{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9956108266276518,
  "eval_steps": 500,
  "global_step": 1023,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.029261155815654718,
      "grad_norm": 2.214355966256512,
      "learning_rate": 5e-06,
      "loss": 0.7976,
      "step": 10
    },
    {
      "epoch": 0.058522311631309436,
      "grad_norm": 1.281388597648664,
      "learning_rate": 5e-06,
      "loss": 0.7383,
      "step": 20
    },
    {
      "epoch": 0.08778346744696415,
      "grad_norm": 1.2874847374087468,
      "learning_rate": 5e-06,
      "loss": 0.7068,
      "step": 30
    },
    {
      "epoch": 0.11704462326261887,
      "grad_norm": 1.0911342229904486,
      "learning_rate": 5e-06,
      "loss": 0.6963,
      "step": 40
    },
    {
      "epoch": 0.14630577907827358,
      "grad_norm": 1.1433555201488177,
      "learning_rate": 5e-06,
      "loss": 0.6869,
      "step": 50
    },
    {
      "epoch": 0.1755669348939283,
      "grad_norm": 0.9269750204811369,
      "learning_rate": 5e-06,
      "loss": 0.6765,
      "step": 60
    },
    {
      "epoch": 0.20482809070958302,
      "grad_norm": 0.5953508309644502,
      "learning_rate": 5e-06,
      "loss": 0.67,
      "step": 70
    },
    {
      "epoch": 0.23408924652523774,
      "grad_norm": 0.41718068806926895,
      "learning_rate": 5e-06,
      "loss": 0.6648,
      "step": 80
    },
    {
      "epoch": 0.26335040234089246,
      "grad_norm": 0.46544885140833864,
      "learning_rate": 5e-06,
      "loss": 0.662,
      "step": 90
    },
    {
      "epoch": 0.29261155815654716,
      "grad_norm": 0.4427594704326977,
      "learning_rate": 5e-06,
      "loss": 0.6545,
      "step": 100
    },
    {
      "epoch": 0.3218727139722019,
      "grad_norm": 0.4255743712663812,
      "learning_rate": 5e-06,
      "loss": 0.6633,
      "step": 110
    },
    {
      "epoch": 0.3511338697878566,
      "grad_norm": 0.37382775787193123,
      "learning_rate": 5e-06,
      "loss": 0.6682,
      "step": 120
    },
    {
      "epoch": 0.38039502560351135,
      "grad_norm": 0.38055941012143985,
      "learning_rate": 5e-06,
      "loss": 0.652,
      "step": 130
    },
    {
      "epoch": 0.40965618141916604,
      "grad_norm": 0.365314239083999,
      "learning_rate": 5e-06,
      "loss": 0.6527,
      "step": 140
    },
    {
      "epoch": 0.4389173372348208,
      "grad_norm": 0.34589597918392456,
      "learning_rate": 5e-06,
      "loss": 0.6481,
      "step": 150
    },
    {
      "epoch": 0.4681784930504755,
      "grad_norm": 0.3891716866109797,
      "learning_rate": 5e-06,
      "loss": 0.65,
      "step": 160
    },
    {
      "epoch": 0.49743964886613024,
      "grad_norm": 0.3629334963604037,
      "learning_rate": 5e-06,
      "loss": 0.655,
      "step": 170
    },
    {
      "epoch": 0.5267008046817849,
      "grad_norm": 0.33370615827223327,
      "learning_rate": 5e-06,
      "loss": 0.6546,
      "step": 180
    },
    {
      "epoch": 0.5559619604974396,
      "grad_norm": 0.36451231535366374,
      "learning_rate": 5e-06,
      "loss": 0.6432,
      "step": 190
    },
    {
      "epoch": 0.5852231163130943,
      "grad_norm": 0.3433862105922731,
      "learning_rate": 5e-06,
      "loss": 0.6444,
      "step": 200
    },
    {
      "epoch": 0.6144842721287491,
      "grad_norm": 0.3402627825523363,
      "learning_rate": 5e-06,
      "loss": 0.6509,
      "step": 210
    },
