openmathreasoning_3k / trainer_state.json
ryanmarten's picture
Upload model
3d61b7b 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": 6.048936306987692,
"learning_rate": 8.695652173913044e-07,
"loss": 0.8419,
"step": 1
},
{
"epoch": 0.060759493670886074,
"grad_norm": 6.359706790120916,
"learning_rate": 1.7391304347826088e-06,
"loss": 0.8759,
"step": 2
},
{
"epoch": 0.09113924050632911,
"grad_norm": 6.131019897142869,
"learning_rate": 2.6086956521739132e-06,
"loss": 0.8305,
"step": 3
},
{
"epoch": 0.12151898734177215,
"grad_norm": 5.574055055372666,
"learning_rate": 3.4782608695652175e-06,
"loss": 0.8242,
"step": 4
},
{
"epoch": 0.1518987341772152,
"grad_norm": 4.265951668457725,
"learning_rate": 4.347826086956522e-06,
"loss": 0.7634,
"step": 5
},
{
"epoch": 0.18227848101265823,
"grad_norm": 2.464962480859038,
"learning_rate": 5.2173913043478265e-06,
"loss": 0.7492,
"step": 6
},
{
"epoch": 0.21265822784810126,
"grad_norm": 2.077337266343512,
"learning_rate": 6.086956521739132e-06,
"loss": 0.7265,
"step": 7
},
{
"epoch": 0.2430379746835443,
"grad_norm": 4.14036522612642,
"learning_rate": 6.956521739130435e-06,
"loss": 0.7563,
"step": 8
},
{
"epoch": 0.27341772151898736,
"grad_norm": 4.45973658282638,
"learning_rate": 7.82608695652174e-06,
"loss": 0.7747,
"step": 9
},
{
"epoch": 0.3037974683544304,
"grad_norm": 4.521818388157711,
"learning_rate": 8.695652173913044e-06,
"loss": 0.7341,
"step": 10
},
{
"epoch": 0.3341772151898734,
"grad_norm": 4.422444866803943,
"learning_rate": 9.565217391304349e-06,
"loss": 0.6844,
"step": 11
},
{
"epoch": 0.36455696202531646,
"grad_norm": 3.9402544164657844,
"learning_rate": 1.0434782608695653e-05,
"loss": 0.692,
"step": 12
},
{
"epoch": 0.3949367088607595,
"grad_norm": 2.6928462031464337,
"learning_rate": 1.1304347826086957e-05,
"loss": 0.6945,
"step": 13
},
{
"epoch": 0.4253164556962025,
"grad_norm": 1.8595232870527427,
"learning_rate": 1.2173913043478263e-05,
"loss": 0.654,
"step": 14
},
{
"epoch": 0.45569620253164556,
"grad_norm": 2.613185640118858,
"learning_rate": 1.3043478260869566e-05,
"loss": 0.671,
"step": 15
},
{
"epoch": 0.4860759493670886,
"grad_norm": 2.110958057017735,
"learning_rate": 1.391304347826087e-05,
"loss": 0.6169,
"step": 16
},
{
"epoch": 0.5164556962025316,
"grad_norm": 1.737170053034775,
"learning_rate": 1.4782608695652174e-05,
"loss": 0.6203,
"step": 17
},
{
"epoch": 0.5468354430379747,
"grad_norm": 1.5084674691399222,
"learning_rate": 1.565217391304348e-05,
"loss": 0.6149,
"step": 18
},
{
"epoch": 0.5772151898734177,
"grad_norm": 1.3494948400477569,
"learning_rate": 1.6521739130434785e-05,
"loss": 0.6517,
"step": 19
},
{
"epoch": 0.6075949367088608,
"grad_norm": 1.1751438322676817,
"learning_rate": 1.739130434782609e-05,
"loss": 0.6033,
"step": 20
},
{
"epoch": 0.6379746835443038,
"grad_norm": 1.0526414875931804,
"learning_rate": 1.8260869565217393e-05,
"loss": 0.64,
"step": 21
},
{
"epoch": 0.6683544303797468,
"grad_norm": 0.9715611441669768,
"learning_rate": 1.9130434782608697e-05,
"loss": 0.5927,
"step": 22
},
{
"epoch": 0.6987341772151898,
"grad_norm": 0.8125624310216422,
"learning_rate": 2e-05,
"loss": 0.607,
"step": 23
},
{
"epoch": 0.7291139240506329,
"grad_norm": 0.9223345735056782,
"learning_rate": 1.999877856940653e-05,
"loss": 0.561,
"step": 24
},
{
"epoch": 0.759493670886076,
"grad_norm": 0.8243964896311464,
"learning_rate": 1.999511457600466e-05,
"loss": 0.5872,
"step": 25
},
{
"epoch": 0.789873417721519,
"grad_norm": 0.7512429692602848,
"learning_rate": 1.9989008914857115e-05,
"loss": 0.5711,
"step": 26
},
{
"epoch": 0.8202531645569621,
"grad_norm": 0.7459000930728743,
"learning_rate": 1.998046307749216e-05,
"loss": 0.5801,
"step": 27
},
{
"epoch": 0.850632911392405,
"grad_norm": 0.6995303209474417,
"learning_rate": 1.9969479151539238e-05,
"loss": 0.5549,
"step": 28
