ryanmarten's picture
End of training
d200647 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": 7.821046188822606,
"learning_rate": 8.695652173913044e-07,
"loss": 1.1558,
"step": 1
},
{
"epoch": 0.060759493670886074,
"grad_norm": 7.921825084451515,
"learning_rate": 1.7391304347826088e-06,
"loss": 1.2051,
"step": 2
},
{
"epoch": 0.09113924050632911,
"grad_norm": 7.949194540802856,
"learning_rate": 2.6086956521739132e-06,
"loss": 1.2081,
"step": 3
},
{
"epoch": 0.12151898734177215,
"grad_norm": 7.419381898775899,
"learning_rate": 3.4782608695652175e-06,
"loss": 1.1778,
"step": 4
},
{
"epoch": 0.1518987341772152,
"grad_norm": 5.8147744470812315,
"learning_rate": 4.347826086956522e-06,
"loss": 1.133,
"step": 5
},
{
"epoch": 0.18227848101265823,
"grad_norm": 3.1488141527120717,
"learning_rate": 5.2173913043478265e-06,
"loss": 1.0355,
"step": 6
},
{
"epoch": 0.21265822784810126,
"grad_norm": 2.6133812217685786,
"learning_rate": 6.086956521739132e-06,
"loss": 0.9942,
"step": 7
},
{
"epoch": 0.2430379746835443,
"grad_norm": 4.53053450724563,
"learning_rate": 6.956521739130435e-06,
"loss": 0.9946,
"step": 8
},
{
"epoch": 0.27341772151898736,
"grad_norm": 4.780306428776297,
"learning_rate": 7.82608695652174e-06,
"loss": 1.0056,
"step": 9
},
{
"epoch": 0.3037974683544304,
"grad_norm": 4.288850924374228,
"learning_rate": 8.695652173913044e-06,
"loss": 0.9472,
"step": 10
},
{
"epoch": 0.3341772151898734,
"grad_norm": 4.439969935534219,
"learning_rate": 9.565217391304349e-06,
"loss": 0.9123,
"step": 11
},
{
"epoch": 0.36455696202531646,
"grad_norm": 4.010491564592064,
"learning_rate": 1.0434782608695653e-05,
"loss": 0.8883,
"step": 12
},
{
"epoch": 0.3949367088607595,
"grad_norm": 3.3294777717525594,
"learning_rate": 1.1304347826086957e-05,
"loss": 0.8939,
"step": 13
},
{
"epoch": 0.4253164556962025,
"grad_norm": 2.7664993482699534,
"learning_rate": 1.2173913043478263e-05,
"loss": 0.875,
"step": 14
},
{
"epoch": 0.45569620253164556,
"grad_norm": 2.8260967544313385,
"learning_rate": 1.3043478260869566e-05,
"loss": 0.827,
"step": 15
},
{
"epoch": 0.4860759493670886,
"grad_norm": 2.622718788057903,
"learning_rate": 1.391304347826087e-05,
"loss": 0.8501,
"step": 16
},
{
"epoch": 0.5164556962025316,
"grad_norm": 2.4404720537483193,
"learning_rate": 1.4782608695652174e-05,
"loss": 0.8602,
"step": 17
},
{
"epoch": 0.5468354430379747,
"grad_norm": 2.378257567990093,
"learning_rate": 1.565217391304348e-05,
"loss": 0.8492,
"step": 18
},
{
"epoch": 0.5772151898734177,
"grad_norm": 2.136063926093358,
"learning_rate": 1.6521739130434785e-05,
"loss": 0.8254,
"step": 19
},
{
"epoch": 0.6075949367088608,
"grad_norm": 1.7328481110273704,
"learning_rate": 1.739130434782609e-05,
"loss": 0.862,
"step": 20
},
{
"epoch": 0.6379746835443038,
"grad_norm": 1.8273457611644959,
"learning_rate": 1.8260869565217393e-05,
"loss": 0.8062,
"step": 21
},
{
"epoch": 0.6683544303797468,
"grad_norm": 1.502333605934096,
"learning_rate": 1.9130434782608697e-05,
"loss": 0.8299,
"step": 22
},
{
"epoch": 0.6987341772151898,
"grad_norm": 1.2900310524495506,
"learning_rate": 2e-05,
"loss": 0.807,
"step": 23
},
{
"epoch": 0.7291139240506329,
"grad_norm": 1.1456325043371915,
"learning_rate": 1.999877856940653e-05,
"loss": 0.7821,
"step": 24
},
{
"epoch": 0.759493670886076,
"grad_norm": 1.2018149758777508,
"learning_rate": 1.999511457600466e-05,
"loss": 0.8497,
"step": 25
},
{
"epoch": 0.789873417721519,
"grad_norm": 0.9889852771780683,
"learning_rate": 1.9989008914857115e-05,
"loss": 0.8075,
"step": 26
},
{
"epoch": 0.8202531645569621,
"grad_norm": 1.1076240476548542,
"learning_rate": 1.998046307749216e-05,
"loss": 0.7513,
"step": 27
},
{
"epoch": 0.850632911392405,
"grad_norm": 0.8803163368784866,
"learning_rate": 1.9969479151539238e-05,
"loss": 0.7859,
"step": 28
},
{
"epoch": 0.8810126582278481,
