss": 1.8233,
"step": 720
},
{
"epoch": 0.6163710194486002,
"grad_norm": 2.2092738151550293,
"learning_rate": 8.28352619291566e-06,
"loss": 1.5552,
"step": 721
},
{
"epoch": 0.6172259029707202,
"grad_norm": 1.7766340970993042,
"learning_rate": 8.27818922282345e-06,
"loss": 1.5893,
"step": 722
},
{
"epoch": 0.6180807864928404,
"grad_norm": 2.231019973754883,
"learning_rate": 8.2728456937472e-06,
"loss": 1.4948,
"step": 723
},
{
"epoch": 0.6189356700149604,
"grad_norm": 1.745932936668396,
"learning_rate": 8.267495616378218e-06,
"loss": 1.5268,
"step": 724
},
{
"epoch": 0.6197905535370806,
"grad_norm": 2.0638906955718994,
"learning_rate": 8.262139001420908e-06,
"loss": 1.6511,
"step": 725
},
{
"epoch": 0.6206454370592007,
"grad_norm": 2.589869976043701,
"learning_rate": 8.25677585959276e-06,
"loss": 1.4582,
"step": 726
},
{
"epoch": 0.6215003205813208,
"grad_norm": 1.792433500289917,
"learning_rate": 8.25140620162432e-06,
"loss": 1.8182,
"step": 727
},
{
"epoch": 0.6223552041034409,
"grad_norm": 2.4035418033599854,
"learning_rate": 8.246030038259168e-06,
"loss": 1.6119,
"step": 728
},
{
"epoch": 0.6232100876255611,
"grad_norm": 1.8025459051132202,
"learning_rate": 8.24064738025391e-06,
"loss": 1.6602,
"step": 729
},
{
"epoch": 0.6240649711476811,
"grad_norm": 2.1396055221557617,
"learning_rate": 8.235258238378137e-06,
"loss": 1.7282,
"step": 730
},
{
"epoch": 0.6249198546698013,
"grad_norm": 2.219912052154541,
"learning_rate": 8.229862623414414e-06,
"loss": 1.4117,
"step": 731
},
{
"epoch": 0.6257747381919213,
"grad_norm": 2.3299050331115723,
"learning_rate": 8.224460546158263e-06,
"loss": 1.8685,
"step": 732
},
{
"epoch": 0.6266296217140415,
"grad_norm": 1.8506113290786743,
"learning_rate": 8.219052017418132e-06,
"loss": 1.6644,
"step": 733
},
{
"epoch": 0.6274845052361616,
"grad_norm": 1.7105852365493774,
"learning_rate": 8.213637048015377e-06,
"loss": 1.5937,
"step": 734
},
{
"epoch": 0.6283393887582817,
"grad_norm": 2.0613906383514404,
"learning_rate": 8.208215648784239e-06,
"loss": 1.4237,
"step": 735
},
{
"epoch": 0.6291942722804018,
"grad_norm": 1.8658533096313477,
"learning_rate": 8.202787830571827e-06,
"loss": 1.5703,
"step": 736
},
{
"epoch": 0.6300491558025219,
"grad_norm": 1.8278007507324219,
"learning_rate": 8.197353604238092e-06,
"loss": 1.6099,
"step": 737
},
{
"epoch": 0.630904039324642,
"grad_norm": 1.771121621131897,
"learning_rate": 8.191912980655805e-06,
"loss": 1.6359,
"step": 738
},
{
"epoch": 0.6317589228467622,
"grad_norm": 1.960795283317566,
"learning_rate": 8.186465970710538e-06,
"loss": 1.4287,
"step": 739
},
{
"epoch": 0.6326138063688822,
"grad_norm": 2.8525185585021973,
"learning_rate": 8.18101258530064e-06,
"loss": 1.6827,
"step": 740
},
{
"epoch": 0.6334686898910024,
"grad_norm": 2.644296646118164,
"learning_rate": 8.175552835337217e-06,
"loss": 1.6391,
"step": 741
},
{
"epoch": 0.6343235734131225,
"grad_norm": 1.9095778465270996,
"learning_rate": 8.170086731744108e-06,
"loss": 1.4497,
"step": 742
},
{
"epoch": 0.6351784569352426,
"grad_norm": 2.616870403289795,
"learning_rate": 8.164614285457865e-06,
"loss": 1.603,
"step": 743
},
{
"epoch": 0.6360333404573627,
"grad_norm": 2.0195326805114746,
"learning_rate": 8.159135507427728e-06,
"loss": 1.7662,
"step": 744
},
{
"epoch": 0.6368882239794827,
"grad_norm": 1.9145680665969849,
"learning_rate": 8.153650408615612e-06,
"loss": 1.6994,
"step": 745
},
{
"epoch": 0.6377431075016029,
"grad_norm": 1.7627846002578735,
"learning_rate": 8.148158999996072e-06,
"loss": 1.6093,
"step": 746
},
{
"epoch": 0.638597991023723,
"grad_norm": 2.2810473442077637,
"learning_rate": 8.142661292556289e-06,
"loss": 1.5305,
"step": 747
},
{
"epoch": 0.6394528745458431,
"grad_norm": 1.902381420135498,
"learning_rate": 8.13715729729605e-06,
"loss": 1.5481,
"step": 748
},
{
"epoch": 0.6403077580679633,
"grad_norm": 2.120807647705078,
"learning_rate": 8.131647025227718e-06,
"loss": 1.4634,
"step": 749
},
{
"epoch": 0.6411626415900834,
"grad_norm": 1.7931264638900757,
"learning_rate": 8.126130487376217e-06,
"loss": 1.5927,
"step": 750
},
{
"epoch": 0.6420175251122034,
"grad_norm": 2.521458864212036,
"learning_rate": 8.12060769477901e-06,
"loss": 1.494,
"step": 751
},
{
"epoch": 0.6428724086343236,
"grad_norm": 1.7701094150543213,
"learning_rate": 8.115078658486069e-06,
"loss": 1.8399,
"step": 752
},
{
"epoch": 0.6437272921564436,
"grad_norm": 1.8709700107574463,
"learning_rate": 8.109543389559861e-06,
"loss": 1.6305,
"step": 753
},
{
"epoch": 0.6445821756785638,
"grad_norm": 1.9467986822128296,
"learning_rate": 8.104001899075326e-06,
"loss": 1.4801,
"step": 754
},
{
"epoch": 0.645437059200684,
"grad_norm": 1.808092713356018,
"learning_rate": 8.098454198119847e-06,
"loss": 1.5535,
"step": 755
},
{
"epoch": 0.646291942722804,
"grad_norm": 2.0982744693756104,
"learning_rate": 8.092900297793238e-06,
"loss": 1.3704,
"step": 756
},
{
"epoch": 0.6471468262449241,
"grad_norm": 1.8450520038604736,
"learning_rate": 8.087340209207713e-06,
"loss": 1.5287,
"step": 757
},
{
"epoch": 0.6480017097670442,
"grad_norm": 1.7327725887298584,
"learning_rate": 8.081773943487868e-06,
"loss": 1.7342,
"step": 758
},
{
"epoch": 0.6488565932891643,
"grad_norm": 1.7313075065612793,
"learning_rate": 8.076201511770656e-06,
"loss": 1.4301,
"step": 759
},
{
"epoch": 0.6497114768112845,
"grad_norm": 1.9029062986373901,
"learning_rate": 8.070622925205373e-06,
"loss": 1.7459,
"step": 760
},
{
"epoch": 0.6505663603334045,
"grad_norm": 1.8386952877044678,
"learning_rate": 8.065038194953629e-06,
"loss": 1.596,
"step": 761
},
{
"epoch": 0.6514212438555247,
"grad_norm": 1.8669521808624268,
"learning_rate": 8.059447332189317e-06,
"loss": 1.5973,
"step": 762
},
{
"epoch": 0.6522761273776448,
"grad_norm": 1.802152395248413,
"learning_rate": 8.053850348098609e-06,
"loss": 1.7115,
"step": 763
},
{
"epoch": 0.6531310108997649,
"grad_norm": 1.7956647872924805,
"learning_rate": 8.048247253879922e-06,
"loss": 1.73,
"step": 764
},
{
"epoch": 0.653985894421885,
"grad_norm": 1.870807409286499,
"learning_rate": 8.042638060743898e-06,
"loss": 1.4755,
"step": 765
},
{
"epoch": 0.6548407779440051,
"grad_norm": 1.993764042854309,
"learning_rate": 8.037022779913382e-06,
"loss": 1.2867,
"step": 766
},
{
"epoch": 0.6556956614661252,
"grad_norm": 1.7236435413360596,
"learning_rate": 8.031401422623398e-06,
"loss": 1.8303,
"step": 767
},
{
"epoch": 0.6565505449882454,
"grad_norm": 1.9870823621749878,
"learning_rate": 8.02577400012113e-06,
"loss": 1.6378,
"step": 768
},
{
"epoch": 0.6574054285103654,
"grad_norm": 1.9288864135742188,
"learning_rate": 8.020140523665891e-06,
"loss": 1.5775,
"step": 769
},
{
"epoch": 0.6582603120324856,
"grad_norm": 1.7029926776885986,
"learning_rate": 8.014501004529118e-06,
"loss": 1.53,
"step": 770
},
{
"epoch": 0.6591151955546057,
"grad_norm": 1.9869303703308105,
"learning_rate": 8.00885545399433e-06,
"loss": 1.4813,
"step": 771
},
{
"epoch": 0.6599700790767258,
"grad_norm": 1.790546178817749,
"learning_rate": 8.003203883357113e-06,
"loss": 1.7271,
"step": 772
},
{
"epoch": 0.6608249625988459,
"grad_norm": 1.8250300884246826,
"learning_rate": 7.9975463039251e-06,
"loss": 1.682,
"step": 773
},
{
"epoch": 0.661679846120966,
"grad_norm": 1.9827724695205688,
"learning_rate": 7.99188272701795e-06,
"loss": 1.6004,
"step": 774
},
{
"epoch": 0.6625347296430861,
"grad_norm": 2.0887629985809326,
"learning_rate": 7.986213163967319e-06,
"loss": 1.4962,
"step": 775
},
{
"epoch": 0.6633896131652063,
"grad_norm": 1.8804274797439575,
"learning_rate": 7.980537626116833e-06,
"loss": 1.6097,
"step": 776
},
{
"epoch": 0.6642444966873263,
"grad_norm": 1.977057695388794,
"learning_rate": 7.974856124822084e-06,
"loss": 1.7107,
"step": 777
},
{
