b2_code_askllm_3k / trainer_state.json
ryanmarten's picture
End of training
d1580cd 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": 6.549595906344039,
"learning_rate": 8.695652173913044e-07,
"loss": 1.0416,
"step": 1
},
{
"epoch": 0.060759493670886074,
"grad_norm": 6.375712098928406,
"learning_rate": 1.7391304347826088e-06,
"loss": 1.0122,
"step": 2
},
{
"epoch": 0.09113924050632911,
"grad_norm": 6.398000035889488,
"learning_rate": 2.6086956521739132e-06,
"loss": 1.0241,
"step": 3
},
{
"epoch": 0.12151898734177215,
"grad_norm": 5.928516388947523,
"learning_rate": 3.4782608695652175e-06,
"loss": 1.0056,
"step": 4
},
{
"epoch": 0.1518987341772152,
"grad_norm": 4.744802600226169,
"learning_rate": 4.347826086956522e-06,
"loss": 0.9803,
"step": 5
},
{
"epoch": 0.18227848101265823,
"grad_norm": 2.8106652620061774,
"learning_rate": 5.2173913043478265e-06,
"loss": 0.9517,
"step": 6
},
{
"epoch": 0.21265822784810126,
"grad_norm": 2.5035430791502726,
"learning_rate": 6.086956521739132e-06,
"loss": 0.9401,
"step": 7
},
{
"epoch": 0.2430379746835443,
"grad_norm": 4.09236289353153,
"learning_rate": 6.956521739130435e-06,
"loss": 0.933,
"step": 8
},
{
"epoch": 0.27341772151898736,
"grad_norm": 4.258028658427849,
"learning_rate": 7.82608695652174e-06,
"loss": 0.9264,
"step": 9
},
{
"epoch": 0.3037974683544304,
"grad_norm": 3.7477291943955744,
"learning_rate": 8.695652173913044e-06,
"loss": 0.8878,
"step": 10
},
{
"epoch": 0.3341772151898734,
"grad_norm": 3.5523572665115326,
"learning_rate": 9.565217391304349e-06,
"loss": 0.8678,
"step": 11
},
{
"epoch": 0.36455696202531646,
"grad_norm": 2.9151521969418757,
"learning_rate": 1.0434782608695653e-05,
"loss": 0.8734,
"step": 12
},
{
"epoch": 0.3949367088607595,
"grad_norm": 2.0598369331183313,
"learning_rate": 1.1304347826086957e-05,
"loss": 0.8262,
"step": 13
},
{
"epoch": 0.4253164556962025,
"grad_norm": 1.5311491808060311,
"learning_rate": 1.2173913043478263e-05,
"loss": 0.8079,
"step": 14
},
{
"epoch": 0.45569620253164556,
"grad_norm": 1.716927570672294,
"learning_rate": 1.3043478260869566e-05,
"loss": 0.8041,
"step": 15
},
{
"epoch": 0.4860759493670886,
"grad_norm": 1.3269628478082236,
"learning_rate": 1.391304347826087e-05,
"loss": 0.7839,
"step": 16
},
{
"epoch": 0.5164556962025316,
"grad_norm": 1.2621417732471538,
"learning_rate": 1.4782608695652174e-05,
"loss": 0.7839,
"step": 17
},
{
"epoch": 0.5468354430379747,
"grad_norm": 1.126329743535352,
"learning_rate": 1.565217391304348e-05,
"loss": 0.7352,
"step": 18
},
{
"epoch": 0.5772151898734177,
"grad_norm": 0.9738504131509127,
"learning_rate": 1.6521739130434785e-05,
"loss": 0.7666,
"step": 19
},
{
"epoch": 0.6075949367088608,
"grad_norm": 1.1177802513070505,
"learning_rate": 1.739130434782609e-05,
"loss": 0.7426,
"step": 20
},
{
"epoch": 0.6379746835443038,
"grad_norm": 1.2112816778484001,
"learning_rate": 1.8260869565217393e-05,
"loss": 0.7331,
"step": 21
},
{
"epoch": 0.6683544303797468,
"grad_norm": 0.9256367713745799,
"learning_rate": 1.9130434782608697e-05,
"loss": 0.7392,
"step": 22
},
{
"epoch": 0.6987341772151898,
"grad_norm": 0.9216352263236964,
"learning_rate": 2e-05,
"loss": 0.7206,
"step": 23
},
{
"epoch": 0.7291139240506329,
"grad_norm": 0.9074113548035473,
"learning_rate": 1.999877856940653e-05,
"loss": 0.6999,
"step": 24
},
{
"epoch": 0.759493670886076,
"grad_norm": 0.8997823742741556,
"learning_rate": 1.999511457600466e-05,
"loss": 0.7023,
"step": 25
},
{
"epoch": 0.789873417721519,
"grad_norm": 0.7248508885291585,
"learning_rate": 1.9989008914857115e-05,
"loss": 0.7085,
"step": 26
},
{
"epoch": 0.8202531645569621,
"grad_norm": 0.7982289249325077,
"learning_rate": 1.998046307749216e-05,
"loss": 0.7076,
"step": 27
},
{
"epoch": 0.850632911392405,
"grad_norm": 0.7333910373920665,
"learning_rate": 1.9969479151539238e-05,
"loss": 0.7035,
