sedrickkeh's picture
End of training
f84bda0 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 6.850632911392405,
"eval_steps": 500,
"global_step": 224,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.030379746835443037,
"grad_norm": 7.6912534284866645,
"learning_rate": 8.695652173913044e-07,
"loss": 1.2383,
"step": 1
},
{
"epoch": 0.060759493670886074,
"grad_norm": 7.415491304348422,
"learning_rate": 1.7391304347826088e-06,
"loss": 1.1955,
"step": 2
},
{
"epoch": 0.09113924050632911,
"grad_norm": 7.5008192198019294,
"learning_rate": 2.6086956521739132e-06,
"loss": 1.2321,
"step": 3
},
{
"epoch": 0.12151898734177215,
"grad_norm": 6.713619280662549,
"learning_rate": 3.4782608695652175e-06,
"loss": 1.159,
"step": 4
},
{
"epoch": 0.1518987341772152,
"grad_norm": 5.5416321120015795,
"learning_rate": 4.347826086956522e-06,
"loss": 1.1539,
"step": 5
},
{
"epoch": 0.18227848101265823,
"grad_norm": 2.8678375841200263,
"learning_rate": 5.2173913043478265e-06,
"loss": 1.0654,
"step": 6
},
{
"epoch": 0.21265822784810126,
"grad_norm": 2.465173821628259,
"learning_rate": 6.086956521739132e-06,
"loss": 1.0894,
"step": 7
},
{
"epoch": 0.2430379746835443,
"grad_norm": 5.238678378555141,
"learning_rate": 6.956521739130435e-06,
"loss": 1.0201,
"step": 8
},
{
"epoch": 0.27341772151898736,
"grad_norm": 5.840121256192981,
"learning_rate": 7.82608695652174e-06,
"loss": 1.08,
"step": 9
},
{
"epoch": 0.3037974683544304,
"grad_norm": 5.337949915631354,
"learning_rate": 8.695652173913044e-06,
"loss": 0.9973,
"step": 10
},
{
"epoch": 0.3341772151898734,
"grad_norm": 4.924666358205418,
"learning_rate": 9.565217391304349e-06,
"loss": 1.034,
"step": 11
},
{
"epoch": 0.36455696202531646,
"grad_norm": 4.069952956992021,
"learning_rate": 1.0434782608695653e-05,
"loss": 1.0118,
"step": 12
},
{
"epoch": 0.3949367088607595,
"grad_norm": 3.3743164109532278,
"learning_rate": 1.1304347826086957e-05,
"loss": 0.9987,
"step": 13
},
{
"epoch": 0.4253164556962025,
"grad_norm": 2.9510267199234432,
"learning_rate": 1.2173913043478263e-05,
"loss": 0.9239,
"step": 14
},
{
"epoch": 0.45569620253164556,
"grad_norm": 3.0027474688771565,
"learning_rate": 1.3043478260869566e-05,
"loss": 0.9708,
"step": 15
},
{
"epoch": 0.4860759493670886,
"grad_norm": 2.7289566667875227,
"learning_rate": 1.391304347826087e-05,
"loss": 0.924,
"step": 16
},
{
"epoch": 0.5164556962025316,
"grad_norm": 2.3551150800539635,
"learning_rate": 1.4782608695652174e-05,
"loss": 0.9248,
"step": 17
},
{
"epoch": 0.5468354430379747,
"grad_norm": 1.648579932202011,
"learning_rate": 1.565217391304348e-05,
"loss": 0.8767,
"step": 18
},
{
"epoch": 0.5772151898734177,
"grad_norm": 1.4968967314840704,
"learning_rate": 1.6521739130434785e-05,
"loss": 0.8971,
"step": 19
},
{
"epoch": 0.6075949367088608,
"grad_norm": 1.8272973840771995,
"learning_rate": 1.739130434782609e-05,
"loss": 0.9031,
"step": 20
},
{
"epoch": 0.6379746835443038,
"grad_norm": 1.518235320261817,
"learning_rate": 1.8260869565217393e-05,
"loss": 0.8878,
"step": 21
},
{
"epoch": 0.6683544303797468,
"grad_norm": 1.3177377026167125,
"learning_rate": 1.9130434782608697e-05,
"loss": 0.8703,
"step": 22
},
{
"epoch": 0.6987341772151898,
"grad_norm": 1.2646511975216501,
"learning_rate": 2e-05,
"loss": 0.8827,
"step": 23
},
{
"epoch": 0.7291139240506329,
"grad_norm": 1.1675439908936511,
"learning_rate": 1.999877856940653e-05,
"loss": 0.8873,
"step": 24
},
{
"epoch": 0.759493670886076,
"grad_norm": 1.0475893044643432,
"learning_rate": 1.999511457600466e-05,
"loss": 0.8589,
"step": 25
},
{
"epoch": 0.789873417721519,
"grad_norm": 1.0862558474490158,
"learning_rate": 1.9989008914857115e-05,
"loss": 0.8423,
"step": 26
},
{
"epoch": 0.8202531645569621,
"grad_norm": 0.9130750941437369,
"learning_rate": 1.998046307749216e-05,
"loss": 0.871,
"step": 27
},
{
"epoch": 0.850632911392405,
