{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 435,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03466204506065858,
      "grad_norm": 1.530611515045166,
      "learning_rate": 0.0002,
      "loss": 3.0151,
      "step": 5
    },
    {
      "epoch": 0.06932409012131716,
      "grad_norm": 1.7004058361053467,
      "learning_rate": 0.0002,
      "loss": 2.0235,
      "step": 10
    },
    {
      "epoch": 0.10398613518197573,
      "grad_norm": 1.933908462524414,
      "learning_rate": 0.0002,
      "loss": 1.1225,
      "step": 15
    },
    {
      "epoch": 0.1386481802426343,
      "grad_norm": 0.9951248168945312,
      "learning_rate": 0.0002,
      "loss": 0.5422,
      "step": 20
    },
    {
      "epoch": 0.1733102253032929,
      "grad_norm": 6.152623176574707,
      "learning_rate": 0.0002,
      "loss": 1.5639,
      "step": 25
    },
    {
      "epoch": 0.20797227036395147,
      "grad_norm": 8.008278846740723,
      "learning_rate": 0.0002,
      "loss": 2.6486,
      "step": 30
    },
    {
      "epoch": 0.24263431542461006,
      "grad_norm": 4.960943222045898,
      "learning_rate": 0.0002,
      "loss": 2.6059,
      "step": 35
    },
    {
      "epoch": 0.2772963604852686,
      "grad_norm": 4.607645511627197,
      "learning_rate": 0.0002,
      "loss": 1.6898,
      "step": 40
    },
    {
      "epoch": 0.3119584055459272,
      "grad_norm": 0.8448249101638794,
      "learning_rate": 0.0002,
      "loss": 0.799,
      "step": 45
    },
    {
      "epoch": 0.3466204506065858,
      "grad_norm": 0.46238261461257935,
      "learning_rate": 0.0002,
      "loss": 0.5374,
      "step": 50
    },
    {
      "epoch": 0.38128249566724437,
      "grad_norm": 0.3575257956981659,
      "learning_rate": 0.0002,
      "loss": 0.4247,
      "step": 55
    },
    {
      "epoch": 0.41594454072790293,
      "grad_norm": 2.5151493549346924,
      "learning_rate": 0.0002,
      "loss": 0.7472,
      "step": 60
    },
    {
      "epoch": 0.4506065857885615,
      "grad_norm": 17.38052749633789,
      "learning_rate": 0.0002,
      "loss": 1.8466,
      "step": 65
    },
    {
      "epoch": 0.4852686308492201,
      "grad_norm": 15.523968696594238,
      "learning_rate": 0.0002,
      "loss": 2.1105,
      "step": 70
    },
    {
      "epoch": 0.5199306759098787,
      "grad_norm": 1.0907574892044067,
      "learning_rate": 0.0002,
      "loss": 1.1052,
      "step": 75
    },
    {
      "epoch": 0.5545927209705372,
      "grad_norm": 0.5225581526756287,
      "learning_rate": 0.0002,
      "loss": 0.5663,
      "step": 80
    },
    {
      "epoch": 0.5892547660311959,
      "grad_norm": 0.3306778073310852,
      "learning_rate": 0.0002,
      "loss": 0.4648,
      "step": 85
    },
    {
      "epoch": 0.6239168110918544,
      "grad_norm": 0.33595138788223267,
      "learning_rate": 0.0002,
      "loss": 0.3762,
      "step": 90
    },
    {
      "epoch": 0.658578856152513,
      "grad_norm": 1.978458285331726,
      "learning_rate": 0.0002,
      "loss": 0.9162,
      "step": 95
    },
    {
      "epoch": 0.6932409012131716,
      "grad_norm": 1.1226632595062256,
      "learning_rate": 0.0002,
      "loss": 1.5477,
      "step": 100
    },
    {
      "epoch": 0.7279029462738301,
      "grad_norm": 22.263992309570312,
      "learning_rate": 0.0002,
      "loss": 1.8063,
      "step": 105
    },
    {
      "epoch": 0.7625649913344887,
      "grad_norm": 1.3690563440322876,