},
{
"epoch": 0.8810126582278481,
"grad_norm": 0.7124104382437041,
"learning_rate": 1.9956059820218982e-05,
"loss": 0.5468,
"step": 29
},
{
"epoch": 0.9113924050632911,
"grad_norm": 0.7059343154396499,
"learning_rate": 1.9940208361687762e-05,
"loss": 0.5723,
"step": 30
},
{
"epoch": 0.9417721518987342,
"grad_norm": 0.7009167310881045,
"learning_rate": 1.9921928648236855e-05,
"loss": 0.548,
"step": 31
},
{
"epoch": 0.9721518987341772,
"grad_norm": 0.8724240967159428,
"learning_rate": 1.990122514534651e-05,
"loss": 0.5918,
"step": 32
},
{
"epoch": 1.010126582278481,
"grad_norm": 0.8468019563645511,
"learning_rate": 1.9878102910595097e-05,
"loss": 0.7317,
"step": 33
},
{
"epoch": 1.040506329113924,
"grad_norm": 0.5559186721993208,
"learning_rate": 1.985256759242359e-05,
"loss": 0.4849,
"step": 34
},
{
"epoch": 1.070886075949367,
"grad_norm": 0.5507474685198273,
"learning_rate": 1.982462542875576e-05,
"loss": 0.5334,
"step": 35
},
{
"epoch": 1.1012658227848102,
"grad_norm": 0.543870017484278,
"learning_rate": 1.979428324547432e-05,
"loss": 0.5487,
"step": 36
},
{
"epoch": 1.1316455696202532,
"grad_norm": 0.6225002865248337,
"learning_rate": 1.9761548454753455e-05,
"loss": 0.5186,
"step": 37
},
{
"epoch": 1.1620253164556962,
"grad_norm": 0.5335951367889052,
"learning_rate": 1.972642905324813e-05,
"loss": 0.5121,
"step": 38
},
{
"epoch": 1.1924050632911392,
"grad_norm": 0.569943007419904,
"learning_rate": 1.9688933620140638e-05,
"loss": 0.4835,
"step": 39
},
{
"epoch": 1.2227848101265824,
"grad_norm": 0.5616599542859847,
"learning_rate": 1.96490713150448e-05,
"loss": 0.5062,
"step": 40
},
{
"epoch": 1.2531645569620253,
"grad_norm": 0.5176704614796857,
"learning_rate": 1.9606851875768404e-05,
"loss": 0.4821,
"step": 41
},
{
"epoch": 1.2835443037974683,
"grad_norm": 0.6013616477281641,
"learning_rate": 1.956228561593441e-05,
"loss": 0.4862,
"step": 42
},
{
"epoch": 1.3139240506329113,
"grad_norm": 0.5799218399260377,
"learning_rate": 1.9515383422461457e-05,
"loss": 0.5455,
"step": 43
},
{
"epoch": 1.3443037974683545,
"grad_norm": 0.48791349493694947,
"learning_rate": 1.9466156752904344e-05,
"loss": 0.4558,
"step": 44
},
{
"epoch": 1.3746835443037975,
"grad_norm": 0.5460867482558168,
"learning_rate": 1.9414617632655114e-05,
"loss": 0.4949,
"step": 45
},
{
"epoch": 1.4050632911392404,
"grad_norm": 0.5200300630053336,
"learning_rate": 1.9360778652005416e-05,
"loss": 0.5226,
"step": 46
},
{
"epoch": 1.4354430379746836,
"grad_norm": 0.49835905260454255,
"learning_rate": 1.9304652963070868e-05,
"loss": 0.4988,
"step": 47
},
{
"epoch": 1.4658227848101266,
"grad_norm": 0.555402108007746,
"learning_rate": 1.9246254276578175e-05,
"loss": 0.4811,
"step": 48
},
{
"epoch": 1.4962025316455696,
"grad_norm": 0.5043821831864128,
"learning_rate": 1.9185596858515797e-05,
"loss": 0.5409,
"step": 49
},
{
"epoch": 1.5265822784810128,
"grad_norm": 0.5095173005875876,
"learning_rate": 1.9122695526648968e-05,
"loss": 0.4574,
"step": 50
},
{
"epoch": 1.5569620253164556,
"grad_norm": 0.5297774307671909,
"learning_rate": 1.905756564689991e-05,
"loss": 0.4825,
"step": 51
},
{
"epoch": 1.5873417721518988,
"grad_norm": 0.4497569232214527,
"learning_rate": 1.8990223129594146e-05,
"loss": 0.4634,
"step": 52
},
{
"epoch": 1.6177215189873417,
"grad_norm": 0.5108891340546695,
"learning_rate": 1.8920684425573865e-05,
"loss": 0.469,
"step": 53
},
{
"epoch": 1.6481012658227847,
"grad_norm": 0.5389740099999035,
"learning_rate": 1.884896652217917e-05,
"loss": 0.5486,
"step": 54
},
{
"epoch": 1.678481012658228,
"grad_norm": 0.5137420177298216,
"learning_rate": 1.877508693909831e-05,
"loss": 0.4983,
"step": 55
},
{
"epoch": 1.7088607594936709,
"grad_norm": 0.49925713696145874,
"learning_rate": 1.8699063724087905e-05,
"loss": 0.5272,
"step": 56
},
{
"epoch": 1.7392405063291139,