"grad_norm": 1.1487187936062315,
"learning_rate": 1.9969479151539238e-05,
"loss": 0.8434,
"step": 28
},
{
"epoch": 0.8810126582278481,
"grad_norm": 0.9647623785498749,
"learning_rate": 1.9956059820218982e-05,
"loss": 0.8257,
"step": 29
},
{
"epoch": 0.9113924050632911,
"grad_norm": 1.0254806580535396,
"learning_rate": 1.9940208361687762e-05,
"loss": 0.8309,
"step": 30
},
{
"epoch": 0.9417721518987342,
"grad_norm": 1.098297250435345,
"learning_rate": 1.9921928648236855e-05,
"loss": 0.8382,
"step": 31
},
{
"epoch": 0.9721518987341772,
"grad_norm": 0.9346925235499104,
"learning_rate": 1.990122514534651e-05,
"loss": 0.8352,
"step": 32
},
{
"epoch": 1.010126582278481,
"grad_norm": 1.1577601296811806,
"learning_rate": 1.9878102910595097e-05,
"loss": 0.8005,
"step": 33
},
{
"epoch": 1.040506329113924,
"grad_norm": 1.0626279806933834,
"learning_rate": 1.985256759242359e-05,
"loss": 0.746,
"step": 34
},
{
"epoch": 1.070886075949367,
"grad_norm": 0.9839375799126031,
"learning_rate": 1.982462542875576e-05,
"loss": 0.7423,
"step": 35
},
{
"epoch": 1.1012658227848102,
"grad_norm": 1.1443779611551959,
"learning_rate": 1.979428324547432e-05,
"loss": 0.7327,
"step": 36
},
{
"epoch": 1.1316455696202532,
"grad_norm": 0.8825981958214109,
"learning_rate": 1.9761548454753455e-05,
"loss": 0.7419,
"step": 37
},
{
"epoch": 1.1620253164556962,
"grad_norm": 0.9853194421783852,
"learning_rate": 1.972642905324813e-05,
"loss": 0.7036,
"step": 38
},
{
"epoch": 1.1924050632911392,
"grad_norm": 0.8512312055668795,
"learning_rate": 1.9688933620140638e-05,
"loss": 0.7087,
"step": 39
},
{
"epoch": 1.2227848101265824,
"grad_norm": 0.854241628378713,
"learning_rate": 1.96490713150448e-05,
"loss": 0.7056,
"step": 40
},
{
"epoch": 1.2531645569620253,
"grad_norm": 0.8438559023883536,
"learning_rate": 1.9606851875768404e-05,
"loss": 0.7244,
"step": 41
},
{
"epoch": 1.2835443037974683,
"grad_norm": 0.7345095384436736,
"learning_rate": 1.956228561593441e-05,
"loss": 0.6866,
"step": 42
},
{
"epoch": 1.3139240506329113,
"grad_norm": 0.7770540129867073,
"learning_rate": 1.9515383422461457e-05,
"loss": 0.6889,
"step": 43
},
{
"epoch": 1.3443037974683545,
"grad_norm": 0.8554933876729495,
"learning_rate": 1.9466156752904344e-05,
"loss": 0.6944,
"step": 44
},
{
"epoch": 1.3746835443037975,
"grad_norm": 0.7415869597357176,
"learning_rate": 1.9414617632655114e-05,
"loss": 0.6681,
"step": 45
},
{
"epoch": 1.4050632911392404,
"grad_norm": 2.211488856502809,
"learning_rate": 1.9360778652005416e-05,
"loss": 0.7028,
"step": 46
},
{
"epoch": 1.4354430379746836,
"grad_norm": 0.9933335718234013,
"learning_rate": 1.9304652963070868e-05,
"loss": 0.7157,
"step": 47
},
{
"epoch": 1.4658227848101266,
"grad_norm": 0.9878737122521736,
"learning_rate": 1.9246254276578175e-05,
"loss": 0.6983,
"step": 48
},
{
"epoch": 1.4962025316455696,
"grad_norm": 0.9936743484082159,
"learning_rate": 1.9185596858515797e-05,
"loss": 0.7009,
"step": 49
},
{
"epoch": 1.5265822784810128,
"grad_norm": 0.7731957619850819,
"learning_rate": 1.9122695526648968e-05,
"loss": 0.669,
"step": 50
},
{
"epoch": 1.5569620253164556,
"grad_norm": 0.971422608213987,
"learning_rate": 1.905756564689991e-05,
"loss": 0.7282,
"step": 51
},
{
"epoch": 1.5873417721518988,
"grad_norm": 0.7954959737506944,
"learning_rate": 1.8990223129594146e-05,
"loss": 0.6642,
"step": 52
},
{
"epoch": 1.6177215189873417,
"grad_norm": 0.9299472357641544,
"learning_rate": 1.8920684425573865e-05,
"loss": 0.6935,
"step": 53
},
{
"epoch": 1.6481012658227847,
"grad_norm": 0.8518445688455599,
"learning_rate": 1.884896652217917e-05,
"loss": 0.6892,
"step": 54
},
{
"epoch": 1.678481012658228,
"grad_norm": 0.7631570454134062,
"learning_rate": 1.877508693909831e-05,
"loss": 0.6705,
"step": 55
},
{
"epoch": 1.7088607594936709,
"grad_norm": 0.873736733324705,
"learning_rate": 1.8699063724087905e-05,