"grad_norm": 1.0491156615385184,
"learning_rate": 1.9956059820218982e-05,
"loss": 0.7526,
"step": 29
},
{
"epoch": 0.9113924050632911,
"grad_norm": 1.10152854864363,
"learning_rate": 1.9940208361687762e-05,
"loss": 0.7491,
"step": 30
},
{
"epoch": 0.9417721518987342,
"grad_norm": 1.0228949281794228,
"learning_rate": 1.9921928648236855e-05,
"loss": 0.7853,
"step": 31
},
{
"epoch": 0.9721518987341772,
"grad_norm": 1.0034300575346555,
"learning_rate": 1.990122514534651e-05,
"loss": 0.8105,
"step": 32
},
{
"epoch": 1.010126582278481,
"grad_norm": 1.1172162915635493,
"learning_rate": 1.9878102910595097e-05,
"loss": 0.7464,
"step": 33
},
{
"epoch": 1.040506329113924,
"grad_norm": 0.9591624728466743,
"learning_rate": 1.985256759242359e-05,
"loss": 0.6626,
"step": 34
},
{
"epoch": 1.070886075949367,
"grad_norm": 1.0340759260382315,
"learning_rate": 1.982462542875576e-05,
"loss": 0.6708,
"step": 35
},
{
"epoch": 1.1012658227848102,
"grad_norm": 0.9433503158572933,
"learning_rate": 1.979428324547432e-05,
"loss": 0.6447,
"step": 36
},
{
"epoch": 1.1316455696202532,
"grad_norm": 0.9218281307494127,
"learning_rate": 1.9761548454753455e-05,
"loss": 0.6418,
"step": 37
},
{
"epoch": 1.1620253164556962,
"grad_norm": 0.9198714860449547,
"learning_rate": 1.972642905324813e-05,
"loss": 0.6677,
"step": 38
},
{
"epoch": 1.1924050632911392,
"grad_norm": 0.9387185070917101,
"learning_rate": 1.9688933620140638e-05,
"loss": 0.6054,
"step": 39
},
{
"epoch": 1.2227848101265824,
"grad_norm": 0.8728726429722485,
"learning_rate": 1.96490713150448e-05,
"loss": 0.6298,
"step": 40
},
{
"epoch": 1.2531645569620253,
"grad_norm": 0.8752898789891731,
"learning_rate": 1.9606851875768404e-05,
"loss": 0.6111,
"step": 41
},
{
"epoch": 1.2835443037974683,
"grad_norm": 0.893778572005734,
"learning_rate": 1.956228561593441e-05,
"loss": 0.6404,
"step": 42
},
{
"epoch": 1.3139240506329113,
"grad_norm": 0.8160072296242408,
"learning_rate": 1.9515383422461457e-05,
"loss": 0.6291,
"step": 43
},
{
"epoch": 1.3443037974683545,
"grad_norm": 0.8392921428856774,
"learning_rate": 1.9466156752904344e-05,
"loss": 0.6716,
"step": 44
},
{
"epoch": 1.3746835443037975,
"grad_norm": 0.8409571411034287,
"learning_rate": 1.9414617632655114e-05,
"loss": 0.6197,
"step": 45
},
{
"epoch": 1.4050632911392404,
"grad_norm": 0.7944502463591191,
"learning_rate": 1.9360778652005416e-05,
"loss": 0.6277,
"step": 46
},
{
"epoch": 1.4354430379746836,
"grad_norm": 0.7646898863461067,
"learning_rate": 1.9304652963070868e-05,
"loss": 0.6033,
"step": 47
},
{
"epoch": 1.4658227848101266,
"grad_norm": 0.8293604918278636,
"learning_rate": 1.9246254276578175e-05,
"loss": 0.5995,
"step": 48
},
{
"epoch": 1.4962025316455696,
"grad_norm": 0.8011654631247795,
"learning_rate": 1.9185596858515797e-05,
"loss": 0.6169,
"step": 49
},
{
"epoch": 1.5265822784810128,
"grad_norm": 0.7824727918529569,
"learning_rate": 1.9122695526648968e-05,
"loss": 0.6084,
"step": 50
},
{
"epoch": 1.5569620253164556,
"grad_norm": 0.8480236748326004,
"learning_rate": 1.905756564689991e-05,
"loss": 0.6129,
"step": 51
},
{
"epoch": 1.5873417721518988,
"grad_norm": 0.7639111105033703,
"learning_rate": 1.8990223129594146e-05,
"loss": 0.6053,
"step": 52
},
{
"epoch": 1.6177215189873417,
"grad_norm": 0.9093137184868099,
"learning_rate": 1.8920684425573865e-05,
"loss": 0.6422,
"step": 53
},
{
"epoch": 1.6481012658227847,
"grad_norm": 0.6994028366767042,
"learning_rate": 1.884896652217917e-05,
"loss": 0.5946,
"step": 54
},
{
"epoch": 1.678481012658228,
"grad_norm": 0.8968558583216436,
"learning_rate": 1.877508693909831e-05,
"loss": 0.6207,
"step": 55
},
{
"epoch": 1.7088607594936709,
"grad_norm": 0.811839332119214,
"learning_rate": 1.8699063724087905e-05,
"loss": 0.618,
"step": 56
},
{
"epoch": 1.7392405063291139,
"grad_norm": 0.9002757348285215,