      "learning_rate": 0.0002,
      "loss": 1.3102,
      "step": 110
    },
    {
      "epoch": 0.7972270363951474,
      "grad_norm": 0.5651267766952515,
      "learning_rate": 0.0002,
      "loss": 0.553,
      "step": 115
    },
    {
      "epoch": 0.8318890814558059,
      "grad_norm": 0.3272489011287689,
      "learning_rate": 0.0002,
      "loss": 0.4813,
      "step": 120
    },
    {
      "epoch": 0.8665511265164645,
      "grad_norm": 0.30475500226020813,
      "learning_rate": 0.0002,
      "loss": 0.3746,
      "step": 125
    },
    {
      "epoch": 0.901213171577123,
      "grad_norm": 0.2812097370624542,
      "learning_rate": 0.0002,
      "loss": 0.284,
      "step": 130
    },
    {
      "epoch": 0.9358752166377816,
      "grad_norm": 1.159839391708374,
      "learning_rate": 0.0002,
      "loss": 1.5179,
      "step": 135
    },
    {
      "epoch": 0.9705372616984402,
      "grad_norm": 4.740174770355225,
      "learning_rate": 0.0002,
      "loss": 1.549,
      "step": 140
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.613008499145508,
      "learning_rate": 0.0002,
      "loss": 1.3938,
      "step": 145
    },
    {
      "epoch": 1.0346620450606585,
      "grad_norm": 0.31811827421188354,
      "learning_rate": 0.0002,
      "loss": 0.5353,
      "step": 150
    },
    {
      "epoch": 1.0693240901213172,
      "grad_norm": 0.42897579073905945,
      "learning_rate": 0.0002,
      "loss": 0.4452,
      "step": 155
    },
    {
      "epoch": 1.1039861351819757,
      "grad_norm": 0.28854838013648987,
      "learning_rate": 0.0002,
      "loss": 0.3563,
      "step": 160
    },
    {
      "epoch": 1.1386481802426343,
      "grad_norm": 0.32319992780685425,
      "learning_rate": 0.0002,
      "loss": 0.2697,
      "step": 165
    },
    {
      "epoch": 1.173310225303293,
      "grad_norm": 1.0144641399383545,
      "learning_rate": 0.0002,
      "loss": 1.3199,
      "step": 170
    },
    {
      "epoch": 1.2079722703639515,
      "grad_norm": 2.1387648582458496,
      "learning_rate": 0.0002,
      "loss": 1.1948,
      "step": 175
    },
    {
      "epoch": 1.24263431542461,
      "grad_norm": 5.240429401397705,
      "learning_rate": 0.0002,
      "loss": 1.2138,
      "step": 180
    },
    {
      "epoch": 1.2772963604852685,
      "grad_norm": 0.5809195637702942,
      "learning_rate": 0.0002,
      "loss": 0.7417,
      "step": 185
    },
    {
      "epoch": 1.3119584055459272,
      "grad_norm": 0.3426031768321991,
      "learning_rate": 0.0002,
      "loss": 0.4541,
      "step": 190
    },
    {
      "epoch": 1.3466204506065858,
      "grad_norm": 0.34089571237564087,
      "learning_rate": 0.0002,
      "loss": 0.3709,
      "step": 195
    },
    {
      "epoch": 1.3812824956672443,
      "grad_norm": 0.2676282823085785,
      "learning_rate": 0.0002,
      "loss": 0.2981,
      "step": 200
    },
    {
      "epoch": 1.415944540727903,
      "grad_norm": 1.8662705421447754,
      "learning_rate": 0.0002,
      "loss": 0.8353,
      "step": 205
    },
    {
      "epoch": 1.4506065857885615,
      "grad_norm": 3.2310688495635986,
      "learning_rate": 0.0002,
      "loss": 1.2188,
      "step": 210
    },
    {
      "epoch": 1.48526863084922,
      "grad_norm": 2.255415916442871,
      "learning_rate": 0.0002,
      "loss": 1.1677,
      "step": 215
    },
    {
      "epoch": 1.5199306759098787,
      "grad_norm": 0.5544691681861877,
      "learning_rate": 0.0002,