"loss": 0.6935,
"step": 56
},
{
"epoch": 1.7392405063291139,
"grad_norm": 0.771976731823146,
"learning_rate": 1.862091544856407e-05,
"loss": 0.6704,
"step": 57
},
{
"epoch": 1.769620253164557,
"grad_norm": 0.763818465057948,
"learning_rate": 1.854066120306571e-05,
"loss": 0.6701,
"step": 58
},
{
"epoch": 1.8,
"grad_norm": 0.9246580418933302,
"learning_rate": 1.8458320592590976e-05,
"loss": 0.6855,
"step": 59
},
{
"epoch": 1.830379746835443,
"grad_norm": 0.9592587565428569,
"learning_rate": 1.837391373180801e-05,
"loss": 0.6872,
"step": 60
},
{
"epoch": 1.8607594936708862,
"grad_norm": 0.7561392208454594,
"learning_rate": 1.8287461240141217e-05,
"loss": 0.6716,
"step": 61
},
{
"epoch": 1.891139240506329,
"grad_norm": 0.7162261165784776,
"learning_rate": 1.8198984236734246e-05,
"loss": 0.656,
"step": 62
},
{
"epoch": 1.9215189873417722,
"grad_norm": 0.7224476840431732,
"learning_rate": 1.8108504335290852e-05,
"loss": 0.66,
"step": 63
},
{
"epoch": 1.9518987341772152,
"grad_norm": 0.7263470134283716,
"learning_rate": 1.8016043638794975e-05,
"loss": 0.6629,
"step": 64
},
{
"epoch": 1.9822784810126581,
"grad_norm": 0.744233743993539,
"learning_rate": 1.7921624734111292e-05,
"loss": 0.6667,
"step": 65
},
{
"epoch": 2.020253164556962,
"grad_norm": 0.8734467773446197,
"learning_rate": 1.7825270686467567e-05,
"loss": 0.5958,
"step": 66
},
{
"epoch": 2.050632911392405,
"grad_norm": 0.7462179214463738,
"learning_rate": 1.7727005033820117e-05,
"loss": 0.4958,
"step": 67
},
{
"epoch": 2.081012658227848,
"grad_norm": 1.1641340433764606,
"learning_rate": 1.762685178110382e-05,
"loss": 0.4652,
"step": 68
},
{
"epoch": 2.1113924050632913,
"grad_norm": 0.7738254780998187,
"learning_rate": 1.752483539436807e-05,
"loss": 0.451,
"step": 69
},
{
"epoch": 2.141772151898734,
"grad_norm": 0.9297189052652063,
"learning_rate": 1.7420980794800013e-05,
"loss": 0.4843,
"step": 70
},
{
"epoch": 2.1721518987341772,
"grad_norm": 0.778811306204785,
"learning_rate": 1.731531335263669e-05,
"loss": 0.4779,
"step": 71
},
{
"epoch": 2.2025316455696204,
"grad_norm": 0.789422228448572,
"learning_rate": 1.720785888096743e-05,
"loss": 0.4812,
"step": 72
},
{
"epoch": 2.232911392405063,
"grad_norm": 0.7697028760017353,
"learning_rate": 1.7098643629428035e-05,
"loss": 0.4881,
"step": 73
},
{
"epoch": 2.2632911392405064,
"grad_norm": 0.7441471997757925,
"learning_rate": 1.698769427778842e-05,
"loss": 0.4389,
"step": 74
},
{
"epoch": 2.293670886075949,
"grad_norm": 0.746922874259592,
"learning_rate": 1.687503792943506e-05,
"loss": 0.4898,
"step": 75
},
{
"epoch": 2.3240506329113924,
"grad_norm": 0.7034063769926476,
"learning_rate": 1.6760702104750046e-05,
"loss": 0.4513,
"step": 76
},
{
"epoch": 2.3544303797468356,
"grad_norm": 0.7663619350843316,
"learning_rate": 1.664471473438822e-05,
"loss": 0.4544,
"step": 77
},
{
"epoch": 2.3848101265822783,
"grad_norm": 0.6890207487290108,
"learning_rate": 1.6527104152454096e-05,
"loss": 0.4695,
"step": 78
},
{
"epoch": 2.4151898734177215,
"grad_norm": 0.6873441099041688,
"learning_rate": 1.6407899089580263e-05,
"loss": 0.5128,
"step": 79
},
{
"epoch": 2.4455696202531647,
"grad_norm": 0.7094778278777062,
"learning_rate": 1.628712866590885e-05,
"loss": 0.4573,
"step": 80
},
{
"epoch": 2.4759493670886075,
"grad_norm": 0.7173326342536432,
"learning_rate": 1.6164822383977912e-05,
"loss": 0.4605,
"step": 81
},
{
"epoch": 2.5063291139240507,
"grad_norm": 0.7931963793628707,
"learning_rate": 1.604101012151436e-05,
"loss": 0.4683,
"step": 82
},
{
"epoch": 2.536708860759494,
"grad_norm": 0.6561396051436904,
"learning_rate": 1.5915722124135227e-05,
"loss": 0.4751,
"step": 83
},
{
"epoch": 2.5670886075949366,
"grad_norm": 0.7844991936036958,
"learning_rate": 1.5788988997959115e-05,
"loss": 0.4879,
"step": 84
},
{
"epoch": 2.59746835443038,
"grad_norm": 0.6558250216676932,
