{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.992616899097621,
  "eval_steps": 500,
  "global_step": 912,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03281378178835111,
      "grad_norm": 7.841750232611161,
      "learning_rate": 5e-06,
      "loss": 0.8915,
      "step": 10
    },
    {
      "epoch": 0.06562756357670221,
      "grad_norm": 2.8254265829702723,
      "learning_rate": 5e-06,
      "loss": 0.7744,
      "step": 20
    },
    {
      "epoch": 0.09844134536505332,
      "grad_norm": 1.2137270648230942,
      "learning_rate": 5e-06,
      "loss": 0.7284,
      "step": 30
    },
    {
      "epoch": 0.13125512715340443,
      "grad_norm": 1.0119344856669166,
      "learning_rate": 5e-06,
      "loss": 0.7015,
      "step": 40
    },
    {
      "epoch": 0.16406890894175555,
      "grad_norm": 1.1590120587560695,
      "learning_rate": 5e-06,
      "loss": 0.6751,
      "step": 50
    },
    {
      "epoch": 0.19688269073010664,
      "grad_norm": 1.0688354918846648,
      "learning_rate": 5e-06,
      "loss": 0.6539,
      "step": 60
    },
    {
      "epoch": 0.22969647251845776,
      "grad_norm": 0.7962599254830892,
      "learning_rate": 5e-06,
      "loss": 0.6416,
      "step": 70
    },
    {
      "epoch": 0.26251025430680885,
      "grad_norm": 1.3016899088803453,
      "learning_rate": 5e-06,
      "loss": 0.6401,
      "step": 80
    },
    {
      "epoch": 0.29532403609515995,
      "grad_norm": 0.8330196899066211,
      "learning_rate": 5e-06,
      "loss": 0.618,
      "step": 90
    },
    {
      "epoch": 0.3281378178835111,
      "grad_norm": 0.667189033403046,
      "learning_rate": 5e-06,
      "loss": 0.6196,
      "step": 100
    },
    {
      "epoch": 0.3609515996718622,
      "grad_norm": 0.7289539260596677,
      "learning_rate": 5e-06,
      "loss": 0.6297,
      "step": 110
    },
    {
      "epoch": 0.3937653814602133,
      "grad_norm": 0.6409803463860579,
      "learning_rate": 5e-06,
      "loss": 0.6216,
      "step": 120
    },
    {
      "epoch": 0.4265791632485644,
      "grad_norm": 0.70735959118925,
      "learning_rate": 5e-06,
      "loss": 0.6092,
      "step": 130
    },
    {
      "epoch": 0.4593929450369155,
      "grad_norm": 0.8142813291097145,
      "learning_rate": 5e-06,
      "loss": 0.6024,
      "step": 140
    },
    {
      "epoch": 0.4922067268252666,
      "grad_norm": 0.6426092966393037,
      "learning_rate": 5e-06,
      "loss": 0.6028,
      "step": 150
    },
    {
      "epoch": 0.5250205086136177,
      "grad_norm": 0.9814251564680376,
      "learning_rate": 5e-06,
      "loss": 0.6042,
      "step": 160
    },
    {
      "epoch": 0.5578342904019689,
      "grad_norm": 0.601307551623306,
      "learning_rate": 5e-06,
      "loss": 0.6047,
      "step": 170
    },
    {
      "epoch": 0.5906480721903199,
      "grad_norm": 0.5895692038996282,
      "learning_rate": 5e-06,
      "loss": 0.5936,
      "step": 180
    },
    {
      "epoch": 0.623461853978671,
      "grad_norm": 0.5348923163508846,
      "learning_rate": 5e-06,
      "loss": 0.5906,
      "step": 190
    },
    {
      "epoch": 0.6562756357670222,
      "grad_norm": 0.6710759767714962,
      "learning_rate": 5e-06,
      "loss": 0.5863,
      "step": 200
    },
    {
      "epoch": 0.6890894175553732,
      "grad_norm": 0.5530954428148116,
      "learning_rate": 5e-06,
      "loss": 0.5972,
      "step": 210
    },
    {
      "epoch": 0.7219031993437244,
      "grad_norm": 0.6414930112608357,
      "learning_rate": 5e-06,
      "loss": 0.5888,
      "step": 220
    },
    {
      "epoch": 0.7547169811320755,
      "grad_norm": 0.730574957468606,
      "learning_rate": 5e-06,
      "loss": 0.5913,
      "step": 230
    },
    {
      "epoch": 0.7875307629204266,
      "grad_norm": 0.8034131557047212,
      "learning_rate": 5e-06,