"epoch": 0.6650993802094465,
"grad_norm": 1.8675955533981323,
"learning_rate": 7.969168671450589e-06,
"loss": 1.5859,
"step": 778
},
{
"epoch": 0.6659542637315665,
"grad_norm": 1.7858625650405884,
"learning_rate": 7.963475277381776e-06,
"loss": 1.6198,
"step": 779
},
{
"epoch": 0.6668091472536867,
"grad_norm": 1.965219259262085,
"learning_rate": 7.957775954006958e-06,
"loss": 1.7028,
"step": 780
},
{
"epoch": 0.6676640307758068,
"grad_norm": 2.2767865657806396,
"learning_rate": 7.952070712729312e-06,
"loss": 1.6028,
"step": 781
},
{
"epoch": 0.6685189142979269,
"grad_norm": 2.385225772857666,
"learning_rate": 7.946359564963852e-06,
"loss": 1.4741,
"step": 782
},
{
"epoch": 0.669373797820047,
"grad_norm": 1.8306634426116943,
"learning_rate": 7.94064252213742e-06,
"loss": 1.5779,
"step": 783
},
{
"epoch": 0.6702286813421672,
"grad_norm": 1.881840705871582,
"learning_rate": 7.934919595688639e-06,
"loss": 1.5447,
"step": 784
},
{
"epoch": 0.6710835648642872,
"grad_norm": 2.4943602085113525,
"learning_rate": 7.929190797067913e-06,
"loss": 1.5807,
"step": 785
},
{
"epoch": 0.6719384483864074,
"grad_norm": 1.7710949182510376,
"learning_rate": 7.923456137737396e-06,
"loss": 1.5805,
"step": 786
},
{
"epoch": 0.6727933319085274,
"grad_norm": 1.6917473077774048,
"learning_rate": 7.917715629170957e-06,
"loss": 1.5093,
"step": 787
},
{
"epoch": 0.6736482154306476,
"grad_norm": 2.0921974182128906,
"learning_rate": 7.911969282854184e-06,
"loss": 1.6146,
"step": 788
},
{
"epoch": 0.6745030989527677,
"grad_norm": 2.2254960536956787,
"learning_rate": 7.90621711028433e-06,
"loss": 1.7173,
"step": 789
},
{
"epoch": 0.6753579824748878,
"grad_norm": 1.8926316499710083,
"learning_rate": 7.900459122970318e-06,
"loss": 1.6318,
"step": 790
},
{
"epoch": 0.6762128659970079,
"grad_norm": 2.05529522895813,
"learning_rate": 7.894695332432695e-06,
"loss": 1.5956,
"step": 791
},
{
"epoch": 0.6770677495191281,
"grad_norm": 1.8146142959594727,
"learning_rate": 7.888925750203627e-06,
"loss": 1.6321,
"step": 792
},
{
"epoch": 0.6779226330412481,
"grad_norm": 2.046912431716919,
"learning_rate": 7.88315038782686e-06,
"loss": 1.429,
"step": 793
},
{
"epoch": 0.6787775165633683,
"grad_norm": 1.7644606828689575,
"learning_rate": 7.877369256857712e-06,
"loss": 1.6365,
"step": 794
},
{
"epoch": 0.6796324000854883,
"grad_norm": 2.004549264907837,
"learning_rate": 7.87158236886304e-06,
"loss": 1.4164,
"step": 795
},
{
"epoch": 0.6804872836076085,
"grad_norm": 1.8180807828903198,
"learning_rate": 7.865789735421218e-06,
"loss": 1.7249,
"step": 796
},
{
"epoch": 0.6813421671297286,
"grad_norm": 1.9642592668533325,
"learning_rate": 7.85999136812212e-06,
"loss": 1.5871,
"step": 797
},
{
"epoch": 0.6821970506518487,
"grad_norm": 1.7459617853164673,
"learning_rate": 7.854187278567084e-06,
"loss": 1.6564,
"step": 798
},
{
"epoch": 0.6830519341739688,
"grad_norm": 1.795413851737976,
"learning_rate": 7.848377478368907e-06,
"loss": 1.5304,
"step": 799
},
{
"epoch": 0.6839068176960889,
"grad_norm": 2.375990629196167,
"learning_rate": 7.842561979151806e-06,
"loss": 1.4079,
"step": 800
},
{
"epoch": 0.684761701218209,
"grad_norm": 2.3698506355285645,
"learning_rate": 7.836740792551402e-06,
"loss": 1.7428,
"step": 801
},
{
"epoch": 0.6856165847403292,
"grad_norm": 2.1372928619384766,
"learning_rate": 7.830913930214693e-06,
"loss": 1.5636,
"step": 802
},
{
"epoch": 0.6864714682624492,
"grad_norm": 1.936754584312439,
"learning_rate": 7.825081403800039e-06,
"loss": 1.6307,
"step": 803
},
{
"epoch": 0.6873263517845694,
"grad_norm": 1.8657773733139038,
"learning_rate": 7.819243224977125e-06,
"loss": 1.6783,
"step": 804
},
{
"epoch": 0.6881812353066895,
"grad_norm": 2.2650933265686035,
"learning_rate": 7.813399405426951e-06,
"loss": 1.4729,
"step": 805
},
{
"epoch": 0.6890361188288096,
"grad_norm": 1.953281044960022,
"learning_rate": 7.807549956841799e-06,
"loss": 1.544,
"step": 806
},
{
"epoch": 0.6898910023509297,
"grad_norm": 2.140019416809082,
"learning_rate": 7.801694890925218e-06,
"loss": 1.411,
"step": 807
},
{
"epoch": 0.6907458858730497,
"grad_norm": 2.071019411087036,
"learning_rate": 7.795834219391991e-06,
"loss": 1.5566,
"step": 808
},
{
"epoch": 0.6916007693951699,
"grad_norm": 2.667649269104004,
"learning_rate": 7.78996795396812e-06,
"loss": 1.5058,
"step": 809
},
{
"epoch": 0.69245565291729,
"grad_norm": 1.9877266883850098,
"learning_rate": 7.7840961063908e-06,
"loss": 1.6074,
"step": 810
},
{
"epoch": 0.6933105364394101,
"grad_norm": 2.031243324279785,
"learning_rate": 7.778218688408391e-06,
"loss": 1.5835,
"step": 811
},
{
"epoch": 0.6941654199615303,
"grad_norm": 1.9558823108673096,
"learning_rate": 7.772335711780404e-06,
"loss": 1.4158,
"step": 812
},
{
"epoch": 0.6950203034836504,
"grad_norm": 1.8911411762237549,
"learning_rate": 7.766447188277465e-06,
"loss": 1.6014,
"step": 813
},
{
"epoch": 0.6958751870057704,
"grad_norm": 2.080173969268799,
"learning_rate": 7.760553129681303e-06,
"loss": 1.7275,
"step": 814
},
{
"epoch": 0.6967300705278906,
"grad_norm": 2.0678954124450684,
"learning_rate": 7.754653547784718e-06,
"loss": 1.5159,
"step": 815
},
{
"epoch": 0.6975849540500106,
"grad_norm": 3.0976686477661133,
"learning_rate": 7.748748454391565e-06,
"loss": 1.6922,
"step": 816
},
{
"epoch": 0.6984398375721308,
"grad_norm": 1.6842857599258423,
"learning_rate": 7.742837861316722e-06,
"loss": 1.7449,
"step": 817
},
{
"epoch": 0.699294721094251,
"grad_norm": 1.756474494934082,
"learning_rate": 7.736921780386077e-06,
"loss": 1.7359,
"step": 818
},
{
"epoch": 0.700149604616371,
"grad_norm": 1.9712620973587036,
"learning_rate": 7.731000223436491e-06,
"loss": 1.5419,
"step": 819
},
{
"epoch": 0.7010044881384911,
"grad_norm": 2.3988850116729736,
"learning_rate": 7.725073202315786e-06,
"loss": 1.6395,
"step": 820
},
{
"epoch": 0.7018593716606112,
"grad_norm": 1.8440942764282227,
"learning_rate": 7.719140728882713e-06,
"loss": 1.7084,
"step": 821
},
{
"epoch": 0.7027142551827313,
"grad_norm": 1.777246356010437,
"learning_rate": 7.713202815006938e-06,
"loss": 1.7737,
"step": 822
},
{
"epoch": 0.7035691387048515,
"grad_norm": 1.8486806154251099,
"learning_rate": 7.707259472569001e-06,
"loss": 1.6888,
"step": 823
},
{
"epoch": 0.7044240222269715,
"grad_norm": 1.8133748769760132,
"learning_rate": 7.70131071346032e-06,
"loss": 1.7211,
"step": 824
},
{
"epoch": 0.7052789057490917,
"grad_norm": 1.8560314178466797,
"learning_rate": 7.695356549583135e-06,
"loss": 1.5751,
"step": 825
},
{
"epoch": 0.7061337892712118,
"grad_norm": 1.7498633861541748,
"learning_rate": 7.689396992850511e-06,
"loss": 1.6105,
"step": 826
},
{
"epoch": 0.7069886727933319,
"grad_norm": 2.0831539630889893,
"learning_rate": 7.683432055186293e-06,
"loss": 1.4881,
"step": 827
},
{
"epoch": 0.707843556315452,
"grad_norm": 1.8828967809677124,
"learning_rate": 7.677461748525103e-06,
"loss": 1.5878,
"step": 828
},
{
"epoch": 0.7086984398375721,
"grad_norm": 2.1139395236968994,
"learning_rate": 7.671486084812297e-06,
"loss": 1.5399,
"step": 829
},
{
"epoch": 0.7095533233596922,
"grad_norm": 1.7683391571044922,
"learning_rate": 7.66550507600395e-06,
"loss": 1.629,
"step": 830
},
{
"epoch": 0.7104082068818124,
"grad_norm": 2.1067309379577637,
"learning_rate": 7.659518734066836e-06,
"loss": 1.6089,
"step": 831
},
{
"epoch": 0.7112630904039324,
"grad_norm": 2.715237855911255,
"learning_rate": 7.653527070978396e-06,
"loss": 1.7623,
"step": 832
},
{
"epoch": 0.7121179739260526,
"grad_norm": 2.029066562652588,
"learning_rate": 7.64753009872672e-06,
"loss": 1.4605,
"step": 833
},
{
"epoch": 0.7129728574481727,
"grad_norm": 2.040937662124634,
"learning_rate": 7.641527829310516e-06,
"loss": 1.6259,
"step": 834
},
{
"epoch": 0.7138277409702928,
"grad_norm": 1.8791722059249878,