"learning_rate": 1.5660841702129533e-05,
"loss": 0.4601,
"step": 85
},
{
"epoch": 2.6278481012658226,
"grad_norm": 0.675961955528535,
"learning_rate": 1.5531311541251995e-05,
"loss": 0.4797,
"step": 86
},
{
"epoch": 2.6582278481012658,
"grad_norm": 0.6627071211501973,
"learning_rate": 1.540043015774676e-05,
"loss": 0.4646,
"step": 87
},
{
"epoch": 2.688607594936709,
"grad_norm": 0.6702323242346955,
"learning_rate": 1.5268229524119007e-05,
"loss": 0.4658,
"step": 88
},
{
"epoch": 2.7189873417721517,
"grad_norm": 0.7001004199370537,
"learning_rate": 1.513474193514842e-05,
"loss": 0.4632,
"step": 89
},
{
"epoch": 2.749367088607595,
"grad_norm": 0.672977652852335,
"learning_rate": 1.5000000000000002e-05,
"loss": 0.4835,
"step": 90
},
{
"epoch": 2.779746835443038,
"grad_norm": 0.6657349064423453,
"learning_rate": 1.4864036634258112e-05,
"loss": 0.4503,
"step": 91
},
{
"epoch": 2.810126582278481,
"grad_norm": 0.6925505801894267,
"learning_rate": 1.4726885051885654e-05,
"loss": 0.4418,
"step": 92
},
{
"epoch": 2.840506329113924,
"grad_norm": 0.7512602776531857,
"learning_rate": 1.4588578757110359e-05,
"loss": 0.4674,
"step": 93
},
{
"epoch": 2.8708860759493673,
"grad_norm": 0.6742572925621539,
"learning_rate": 1.4449151536240167e-05,
"loss": 0.4354,
"step": 94
},
{
"epoch": 2.90126582278481,
"grad_norm": 0.7020887848379376,
"learning_rate": 1.4308637449409705e-05,
"loss": 0.4402,
"step": 95
},
{
"epoch": 2.9316455696202532,
"grad_norm": 0.6971827822568242,
"learning_rate": 1.4167070822259868e-05,
"loss": 0.4654,
"step": 96
},
{
"epoch": 2.962025316455696,
"grad_norm": 0.6863817855879132,
"learning_rate": 1.402448623755254e-05,
"loss": 0.4391,
"step": 97
},
{
"epoch": 2.992405063291139,
"grad_norm": 0.6470950110598627,
"learning_rate": 1.3880918526722497e-05,
"loss": 0.4737,
"step": 98
},
{
"epoch": 3.030379746835443,
"grad_norm": 1.0877209897285216,
"learning_rate": 1.3736402761368597e-05,
"loss": 0.3205,
"step": 99
},
{
"epoch": 3.060759493670886,
"grad_norm": 0.7418138559493466,
"learning_rate": 1.3590974244686248e-05,
"loss": 0.3245,
"step": 100
},
{
"epoch": 3.091139240506329,
"grad_norm": 1.3473069899969108,
"learning_rate": 1.344466850284333e-05,
"loss": 0.3338,
"step": 101
},
{
"epoch": 3.1215189873417724,
"grad_norm": 1.6171407290157822,
"learning_rate": 1.3297521276301666e-05,
"loss": 0.3402,
"step": 102
},
{
"epoch": 3.151898734177215,
"grad_norm": 0.7497294989859103,
"learning_rate": 1.3149568511086104e-05,
"loss": 0.3152,
"step": 103
},
{
"epoch": 3.1822784810126583,
"grad_norm": 0.9920135067381901,
"learning_rate": 1.300084635000341e-05,
"loss": 0.3116,
"step": 104
},
{
"epoch": 3.212658227848101,
"grad_norm": 0.8988701653671478,
"learning_rate": 1.2851391123813075e-05,
"loss": 0.3001,
"step": 105
},
{
"epoch": 3.2430379746835443,
"grad_norm": 0.6946510578007269,
"learning_rate": 1.2701239342352223e-05,
"loss": 0.3524,
"step": 106
},
{
"epoch": 3.2734177215189875,
"grad_norm": 0.741099468324544,
"learning_rate": 1.2550427685616767e-05,
"loss": 0.299,
"step": 107
},
{
"epoch": 3.3037974683544302,
"grad_norm": 0.7756431455367662,
"learning_rate": 1.239899299480098e-05,
"loss": 0.3037,
"step": 108
},
{
"epoch": 3.3341772151898734,
"grad_norm": 0.7301089125332831,
"learning_rate": 1.2246972263297718e-05,
"loss": 0.2915,
"step": 109
},
{
"epoch": 3.3645569620253166,
"grad_norm": 0.6634861198552179,
"learning_rate": 1.2094402627661447e-05,
"loss": 0.3032,
"step": 110
},
{
"epoch": 3.3949367088607594,
"grad_norm": 0.6926058416471517,
"learning_rate": 1.1941321358536278e-05,
"loss": 0.3103,
"step": 111
},
{
"epoch": 3.4253164556962026,
"grad_norm": 0.6846600799343063,
"learning_rate": 1.1787765851551296e-05,
"loss": 0.3146,
"step": 112
},
{
"epoch": 3.4556962025316453,
"grad_norm": 0.6552722257392178,
"learning_rate": 1.1633773618185302e-05,
"loss": 0.3086,
"step": 113