"grad_norm": 0.5914481358656738,
"learning_rate": 1.862091544856407e-05,
"loss": 0.4924,
"step": 57
},
{
"epoch": 1.769620253164557,
"grad_norm": 0.4664469979995995,
"learning_rate": 1.854066120306571e-05,
"loss": 0.4759,
"step": 58
},
{
"epoch": 1.8,
"grad_norm": 0.47080488802947457,
"learning_rate": 1.8458320592590976e-05,
"loss": 0.4812,
"step": 59
},
{
"epoch": 1.830379746835443,
"grad_norm": 0.5587905613183901,
"learning_rate": 1.837391373180801e-05,
"loss": 0.4888,
"step": 60
},
{
"epoch": 1.8607594936708862,
"grad_norm": 0.5050554675255995,
"learning_rate": 1.8287461240141217e-05,
"loss": 0.5033,
"step": 61
},
{
"epoch": 1.891139240506329,
"grad_norm": 0.47145338803039966,
"learning_rate": 1.8198984236734246e-05,
"loss": 0.4764,
"step": 62
},
{
"epoch": 1.9215189873417722,
"grad_norm": 0.5018576539215808,
"learning_rate": 1.8108504335290852e-05,
"loss": 0.4561,
"step": 63
},
{
"epoch": 1.9518987341772152,
"grad_norm": 0.45811612746325875,
"learning_rate": 1.8016043638794975e-05,
"loss": 0.5324,
"step": 64
},
{
"epoch": 1.9822784810126581,
"grad_norm": 0.6144932201086315,
"learning_rate": 1.7921624734111292e-05,
"loss": 0.578,
"step": 65
},
{
"epoch": 2.020253164556962,
"grad_norm": 0.5726068435884388,
"learning_rate": 1.7825270686467567e-05,
"loss": 0.544,
"step": 66
},
{
"epoch": 2.050632911392405,
"grad_norm": 0.4648598668226982,
"learning_rate": 1.7727005033820117e-05,
"loss": 0.4308,
"step": 67
},
{
"epoch": 2.081012658227848,
"grad_norm": 0.4721375558424858,
"learning_rate": 1.762685178110382e-05,
"loss": 0.4194,
"step": 68
},
{
"epoch": 2.1113924050632913,
"grad_norm": 0.4771552931363247,
"learning_rate": 1.752483539436807e-05,
"loss": 0.4197,
"step": 69
},
{
"epoch": 2.141772151898734,
"grad_norm": 0.4797766115828031,
"learning_rate": 1.7420980794800013e-05,
"loss": 0.434,
"step": 70
},
{
"epoch": 2.1721518987341772,
"grad_norm": 0.4847501246260971,
"learning_rate": 1.731531335263669e-05,
"loss": 0.4094,
"step": 71
},
{
"epoch": 2.2025316455696204,
"grad_norm": 0.5715606812513879,
"learning_rate": 1.720785888096743e-05,
"loss": 0.4107,
"step": 72
},
{
"epoch": 2.232911392405063,
"grad_norm": 0.4651167769261771,
"learning_rate": 1.7098643629428035e-05,
"loss": 0.4111,
"step": 73
},
{
"epoch": 2.2632911392405064,
"grad_norm": 0.45587437771999223,
"learning_rate": 1.698769427778842e-05,
"loss": 0.413,
"step": 74
},
{
"epoch": 2.293670886075949,
"grad_norm": 0.5442546749379886,
"learning_rate": 1.687503792943506e-05,
"loss": 0.4373,
"step": 75
},
{
"epoch": 2.3240506329113924,
"grad_norm": 0.4824118869055176,
"learning_rate": 1.6760702104750046e-05,
"loss": 0.4257,
"step": 76
},
{
"epoch": 2.3544303797468356,
"grad_norm": 0.4781817061972643,
"learning_rate": 1.664471473438822e-05,
"loss": 0.4014,
"step": 77
},
{
"epoch": 2.3848101265822783,
"grad_norm": 0.4088771271312156,
"learning_rate": 1.6527104152454096e-05,
"loss": 0.3802,
"step": 78
},
{
"epoch": 2.4151898734177215,
"grad_norm": 0.5516321100838191,
"learning_rate": 1.6407899089580263e-05,
"loss": 0.449,
"step": 79
},
{
"epoch": 2.4455696202531647,
"grad_norm": 0.4716858671975667,
"learning_rate": 1.628712866590885e-05,
"loss": 0.3853,
"step": 80
},
{
"epoch": 2.4759493670886075,
"grad_norm": 0.45334870047529424,
"learning_rate": 1.6164822383977912e-05,
"loss": 0.4197,
"step": 81
},
{
"epoch": 2.5063291139240507,
"grad_norm": 0.4650898860452062,
"learning_rate": 1.604101012151436e-05,
"loss": 0.4325,
"step": 82
},
{
"epoch": 2.536708860759494,
"grad_norm": 0.6733951603850473,
"learning_rate": 1.5915722124135227e-05,
"loss": 0.4346,
"step": 83
},
{
"epoch": 2.5670886075949366,
"grad_norm": 0.3741787332470752,
"learning_rate": 1.5788988997959115e-05,
"loss": 0.4168,
"step": 84
},
{
"epoch": 2.59746835443038,
"grad_norm": 0.4673023466091711,
"learning_rate": 1.5660841702129533e-05,