"step": 28
},
{
"epoch": 0.8810126582278481,
"grad_norm": 0.7192437279997199,
"learning_rate": 1.9956059820218982e-05,
"loss": 0.6862,
"step": 29
},
{
"epoch": 0.9113924050632911,
"grad_norm": 0.8962198711576213,
"learning_rate": 1.9940208361687762e-05,
"loss": 0.6776,
"step": 30
},
{
"epoch": 0.9417721518987342,
"grad_norm": 0.7376907983472578,
"learning_rate": 1.9921928648236855e-05,
"loss": 0.6729,
"step": 31
},
{
"epoch": 0.9721518987341772,
"grad_norm": 1.1011057584386907,
"learning_rate": 1.990122514534651e-05,
"loss": 0.691,
"step": 32
},
{
"epoch": 1.010126582278481,
"grad_norm": 0.7442143851823189,
"learning_rate": 1.9878102910595097e-05,
"loss": 0.6826,
"step": 33
},
{
"epoch": 1.040506329113924,
"grad_norm": 0.8445427044322377,
"learning_rate": 1.985256759242359e-05,
"loss": 0.645,
"step": 34
},
{
"epoch": 1.070886075949367,
"grad_norm": 0.8279379884693239,
"learning_rate": 1.982462542875576e-05,
"loss": 0.6562,
"step": 35
},
{
"epoch": 1.1012658227848102,
"grad_norm": 0.6549064215465842,
"learning_rate": 1.979428324547432e-05,
"loss": 0.646,
"step": 36
},
{
"epoch": 1.1316455696202532,
"grad_norm": 0.6277477849389714,
"learning_rate": 1.9761548454753455e-05,
"loss": 0.6329,
"step": 37
},
{
"epoch": 1.1620253164556962,
"grad_norm": 0.649249738216496,
"learning_rate": 1.972642905324813e-05,
"loss": 0.6396,
"step": 38
},
{
"epoch": 1.1924050632911392,
"grad_norm": 4.428047809077508,
"learning_rate": 1.9688933620140638e-05,
"loss": 0.6611,
"step": 39
},
{
"epoch": 1.2227848101265824,
"grad_norm": 1.0864568240761607,
"learning_rate": 1.96490713150448e-05,
"loss": 0.6425,
"step": 40
},
{
"epoch": 1.2531645569620253,
"grad_norm": 0.9322443597337933,
"learning_rate": 1.9606851875768404e-05,
"loss": 0.6171,
"step": 41
},
{
"epoch": 1.2835443037974683,
"grad_norm": 0.6335078176176129,
"learning_rate": 1.956228561593441e-05,
"loss": 0.6412,
"step": 42
},
{
"epoch": 1.3139240506329113,
"grad_norm": 1.0721015571839054,
"learning_rate": 1.9515383422461457e-05,
"loss": 0.6135,
"step": 43
},
{
"epoch": 1.3443037974683545,
"grad_norm": 0.8203471879338031,
"learning_rate": 1.9466156752904344e-05,
"loss": 0.6292,
"step": 44
},
{
"epoch": 1.3746835443037975,
"grad_norm": 0.9172276744958865,
"learning_rate": 1.9414617632655114e-05,
"loss": 0.6369,
"step": 45
},
{
"epoch": 1.4050632911392404,
"grad_norm": 1.0562731370767,
"learning_rate": 1.9360778652005416e-05,
"loss": 0.6499,
"step": 46
},
{
"epoch": 1.4354430379746836,
"grad_norm": 0.600738721623836,
"learning_rate": 1.9304652963070868e-05,
"loss": 0.6265,
"step": 47
},
{
"epoch": 1.4658227848101266,
"grad_norm": 0.8215375767178755,
"learning_rate": 1.9246254276578175e-05,
"loss": 0.6227,
"step": 48
},
{
"epoch": 1.4962025316455696,
"grad_norm": 0.6340762388627457,
"learning_rate": 1.9185596858515797e-05,
"loss": 0.6153,
"step": 49
},
{
"epoch": 1.5265822784810128,
"grad_norm": 0.5748952315483937,
"learning_rate": 1.9122695526648968e-05,
"loss": 0.6362,
"step": 50
},
{
"epoch": 1.5569620253164556,
"grad_norm": 0.7852211383513371,
"learning_rate": 1.905756564689991e-05,
"loss": 0.6221,
"step": 51
},
{
"epoch": 1.5873417721518988,
"grad_norm": 0.4449000935636123,
"learning_rate": 1.8990223129594146e-05,
"loss": 0.6141,
"step": 52
},
{
"epoch": 1.6177215189873417,
"grad_norm": 0.7433370951176753,
"learning_rate": 1.8920684425573865e-05,
"loss": 0.6261,
"step": 53
},
{
"epoch": 1.6481012658227847,
"grad_norm": 0.5047745349535321,
"learning_rate": 1.884896652217917e-05,
"loss": 0.614,
"step": 54
},
{
"epoch": 1.678481012658228,
"grad_norm": 0.5642919336379415,
"learning_rate": 1.877508693909831e-05,
"loss": 0.6066,
"step": 55
},
{
"epoch": 1.7088607594936709,
"grad_norm": 0.4870712021996647,
"learning_rate": 1.8699063724087905e-05,
"loss": 0.6132,
"step": 56
},
{
"epoch": 1.7392405063291139,
