{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.988009592326139,
  "eval_steps": 200,
  "global_step": 624,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.047961630695443645,
      "grad_norm": 0.48529842495918274,
      "learning_rate": 5.625e-06,
      "loss": 2.5422,
      "step": 10
    },
    {
      "epoch": 0.09592326139088729,
      "grad_norm": 0.5231515169143677,
      "learning_rate": 1.1875e-05,
      "loss": 2.4974,
      "step": 20
    },
    {
      "epoch": 0.14388489208633093,
      "grad_norm": 0.4471396803855896,
      "learning_rate": 1.8125e-05,
      "loss": 2.4382,
      "step": 30
    },
    {
      "epoch": 0.19184652278177458,
      "grad_norm": 0.250693142414093,
      "learning_rate": 1.999310121715203e-05,
      "loss": 2.3647,
      "step": 40
    },
    {
      "epoch": 0.23980815347721823,
      "grad_norm": 0.2678900361061096,
      "learning_rate": 1.9959334172857852e-05,
      "loss": 2.2756,
      "step": 50
    },
    {
      "epoch": 0.28776978417266186,
      "grad_norm": 0.24975475668907166,
      "learning_rate": 1.9897526695650458e-05,
      "loss": 2.2132,
      "step": 60
    },
    {
      "epoch": 0.33573141486810554,
      "grad_norm": 0.25826334953308105,
      "learning_rate": 1.9807852804032306e-05,
      "loss": 2.1933,
      "step": 70
    },
    {
      "epoch": 0.38369304556354916,
      "grad_norm": 0.28782331943511963,
      "learning_rate": 1.9690564974192893e-05,
      "loss": 2.1697,
      "step": 80
    },
    {
      "epoch": 0.4316546762589928,
      "grad_norm": 0.35406047105789185,
      "learning_rate": 1.9545993429163913e-05,
      "loss": 2.1666,
      "step": 90
    },
    {
      "epoch": 0.47961630695443647,
      "grad_norm": 0.4792511463165283,
      "learning_rate": 1.9374545209078687e-05,
      "loss": 2.1381,
      "step": 100
    },
    {
      "epoch": 0.5275779376498801,
      "grad_norm": 0.5407695174217224,
      "learning_rate": 1.9176703025153643e-05,
      "loss": 2.1527,
      "step": 110
    },
    {
      "epoch": 0.5755395683453237,
      "grad_norm": 0.6309888362884521,
      "learning_rate": 1.8953023900618395e-05,
      "loss": 2.0777,
      "step": 120
    },
    {
      "epoch": 0.6235011990407674,
      "grad_norm": 0.34664326906204224,
      "learning_rate": 1.870413760242089e-05,
      "loss": 2.0752,
      "step": 130
    },
    {
      "epoch": 0.6714628297362111,
      "grad_norm": 0.25117745995521545,
      "learning_rate": 1.8430744868123146e-05,
      "loss": 2.0563,
      "step": 140
    },
    {
      "epoch": 0.7194244604316546,
      "grad_norm": 0.38084152340888977,
      "learning_rate": 1.8133615432979742e-05,
      "loss": 2.0572,
      "step": 150
    },
    {
      "epoch": 0.7673860911270983,
      "grad_norm": 0.4128628075122833,
      "learning_rate": 1.7813585862753832e-05,
      "loss": 2.0694,
      "step": 160
    },
    {
      "epoch": 0.815347721822542,
      "grad_norm": 0.2934734523296356,
      "learning_rate": 1.7471557198372277e-05,
      "loss": 2.0339,
      "step": 170
    },
    {
      "epoch": 0.8633093525179856,
      "grad_norm": 0.31436148285865784,
      "learning_rate": 1.710849241905151e-05,
      "loss": 2.0482,
      "step": 180
    },
    {
      "epoch": 0.9112709832134293,
      "grad_norm": 0.3247852623462677,
      "learning_rate": 1.6725413731036562e-05,
      "loss": 2.0122,
      "step": 190
    },
    {
      "epoch": 0.9592326139088729,
      "grad_norm": 0.29776260256767273,
      "learning_rate": 1.632339968958677e-05,
      "loss": 2.0158,
      "step": 200
    },
    {
      "epoch": 1.0047961630695443,
      "grad_norm": 0.44077572226524353,