},
{
"epoch": 3.4860759493670885,
"grad_norm": 0.6930231464377482,
"learning_rate": 1.14793822766033e-05,
"loss": 0.2863,
"step": 114
},
{
"epoch": 3.5164556962025317,
"grad_norm": 0.6626598715078192,
"learning_rate": 1.132462954246688e-05,
"loss": 0.3134,
"step": 115
},
{
"epoch": 3.546835443037975,
"grad_norm": 0.726564658617872,
"learning_rate": 1.1169553219720828e-05,
"loss": 0.304,
"step": 116
},
{
"epoch": 3.5772151898734177,
"grad_norm": 0.6860397272418689,
"learning_rate": 1.1014191191358118e-05,
"loss": 0.3106,
"step": 117
},
{
"epoch": 3.607594936708861,
"grad_norm": 0.6844784748719542,
"learning_rate": 1.085858141016566e-05,
"loss": 0.3236,
"step": 118
},
{
"epoch": 3.6379746835443036,
"grad_norm": 0.6168624887028142,
"learning_rate": 1.070276188945293e-05,
"loss": 0.2767,
"step": 119
},
{
"epoch": 3.668354430379747,
"grad_norm": 0.6198486706825258,
"learning_rate": 1.0546770693765859e-05,
"loss": 0.3,
"step": 120
},
{
"epoch": 3.69873417721519,
"grad_norm": 0.6071644890704456,
"learning_rate": 1.0390645929588197e-05,
"loss": 0.3023,
"step": 121
},
{
"epoch": 3.729113924050633,
"grad_norm": 0.6662446158948692,
"learning_rate": 1.0234425736032607e-05,
"loss": 0.2992,
"step": 122
},
{
"epoch": 3.759493670886076,
"grad_norm": 0.6117324753338166,
"learning_rate": 1.007814827552384e-05,
"loss": 0.3033,
"step": 123
},
{
"epoch": 3.7898734177215188,
"grad_norm": 0.612777777018192,
"learning_rate": 9.92185172447616e-06,
"loss": 0.307,
"step": 124
},
{
"epoch": 3.820253164556962,
"grad_norm": 0.6031984369750417,
"learning_rate": 9.765574263967397e-06,
"loss": 0.3255,
"step": 125
},
{
"epoch": 3.850632911392405,
"grad_norm": 0.5770172855124511,
"learning_rate": 9.609354070411807e-06,
"loss": 0.2935,
"step": 126
},
{
"epoch": 3.8810126582278484,
"grad_norm": 0.6104572768413341,
"learning_rate": 9.453229306234143e-06,
"loss": 0.3161,
"step": 127
},
{
"epoch": 3.911392405063291,
"grad_norm": 0.6224802531724057,
"learning_rate": 9.297238110547075e-06,
"loss": 0.318,
"step": 128
},
{
"epoch": 3.9417721518987343,
"grad_norm": 0.5964137300271851,
"learning_rate": 9.14141858983434e-06,
"loss": 0.2975,
"step": 129
},
{
"epoch": 3.972151898734177,
"grad_norm": 0.6298051124953387,
"learning_rate": 8.985808808641883e-06,
"loss": 0.3,
"step": 130
},
{
"epoch": 4.010126582278481,
"grad_norm": 0.705538498711503,
"learning_rate": 8.830446780279175e-06,
"loss": 0.3041,
"step": 131
},
{
"epoch": 4.040506329113924,
"grad_norm": 0.6092432167473953,
"learning_rate": 8.675370457533122e-06,
"loss": 0.211,
"step": 132
},
{
"epoch": 4.0708860759493675,
"grad_norm": 0.47421727365041805,
"learning_rate": 8.520617723396702e-06,
"loss": 0.2164,
"step": 133
},
{
"epoch": 4.10126582278481,
"grad_norm": 0.6002758466432468,
"learning_rate": 8.366226381814698e-06,
"loss": 0.2216,
"step": 134
},
{
"epoch": 4.131645569620253,
"grad_norm": 0.757128475128808,
"learning_rate": 8.212234148448708e-06,
"loss": 0.2105,
"step": 135
},
{
"epoch": 4.162025316455696,
"grad_norm": 0.6075751286525974,
"learning_rate": 8.058678641463724e-06,
"loss": 0.2421,
"step": 136
},
{
"epoch": 4.192405063291139,
"grad_norm": 0.5484324100316951,
"learning_rate": 7.905597372338558e-06,
"loss": 0.2126,
"step": 137
},
{
"epoch": 4.222784810126583,
"grad_norm": 0.5916340974974845,
"learning_rate": 7.753027736702283e-06,
"loss": 0.2341,
"step": 138
},
{
"epoch": 4.253164556962025,
"grad_norm": 0.4978572036509178,
"learning_rate": 7.601007005199022e-06,
"loss": 0.2211,
"step": 139
},
{
"epoch": 4.283544303797468,
"grad_norm": 0.5054796961969138,
"learning_rate": 7.449572314383237e-06,
"loss": 0.2206,
"step": 140
},
{
"epoch": 4.313924050632911,
"grad_norm": 0.5400024862780566,
"learning_rate": 7.298760657647779e-06,
"loss": 0.2103,
"step": 141
},
{
"epoch": 4.3443037974683545,
"grad_norm": 0.510221362990302,