      "loss": 0.799,
      "step": 220
    },
    {
      "epoch": 1.5545927209705372,
      "grad_norm": 0.4003375172615051,
      "learning_rate": 0.0002,
      "loss": 0.4786,
      "step": 225
    },
    {
      "epoch": 1.5892547660311958,
      "grad_norm": 0.3774619698524475,
      "learning_rate": 0.0002,
      "loss": 0.4233,
      "step": 230
    },
    {
      "epoch": 1.6239168110918545,
      "grad_norm": 0.352490097284317,
      "learning_rate": 0.0002,
      "loss": 0.3332,
      "step": 235
    },
    {
      "epoch": 1.658578856152513,
      "grad_norm": 0.2637154459953308,
      "learning_rate": 0.0002,
      "loss": 0.2438,
      "step": 240
    },
    {
      "epoch": 1.6932409012131715,
      "grad_norm": 1.3437107801437378,
      "learning_rate": 0.0002,
      "loss": 1.4351,
      "step": 245
    },
    {
      "epoch": 1.7279029462738302,
      "grad_norm": 2.647561550140381,
      "learning_rate": 0.0002,
      "loss": 1.0698,
      "step": 250
    },
    {
      "epoch": 1.7625649913344887,
      "grad_norm": 0.6839751601219177,
      "learning_rate": 0.0002,
      "loss": 0.7411,
      "step": 255
    },
    {
      "epoch": 1.7972270363951472,
      "grad_norm": 0.4790812134742737,
      "learning_rate": 0.0002,
      "loss": 0.5009,
      "step": 260
    },
    {
      "epoch": 1.831889081455806,
      "grad_norm": 0.36322328448295593,
      "learning_rate": 0.0002,
      "loss": 0.4014,
      "step": 265
    },
    {
      "epoch": 1.8665511265164645,
      "grad_norm": 0.31694507598876953,
      "learning_rate": 0.0002,
      "loss": 0.3441,
      "step": 270
    },
    {
      "epoch": 1.901213171577123,
      "grad_norm": 0.24292677640914917,
      "learning_rate": 0.0002,
      "loss": 0.2619,
      "step": 275
    },
    {
      "epoch": 1.9358752166377817,
      "grad_norm": 1.133062720298767,
      "learning_rate": 0.0002,
      "loss": 1.1564,
      "step": 280
    },
    {
      "epoch": 1.9705372616984402,
      "grad_norm": 10.754274368286133,
      "learning_rate": 0.0002,
      "loss": 1.436,
      "step": 285
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.6346553564071655,
      "learning_rate": 0.0002,
      "loss": 1.3215,
      "step": 290
    },
    {
      "epoch": 2.0346620450606587,
      "grad_norm": 0.7156389355659485,
      "learning_rate": 0.0002,
      "loss": 0.551,
      "step": 295
    },
    {
      "epoch": 2.069324090121317,
      "grad_norm": 0.3842258155345917,
      "learning_rate": 0.0002,
      "loss": 0.3783,
      "step": 300
    },
    {
      "epoch": 2.1039861351819757,
      "grad_norm": 0.35967278480529785,
      "learning_rate": 0.0002,
      "loss": 0.3124,
      "step": 305
    },
    {
      "epoch": 2.1386481802426345,
      "grad_norm": 0.296977162361145,
      "learning_rate": 0.0002,
      "loss": 0.2367,
      "step": 310
    },
    {
      "epoch": 2.1733102253032928,
      "grad_norm": 1.6834601163864136,
      "learning_rate": 0.0002,
      "loss": 0.7685,
      "step": 315
    },
    {
      "epoch": 2.2079722703639515,
      "grad_norm": 5.758884906768799,
      "learning_rate": 0.0002,
      "loss": 1.0063,
      "step": 320
    },
    {
      "epoch": 2.2426343154246102,
      "grad_norm": 15.24948501586914,
      "learning_rate": 0.0002,
      "loss": 1.231,
      "step": 325
    },
    {
      "epoch": 2.2772963604852685,
      "grad_norm": 0.599730372428894,
      "learning_rate": 0.0002,
      "loss": 0.6392,
      "step": 330