"grad_norm": 0.440645668887891,
"learning_rate": 1.862091544856407e-05,
"loss": 0.6209,
"step": 57
},
{
"epoch": 1.769620253164557,
"grad_norm": 0.48770080817746647,
"learning_rate": 1.854066120306571e-05,
"loss": 0.6188,
"step": 58
},
{
"epoch": 1.8,
"grad_norm": 0.539138867112883,
"learning_rate": 1.8458320592590976e-05,
"loss": 0.6008,
"step": 59
},
{
"epoch": 1.830379746835443,
"grad_norm": 0.48512429057058637,
"learning_rate": 1.837391373180801e-05,
"loss": 0.598,
"step": 60
},
{
"epoch": 1.8607594936708862,
"grad_norm": 0.5898440280342643,
"learning_rate": 1.8287461240141217e-05,
"loss": 0.6278,
"step": 61
},
{
"epoch": 1.891139240506329,
"grad_norm": 0.4841816145979927,
"learning_rate": 1.8198984236734246e-05,
"loss": 0.6051,
"step": 62
},
{
"epoch": 1.9215189873417722,
"grad_norm": 0.48485440546508857,
"learning_rate": 1.8108504335290852e-05,
"loss": 0.6219,
"step": 63
},
{
"epoch": 1.9518987341772152,
"grad_norm": 0.5220173759920478,
"learning_rate": 1.8016043638794975e-05,
"loss": 0.6098,
"step": 64
},
{
"epoch": 1.9822784810126581,
"grad_norm": 0.502133460930607,
"learning_rate": 1.7921624734111292e-05,
"loss": 0.6205,
"step": 65
},
{
"epoch": 2.020253164556962,
"grad_norm": 0.5635425374906448,
"learning_rate": 1.7825270686467567e-05,
"loss": 0.5823,
"step": 66
},
{
"epoch": 2.050632911392405,
"grad_norm": 0.5117197636317842,
"learning_rate": 1.7727005033820117e-05,
"loss": 0.5513,
"step": 67
},
{
"epoch": 2.081012658227848,
"grad_norm": 0.49958272825176053,
"learning_rate": 1.762685178110382e-05,
"loss": 0.5646,
"step": 68
},
{
"epoch": 2.1113924050632913,
"grad_norm": 0.5447529637313504,
"learning_rate": 1.752483539436807e-05,
"loss": 0.5486,
"step": 69
},
{
"epoch": 2.141772151898734,
"grad_norm": 0.5268180564423064,
"learning_rate": 1.7420980794800013e-05,
"loss": 0.5522,
"step": 70
},
{
"epoch": 2.1721518987341772,
"grad_norm": 0.4856033938253083,
"learning_rate": 1.731531335263669e-05,
"loss": 0.5532,
"step": 71
},
{
"epoch": 2.2025316455696204,
"grad_norm": 0.5415435651668967,
"learning_rate": 1.720785888096743e-05,
"loss": 0.549,
"step": 72
},
{
"epoch": 2.232911392405063,
"grad_norm": 0.4628147945836479,
"learning_rate": 1.7098643629428035e-05,
"loss": 0.554,
"step": 73
},
{
"epoch": 2.2632911392405064,
"grad_norm": 0.5566293833446755,
"learning_rate": 1.698769427778842e-05,
"loss": 0.5419,
"step": 74
},
{
"epoch": 2.293670886075949,
"grad_norm": 0.515435980026977,
"learning_rate": 1.687503792943506e-05,
"loss": 0.5408,
"step": 75
},
{
"epoch": 2.3240506329113924,
"grad_norm": 0.5030375899620371,
"learning_rate": 1.6760702104750046e-05,
"loss": 0.5414,
"step": 76
},
{
"epoch": 2.3544303797468356,
"grad_norm": 0.5619329368126017,
"learning_rate": 1.664471473438822e-05,
"loss": 0.5588,
"step": 77
},
{
"epoch": 2.3848101265822783,
"grad_norm": 0.47195912670341617,
"learning_rate": 1.6527104152454096e-05,
"loss": 0.5389,
"step": 78
},
{
"epoch": 2.4151898734177215,
"grad_norm": 0.5382399404801761,
"learning_rate": 1.6407899089580263e-05,
"loss": 0.5506,
"step": 79
},
{
"epoch": 2.4455696202531647,
"grad_norm": 0.6220329212300999,
"learning_rate": 1.628712866590885e-05,
"loss": 0.5587,
"step": 80
},
{
"epoch": 2.4759493670886075,
"grad_norm": 0.5832513130678023,
"learning_rate": 1.6164822383977912e-05,
"loss": 0.5389,
"step": 81
},
{
"epoch": 2.5063291139240507,
"grad_norm": 0.5499544473342975,
"learning_rate": 1.604101012151436e-05,
"loss": 0.5694,
"step": 82
},
{
"epoch": 2.536708860759494,
"grad_norm": 0.44979404406866064,
"learning_rate": 1.5915722124135227e-05,
"loss": 0.5434,
"step": 83
},
{
"epoch": 2.5670886075949366,
"grad_norm": 0.4558290648024083,
"learning_rate": 1.5788988997959115e-05,
"loss": 0.5257,
"step": 84
},
{
"epoch": 2.59746835443038,
"grad_norm": 0.4080370638476428,
"learning_rate": 1.5660841702129533e-05,