"learning_rate": 7.148608876186931e-06,
"loss": 0.1936,
"step": 142
},
{
"epoch": 4.374683544303798,
"grad_norm": 0.5277848538619925,
"learning_rate": 6.999153649996595e-06,
"loss": 0.1836,
"step": 143
},
{
"epoch": 4.405063291139241,
"grad_norm": 0.5025629936983234,
"learning_rate": 6.8504314889138956e-06,
"loss": 0.2174,
"step": 144
},
{
"epoch": 4.435443037974683,
"grad_norm": 0.5555904781129738,
"learning_rate": 6.702478723698336e-06,
"loss": 0.1948,
"step": 145
},
{
"epoch": 4.465822784810126,
"grad_norm": 0.4776001122223669,
"learning_rate": 6.555331497156671e-06,
"loss": 0.2031,
"step": 146
},
{
"epoch": 4.49620253164557,
"grad_norm": 0.49345763935727316,
"learning_rate": 6.4090257553137566e-06,
"loss": 0.2341,
"step": 147
},
{
"epoch": 4.526582278481013,
"grad_norm": 0.5091387085717698,
"learning_rate": 6.263597238631405e-06,
"loss": 0.205,
"step": 148
},
{
"epoch": 4.556962025316456,
"grad_norm": 0.4943594439925399,
"learning_rate": 6.119081473277502e-06,
"loss": 0.1784,
"step": 149
},
{
"epoch": 4.587341772151898,
"grad_norm": 0.49604624605971687,
"learning_rate": 5.975513762447465e-06,
"loss": 0.1828,
"step": 150
},
{
"epoch": 4.6177215189873415,
"grad_norm": 0.48982490711758114,
"learning_rate": 5.832929177740134e-06,
"loss": 0.2021,
"step": 151
},
{
"epoch": 4.648101265822785,
"grad_norm": 0.47704389058114455,
"learning_rate": 5.6913625505902966e-06,
"loss": 0.2081,
"step": 152
},
{
"epoch": 4.678481012658228,
"grad_norm": 0.47163052649359094,
"learning_rate": 5.550848463759835e-06,
"loss": 0.1959,
"step": 153
},
{
"epoch": 4.708860759493671,
"grad_norm": 0.47288321145386625,
"learning_rate": 5.411421242889643e-06,
"loss": 0.2304,
"step": 154
},
{
"epoch": 4.739240506329114,
"grad_norm": 0.4592757450314615,
"learning_rate": 5.273114948114346e-06,
"loss": 0.1915,
"step": 155
},
{
"epoch": 4.769620253164557,
"grad_norm": 0.4786647607840849,
"learning_rate": 5.135963365741892e-06,
"loss": 0.1855,
"step": 156
},
{
"epoch": 4.8,
"grad_norm": 0.5028679602855534,
"learning_rate": 5.000000000000003e-06,
"loss": 0.2222,
"step": 157
},
{
"epoch": 4.830379746835443,
"grad_norm": 0.4536343998325591,
"learning_rate": 4.865258064851579e-06,
"loss": 0.1809,
"step": 158
},
{
"epoch": 4.860759493670886,
"grad_norm": 0.4753385224063438,
"learning_rate": 4.731770475880995e-06,
"loss": 0.1893,
"step": 159
},
{
"epoch": 4.891139240506329,
"grad_norm": 0.4819060873496746,
"learning_rate": 4.599569842253244e-06,
"loss": 0.2049,
"step": 160
},
{
"epoch": 4.921518987341772,
"grad_norm": 0.4558599216294153,
"learning_rate": 4.468688458748006e-06,
"loss": 0.2146,
"step": 161
},
{
"epoch": 4.951898734177215,
"grad_norm": 0.4678070583546109,
"learning_rate": 4.339158297870469e-06,
"loss": 0.2052,
"step": 162
},
{
"epoch": 4.982278481012658,
"grad_norm": 0.4729766518050285,
"learning_rate": 4.211011002040885e-06,
"loss": 0.2207,
"step": 163
},
{
"epoch": 5.020253164556962,
"grad_norm": 0.5384677859922582,
"learning_rate": 4.084277875864776e-06,
"loss": 0.1676,
"step": 164
},
{
"epoch": 5.050632911392405,
"grad_norm": 0.5834965840962288,
"learning_rate": 3.958989878485644e-06,
"loss": 0.1576,
"step": 165
},
{
"epoch": 5.0810126582278485,
"grad_norm": 0.4366429481000407,
"learning_rate": 3.83517761602209e-06,
"loss": 0.1526,
"step": 166
},
{
"epoch": 5.111392405063291,
"grad_norm": 0.3890269073012922,
"learning_rate": 3.712871334091154e-06,
"loss": 0.1462,
"step": 167
},
{
"epoch": 5.141772151898734,
"grad_norm": 0.4652028216883144,
"learning_rate": 3.592100910419738e-06,
"loss": 0.146,
"step": 168
},
{
"epoch": 5.172151898734177,
"grad_norm": 0.5558719448574774,
"learning_rate": 3.4728958475459052e-06,
"loss": 0.1649,
"step": 169
},
{
"epoch": 5.2025316455696204,
"grad_norm": 0.6287344822364331,
"learning_rate": 3.355285265611784e-06,
"loss": 0.1765,
"step": 170
},
{
"epoch": 5.232911392405064,