"learning_rate": 7.635520274739097e-06,
"loss": 1.5471,
"step": 835
},
{
"epoch": 0.7146826244924129,
"grad_norm": 1.9070911407470703,
"learning_rate": 7.629507447032346e-06,
"loss": 1.6921,
"step": 836
},
{
"epoch": 0.715537508014533,
"grad_norm": 1.9708362817764282,
"learning_rate": 7.623489358220696e-06,
"loss": 1.6241,
"step": 837
},
{
"epoch": 0.7163923915366531,
"grad_norm": 2.182068347930908,
"learning_rate": 7.61746602034511e-06,
"loss": 1.7642,
"step": 838
},
{
"epoch": 0.7172472750587733,
"grad_norm": 1.9108189344406128,
"learning_rate": 7.61143744545705e-06,
"loss": 1.5918,
"step": 839
},
{
"epoch": 0.7181021585808933,
"grad_norm": 2.457728624343872,
"learning_rate": 7.605403645618459e-06,
"loss": 1.5499,
"step": 840
},
{
"epoch": 0.7189570421030135,
"grad_norm": 2.1395840644836426,
"learning_rate": 7.599364632901731e-06,
"loss": 1.7547,
"step": 841
},
{
"epoch": 0.7198119256251336,
"grad_norm": 2.3625380992889404,
"learning_rate": 7.593320419389691e-06,
"loss": 1.4591,
"step": 842
},
{
"epoch": 0.7206668091472537,
"grad_norm": 1.7292894124984741,
"learning_rate": 7.5872710171755725e-06,
"loss": 1.6768,
"step": 843
},
{
"epoch": 0.7215216926693738,
"grad_norm": 2.7999610900878906,
"learning_rate": 7.581216438362986e-06,
"loss": 1.645,
"step": 844
},
{
"epoch": 0.7223765761914939,
"grad_norm": 2.0571372509002686,
"learning_rate": 7.575156695065902e-06,
"loss": 1.5302,
"step": 845
},
{
"epoch": 0.723231459713614,
"grad_norm": 2.070894956588745,
"learning_rate": 7.569091799408624e-06,
"loss": 1.8008,
"step": 846
},
{
"epoch": 0.7240863432357342,
"grad_norm": 2.6990160942077637,
"learning_rate": 7.5630217635257615e-06,
"loss": 1.4371,
"step": 847
},
{
"epoch": 0.7249412267578542,
"grad_norm": 1.9898473024368286,
"learning_rate": 7.556946599562216e-06,
"loss": 1.3214,
"step": 848
},
{
"epoch": 0.7257961102799744,
"grad_norm": 2.095768451690674,
"learning_rate": 7.550866319673139e-06,
"loss": 1.5759,
"step": 849
},
{
"epoch": 0.7266509938020944,
"grad_norm": 1.862705945968628,
"learning_rate": 7.544780936023926e-06,
"loss": 1.7743,
"step": 850
},
{
"epoch": 0.7275058773242146,
"grad_norm": 1.8628978729248047,
"learning_rate": 7.538690460790179e-06,
"loss": 1.4388,
"step": 851
},
{
"epoch": 0.7283607608463347,
"grad_norm": 1.8021178245544434,
"learning_rate": 7.532594906157692e-06,
"loss": 1.857,
"step": 852
},
{
"epoch": 0.7292156443684548,
"grad_norm": 2.5704119205474854,
"learning_rate": 7.526494284322416e-06,
"loss": 1.6302,
"step": 853
},
{
"epoch": 0.7300705278905749,
"grad_norm": 1.6791504621505737,
"learning_rate": 7.520388607490447e-06,
"loss": 1.7683,
"step": 854
},
{
"epoch": 0.7309254114126951,
"grad_norm": 3.8832380771636963,
"learning_rate": 7.51427788787799e-06,
"loss": 1.5744,
"step": 855
},
{
"epoch": 0.7317802949348151,
"grad_norm": 3.7836060523986816,
"learning_rate": 7.508162137711341e-06,
"loss": 1.739,
"step": 856
},
{
"epoch": 0.7326351784569353,
"grad_norm": 3.189974308013916,
"learning_rate": 7.502041369226862e-06,
"loss": 1.7167,
"step": 857
},
{
"epoch": 0.7334900619790553,
"grad_norm": 2.0712730884552,
"learning_rate": 7.495915594670953e-06,
"loss": 1.5468,
"step": 858
},
{
"epoch": 0.7343449455011755,
"grad_norm": 1.7717161178588867,
"learning_rate": 7.489784826300033e-06,
"loss": 1.7483,
"step": 859
},
{
"epoch": 0.7351998290232956,
"grad_norm": 2.4180703163146973,
"learning_rate": 7.483649076380512e-06,
"loss": 1.6412,
"step": 860
},
{
"epoch": 0.7360547125454157,
"grad_norm": 2.175175189971924,
"learning_rate": 7.477508357188769e-06,
"loss": 1.5923,
"step": 861
},
{
"epoch": 0.7369095960675358,
"grad_norm": 1.7840341329574585,
"learning_rate": 7.47136268101112e-06,
"loss": 1.7442,
"step": 862
},
{
"epoch": 0.737764479589656,
"grad_norm": 2.045222520828247,
"learning_rate": 7.465212060143802e-06,
"loss": 1.5055,
"step": 863
},
{
"epoch": 0.738619363111776,
"grad_norm": 1.7603466510772705,
"learning_rate": 7.459056506892946e-06,
"loss": 1.5209,
"step": 864
},
{
"epoch": 0.7394742466338962,
"grad_norm": 1.823033094406128,
"learning_rate": 7.452896033574552e-06,
"loss": 1.5858,
"step": 865
},
{
"epoch": 0.7403291301560162,
"grad_norm": 1.8318334817886353,
"learning_rate": 7.446730652514464e-06,
"loss": 1.5982,
"step": 866
},
{
"epoch": 0.7411840136781364,
"grad_norm": 1.8965398073196411,
"learning_rate": 7.4405603760483425e-06,
"loss": 1.4889,
"step": 867
},
{
"epoch": 0.7420388972002565,
"grad_norm": 1.8694148063659668,
"learning_rate": 7.434385216521645e-06,
"loss": 1.5792,
"step": 868
},
{
"epoch": 0.7428937807223766,
"grad_norm": 1.8063355684280396,
"learning_rate": 7.428205186289601e-06,
"loss": 1.617,
"step": 869
},
{
"epoch": 0.7437486642444967,
"grad_norm": 2.0516574382781982,
"learning_rate": 7.42202029771718e-06,
"loss": 1.8309,
"step": 870
},
{
"epoch": 0.7446035477666167,
"grad_norm": 2.1008880138397217,
"learning_rate": 7.415830563179077e-06,
"loss": 1.6068,
"step": 871
},
{
"epoch": 0.7454584312887369,
"grad_norm": 1.826690912246704,
"learning_rate": 7.409635995059679e-06,
"loss": 1.4517,
"step": 872
},
{
"epoch": 0.746313314810857,
"grad_norm": 2.040496826171875,
"learning_rate": 7.403436605753047e-06,
"loss": 1.5598,
"step": 873
},
{
"epoch": 0.7471681983329771,
"grad_norm": 1.6369898319244385,
"learning_rate": 7.3972324076628876e-06,
"loss": 1.6301,
"step": 874
},
{
"epoch": 0.7480230818550972,
"grad_norm": 2.6623289585113525,
"learning_rate": 7.391023413202528e-06,
"loss": 1.7157,
"step": 875
},
{
"epoch": 0.7488779653772174,
"grad_norm": 1.9073917865753174,
"learning_rate": 7.384809634794891e-06,
"loss": 1.6098,
"step": 876
},
{
"epoch": 0.7497328488993374,
"grad_norm": 1.9829678535461426,
"learning_rate": 7.378591084872474e-06,
"loss": 1.6042,
"step": 877
},
{
"epoch": 0.7505877324214576,
"grad_norm": 2.025413990020752,
"learning_rate": 7.372367775877318e-06,
"loss": 1.4811,
"step": 878
},
{
"epoch": 0.7514426159435776,
"grad_norm": 1.8276697397232056,
"learning_rate": 7.366139720260988e-06,
"loss": 1.4816,
"step": 879
},
{
"epoch": 0.7514426159435776,
"eval_loss": 1.6207854747772217,
"eval_runtime": 535.4228,
"eval_samples_per_second": 7.389,
"eval_steps_per_second": 3.694,
"step": 879
},
{
"epoch": 0.7522974994656978,
"grad_norm": 1.7088907957077026,
"learning_rate": 7.359906930484546e-06,
"loss": 1.667,
"step": 880
},
{
"epoch": 0.753152382987818,
"grad_norm": 1.966194748878479,
"learning_rate": 7.353669419018525e-06,
"loss": 1.5384,
"step": 881
},
{
"epoch": 0.754007266509938,
"grad_norm": 1.6948115825653076,
"learning_rate": 7.347427198342907e-06,
"loss": 1.6488,
"step": 882
},
{
"epoch": 0.7548621500320581,
"grad_norm": 1.7349025011062622,
"learning_rate": 7.3411802809470935e-06,
"loss": 1.3846,
"step": 883
},
{
"epoch": 0.7557170335541783,
"grad_norm": 2.215358257293701,
"learning_rate": 7.334928679329882e-06,
"loss": 1.419,
"step": 884
},
{
"epoch": 0.7565719170762983,
"grad_norm": 2.094088315963745,
"learning_rate": 7.328672405999451e-06,
"loss": 1.6216,
"step": 885
},
{
"epoch": 0.7574268005984185,
"grad_norm": 1.7907602787017822,
"learning_rate": 7.3224114734733135e-06,
"loss": 1.5837,
"step": 886
},
{
"epoch": 0.7582816841205385,
"grad_norm": 1.775529384613037,
"learning_rate": 7.316145894278315e-06,
"loss": 1.7301,
"step": 887
},
{
"epoch": 0.7591365676426587,
"grad_norm": 1.867698311805725,
"learning_rate": 7.309875680950591e-06,
"loss": 1.6867,
"step": 888
},
{
"epoch": 0.7599914511647788,
"grad_norm": 1.9435536861419678,
"learning_rate": 7.303600846035556e-06,
"loss": 1.5512,
"step": 889
},
{
"epoch": 0.7608463346868989,
"grad_norm": 1.9748835563659668,
"learning_rate": 7.297321402087861e-06,
"loss": 1.4949,
"step": 890
},
{
"epoch": 0.761701218209019,