"loss": 0.5424,
"step": 85
},
{
"epoch": 2.6278481012658226,
"grad_norm": 0.4524768591155765,
"learning_rate": 1.5531311541251995e-05,
"loss": 0.5365,
"step": 86
},
{
"epoch": 2.6582278481012658,
"grad_norm": 0.43901478370610203,
"learning_rate": 1.540043015774676e-05,
"loss": 0.5247,
"step": 87
},
{
"epoch": 2.688607594936709,
"grad_norm": 0.45251050257927145,
"learning_rate": 1.5268229524119007e-05,
"loss": 0.5516,
"step": 88
},
{
"epoch": 2.7189873417721517,
"grad_norm": 0.4460807863663231,
"learning_rate": 1.513474193514842e-05,
"loss": 0.5288,
"step": 89
},
{
"epoch": 2.749367088607595,
"grad_norm": 0.5497602153673854,
"learning_rate": 1.5000000000000002e-05,
"loss": 0.5506,
"step": 90
},
{
"epoch": 2.779746835443038,
"grad_norm": 0.4936159759777004,
"learning_rate": 1.4864036634258112e-05,
"loss": 0.5567,
"step": 91
},
{
"epoch": 2.810126582278481,
"grad_norm": 0.6302415956022084,
"learning_rate": 1.4726885051885654e-05,
"loss": 0.5221,
"step": 92
},
{
"epoch": 2.840506329113924,
"grad_norm": 0.5126772475277334,
"learning_rate": 1.4588578757110359e-05,
"loss": 0.5124,
"step": 93
},
{
"epoch": 2.8708860759493673,
"grad_norm": 0.5737092482934293,
"learning_rate": 1.4449151536240167e-05,
"loss": 0.5387,
"step": 94
},
{
"epoch": 2.90126582278481,
"grad_norm": 0.4656433948370363,
"learning_rate": 1.4308637449409705e-05,
"loss": 0.538,
"step": 95
},
{
"epoch": 2.9316455696202532,
"grad_norm": 0.49587251070831295,
"learning_rate": 1.4167070822259868e-05,
"loss": 0.5466,
"step": 96
},
{
"epoch": 2.962025316455696,
"grad_norm": 0.5000351200233649,
"learning_rate": 1.402448623755254e-05,
"loss": 0.5333,
"step": 97
},
{
"epoch": 2.992405063291139,
"grad_norm": 0.4065800775405106,
"learning_rate": 1.3880918526722497e-05,
"loss": 0.5527,
"step": 98
},
{
"epoch": 3.030379746835443,
"grad_norm": 0.5402198426802194,
"learning_rate": 1.3736402761368597e-05,
"loss": 0.5009,
"step": 99
},
{
"epoch": 3.060759493670886,
"grad_norm": 0.5088649352575721,
"learning_rate": 1.3590974244686248e-05,
"loss": 0.4796,
"step": 100
},
{
"epoch": 3.091139240506329,
"grad_norm": 0.6648891344191784,
"learning_rate": 1.344466850284333e-05,
"loss": 0.4896,
"step": 101
},
{
"epoch": 3.1215189873417724,
"grad_norm": 0.600737882185822,
"learning_rate": 1.3297521276301666e-05,
"loss": 0.5068,
"step": 102
},
{
"epoch": 3.151898734177215,
"grad_norm": 0.6603232575550092,
"learning_rate": 1.3149568511086104e-05,
"loss": 0.4799,
"step": 103
},
{
"epoch": 3.1822784810126583,
"grad_norm": 0.5882614000247419,
"learning_rate": 1.300084635000341e-05,
"loss": 0.4875,
"step": 104
},
{
"epoch": 3.212658227848101,
"grad_norm": 0.5906412920794121,
"learning_rate": 1.2851391123813075e-05,
"loss": 0.4898,
"step": 105
},
{
"epoch": 3.2430379746835443,
"grad_norm": 0.5999924987188322,
"learning_rate": 1.2701239342352223e-05,
"loss": 0.4691,
"step": 106
},
{
"epoch": 3.2734177215189875,
"grad_norm": 0.5583025148794856,
"learning_rate": 1.2550427685616767e-05,
"loss": 0.4601,
"step": 107
},
{
"epoch": 3.3037974683544302,
"grad_norm": 0.5502390228317201,
"learning_rate": 1.239899299480098e-05,
"loss": 0.4643,
"step": 108
},
{
"epoch": 3.3341772151898734,
"grad_norm": 0.5799823014994865,
"learning_rate": 1.2246972263297718e-05,
"loss": 0.4769,
"step": 109
},
{
"epoch": 3.3645569620253166,
"grad_norm": 0.4883048990403793,
"learning_rate": 1.2094402627661447e-05,
"loss": 0.4811,
"step": 110
},
{
"epoch": 3.3949367088607594,
"grad_norm": 0.5223038360447452,
"learning_rate": 1.1941321358536278e-05,
"loss": 0.4873,
"step": 111
},
{
"epoch": 3.4253164556962026,
"grad_norm": 0.5975267726705484,
"learning_rate": 1.1787765851551296e-05,
"loss": 0.4768,
"step": 112
},
{
"epoch": 3.4556962025316453,
"grad_norm": 0.48692453309501077,
"learning_rate": 1.1633773618185302e-05,
"loss": 0.5089,
"step": 113
},
{