    {
      "epoch": 0.6437454279444038,
      "grad_norm": 0.34977805775534565,
      "learning_rate": 5e-06,
      "loss": 0.6389,
      "step": 220
    },
    {
      "epoch": 0.6730065837600585,
      "grad_norm": 0.36328360263674203,
      "learning_rate": 5e-06,
      "loss": 0.6389,
      "step": 230
    },
    {
      "epoch": 0.7022677395757132,
      "grad_norm": 0.3269783340514597,
      "learning_rate": 5e-06,
      "loss": 0.6457,
      "step": 240
    },
    {
      "epoch": 0.731528895391368,
      "grad_norm": 0.34709148478302637,
      "learning_rate": 5e-06,
      "loss": 0.6441,
      "step": 250
    },
    {
      "epoch": 0.7607900512070227,
      "grad_norm": 0.3386809515446319,
      "learning_rate": 5e-06,
      "loss": 0.6467,
      "step": 260
    },
    {
      "epoch": 0.7900512070226774,
      "grad_norm": 0.3708217576585751,
      "learning_rate": 5e-06,
      "loss": 0.649,
      "step": 270
    },
    {
      "epoch": 0.8193123628383321,
      "grad_norm": 0.3476600949918196,
      "learning_rate": 5e-06,
      "loss": 0.6478,
      "step": 280
    },
    {
      "epoch": 0.8485735186539868,
      "grad_norm": 0.3461817230116753,
      "learning_rate": 5e-06,
      "loss": 0.64,
      "step": 290
    },
    {
      "epoch": 0.8778346744696416,
      "grad_norm": 0.36176209446732716,
      "learning_rate": 5e-06,
      "loss": 0.632,
      "step": 300
    },
    {
      "epoch": 0.9070958302852963,
      "grad_norm": 0.35122909092020915,
      "learning_rate": 5e-06,
      "loss": 0.645,
      "step": 310
    },
    {
      "epoch": 0.936356986100951,
      "grad_norm": 0.3350984536401145,
      "learning_rate": 5e-06,
      "loss": 0.637,
      "step": 320
    },
    {
      "epoch": 0.9656181419166057,
      "grad_norm": 0.37466191333850035,
      "learning_rate": 5e-06,
      "loss": 0.6402,
      "step": 330
    },
    {
      "epoch": 0.9948792977322605,
      "grad_norm": 0.350268525150869,
      "learning_rate": 5e-06,
      "loss": 0.6362,
      "step": 340
    },
    {
      "epoch": 0.9978054133138259,
      "eval_loss": 0.6407278180122375,
      "eval_runtime": 345.7581,
      "eval_samples_per_second": 26.634,
      "eval_steps_per_second": 0.416,
      "step": 341
    },
    {
      "epoch": 1.025237746891002,
      "grad_norm": 0.3726855231058378,
      "learning_rate": 5e-06,
      "loss": 0.6515,
      "step": 350
    },
    {
      "epoch": 1.054498902706657,
      "grad_norm": 0.3528475470359308,
      "learning_rate": 5e-06,
      "loss": 0.6057,
      "step": 360
    },
    {
      "epoch": 1.0837600585223117,
      "grad_norm": 0.40430278120075436,
      "learning_rate": 5e-06,
      "loss": 0.6091,
      "step": 370
    },
    {
      "epoch": 1.1130212143379663,
      "grad_norm": 0.33594394270737427,
      "learning_rate": 5e-06,
      "loss": 0.6065,
      "step": 380
    },
    {
      "epoch": 1.142282370153621,
      "grad_norm": 0.3984462164005305,
      "learning_rate": 5e-06,
      "loss": 0.6118,
      "step": 390
    },
    {
      "epoch": 1.1715435259692757,
      "grad_norm": 0.3613121293262451,
      "learning_rate": 5e-06,
      "loss": 0.6133,
      "step": 400
    },
    {
      "epoch": 1.2008046817849305,
      "grad_norm": 0.35518722154006915,
      "learning_rate": 5e-06,
      "loss": 0.6129,
      "step": 410
    },
    {
      "epoch": 1.2300658376005853,
      "grad_norm": 0.40502626596849745,
      "learning_rate": 5e-06,
