{
  "best_metric": 0.05635024607181549,
  "best_model_checkpoint": "saves/psy-course-doc-info/Llama3-OpenBioLLM-8B/train/fold10/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": 0.5106512308120728,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.3801,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 0.5197479724884033,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.3998,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 0.5541024208068848,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.3922,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 0.45151931047439575,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.3526,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.6477484107017517,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.4106,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 0.4760902225971222,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.3415,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 0.5431287884712219,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.3451,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 0.49672189354896545,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.3091,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.4853785037994385,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.3165,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 0.3720289468765259,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.2596,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.2647669315338135,
      "eval_runtime": 26.8793,
      "eval_samples_per_second": 1.674,
      "eval_steps_per_second": 1.674,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 0.37194719910621643,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.2365,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.3608124554157257,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.2335,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 0.3505507707595825,
      "learning_rate": 0.0001,
      "loss": 0.2001,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.44979187846183777,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.1965,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.42948633432388306,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.2116,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.41949063539505005,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.1727,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.2950837016105652,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.1671,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.3566131293773651,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.1546,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.29245322942733765,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.1469,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.3505765199661255,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.1329,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.1412116140127182,
      "eval_runtime": 26.6671,
      "eval_samples_per_second": 1.687,
      "eval_steps_per_second": 1.687,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.3860943019390106,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.1555,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.48947978019714355,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.1543,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.27813488245010376,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.1194,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.3171389102935791,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.1116,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.3337157368659973,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.109,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 0.6166849136352539,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.2163,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.26566192507743835,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0916,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.2416645735502243,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.1117,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.2803739011287689,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.1135,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.2800113558769226,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.1064,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.10077542066574097,
      "eval_runtime": 26.6492,
      "eval_samples_per_second": 1.689,
      "eval_steps_per_second": 1.689,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.307058721780777,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.0736,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.2415149062871933,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.1029,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.6246124505996704,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.1009,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.3666404187679291,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.0811,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.3263852596282959,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.0929,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.251973420381546,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.0924,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.36438342928886414,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.0908,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.2182905077934265,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.0701,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.2877175807952881,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.0792,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.385664701461792,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.0896,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.07914844900369644,
      "eval_runtime": 26.6379,
      "eval_samples_per_second": 1.689,
      "eval_steps_per_second": 1.689,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.22275643050670624,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0726,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.25856339931488037,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.0742,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.280678927898407,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.0859,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.32174113392829895,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.0838,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.32980456948280334,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.0729,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.3162074387073517,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.0748,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.32116860151290894,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.0801,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.3349587321281433,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0697,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.2565605044364929,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.0601,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.23947444558143616,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.0653,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.06871605664491653,
      "eval_runtime": 26.6488,
      "eval_samples_per_second": 1.689,
      "eval_steps_per_second": 1.689,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 0.4944460391998291,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.1005,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.2734723687171936,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.0587,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.23888619244098663,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.055,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.23405200242996216,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.0703,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.2391197830438614,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0628,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.3020585775375366,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.0606,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.3763893246650696,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.0842,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.3066804111003876,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.0496,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.3990039527416229,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.0566,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.3124942183494568,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.0631,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.06542201340198517,
      "eval_runtime": 26.6622,
      "eval_samples_per_second": 1.688,
      "eval_steps_per_second": 1.688,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.5814349055290222,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.0592,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.33284786343574524,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0577,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.20767299830913544,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.0478,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.22555503249168396,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.0541,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.332785427570343,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.0706,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.2584976553916931,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.0446,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.4790288805961609,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.0582,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.26346492767333984,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.047,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.22466276586055756,
      "learning_rate": 5e-05,
      "loss": 0.0549,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.3361237943172455,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.0644,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.06151283532381058,
      "eval_runtime": 26.6672,
      "eval_samples_per_second": 1.687,
      "eval_steps_per_second": 1.687,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.330278605222702,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.0511,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.28407612442970276,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.0618,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.21083402633666992,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.0473,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.2578127682209015,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.0543,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.2544473111629486,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.0493,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 0.42693087458610535,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0864,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.26000139117240906,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0469,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.2875065505504608,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.055,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.34430980682373047,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.0541,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.26267048716545105,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.053,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.0588352307677269,
      "eval_runtime": 26.6759,
      "eval_samples_per_second": 1.687,
      "eval_steps_per_second": 1.687,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.19224973022937775,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.0418,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.22215387225151062,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.0479,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.22400641441345215,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0459,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.183017298579216,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.0405,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.19174188375473022,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0429,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.22212091088294983,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.0489,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.1947232335805893,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.0508,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.21040835976600647,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.0469,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.4709972143173218,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.0407,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.22298841178417206,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0483,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.0584028884768486,
      "eval_runtime": 26.7019,
      "eval_samples_per_second": 1.685,
      "eval_steps_per_second": 1.685,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.2162885218858719,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.0495,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.21796809136867523,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.0436,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.22345155477523804,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0365,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.2603382170200348,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.0484,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.24862724542617798,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.0589,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.22002187371253967,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.0477,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.24304182827472687,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0444,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.23947277665138245,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.0488,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.18361547589302063,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.0494,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.27605804800987244,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.0429,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.05700517073273659,
      "eval_runtime": 26.6681,
      "eval_samples_per_second": 1.687,
      "eval_steps_per_second": 1.687,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.21074283123016357,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.0552,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.27336469292640686,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.0601,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.1823578029870987,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.0399,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.25295290350914,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0417,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.25032609701156616,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.0385,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.16043569147586823,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0346,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.21470704674720764,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.042,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.15520083904266357,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.0335,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.20020467042922974,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0508,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.1398831009864807,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0395,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.056530214846134186,
      "eval_runtime": 26.6778,
      "eval_samples_per_second": 1.687,
      "eval_steps_per_second": 1.687,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.15054826438426971,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0383,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.21434414386749268,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.0539,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.18074269592761993,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.0447,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.2066810578107834,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.0491,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.20090870559215546,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0437,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.16595977544784546,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.0408,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.18880052864551544,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.043,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.1966697871685028,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0445,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.15843984484672546,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0395,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.21466957032680511,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.0509,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.05635024607181549,
      "eval_runtime": 26.6793,
      "eval_samples_per_second": 1.687,
      "eval_steps_per_second": 1.687,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.18224985897541046,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0385,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.17218565940856934,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0379,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.2255355268716812,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0411,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.17646008729934692,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.0429,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.16532227396965027,
      "learning_rate": 0.0,
      "loss": 0.0388,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.691993656466473e+17,
      "train_loss": 0.09638942113518714,
      "train_runtime": 4778.291,
      "train_samples_per_second": 0.424,
      "train_steps_per_second": 0.026
    }
  ],
  "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": 1.691993656466473e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}