"learning_rate": 1.862091544856407e-05,
"loss": 0.6112,
"step": 57
},
{
"epoch": 1.769620253164557,
"grad_norm": 0.7990305355304187,
"learning_rate": 1.854066120306571e-05,
"loss": 0.6192,
"step": 58
},
{
"epoch": 1.8,
"grad_norm": 0.861399999161712,
"learning_rate": 1.8458320592590976e-05,
"loss": 0.5898,
"step": 59
},
{
"epoch": 1.830379746835443,
"grad_norm": 0.8278930782445296,
"learning_rate": 1.837391373180801e-05,
"loss": 0.6108,
"step": 60
},
{
"epoch": 1.8607594936708862,
"grad_norm": 0.7921513805855641,
"learning_rate": 1.8287461240141217e-05,
"loss": 0.5995,
"step": 61
},
{
"epoch": 1.891139240506329,
"grad_norm": 0.8900711452206441,
"learning_rate": 1.8198984236734246e-05,
"loss": 0.623,
"step": 62
},
{
"epoch": 1.9215189873417722,
"grad_norm": 0.8985909391413275,
"learning_rate": 1.8108504335290852e-05,
"loss": 0.6299,
"step": 63
},
{
"epoch": 1.9518987341772152,
"grad_norm": 0.7194793851130045,
"learning_rate": 1.8016043638794975e-05,
"loss": 0.5897,
"step": 64
},
{
"epoch": 1.9822784810126581,
"grad_norm": 0.8531941724481863,
"learning_rate": 1.7921624734111292e-05,
"loss": 0.6191,
"step": 65
},
{
"epoch": 2.020253164556962,
"grad_norm": 0.8209935083153904,
"learning_rate": 1.7825270686467567e-05,
"loss": 0.4933,
"step": 66
},
{
"epoch": 2.050632911392405,
"grad_norm": 0.7996082296164394,
"learning_rate": 1.7727005033820117e-05,
"loss": 0.44,
"step": 67
},
{
"epoch": 2.081012658227848,
"grad_norm": 1.2840953839544158,
"learning_rate": 1.762685178110382e-05,
"loss": 0.4285,
"step": 68
},
{
"epoch": 2.1113924050632913,
"grad_norm": 0.942479353452438,
"learning_rate": 1.752483539436807e-05,
"loss": 0.4374,
"step": 69
},
{
"epoch": 2.141772151898734,
"grad_norm": 1.2232114430158003,
"learning_rate": 1.7420980794800013e-05,
"loss": 0.4087,
"step": 70
},
{
"epoch": 2.1721518987341772,
"grad_norm": 1.0356734414329936,
"learning_rate": 1.731531335263669e-05,
"loss": 0.3946,
"step": 71
},
{
"epoch": 2.2025316455696204,
"grad_norm": 0.7867140091801025,
"learning_rate": 1.720785888096743e-05,
"loss": 0.4163,
"step": 72
},
{
"epoch": 2.232911392405063,
"grad_norm": 0.9132158139934681,
"learning_rate": 1.7098643629428035e-05,
"loss": 0.3946,
"step": 73
},
{
"epoch": 2.2632911392405064,
"grad_norm": 0.7763347772570146,
"learning_rate": 1.698769427778842e-05,
"loss": 0.3886,
"step": 74
},
{
"epoch": 2.293670886075949,
"grad_norm": 0.8389557995027598,
"learning_rate": 1.687503792943506e-05,
"loss": 0.4095,
"step": 75
},
{
"epoch": 2.3240506329113924,
"grad_norm": 0.7011995417689459,
"learning_rate": 1.6760702104750046e-05,
"loss": 0.4333,
"step": 76
},
{
"epoch": 2.3544303797468356,
"grad_norm": 0.8420627329845638,
"learning_rate": 1.664471473438822e-05,
"loss": 0.4036,
"step": 77
},
{
"epoch": 2.3848101265822783,
"grad_norm": 0.7237704302653927,
"learning_rate": 1.6527104152454096e-05,
"loss": 0.4052,
"step": 78
},
{
"epoch": 2.4151898734177215,
"grad_norm": 0.8791910546924722,
"learning_rate": 1.6407899089580263e-05,
"loss": 0.4346,
"step": 79
},
{
"epoch": 2.4455696202531647,
"grad_norm": 0.7919528470256998,
"learning_rate": 1.628712866590885e-05,
"loss": 0.4288,
"step": 80
},
{
"epoch": 2.4759493670886075,
"grad_norm": 0.6758854624059195,
"learning_rate": 1.6164822383977912e-05,
"loss": 0.3944,
"step": 81
},
{
"epoch": 2.5063291139240507,
"grad_norm": 0.8553142061277994,
"learning_rate": 1.604101012151436e-05,
"loss": 0.4129,
"step": 82
},
{
"epoch": 2.536708860759494,
"grad_norm": 0.6894610348766053,
"learning_rate": 1.5915722124135227e-05,
"loss": 0.4011,
"step": 83
},
{
"epoch": 2.5670886075949366,
"grad_norm": 0.7970929002092169,
"learning_rate": 1.5788988997959115e-05,
"loss": 0.4008,
"step": 84
},
{
"epoch": 2.59746835443038,
"grad_norm": 0.7134359418705393,
"learning_rate": 1.5660841702129533e-05,
"loss": 0.3664,
"step": 85
},