      "loss": 0.5849,
      "step": 240
    },
    {
      "epoch": 0.8203445447087777,
      "grad_norm": 0.6772004609931918,
      "learning_rate": 5e-06,
      "loss": 0.5904,
      "step": 250
    },
    {
      "epoch": 0.8531583264971287,
      "grad_norm": 0.5963848396035898,
      "learning_rate": 5e-06,
      "loss": 0.5814,
      "step": 260
    },
    {
      "epoch": 0.8859721082854799,
      "grad_norm": 0.8533728487617155,
      "learning_rate": 5e-06,
      "loss": 0.5926,
      "step": 270
    },
    {
      "epoch": 0.918785890073831,
      "grad_norm": 0.6929371502886701,
      "learning_rate": 5e-06,
      "loss": 0.584,
      "step": 280
    },
    {
      "epoch": 0.9515996718621821,
      "grad_norm": 1.0646930858335608,
      "learning_rate": 5e-06,
      "loss": 0.583,
      "step": 290
    },
    {
      "epoch": 0.9844134536505332,
      "grad_norm": 0.657886516351812,
      "learning_rate": 5e-06,
      "loss": 0.5822,
      "step": 300
    },
    {
      "epoch": 0.9975389663658737,
      "eval_loss": 0.5811063051223755,
      "eval_runtime": 164.1949,
      "eval_samples_per_second": 49.989,
      "eval_steps_per_second": 0.396,
      "step": 304
    },
    {
      "epoch": 1.0172272354388843,
      "grad_norm": 0.9145633972949372,
      "learning_rate": 5e-06,
      "loss": 0.5615,
      "step": 310
    },
    {
      "epoch": 1.0500410172272354,
      "grad_norm": 0.8330439338358776,
      "learning_rate": 5e-06,
      "loss": 0.5501,
      "step": 320
    },
    {
      "epoch": 1.0828547990155866,
      "grad_norm": 0.9017808771885161,
      "learning_rate": 5e-06,
      "loss": 0.5397,
      "step": 330
    },
    {
      "epoch": 1.1156685808039377,
      "grad_norm": 0.7658877957248926,
      "learning_rate": 5e-06,
      "loss": 0.543,
      "step": 340
    },
    {
      "epoch": 1.1484823625922886,
      "grad_norm": 0.559631564116058,
      "learning_rate": 5e-06,
      "loss": 0.5402,
      "step": 350
    },
    {
      "epoch": 1.1812961443806398,
      "grad_norm": 0.7555936047357931,
      "learning_rate": 5e-06,
      "loss": 0.5424,
      "step": 360
    },
    {
      "epoch": 1.214109926168991,
      "grad_norm": 0.7751086823302814,
      "learning_rate": 5e-06,
      "loss": 0.5338,
      "step": 370
    },
    {
      "epoch": 1.246923707957342,
      "grad_norm": 1.1576515759835613,
      "learning_rate": 5e-06,
      "loss": 0.5447,
      "step": 380
    },
    {
      "epoch": 1.2797374897456932,
      "grad_norm": 0.637673440804281,
      "learning_rate": 5e-06,
      "loss": 0.5436,
      "step": 390
    },
    {
      "epoch": 1.3125512715340442,
      "grad_norm": 0.5608427930549431,
      "learning_rate": 5e-06,
      "loss": 0.538,
      "step": 400
    },
    {
      "epoch": 1.3453650533223955,
      "grad_norm": 0.6236715534816973,
      "learning_rate": 5e-06,
      "loss": 0.5401,
      "step": 410
    },
    {
      "epoch": 1.3781788351107465,
      "grad_norm": 0.6834154815439046,
      "learning_rate": 5e-06,
      "loss": 0.5371,
      "step": 420
    },
    {
      "epoch": 1.4109926168990976,
      "grad_norm": 0.6230411253152371,
      "learning_rate": 5e-06,
      "loss": 0.5396,
      "step": 430
    },
    {
      "epoch": 1.4438063986874488,
      "grad_norm": 0.5735284718821723,
      "learning_rate": 5e-06,
      "loss": 0.546,
      "step": 440
    },
    {
      "epoch": 1.4766201804758,
      "grad_norm": 0.6777341683980052,
      "learning_rate": 5e-06,
      "loss": 0.5312,
      "step": 450
    },
    {
      "epoch": 1.509433962264151,
      "grad_norm": 0.6145373481418245,
      "learning_rate": 5e-06,
      "loss": 0.5363,
      "step": 460
    },
    {
      "epoch": 1.542247744052502,
      "grad_norm": 0.6691485262612896,
      "learning_rate": 5e-06,
      "loss": 0.5405,
      "step": 470
    },
    {