    },
    {
      "epoch": 2.3119584055459272,
      "grad_norm": 0.5307044982910156,
      "learning_rate": 0.0002,
      "loss": 0.3804,
      "step": 335
    },
    {
      "epoch": 2.346620450606586,
      "grad_norm": 0.33558061718940735,
      "learning_rate": 0.0002,
      "loss": 0.3282,
      "step": 340
    },
    {
      "epoch": 2.3812824956672443,
      "grad_norm": 0.2716732919216156,
      "learning_rate": 0.0002,
      "loss": 0.2429,
      "step": 345
    },
    {
      "epoch": 2.415944540727903,
      "grad_norm": 2.454636812210083,
      "learning_rate": 0.0002,
      "loss": 0.5396,
      "step": 350
    },
    {
      "epoch": 2.4506065857885613,
      "grad_norm": 13.286089897155762,
      "learning_rate": 0.0002,
      "loss": 1.0545,
      "step": 355
    },
    {
      "epoch": 2.48526863084922,
      "grad_norm": 12.619502067565918,
      "learning_rate": 0.0002,
      "loss": 1.1547,
      "step": 360
    },
    {
      "epoch": 2.5199306759098787,
      "grad_norm": 0.6347368359565735,
      "learning_rate": 0.0002,
      "loss": 0.7136,
      "step": 365
    },
    {
      "epoch": 2.554592720970537,
      "grad_norm": 0.44485101103782654,
      "learning_rate": 0.0002,
      "loss": 0.3994,
      "step": 370
    },
    {
      "epoch": 2.5892547660311958,
      "grad_norm": 0.36494728922843933,
      "learning_rate": 0.0002,
      "loss": 0.3107,
      "step": 375
    },
    {
      "epoch": 2.6239168110918545,
      "grad_norm": 0.322171688079834,
      "learning_rate": 0.0002,
      "loss": 0.2753,
      "step": 380
    },
    {
      "epoch": 2.6585788561525128,
      "grad_norm": 0.9659174084663391,
      "learning_rate": 0.0002,
      "loss": 0.2948,
      "step": 385
    },
    {
      "epoch": 2.6932409012131715,
      "grad_norm": 0.9371129870414734,
      "learning_rate": 0.0002,
      "loss": 1.0286,
      "step": 390
    },
    {
      "epoch": 2.7279029462738302,
      "grad_norm": 3.4619617462158203,
      "learning_rate": 0.0002,
      "loss": 1.0745,
      "step": 395
    },
    {
      "epoch": 2.7625649913344885,
      "grad_norm": 0.6884852051734924,
      "learning_rate": 0.0002,
      "loss": 0.7637,
      "step": 400
    },
    {
      "epoch": 2.7972270363951472,
      "grad_norm": 0.4440446197986603,
      "learning_rate": 0.0002,
      "loss": 0.4331,
      "step": 405
    },
    {
      "epoch": 2.831889081455806,
      "grad_norm": 0.37561893463134766,
      "learning_rate": 0.0002,
      "loss": 0.3667,
      "step": 410
    },
    {
      "epoch": 2.8665511265164643,
      "grad_norm": 0.320077121257782,
      "learning_rate": 0.0002,
      "loss": 0.2769,
      "step": 415
    },
    {
      "epoch": 2.901213171577123,
      "grad_norm": 1.4914495944976807,
      "learning_rate": 0.0002,
      "loss": 0.4493,
      "step": 420
    },
    {
      "epoch": 2.9358752166377817,
      "grad_norm": 1.164036750793457,
      "learning_rate": 0.0002,
      "loss": 1.1276,
      "step": 425
    },
    {
      "epoch": 2.97053726169844,
      "grad_norm": 5.013108253479004,
      "learning_rate": 0.0002,
      "loss": 1.0841,
      "step": 430
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.2247564792633057,
      "learning_rate": 0.0002,
      "loss": 0.7636,
      "step": 435
    }
  ],
  "logging_steps": 5,
  "max_steps": 1440,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0142828605421568e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}