{
"epoch": 2.6278481012658226,
"grad_norm": 0.7087911471321273,
"learning_rate": 1.5531311541251995e-05,
"loss": 0.3791,
"step": 86
},
{
"epoch": 2.6582278481012658,
"grad_norm": 0.6891445046493652,
"learning_rate": 1.540043015774676e-05,
"loss": 0.3847,
"step": 87
},
{
"epoch": 2.688607594936709,
"grad_norm": 0.7637547952556076,
"learning_rate": 1.5268229524119007e-05,
"loss": 0.4041,
"step": 88
},
{
"epoch": 2.7189873417721517,
"grad_norm": 0.7769177668227595,
"learning_rate": 1.513474193514842e-05,
"loss": 0.3991,
"step": 89
},
{
"epoch": 2.749367088607595,
"grad_norm": 0.7926731473312283,
"learning_rate": 1.5000000000000002e-05,
"loss": 0.3976,
"step": 90
},
{
"epoch": 2.779746835443038,
"grad_norm": 0.6806718036324106,
"learning_rate": 1.4864036634258112e-05,
"loss": 0.3899,
"step": 91
},
{
"epoch": 2.810126582278481,
"grad_norm": 0.7649089907549299,
"learning_rate": 1.4726885051885654e-05,
"loss": 0.3827,
"step": 92
},
{
"epoch": 2.840506329113924,
"grad_norm": 0.7511392853903036,
"learning_rate": 1.4588578757110359e-05,
"loss": 0.3684,
"step": 93
},
{
"epoch": 2.8708860759493673,
"grad_norm": 0.6748860783991397,
"learning_rate": 1.4449151536240167e-05,
"loss": 0.3809,
"step": 94
},
{
"epoch": 2.90126582278481,
"grad_norm": 0.6864747657021409,
"learning_rate": 1.4308637449409705e-05,
"loss": 0.3956,
"step": 95
},
{
"epoch": 2.9316455696202532,
"grad_norm": 0.7753228864719607,
"learning_rate": 1.4167070822259868e-05,
"loss": 0.4254,
"step": 96
},
{
"epoch": 2.962025316455696,
"grad_norm": 0.6651509289577628,
"learning_rate": 1.402448623755254e-05,
"loss": 0.3921,
"step": 97
},
{
"epoch": 2.992405063291139,
"grad_norm": 0.6983791734860466,
"learning_rate": 1.3880918526722497e-05,
"loss": 0.4287,
"step": 98
},
{
"epoch": 3.030379746835443,
"grad_norm": 0.9220251556978855,
"learning_rate": 1.3736402761368597e-05,
"loss": 0.2964,
"step": 99
},
{
"epoch": 3.060759493670886,
"grad_norm": 0.6610795758669731,
"learning_rate": 1.3590974244686248e-05,
"loss": 0.2612,
"step": 100
},
{
"epoch": 3.091139240506329,
"grad_norm": 0.9270782747999269,
"learning_rate": 1.344466850284333e-05,
"loss": 0.2746,
"step": 101
},
{
"epoch": 3.1215189873417724,
"grad_norm": 1.098737259675843,
"learning_rate": 1.3297521276301666e-05,
"loss": 0.2855,
"step": 102
},
{
"epoch": 3.151898734177215,
"grad_norm": 0.648219534073433,
"learning_rate": 1.3149568511086104e-05,
"loss": 0.2586,
"step": 103
},
{
"epoch": 3.1822784810126583,
"grad_norm": 0.7931412589215237,
"learning_rate": 1.300084635000341e-05,
"loss": 0.2858,
"step": 104
},
{
"epoch": 3.212658227848101,
"grad_norm": 0.7611529900120818,
"learning_rate": 1.2851391123813075e-05,
"loss": 0.263,
"step": 105
},
{
"epoch": 3.2430379746835443,
"grad_norm": 0.6482399304581031,
"learning_rate": 1.2701239342352223e-05,
"loss": 0.299,
"step": 106
},
{
"epoch": 3.2734177215189875,
"grad_norm": 0.5954166072264363,
"learning_rate": 1.2550427685616767e-05,
"loss": 0.2868,
"step": 107
},
{
"epoch": 3.3037974683544302,
"grad_norm": 0.6767360371462975,
"learning_rate": 1.239899299480098e-05,
"loss": 0.2564,
"step": 108
},
{
"epoch": 3.3341772151898734,
"grad_norm": 0.6094191230978437,
"learning_rate": 1.2246972263297718e-05,
"loss": 0.2528,
"step": 109
},
{
"epoch": 3.3645569620253166,
"grad_norm": 0.7145739315760229,
"learning_rate": 1.2094402627661447e-05,
"loss": 0.2853,
"step": 110
},
{
"epoch": 3.3949367088607594,
"grad_norm": 0.6231765035888277,
"learning_rate": 1.1941321358536278e-05,
"loss": 0.2429,
"step": 111
},
{
"epoch": 3.4253164556962026,
"grad_norm": 0.6449885249273971,
"learning_rate": 1.1787765851551296e-05,
"loss": 0.2711,
"step": 112
},
{
"epoch": 3.4556962025316453,
"grad_norm": 0.586672980747406,
"learning_rate": 1.1633773618185302e-05,
"loss": 0.2685,
"step": 113
},
{
"epoch": 3.4860759493670885,