      "epoch": 1.5750615258408531,
      "grad_norm": 0.6278473705145111,
      "learning_rate": 5e-06,
      "loss": 0.5336,
      "step": 480
    },
    {
      "epoch": 1.6078753076292043,
      "grad_norm": 0.7195303747825454,
      "learning_rate": 5e-06,
      "loss": 0.5456,
      "step": 490
    },
    {
      "epoch": 1.6406890894175554,
      "grad_norm": 0.6993265245998453,
      "learning_rate": 5e-06,
      "loss": 0.526,
      "step": 500
    },
    {
      "epoch": 1.6735028712059066,
      "grad_norm": 0.5569198466336033,
      "learning_rate": 5e-06,
      "loss": 0.5437,
      "step": 510
    },
    {
      "epoch": 1.7063166529942575,
      "grad_norm": 0.5962729727283363,
      "learning_rate": 5e-06,
      "loss": 0.54,
      "step": 520
    },
    {
      "epoch": 1.7391304347826086,
      "grad_norm": 0.5528562495704502,
      "learning_rate": 5e-06,
      "loss": 0.5348,
      "step": 530
    },
    {
      "epoch": 1.7719442165709598,
      "grad_norm": 0.5117801135768556,
      "learning_rate": 5e-06,
      "loss": 0.5354,
      "step": 540
    },
    {
      "epoch": 1.804757998359311,
      "grad_norm": 0.6270359146501516,
      "learning_rate": 5e-06,
      "loss": 0.5405,
      "step": 550
    },
    {
      "epoch": 1.837571780147662,
      "grad_norm": 0.49991108374112964,
      "learning_rate": 5e-06,
      "loss": 0.5311,
      "step": 560
    },
    {
      "epoch": 1.870385561936013,
      "grad_norm": 0.8786052238787824,
      "learning_rate": 5e-06,
      "loss": 0.5276,
      "step": 570
    },
    {
      "epoch": 1.9031993437243644,
      "grad_norm": 0.5526276905535635,
      "learning_rate": 5e-06,
      "loss": 0.5303,
      "step": 580
    },
    {
      "epoch": 1.9360131255127153,
      "grad_norm": 0.6424736342148375,
      "learning_rate": 5e-06,
      "loss": 0.5378,
      "step": 590
    },
    {
      "epoch": 1.9688269073010665,
      "grad_norm": 0.4985928762767277,
      "learning_rate": 5e-06,
      "loss": 0.5331,
      "step": 600
    },
    {
      "epoch": 1.9983593109105824,
      "eval_loss": 0.5679268836975098,
      "eval_runtime": 165.1141,
      "eval_samples_per_second": 49.711,
      "eval_steps_per_second": 0.394,
      "step": 609
    },
    {
      "epoch": 2.0016406890894176,
      "grad_norm": 0.8535377767409578,
      "learning_rate": 5e-06,
      "loss": 0.5258,
      "step": 610
    },
    {
      "epoch": 2.0344544708777685,
      "grad_norm": 0.8392464205497018,
      "learning_rate": 5e-06,
      "loss": 0.4982,
      "step": 620
    },
    {
      "epoch": 2.06726825266612,
      "grad_norm": 0.6991396805774981,
      "learning_rate": 5e-06,
      "loss": 0.4856,
      "step": 630
    },
    {
      "epoch": 2.100082034454471,
      "grad_norm": 0.6363700778523905,
      "learning_rate": 5e-06,
      "loss": 0.49,
      "step": 640
    },
    {
      "epoch": 2.132895816242822,
      "grad_norm": 0.6689991208530507,
      "learning_rate": 5e-06,
      "loss": 0.49,
      "step": 650
    },
    {
      "epoch": 2.165709598031173,
      "grad_norm": 0.5725274111655418,
      "learning_rate": 5e-06,
      "loss": 0.4926,
      "step": 660
    },
    {
      "epoch": 2.198523379819524,
      "grad_norm": 0.8141370837443801,
      "learning_rate": 5e-06,
      "loss": 0.4876,
      "step": 670
    },
    {
      "epoch": 2.2313371616078754,
      "grad_norm": 0.6282724145860844,
      "learning_rate": 5e-06,
      "loss": 0.4878,
      "step": 680
    },
    {
      "epoch": 2.2641509433962264,
      "grad_norm": 0.6530073663418564,
      "learning_rate": 5e-06,
      "loss": 0.4944,
      "step": 690
    },
    {
      "epoch": 2.2969647251845773,
      "grad_norm": 0.5699233164866262,
      "learning_rate": 5e-06,
      "loss": 0.4966,
      "step": 700
    },
    {
      "epoch": 2.3297785069729287,
      "grad_norm": 0.610417793848035,
