{
  "best_metric": 0.12398771941661835,
  "best_model_checkpoint": "saves/psy-course-info/MentaLLaMA-chat-7B/train/fold8/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": 0.8675529360771179,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.9945,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 0.8944142460823059,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 1.0887,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 0.9208359718322754,
      "learning_rate": 2.307692307692308e-05,
      "loss": 1.1487,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 0.9287604689598083,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 1.0726,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 1.0444982051849365,
      "learning_rate": 3.846153846153846e-05,
      "loss": 1.0265,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 1.1198339462280273,
      "learning_rate": 4.615384615384616e-05,
      "loss": 1.0749,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 1.102598786354065,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.9759,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 1.1620919704437256,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.9162,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 1.2454581260681152,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.7766,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 1.3416180610656738,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.7993,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.6858012676239014,
      "eval_runtime": 23.8998,
      "eval_samples_per_second": 1.883,
      "eval_steps_per_second": 1.883,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 1.304099678993225,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.6006,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.8608598113059998,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.6178,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 0.616691529750824,
      "learning_rate": 0.0001,
      "loss": 0.4103,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.6747854948043823,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.3027,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.7708611488342285,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.3992,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.5903160572052002,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.2981,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.4760120213031769,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.3506,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.43523460626602173,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.2913,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.48325905203819275,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.3036,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.4313216805458069,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.3021,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.26128822565078735,
      "eval_runtime": 23.9074,
      "eval_samples_per_second": 1.882,
      "eval_steps_per_second": 1.882,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.4966522455215454,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.354,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.4777924716472626,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.2446,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.5451173186302185,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.2386,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.5708733797073364,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.3544,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.4940994679927826,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.3344,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 0.8775020837783813,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.4805,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.3548310399055481,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.1788,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.3273223638534546,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.1947,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.42160937190055847,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.2183,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.3696368336677551,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.2318,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.19153578579425812,
      "eval_runtime": 23.9273,
      "eval_samples_per_second": 1.881,
      "eval_steps_per_second": 1.881,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.3225826919078827,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.1973,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.42450225353240967,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.2361,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.4117230474948883,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.2435,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.3251242935657501,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.1893,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.38783490657806396,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.1609,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.37693729996681213,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.1418,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.3340540826320648,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.1652,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.3385281562805176,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.156,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.44600149989128113,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.2173,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.3864341974258423,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.1743,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.1545971930027008,
      "eval_runtime": 23.9012,
      "eval_samples_per_second": 1.883,
      "eval_steps_per_second": 1.883,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.43386831879615784,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.1918,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.29376742243766785,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.1288,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.43806561827659607,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.1951,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.41537731885910034,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.1153,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.40148958563804626,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.1483,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.3560972511768341,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.1618,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.420926034450531,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.1794,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.32773280143737793,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.1562,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.33109918236732483,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.1379,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.3512752950191498,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.1373,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.14374911785125732,
      "eval_runtime": 23.9156,
      "eval_samples_per_second": 1.882,
      "eval_steps_per_second": 1.882,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 0.7311609387397766,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.2158,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.3545830547809601,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.1248,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.2856281101703644,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.136,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.3416348397731781,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.1444,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.33023980259895325,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.1308,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.2513393759727478,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.1128,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.2757166922092438,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.1203,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.38743627071380615,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.1585,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.34741050004959106,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.1375,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.33248865604400635,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.1491,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.13426543772220612,
      "eval_runtime": 23.8691,
      "eval_samples_per_second": 1.885,
      "eval_steps_per_second": 1.885,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.2818622291088104,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.1235,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.38490030169487,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.1508,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.3181605637073517,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.129,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.3982134461402893,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.145,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.32825320959091187,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.1537,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.26397883892059326,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.0901,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.36104556918144226,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.1329,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.3000679612159729,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.0872,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.4082680344581604,
      "learning_rate": 5e-05,
      "loss": 0.1692,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.34902024269104004,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.1278,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.1314055323600769,
      "eval_runtime": 23.8707,
      "eval_samples_per_second": 1.885,
      "eval_steps_per_second": 1.885,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.3654286563396454,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.124,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.33582472801208496,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.1146,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.41803666949272156,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.1513,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.2869530916213989,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.1189,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.27885007858276367,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.1135,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 0.7430658936500549,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.1684,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.30931901931762695,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.1049,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.29128265380859375,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.0922,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.3479529321193695,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.1077,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.2943395674228668,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.0769,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.12538863718509674,
      "eval_runtime": 23.8557,
      "eval_samples_per_second": 1.886,
      "eval_steps_per_second": 1.886,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.35640382766723633,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.1005,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.2783397436141968,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.1027,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.3699216842651367,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.1198,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.322053998708725,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.1026,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.3645796477794647,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.1294,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.40537235140800476,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.1166,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.35445636510849,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.1114,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.31302410364151,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.1308,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.3505587577819824,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.1064,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.39508962631225586,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.1553,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.1250363439321518,
      "eval_runtime": 23.8519,
      "eval_samples_per_second": 1.887,
      "eval_steps_per_second": 1.887,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.2556037902832031,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.0892,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.2695337235927582,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.0745,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.3305060863494873,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0763,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.347483366727829,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.1088,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.38586747646331787,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.1374,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.3138890862464905,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.0668,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.29145747423171997,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0966,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.39403265714645386,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.1173,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.43642759323120117,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.1026,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.4332689046859741,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.1326,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.12556719779968262,
      "eval_runtime": 23.8478,
      "eval_samples_per_second": 1.887,
      "eval_steps_per_second": 1.887,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.4673304557800293,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.1527,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.5425440669059753,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.1542,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.2782837152481079,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.0683,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.32392066717147827,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0845,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.30892446637153625,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.0881,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.29827043414115906,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.1018,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.37444230914115906,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.1026,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.2951546311378479,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.1048,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.30318400263786316,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.098,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.2880128026008606,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0921,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.12534238398075104,
      "eval_runtime": 23.8662,
      "eval_samples_per_second": 1.886,
      "eval_steps_per_second": 1.886,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.30416932702064514,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0882,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.41968315839767456,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.1271,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.23992496728897095,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.071,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.40484482049942017,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.097,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.35164403915405273,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0896,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.26261723041534424,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.0929,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.4215531349182129,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.107,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.40337318181991577,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.1304,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.2487679421901703,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0879,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.3238370418548584,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.0907,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.12398771941661835,
      "eval_runtime": 23.8565,
      "eval_samples_per_second": 1.886,
      "eval_steps_per_second": 1.886,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.32497438788414,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.088,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.38367336988449097,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.1265,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.2737630307674408,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.1068,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.3590848445892334,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.0873,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.38492459058761597,
      "learning_rate": 0.0,
      "loss": 0.1242,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.3829057715693158e+17,
      "train_loss": 0.22931858515739442,
      "train_runtime": 4045.9011,
      "train_samples_per_second": 0.501,
      "train_steps_per_second": 0.031
    }
  ],
  "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": 1.3829057715693158e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}