"grad_norm": 0.6467921689659367,
"learning_rate": 1.14793822766033e-05,
"loss": 0.2818,
"step": 114
},
{
"epoch": 3.5164556962025317,
"grad_norm": 0.6381786906313327,
"learning_rate": 1.132462954246688e-05,
"loss": 0.2711,
"step": 115
},
{
"epoch": 3.546835443037975,
"grad_norm": 0.6314811402603955,
"learning_rate": 1.1169553219720828e-05,
"loss": 0.2773,
"step": 116
},
{
"epoch": 3.5772151898734177,
"grad_norm": 0.6097770409637793,
"learning_rate": 1.1014191191358118e-05,
"loss": 0.2512,
"step": 117
},
{
"epoch": 3.607594936708861,
"grad_norm": 0.6449724975686235,
"learning_rate": 1.085858141016566e-05,
"loss": 0.2551,
"step": 118
},
{
"epoch": 3.6379746835443036,
"grad_norm": 0.5877968560776582,
"learning_rate": 1.070276188945293e-05,
"loss": 0.258,
"step": 119
},
{
"epoch": 3.668354430379747,
"grad_norm": 0.5780608872071732,
"learning_rate": 1.0546770693765859e-05,
"loss": 0.2479,
"step": 120
},
{
"epoch": 3.69873417721519,
"grad_norm": 0.605807815077805,
"learning_rate": 1.0390645929588197e-05,
"loss": 0.2396,
"step": 121
},
{
"epoch": 3.729113924050633,
"grad_norm": 0.6245049664156804,
"learning_rate": 1.0234425736032607e-05,
"loss": 0.251,
"step": 122
},
{
"epoch": 3.759493670886076,
"grad_norm": 0.5569457656088611,
"learning_rate": 1.007814827552384e-05,
"loss": 0.2819,
"step": 123
},
{
"epoch": 3.7898734177215188,
"grad_norm": 0.5624015217598239,
"learning_rate": 9.92185172447616e-06,
"loss": 0.2689,
"step": 124
},
{
"epoch": 3.820253164556962,
"grad_norm": 0.5812377663228203,
"learning_rate": 9.765574263967397e-06,
"loss": 0.2813,
"step": 125
},
{
"epoch": 3.850632911392405,
"grad_norm": 0.5599182490663513,
"learning_rate": 9.609354070411807e-06,
"loss": 0.257,
"step": 126
},
{
"epoch": 3.8810126582278484,
"grad_norm": 0.6016379361147123,
"learning_rate": 9.453229306234143e-06,
"loss": 0.2843,
"step": 127
},
{
"epoch": 3.911392405063291,
"grad_norm": 0.5684696439235135,
"learning_rate": 9.297238110547075e-06,
"loss": 0.2456,
"step": 128
},
{
"epoch": 3.9417721518987343,
"grad_norm": 0.6221379537641375,
"learning_rate": 9.14141858983434e-06,
"loss": 0.281,
"step": 129
},
{
"epoch": 3.972151898734177,
"grad_norm": 0.5382276086945389,
"learning_rate": 8.985808808641883e-06,
"loss": 0.239,
"step": 130
},
{
"epoch": 4.010126582278481,
"grad_norm": 0.559689443479499,
"learning_rate": 8.830446780279175e-06,
"loss": 0.2443,
"step": 131
},
{
"epoch": 4.040506329113924,
"grad_norm": 0.6771012317985544,
"learning_rate": 8.675370457533122e-06,
"loss": 0.1531,
"step": 132
},
{
"epoch": 4.0708860759493675,
"grad_norm": 0.4818948876907526,
"learning_rate": 8.520617723396702e-06,
"loss": 0.1804,
"step": 133
},
{
"epoch": 4.10126582278481,
"grad_norm": 0.46716252875726966,
"learning_rate": 8.366226381814698e-06,
"loss": 0.1701,
"step": 134
},
{
"epoch": 4.131645569620253,
"grad_norm": 0.7589325984739113,
"learning_rate": 8.212234148448708e-06,
"loss": 0.2187,
"step": 135
},
{
"epoch": 4.162025316455696,
"grad_norm": 0.6267149137544038,
"learning_rate": 8.058678641463724e-06,
"loss": 0.1734,
"step": 136
},
{
"epoch": 4.192405063291139,
"grad_norm": 0.5366476862319358,
"learning_rate": 7.905597372338558e-06,
"loss": 0.1631,
"step": 137
},
{
"epoch": 4.222784810126583,
"grad_norm": 0.5026922154496697,
"learning_rate": 7.753027736702283e-06,
"loss": 0.1769,
"step": 138
},
{
"epoch": 4.253164556962025,
"grad_norm": 0.4838485106407902,
"learning_rate": 7.601007005199022e-06,
"loss": 0.1776,
"step": 139
},
{
"epoch": 4.283544303797468,
"grad_norm": 0.5389049533638387,
"learning_rate": 7.449572314383237e-06,
"loss": 0.1863,
"step": 140
},
{
"epoch": 4.313924050632911,
"grad_norm": 0.4980671758980592,
"learning_rate": 7.298760657647779e-06,
"loss": 0.1876,
"step": 141
},
{
"epoch": 4.3443037974683545,
"grad_norm": 0.4831633711677618,
"learning_rate": 7.148608876186931e-06,
