{
  "best_metric": 0.07224522531032562,
  "best_model_checkpoint": "saves/psy-course-info-chain/Llama3-OpenBioLLM-8B/train/fold1/checkpoint-90",
  "epoch": 4.938271604938271,
  "eval_steps": 10,
  "global_step": 125,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03950617283950617,
      "grad_norm": 1.1096316576004028,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.2888,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 1.0507583618164062,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.3894,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 1.1098066568374634,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.2867,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 1.1359410285949707,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.2826,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 1.21199631690979,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.347,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 1.130179762840271,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.3044,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 1.1210029125213623,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.3058,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 1.4364897012710571,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.3171,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 1.210524559020996,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.1984,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 0.8581638932228088,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.1976,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.1778651922941208,
      "eval_runtime": 22.6197,
      "eval_samples_per_second": 1.989,
      "eval_steps_per_second": 1.989,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 0.9453576803207397,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.1234,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 1.0153533220291138,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.2474,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 1.057861566543579,
      "learning_rate": 0.0001,
      "loss": 0.2775,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.7954065799713135,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.1487,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.8518949747085571,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.1909,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.7310432195663452,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.2095,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.8436449766159058,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.1778,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.6841358542442322,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.1514,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.547307550907135,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.1264,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.5207089185714722,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.0969,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.1176198199391365,
      "eval_runtime": 22.4775,
      "eval_samples_per_second": 2.002,
      "eval_steps_per_second": 2.002,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.553368330001831,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.1257,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.36866626143455505,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.0874,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.5008062720298767,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.0882,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.5789878964424133,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.1235,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.6592782139778137,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.1427,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 1.2294331789016724,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.2081,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.4095362722873688,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0736,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.7326230406761169,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.1328,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.5066757202148438,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.0937,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.509709358215332,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.102,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.10356403887271881,
      "eval_runtime": 22.5131,
      "eval_samples_per_second": 1.999,
      "eval_steps_per_second": 1.999,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.4245166778564453,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.0669,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.6209756135940552,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.1102,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.7132821083068848,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.138,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.443069726228714,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.0978,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.5783316493034363,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.0877,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.5873170495033264,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.1071,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.5559806227684021,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.0932,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.6741563677787781,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.0943,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.5920282602310181,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.132,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.528616189956665,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.0771,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.08718088269233704,
      "eval_runtime": 22.5544,
      "eval_samples_per_second": 1.995,
      "eval_steps_per_second": 1.995,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.6518641710281372,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0943,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.38192376494407654,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.0587,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.5122020840644836,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.0983,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.45858749747276306,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.0812,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.6836743354797363,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.1191,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.5675541162490845,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.1048,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.4633074104785919,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.0448,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.5370000600814819,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0694,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.6133498549461365,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.143,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.40587764978408813,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.0616,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.08084142208099365,
      "eval_runtime": 22.6161,
      "eval_samples_per_second": 1.99,
      "eval_steps_per_second": 1.99,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 1.258851408958435,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.1505,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.3616649806499481,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.0581,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.45230603218078613,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.0639,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.4213079512119293,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.1126,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.48260489106178284,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0835,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.40098464488983154,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.0472,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.450137734413147,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.0497,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.3459758460521698,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.0438,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.3622719943523407,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.0459,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.32412558794021606,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.0422,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.07746158540248871,
      "eval_runtime": 22.5809,
      "eval_samples_per_second": 1.993,
      "eval_steps_per_second": 1.993,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.5481826066970825,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.0514,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.6609352827072144,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0824,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.4882703721523285,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.0597,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.5577695965766907,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.0646,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.5503864884376526,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.0735,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.6314455270767212,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.0445,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.5152661204338074,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.0459,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.50832599401474,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.0646,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.7016147971153259,
      "learning_rate": 5e-05,
      "loss": 0.0583,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.8187812566757202,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.0659,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.0735732838511467,
      "eval_runtime": 22.4924,
      "eval_samples_per_second": 2.001,
      "eval_steps_per_second": 2.001,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.7435764074325562,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.0795,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.8281508684158325,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.0952,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.7053366303443909,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.1087,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.5093929171562195,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.065,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.4338543713092804,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.0636,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 1.076513648033142,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.1318,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.4114990532398224,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0429,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.592841625213623,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.057,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.6330917477607727,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.0611,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.45612314343452454,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.0278,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.07673414796590805,
      "eval_runtime": 22.5559,
      "eval_samples_per_second": 1.995,
      "eval_steps_per_second": 1.995,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.36881062388420105,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.0403,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.6664642095565796,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.0485,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.34261953830718994,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0427,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.47435155510902405,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.0697,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.6575294733047485,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0419,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.4077962338924408,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.0502,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.469061017036438,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.056,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.611589252948761,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.0506,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.4768570363521576,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.0504,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.2869800627231598,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0361,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.07224522531032562,
      "eval_runtime": 22.5316,
      "eval_samples_per_second": 1.997,
      "eval_steps_per_second": 1.997,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.6124139428138733,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.0834,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.6142622232437134,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.059,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.3966939151287079,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0373,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.4776970446109772,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.0469,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.4221872389316559,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.0289,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.49492019414901733,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.0477,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.4239863157272339,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0458,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.415012001991272,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.0404,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.4527052342891693,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.0466,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.4780322015285492,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.0473,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.0731634795665741,
      "eval_runtime": 22.5898,
      "eval_samples_per_second": 1.992,
      "eval_steps_per_second": 1.992,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.682929277420044,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.0788,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 1.2252761125564575,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.0921,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.4369805157184601,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.0374,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.41052401065826416,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0405,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.3612029254436493,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.0315,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.37653303146362305,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0287,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.332688570022583,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.024,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.41574814915657043,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.042,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.6005021333694458,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0508,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.3289340138435364,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0282,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.07286052405834198,
      "eval_runtime": 22.5742,
      "eval_samples_per_second": 1.993,
      "eval_steps_per_second": 1.993,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.3859937787055969,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0358,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.4927835166454315,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.0441,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.28594833612442017,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.025,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.370209664106369,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.0323,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.41170862317085266,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0267,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.30354800820350647,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.0249,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.511085033416748,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.0468,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.3785458505153656,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0351,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.4578462243080139,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0487,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.5015906691551208,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.0524,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.07267860323190689,
      "eval_runtime": 22.5514,
      "eval_samples_per_second": 1.995,
      "eval_steps_per_second": 1.995,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.3526356816291809,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0194,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.4435887634754181,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0538,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.3656042516231537,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.053,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.39171698689460754,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.0357,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.42321211099624634,
      "learning_rate": 0.0,
      "loss": 0.0486,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.3285867935773491e+17,
      "train_loss": 0.0941709113419056,
      "train_runtime": 3940.5707,
      "train_samples_per_second": 0.514,
      "train_steps_per_second": 0.032
    }
  ],
  "logging_steps": 1,
  "max_steps": 125,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3285867935773491e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}