{
  "best_metric": 0.07107812166213989,
  "best_model_checkpoint": "saves/psy-course-info-chain/MentaLLaMA-chat-7B/train/fold1/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": 0.8131992816925049,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.6196,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 0.6756157279014587,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.6055,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 0.8220041990280151,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.5944,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 0.8677139282226562,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.6822,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.8316059112548828,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.6711,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 0.8798419833183289,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.6478,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 0.8822293281555176,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.6169,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 0.9301314353942871,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.5716,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.9963797926902771,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.4576,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 1.0995820760726929,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.4415,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.3052022159099579,
      "eval_runtime": 23.5685,
      "eval_samples_per_second": 1.909,
      "eval_steps_per_second": 1.909,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 0.9582700729370117,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.2228,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 1.0678330659866333,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.7702,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 0.47970885038375854,
      "learning_rate": 0.0001,
      "loss": 0.2514,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.45366111397743225,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.1728,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.8830119967460632,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.6639,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.7556428909301758,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.3343,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.5276148319244385,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.1645,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.38598400354385376,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.1508,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.28601983189582825,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.1369,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.3422916829586029,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.1181,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.12648841738700867,
      "eval_runtime": 23.4751,
      "eval_samples_per_second": 1.917,
      "eval_steps_per_second": 1.917,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.3251834213733673,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.1442,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.32857128977775574,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.0917,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.24753552675247192,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.0824,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.30322325229644775,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.1357,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.2718782424926758,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.1586,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 0.4190542697906494,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.1844,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.2677045464515686,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.1187,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.2769218981266022,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.138,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.2841409742832184,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.1135,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.29981911182403564,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.0943,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.10279203951358795,
      "eval_runtime": 23.4914,
      "eval_samples_per_second": 1.916,
      "eval_steps_per_second": 1.916,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.26499536633491516,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.0828,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.7924699187278748,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.4211,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.3366664946079254,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.1562,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.3028837740421295,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.1208,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.26056259870529175,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.0965,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.5302550792694092,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.1877,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.19122838973999023,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.0827,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.24521057307720184,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.0935,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.35038211941719055,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.1352,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.254691481590271,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.0863,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.0925823524594307,
      "eval_runtime": 23.4838,
      "eval_samples_per_second": 1.916,
      "eval_steps_per_second": 1.916,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.28709110617637634,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.105,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.2292962372303009,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.0722,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.2535107135772705,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.1035,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.7570321559906006,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.3208,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.32249224185943604,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.1158,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.29127803444862366,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.1008,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.2509024441242218,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.0553,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.2825043499469757,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0741,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.31107547879219055,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.1386,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.20417183637619019,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.077,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.08443699777126312,
      "eval_runtime": 23.498,
      "eval_samples_per_second": 1.915,
      "eval_steps_per_second": 1.915,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 0.5382072925567627,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.1532,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.20296542346477509,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.0652,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.24265052378177643,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.0679,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.2811442017555237,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.124,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.2534279525279999,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.09,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.2520988881587982,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.0664,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.19228361546993256,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.0629,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.21637821197509766,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.0571,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.18331283330917358,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.0506,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.18309442698955536,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.0479,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.07746938616037369,
      "eval_runtime": 23.4949,
      "eval_samples_per_second": 1.915,
      "eval_steps_per_second": 1.915,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.24753379821777344,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.061,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.3204699456691742,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0977,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.23014326393604279,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.0696,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.3470498025417328,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.085,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 1.3012917041778564,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.3778,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.23590506613254547,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.0491,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.27994075417518616,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.0537,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.23847739398479462,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.0803,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.29963862895965576,
      "learning_rate": 5e-05,
      "loss": 0.0653,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.35982105135917664,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.0847,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.07512889802455902,
      "eval_runtime": 23.4966,
      "eval_samples_per_second": 1.915,
      "eval_steps_per_second": 1.915,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.26218411326408386,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.0755,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.4425470530986786,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.143,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.32385924458503723,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.1058,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.24356195330619812,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.075,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.27631112933158875,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.0812,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 0.6474853157997131,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.1468,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.2268538475036621,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0535,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.3312813937664032,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.0696,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.26187577843666077,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.0629,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.21818110346794128,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.0403,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.07612457126379013,
      "eval_runtime": 23.4912,
      "eval_samples_per_second": 1.916,
      "eval_steps_per_second": 1.916,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.2215111404657364,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.0519,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.2890028953552246,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.0639,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.2816307842731476,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0666,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.290176123380661,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.0715,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.23932211101055145,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0553,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.2118745595216751,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.0545,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.6983291506767273,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.1959,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.292412668466568,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.0681,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.287293940782547,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.0678,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.3901762366294861,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0613,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.07830735296010971,
      "eval_runtime": 23.4776,
      "eval_samples_per_second": 1.917,
      "eval_steps_per_second": 1.917,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.3545040190219879,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.1028,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.3520561754703522,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.0889,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.3711622357368469,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0545,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.7003312110900879,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.2112,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.27219030261039734,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.0636,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.2443360686302185,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.055,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.22600460052490234,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0568,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.28427350521087646,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.0635,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.2338804006576538,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.0574,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.2579467296600342,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.0663,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.0723663717508316,
      "eval_runtime": 23.4463,
      "eval_samples_per_second": 1.919,
      "eval_steps_per_second": 1.919,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.29240384697914124,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.0814,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.8370925784111023,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.1441,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.22413119673728943,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.0526,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.22951290011405945,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0533,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.25298362970352173,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.0514,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.2100663036108017,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0586,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.18508443236351013,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.0449,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.2820706367492676,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.0629,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.6235764026641846,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.1886,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.18371571600437164,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0456,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.0711599588394165,
      "eval_runtime": 23.4522,
      "eval_samples_per_second": 1.919,
      "eval_steps_per_second": 1.919,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.2927962839603424,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0579,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.2626715898513794,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.0697,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.2021176666021347,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.0522,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.23246648907661438,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.0523,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.247786283493042,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0601,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.2007468044757843,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.0424,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.2307518869638443,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.0553,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.21371154487133026,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0504,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.2868208885192871,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0802,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.4068514406681061,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.1496,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.07107812166213989,
      "eval_runtime": 23.4608,
      "eval_samples_per_second": 1.918,
      "eval_steps_per_second": 1.918,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.3418703079223633,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0365,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.2885831892490387,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0713,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.2350940704345703,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0674,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.29358816146850586,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.0571,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.22837890684604645,
      "learning_rate": 0.0,
      "loss": 0.0537,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.4234586817580237e+17,
      "train_loss": 0.15008853629231453,
      "train_runtime": 4282.5207,
      "train_samples_per_second": 0.473,
      "train_steps_per_second": 0.029
    }
  ],
  "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": 1.4234586817580237e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}