      "learning_rate": 1.590358216231134e-05,
      "loss": 2.0056,
      "step": 210
    },
    {
      "epoch": 1.052757793764988,
      "grad_norm": 0.31072619557380676,
      "learning_rate": 1.546714314240429e-05,
      "loss": 2.0118,
      "step": 220
    },
    {
      "epoch": 1.1007194244604317,
      "grad_norm": 0.4204866588115692,
      "learning_rate": 1.5015311420751243e-05,
      "loss": 1.9779,
      "step": 230
    },
    {
      "epoch": 1.1486810551558753,
      "grad_norm": 0.38263222575187683,
      "learning_rate": 1.454935912627761e-05,
      "loss": 1.969,
      "step": 240
    },
    {
      "epoch": 1.196642685851319,
      "grad_norm": 0.3890452980995178,
      "learning_rate": 1.407059814427884e-05,
      "loss": 1.9723,
      "step": 250
    },
    {
      "epoch": 1.2446043165467626,
      "grad_norm": 0.4386310875415802,
      "learning_rate": 1.3580376422816945e-05,
      "loss": 1.9566,
      "step": 260
    },
    {
      "epoch": 1.2925659472422062,
      "grad_norm": 0.41672301292419434,
      "learning_rate": 1.3080074177582527e-05,
      "loss": 1.9365,
      "step": 270
    },
    {
      "epoch": 1.34052757793765,
      "grad_norm": 0.45278477668762207,
      "learning_rate": 1.2571100005907522e-05,
      "loss": 1.9445,
      "step": 280
    },
    {
      "epoch": 1.3884892086330936,
      "grad_norm": 0.4160229563713074,
      "learning_rate": 1.2054886920869682e-05,
      "loss": 1.9696,
      "step": 290
    },
    {
      "epoch": 1.4364508393285371,
      "grad_norm": 0.46161898970603943,
      "learning_rate": 1.1532888316654675e-05,
      "loss": 1.9435,
      "step": 300
    },
    {
      "epoch": 1.484412470023981,
      "grad_norm": 0.4921852648258209,
      "learning_rate": 1.1006573876535322e-05,
      "loss": 1.9428,
      "step": 310
    },
    {
      "epoch": 1.5323741007194245,
      "grad_norm": 0.5233998894691467,
      "learning_rate": 1.0477425434989038e-05,
      "loss": 1.9241,
      "step": 320
    },
    {
      "epoch": 1.580335731414868,
      "grad_norm": 0.5583417415618896,
      "learning_rate": 9.946932805603635e-06,
      "loss": 1.9444,
      "step": 330
    },
    {
      "epoch": 1.6282973621103118,
      "grad_norm": 0.48175185918807983,
      "learning_rate": 9.416589586518009e-06,
      "loss": 1.8964,
      "step": 340
    },
    {
      "epoch": 1.6762589928057554,
      "grad_norm": 0.5539340376853943,
      "learning_rate": 8.887888955207444e-06,
      "loss": 1.894,
      "step": 350
    },
    {
      "epoch": 1.724220623501199,
      "grad_norm": 0.5731947422027588,
      "learning_rate": 8.362319464453301e-06,
      "loss": 1.9005,
      "step": 360
    },
    {
      "epoch": 1.7721822541966428,
      "grad_norm": 0.6053941249847412,
      "learning_rate": 7.84136085133347e-06,
      "loss": 1.8858,
      "step": 370
    },
    {
      "epoch": 1.8201438848920863,
      "grad_norm": 0.6071736812591553,
      "learning_rate": 7.326479871033408e-06,
      "loss": 1.8869,
      "step": 380
    },
    {
      "epoch": 1.86810551558753,
      "grad_norm": 0.6168338060379028,
      "learning_rate": 6.819126167207586e-06,
      "loss": 1.8783,
      "step": 390
    },
    {
      "epoch": 1.9160671462829737,
      "grad_norm": 0.697503387928009,
      "learning_rate": 6.320728190518308e-06,
      "loss": 1.8764,
      "step": 400
    },
    {
      "epoch": 1.9640287769784173,
      "grad_norm": 0.6182295680046082,
      "learning_rate": 5.832689176843291e-06,
      "loss": 1.865,
      "step": 410
    },
    {
      "epoch": 2.0095923261390887,
      "grad_norm": 0.5304880738258362,
      "learning_rate": 5.356383196475226e-06,