"loss": 0.4387,
"step": 85
},
{
"epoch": 2.6278481012658226,
"grad_norm": 0.5113903636282513,
"learning_rate": 1.5531311541251995e-05,
"loss": 0.3882,
"step": 86
},
{
"epoch": 2.6582278481012658,
"grad_norm": 0.3987776866070054,
"learning_rate": 1.540043015774676e-05,
"loss": 0.4384,
"step": 87
},
{
"epoch": 2.688607594936709,
"grad_norm": 0.5000328088996094,
"learning_rate": 1.5268229524119007e-05,
"loss": 0.4427,
"step": 88
},
{
"epoch": 2.7189873417721517,
"grad_norm": 0.42774760061205236,
"learning_rate": 1.513474193514842e-05,
"loss": 0.4242,
"step": 89
},
{
"epoch": 2.749367088607595,
"grad_norm": 0.4770182422848908,
"learning_rate": 1.5000000000000002e-05,
"loss": 0.4079,
"step": 90
},
{
"epoch": 2.779746835443038,
"grad_norm": 0.5326476152699332,
"learning_rate": 1.4864036634258112e-05,
"loss": 0.4264,
"step": 91
},
{
"epoch": 2.810126582278481,
"grad_norm": 0.4142295571778557,
"learning_rate": 1.4726885051885654e-05,
"loss": 0.4049,
"step": 92
},
{
"epoch": 2.840506329113924,
"grad_norm": 0.5296388184052468,
"learning_rate": 1.4588578757110359e-05,
"loss": 0.4073,
"step": 93
},
{
"epoch": 2.8708860759493673,
"grad_norm": 0.4359077641154996,
"learning_rate": 1.4449151536240167e-05,
"loss": 0.4054,
"step": 94
},
{
"epoch": 2.90126582278481,
"grad_norm": 0.53763398646354,
"learning_rate": 1.4308637449409705e-05,
"loss": 0.3915,
"step": 95
},
{
"epoch": 2.9316455696202532,
"grad_norm": 0.5156253519333039,
"learning_rate": 1.4167070822259868e-05,
"loss": 0.4718,
"step": 96
},
{
"epoch": 2.962025316455696,
"grad_norm": 0.4317302365758521,
"learning_rate": 1.402448623755254e-05,
"loss": 0.3884,
"step": 97
},
{
"epoch": 2.992405063291139,
"grad_norm": 0.5536609198782718,
"learning_rate": 1.3880918526722497e-05,
"loss": 0.5473,
"step": 98
},
{
"epoch": 3.030379746835443,
"grad_norm": 0.5545528571506598,
"learning_rate": 1.3736402761368597e-05,
"loss": 0.3687,
"step": 99
},
{
"epoch": 3.060759493670886,
"grad_norm": 0.47540586403474266,
"learning_rate": 1.3590974244686248e-05,
"loss": 0.3472,
"step": 100
},
{
"epoch": 3.091139240506329,
"grad_norm": 0.515690188434661,
"learning_rate": 1.344466850284333e-05,
"loss": 0.3524,
"step": 101
},
{
"epoch": 3.1215189873417724,
"grad_norm": 0.5494008492815136,
"learning_rate": 1.3297521276301666e-05,
"loss": 0.3492,
"step": 102
},
{
"epoch": 3.151898734177215,
"grad_norm": 0.5613723693617616,
"learning_rate": 1.3149568511086104e-05,
"loss": 0.3475,
"step": 103
},
{
"epoch": 3.1822784810126583,
"grad_norm": 0.5459731136472022,
"learning_rate": 1.300084635000341e-05,
"loss": 0.3516,
"step": 104
},
{
"epoch": 3.212658227848101,
"grad_norm": 0.4928481785761879,
"learning_rate": 1.2851391123813075e-05,
"loss": 0.3367,
"step": 105
},
{
"epoch": 3.2430379746835443,
"grad_norm": 0.5784610134826562,
"learning_rate": 1.2701239342352223e-05,
"loss": 0.3711,
"step": 106
},
{
"epoch": 3.2734177215189875,
"grad_norm": 0.5334142496880356,
"learning_rate": 1.2550427685616767e-05,
"loss": 0.3632,
"step": 107
},
{
"epoch": 3.3037974683544302,
"grad_norm": 0.45364002557641886,
"learning_rate": 1.239899299480098e-05,
"loss": 0.3456,
"step": 108
},
{
"epoch": 3.3341772151898734,
"grad_norm": 0.5342722692936496,
"learning_rate": 1.2246972263297718e-05,
"loss": 0.3521,
"step": 109
},
{
"epoch": 3.3645569620253166,
"grad_norm": 0.45373690200799116,
"learning_rate": 1.2094402627661447e-05,
"loss": 0.3482,
"step": 110
},
{
"epoch": 3.3949367088607594,
"grad_norm": 0.5348735784600784,
"learning_rate": 1.1941321358536278e-05,
"loss": 0.347,
"step": 111
},
{
"epoch": 3.4253164556962026,
"grad_norm": 0.42289751752473753,
"learning_rate": 1.1787765851551296e-05,
"loss": 0.3523,
"step": 112
},
{
"epoch": 3.4556962025316453,
"grad_norm": 0.4787683178291163,
"learning_rate": 1.1633773618185302e-05,
"loss": 0.3406,
"step": 113
},
{