"grad_norm": 0.4933435252880539,
"learning_rate": 3.2392978952499553e-06,
"loss": 0.1491,
"step": 171
},
{
"epoch": 5.263291139240506,
"grad_norm": 0.4070617510749904,
"learning_rate": 3.1249620705649417e-06,
"loss": 0.15,
"step": 172
},
{
"epoch": 5.293670886075949,
"grad_norm": 0.42897232866118207,
"learning_rate": 3.0123057222115835e-06,
"loss": 0.1674,
"step": 173
},
{
"epoch": 5.324050632911392,
"grad_norm": 0.41482457525994504,
"learning_rate": 2.9013563705719673e-06,
"loss": 0.1224,
"step": 174
},
{
"epoch": 5.3544303797468356,
"grad_norm": 0.4469204158631456,
"learning_rate": 2.7921411190325753e-06,
"loss": 0.1749,
"step": 175
},
{
"epoch": 5.384810126582279,
"grad_norm": 0.40495147435702966,
"learning_rate": 2.6846866473633126e-06,
"loss": 0.1434,
"step": 176
},
{
"epoch": 5.415189873417722,
"grad_norm": 0.3626006361389642,
"learning_rate": 2.579019205199992e-06,
"loss": 0.136,
"step": 177
},
{
"epoch": 5.445569620253164,
"grad_norm": 0.3927381732440496,
"learning_rate": 2.4751646056319334e-06,
"loss": 0.1534,
"step": 178
},
{
"epoch": 5.4759493670886075,
"grad_norm": 0.393383637529644,
"learning_rate": 2.373148218896182e-06,
"loss": 0.1533,
"step": 179
},
{
"epoch": 5.506329113924051,
"grad_norm": 0.37818144537507725,
"learning_rate": 2.2729949661798876e-06,
"loss": 0.1407,
"step": 180
},
{
"epoch": 5.536708860759494,
"grad_norm": 0.37814258108822946,
"learning_rate": 2.174729313532433e-06,
"loss": 0.1623,
"step": 181
},
{
"epoch": 5.567088607594937,
"grad_norm": 0.3543733332507438,
"learning_rate": 2.078375265888707e-06,
"loss": 0.156,
"step": 182
},
{
"epoch": 5.597468354430379,
"grad_norm": 0.3891039866598053,
"learning_rate": 1.9839563612050273e-06,
"loss": 0.1931,
"step": 183
},
{
"epoch": 5.627848101265823,
"grad_norm": 0.36269503020522537,
"learning_rate": 1.8914956647091497e-06,
"loss": 0.1774,
"step": 184
},
{
"epoch": 5.658227848101266,
"grad_norm": 0.35477468835011383,
"learning_rate": 1.8010157632657544e-06,
"loss": 0.1459,
"step": 185
},
{
"epoch": 5.688607594936709,
"grad_norm": 0.38906643311913225,
"learning_rate": 1.7125387598587862e-06,
"loss": 0.1389,
"step": 186
},
{
"epoch": 5.718987341772152,
"grad_norm": 0.3700566818643237,
"learning_rate": 1.6260862681919965e-06,
"loss": 0.1732,
"step": 187
},
{
"epoch": 5.749367088607595,
"grad_norm": 0.3751626638789399,
"learning_rate": 1.5416794074090258e-06,
"loss": 0.1417,
"step": 188
},
{
"epoch": 5.779746835443038,
"grad_norm": 0.38189820427946275,
"learning_rate": 1.459338796934293e-06,
"loss": 0.1578,
"step": 189
},
{
"epoch": 5.810126582278481,
"grad_norm": 0.3652382329097348,
"learning_rate": 1.3790845514359363e-06,
"loss": 0.139,
"step": 190
},
{
"epoch": 5.840506329113924,
"grad_norm": 0.3626182817102621,
"learning_rate": 1.300936275912098e-06,
"loss": 0.1434,
"step": 191
},
{
"epoch": 5.870886075949367,
"grad_norm": 0.3682414856340017,
"learning_rate": 1.224913060901688e-06,
"loss": 0.1439,
"step": 192
},
{
"epoch": 5.9012658227848105,
"grad_norm": 0.3569142845597007,
"learning_rate": 1.1510334778208332e-06,
"loss": 0.1535,
"step": 193
},
{
"epoch": 5.931645569620253,
"grad_norm": 0.36498254336900937,
"learning_rate": 1.0793155744261352e-06,
"loss": 0.1739,
"step": 194
},
{
"epoch": 5.962025316455696,
"grad_norm": 0.3584872947997238,
"learning_rate": 1.0097768704058542e-06,
"loss": 0.1783,
"step": 195
},
{
"epoch": 5.992405063291139,
"grad_norm": 0.3493822787353838,
"learning_rate": 9.424343531000968e-07,
"loss": 0.1879,
"step": 196
},
{
"epoch": 6.030379746835443,
"grad_norm": 0.4333958630535925,
"learning_rate": 8.773044733510338e-07,
"loss": 0.1484,
"step": 197
},
{
"epoch": 6.060759493670886,
"grad_norm": 0.4474643638818568,
"learning_rate": 8.144031414842012e-07,
"loss": 0.1436,
"step": 198
},
{
"epoch": 6.091139240506329,
"grad_norm": 0.3765894444623236,
"learning_rate": 7.537457234218271e-07,
