{
  "best_metric": 0.06161228194832802,
  "best_model_checkpoint": "saves/psy-course-doc/Llama-3.1-8B-Instruct/train/fold2/checkpoint-110",
  "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": 0.1759316474199295,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.1931,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 0.16981805860996246,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.2545,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 0.16818922758102417,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.1963,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 0.16523034870624542,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.2614,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.16595442593097687,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.2317,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 0.17669977247714996,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.2203,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 0.18929621577262878,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.175,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 0.18715110421180725,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.3006,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.17180511355400085,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.1531,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 0.13557247817516327,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.1476,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.14158716797828674,
      "eval_runtime": 26.2008,
      "eval_samples_per_second": 1.718,
      "eval_steps_per_second": 1.718,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 0.13597746193408966,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.1242,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.15132653713226318,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.1515,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 0.1521364003419876,
      "learning_rate": 0.0001,
      "loss": 0.1248,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.16990229487419128,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.1195,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.15539488196372986,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.1359,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.12689398229122162,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.1375,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.13956010341644287,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.112,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.12834763526916504,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.1264,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.1315171867609024,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.1533,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.10342627763748169,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.0977,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.09028898179531097,
      "eval_runtime": 25.9599,
      "eval_samples_per_second": 1.733,
      "eval_steps_per_second": 1.733,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.11502320319414139,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.1086,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.11507999151945114,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.0933,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.10153067857027054,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.1016,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.09318060427904129,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.0898,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.10934671759605408,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.0995,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 0.25399255752563477,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.2805,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.07778014987707138,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0532,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.09652764350175858,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.1541,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.09653695672750473,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.0906,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.1240464523434639,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.1032,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.0757087990641594,
      "eval_runtime": 25.958,
      "eval_samples_per_second": 1.734,
      "eval_steps_per_second": 1.734,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.08644452691078186,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.0785,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.10954375565052032,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.1541,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.11143830418586731,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.1211,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.08459561318159103,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.0548,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.08675628900527954,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.0288,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.1071229800581932,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.0867,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.08263108879327774,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.0692,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.10853084176778793,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.134,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.08550621569156647,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.0977,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.08760742843151093,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.0877,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.06949209421873093,
      "eval_runtime": 26.0047,
      "eval_samples_per_second": 1.73,
      "eval_steps_per_second": 1.73,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.07491857558488846,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0422,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.0800999253988266,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.0746,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.09285952150821686,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.0835,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.09627781808376312,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.136,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.08221036195755005,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.077,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.09476348012685776,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.0717,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.0914408415555954,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.094,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.08048124611377716,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0432,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.09025293588638306,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.1043,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.08645343780517578,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.0399,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.06636413931846619,
      "eval_runtime": 25.9121,
      "eval_samples_per_second": 1.737,
      "eval_steps_per_second": 1.737,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 0.15998046100139618,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.1271,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.07916560024023056,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.0787,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.11009065061807632,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.0976,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.08440341800451279,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.0529,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.0859469398856163,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.1126,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.101343534886837,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.1407,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.1007806584239006,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.1012,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.10526702553033829,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.06,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.09874005615711212,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.1023,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.09057644009590149,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.0469,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.06510460376739502,
      "eval_runtime": 25.9519,
      "eval_samples_per_second": 1.734,
      "eval_steps_per_second": 1.734,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.13884912431240082,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.0282,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.09130292385816574,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0872,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.06966403871774673,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.0482,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.08004425466060638,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.0542,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.09040854871273041,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.0861,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.0787978395819664,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.0542,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.09369169175624847,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.0639,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.09942405670881271,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.1019,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.10206972062587738,
      "learning_rate": 5e-05,
      "loss": 0.0933,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.09592077136039734,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.0914,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.06328409165143967,
      "eval_runtime": 25.9296,
      "eval_samples_per_second": 1.735,
      "eval_steps_per_second": 1.735,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.07886040955781937,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.066,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.09000278264284134,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.1231,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.0852745920419693,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.0888,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.08423364907503128,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.0595,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.07133214175701141,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.0413,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 0.17634859681129456,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0801,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.09194955229759216,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.107,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.10921759158372879,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.1335,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.059805043041706085,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.0339,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.1159745380282402,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.0906,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.06253591924905777,
      "eval_runtime": 25.9184,
      "eval_samples_per_second": 1.736,
      "eval_steps_per_second": 1.736,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.07730959355831146,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.0607,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.08900146186351776,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.0261,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.08575031161308289,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0681,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.11871743947267532,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.0916,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.0912146344780922,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0609,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.09014171361923218,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.0824,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.08651959151029587,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.0462,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.083955779671669,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.0523,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.09596166759729385,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.0985,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.09306661784648895,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0439,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.06229422241449356,
      "eval_runtime": 25.8404,
      "eval_samples_per_second": 1.741,
      "eval_steps_per_second": 1.741,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.12268614023923874,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.0777,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.08523562550544739,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.0638,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.08131159096956253,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0564,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.10053308308124542,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.0652,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.10830798745155334,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.0885,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.11290527880191803,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.0915,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.09375885874032974,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0503,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.11435624212026596,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.079,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.1073007583618164,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.1036,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.0950460284948349,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.07,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.06168016791343689,
      "eval_runtime": 25.6122,
      "eval_samples_per_second": 1.757,
      "eval_steps_per_second": 1.757,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.0964621901512146,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.0727,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.1518649309873581,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.0949,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.08398684859275818,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.0543,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.07389311492443085,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0401,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.1130579486489296,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.1317,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.07304566353559494,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0432,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.11213716119527817,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.1217,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.08982303738594055,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.0544,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.09592804312705994,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0775,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.07601446658372879,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0511,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.06161228194832802,
      "eval_runtime": 25.8539,
      "eval_samples_per_second": 1.741,
      "eval_steps_per_second": 1.741,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.07823565602302551,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0415,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.07564640790224075,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.0364,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.06842712312936783,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.0195,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.11136295646429062,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.1019,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.07317179441452026,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0113,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.0774075984954834,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.0296,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.08441270887851715,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.0686,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.10875315219163895,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0702,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.08961249142885208,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0606,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.1266225427389145,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.1251,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.061677660793066025,
      "eval_runtime": 25.9128,
      "eval_samples_per_second": 1.737,
      "eval_steps_per_second": 1.737,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.08445505797863007,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0557,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.10369012504816055,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0965,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.09647972881793976,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0841,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.09594930708408356,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.0866,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.09059258550405502,
      "learning_rate": 0.0,
      "loss": 0.0724,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.5041978615365632e+17,
      "train_loss": 0.09440466659516096,
      "train_runtime": 4183.0356,
      "train_samples_per_second": 0.484,
      "train_steps_per_second": 0.03
    }
  ],
  "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": 1.5041978615365632e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}