"epoch": 3.4860759493670885,
"grad_norm": 0.5114943466720573,
"learning_rate": 1.14793822766033e-05,
"loss": 0.3488,
"step": 114
},
{
"epoch": 3.5164556962025317,
"grad_norm": 0.4725452864287685,
"learning_rate": 1.132462954246688e-05,
"loss": 0.3417,
"step": 115
},
{
"epoch": 3.546835443037975,
"grad_norm": 0.42049657665542955,
"learning_rate": 1.1169553219720828e-05,
"loss": 0.3619,
"step": 116
},
{
"epoch": 3.5772151898734177,
"grad_norm": 0.4686354978703038,
"learning_rate": 1.1014191191358118e-05,
"loss": 0.357,
"step": 117
},
{
"epoch": 3.607594936708861,
"grad_norm": 0.4205375090893493,
"learning_rate": 1.085858141016566e-05,
"loss": 0.353,
"step": 118
},
{
"epoch": 3.6379746835443036,
"grad_norm": 0.48202907492458946,
"learning_rate": 1.070276188945293e-05,
"loss": 0.3616,
"step": 119
},
{
"epoch": 3.668354430379747,
"grad_norm": 0.43220350995269835,
"learning_rate": 1.0546770693765859e-05,
"loss": 0.3573,
"step": 120
},
{
"epoch": 3.69873417721519,
"grad_norm": 0.4056113080170557,
"learning_rate": 1.0390645929588197e-05,
"loss": 0.3527,
"step": 121
},
{
"epoch": 3.729113924050633,
"grad_norm": 0.38542910276260156,
"learning_rate": 1.0234425736032607e-05,
"loss": 0.3546,
"step": 122
},
{
"epoch": 3.759493670886076,
"grad_norm": 0.41172976094134517,
"learning_rate": 1.007814827552384e-05,
"loss": 0.3383,
"step": 123
},
{
"epoch": 3.7898734177215188,
"grad_norm": 0.3422368161340203,
"learning_rate": 9.92185172447616e-06,
"loss": 0.3325,
"step": 124
},
{
"epoch": 3.820253164556962,
"grad_norm": 0.4074688839173423,
"learning_rate": 9.765574263967397e-06,
"loss": 0.3437,
"step": 125
},
{
"epoch": 3.850632911392405,
"grad_norm": 0.34849002000782986,
"learning_rate": 9.609354070411807e-06,
"loss": 0.3607,
"step": 126
},
{
"epoch": 3.8810126582278484,
"grad_norm": 0.4029722649627817,
"learning_rate": 9.453229306234143e-06,
"loss": 0.3485,
"step": 127
},
{
"epoch": 3.911392405063291,
"grad_norm": 0.36141335416240483,
"learning_rate": 9.297238110547075e-06,
"loss": 0.3584,
"step": 128
},
{
"epoch": 3.9417721518987343,
"grad_norm": 0.37260661041502396,
"learning_rate": 9.14141858983434e-06,
"loss": 0.3416,
"step": 129
},
{
"epoch": 3.972151898734177,
"grad_norm": 0.32216912148540366,
"learning_rate": 8.985808808641883e-06,
"loss": 0.3286,
"step": 130
},
{
"epoch": 4.010126582278481,
"grad_norm": 0.5313463942187743,
"learning_rate": 8.830446780279175e-06,
"loss": 0.4363,
"step": 131
},
{
"epoch": 4.040506329113924,
"grad_norm": 0.4707890932151999,
"learning_rate": 8.675370457533122e-06,
"loss": 0.2624,
"step": 132
},
{
"epoch": 4.0708860759493675,
"grad_norm": 0.4041133834341088,
"learning_rate": 8.520617723396702e-06,
"loss": 0.2915,
"step": 133
},
{
"epoch": 4.10126582278481,
"grad_norm": 0.6431830303938959,
"learning_rate": 8.366226381814698e-06,
"loss": 0.2931,
"step": 134
},
{
"epoch": 4.131645569620253,
"grad_norm": 0.453099306620913,
"learning_rate": 8.212234148448708e-06,
"loss": 0.2703,
"step": 135
},
{
"epoch": 4.162025316455696,
"grad_norm": 0.41936391731434275,
"learning_rate": 8.058678641463724e-06,
"loss": 0.2771,
"step": 136
},
{
"epoch": 4.192405063291139,
"grad_norm": 0.4505732726130199,
"learning_rate": 7.905597372338558e-06,
"loss": 0.2985,
"step": 137
},
{
"epoch": 4.222784810126583,
"grad_norm": 0.4103967350890258,
"learning_rate": 7.753027736702283e-06,
"loss": 0.2758,
"step": 138
},
{
"epoch": 4.253164556962025,
"grad_norm": 0.3973605581799497,
"learning_rate": 7.601007005199022e-06,
"loss": 0.2813,
"step": 139
},
{
"epoch": 4.283544303797468,
"grad_norm": 0.4589582439764549,
"learning_rate": 7.449572314383237e-06,
"loss": 0.3221,
"step": 140
},
{
"epoch": 4.313924050632911,
"grad_norm": 0.4274255668686267,
"learning_rate": 7.298760657647779e-06,
"loss": 0.3047,
"step": 141
},
{
"epoch": 4.3443037974683545,
"grad_norm": 0.35657773449481966,