"loss": 0.1643,
"step": 199
},
{
"epoch": 6.121518987341772,
"grad_norm": 0.38820536001193745,
"learning_rate": 6.953470369291349e-07,
"loss": 0.1174,
"step": 200
},
{
"epoch": 6.151898734177215,
"grad_norm": 0.3177905228419055,
"learning_rate": 6.392213479945852e-07,
"loss": 0.1283,
"step": 201
},
{
"epoch": 6.182278481012658,
"grad_norm": 0.31576694162402763,
"learning_rate": 5.853823673448877e-07,
"loss": 0.1456,
"step": 202
},
{
"epoch": 6.2126582278481015,
"grad_norm": 0.34207791694207995,
"learning_rate": 5.33843247095659e-07,
"loss": 0.1358,
"step": 203
},
{
"epoch": 6.243037974683545,
"grad_norm": 0.27751632199392284,
"learning_rate": 4.846165775385459e-07,
"loss": 0.1138,
"step": 204
},
{
"epoch": 6.273417721518987,
"grad_norm": 0.3122301638385489,
"learning_rate": 4.3771438406559173e-07,
"loss": 0.138,
"step": 205
},
{
"epoch": 6.30379746835443,
"grad_norm": 0.3108854631691516,
"learning_rate": 3.931481242315993e-07,
"loss": 0.1246,
"step": 206
},
{
"epoch": 6.334177215189873,
"grad_norm": 0.2948544251012109,
"learning_rate": 3.5092868495520294e-07,
"loss": 0.1165,
"step": 207
},
{
"epoch": 6.364556962025317,
"grad_norm": 0.3525972633231032,
"learning_rate": 3.110663798593616e-07,
"loss": 0.1454,
"step": 208
},
{
"epoch": 6.39493670886076,
"grad_norm": 0.31278306800138356,
"learning_rate": 2.735709467518699e-07,
"loss": 0.1367,
"step": 209
},
{
"epoch": 6.425316455696202,
"grad_norm": 0.35100643862931596,
"learning_rate": 2.384515452465475e-07,
"loss": 0.1772,
"step": 210
},
{
"epoch": 6.455696202531645,
"grad_norm": 0.3364042748748478,
"learning_rate": 2.0571675452567997e-07,
"loss": 0.1359,
"step": 211
},
{
"epoch": 6.4860759493670885,
"grad_norm": 0.3204155609685813,
"learning_rate": 1.7537457124423896e-07,
"loss": 0.1115,
"step": 212
},
{
"epoch": 6.516455696202532,
"grad_norm": 0.3034280877221085,
"learning_rate": 1.474324075764111e-07,
"loss": 0.1114,
"step": 213
},
{
"epoch": 6.546835443037975,
"grad_norm": 0.3121779171458754,
"learning_rate": 1.2189708940490653e-07,
"loss": 0.1476,
"step": 214
},
{
"epoch": 6.577215189873417,
"grad_norm": 0.30675325928912706,
"learning_rate": 9.877485465349057e-08,
"loss": 0.1308,
"step": 215
},
{
"epoch": 6.6075949367088604,
"grad_norm": 0.3287951926822999,
"learning_rate": 7.807135176314707e-08,
"loss": 0.1609,
"step": 216
},
{
"epoch": 6.637974683544304,
"grad_norm": 0.3108794510267372,
"learning_rate": 5.979163831223988e-08,
"loss": 0.1427,
"step": 217
},
{
"epoch": 6.668354430379747,
"grad_norm": 0.30236590943049796,
"learning_rate": 4.394017978101905e-08,
"loss": 0.1332,
"step": 218
},
{
"epoch": 6.69873417721519,
"grad_norm": 0.30705840342881063,
"learning_rate": 3.0520848460765525e-08,
"loss": 0.1378,
"step": 219
},
{
"epoch": 6.729113924050633,
"grad_norm": 0.32895477613180973,
"learning_rate": 1.9536922507841227e-08,
"loss": 0.1444,
"step": 220
},
{
"epoch": 6.759493670886076,
"grad_norm": 0.32058700239368076,
"learning_rate": 1.099108514288627e-08,
"loss": 0.1553,
"step": 221
},
{
"epoch": 6.789873417721519,
"grad_norm": 0.3210168327276288,
"learning_rate": 4.885423995341088e-09,
"loss": 0.1234,
"step": 222
},
{
"epoch": 6.820253164556962,
"grad_norm": 0.3090894443819321,
"learning_rate": 1.2214305934699078e-09,
"loss": 0.1498,
"step": 223
},
{
"epoch": 6.850632911392405,
"grad_norm": 0.3124379456128032,
"learning_rate": 0.0,
"loss": 0.1446,
"step": 224
},
{
"epoch": 6.850632911392405,
"step": 224,
"total_flos": 2.6143502793650995e+17,
"train_loss": 0.4258576862380973,
"train_runtime": 10013.9779,
"train_samples_per_second": 2.209,
"train_steps_per_second": 0.022
}
],
"logging_steps": 1,
"max_steps": 224,
"num_input_tokens_seen": 0,
"num_train_epochs": 7,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 2.6143502793650995e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}