      "loss": 0.6011,
      "step": 420
    },
    {
      "epoch": 1.2593269934162399,
      "grad_norm": 0.3612357129760361,
      "learning_rate": 5e-06,
      "loss": 0.6113,
      "step": 430
    },
    {
      "epoch": 1.2885881492318947,
      "grad_norm": 0.3444217486315101,
      "learning_rate": 5e-06,
      "loss": 0.6038,
      "step": 440
    },
    {
      "epoch": 1.3178493050475493,
      "grad_norm": 0.36580965939804105,
      "learning_rate": 5e-06,
      "loss": 0.6076,
      "step": 450
    },
    {
      "epoch": 1.347110460863204,
      "grad_norm": 0.37654968983720283,
      "learning_rate": 5e-06,
      "loss": 0.6053,
      "step": 460
    },
    {
      "epoch": 1.3763716166788589,
      "grad_norm": 0.3223916565231839,
      "learning_rate": 5e-06,
      "loss": 0.6026,
      "step": 470
    },
    {
      "epoch": 1.4056327724945135,
      "grad_norm": 0.3686887217181575,
      "learning_rate": 5e-06,
      "loss": 0.6035,
      "step": 480
    },
    {
      "epoch": 1.4348939283101683,
      "grad_norm": 0.34546616075721737,
      "learning_rate": 5e-06,
      "loss": 0.6098,
      "step": 490
    },
    {
      "epoch": 1.464155084125823,
      "grad_norm": 0.34062759074897847,
      "learning_rate": 5e-06,
      "loss": 0.5982,
      "step": 500
    },
    {
      "epoch": 1.4934162399414777,
      "grad_norm": 0.34984758972682745,
      "learning_rate": 5e-06,
      "loss": 0.6062,
      "step": 510
    },
    {
      "epoch": 1.5226773957571325,
      "grad_norm": 0.38653752701593264,
      "learning_rate": 5e-06,
      "loss": 0.6085,
      "step": 520
    },
    {
      "epoch": 1.5519385515727873,
      "grad_norm": 0.34980776029961624,
      "learning_rate": 5e-06,
      "loss": 0.6071,
      "step": 530
    },
    {
      "epoch": 1.5811997073884418,
      "grad_norm": 0.36760348585346686,
      "learning_rate": 5e-06,
      "loss": 0.6137,
      "step": 540
    },
    {
      "epoch": 1.6104608632040964,
      "grad_norm": 0.3547689325544471,
      "learning_rate": 5e-06,
      "loss": 0.6048,
      "step": 550
    },
    {
      "epoch": 1.6397220190197512,
      "grad_norm": 0.3543839427681781,
      "learning_rate": 5e-06,
      "loss": 0.6065,
      "step": 560
    },
    {
      "epoch": 1.668983174835406,
      "grad_norm": 0.32142999725489213,
      "learning_rate": 5e-06,
      "loss": 0.5971,
      "step": 570
    },
    {
      "epoch": 1.6982443306510606,
      "grad_norm": 0.3492941780396127,
      "learning_rate": 5e-06,
      "loss": 0.6064,
      "step": 580
    },
    {
      "epoch": 1.7275054864667154,
      "grad_norm": 0.4044986438848018,
      "learning_rate": 5e-06,
      "loss": 0.6066,
      "step": 590
    },
    {
      "epoch": 1.7567666422823702,
      "grad_norm": 0.33644823828470133,
      "learning_rate": 5e-06,
      "loss": 0.6035,
      "step": 600
    },
    {
      "epoch": 1.7860277980980248,
      "grad_norm": 0.3426307215328823,
      "learning_rate": 5e-06,
      "loss": 0.606,
      "step": 610
    },
    {
      "epoch": 1.8152889539136796,
      "grad_norm": 0.3228193342410931,
      "learning_rate": 5e-06,
      "loss": 0.6064,
      "step": 620
    },
    {
      "epoch": 1.8445501097293344,
      "grad_norm": 0.35917298085170585,
      "learning_rate": 5e-06,
      "loss": 0.6055,
      "step": 630
    },
    {
      "epoch": 1.873811265544989,
      "grad_norm": 0.3266610800239347,