"epoch": 3.4860759493670885,
"grad_norm": 0.47251149417000665,
"learning_rate": 1.14793822766033e-05,
"loss": 0.4615,
"step": 114
},
{
"epoch": 3.5164556962025317,
"grad_norm": 0.475946998466237,
"learning_rate": 1.132462954246688e-05,
"loss": 0.4716,
"step": 115
},
{
"epoch": 3.546835443037975,
"grad_norm": 0.4616029086308266,
"learning_rate": 1.1169553219720828e-05,
"loss": 0.496,
"step": 116
},
{
"epoch": 3.5772151898734177,
"grad_norm": 0.4268382488250146,
"learning_rate": 1.1014191191358118e-05,
"loss": 0.4851,
"step": 117
},
{
"epoch": 3.607594936708861,
"grad_norm": 0.46542247035196477,
"learning_rate": 1.085858141016566e-05,
"loss": 0.4718,
"step": 118
},
{
"epoch": 3.6379746835443036,
"grad_norm": 0.474857258069365,
"learning_rate": 1.070276188945293e-05,
"loss": 0.4695,
"step": 119
},
{
"epoch": 3.668354430379747,
"grad_norm": 0.42338443058911773,
"learning_rate": 1.0546770693765859e-05,
"loss": 0.4641,
"step": 120
},
{
"epoch": 3.69873417721519,
"grad_norm": 0.4452828928438565,
"learning_rate": 1.0390645929588197e-05,
"loss": 0.4827,
"step": 121
},
{
"epoch": 3.729113924050633,
"grad_norm": 0.42897833895185894,
"learning_rate": 1.0234425736032607e-05,
"loss": 0.4634,
"step": 122
},
{
"epoch": 3.759493670886076,
"grad_norm": 0.4148779935016203,
"learning_rate": 1.007814827552384e-05,
"loss": 0.4974,
"step": 123
},
{
"epoch": 3.7898734177215188,
"grad_norm": 0.41055000009098125,
"learning_rate": 9.92185172447616e-06,
"loss": 0.4555,
"step": 124
},
{
"epoch": 3.820253164556962,
"grad_norm": 0.41782118661845763,
"learning_rate": 9.765574263967397e-06,
"loss": 0.4824,
"step": 125
},
{
"epoch": 3.850632911392405,
"grad_norm": 0.3888031915527682,
"learning_rate": 9.609354070411807e-06,
"loss": 0.5039,
"step": 126
},
{
"epoch": 3.8810126582278484,
"grad_norm": 0.4073201115649246,
"learning_rate": 9.453229306234143e-06,
"loss": 0.4735,
"step": 127
},
{
"epoch": 3.911392405063291,
"grad_norm": 0.42699627451477756,
"learning_rate": 9.297238110547075e-06,
"loss": 0.4888,
"step": 128
},
{
"epoch": 3.9417721518987343,
"grad_norm": 0.3434982736334974,
"learning_rate": 9.14141858983434e-06,
"loss": 0.4623,
"step": 129
},
{
"epoch": 3.972151898734177,
"grad_norm": 0.41593558830345667,
"learning_rate": 8.985808808641883e-06,
"loss": 0.4519,
"step": 130
},
{
"epoch": 4.010126582278481,
"grad_norm": 0.3915507496654778,
"learning_rate": 8.830446780279175e-06,
"loss": 0.4641,
"step": 131
},
{
"epoch": 4.040506329113924,
"grad_norm": 0.42857934177696616,
"learning_rate": 8.675370457533122e-06,
"loss": 0.4302,
"step": 132
},
{
"epoch": 4.0708860759493675,
"grad_norm": 0.5651540006510074,
"learning_rate": 8.520617723396702e-06,
"loss": 0.4472,
"step": 133
},
{
"epoch": 4.10126582278481,
"grad_norm": 0.41979927666805544,
"learning_rate": 8.366226381814698e-06,
"loss": 0.4255,
"step": 134
},
{
"epoch": 4.131645569620253,
"grad_norm": 0.4558163297885289,
"learning_rate": 8.212234148448708e-06,
"loss": 0.4401,
"step": 135
},
{
"epoch": 4.162025316455696,
"grad_norm": 0.477619358533199,
"learning_rate": 8.058678641463724e-06,
"loss": 0.4356,
"step": 136
},
{
"epoch": 4.192405063291139,
"grad_norm": 0.40252379377050157,
"learning_rate": 7.905597372338558e-06,
"loss": 0.4345,
"step": 137
},
{
"epoch": 4.222784810126583,
"grad_norm": 0.4018848840956527,
"learning_rate": 7.753027736702283e-06,
"loss": 0.4214,
"step": 138
},
{
"epoch": 4.253164556962025,
"grad_norm": 0.5399106231043995,
"learning_rate": 7.601007005199022e-06,
"loss": 0.4322,
"step": 139
},
{
"epoch": 4.283544303797468,
"grad_norm": 0.35248264391645606,
"learning_rate": 7.449572314383237e-06,
"loss": 0.418,
"step": 140
},
{
"epoch": 4.313924050632911,
"grad_norm": 0.41837189552929904,
"learning_rate": 7.298760657647779e-06,
"loss": 0.4027,
"step": 141
},
{
"epoch": 4.3443037974683545,
"grad_norm": 0.3943860433243488,