"loss": 0.1855,
"step": 142
},
{
"epoch": 4.374683544303798,
"grad_norm": 0.4641726517540608,
"learning_rate": 6.999153649996595e-06,
"loss": 0.1737,
"step": 143
},
{
"epoch": 4.405063291139241,
"grad_norm": 0.5158696225253259,
"learning_rate": 6.8504314889138956e-06,
"loss": 0.1648,
"step": 144
},
{
"epoch": 4.435443037974683,
"grad_norm": 0.48928414438839596,
"learning_rate": 6.702478723698336e-06,
"loss": 0.1854,
"step": 145
},
{
"epoch": 4.465822784810126,
"grad_norm": 0.4794880251747116,
"learning_rate": 6.555331497156671e-06,
"loss": 0.1733,
"step": 146
},
{
"epoch": 4.49620253164557,
"grad_norm": 0.4905261382023579,
"learning_rate": 6.4090257553137566e-06,
"loss": 0.2232,
"step": 147
},
{
"epoch": 4.526582278481013,
"grad_norm": 0.4844078129632487,
"learning_rate": 6.263597238631405e-06,
"loss": 0.1751,
"step": 148
},
{
"epoch": 4.556962025316456,
"grad_norm": 0.4232714617536975,
"learning_rate": 6.119081473277502e-06,
"loss": 0.1436,
"step": 149
},
{
"epoch": 4.587341772151898,
"grad_norm": 0.4998005504636481,
"learning_rate": 5.975513762447465e-06,
"loss": 0.1788,
"step": 150
},
{
"epoch": 4.6177215189873415,
"grad_norm": 0.46096522684791935,
"learning_rate": 5.832929177740134e-06,
"loss": 0.1723,
"step": 151
},
{
"epoch": 4.648101265822785,
"grad_norm": 0.44310779188262656,
"learning_rate": 5.6913625505902966e-06,
"loss": 0.2135,
"step": 152
},
{
"epoch": 4.678481012658228,
"grad_norm": 0.43432359900287715,
"learning_rate": 5.550848463759835e-06,
"loss": 0.2117,
"step": 153
},
{
"epoch": 4.708860759493671,
"grad_norm": 0.45740523869128913,
"learning_rate": 5.411421242889643e-06,
"loss": 0.1759,
"step": 154
},
{
"epoch": 4.739240506329114,
"grad_norm": 0.43490763870000326,
"learning_rate": 5.273114948114346e-06,
"loss": 0.1997,
"step": 155
},
{
"epoch": 4.769620253164557,
"grad_norm": 0.42643435294558374,
"learning_rate": 5.135963365741892e-06,
"loss": 0.1589,
"step": 156
},
{
"epoch": 4.8,
"grad_norm": 0.4579379938540636,
"learning_rate": 5.000000000000003e-06,
"loss": 0.1688,
"step": 157
},
{
"epoch": 4.830379746835443,
"grad_norm": 0.46926368219814496,
"learning_rate": 4.865258064851579e-06,
"loss": 0.1789,
"step": 158
},
{
"epoch": 4.860759493670886,
"grad_norm": 0.42237044030544385,
"learning_rate": 4.731770475880995e-06,
"loss": 0.1665,
"step": 159
},
{
"epoch": 4.891139240506329,
"grad_norm": 0.4169500416949454,
"learning_rate": 4.599569842253244e-06,
"loss": 0.2036,
"step": 160
},
{
"epoch": 4.921518987341772,
"grad_norm": 0.44081050832610535,
"learning_rate": 4.468688458748006e-06,
"loss": 0.213,
"step": 161
},
{
"epoch": 4.951898734177215,
"grad_norm": 0.4316863039504753,
"learning_rate": 4.339158297870469e-06,
"loss": 0.1749,
"step": 162
},
{
"epoch": 4.982278481012658,
"grad_norm": 0.4324971156906421,
"learning_rate": 4.211011002040885e-06,
"loss": 0.1607,
"step": 163
},
{
"epoch": 5.020253164556962,
"grad_norm": 0.47288082007126075,
"learning_rate": 4.084277875864776e-06,
"loss": 0.1362,
"step": 164
},
{
"epoch": 5.050632911392405,
"grad_norm": 0.5108205750113229,
"learning_rate": 3.958989878485644e-06,
"loss": 0.1461,
"step": 165
},
{
"epoch": 5.0810126582278485,
"grad_norm": 0.39521771420241175,
"learning_rate": 3.83517761602209e-06,
"loss": 0.192,
"step": 166
},
{
"epoch": 5.111392405063291,
"grad_norm": 0.3238187214130239,
"learning_rate": 3.712871334091154e-06,
"loss": 0.1236,
"step": 167
},
{
"epoch": 5.141772151898734,
"grad_norm": 0.3549472032181739,
"learning_rate": 3.592100910419738e-06,
"loss": 0.1787,
"step": 168
},
{
"epoch": 5.172151898734177,
"grad_norm": 0.3414716515241834,
"learning_rate": 3.4728958475459052e-06,
"loss": 0.1366,
"step": 169
},
{
"epoch": 5.2025316455696204,
"grad_norm": 0.4134782796791461,
"learning_rate": 3.355285265611784e-06,
"loss": 0.1401,
"step": 170
},
{