"grad_norm": 2.0852553844451904,
"learning_rate": 7.291037361671392e-06,
"loss": 1.6525,
"step": 891
},
{
"epoch": 0.7625561017311391,
"grad_norm": 1.7555006742477417,
"learning_rate": 7.28474873735922e-06,
"loss": 1.8248,
"step": 892
},
{
"epoch": 0.7634109852532592,
"grad_norm": 2.189694881439209,
"learning_rate": 7.2784555417335935e-06,
"loss": 1.6947,
"step": 893
},
{
"epoch": 0.7642658687753794,
"grad_norm": 1.8032170534133911,
"learning_rate": 7.272157787385904e-06,
"loss": 1.804,
"step": 894
},
{
"epoch": 0.7651207522974994,
"grad_norm": 2.116745710372925,
"learning_rate": 7.265855486916668e-06,
"loss": 1.6142,
"step": 895
},
{
"epoch": 0.7659756358196196,
"grad_norm": 1.9036099910736084,
"learning_rate": 7.259548652935495e-06,
"loss": 1.4026,
"step": 896
},
{
"epoch": 0.7668305193417397,
"grad_norm": 1.8711966276168823,
"learning_rate": 7.253237298061066e-06,
"loss": 1.6825,
"step": 897
},
{
"epoch": 0.7676854028638598,
"grad_norm": 1.8057702779769897,
"learning_rate": 7.246921434921106e-06,
"loss": 1.5902,
"step": 898
},
{
"epoch": 0.7685402863859799,
"grad_norm": 1.9403468370437622,
"learning_rate": 7.2406010761523624e-06,
"loss": 1.5219,
"step": 899
},
{
"epoch": 0.7693951699081,
"grad_norm": 1.751898169517517,
"learning_rate": 7.234276234400577e-06,
"loss": 1.7528,
"step": 900
},
{
"epoch": 0.7702500534302201,
"grad_norm": 1.8883317708969116,
"learning_rate": 7.22794692232046e-06,
"loss": 1.517,
"step": 901
},
{
"epoch": 0.7711049369523403,
"grad_norm": 2.5952086448669434,
"learning_rate": 7.221613152575664e-06,
"loss": 1.6828,
"step": 902
},
{
"epoch": 0.7719598204744603,
"grad_norm": 2.416489362716675,
"learning_rate": 7.215274937838768e-06,
"loss": 1.7045,
"step": 903
},
{
"epoch": 0.7728147039965805,
"grad_norm": 1.994223952293396,
"learning_rate": 7.208932290791232e-06,
"loss": 1.577,
"step": 904
},
{
"epoch": 0.7736695875187006,
"grad_norm": 2.458573341369629,
"learning_rate": 7.2025852241233975e-06,
"loss": 1.8009,
"step": 905
},
{
"epoch": 0.7745244710408207,
"grad_norm": 1.8616794347763062,
"learning_rate": 7.1962337505344385e-06,
"loss": 1.5317,
"step": 906
},
{
"epoch": 0.7753793545629408,
"grad_norm": 2.1416566371917725,
"learning_rate": 7.1898778827323544e-06,
"loss": 1.9288,
"step": 907
},
{
"epoch": 0.7762342380850609,
"grad_norm": 2.3308708667755127,
"learning_rate": 7.18351763343393e-06,
"loss": 1.4747,
"step": 908
},
{
"epoch": 0.777089121607181,
"grad_norm": 1.7730233669281006,
"learning_rate": 7.17715301536472e-06,
"loss": 1.7181,
"step": 909
},
{
"epoch": 0.7779440051293012,
"grad_norm": 2.1546826362609863,
"learning_rate": 7.170784041259018e-06,
"loss": 1.6143,
"step": 910
},
{
"epoch": 0.7787988886514212,
"grad_norm": 1.9400556087493896,
"learning_rate": 7.164410723859837e-06,
"loss": 1.6772,
"step": 911
},
{
"epoch": 0.7796537721735414,
"grad_norm": 1.798427700996399,
"learning_rate": 7.1580330759188755e-06,
"loss": 1.5083,
"step": 912
},
{
"epoch": 0.7805086556956614,
"grad_norm": 1.7825255393981934,
"learning_rate": 7.151651110196499e-06,
"loss": 1.6398,
"step": 913
},
{
"epoch": 0.7813635392177816,
"grad_norm": 2.0335419178009033,
"learning_rate": 7.145264839461712e-06,
"loss": 1.4382,
"step": 914
},
{
"epoch": 0.7822184227399017,
"grad_norm": 2.093400239944458,
"learning_rate": 7.13887427649213e-06,
"loss": 1.5794,
"step": 915
},
{
"epoch": 0.7830733062620218,
"grad_norm": 2.1397252082824707,
"learning_rate": 7.132479434073961e-06,
"loss": 1.6183,
"step": 916
},
{
"epoch": 0.7839281897841419,
"grad_norm": 2.8461811542510986,
"learning_rate": 7.126080325001972e-06,
"loss": 1.531,
"step": 917
},
{
"epoch": 0.7847830733062621,
"grad_norm": 3.3926584720611572,
"learning_rate": 7.119676962079467e-06,
"loss": 1.341,
"step": 918
},
{
"epoch": 0.7856379568283821,
"grad_norm": 2.23746395111084,
"learning_rate": 7.113269358118261e-06,
"loss": 1.4222,
"step": 919
},
{
"epoch": 0.7864928403505023,
"grad_norm": 3.6582369804382324,
"learning_rate": 7.106857525938653e-06,
"loss": 1.5119,
"step": 920
},
{
"epoch": 0.7873477238726223,
"grad_norm": 2.5623018741607666,
"learning_rate": 7.1004414783694086e-06,
"loss": 1.485,
"step": 921
},
{
"epoch": 0.7882026073947425,
"grad_norm": 2.459796667098999,
"learning_rate": 7.094021228247719e-06,
"loss": 1.3955,
"step": 922
},
{
"epoch": 0.7890574909168626,
"grad_norm": 1.6993489265441895,
"learning_rate": 7.087596788419188e-06,
"loss": 1.607,
"step": 923
},
{
"epoch": 0.7899123744389827,
"grad_norm": 1.889883279800415,
"learning_rate": 7.0811681717378e-06,
"loss": 1.6804,
"step": 924
},
{
"epoch": 0.7907672579611028,
"grad_norm": 2.538088321685791,
"learning_rate": 7.074735391065902e-06,
"loss": 1.3981,
"step": 925
},
{
"epoch": 0.791622141483223,
"grad_norm": 1.839068055152893,
"learning_rate": 7.068298459274164e-06,
"loss": 1.7209,
"step": 926
},
{
"epoch": 0.792477025005343,
"grad_norm": 1.996674656867981,
"learning_rate": 7.061857389241571e-06,
"loss": 1.6024,
"step": 927
},
{
"epoch": 0.7933319085274632,
"grad_norm": 1.8009898662567139,
"learning_rate": 7.055412193855378e-06,
"loss": 1.6207,
"step": 928
},
{
"epoch": 0.7941867920495832,
"grad_norm": 2.152193307876587,
"learning_rate": 7.0489628860110995e-06,
"loss": 1.5904,
"step": 929
},
{
"epoch": 0.7950416755717034,
"grad_norm": 1.833527684211731,
"learning_rate": 7.042509478612478e-06,
"loss": 1.6231,
"step": 930
},
{
"epoch": 0.7958965590938235,
"grad_norm": 1.7650495767593384,
"learning_rate": 7.036051984571457e-06,
"loss": 1.7468,
"step": 931
},
{
"epoch": 0.7967514426159436,
"grad_norm": 1.8895305395126343,
"learning_rate": 7.029590416808159e-06,
"loss": 1.6374,
"step": 932
},
{
"epoch": 0.7976063261380637,
"grad_norm": 2.057009696960449,
"learning_rate": 7.0231247882508525e-06,
"loss": 1.8619,
"step": 933
},
{
"epoch": 0.7984612096601837,
"grad_norm": 2.100050687789917,
"learning_rate": 7.016655111835936e-06,
"loss": 1.8066,
"step": 934
},
{
"epoch": 0.7993160931823039,
"grad_norm": 2.233248233795166,
"learning_rate": 7.010181400507903e-06,
"loss": 1.344,
"step": 935
},
{
"epoch": 0.800170976704424,
"grad_norm": 3.189713954925537,
"learning_rate": 7.003703667219323e-06,
"loss": 1.6922,
"step": 936
},
{
"epoch": 0.8010258602265441,
"grad_norm": 2.6081111431121826,
"learning_rate": 6.997221924930811e-06,
"loss": 1.4681,
"step": 937
},
{
"epoch": 0.8018807437486642,
"grad_norm": 2.012056350708008,
"learning_rate": 6.9907361866110026e-06,
"loss": 1.6555,
"step": 938
},
{
"epoch": 0.8027356272707844,
"grad_norm": 1.9229539632797241,
"learning_rate": 6.984246465236532e-06,
"loss": 1.6648,
"step": 939
},
{
"epoch": 0.8035905107929044,
"grad_norm": 2.1851089000701904,
"learning_rate": 6.9777527737919945e-06,
"loss": 1.5953,
"step": 940
},
{
"epoch": 0.8044453943150246,
"grad_norm": 1.743334412574768,
"learning_rate": 6.971255125269941e-06,
"loss": 1.591,
"step": 941
},
{
"epoch": 0.8053002778371446,
"grad_norm": 2.002300977706909,
"learning_rate": 6.9647535326708274e-06,
"loss": 1.6162,
"step": 942
},
{
"epoch": 0.8061551613592648,
"grad_norm": 2.2001571655273438,
"learning_rate": 6.958248009003013e-06,
"loss": 1.6559,
"step": 943
},
{
"epoch": 0.807010044881385,
"grad_norm": 1.9847776889801025,
"learning_rate": 6.951738567282709e-06,
"loss": 1.5787,
"step": 944
},
{
"epoch": 0.807864928403505,
"grad_norm": 2.376133680343628,
"learning_rate": 6.945225220533977e-06,
"loss": 1.5572,
"step": 945
},
{
"epoch": 0.8087198119256251,
"grad_norm": 2.4176290035247803,
"learning_rate": 6.938707981788685e-06,
"loss": 1.4635,
"step": 946
},
{
"epoch": 0.8095746954477453,
"grad_norm": 1.9553080797195435,
"learning_rate": 6.932186864086493e-06,
"loss": 1.5046,
"step": 947
},
{
"epoch": 0.8104295789698653,
"grad_norm": 1.8396267890930176,