"learning_rate": 7.148608876186931e-06,
"loss": 0.2554,
"step": 142
},
{
"epoch": 4.374683544303798,
"grad_norm": 0.3620039303083875,
"learning_rate": 6.999153649996595e-06,
"loss": 0.2675,
"step": 143
},
{
"epoch": 4.405063291139241,
"grad_norm": 0.3989026378463725,
"learning_rate": 6.8504314889138956e-06,
"loss": 0.2979,
"step": 144
},
{
"epoch": 4.435443037974683,
"grad_norm": 0.3873971390047792,
"learning_rate": 6.702478723698336e-06,
"loss": 0.3001,
"step": 145
},
{
"epoch": 4.465822784810126,
"grad_norm": 0.3638331605928393,
"learning_rate": 6.555331497156671e-06,
"loss": 0.2889,
"step": 146
},
{
"epoch": 4.49620253164557,
"grad_norm": 0.3838325042159884,
"learning_rate": 6.4090257553137566e-06,
"loss": 0.2867,
"step": 147
},
{
"epoch": 4.526582278481013,
"grad_norm": 0.36671976978412335,
"learning_rate": 6.263597238631405e-06,
"loss": 0.28,
"step": 148
},
{
"epoch": 4.556962025316456,
"grad_norm": 0.3529133852651092,
"learning_rate": 6.119081473277502e-06,
"loss": 0.2734,
"step": 149
},
{
"epoch": 4.587341772151898,
"grad_norm": 0.36640770826259494,
"learning_rate": 5.975513762447465e-06,
"loss": 0.3092,
"step": 150
},
{
"epoch": 4.6177215189873415,
"grad_norm": 0.3100594224902787,
"learning_rate": 5.832929177740134e-06,
"loss": 0.2669,
"step": 151
},
{
"epoch": 4.648101265822785,
"grad_norm": 0.377115982323163,
"learning_rate": 5.6913625505902966e-06,
"loss": 0.3186,
"step": 152
},
{
"epoch": 4.678481012658228,
"grad_norm": 0.33216684017323544,
"learning_rate": 5.550848463759835e-06,
"loss": 0.286,
"step": 153
},
{
"epoch": 4.708860759493671,
"grad_norm": 0.40784371682031095,
"learning_rate": 5.411421242889643e-06,
"loss": 0.2838,
"step": 154
},
{
"epoch": 4.739240506329114,
"grad_norm": 0.3120609511166079,
"learning_rate": 5.273114948114346e-06,
"loss": 0.2676,
"step": 155
},
{
"epoch": 4.769620253164557,
"grad_norm": 0.35298019160098854,
"learning_rate": 5.135963365741892e-06,
"loss": 0.3151,
"step": 156
},
{
"epoch": 4.8,
"grad_norm": 0.3237915668775047,
"learning_rate": 5.000000000000003e-06,
"loss": 0.2875,
"step": 157
},
{
"epoch": 4.830379746835443,
"grad_norm": 0.3341363814264824,
"learning_rate": 4.865258064851579e-06,
"loss": 0.2942,
"step": 158
},
{
"epoch": 4.860759493670886,
"grad_norm": 0.36919767508786167,
"learning_rate": 4.731770475880995e-06,
"loss": 0.3048,
"step": 159
},
{
"epoch": 4.891139240506329,
"grad_norm": 0.3091966055573231,
"learning_rate": 4.599569842253244e-06,
"loss": 0.2449,
"step": 160
},
{
"epoch": 4.921518987341772,
"grad_norm": 0.30134927381043464,
"learning_rate": 4.468688458748006e-06,
"loss": 0.2842,
"step": 161
},
{
"epoch": 4.951898734177215,
"grad_norm": 0.33724978042903153,
"learning_rate": 4.339158297870469e-06,
"loss": 0.2991,
"step": 162
},
{
"epoch": 4.982278481012658,
"grad_norm": 0.37910349336098464,
"learning_rate": 4.211011002040885e-06,
"loss": 0.3041,
"step": 163
},
{
"epoch": 5.020253164556962,
"grad_norm": 0.4523545633061669,
"learning_rate": 4.084277875864776e-06,
"loss": 0.309,
"step": 164
},
{
"epoch": 5.050632911392405,
"grad_norm": 0.4730924017069626,
"learning_rate": 3.958989878485644e-06,
"loss": 0.2502,
"step": 165
},
{
"epoch": 5.0810126582278485,
"grad_norm": 0.32201262114708323,
"learning_rate": 3.83517761602209e-06,
"loss": 0.2423,
"step": 166
},
{
"epoch": 5.111392405063291,
"grad_norm": 0.3821460864301905,
"learning_rate": 3.712871334091154e-06,
"loss": 0.2684,
"step": 167
},
{
"epoch": 5.141772151898734,
"grad_norm": 0.5256405500408324,
"learning_rate": 3.592100910419738e-06,
"loss": 0.2356,
"step": 168
},
{
"epoch": 5.172151898734177,
"grad_norm": 0.4491399278571054,
"learning_rate": 3.4728958475459052e-06,
"loss": 0.2432,
"step": 169
},
{
"epoch": 5.2025316455696204,
"grad_norm": 0.3335828076072433,
"learning_rate": 3.355285265611784e-06,
"loss": 0.2306,