      "learning_rate": 5e-06,
      "loss": 0.49,
      "step": 710
    },
    {
      "epoch": 2.3625922887612796,
      "grad_norm": 0.6289268935164573,
      "learning_rate": 5e-06,
      "loss": 0.5036,
      "step": 720
    },
    {
      "epoch": 2.395406070549631,
      "grad_norm": 0.6537483086050372,
      "learning_rate": 5e-06,
      "loss": 0.4927,
      "step": 730
    },
    {
      "epoch": 2.428219852337982,
      "grad_norm": 0.6648368643526823,
      "learning_rate": 5e-06,
      "loss": 0.4983,
      "step": 740
    },
    {
      "epoch": 2.4610336341263332,
      "grad_norm": 0.6722645125843071,
      "learning_rate": 5e-06,
      "loss": 0.4949,
      "step": 750
    },
    {
      "epoch": 2.493847415914684,
      "grad_norm": 0.5717762614134606,
      "learning_rate": 5e-06,
      "loss": 0.5014,
      "step": 760
    },
    {
      "epoch": 2.526661197703035,
      "grad_norm": 0.6732475102422392,
      "learning_rate": 5e-06,
      "loss": 0.4978,
      "step": 770
    },
    {
      "epoch": 2.5594749794913865,
      "grad_norm": 0.6176484271038984,
      "learning_rate": 5e-06,
      "loss": 0.4969,
      "step": 780
    },
    {
      "epoch": 2.5922887612797374,
      "grad_norm": 0.5794899161431503,
      "learning_rate": 5e-06,
      "loss": 0.497,
      "step": 790
    },
    {
      "epoch": 2.6251025430680883,
      "grad_norm": 0.6254525725000455,
      "learning_rate": 5e-06,
      "loss": 0.4881,
      "step": 800
    },
    {
      "epoch": 2.6579163248564397,
      "grad_norm": 0.4997430504095228,
      "learning_rate": 5e-06,
      "loss": 0.4986,
      "step": 810
    },
    {
      "epoch": 2.690730106644791,
      "grad_norm": 0.6452212092676007,
      "learning_rate": 5e-06,
      "loss": 0.4937,
      "step": 820
    },
    {
      "epoch": 2.723543888433142,
      "grad_norm": 0.6248001192436421,
      "learning_rate": 5e-06,
      "loss": 0.5017,
      "step": 830
    },
    {
      "epoch": 2.756357670221493,
      "grad_norm": 0.5729926597313496,
      "learning_rate": 5e-06,
      "loss": 0.4997,
      "step": 840
    },
    {
      "epoch": 2.7891714520098443,
      "grad_norm": 0.6322042992676079,
      "learning_rate": 5e-06,
      "loss": 0.4975,
      "step": 850
    },
    {
      "epoch": 2.821985233798195,
      "grad_norm": 0.6001289917677007,
      "learning_rate": 5e-06,
      "loss": 0.4932,
      "step": 860
    },
    {
      "epoch": 2.854799015586546,
      "grad_norm": 0.6372644243152534,
      "learning_rate": 5e-06,
      "loss": 0.5005,
      "step": 870
    },
    {
      "epoch": 2.8876127973748975,
      "grad_norm": 0.6486605042735685,
      "learning_rate": 5e-06,
      "loss": 0.4996,
      "step": 880
    },
    {
      "epoch": 2.9204265791632484,
      "grad_norm": 0.5285905512046695,
      "learning_rate": 5e-06,
      "loss": 0.5018,
      "step": 890
    },
    {
      "epoch": 2.9532403609516,
      "grad_norm": 0.6212025899780993,
      "learning_rate": 5e-06,
      "loss": 0.4993,
      "step": 900
    },
    {
      "epoch": 2.9860541427399507,
      "grad_norm": 0.6141734836175889,
      "learning_rate": 5e-06,
      "loss": 0.4973,
      "step": 910
    },
    {
      "epoch": 2.992616899097621,
      "eval_loss": 0.5682421326637268,
      "eval_runtime": 165.8526,
      "eval_samples_per_second": 49.49,
      "eval_steps_per_second": 0.392,
      "step": 912
    },
    {
      "epoch": 2.992616899097621,
      "step": 912,
      "total_flos": 1527215208529920.0,
      "train_loss": 0.5539279884021533,
      "train_runtime": 27411.4767,
      "train_samples_per_second": 17.066,
      "train_steps_per_second": 0.033
    }
  ],
  "logging_steps": 10,
  "max_steps": 912,
  "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": 1527215208529920.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}