"learning_rate": 6.925661880474818e-06,
"loss": 1.5988,
"step": 948
},
{
"epoch": 0.8112844624919855,
"grad_norm": 2.076810836791992,
"learning_rate": 6.919133044008815e-06,
"loss": 1.5742,
"step": 949
},
{
"epoch": 0.8121393460141055,
"grad_norm": 2.0050506591796875,
"learning_rate": 6.9126003677513435e-06,
"loss": 1.701,
"step": 950
},
{
"epoch": 0.8129942295362257,
"grad_norm": 1.8712939023971558,
"learning_rate": 6.906063864772951e-06,
"loss": 1.7932,
"step": 951
},
{
"epoch": 0.8138491130583458,
"grad_norm": 1.9611555337905884,
"learning_rate": 6.899523548151837e-06,
"loss": 1.6026,
"step": 952
},
{
"epoch": 0.8147039965804659,
"grad_norm": 2.152019500732422,
"learning_rate": 6.892979430973834e-06,
"loss": 1.7248,
"step": 953
},
{
"epoch": 0.815558880102586,
"grad_norm": 1.851959228515625,
"learning_rate": 6.8864315263323775e-06,
"loss": 1.5555,
"step": 954
},
{
"epoch": 0.8164137636247061,
"grad_norm": 2.021026611328125,
"learning_rate": 6.879879847328483e-06,
"loss": 1.548,
"step": 955
},
{
"epoch": 0.8172686471468262,
"grad_norm": 1.8437577486038208,
"learning_rate": 6.873324407070714e-06,
"loss": 1.5043,
"step": 956
},
{
"epoch": 0.8181235306689464,
"grad_norm": 1.8212240934371948,
"learning_rate": 6.866765218675162e-06,
"loss": 1.5855,
"step": 957
},
{
"epoch": 0.8189784141910664,
"grad_norm": 1.8274058103561401,
"learning_rate": 6.8602022952654164e-06,
"loss": 1.5723,
"step": 958
},
{
"epoch": 0.8198332977131866,
"grad_norm": 1.9869805574417114,
"learning_rate": 6.853635649972542e-06,
"loss": 1.5586,
"step": 959
},
{
"epoch": 0.8206881812353067,
"grad_norm": 1.8559073209762573,
"learning_rate": 6.847065295935047e-06,
"loss": 1.6032,
"step": 960
},
{
"epoch": 0.8215430647574268,
"grad_norm": 1.9623775482177734,
"learning_rate": 6.8404912462988635e-06,
"loss": 1.5828,
"step": 961
},
{
"epoch": 0.8223979482795469,
"grad_norm": 1.7365514039993286,
"learning_rate": 6.833913514217314e-06,
"loss": 1.7433,
"step": 962
},
{
"epoch": 0.823252831801667,
"grad_norm": 1.9759365320205688,
"learning_rate": 6.827332112851093e-06,
"loss": 1.616,
"step": 963
},
{
"epoch": 0.8241077153237871,
"grad_norm": 1.8827824592590332,
"learning_rate": 6.820747055368233e-06,
"loss": 1.5392,
"step": 964
},
{
"epoch": 0.8249625988459073,
"grad_norm": 2.1110143661499023,
"learning_rate": 6.814158354944084e-06,
"loss": 1.5172,
"step": 965
},
{
"epoch": 0.8258174823680273,
"grad_norm": 1.9254096746444702,
"learning_rate": 6.807566024761282e-06,
"loss": 1.4199,
"step": 966
},
{
"epoch": 0.8266723658901475,
"grad_norm": 3.650379180908203,
"learning_rate": 6.800970078009728e-06,
"loss": 1.6676,
"step": 967
},
{
"epoch": 0.8275272494122676,
"grad_norm": 1.826330542564392,
"learning_rate": 6.794370527886558e-06,
"loss": 1.764,
"step": 968
},
{
"epoch": 0.8283821329343877,
"grad_norm": 1.7885780334472656,
"learning_rate": 6.787767387596118e-06,
"loss": 1.4865,
"step": 969
},
{
"epoch": 0.8292370164565078,
"grad_norm": 1.9366446733474731,
"learning_rate": 6.781160670349939e-06,
"loss": 1.7136,
"step": 970
},
{
"epoch": 0.8300918999786279,
"grad_norm": 1.978267788887024,
"learning_rate": 6.7745503893667016e-06,
"loss": 1.4599,
"step": 971
},
{
"epoch": 0.830946783500748,
"grad_norm": 2.08886456489563,
"learning_rate": 6.7679365578722275e-06,
"loss": 1.506,
"step": 972
},
{
"epoch": 0.8318016670228682,
"grad_norm": 1.8797976970672607,
"learning_rate": 6.761319189099432e-06,
"loss": 1.7517,
"step": 973
},
{
"epoch": 0.8326565505449882,
"grad_norm": 1.885097861289978,
"learning_rate": 6.754698296288315e-06,
"loss": 1.5816,
"step": 974
},
{
"epoch": 0.8335114340671084,
"grad_norm": 2.1740825176239014,
"learning_rate": 6.7480738926859234e-06,
"loss": 1.5838,
"step": 975
},
{
"epoch": 0.8343663175892284,
"grad_norm": 1.6993968486785889,
"learning_rate": 6.74144599154633e-06,
"loss": 1.6185,
"step": 976
},
{
"epoch": 0.8352212011113486,
"grad_norm": 1.847494125366211,
"learning_rate": 6.734814606130605e-06,
"loss": 1.6438,
"step": 977
},
{
"epoch": 0.8360760846334687,
"grad_norm": 1.6532142162322998,
"learning_rate": 6.728179749706792e-06,
"loss": 1.7054,
"step": 978
},
{
"epoch": 0.8369309681555888,
"grad_norm": 1.8226687908172607,
"learning_rate": 6.721541435549872e-06,
"loss": 1.4887,
"step": 979
},
{
"epoch": 0.8377858516777089,
"grad_norm": 3.3552751541137695,
"learning_rate": 6.714899676941755e-06,
"loss": 1.5384,
"step": 980
},
{
"epoch": 0.8386407351998291,
"grad_norm": 2.1226840019226074,
"learning_rate": 6.7082544871712366e-06,
"loss": 1.6166,
"step": 981
},
{
"epoch": 0.8394956187219491,
"grad_norm": 1.9226521253585815,
"learning_rate": 6.7016058795339765e-06,
"loss": 1.6108,
"step": 982
},
{
"epoch": 0.8403505022440693,
"grad_norm": 2.033696174621582,
"learning_rate": 6.694953867332473e-06,
"loss": 1.547,
"step": 983
},
{
"epoch": 0.8412053857661893,
"grad_norm": 2.0900063514709473,
"learning_rate": 6.688298463876042e-06,
"loss": 1.7125,
"step": 984
},
{
"epoch": 0.8420602692883095,
"grad_norm": 1.6653790473937988,
"learning_rate": 6.681639682480776e-06,
"loss": 1.823,
"step": 985
},
{
"epoch": 0.8429151528104296,
"grad_norm": 1.7410255670547485,
"learning_rate": 6.6749775364695335e-06,
"loss": 1.5678,
"step": 986
},
{
"epoch": 0.8437700363325497,
"grad_norm": 1.8242837190628052,
"learning_rate": 6.668312039171901e-06,
"loss": 1.7127,
"step": 987
},
{
"epoch": 0.8446249198546698,
"grad_norm": 1.8510127067565918,
"learning_rate": 6.66164320392417e-06,
"loss": 1.7295,
"step": 988
},
{
"epoch": 0.84547980337679,
"grad_norm": 1.6781837940216064,
"learning_rate": 6.65497104406931e-06,
"loss": 1.6511,
"step": 989
},
{
"epoch": 0.84633468689891,
"grad_norm": 1.7391432523727417,
"learning_rate": 6.64829557295695e-06,
"loss": 1.7455,
"step": 990
},
{
"epoch": 0.8471895704210302,
"grad_norm": 1.8074300289154053,
"learning_rate": 6.641616803943331e-06,
"loss": 1.6085,
"step": 991
},
{
"epoch": 0.8480444539431502,
"grad_norm": 1.731606364250183,
"learning_rate": 6.634934750391305e-06,
"loss": 1.7347,
"step": 992
},
{
"epoch": 0.8488993374652704,
"grad_norm": 2.0392024517059326,
"learning_rate": 6.628249425670286e-06,
"loss": 1.7722,
"step": 993
},
{
"epoch": 0.8497542209873905,
"grad_norm": 2.1152353286743164,
"learning_rate": 6.621560843156241e-06,
"loss": 1.6308,
"step": 994
},
{
"epoch": 0.8506091045095105,
"grad_norm": 2.0195107460021973,
"learning_rate": 6.614869016231648e-06,
"loss": 1.4781,
"step": 995
},
{
"epoch": 0.8514639880316307,
"grad_norm": 1.8734263181686401,
"learning_rate": 6.60817395828548e-06,
"loss": 1.3614,
"step": 996
},
{
"epoch": 0.8523188715537509,
"grad_norm": 2.6763031482696533,
"learning_rate": 6.601475682713176e-06,
"loss": 1.654,
"step": 997
},
{
"epoch": 0.8531737550758709,
"grad_norm": 1.8202966451644897,
"learning_rate": 6.594774202916612e-06,
"loss": 1.7154,
"step": 998
},
{
"epoch": 0.854028638597991,
"grad_norm": 2.3950650691986084,
"learning_rate": 6.58806953230407e-06,
"loss": 1.6501,
"step": 999
},
{
"epoch": 0.8548835221201111,
"grad_norm": 1.8744430541992188,
"learning_rate": 6.581361684290225e-06,
"loss": 1.7473,
"step": 1000
},
{
"epoch": 0.8557384056422312,
"grad_norm": 1.8787147998809814,
"learning_rate": 6.5746506722961e-06,
"loss": 1.6708,
"step": 1001
},
{
"epoch": 0.8565932891643514,
"grad_norm": 1.665242314338684,
"learning_rate": 6.567936509749058e-06,
"loss": 1.695,
"step": 1002
},
{
"epoch": 0.8574481726864714,
"grad_norm": 1.9135111570358276,
"learning_rate": 6.561219210082755e-06,
"loss": 1.5917,
"step": 1003
},
{
"epoch": 0.8583030562085916,
"grad_norm": 1.9543577432632446,
"learning_rate": 6.554498786737136e-06,
"loss": 1.6085,
"step": 1004
},
{
"epoch": 0.8591579397307116,
"grad_norm": 1.9068609476089478,
"learning_rate": 6.547775253158383e-06,