"learning_rate": 7.148608876186931e-06,
"loss": 0.4393,
"step": 142
},
{
"epoch": 4.374683544303798,
"grad_norm": 0.3579441326946409,
"learning_rate": 6.999153649996595e-06,
"loss": 0.4502,
"step": 143
},
{
"epoch": 4.405063291139241,
"grad_norm": 0.40753315605228935,
"learning_rate": 6.8504314889138956e-06,
"loss": 0.4207,
"step": 144
},
{
"epoch": 4.435443037974683,
"grad_norm": 0.4081507478669719,
"learning_rate": 6.702478723698336e-06,
"loss": 0.4249,
"step": 145
},
{
"epoch": 4.465822784810126,
"grad_norm": 0.36890197128598784,
"learning_rate": 6.555331497156671e-06,
"loss": 0.4128,
"step": 146
},
{
"epoch": 4.49620253164557,
"grad_norm": 0.481099621242718,
"learning_rate": 6.4090257553137566e-06,
"loss": 0.4187,
"step": 147
},
{
"epoch": 4.526582278481013,
"grad_norm": 0.36686398156171945,
"learning_rate": 6.263597238631405e-06,
"loss": 0.4052,
"step": 148
},
{
"epoch": 4.556962025316456,
"grad_norm": 0.34468554356330017,
"learning_rate": 6.119081473277502e-06,
"loss": 0.4339,
"step": 149
},
{
"epoch": 4.587341772151898,
"grad_norm": 0.4166257919100586,
"learning_rate": 5.975513762447465e-06,
"loss": 0.4434,
"step": 150
},
{
"epoch": 4.6177215189873415,
"grad_norm": 0.36364664066674074,
"learning_rate": 5.832929177740134e-06,
"loss": 0.4261,
"step": 151
},
{
"epoch": 4.648101265822785,
"grad_norm": 0.35834652584690485,
"learning_rate": 5.6913625505902966e-06,
"loss": 0.4278,
"step": 152
},
{
"epoch": 4.678481012658228,
"grad_norm": 0.37187486055326996,
"learning_rate": 5.550848463759835e-06,
"loss": 0.3911,
"step": 153
},
{
"epoch": 4.708860759493671,
"grad_norm": 0.3418240936658773,
"learning_rate": 5.411421242889643e-06,
"loss": 0.4286,
"step": 154
},
{
"epoch": 4.739240506329114,
"grad_norm": 0.3695849153359289,
"learning_rate": 5.273114948114346e-06,
"loss": 0.4316,
"step": 155
},
{
"epoch": 4.769620253164557,
"grad_norm": 0.3866115865916404,
"learning_rate": 5.135963365741892e-06,
"loss": 0.4392,
"step": 156
},
{
"epoch": 4.8,
"grad_norm": 0.344180956166334,
"learning_rate": 5.000000000000003e-06,
"loss": 0.4076,
"step": 157
},
{
"epoch": 4.830379746835443,
"grad_norm": 0.36552379403720425,
"learning_rate": 4.865258064851579e-06,
"loss": 0.4237,
"step": 158
},
{
"epoch": 4.860759493670886,
"grad_norm": 0.34717055529811003,
"learning_rate": 4.731770475880995e-06,
"loss": 0.4352,
"step": 159
},
{
"epoch": 4.891139240506329,
"grad_norm": 0.3246948452038267,
"learning_rate": 4.599569842253244e-06,
"loss": 0.431,
"step": 160
},
{
"epoch": 4.921518987341772,
"grad_norm": 0.3358430607698732,
"learning_rate": 4.468688458748006e-06,
"loss": 0.4086,
"step": 161
},
{
"epoch": 4.951898734177215,
"grad_norm": 0.3079432894760639,
"learning_rate": 4.339158297870469e-06,
"loss": 0.4367,
"step": 162
},
{
"epoch": 4.982278481012658,
"grad_norm": 0.3201394766974603,
"learning_rate": 4.211011002040885e-06,
"loss": 0.4286,
"step": 163
},
{
"epoch": 5.020253164556962,
"grad_norm": 0.3928967998122616,
"learning_rate": 4.084277875864776e-06,
"loss": 0.4124,
"step": 164
},
{
"epoch": 5.050632911392405,
"grad_norm": 0.4159780302431673,
"learning_rate": 3.958989878485644e-06,
"loss": 0.3928,
"step": 165
},
{
"epoch": 5.0810126582278485,
"grad_norm": 0.3650902521494742,
"learning_rate": 3.83517761602209e-06,
"loss": 0.4198,
"step": 166
},
{
"epoch": 5.111392405063291,
"grad_norm": 0.4443363765226467,
"learning_rate": 3.712871334091154e-06,
"loss": 0.3967,
"step": 167
},
{
"epoch": 5.141772151898734,
"grad_norm": 0.4470333627951731,
"learning_rate": 3.592100910419738e-06,
"loss": 0.3821,
"step": 168
},
{
"epoch": 5.172151898734177,
"grad_norm": 0.3437060498642169,
"learning_rate": 3.4728958475459052e-06,
"loss": 0.3916,
"step": 169
},
{
"epoch": 5.2025316455696204,
"grad_norm": 0.38136157732196546,
"learning_rate": 3.355285265611784e-06,
"loss": 0.4074,