      "loss": 1.879,
      "step": 420
    },
    {
      "epoch": 2.0575539568345325,
      "grad_norm": 0.5878423452377319,
      "learning_rate": 4.893151285436891e-06,
      "loss": 1.8399,
      "step": 430
    },
    {
      "epoch": 2.105515587529976,
      "grad_norm": 0.6464638710021973,
      "learning_rate": 4.444297669803981e-06,
      "loss": 1.8491,
      "step": 440
    },
    {
      "epoch": 2.1534772182254196,
      "grad_norm": 0.6010664701461792,
      "learning_rate": 4.011086093666057e-06,
      "loss": 1.8552,
      "step": 450
    },
    {
      "epoch": 2.2014388489208634,
      "grad_norm": 0.6692630052566528,
      "learning_rate": 3.5947362610642854e-06,
      "loss": 1.8616,
      "step": 460
    },
    {
      "epoch": 2.249400479616307,
      "grad_norm": 0.6113582849502563,
      "learning_rate": 3.196420401923567e-06,
      "loss": 1.8552,
      "step": 470
    },
    {
      "epoch": 2.2973621103117505,
      "grad_norm": 0.6936492919921875,
      "learning_rate": 2.8172599716477145e-06,
      "loss": 1.8145,
      "step": 480
    },
    {
      "epoch": 2.3453237410071943,
      "grad_norm": 0.6148903369903564,
      "learning_rate": 2.458322493669911e-06,
      "loss": 1.8115,
      "step": 490
    },
    {
      "epoch": 2.393285371702638,
      "grad_norm": 0.679800808429718,
      "learning_rate": 2.1206185538482704e-06,
      "loss": 1.8344,
      "step": 500
    },
    {
      "epoch": 2.4412470023980815,
      "grad_norm": 0.6589268445968628,
      "learning_rate": 1.8050989551686915e-06,
      "loss": 1.8587,
      "step": 510
    },
    {
      "epoch": 2.4892086330935252,
      "grad_norm": 0.7750632166862488,
      "learning_rate": 1.5126520407659618e-06,
      "loss": 1.8445,
      "step": 520
    },
    {
      "epoch": 2.537170263788969,
      "grad_norm": 0.89366215467453,
      "learning_rate": 1.2441011928001435e-06,
      "loss": 1.8361,
      "step": 530
    },
    {
      "epoch": 2.5851318944844124,
      "grad_norm": 0.6380264163017273,
      "learning_rate": 1.0002025142300764e-06,
      "loss": 1.8379,
      "step": 540
    },
    {
      "epoch": 2.633093525179856,
      "grad_norm": 0.7115680575370789,
      "learning_rate": 7.816427000110016e-07,
      "loss": 1.8221,
      "step": 550
    },
    {
      "epoch": 2.6810551558753,
      "grad_norm": 0.6720678806304932,
      "learning_rate": 5.890371037099107e-07,
      "loss": 1.8332,
      "step": 560
    },
    {
      "epoch": 2.7290167865707433,
      "grad_norm": 0.6737195253372192,
      "learning_rate": 4.229280049820561e-07,
      "loss": 1.8309,
      "step": 570
    },
    {
      "epoch": 2.776978417266187,
      "grad_norm": 0.7314239144325256,
      "learning_rate": 2.837830827865229e-07,
      "loss": 1.8679,
      "step": 580
    },
    {
      "epoch": 2.824940047961631,
      "grad_norm": 0.6641331911087036,
      "learning_rate": 1.719940986395252e-07,
      "loss": 1.8305,
      "step": 590
    },
    {
      "epoch": 2.8729016786570742,
      "grad_norm": 0.8098570108413696,
      "learning_rate": 8.787579361270616e-08,
      "loss": 1.8158,
      "step": 600
    },
    {
      "epoch": 2.920863309352518,
      "grad_norm": 0.6149157881736755,
      "learning_rate": 3.1665002181937575e-08,
      "loss": 1.8446,
      "step": 610
    },
    {
      "epoch": 2.968824940047962,
      "grad_norm": 0.6571503281593323,
      "learning_rate": 3.5199854215817176e-09,
      "loss": 1.8486,
      "step": 620
    }
  ],
  "logging_steps": 10,
  "max_steps": 624,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.071044597856338e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}