"loss": 1.7286,
"step": 1005
},
{
"epoch": 0.8600128232528318,
"grad_norm": 1.743898630142212,
"learning_rate": 6.541048622798912e-06,
"loss": 1.6818,
"step": 1006
},
{
"epoch": 0.860867706774952,
"grad_norm": 2.116328239440918,
"learning_rate": 6.534318909117326e-06,
"loss": 1.6031,
"step": 1007
},
{
"epoch": 0.861722590297072,
"grad_norm": 1.876155138015747,
"learning_rate": 6.527586125578407e-06,
"loss": 1.4219,
"step": 1008
},
{
"epoch": 0.8625774738191921,
"grad_norm": 2.2201461791992188,
"learning_rate": 6.520850285653067e-06,
"loss": 1.5063,
"step": 1009
},
{
"epoch": 0.8634323573413123,
"grad_norm": 2.414156675338745,
"learning_rate": 6.514111402818345e-06,
"loss": 1.6914,
"step": 1010
},
{
"epoch": 0.8642872408634323,
"grad_norm": 1.7859731912612915,
"learning_rate": 6.507369490557359e-06,
"loss": 1.7863,
"step": 1011
},
{
"epoch": 0.8651421243855525,
"grad_norm": 1.9573917388916016,
"learning_rate": 6.5006245623592945e-06,
"loss": 1.484,
"step": 1012
},
{
"epoch": 0.8659970079076725,
"grad_norm": 2.2137091159820557,
"learning_rate": 6.493876631719368e-06,
"loss": 1.3974,
"step": 1013
},
{
"epoch": 0.8668518914297927,
"grad_norm": 1.8472415208816528,
"learning_rate": 6.487125712138804e-06,
"loss": 1.4936,
"step": 1014
},
{
"epoch": 0.8677067749519128,
"grad_norm": 1.7957123517990112,
"learning_rate": 6.480371817124809e-06,
"loss": 1.4753,
"step": 1015
},
{
"epoch": 0.8685616584740329,
"grad_norm": 1.9084787368774414,
"learning_rate": 6.4736149601905394e-06,
"loss": 1.4901,
"step": 1016
},
{
"epoch": 0.869416541996153,
"grad_norm": 2.067575216293335,
"learning_rate": 6.466855154855081e-06,
"loss": 1.6117,
"step": 1017
},
{
"epoch": 0.8702714255182732,
"grad_norm": 1.971130132675171,
"learning_rate": 6.460092414643417e-06,
"loss": 1.5208,
"step": 1018
},
{
"epoch": 0.8711263090403932,
"grad_norm": 2.3874399662017822,
"learning_rate": 6.453326753086402e-06,
"loss": 1.5572,
"step": 1019
},
{
"epoch": 0.8719811925625134,
"grad_norm": 2.069075584411621,
"learning_rate": 6.446558183720738e-06,
"loss": 1.4789,
"step": 1020
},
{
"epoch": 0.8728360760846334,
"grad_norm": 2.126783847808838,
"learning_rate": 6.439786720088942e-06,
"loss": 1.5286,
"step": 1021
},
{
"epoch": 0.8736909596067536,
"grad_norm": 2.263805389404297,
"learning_rate": 6.433012375739326e-06,
"loss": 1.4588,
"step": 1022
},
{
"epoch": 0.8745458431288737,
"grad_norm": 2.54403018951416,
"learning_rate": 6.426235164225959e-06,
"loss": 1.6166,
"step": 1023
},
{
"epoch": 0.8754007266509938,
"grad_norm": 2.790661334991455,
"learning_rate": 6.419455099108656e-06,
"loss": 1.8078,
"step": 1024
},
{
"epoch": 0.8762556101731139,
"grad_norm": 1.7536730766296387,
"learning_rate": 6.412672193952931e-06,
"loss": 1.6686,
"step": 1025
},
{
"epoch": 0.877110493695234,
"grad_norm": 1.9725817441940308,
"learning_rate": 6.40588646232999e-06,
"loss": 1.6277,
"step": 1026
},
{
"epoch": 0.8779653772173541,
"grad_norm": 2.001371383666992,
"learning_rate": 6.3990979178166865e-06,
"loss": 1.7229,
"step": 1027
},
{
"epoch": 0.8788202607394743,
"grad_norm": 2.239229679107666,
"learning_rate": 6.3923065739955074e-06,
"loss": 1.4867,
"step": 1028
},
{
"epoch": 0.8796751442615943,
"grad_norm": 2.3648579120635986,
"learning_rate": 6.385512444454536e-06,
"loss": 1.6231,
"step": 1029
},
{
"epoch": 0.8805300277837145,
"grad_norm": 1.9137940406799316,
"learning_rate": 6.378715542787435e-06,
"loss": 1.5501,
"step": 1030
},
{
"epoch": 0.8813849113058346,
"grad_norm": 3.1135456562042236,
"learning_rate": 6.371915882593406e-06,
"loss": 1.521,
"step": 1031
},
{
"epoch": 0.8822397948279547,
"grad_norm": 1.8897255659103394,
"learning_rate": 6.365113477477176e-06,
"loss": 1.7424,
"step": 1032
},
{
"epoch": 0.8830946783500748,
"grad_norm": 1.892958402633667,
"learning_rate": 6.358308341048963e-06,
"loss": 1.6762,
"step": 1033
},
{
"epoch": 0.8839495618721949,
"grad_norm": 1.7024919986724854,
"learning_rate": 6.351500486924447e-06,
"loss": 1.6999,
"step": 1034
},
{
"epoch": 0.884804445394315,
"grad_norm": 1.8556098937988281,
"learning_rate": 6.344689928724749e-06,
"loss": 1.5675,
"step": 1035
},
{
"epoch": 0.8856593289164352,
"grad_norm": 1.7438766956329346,
"learning_rate": 6.337876680076398e-06,
"loss": 1.5188,
"step": 1036
},
{
"epoch": 0.8865142124385552,
"grad_norm": 1.9027405977249146,
"learning_rate": 6.331060754611304e-06,
"loss": 1.6641,
"step": 1037
},
{
"epoch": 0.8873690959606754,
"grad_norm": 1.7773973941802979,
"learning_rate": 6.32424216596674e-06,
"loss": 1.6512,
"step": 1038
},
{
"epoch": 0.8882239794827955,
"grad_norm": 1.840724229812622,
"learning_rate": 6.317420927785298e-06,
"loss": 1.6899,
"step": 1039
},
{
"epoch": 0.8890788630049156,
"grad_norm": 1.785825490951538,
"learning_rate": 6.310597053714881e-06,
"loss": 1.4954,
"step": 1040
},
{
"epoch": 0.8899337465270357,
"grad_norm": 1.8115184307098389,
"learning_rate": 6.303770557408657e-06,
"loss": 1.6515,
"step": 1041
},
{
"epoch": 0.8907886300491558,
"grad_norm": 2.2055771350860596,
"learning_rate": 6.296941452525048e-06,
"loss": 1.6381,
"step": 1042
},
{
"epoch": 0.8916435135712759,
"grad_norm": 1.7307052612304688,
"learning_rate": 6.290109752727687e-06,
"loss": 1.5122,
"step": 1043
},
{
"epoch": 0.8924983970933961,
"grad_norm": 1.7290875911712646,
"learning_rate": 6.283275471685408e-06,
"loss": 1.7985,
"step": 1044
},
{
"epoch": 0.8933532806155161,
"grad_norm": 2.136174440383911,
"learning_rate": 6.276438623072204e-06,
"loss": 1.5584,
"step": 1045
},
{
"epoch": 0.8942081641376363,
"grad_norm": 1.942376732826233,
"learning_rate": 6.269599220567205e-06,
"loss": 1.6992,
"step": 1046
},
{
"epoch": 0.8950630476597563,
"grad_norm": 1.8792293071746826,
"learning_rate": 6.262757277854654e-06,
"loss": 1.4932,
"step": 1047
},
{
"epoch": 0.8959179311818765,
"grad_norm": 2.496633768081665,
"learning_rate": 6.2559128086238715e-06,
"loss": 1.8053,
"step": 1048
},
{
"epoch": 0.8967728147039966,
"grad_norm": 2.0031940937042236,
"learning_rate": 6.24906582656924e-06,
"loss": 1.6923,
"step": 1049
},
{
"epoch": 0.8976276982261167,
"grad_norm": 1.8933215141296387,
"learning_rate": 6.242216345390164e-06,
"loss": 1.4336,
"step": 1050
},
{
"epoch": 0.8984825817482368,
"grad_norm": 2.275301456451416,
"learning_rate": 6.23536437879105e-06,
"loss": 1.6945,
"step": 1051
},
{
"epoch": 0.899337465270357,
"grad_norm": 2.035141944885254,
"learning_rate": 6.228509940481278e-06,
"loss": 1.5628,
"step": 1052
},
{
"epoch": 0.900192348792477,
"grad_norm": 2.141824960708618,
"learning_rate": 6.221653044175171e-06,
"loss": 1.5929,
"step": 1053
},
{
"epoch": 0.9010472323145972,
"grad_norm": 2.2444586753845215,
"learning_rate": 6.2147937035919734e-06,
"loss": 1.5017,
"step": 1054
},
{
"epoch": 0.9019021158367172,
"grad_norm": 1.9875540733337402,
"learning_rate": 6.207931932455818e-06,
"loss": 1.5285,
"step": 1055
},
{
"epoch": 0.9027569993588374,
"grad_norm": 2.033687114715576,
"learning_rate": 6.2010677444957e-06,
"loss": 1.5152,
"step": 1056
},
{
"epoch": 0.9036118828809575,
"grad_norm": 2.0552401542663574,
"learning_rate": 6.194201153445451e-06,
"loss": 1.6341,
"step": 1057
},
{
"epoch": 0.9044667664030775,
"grad_norm": 2.3873775005340576,
"learning_rate": 6.187332173043714e-06,
"loss": 1.4909,
"step": 1058
},
{
"epoch": 0.9053216499251977,
"grad_norm": 2.0585362911224365,
"learning_rate": 6.180460817033905e-06,
"loss": 1.7219,
"step": 1059
},
{
"epoch": 0.9061765334473179,
"grad_norm": 2.2529118061065674,
"learning_rate": 6.173587099164201e-06,
"loss": 1.5878,
"step": 1060
},
{
"epoch": 0.9070314169694379,
"grad_norm": 1.8679263591766357,
"learning_rate": 6.1667110331875e-06,
"loss": 1.6209,
"step": 1061
},
{
"epoch": 0.907886300491558,
"grad_norm": 1.7941343784332275,
