{
  "best_metric": 0.02043716236948967,
  "best_model_checkpoint": "saves/psy-course-doc/Qwen2.5-7B-Instruct/train/fold1/checkpoint-110",
  "epoch": 4.938271604938271,
  "eval_steps": 10,
  "global_step": 125,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03950617283950617,
      "grad_norm": 0.1509150266647339,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.1274,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 0.16291971504688263,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.1487,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 0.19172553718090057,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.168,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 0.14272353053092957,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.1279,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.1483301967382431,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.1347,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 0.1715272068977356,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.1314,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 0.1370067149400711,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.1146,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 0.14581124484539032,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.1316,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.14886367321014404,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.1318,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 0.13548903167247772,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.1222,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.1259034425020218,
      "eval_runtime": 27.9238,
      "eval_samples_per_second": 1.612,
      "eval_steps_per_second": 1.612,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 0.13764776289463043,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.1177,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.07854989916086197,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.0781,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 0.07467270642518997,
      "learning_rate": 0.0001,
      "loss": 0.0794,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.0828498899936676,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.0857,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.08465993404388428,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.0733,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.06393633037805557,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.0601,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.07872748374938965,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.0619,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.0887727364897728,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.0641,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.07835479080677032,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.061,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.1018042266368866,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.0678,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.06134464964270592,
      "eval_runtime": 27.7424,
      "eval_samples_per_second": 1.622,
      "eval_steps_per_second": 1.622,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.07151088118553162,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.0561,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.08167034387588501,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.0516,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.06945527344942093,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.0471,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.06558752059936523,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.0399,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.05952519550919533,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.0453,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 0.10258723795413971,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.0671,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.05091485008597374,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.034,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.04971904307603836,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.0295,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.05168008804321289,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.0381,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.05195747688412666,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.0283,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.0365583561360836,
      "eval_runtime": 27.763,
      "eval_samples_per_second": 1.621,
      "eval_steps_per_second": 1.621,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.0532643087208271,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.0252,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.047463443130254745,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.0287,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.06436702609062195,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.0303,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.06790897995233536,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.0268,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.07216787338256836,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.0333,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.058790091425180435,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.0271,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.05060062184929848,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.0202,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.05854890123009682,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.0285,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.06598477065563202,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.0252,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.0673094168305397,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.0251,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.028873544186353683,
      "eval_runtime": 27.7717,
      "eval_samples_per_second": 1.62,
      "eval_steps_per_second": 1.62,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.058573104441165924,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0245,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.051874738186597824,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.0218,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.05535874515771866,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.0198,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.06258092075586319,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.0242,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.04409225657582283,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.0218,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.05262930691242218,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.0197,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.05298051983118057,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.0235,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.04044971242547035,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0164,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.037041474133729935,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.0194,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.03892625495791435,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.0179,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.024944743141531944,
      "eval_runtime": 27.7755,
      "eval_samples_per_second": 1.62,
      "eval_steps_per_second": 1.62,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 0.08201976865530014,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.0272,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.04105715826153755,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.016,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.041981227695941925,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.0144,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.04033970087766647,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.0193,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.03424157202243805,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0133,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.048471905291080475,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.0181,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.04310033470392227,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.0209,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.0408971831202507,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.0143,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.04192313179373741,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.0157,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.04360027611255646,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.018,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.023204734548926353,
      "eval_runtime": 27.7712,
      "eval_samples_per_second": 1.62,
      "eval_steps_per_second": 1.62,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.040823064744472504,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.0168,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.04717613011598587,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0195,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.05095936357975006,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.0166,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.04839678108692169,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.0152,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.05388380214571953,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.0221,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.039329640567302704,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.0136,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.053313761949539185,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.0191,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.04778140410780907,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.0198,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.0399940051138401,
      "learning_rate": 5e-05,
      "loss": 0.0127,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.040002644062042236,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.016,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.021724041551351547,
      "eval_runtime": 27.7603,
      "eval_samples_per_second": 1.621,
      "eval_steps_per_second": 1.621,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.040490396320819855,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.0128,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.05062146112322807,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.0175,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.040068238973617554,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.0151,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.05295821279287338,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.0164,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.04163362458348274,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.0168,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 0.09368108958005905,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0302,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.036730244755744934,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0134,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.04223793372511864,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.0197,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.0538126602768898,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.0144,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.06311777979135513,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.0145,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.021255817264318466,
      "eval_runtime": 27.7575,
      "eval_samples_per_second": 1.621,
      "eval_steps_per_second": 1.621,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.03893658518791199,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.0137,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.051709748804569244,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.0173,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.04225800186395645,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0128,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.05286078900098801,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.0135,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.04983971640467644,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0153,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.0425754114985466,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.012,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.036048419773578644,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.0148,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.03447972983121872,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.0124,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.041823286563158035,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.014,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.0567748136818409,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0145,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.021111128851771355,
      "eval_runtime": 27.7514,
      "eval_samples_per_second": 1.622,
      "eval_steps_per_second": 1.622,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.06299569457769394,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.0151,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.037380050867795944,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.013,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.03781064227223396,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0132,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.03186571225523949,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.0122,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.05441493168473244,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.0169,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.04691130667924881,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.0142,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.04801324009895325,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.014,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.05919886380434036,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.0154,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.04588574171066284,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.0136,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.04301901534199715,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.0133,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.020607471466064453,
      "eval_runtime": 27.7729,
      "eval_samples_per_second": 1.62,
      "eval_steps_per_second": 1.62,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.05181490629911423,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.0185,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.06857705861330032,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.0195,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.032683972269296646,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.0114,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.03286903724074364,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.011,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.03541383892297745,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.014,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.03429628908634186,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0137,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.04341363534331322,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.0165,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.031999439001083374,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.0119,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.03990150988101959,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0172,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.03196193650364876,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0122,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.02043716236948967,
      "eval_runtime": 27.7795,
      "eval_samples_per_second": 1.62,
      "eval_steps_per_second": 1.62,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.03463876247406006,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0109,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.04224812239408493,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.0155,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.04356950893998146,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.014,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.03794657811522484,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.0126,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.04085282236337662,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0164,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.035113293677568436,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.0101,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.04539134353399277,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.0136,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.043190810829401016,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0112,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.03854599967598915,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0113,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.03854290768504143,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.0176,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.020438985899090767,
      "eval_runtime": 27.8012,
      "eval_samples_per_second": 1.619,
      "eval_steps_per_second": 1.619,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.04165588319301605,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0138,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.048458412289619446,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0132,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.03473648428916931,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0134,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.030696958303451538,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.0104,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.04053562879562378,
      "learning_rate": 0.0,
      "loss": 0.0139,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.828641261419643e+17,
      "train_loss": 0.033187155663967134,
      "train_runtime": 5107.6916,
      "train_samples_per_second": 0.396,
      "train_steps_per_second": 0.024
    }
  ],
  "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": 1.828641261419643e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}