"epoch": 5.232911392405064,
"grad_norm": 0.42514728956855424,
"learning_rate": 3.2392978952499553e-06,
"loss": 0.1247,
"step": 171
},
{
"epoch": 5.263291139240506,
"grad_norm": 0.4877649516931133,
"learning_rate": 3.1249620705649417e-06,
"loss": 0.1472,
"step": 172
},
{
"epoch": 5.293670886075949,
"grad_norm": 0.37482117862804326,
"learning_rate": 3.0123057222115835e-06,
"loss": 0.1306,
"step": 173
},
{
"epoch": 5.324050632911392,
"grad_norm": 0.3546177403178053,
"learning_rate": 2.9013563705719673e-06,
"loss": 0.1328,
"step": 174
},
{
"epoch": 5.3544303797468356,
"grad_norm": 0.3259361591237675,
"learning_rate": 2.7921411190325753e-06,
"loss": 0.1397,
"step": 175
},
{
"epoch": 5.384810126582279,
"grad_norm": 0.3374114179522559,
"learning_rate": 2.6846866473633126e-06,
"loss": 0.1525,
"step": 176
},
{
"epoch": 5.415189873417722,
"grad_norm": 0.3549149472069972,
"learning_rate": 2.579019205199992e-06,
"loss": 0.1358,
"step": 177
},
{
"epoch": 5.445569620253164,
"grad_norm": 0.3307718981628869,
"learning_rate": 2.4751646056319334e-06,
"loss": 0.1314,
"step": 178
},
{
"epoch": 5.4759493670886075,
"grad_norm": 0.32669053163129463,
"learning_rate": 2.373148218896182e-06,
"loss": 0.1168,
"step": 179
},
{
"epoch": 5.506329113924051,
"grad_norm": 0.3259651847932475,
"learning_rate": 2.2729949661798876e-06,
"loss": 0.1415,
"step": 180
},
{
"epoch": 5.536708860759494,
"grad_norm": 0.325038079393212,
"learning_rate": 2.174729313532433e-06,
"loss": 0.1256,
"step": 181
},
{
"epoch": 5.567088607594937,
"grad_norm": 0.3141018286982485,
"learning_rate": 2.078375265888707e-06,
"loss": 0.1301,
"step": 182
},
{
"epoch": 5.597468354430379,
"grad_norm": 0.3176620545390375,
"learning_rate": 1.9839563612050273e-06,
"loss": 0.1153,
"step": 183
},
{
"epoch": 5.627848101265823,
"grad_norm": 0.3301647459616926,
"learning_rate": 1.8914956647091497e-06,
"loss": 0.1537,
"step": 184
},
{
"epoch": 5.658227848101266,
"grad_norm": 0.3397085044879637,
"learning_rate": 1.8010157632657544e-06,
"loss": 0.1341,
"step": 185
},
{
"epoch": 5.688607594936709,
"grad_norm": 0.3388905356198473,
"learning_rate": 1.7125387598587862e-06,
"loss": 0.1557,
"step": 186
},
{
"epoch": 5.718987341772152,
"grad_norm": 0.3360444342069633,
"learning_rate": 1.6260862681919965e-06,
"loss": 0.119,
"step": 187
},
{
"epoch": 5.749367088607595,
"grad_norm": 0.3548570154065725,
"learning_rate": 1.5416794074090258e-06,
"loss": 0.1572,
"step": 188
},
{
"epoch": 5.779746835443038,
"grad_norm": 0.35386114026628934,
"learning_rate": 1.459338796934293e-06,
"loss": 0.1387,
"step": 189
},
{
"epoch": 5.810126582278481,
"grad_norm": 0.34933293542753524,
"learning_rate": 1.3790845514359363e-06,
"loss": 0.1463,
"step": 190
},
{
"epoch": 5.840506329113924,
"grad_norm": 0.33080764916648525,
"learning_rate": 1.300936275912098e-06,
"loss": 0.1313,
"step": 191
},
{
"epoch": 5.870886075949367,
"grad_norm": 0.32479303869035625,
"learning_rate": 1.224913060901688e-06,
"loss": 0.123,
"step": 192
},
{
"epoch": 5.9012658227848105,
"grad_norm": 0.3504712677214653,
"learning_rate": 1.1510334778208332e-06,
"loss": 0.1245,
"step": 193
},
{
"epoch": 5.931645569620253,
"grad_norm": 0.3185986850437643,
"learning_rate": 1.0793155744261352e-06,
"loss": 0.1238,
"step": 194
},
{
"epoch": 5.962025316455696,
"grad_norm": 0.3265603887208977,
"learning_rate": 1.0097768704058542e-06,
"loss": 0.1623,
"step": 195
},
{
"epoch": 5.992405063291139,
"grad_norm": 0.33545098544813473,
"learning_rate": 9.424343531000968e-07,
"loss": 0.1353,
"step": 196
},
{
"epoch": 6.030379746835443,
"grad_norm": 0.31145041522431705,
"learning_rate": 8.773044733510338e-07,
"loss": 0.1185,
"step": 197
},
{
"epoch": 6.060759493670886,
"grad_norm": 0.32178985162717133,
"learning_rate": 8.144031414842012e-07,
"loss": 0.1562,
"step": 198
},
{
"epoch": 6.091139240506329,