"learning_rate": 6.159832632861399e-06,
"loss": 1.5526,
"step": 1062
},
{
"epoch": 0.9087411840136781,
"grad_norm": 1.9600245952606201,
"learning_rate": 6.152951911948165e-06,
"loss": 1.3754,
"step": 1063
},
{
"epoch": 0.9095960675357982,
"grad_norm": 1.9597649574279785,
"learning_rate": 6.14606888421471e-06,
"loss": 1.5851,
"step": 1064
},
{
"epoch": 0.9104509510579184,
"grad_norm": 2.3222103118896484,
"learning_rate": 6.1391835634325605e-06,
"loss": 1.7639,
"step": 1065
},
{
"epoch": 0.9113058345800384,
"grad_norm": 1.9706284999847412,
"learning_rate": 6.1322959633778305e-06,
"loss": 1.5823,
"step": 1066
},
{
"epoch": 0.9121607181021586,
"grad_norm": 1.8868184089660645,
"learning_rate": 6.125406097831194e-06,
"loss": 1.6515,
"step": 1067
},
{
"epoch": 0.9130156016242786,
"grad_norm": 1.833493709564209,
"learning_rate": 6.118513980577858e-06,
"loss": 1.55,
"step": 1068
},
{
"epoch": 0.9138704851463988,
"grad_norm": 1.917563557624817,
"learning_rate": 6.111619625407536e-06,
"loss": 1.6528,
"step": 1069
},
{
"epoch": 0.914725368668519,
"grad_norm": 1.8444433212280273,
"learning_rate": 6.104723046114418e-06,
"loss": 1.7479,
"step": 1070
},
{
"epoch": 0.915580252190639,
"grad_norm": 2.0832955837249756,
"learning_rate": 6.097824256497145e-06,
"loss": 1.6926,
"step": 1071
},
{
"epoch": 0.9164351357127591,
"grad_norm": 1.9241522550582886,
"learning_rate": 6.090923270358777e-06,
"loss": 1.4728,
"step": 1072
},
{
"epoch": 0.9172900192348793,
"grad_norm": 1.7187578678131104,
"learning_rate": 6.0840201015067735e-06,
"loss": 1.743,
"step": 1073
},
{
"epoch": 0.9181449027569993,
"grad_norm": 2.5005061626434326,
"learning_rate": 6.077114763752958e-06,
"loss": 1.4749,
"step": 1074
},
{
"epoch": 0.9189997862791195,
"grad_norm": 2.1376984119415283,
"learning_rate": 6.070207270913495e-06,
"loss": 1.7223,
"step": 1075
},
{
"epoch": 0.9198546698012395,
"grad_norm": 2.73537278175354,
"learning_rate": 6.063297636808862e-06,
"loss": 1.4193,
"step": 1076
},
{
"epoch": 0.9207095533233597,
"grad_norm": 1.7628402709960938,
"learning_rate": 6.056385875263816e-06,
"loss": 1.7398,
"step": 1077
},
{
"epoch": 0.9215644368454798,
"grad_norm": 1.917742133140564,
"learning_rate": 6.049472000107376e-06,
"loss": 1.6026,
"step": 1078
},
{
"epoch": 0.9224193203675999,
"grad_norm": 1.6675467491149902,
"learning_rate": 6.042556025172787e-06,
"loss": 1.6473,
"step": 1079
},
{
"epoch": 0.92327420388972,
"grad_norm": 1.7674387693405151,
"learning_rate": 6.035637964297496e-06,
"loss": 1.5639,
"step": 1080
},
{
"epoch": 0.9241290874118402,
"grad_norm": 1.7522715330123901,
"learning_rate": 6.028717831323123e-06,
"loss": 1.7759,
"step": 1081
},
{
"epoch": 0.9249839709339602,
"grad_norm": 2.054579496383667,
"learning_rate": 6.021795640095434e-06,
"loss": 1.849,
"step": 1082
},
{
"epoch": 0.9258388544560804,
"grad_norm": 2.0761284828186035,
"learning_rate": 6.014871404464316e-06,
"loss": 1.8344,
"step": 1083
},
{
"epoch": 0.9266937379782004,
"grad_norm": 1.839158058166504,
"learning_rate": 6.0079451382837405e-06,
"loss": 1.7051,
"step": 1084
},
{
"epoch": 0.9275486215003206,
"grad_norm": 2.337629795074463,
"learning_rate": 6.0010168554117474e-06,
"loss": 1.5102,
"step": 1085
},
{
"epoch": 0.9284035050224407,
"grad_norm": 2.650710105895996,
"learning_rate": 5.9940865697104055e-06,
"loss": 1.5373,
"step": 1086
},
{
"epoch": 0.9292583885445608,
"grad_norm": 3.5047664642333984,
"learning_rate": 5.987154295045801e-06,
"loss": 1.6132,
"step": 1087
},
{
"epoch": 0.9301132720666809,
"grad_norm": 1.9641162157058716,
"learning_rate": 5.980220045287986e-06,
"loss": 1.5715,
"step": 1088
},
{
"epoch": 0.930968155588801,
"grad_norm": 2.2403674125671387,
"learning_rate": 5.973283834310978e-06,
"loss": 1.6544,
"step": 1089
},
{
"epoch": 0.9318230391109211,
"grad_norm": 1.8391705751419067,
"learning_rate": 5.966345675992707e-06,
"loss": 1.6286,
"step": 1090
},
{
"epoch": 0.9326779226330413,
"grad_norm": 1.8932671546936035,
"learning_rate": 5.959405584215007e-06,
"loss": 1.5434,
"step": 1091
},
{
"epoch": 0.9335328061551613,
"grad_norm": 2.0733065605163574,
"learning_rate": 5.952463572863577e-06,
"loss": 1.4035,
"step": 1092
},
{
"epoch": 0.9343876896772815,
"grad_norm": 1.7531025409698486,
"learning_rate": 5.945519655827957e-06,
"loss": 1.6864,
"step": 1093
},
{
"epoch": 0.9352425731994016,
"grad_norm": 1.679069995880127,
"learning_rate": 5.938573847001502e-06,
"loss": 1.7121,
"step": 1094
},
{
"epoch": 0.9360974567215217,
"grad_norm": 1.8652360439300537,
"learning_rate": 5.931626160281347e-06,
"loss": 1.6491,
"step": 1095
},
{
"epoch": 0.9369523402436418,
"grad_norm": 1.819766640663147,
"learning_rate": 5.924676609568392e-06,
"loss": 1.5042,
"step": 1096
},
{
"epoch": 0.9378072237657619,
"grad_norm": 1.9549850225448608,
"learning_rate": 5.917725208767259e-06,
"loss": 1.7763,
"step": 1097
},
{
"epoch": 0.938662107287882,
"grad_norm": 2.392908811569214,
"learning_rate": 5.9107719717862756e-06,
"loss": 1.6243,
"step": 1098
},
{
"epoch": 0.9395169908100022,
"grad_norm": 1.7446740865707397,
"learning_rate": 5.903816912537444e-06,
"loss": 1.7163,
"step": 1099
},
{
"epoch": 0.9403718743321222,
"grad_norm": 1.9705148935317993,
"learning_rate": 5.896860044936406e-06,
"loss": 1.6139,
"step": 1100
},
{
"epoch": 0.9412267578542424,
"grad_norm": 1.883777379989624,
"learning_rate": 5.889901382902432e-06,
"loss": 1.6398,
"step": 1101
},
{
"epoch": 0.9420816413763625,
"grad_norm": 2.556436777114868,
"learning_rate": 5.882940940358373e-06,
"loss": 1.4316,
"step": 1102
},
{
"epoch": 0.9429365248984826,
"grad_norm": 1.8999799489974976,
"learning_rate": 5.875978731230648e-06,
"loss": 1.6339,
"step": 1103
},
{
"epoch": 0.9437914084206027,
"grad_norm": 2.2275121212005615,
"learning_rate": 5.869014769449208e-06,
"loss": 1.3929,
"step": 1104
},
{
"epoch": 0.9446462919427228,
"grad_norm": 1.9651514291763306,
"learning_rate": 5.862049068947516e-06,
"loss": 1.5237,
"step": 1105
},
{
"epoch": 0.9455011754648429,
"grad_norm": 1.848996877670288,
"learning_rate": 5.855081643662504e-06,
"loss": 1.5521,
"step": 1106
},
{
"epoch": 0.9463560589869631,
"grad_norm": 1.80025053024292,
"learning_rate": 5.848112507534564e-06,
"loss": 1.5609,
"step": 1107
},
{
"epoch": 0.9472109425090831,
"grad_norm": 2.1637113094329834,
"learning_rate": 5.841141674507504e-06,
"loss": 1.5524,
"step": 1108
},
{
"epoch": 0.9480658260312033,
"grad_norm": 2.1026487350463867,
"learning_rate": 5.834169158528534e-06,
"loss": 1.398,
"step": 1109
},
{
"epoch": 0.9489207095533233,
"grad_norm": 2.1661503314971924,
"learning_rate": 5.827194973548227e-06,
"loss": 1.5773,
"step": 1110
},
{
"epoch": 0.9497755930754435,
"grad_norm": 1.7545636892318726,
"learning_rate": 5.820219133520495e-06,
"loss": 1.691,
"step": 1111
},
{
"epoch": 0.9506304765975636,
"grad_norm": 2.0873961448669434,
"learning_rate": 5.813241652402564e-06,
"loss": 1.4826,
"step": 1112
},
{
"epoch": 0.9514853601196837,
"grad_norm": 1.7167503833770752,
"learning_rate": 5.806262544154941e-06,
"loss": 1.7625,
"step": 1113
},
{
"epoch": 0.9523402436418038,
"grad_norm": 2.3546254634857178,
"learning_rate": 5.799281822741392e-06,
"loss": 1.3234,
"step": 1114
},
{
"epoch": 0.953195127163924,
"grad_norm": 1.9529823064804077,
"learning_rate": 5.792299502128906e-06,
"loss": 1.5489,
"step": 1115
},
{
"epoch": 0.954050010686044,
"grad_norm": 1.9048004150390625,
"learning_rate": 5.785315596287675e-06,
"loss": 1.6327,
"step": 1116
},
{
"epoch": 0.9549048942081642,
"grad_norm": 2.040055751800537,
"learning_rate": 5.778330119191063e-06,
"loss": 1.6707,
"step": 1117
},
{
"epoch": 0.9557597777302842,
"grad_norm": 1.817842960357666,
"learning_rate": 5.771343084815571e-06,
"loss": 1.4015,
"step": 1118
},
{
"epoch": 0.9566146612524044,