"step": 170
},
{
"epoch": 5.232911392405064,
"grad_norm": 0.35927027153636726,
"learning_rate": 3.2392978952499553e-06,
"loss": 0.2499,
"step": 171
},
{
"epoch": 5.263291139240506,
"grad_norm": 0.37950495707252624,
"learning_rate": 3.1249620705649417e-06,
"loss": 0.268,
"step": 172
},
{
"epoch": 5.293670886075949,
"grad_norm": 0.38081595421286196,
"learning_rate": 3.0123057222115835e-06,
"loss": 0.2262,
"step": 173
},
{
"epoch": 5.324050632911392,
"grad_norm": 0.3490511429252917,
"learning_rate": 2.9013563705719673e-06,
"loss": 0.2461,
"step": 174
},
{
"epoch": 5.3544303797468356,
"grad_norm": 0.3185986215642651,
"learning_rate": 2.7921411190325753e-06,
"loss": 0.2493,
"step": 175
},
{
"epoch": 5.384810126582279,
"grad_norm": 0.3417114934255241,
"learning_rate": 2.6846866473633126e-06,
"loss": 0.2504,
"step": 176
},
{
"epoch": 5.415189873417722,
"grad_norm": 0.3607610625513573,
"learning_rate": 2.579019205199992e-06,
"loss": 0.2463,
"step": 177
},
{
"epoch": 5.445569620253164,
"grad_norm": 0.4170005526871216,
"learning_rate": 2.4751646056319334e-06,
"loss": 0.2606,
"step": 178
},
{
"epoch": 5.4759493670886075,
"grad_norm": 0.3233946450979762,
"learning_rate": 2.373148218896182e-06,
"loss": 0.2228,
"step": 179
},
{
"epoch": 5.506329113924051,
"grad_norm": 0.3177352084454099,
"learning_rate": 2.2729949661798876e-06,
"loss": 0.2477,
"step": 180
},
{
"epoch": 5.536708860759494,
"grad_norm": 0.3141459292831218,
"learning_rate": 2.174729313532433e-06,
"loss": 0.2358,
"step": 181
},
{
"epoch": 5.567088607594937,
"grad_norm": 0.3133255531748914,
"learning_rate": 2.078375265888707e-06,
"loss": 0.2372,
"step": 182
},
{
"epoch": 5.597468354430379,
"grad_norm": 0.33090769348276167,
"learning_rate": 1.9839563612050273e-06,
"loss": 0.2578,
"step": 183
},
{
"epoch": 5.627848101265823,
"grad_norm": 0.30752461939556636,
"learning_rate": 1.8914956647091497e-06,
"loss": 0.2225,
"step": 184
},
{
"epoch": 5.658227848101266,
"grad_norm": 0.3212700019589481,
"learning_rate": 1.8010157632657544e-06,
"loss": 0.2503,
"step": 185
},
{
"epoch": 5.688607594936709,
"grad_norm": 0.30346268594769565,
"learning_rate": 1.7125387598587862e-06,
"loss": 0.2596,
"step": 186
},
{
"epoch": 5.718987341772152,
"grad_norm": 0.3006756556681579,
"learning_rate": 1.6260862681919965e-06,
"loss": 0.2301,
"step": 187
},
{
"epoch": 5.749367088607595,
"grad_norm": 0.31423052889864206,
"learning_rate": 1.5416794074090258e-06,
"loss": 0.2429,
"step": 188
},
{
"epoch": 5.779746835443038,
"grad_norm": 0.30980107031353704,
"learning_rate": 1.459338796934293e-06,
"loss": 0.2291,
"step": 189
},
{
"epoch": 5.810126582278481,
"grad_norm": 0.33434803432375376,
"learning_rate": 1.3790845514359363e-06,
"loss": 0.2571,
"step": 190
},
{
"epoch": 5.840506329113924,
"grad_norm": 0.292122548663931,
"learning_rate": 1.300936275912098e-06,
"loss": 0.218,
"step": 191
},
{
"epoch": 5.870886075949367,
"grad_norm": 0.297080299478135,
"learning_rate": 1.224913060901688e-06,
"loss": 0.2215,
"step": 192
},
{
"epoch": 5.9012658227848105,
"grad_norm": 0.30222638091145526,
"learning_rate": 1.1510334778208332e-06,
"loss": 0.2474,
"step": 193
},
{
"epoch": 5.931645569620253,
"grad_norm": 0.3085881315778646,
"learning_rate": 1.0793155744261352e-06,
"loss": 0.2553,
"step": 194
},
{
"epoch": 5.962025316455696,
"grad_norm": 0.28842240439901007,
"learning_rate": 1.0097768704058542e-06,
"loss": 0.2308,
"step": 195
},
{
"epoch": 5.992405063291139,
"grad_norm": 0.38844373768880613,
"learning_rate": 9.424343531000968e-07,
"loss": 0.3175,
"step": 196
},
{
"epoch": 6.030379746835443,
"grad_norm": 0.3756548730251041,
"learning_rate": 8.773044733510338e-07,
"loss": 0.2141,
"step": 197
},
{
"epoch": 6.060759493670886,
"grad_norm": 0.36880100887113676,
"learning_rate": 8.144031414842012e-07,
"loss": 0.2378,
"step": 198
},
{
