{
  "best_metric": 0.05721065774559975,
  "best_model_checkpoint": "saves/psy-course-doc-info/Llama3-OpenBioLLM-8B/train/fold2/checkpoint-120",
  "epoch": 4.938271604938271,
  "eval_steps": 10,
  "global_step": 125,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03950617283950617,
      "grad_norm": 0.49626830220222473,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.3653,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 0.521016538143158,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.4036,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 0.5141693353652954,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.39,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 0.49269235134124756,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.3822,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.5335143208503723,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.3984,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 0.5178160667419434,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.343,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 0.6037830710411072,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.3637,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 0.44932520389556885,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.3117,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.5065156817436218,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.3282,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 0.43244287371635437,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.2928,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.259917289018631,
      "eval_runtime": 33.0584,
      "eval_samples_per_second": 1.361,
      "eval_steps_per_second": 1.361,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 0.3919331729412079,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.2619,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.39565983414649963,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.222,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 0.4410531520843506,
      "learning_rate": 0.0001,
      "loss": 0.2142,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.4912864863872528,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.2232,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.5322580933570862,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.1854,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.38273632526397705,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.1565,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.3022131025791168,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.1612,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.3910534083843231,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.1671,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.3179962933063507,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.147,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.33097004890441895,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.1439,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.14672890305519104,
      "eval_runtime": 32.6927,
      "eval_samples_per_second": 1.376,
      "eval_steps_per_second": 1.376,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.3314151167869568,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.1475,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.525453507900238,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.1517,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.2757347524166107,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.1236,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.49588459730148315,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.117,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.4024468958377838,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.1225,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 0.7174263000488281,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.232,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.49826523661613464,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0883,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.2875238060951233,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.1223,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.3072264492511749,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.105,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.29830363392829895,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.1255,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.10965856909751892,
      "eval_runtime": 31.45,
      "eval_samples_per_second": 1.431,
      "eval_steps_per_second": 1.431,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.22724641859531403,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.0876,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.32522305846214294,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.1119,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.28745728731155396,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.0944,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.240428626537323,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.0848,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.2490164190530777,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.0853,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.33685141801834106,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.0907,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.21755076944828033,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.0832,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.21820326149463654,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.0986,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.29970023036003113,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.0901,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.27403804659843445,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.0732,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.08768974244594574,
      "eval_runtime": 33.0961,
      "eval_samples_per_second": 1.36,
      "eval_steps_per_second": 1.36,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.3028722405433655,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.077,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.286651611328125,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.0739,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.3032870292663574,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.0796,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.27461209893226624,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.0817,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.25890275835990906,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.0631,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.27423951029777527,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.0699,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.32439902424812317,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.0923,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.3356514573097229,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0702,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.23812074959278107,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.0782,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.2415958046913147,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.0723,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.07418181002140045,
      "eval_runtime": 33.0643,
      "eval_samples_per_second": 1.361,
      "eval_steps_per_second": 1.361,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 0.3946520686149597,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.1049,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.28124773502349854,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.0562,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.2361806035041809,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.0664,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.1988665610551834,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.0738,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.18909139931201935,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0477,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.2655848264694214,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.0606,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.2603634297847748,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.083,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.21051624417304993,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.0517,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.2710628807544708,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.0656,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.18492309749126434,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.05,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.06763853132724762,
      "eval_runtime": 33.325,
      "eval_samples_per_second": 1.35,
      "eval_steps_per_second": 1.35,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.29135626554489136,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.0539,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.2071138173341751,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0566,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.21822422742843628,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.0557,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.34843674302101135,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.0682,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.2512977421283722,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.0575,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.24508462846279144,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.0591,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.2660422623157501,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.0576,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.2768794298171997,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.0591,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.216055765748024,
      "learning_rate": 5e-05,
      "loss": 0.0587,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.3476886749267578,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.0593,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.06416059285402298,
      "eval_runtime": 33.5466,
      "eval_samples_per_second": 1.341,
      "eval_steps_per_second": 1.341,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.2119748741388321,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.0532,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.24177120625972748,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.0574,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.20293273031711578,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.0499,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.254482626914978,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.0568,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.2524335980415344,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.0615,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 0.4988026022911072,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0922,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.15946049988269806,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0424,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.20786626636981964,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.0491,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.22144515812397003,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.0408,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.28071412444114685,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.059,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.06093685328960419,
      "eval_runtime": 33.7012,
      "eval_samples_per_second": 1.335,
      "eval_steps_per_second": 1.335,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.28080296516418457,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.0508,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.21496915817260742,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.0372,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.161954864859581,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0413,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.2559185028076172,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.0507,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.17149633169174194,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0383,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.2029973566532135,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.0489,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.19052408635616302,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.0429,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.19820784032344818,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.0406,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.21906447410583496,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.052,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.20219136774539948,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0453,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.058930400758981705,
      "eval_runtime": 33.8117,
      "eval_samples_per_second": 1.331,
      "eval_steps_per_second": 1.331,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.2042054831981659,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.0575,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.16364413499832153,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.0434,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.20904132723808289,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0429,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.24850332736968994,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.0542,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.3608364760875702,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.0604,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.24584326148033142,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.0488,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.21097926795482635,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0459,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.22628863155841827,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.0437,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.2070254236459732,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.0499,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.2497604638338089,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.0442,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.05763997510075569,
      "eval_runtime": 33.9623,
      "eval_samples_per_second": 1.325,
      "eval_steps_per_second": 1.325,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.25075563788414,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.0554,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.4386538863182068,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.0816,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.2014068067073822,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.0409,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.21947996318340302,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0468,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.20927006006240845,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.0545,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.1425045132637024,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0275,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.2148745208978653,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.0493,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.19486626982688904,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.0394,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.19943656027317047,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0505,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.17016761004924774,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0355,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.057480812072753906,
      "eval_runtime": 32.6384,
      "eval_samples_per_second": 1.379,
      "eval_steps_per_second": 1.379,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.18478132784366608,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0408,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.23380737006664276,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.0408,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.2138303816318512,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.0458,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.24958403408527374,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.0579,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.16673912107944489,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0316,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.17822468280792236,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.0405,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.1921006739139557,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.0317,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.21151737868785858,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.045,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.20544689893722534,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0467,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.2343815118074417,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.0541,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.05721065774559975,
      "eval_runtime": 34.2527,
      "eval_samples_per_second": 1.314,
      "eval_steps_per_second": 1.314,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.21054838597774506,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0493,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.16229994595050812,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0349,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.21351274847984314,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0403,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.1838654726743698,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.0389,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.17330335080623627,
      "learning_rate": 0.0,
      "loss": 0.0419,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.6732379190126182e+17,
      "train_loss": 0.09858836162090301,
      "train_runtime": 5549.9172,
      "train_samples_per_second": 0.365,
      "train_steps_per_second": 0.023
    }
  ],
  "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": 1.6732379190126182e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}