"grad_norm": 1.8240433931350708,
"learning_rate": 5.7643545071408265e-06,
"loss": 1.6692,
"step": 1119
},
{
"epoch": 0.9574695447745245,
"grad_norm": 1.931836485862732,
"learning_rate": 5.7573644001495375e-06,
"loss": 1.5152,
"step": 1120
},
{
"epoch": 0.9583244282966445,
"grad_norm": 2.3037421703338623,
"learning_rate": 5.7503727778274765e-06,
"loss": 1.6528,
"step": 1121
},
{
"epoch": 0.9591793118187647,
"grad_norm": 1.6994976997375488,
"learning_rate": 5.743379654163441e-06,
"loss": 1.7431,
"step": 1122
},
{
"epoch": 0.9600341953408849,
"grad_norm": 2.0386931896209717,
"learning_rate": 5.736385043149242e-06,
"loss": 1.543,
"step": 1123
},
{
"epoch": 0.9608890788630049,
"grad_norm": 1.81898832321167,
"learning_rate": 5.729388958779654e-06,
"loss": 1.7186,
"step": 1124
},
{
"epoch": 0.961743962385125,
"grad_norm": 1.7468756437301636,
"learning_rate": 5.722391415052413e-06,
"loss": 1.7129,
"step": 1125
},
{
"epoch": 0.9625988459072451,
"grad_norm": 2.1387693881988525,
"learning_rate": 5.715392425968165e-06,
"loss": 1.7084,
"step": 1126
},
{
"epoch": 0.9634537294293652,
"grad_norm": 1.9089514017105103,
"learning_rate": 5.708392005530452e-06,
"loss": 1.3784,
"step": 1127
},
{
"epoch": 0.9643086129514854,
"grad_norm": 1.9345386028289795,
"learning_rate": 5.7013901677456784e-06,
"loss": 1.4172,
"step": 1128
},
{
"epoch": 0.9651634964736054,
"grad_norm": 1.9413198232650757,
"learning_rate": 5.694386926623085e-06,
"loss": 1.7237,
"step": 1129
},
{
"epoch": 0.9660183799957256,
"grad_norm": 1.9111895561218262,
"learning_rate": 5.687382296174722e-06,
"loss": 1.5112,
"step": 1130
},
{
"epoch": 0.9668732635178456,
"grad_norm": 1.9282513856887817,
"learning_rate": 5.6803762904154155e-06,
"loss": 1.6268,
"step": 1131
},
{
"epoch": 0.9677281470399658,
"grad_norm": 1.959633469581604,
"learning_rate": 5.6733689233627476e-06,
"loss": 1.5489,
"step": 1132
},
{
"epoch": 0.968583030562086,
"grad_norm": 1.8871335983276367,
"learning_rate": 5.666360209037021e-06,
"loss": 1.623,
"step": 1133
},
{
"epoch": 0.969437914084206,
"grad_norm": 1.9780254364013672,
"learning_rate": 5.659350161461234e-06,
"loss": 1.5818,
"step": 1134
},
{
"epoch": 0.9702927976063261,
"grad_norm": 4.364112377166748,
"learning_rate": 5.6523387946610575e-06,
"loss": 1.7556,
"step": 1135
},
{
"epoch": 0.9711476811284463,
"grad_norm": 1.9129712581634521,
"learning_rate": 5.645326122664793e-06,
"loss": 1.6293,
"step": 1136
},
{
"epoch": 0.9720025646505663,
"grad_norm": 3.172373056411743,
"learning_rate": 5.638312159503361e-06,
"loss": 1.6633,
"step": 1137
},
{
"epoch": 0.9728574481726865,
"grad_norm": 1.857598066329956,
"learning_rate": 5.631296919210261e-06,
"loss": 1.4858,
"step": 1138
},
{
"epoch": 0.9737123316948065,
"grad_norm": 1.9570964574813843,
"learning_rate": 5.624280415821553e-06,
"loss": 1.6073,
"step": 1139
},
{
"epoch": 0.9745672152169267,
"grad_norm": 2.047363758087158,
"learning_rate": 5.617262663375815e-06,
"loss": 1.4474,
"step": 1140
},
{
"epoch": 0.9754220987390468,
"grad_norm": 1.8771976232528687,
"learning_rate": 5.610243675914138e-06,
"loss": 1.3981,
"step": 1141
},
{
"epoch": 0.9762769822611669,
"grad_norm": 1.9068803787231445,
"learning_rate": 5.603223467480067e-06,
"loss": 1.6599,
"step": 1142
},
{
"epoch": 0.977131865783287,
"grad_norm": 2.1292192935943604,
"learning_rate": 5.5962020521196046e-06,
"loss": 1.5937,
"step": 1143
},
{
"epoch": 0.9779867493054072,
"grad_norm": 2.0215260982513428,
"learning_rate": 5.58917944388116e-06,
"loss": 1.4024,
"step": 1144
},
{
"epoch": 0.9788416328275272,
"grad_norm": 1.7946442365646362,
"learning_rate": 5.582155656815531e-06,
"loss": 1.5434,
"step": 1145
},
{
"epoch": 0.9796965163496474,
"grad_norm": 2.0026910305023193,
"learning_rate": 5.575130704975877e-06,
"loss": 1.5286,
"step": 1146
},
{
"epoch": 0.9805513998717674,
"grad_norm": 1.9159256219863892,
"learning_rate": 5.568104602417682e-06,
"loss": 1.565,
"step": 1147
},
{
"epoch": 0.9814062833938876,
"grad_norm": 1.912210464477539,
"learning_rate": 5.561077363198738e-06,
"loss": 1.4228,
"step": 1148
},
{
"epoch": 0.9822611669160077,
"grad_norm": 1.8582370281219482,
"learning_rate": 5.554049001379108e-06,
"loss": 1.529,
"step": 1149
},
{
"epoch": 0.9831160504381278,
"grad_norm": 1.9566824436187744,
"learning_rate": 5.5470195310211015e-06,
"loss": 1.6577,
"step": 1150
},
{
"epoch": 0.9839709339602479,
"grad_norm": 2.0170326232910156,
"learning_rate": 5.539988966189248e-06,
"loss": 1.6307,
"step": 1151
},
{
"epoch": 0.9848258174823681,
"grad_norm": 1.9601041078567505,
"learning_rate": 5.532957320950264e-06,
"loss": 1.6092,
"step": 1152
},
{
"epoch": 0.9856807010044881,
"grad_norm": 1.9974137544631958,
"learning_rate": 5.5259246093730305e-06,
"loss": 1.6367,
"step": 1153
},
{
"epoch": 0.9865355845266083,
"grad_norm": 2.220414161682129,
"learning_rate": 5.5188908455285565e-06,
"loss": 1.5377,
"step": 1154
},
{
"epoch": 0.9873904680487283,
"grad_norm": 2.020720958709717,
"learning_rate": 5.511856043489965e-06,
"loss": 1.6013,
"step": 1155
},
{
"epoch": 0.9882453515708485,
"grad_norm": 1.8889501094818115,
"learning_rate": 5.504820217332447e-06,
"loss": 1.689,
"step": 1156
},
{
"epoch": 0.9891002350929686,
"grad_norm": 1.811374306678772,
"learning_rate": 5.4977833811332525e-06,
"loss": 1.4317,
"step": 1157
},
{
"epoch": 0.9899551186150887,
"grad_norm": 2.801724910736084,
"learning_rate": 5.490745548971644e-06,
"loss": 1.7369,
"step": 1158
},
{
"epoch": 0.9908100021372088,
"grad_norm": 2.1599671840667725,
"learning_rate": 5.483706734928877e-06,
"loss": 1.5232,
"step": 1159
},
{
"epoch": 0.9916648856593289,
"grad_norm": 2.0417938232421875,
"learning_rate": 5.476666953088179e-06,
"loss": 1.505,
"step": 1160
},
{
"epoch": 0.992519769181449,
"grad_norm": 2.6418049335479736,
"learning_rate": 5.469626217534707e-06,
"loss": 1.6385,
"step": 1161
},
{
"epoch": 0.9933746527035692,
"grad_norm": 1.836726427078247,
"learning_rate": 5.462584542355528e-06,
"loss": 1.6968,
"step": 1162
},
{
"epoch": 0.9942295362256892,
"grad_norm": 4.359468936920166,
"learning_rate": 5.45554194163959e-06,
"loss": 1.4797,
"step": 1163
},
{
"epoch": 0.9950844197478094,
"grad_norm": 2.071335554122925,
"learning_rate": 5.44849842947769e-06,
"loss": 1.4227,
"step": 1164
},
{
"epoch": 0.9959393032699295,
"grad_norm": 1.8535865545272827,
"learning_rate": 5.4414540199624536e-06,
"loss": 1.4956,
"step": 1165
},
{
"epoch": 0.9967941867920496,
"grad_norm": 2.3737199306488037,
"learning_rate": 5.434408727188297e-06,
"loss": 1.5244,
"step": 1166
},
{
"epoch": 0.9976490703141697,
"grad_norm": 1.9199711084365845,
"learning_rate": 5.427362565251407e-06,
"loss": 1.5126,
"step": 1167
},
{
"epoch": 0.9985039538362898,
"grad_norm": 2.217866897583008,
"learning_rate": 5.4203155482497075e-06,
"loss": 1.6553,
"step": 1168
},
{
"epoch": 0.9993588373584099,
"grad_norm": 2.2763781547546387,
"learning_rate": 5.413267690282832e-06,
"loss": 1.5742,
"step": 1169
},
{
"epoch": 1.0,
"grad_norm": 1.6807893514633179,
"learning_rate": 5.4062190054521e-06,
"loss": 1.1283,
"step": 1170
},
{
"epoch": 1.00085488352212,
"grad_norm": 1.7158795595169067,
"learning_rate": 5.399169507860484e-06,
"loss": 1.5498,
"step": 1171
},
{
"epoch": 1.0017097670442403,
"grad_norm": 2.0779738426208496,
"learning_rate": 5.392119211612582e-06,
"loss": 1.3149,
"step": 1172
},
{
"epoch": 1.0017097670442403,
"eval_loss": 1.6148672103881836,
"eval_runtime": 534.1841,
"eval_samples_per_second": 7.406,
"eval_steps_per_second": 3.703,
"step": 1172
}
],
"logging_steps": 1,
"max_steps": 2338,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 293,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 2.1784816724150845e+19,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}