{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 265,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09603841536614646,
      "grad_norm": 0.7072356343269348,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 3.1026,
      "step": 5
    },
    {
      "epoch": 0.19207683073229292,
      "grad_norm": 0.7724522948265076,
      "learning_rate": 3.6e-05,
      "loss": 3.1732,
      "step": 10
    },
    {
      "epoch": 0.28811524609843936,
      "grad_norm": 0.9103713035583496,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 3.1209,
      "step": 15
    },
    {
      "epoch": 0.38415366146458585,
      "grad_norm": 0.9525737166404724,
      "learning_rate": 7.6e-05,
      "loss": 3.0653,
      "step": 20
    },
    {
      "epoch": 0.4801920768307323,
      "grad_norm": 0.9877885580062866,
      "learning_rate": 9.6e-05,
      "loss": 2.7498,
      "step": 25
    },
    {
      "epoch": 0.5762304921968787,
      "grad_norm": 0.8707166910171509,
      "learning_rate": 0.000116,
      "loss": 2.6275,
      "step": 30
    },
    {
      "epoch": 0.6722689075630253,
      "grad_norm": 1.3398517370224,
      "learning_rate": 0.00013600000000000003,
      "loss": 2.475,
      "step": 35
    },
    {
      "epoch": 0.7683073229291717,
      "grad_norm": 1.2803456783294678,
      "learning_rate": 0.00015600000000000002,
      "loss": 2.207,
      "step": 40
    },
    {
      "epoch": 0.8643457382953181,
      "grad_norm": 1.3441357612609863,
      "learning_rate": 0.00017600000000000002,
      "loss": 1.83,
      "step": 45
    },
    {
      "epoch": 0.9603841536614646,
      "grad_norm": 0.9121316075325012,
      "learning_rate": 0.000196,
      "loss": 1.7398,
      "step": 50
    },
    {
      "epoch": 1.0384153661464586,
      "grad_norm": 0.7634927034378052,
      "learning_rate": 0.00019627906976744185,
      "loss": 1.8408,
      "step": 55
    },
    {
      "epoch": 1.134453781512605,
      "grad_norm": 0.8097577691078186,
      "learning_rate": 0.0001916279069767442,
      "loss": 1.6271,
      "step": 60
    },
    {
      "epoch": 1.2304921968787514,
      "grad_norm": 0.7660069465637207,
      "learning_rate": 0.00018697674418604652,
      "loss": 1.707,
      "step": 65
    },
    {
      "epoch": 1.3265306122448979,
      "grad_norm": 0.7814516425132751,
      "learning_rate": 0.00018232558139534886,
      "loss": 1.6397,
      "step": 70
    },
    {
      "epoch": 1.4225690276110443,
      "grad_norm": 1.1940962076187134,
      "learning_rate": 0.00017767441860465117,
      "loss": 1.6707,
      "step": 75
    },
    {
      "epoch": 1.5186074429771907,
      "grad_norm": 1.1954811811447144,
      "learning_rate": 0.00017302325581395348,
      "loss": 1.5648,
      "step": 80
    },
    {
      "epoch": 1.6146458583433372,
      "grad_norm": 1.1031644344329834,
      "learning_rate": 0.00016837209302325584,
      "loss": 1.5376,
      "step": 85
    },
    {
      "epoch": 1.7106842737094838,
      "grad_norm": 1.2271337509155273,
      "learning_rate": 0.00016372093023255815,
      "loss": 1.5206,
      "step": 90
    },
    {
      "epoch": 1.8067226890756303,
      "grad_norm": 1.5525450706481934,
      "learning_rate": 0.00015906976744186046,
      "loss": 1.4246,
      "step": 95
    },
    {
      "epoch": 1.9027611044417767,
      "grad_norm": 1.0928661823272705,
      "learning_rate": 0.0001544186046511628,
      "loss": 1.4618,
      "step": 100
    },
    {
      "epoch": 1.9987995198079231,
      "grad_norm": 1.430029273033142,
      "learning_rate": 0.0001497674418604651,
      "loss": 1.373,
      "step": 105
    },
    {
      "epoch": 2.076830732292917,
      "grad_norm": 1.303673505783081,
      "learning_rate": 0.00014511627906976747,
      "loss": 1.2444,
      "step": 110
    },
    {
      "epoch": 2.1728691476590636,
      "grad_norm": 1.9656398296356201,
      "learning_rate": 0.00014046511627906978,
      "loss": 1.2816,
      "step": 115
    },
    {
      "epoch": 2.26890756302521,
      "grad_norm": 1.633468747138977,
      "learning_rate": 0.0001358139534883721,
      "loss": 1.2165,
      "step": 120
    },
    {
      "epoch": 2.3649459783913565,
      "grad_norm": 1.5862339735031128,
      "learning_rate": 0.00013116279069767442,
      "loss": 1.2797,
      "step": 125
    },
    {
      "epoch": 2.460984393757503,
      "grad_norm": 1.2453504800796509,
      "learning_rate": 0.00012651162790697676,
      "loss": 1.2173,
      "step": 130
    },
    {
      "epoch": 2.5570228091236493,
      "grad_norm": 1.7630853652954102,
      "learning_rate": 0.00012186046511627907,
      "loss": 1.2752,