      "learning_rate": 5e-06,
      "loss": 0.6003,
      "step": 640
    },
    {
      "epoch": 1.9030724213606436,
      "grad_norm": 0.3663755934667714,
      "learning_rate": 5e-06,
      "loss": 0.606,
      "step": 650
    },
    {
      "epoch": 1.9323335771762986,
      "grad_norm": 0.3377853190846914,
      "learning_rate": 5e-06,
      "loss": 0.6065,
      "step": 660
    },
    {
      "epoch": 1.9615947329919532,
      "grad_norm": 0.3309604588866561,
      "learning_rate": 5e-06,
      "loss": 0.5954,
      "step": 670
    },
    {
      "epoch": 1.9908558888076078,
      "grad_norm": 0.3506238935132811,
      "learning_rate": 5e-06,
      "loss": 0.6098,
      "step": 680
    },
    {
      "epoch": 1.9967081199707388,
      "eval_loss": 0.6332589387893677,
      "eval_runtime": 344.3907,
      "eval_samples_per_second": 26.74,
      "eval_steps_per_second": 0.418,
      "step": 682
    },
    {
      "epoch": 2.0212143379663496,
      "grad_norm": 0.38883682801871317,
      "learning_rate": 5e-06,
      "loss": 0.6199,
      "step": 690
    },
    {
      "epoch": 2.050475493782004,
      "grad_norm": 0.4419278583439316,
      "learning_rate": 5e-06,
      "loss": 0.5676,
      "step": 700
    },
    {
      "epoch": 2.0797366495976592,
      "grad_norm": 0.35170054794891586,
      "learning_rate": 5e-06,
      "loss": 0.5696,
      "step": 710
    },
    {
      "epoch": 2.108997805413314,
      "grad_norm": 0.3754626962728891,
      "learning_rate": 5e-06,
      "loss": 0.5706,
      "step": 720
    },
    {
      "epoch": 2.1382589612289684,
      "grad_norm": 0.34912008172674025,
      "learning_rate": 5e-06,
      "loss": 0.5725,
      "step": 730
    },
    {
      "epoch": 2.1675201170446234,
      "grad_norm": 0.3477889316265806,
      "learning_rate": 5e-06,
      "loss": 0.5777,
      "step": 740
    },
    {
      "epoch": 2.196781272860278,
      "grad_norm": 0.3159196077934605,
      "learning_rate": 5e-06,
      "loss": 0.5765,
      "step": 750
    },
    {
      "epoch": 2.2260424286759326,
      "grad_norm": 0.36710603345755066,
      "learning_rate": 5e-06,
      "loss": 0.5739,
      "step": 760
    },
    {
      "epoch": 2.255303584491587,
      "grad_norm": 0.3287401830878657,
      "learning_rate": 5e-06,
      "loss": 0.5727,
      "step": 770
    },
    {
      "epoch": 2.284564740307242,
      "grad_norm": 0.3338056309536922,
      "learning_rate": 5e-06,
      "loss": 0.5718,
      "step": 780
    },
    {
      "epoch": 2.313825896122897,
      "grad_norm": 0.3284098603353004,
      "learning_rate": 5e-06,
      "loss": 0.5701,
      "step": 790
    },
    {
      "epoch": 2.3430870519385514,
      "grad_norm": 0.3604858195175541,
      "learning_rate": 5e-06,
      "loss": 0.5779,
      "step": 800
    },
    {
      "epoch": 2.3723482077542064,
      "grad_norm": 0.3372639613027786,
      "learning_rate": 5e-06,
      "loss": 0.573,
      "step": 810
    },
    {
      "epoch": 2.401609363569861,
      "grad_norm": 0.33077310241977137,
      "learning_rate": 5e-06,
      "loss": 0.5793,
      "step": 820
    },
    {
      "epoch": 2.4308705193855156,
      "grad_norm": 0.317174042992232,
      "learning_rate": 5e-06,
      "loss": 0.5716,
      "step": 830
    },
    {
      "epoch": 2.4601316752011706,
      "grad_norm": 0.35720787387470887,
      "learning_rate": 5e-06,
      "loss": 0.572,
      "step": 840
    },
    {
      "epoch": 2.489392831016825,