"epoch": 6.091139240506329,
"grad_norm": 0.3740777777425036,
"learning_rate": 7.537457234218271e-07,
"loss": 0.2105,
"step": 199
},
{
"epoch": 6.121518987341772,
"grad_norm": 0.2916833710946818,
"learning_rate": 6.953470369291349e-07,
"loss": 0.2225,
"step": 200
},
{
"epoch": 6.151898734177215,
"grad_norm": 0.2877930871488456,
"learning_rate": 6.392213479945852e-07,
"loss": 0.2296,
"step": 201
},
{
"epoch": 6.182278481012658,
"grad_norm": 0.28872553378838456,
"learning_rate": 5.853823673448877e-07,
"loss": 0.2133,
"step": 202
},
{
"epoch": 6.2126582278481015,
"grad_norm": 0.2954608978578038,
"learning_rate": 5.33843247095659e-07,
"loss": 0.2275,
"step": 203
},
{
"epoch": 6.243037974683545,
"grad_norm": 0.30402408500591077,
"learning_rate": 4.846165775385459e-07,
"loss": 0.2442,
"step": 204
},
{
"epoch": 6.273417721518987,
"grad_norm": 0.30076848845189774,
"learning_rate": 4.3771438406559173e-07,
"loss": 0.2196,
"step": 205
},
{
"epoch": 6.30379746835443,
"grad_norm": 0.3416948675216863,
"learning_rate": 3.931481242315993e-07,
"loss": 0.227,
"step": 206
},
{
"epoch": 6.334177215189873,
"grad_norm": 0.30696108823223234,
"learning_rate": 3.5092868495520294e-07,
"loss": 0.2125,
"step": 207
},
{
"epoch": 6.364556962025317,
"grad_norm": 0.336665786751688,
"learning_rate": 3.110663798593616e-07,
"loss": 0.244,
"step": 208
},
{
"epoch": 6.39493670886076,
"grad_norm": 0.2882724454027941,
"learning_rate": 2.735709467518699e-07,
"loss": 0.2124,
"step": 209
},
{
"epoch": 6.425316455696202,
"grad_norm": 0.29760382515379885,
"learning_rate": 2.384515452465475e-07,
"loss": 0.2194,
"step": 210
},
{
"epoch": 6.455696202531645,
"grad_norm": 0.295342001002325,
"learning_rate": 2.0571675452567997e-07,
"loss": 0.2325,
"step": 211
},
{
"epoch": 6.4860759493670885,
"grad_norm": 0.2835777661113264,
"learning_rate": 1.7537457124423896e-07,
"loss": 0.2102,
"step": 212
},
{
"epoch": 6.516455696202532,
"grad_norm": 0.27479736988784964,
"learning_rate": 1.474324075764111e-07,
"loss": 0.2152,
"step": 213
},
{
"epoch": 6.546835443037975,
"grad_norm": 0.27910917975904814,
"learning_rate": 1.2189708940490653e-07,
"loss": 0.2158,
"step": 214
},
{
"epoch": 6.577215189873417,
"grad_norm": 0.2828526623147071,
"learning_rate": 9.877485465349057e-08,
"loss": 0.2276,
"step": 215
},
{
"epoch": 6.6075949367088604,
"grad_norm": 0.28225492331747004,
"learning_rate": 7.807135176314707e-08,
"loss": 0.2327,
"step": 216
},
{
"epoch": 6.637974683544304,
"grad_norm": 0.28194784767364817,
"learning_rate": 5.979163831223988e-08,
"loss": 0.23,
"step": 217
},
{
"epoch": 6.668354430379747,
"grad_norm": 0.28029183381258665,
"learning_rate": 4.394017978101905e-08,
"loss": 0.2219,
"step": 218
},
{
"epoch": 6.69873417721519,
"grad_norm": 0.28779964462670415,
"learning_rate": 3.0520848460765525e-08,
"loss": 0.2191,
"step": 219
},
{
"epoch": 6.729113924050633,
"grad_norm": 0.2873186242341778,
"learning_rate": 1.9536922507841227e-08,
"loss": 0.2228,
"step": 220
},
{
"epoch": 6.759493670886076,
"grad_norm": 0.29578442444567216,
"learning_rate": 1.099108514288627e-08,
"loss": 0.2269,
"step": 221
},
{
"epoch": 6.789873417721519,
"grad_norm": 0.27426473251329325,
"learning_rate": 4.885423995341088e-09,
"loss": 0.2095,
"step": 222
},
{
"epoch": 6.820253164556962,
"grad_norm": 0.27895748053180836,
"learning_rate": 1.2214305934699078e-09,
"loss": 0.2283,
"step": 223
},
{
"epoch": 6.850632911392405,
"grad_norm": 0.2729179279839403,
"learning_rate": 0.0,
"loss": 0.222,
"step": 224
},
{
"epoch": 6.850632911392405,
"step": 224,
"total_flos": 5.277578878380933e+17,
"train_loss": 0.39017832059679286,
"train_runtime": 21047.8381,
"train_samples_per_second": 1.051,
"train_steps_per_second": 0.011
}
],
"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": 5.277578878380933e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}