      "step": 135
    },
    {
      "epoch": 2.6530612244897958,
      "grad_norm": 2.465102195739746,
      "learning_rate": 0.00011720930232558141,
      "loss": 1.12,
      "step": 140
    },
    {
      "epoch": 2.7490996398559426,
      "grad_norm": 2.226787805557251,
      "learning_rate": 0.00011255813953488372,
      "loss": 1.1776,
      "step": 145
    },
    {
      "epoch": 2.8451380552220886,
      "grad_norm": 2.306854248046875,
      "learning_rate": 0.00010790697674418607,
      "loss": 1.1599,
      "step": 150
    },
    {
      "epoch": 2.9411764705882355,
      "grad_norm": 1.749025821685791,
      "learning_rate": 0.00010325581395348838,
      "loss": 1.089,
      "step": 155
    },
    {
      "epoch": 3.0192076830732293,
      "grad_norm": 2.295750856399536,
      "learning_rate": 9.86046511627907e-05,
      "loss": 1.2437,
      "step": 160
    },
    {
      "epoch": 3.1152460984393757,
      "grad_norm": 2.4508137702941895,
      "learning_rate": 9.395348837209302e-05,
      "loss": 1.097,
      "step": 165
    },
    {
      "epoch": 3.211284513805522,
      "grad_norm": 2.6268515586853027,
      "learning_rate": 8.930232558139535e-05,
      "loss": 1.0338,
      "step": 170
    },
    {
      "epoch": 3.3073229291716686,
      "grad_norm": 2.7699310779571533,
      "learning_rate": 8.465116279069768e-05,
      "loss": 1.0605,
      "step": 175
    },
    {
      "epoch": 3.403361344537815,
      "grad_norm": 2.2988967895507812,
      "learning_rate": 8e-05,
      "loss": 1.0653,
      "step": 180
    },
    {
      "epoch": 3.4993997599039615,
      "grad_norm": 3.493929386138916,
      "learning_rate": 7.534883720930233e-05,
      "loss": 0.9758,
      "step": 185
    },
    {
      "epoch": 3.595438175270108,
      "grad_norm": 1.8273813724517822,
      "learning_rate": 7.069767441860465e-05,
      "loss": 0.9684,
      "step": 190
    },
    {
      "epoch": 3.6914765906362543,
      "grad_norm": 2.5960426330566406,
      "learning_rate": 6.604651162790698e-05,
      "loss": 0.9856,
      "step": 195
    },
    {
      "epoch": 3.787515006002401,
      "grad_norm": 2.3766703605651855,
      "learning_rate": 6.139534883720931e-05,
      "loss": 0.8215,
      "step": 200
    },
    {
      "epoch": 3.883553421368547,
      "grad_norm": 1.8748396635055542,
      "learning_rate": 5.674418604651163e-05,
      "loss": 0.8761,
      "step": 205
    },
    {
      "epoch": 3.979591836734694,
      "grad_norm": 3.0460057258605957,
      "learning_rate": 5.209302325581395e-05,
      "loss": 0.872,
      "step": 210
    },
    {
      "epoch": 4.057623049219688,
      "grad_norm": 2.0809686183929443,
      "learning_rate": 4.744186046511628e-05,
      "loss": 0.7135,
      "step": 215
    },
    {
      "epoch": 4.153661464585834,
      "grad_norm": 2.5814781188964844,
      "learning_rate": 4.2790697674418605e-05,
      "loss": 0.957,
      "step": 220
    },
    {
      "epoch": 4.249699879951981,
      "grad_norm": 2.4936790466308594,
      "learning_rate": 3.8139534883720935e-05,
      "loss": 0.9361,
      "step": 225
    },
    {
      "epoch": 4.345738295318127,
      "grad_norm": 2.3625705242156982,
      "learning_rate": 3.348837209302326e-05,
      "loss": 0.8608,
      "step": 230
    },
    {
      "epoch": 4.441776710684274,
      "grad_norm": 1.8307788372039795,
      "learning_rate": 2.8837209302325585e-05,
      "loss": 0.8447,
      "step": 235
    },
    {
      "epoch": 4.53781512605042,
      "grad_norm": 2.044945001602173,
      "learning_rate": 2.4186046511627908e-05,
      "loss": 0.8737,
      "step": 240
    },
    {
      "epoch": 4.633853541416567,
      "grad_norm": 2.2939560413360596,
      "learning_rate": 1.9534883720930235e-05,
      "loss": 0.9019,
      "step": 245
    },
    {
      "epoch": 4.729891956782713,
      "grad_norm": 2.2410664558410645,
      "learning_rate": 1.488372093023256e-05,
      "loss": 0.7932,
      "step": 250
    },
    {
      "epoch": 4.82593037214886,
      "grad_norm": 2.9812769889831543,
      "learning_rate": 1.0232558139534884e-05,
      "loss": 0.8736,
      "step": 255
    },
    {
      "epoch": 4.921968787515006,
      "grad_norm": 2.267162799835205,
      "learning_rate": 5.581395348837209e-06,
      "loss": 0.7703,
      "step": 260
    },
    {
      "epoch": 5.0,
      "grad_norm": 10.240612030029297,
      "learning_rate": 9.30232558139535e-07,
      "loss": 0.853,
      "step": 265
    }
  ],
  "logging_steps": 5,
  "max_steps": 265,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.10237507780608e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}