{
  "best_metric": 0.142436221241951,
  "best_model_checkpoint": "saves/psy-course-info/Llama-3.1-8B-Instruct/train/fold2/checkpoint-120",
  "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": 2.2186996936798096,
      "learning_rate": 7.692307692307694e-06,
      "loss": 1.0034,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 2.274477958679199,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 1.1038,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 2.1551973819732666,
      "learning_rate": 2.307692307692308e-05,
      "loss": 1.1047,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 2.3336920738220215,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 1.0642,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 2.153421401977539,
      "learning_rate": 3.846153846153846e-05,
      "loss": 1.0198,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 2.728181838989258,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.9166,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 2.329559326171875,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.9333,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 2.1600072383880615,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.7294,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 2.5714714527130127,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.7403,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 1.37794029712677,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.5543,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.449770450592041,
      "eval_runtime": 21.0531,
      "eval_samples_per_second": 2.137,
      "eval_steps_per_second": 2.137,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 1.0996536016464233,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.438,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 1.173868179321289,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.4377,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 1.1088860034942627,
      "learning_rate": 0.0001,
      "loss": 0.3924,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 1.0363175868988037,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.3749,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.9811908006668091,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.334,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.8342099189758301,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.325,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.6869753003120422,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.3349,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.5685352683067322,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.229,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.6491856575012207,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.2303,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.6617429852485657,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.2353,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.2681349515914917,
      "eval_runtime": 20.973,
      "eval_samples_per_second": 2.146,
      "eval_steps_per_second": 2.146,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.7104077935218811,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.3282,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.6330664753913879,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.2635,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.6205520629882812,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.2481,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.6416417360305786,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.2331,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.5937696099281311,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.2266,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 1.2359470129013062,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.4042,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.47444239258766174,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.162,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.4368915557861328,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.2054,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.6558144092559814,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.213,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.6151806712150574,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.2359,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.1912369579076767,
      "eval_runtime": 20.9975,
      "eval_samples_per_second": 2.143,
      "eval_steps_per_second": 2.143,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.5663303732872009,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.2041,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.6146963238716125,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.1981,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.6697759032249451,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.1684,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.508050262928009,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.1484,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.5851507186889648,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.1532,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.5933696627616882,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.1493,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.6116485595703125,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.1204,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.658832848072052,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.1802,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.4987144470214844,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.1612,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.5062479376792908,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.1345,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.17030280828475952,
      "eval_runtime": 21.0082,
      "eval_samples_per_second": 2.142,
      "eval_steps_per_second": 2.142,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.6734199523925781,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.2213,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.6487348675727844,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.158,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.6126502156257629,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.1618,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.5005550980567932,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.1352,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.5513657927513123,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.1127,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.6094308495521545,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.193,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.6127196550369263,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.1368,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.5071837306022644,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.1298,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.4896073639392853,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.1403,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.6859228610992432,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.1958,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.16646169126033783,
      "eval_runtime": 21.0012,
      "eval_samples_per_second": 2.143,
      "eval_steps_per_second": 2.143,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 1.3290352821350098,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.3398,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.4577043950557709,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.124,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.5173030495643616,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.1444,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.6029992699623108,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.1491,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.5186848044395447,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.1019,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.6197696328163147,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.1277,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.4823063611984253,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.0888,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.5110309720039368,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.1129,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.6826696395874023,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.1531,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.6599043011665344,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.1009,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.15670639276504517,
      "eval_runtime": 20.9935,
      "eval_samples_per_second": 2.144,
      "eval_steps_per_second": 2.144,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.4059021472930908,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.0949,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.7496136426925659,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.1169,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.6210371851921082,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.1466,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.7109023928642273,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.1291,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.5798744559288025,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.1097,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.5529230833053589,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.119,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.6859407424926758,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.0838,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.5908403992652893,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.089,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.5872823596000671,
      "learning_rate": 5e-05,
      "loss": 0.1184,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.6210851073265076,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.1268,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.14835962653160095,
      "eval_runtime": 21.0099,
      "eval_samples_per_second": 2.142,
      "eval_steps_per_second": 2.142,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.5743966102600098,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.0881,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.6463377475738525,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.1038,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.45964911580085754,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.1105,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.6548458337783813,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.122,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.6685418486595154,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.1322,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 0.8583851456642151,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.1729,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.5213847160339355,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0707,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.5580831170082092,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.0897,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.6014366149902344,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.1044,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.42244166135787964,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.072,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.14374859631061554,
      "eval_runtime": 20.9964,
      "eval_samples_per_second": 2.143,
      "eval_steps_per_second": 2.143,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.5718027353286743,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.0942,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.46368929743766785,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.0598,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.6159793138504028,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.1066,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.5498052835464478,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.0879,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.5381328463554382,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0766,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.5300482511520386,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.0974,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.5681226253509521,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.0905,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.5593484044075012,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.0625,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.6125144362449646,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.0712,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.5398672223091125,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0557,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.14451438188552856,
      "eval_runtime": 21.008,
      "eval_samples_per_second": 2.142,
      "eval_steps_per_second": 2.142,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.6828307509422302,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.1269,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.5803796648979187,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.0985,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.5412408709526062,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0685,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.537438154220581,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.076,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.6392014026641846,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.1152,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.6631283164024353,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.0799,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.7509649991989136,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0754,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.5939491391181946,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.0994,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.6626772880554199,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.1077,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.6295253038406372,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.074,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.14659975469112396,
      "eval_runtime": 21.021,
      "eval_samples_per_second": 2.141,
      "eval_steps_per_second": 2.141,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 1.0130414962768555,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.1417,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 1.0415602922439575,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.152,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.5136945247650146,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.0509,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.5922423601150513,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0879,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.6454489827156067,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.0732,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.5536893010139465,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0641,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.4388667047023773,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.0638,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.5916503667831421,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.0829,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.7726590037345886,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0976,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.563194215297699,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0619,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.14396603405475616,
      "eval_runtime": 21.0219,
      "eval_samples_per_second": 2.141,
      "eval_steps_per_second": 2.141,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.5730535387992859,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0623,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.7528649568557739,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.0721,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.5723280310630798,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.071,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.630484402179718,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.1107,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.48448678851127625,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0545,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.5648594498634338,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.0709,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.5293920040130615,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.0567,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.6857571005821228,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0828,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.7334778904914856,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0813,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.6790494918823242,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.0661,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.142436221241951,
      "eval_runtime": 21.0151,
      "eval_samples_per_second": 2.141,
      "eval_steps_per_second": 2.141,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.6744362711906433,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0952,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.43662533164024353,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0482,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.5890761613845825,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0784,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.5447983145713806,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.0625,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.4216794967651367,
      "learning_rate": 0.0,
      "loss": 0.0443,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.251548107725865e+17,
      "train_loss": 0.20418572583794595,
      "train_runtime": 3485.9699,
      "train_samples_per_second": 0.581,
      "train_steps_per_second": 0.036
    }
  ],
  "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": 1.251548107725865e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}