"step": 170
},
{
"epoch": 5.232911392405064,
"grad_norm": 0.38942314171126446,
"learning_rate": 3.2392978952499553e-06,
"loss": 0.4004,
"step": 171
},
{
"epoch": 5.263291139240506,
"grad_norm": 0.3431892335641562,
"learning_rate": 3.1249620705649417e-06,
"loss": 0.3891,
"step": 172
},
{
"epoch": 5.293670886075949,
"grad_norm": 0.3793448571223638,
"learning_rate": 3.0123057222115835e-06,
"loss": 0.4024,
"step": 173
},
{
"epoch": 5.324050632911392,
"grad_norm": 0.36658520736417405,
"learning_rate": 2.9013563705719673e-06,
"loss": 0.3838,
"step": 174
},
{
"epoch": 5.3544303797468356,
"grad_norm": 0.34717223560979876,
"learning_rate": 2.7921411190325753e-06,
"loss": 0.3895,
"step": 175
},
{
"epoch": 5.384810126582279,
"grad_norm": 0.3430941356052756,
"learning_rate": 2.6846866473633126e-06,
"loss": 0.3946,
"step": 176
},
{
"epoch": 5.415189873417722,
"grad_norm": 0.3469638625694526,
"learning_rate": 2.579019205199992e-06,
"loss": 0.3903,
"step": 177
},
{
"epoch": 5.445569620253164,
"grad_norm": 0.30521679487375425,
"learning_rate": 2.4751646056319334e-06,
"loss": 0.3879,
"step": 178
},
{
"epoch": 5.4759493670886075,
"grad_norm": 0.3179018532571727,
"learning_rate": 2.373148218896182e-06,
"loss": 0.3912,
"step": 179
},
{
"epoch": 5.506329113924051,
"grad_norm": 0.3402824277752787,
"learning_rate": 2.2729949661798876e-06,
"loss": 0.4007,
"step": 180
},
{
"epoch": 5.536708860759494,
"grad_norm": 0.3578528812826907,
"learning_rate": 2.174729313532433e-06,
"loss": 0.3657,
"step": 181
},
{
"epoch": 5.567088607594937,
"grad_norm": 0.2959834084621492,
"learning_rate": 2.078375265888707e-06,
"loss": 0.3788,
"step": 182
},
{
"epoch": 5.597468354430379,
"grad_norm": 0.29290654718464815,
"learning_rate": 1.9839563612050273e-06,
"loss": 0.3871,
"step": 183
},
{
"epoch": 5.627848101265823,
"grad_norm": 0.29188688828705833,
"learning_rate": 1.8914956647091497e-06,
"loss": 0.3869,
"step": 184
},
{
"epoch": 5.658227848101266,
"grad_norm": 0.3193309187887589,
"learning_rate": 1.8010157632657544e-06,
"loss": 0.3966,
"step": 185
},
{
"epoch": 5.688607594936709,
"grad_norm": 0.30194074627870426,
"learning_rate": 1.7125387598587862e-06,
"loss": 0.3956,
"step": 186
},
{
"epoch": 5.718987341772152,
"grad_norm": 0.2714878989148742,
"learning_rate": 1.6260862681919965e-06,
"loss": 0.3937,
"step": 187
},
{
"epoch": 5.749367088607595,
"grad_norm": 0.29404832471365455,
"learning_rate": 1.5416794074090258e-06,
"loss": 0.3863,
"step": 188
},
{
"epoch": 5.779746835443038,
"grad_norm": 0.29973651306076543,
"learning_rate": 1.459338796934293e-06,
"loss": 0.3989,
"step": 189
},
{
"epoch": 5.810126582278481,
"grad_norm": 0.2962464557587159,
"learning_rate": 1.3790845514359363e-06,
"loss": 0.4003,
"step": 190
},
{
"epoch": 5.840506329113924,
"grad_norm": 0.2828017394121654,
"learning_rate": 1.300936275912098e-06,
"loss": 0.3853,
"step": 191
},
{
"epoch": 5.870886075949367,
"grad_norm": 0.2937797948776522,
"learning_rate": 1.224913060901688e-06,
"loss": 0.3732,
"step": 192
},
{
"epoch": 5.9012658227848105,
"grad_norm": 0.2801265996353137,
"learning_rate": 1.1510334778208332e-06,
"loss": 0.389,
"step": 193
},
{
"epoch": 5.931645569620253,
"grad_norm": 0.26816619373364253,
"learning_rate": 1.0793155744261352e-06,
"loss": 0.3757,
"step": 194
},
{
"epoch": 5.962025316455696,
"grad_norm": 0.27282938063638174,
"learning_rate": 1.0097768704058542e-06,
"loss": 0.3881,
"step": 195
},
{
"epoch": 5.992405063291139,
"grad_norm": 0.27663735954842056,
"learning_rate": 9.424343531000968e-07,
"loss": 0.3825,
"step": 196
},
{
"epoch": 6.030379746835443,
"grad_norm": 0.3204006850212176,
"learning_rate": 8.773044733510338e-07,
"loss": 0.3664,
"step": 197
},
{
"epoch": 6.060759493670886,
"grad_norm": 0.29808170799028405,
"learning_rate": 8.144031414842012e-07,
"loss": 0.3516,
"step": 198
},
{