      "grad_norm": 0.34716951034356963,
      "learning_rate": 5e-06,
      "loss": 0.5743,
      "step": 850
    },
    {
      "epoch": 2.5186539868324798,
      "grad_norm": 0.3548928579154118,
      "learning_rate": 5e-06,
      "loss": 0.5673,
      "step": 860
    },
    {
      "epoch": 2.547915142648135,
      "grad_norm": 0.39809013054159753,
      "learning_rate": 5e-06,
      "loss": 0.5698,
      "step": 870
    },
    {
      "epoch": 2.5771762984637894,
      "grad_norm": 0.34975749471054834,
      "learning_rate": 5e-06,
      "loss": 0.574,
      "step": 880
    },
    {
      "epoch": 2.606437454279444,
      "grad_norm": 0.3597960490980802,
      "learning_rate": 5e-06,
      "loss": 0.5733,
      "step": 890
    },
    {
      "epoch": 2.6356986100950985,
      "grad_norm": 0.3387827525529806,
      "learning_rate": 5e-06,
      "loss": 0.5779,
      "step": 900
    },
    {
      "epoch": 2.6649597659107536,
      "grad_norm": 0.3595617862544763,
      "learning_rate": 5e-06,
      "loss": 0.578,
      "step": 910
    },
    {
      "epoch": 2.694220921726408,
      "grad_norm": 0.35719839432443745,
      "learning_rate": 5e-06,
      "loss": 0.5724,
      "step": 920
    },
    {
      "epoch": 2.723482077542063,
      "grad_norm": 0.352313951049118,
      "learning_rate": 5e-06,
      "loss": 0.576,
      "step": 930
    },
    {
      "epoch": 2.7527432333577178,
      "grad_norm": 0.34939286466829683,
      "learning_rate": 5e-06,
      "loss": 0.575,
      "step": 940
    },
    {
      "epoch": 2.7820043891733723,
      "grad_norm": 0.34251101062213785,
      "learning_rate": 5e-06,
      "loss": 0.5737,
      "step": 950
    },
    {
      "epoch": 2.811265544989027,
      "grad_norm": 0.3751942224920435,
      "learning_rate": 5e-06,
      "loss": 0.5776,
      "step": 960
    },
    {
      "epoch": 2.840526700804682,
      "grad_norm": 0.34536278066429604,
      "learning_rate": 5e-06,
      "loss": 0.5733,
      "step": 970
    },
    {
      "epoch": 2.8697878566203365,
      "grad_norm": 0.3744437847623413,
      "learning_rate": 5e-06,
      "loss": 0.5731,
      "step": 980
    },
    {
      "epoch": 2.899049012435991,
      "grad_norm": 0.32468861500765744,
      "learning_rate": 5e-06,
      "loss": 0.5661,
      "step": 990
    },
    {
      "epoch": 2.928310168251646,
      "grad_norm": 0.32492564537112933,
      "learning_rate": 5e-06,
      "loss": 0.5739,
      "step": 1000
    },
    {
      "epoch": 2.9575713240673007,
      "grad_norm": 0.3516943430167048,
      "learning_rate": 5e-06,
      "loss": 0.5656,
      "step": 1010
    },
    {
      "epoch": 2.9868324798829553,
      "grad_norm": 0.3370882708288318,
      "learning_rate": 5e-06,
      "loss": 0.5773,
      "step": 1020
    },
    {
      "epoch": 2.9956108266276518,
      "eval_loss": 0.6331183314323425,
      "eval_runtime": 344.6885,
      "eval_samples_per_second": 26.717,
      "eval_steps_per_second": 0.418,
      "step": 1023
    },
    {
      "epoch": 2.9956108266276518,
      "step": 1023,
      "total_flos": 2144987064041472.0,
      "train_loss": 0.614284630744688,
      "train_runtime": 55138.6251,
      "train_samples_per_second": 9.519,
      "train_steps_per_second": 0.019
    }
  ],
  "logging_steps": 10,
  "max_steps": 1023,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2144987064041472.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}