{
  "best_metric": 0.07766559720039368,
  "best_model_checkpoint": "saves/psy-course-info-chain/Llama-3.1-8B-Instruct/train/fold6/checkpoint-80",
  "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": 1.7698736190795898,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.5617,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 1.7037315368652344,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.5144,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 1.8047187328338623,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.5559,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 1.641060471534729,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.5292,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 1.7154407501220703,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.5313,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 1.6111056804656982,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.4751,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 1.79718017578125,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.4056,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 2.119922399520874,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.3494,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 1.2907480001449585,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.1965,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 0.7529057264328003,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.187,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.1524019092321396,
      "eval_runtime": 20.329,
      "eval_samples_per_second": 2.214,
      "eval_steps_per_second": 2.214,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 0.6390246152877808,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.2069,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.7073726058006287,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.1474,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 0.8451089262962341,
      "learning_rate": 0.0001,
      "loss": 0.1724,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.7238600850105286,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.1598,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.49667784571647644,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.1404,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.42919790744781494,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.1244,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.435283362865448,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.0958,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.4585147500038147,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.1282,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.45510414242744446,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.1068,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.5325706601142883,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.1483,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.11818620562553406,
      "eval_runtime": 20.3279,
      "eval_samples_per_second": 2.214,
      "eval_steps_per_second": 2.214,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.38932332396507263,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.1412,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.499255895614624,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.1895,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.33275699615478516,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.0794,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.5205209851264954,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.1314,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.4127623736858368,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.1283,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 0.5221022963523865,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.1671,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.45824888348579407,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0771,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.43346643447875977,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.0936,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.413423627614975,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.1324,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.4286034405231476,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.1313,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.10028121620416641,
      "eval_runtime": 20.3221,
      "eval_samples_per_second": 2.214,
      "eval_steps_per_second": 2.214,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.5170679092407227,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.1255,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.36519959568977356,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.0905,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.40629127621650696,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.0878,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.4493611752986908,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.0808,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.4025000035762787,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.1256,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.3855774700641632,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.114,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.6697561144828796,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.0823,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.41952982544898987,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.0735,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.49231407046318054,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.1405,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.4483892023563385,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.0993,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.09125087410211563,
      "eval_runtime": 20.3349,
      "eval_samples_per_second": 2.213,
      "eval_steps_per_second": 2.213,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.35849496722221375,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0468,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.3673677146434784,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.076,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.5010141730308533,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.092,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.3363807201385498,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.033,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.3845888674259186,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.0728,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.3891776502132416,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.0835,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.44744396209716797,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.0824,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.4261585772037506,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0863,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.567549467086792,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.1213,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.4647541046142578,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.1038,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.08205381780862808,
      "eval_runtime": 20.3296,
      "eval_samples_per_second": 2.214,
      "eval_steps_per_second": 2.214,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 0.8489061594009399,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.1406,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.29464560747146606,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.0574,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.3478313386440277,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.0673,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.2896467447280884,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.0628,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.34994441270828247,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0763,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.414267361164093,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.0847,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.3801305890083313,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.065,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.4722614884376526,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.0863,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.3752667307853699,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.0547,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.47775202989578247,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.0994,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.0842379480600357,
      "eval_runtime": 20.3916,
      "eval_samples_per_second": 2.207,
      "eval_steps_per_second": 2.207,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.3234831690788269,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.0529,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.4891799986362457,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0389,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.41994285583496094,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.082,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.39198052883148193,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.0439,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.3681733310222626,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.0722,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.5854647159576416,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.1136,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.6133779883384705,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.0648,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.3450675904750824,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.0435,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.6945337653160095,
      "learning_rate": 5e-05,
      "loss": 0.0722,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.41523975133895874,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.0678,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.08305278420448303,
      "eval_runtime": 20.3778,
      "eval_samples_per_second": 2.208,
      "eval_steps_per_second": 2.208,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.5459586381912231,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.0526,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.6487681269645691,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.104,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.4293457269668579,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.0498,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.5327795147895813,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.0838,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.5651213526725769,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.0527,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 1.0515722036361694,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.1594,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.43420153856277466,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0582,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.2715323567390442,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.0303,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.3434921205043793,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.0581,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.29004228115081787,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.0332,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.07766559720039368,
      "eval_runtime": 20.3889,
      "eval_samples_per_second": 2.207,
      "eval_steps_per_second": 2.207,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.6893432140350342,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.0538,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.5385918021202087,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.0596,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.40365898609161377,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0664,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.4228366017341614,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.0434,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.2778053879737854,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0407,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.3868256211280823,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.0442,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.36130446195602417,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.0584,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.5353342890739441,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.081,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.5428279042243958,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.0654,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.5292253494262695,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0807,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.081960029900074,
      "eval_runtime": 20.4311,
      "eval_samples_per_second": 2.203,
      "eval_steps_per_second": 2.203,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.5420523285865784,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.0528,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.49304547905921936,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.0587,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.3465275466442108,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0309,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.4240114688873291,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.0422,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.4325898587703705,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.0474,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.25978150963783264,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.0345,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.4842377007007599,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0548,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.5019432306289673,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.0654,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.6426694393157959,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.0639,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.5049530267715454,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.0478,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.07966896146535873,
      "eval_runtime": 20.414,
      "eval_samples_per_second": 2.204,
      "eval_steps_per_second": 2.204,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.6204338669776917,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.0673,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.6890730857849121,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.0848,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.41207751631736755,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.0432,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.3234724998474121,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0223,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.4301011562347412,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.0504,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.4847738742828369,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0567,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.3682093024253845,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.0339,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.3746218681335449,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.0502,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.3743288218975067,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0329,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.3928055465221405,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0562,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.08193833380937576,
      "eval_runtime": 20.4268,
      "eval_samples_per_second": 2.203,
      "eval_steps_per_second": 2.203,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.4117301106452942,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0417,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.49983838200569153,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.0556,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.4991866648197174,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.0573,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.36722415685653687,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.0279,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.3744066059589386,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0434,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.5231197476387024,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.0563,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.5917083024978638,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.0551,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.56373131275177,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0444,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.3194548785686493,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0263,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.384220689535141,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.05,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.08223649859428406,
      "eval_runtime": 20.4133,
      "eval_samples_per_second": 2.204,
      "eval_steps_per_second": 2.204,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.45307236909866333,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0632,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.33957305550575256,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0374,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.4605557322502136,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0547,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.4662182927131653,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.04,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.35404232144355774,
      "learning_rate": 0.0,
      "loss": 0.0373,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.3555716469633843e+17,
      "train_loss": 0.10587314392626286,
      "train_runtime": 3790.3295,
      "train_samples_per_second": 0.534,
      "train_steps_per_second": 0.033
    }
  ],
  "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": 1.3555716469633843e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}