"grad_norm": 0.3109905615008904,
"learning_rate": 7.537457234218271e-07,
"loss": 0.1399,
"step": 199
},
{
"epoch": 6.121518987341772,
"grad_norm": 0.29859282658595293,
"learning_rate": 6.953470369291349e-07,
"loss": 0.1209,
"step": 200
},
{
"epoch": 6.151898734177215,
"grad_norm": 0.32612724958390515,
"learning_rate": 6.392213479945852e-07,
"loss": 0.1172,
"step": 201
},
{
"epoch": 6.182278481012658,
"grad_norm": 0.26138279202370573,
"learning_rate": 5.853823673448877e-07,
"loss": 0.1313,
"step": 202
},
{
"epoch": 6.2126582278481015,
"grad_norm": 0.28727956221648643,
"learning_rate": 5.33843247095659e-07,
"loss": 0.1563,
"step": 203
},
{
"epoch": 6.243037974683545,
"grad_norm": 0.2864062480611515,
"learning_rate": 4.846165775385459e-07,
"loss": 0.1395,
"step": 204
},
{
"epoch": 6.273417721518987,
"grad_norm": 0.2815198905586832,
"learning_rate": 4.3771438406559173e-07,
"loss": 0.1196,
"step": 205
},
{
"epoch": 6.30379746835443,
"grad_norm": 0.24928897666772976,
"learning_rate": 3.931481242315993e-07,
"loss": 0.1037,
"step": 206
},
{
"epoch": 6.334177215189873,
"grad_norm": 0.2645356258035024,
"learning_rate": 3.5092868495520294e-07,
"loss": 0.1086,
"step": 207
},
{
"epoch": 6.364556962025317,
"grad_norm": 0.26878790834169397,
"learning_rate": 3.110663798593616e-07,
"loss": 0.1252,
"step": 208
},
{
"epoch": 6.39493670886076,
"grad_norm": 0.24158485069168198,
"learning_rate": 2.735709467518699e-07,
"loss": 0.1064,
"step": 209
},
{
"epoch": 6.425316455696202,
"grad_norm": 0.2894081062776572,
"learning_rate": 2.384515452465475e-07,
"loss": 0.1467,
"step": 210
},
{
"epoch": 6.455696202531645,
"grad_norm": 0.2682251204654294,
"learning_rate": 2.0571675452567997e-07,
"loss": 0.1426,
"step": 211
},
{
"epoch": 6.4860759493670885,
"grad_norm": 0.2757021644220485,
"learning_rate": 1.7537457124423896e-07,
"loss": 0.108,
"step": 212
},
{
"epoch": 6.516455696202532,
"grad_norm": 0.26666054538960254,
"learning_rate": 1.474324075764111e-07,
"loss": 0.1308,
"step": 213
},
{
"epoch": 6.546835443037975,
"grad_norm": 0.27128326398580616,
"learning_rate": 1.2189708940490653e-07,
"loss": 0.1186,
"step": 214
},
{
"epoch": 6.577215189873417,
"grad_norm": 0.2516746818356812,
"learning_rate": 9.877485465349057e-08,
"loss": 0.1421,
"step": 215
},
{
"epoch": 6.6075949367088604,
"grad_norm": 0.2811026990882255,
"learning_rate": 7.807135176314707e-08,
"loss": 0.1157,
"step": 216
},
{
"epoch": 6.637974683544304,
"grad_norm": 0.2781430871205741,
"learning_rate": 5.979163831223988e-08,
"loss": 0.1158,
"step": 217
},
{
"epoch": 6.668354430379747,
"grad_norm": 0.26752367927032317,
"learning_rate": 4.394017978101905e-08,
"loss": 0.1186,
"step": 218
},
{
"epoch": 6.69873417721519,
"grad_norm": 0.25689888335881983,
"learning_rate": 3.0520848460765525e-08,
"loss": 0.1144,
"step": 219
},
{
"epoch": 6.729113924050633,
"grad_norm": 0.29632821016666816,
"learning_rate": 1.9536922507841227e-08,
"loss": 0.1483,
"step": 220
},
{
"epoch": 6.759493670886076,
"grad_norm": 0.26832793754980955,
"learning_rate": 1.099108514288627e-08,
"loss": 0.1267,
"step": 221
},
{
"epoch": 6.789873417721519,
"grad_norm": 0.2705156579423521,
"learning_rate": 4.885423995341088e-09,
"loss": 0.1328,
"step": 222
},
{
"epoch": 6.820253164556962,
"grad_norm": 0.2592374115580099,
"learning_rate": 1.2214305934699078e-09,
"loss": 0.0986,
"step": 223
},
{
"epoch": 6.850632911392405,
"grad_norm": 0.26582605276588783,
"learning_rate": 0.0,
"loss": 0.1222,
"step": 224
},
{
"epoch": 6.850632911392405,
"step": 224,
"total_flos": 2.2606970276859085e+17,
"train_loss": 0.3831337048738663,
"train_runtime": 9209.4419,
"train_samples_per_second": 2.402,
"train_steps_per_second": 0.024
}
],
"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": 2.2606970276859085e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}