"epoch": 6.091139240506329,
"grad_norm": 0.2784359052824668,
"learning_rate": 7.537457234218271e-07,
"loss": 0.3859,
"step": 199
},
{
"epoch": 6.121518987341772,
"grad_norm": 0.2706108920249029,
"learning_rate": 6.953470369291349e-07,
"loss": 0.3619,
"step": 200
},
{
"epoch": 6.151898734177215,
"grad_norm": 0.2687933420571409,
"learning_rate": 6.392213479945852e-07,
"loss": 0.3949,
"step": 201
},
{
"epoch": 6.182278481012658,
"grad_norm": 0.2554531613541232,
"learning_rate": 5.853823673448877e-07,
"loss": 0.3531,
"step": 202
},
{
"epoch": 6.2126582278481015,
"grad_norm": 0.2601201694149999,
"learning_rate": 5.33843247095659e-07,
"loss": 0.3676,
"step": 203
},
{
"epoch": 6.243037974683545,
"grad_norm": 0.29711625844623596,
"learning_rate": 4.846165775385459e-07,
"loss": 0.389,
"step": 204
},
{
"epoch": 6.273417721518987,
"grad_norm": 0.26405511439565393,
"learning_rate": 4.3771438406559173e-07,
"loss": 0.3888,
"step": 205
},
{
"epoch": 6.30379746835443,
"grad_norm": 0.2673105384708554,
"learning_rate": 3.931481242315993e-07,
"loss": 0.3735,
"step": 206
},
{
"epoch": 6.334177215189873,
"grad_norm": 0.2605523854067743,
"learning_rate": 3.5092868495520294e-07,
"loss": 0.3817,
"step": 207
},
{
"epoch": 6.364556962025317,
"grad_norm": 0.2695487698875214,
"learning_rate": 3.110663798593616e-07,
"loss": 0.3552,
"step": 208
},
{
"epoch": 6.39493670886076,
"grad_norm": 0.2632496323185191,
"learning_rate": 2.735709467518699e-07,
"loss": 0.3951,
"step": 209
},
{
"epoch": 6.425316455696202,
"grad_norm": 0.26319493343428935,
"learning_rate": 2.384515452465475e-07,
"loss": 0.3844,
"step": 210
},
{
"epoch": 6.455696202531645,
"grad_norm": 0.2681183752860782,
"learning_rate": 2.0571675452567997e-07,
"loss": 0.3609,
"step": 211
},
{
"epoch": 6.4860759493670885,
"grad_norm": 0.2639707830859557,
"learning_rate": 1.7537457124423896e-07,
"loss": 0.3546,
"step": 212
},
{
"epoch": 6.516455696202532,
"grad_norm": 0.25038051168665226,
"learning_rate": 1.474324075764111e-07,
"loss": 0.3779,
"step": 213
},
{
"epoch": 6.546835443037975,
"grad_norm": 0.25624777877512755,
"learning_rate": 1.2189708940490653e-07,
"loss": 0.3578,
"step": 214
},
{
"epoch": 6.577215189873417,
"grad_norm": 0.25930387227382895,
"learning_rate": 9.877485465349057e-08,
"loss": 0.3978,
"step": 215
},
{
"epoch": 6.6075949367088604,
"grad_norm": 0.25883324610741487,
"learning_rate": 7.807135176314707e-08,
"loss": 0.3708,
"step": 216
},
{
"epoch": 6.637974683544304,
"grad_norm": 0.25186354236219294,
"learning_rate": 5.979163831223988e-08,
"loss": 0.3781,
"step": 217
},
{
"epoch": 6.668354430379747,
"grad_norm": 0.26201469315535847,
"learning_rate": 4.394017978101905e-08,
"loss": 0.361,
"step": 218
},
{
"epoch": 6.69873417721519,
"grad_norm": 0.2472812453750152,
"learning_rate": 3.0520848460765525e-08,
"loss": 0.3743,
"step": 219
},
{
"epoch": 6.729113924050633,
"grad_norm": 0.2538763807451828,
"learning_rate": 1.9536922507841227e-08,
"loss": 0.3953,
"step": 220
},
{
"epoch": 6.759493670886076,
"grad_norm": 0.24560347295573776,
"learning_rate": 1.099108514288627e-08,
"loss": 0.402,
"step": 221
},
{
"epoch": 6.789873417721519,
"grad_norm": 0.2466972985551776,
"learning_rate": 4.885423995341088e-09,
"loss": 0.3898,
"step": 222
},
{
"epoch": 6.820253164556962,
"grad_norm": 0.26633009953562375,
"learning_rate": 1.2214305934699078e-09,
"loss": 0.3493,
"step": 223
},
{
"epoch": 6.850632911392405,
"grad_norm": 0.25554676720440084,
"learning_rate": 0.0,
"loss": 0.3742,
"step": 224
},
{
"epoch": 6.850632911392405,
"step": 224,
"total_flos": 8.23521885332439e+17,
"train_loss": 0.5255122670371618,
"train_runtime": 26603.9028,
"train_samples_per_second": 0.831,
"train_steps_per_second": 0.008
}
],
"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": 8.23521885332439e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}