{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 867,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03460207612456748,
      "grad_norm": 5.743846893310547,
      "learning_rate": 5e-06,
      "loss": 0.9289,
      "step": 10
    },
    {
      "epoch": 0.06920415224913495,
      "grad_norm": 5.331993103027344,
      "learning_rate": 5e-06,
      "loss": 0.8126,
      "step": 20
    },
    {
      "epoch": 0.10380622837370242,
      "grad_norm": 5.425512790679932,
      "learning_rate": 5e-06,
      "loss": 0.7742,
      "step": 30
    },
    {
      "epoch": 0.1384083044982699,
      "grad_norm": 1.6510249376296997,
      "learning_rate": 5e-06,
      "loss": 0.747,
      "step": 40
    },
    {
      "epoch": 0.17301038062283736,
      "grad_norm": 1.0029033422470093,
      "learning_rate": 5e-06,
      "loss": 0.7119,
      "step": 50
    },
    {
      "epoch": 0.20761245674740483,
      "grad_norm": 1.1877987384796143,
      "learning_rate": 5e-06,
      "loss": 0.688,
      "step": 60
    },
    {
      "epoch": 0.2422145328719723,
      "grad_norm": 1.0992727279663086,
      "learning_rate": 5e-06,
      "loss": 0.6709,
      "step": 70
    },
    {
      "epoch": 0.2768166089965398,
      "grad_norm": 1.0378435850143433,
      "learning_rate": 5e-06,
      "loss": 0.6633,
      "step": 80
    },
    {
      "epoch": 0.31141868512110726,
      "grad_norm": 0.7307208776473999,
      "learning_rate": 5e-06,
      "loss": 0.659,
      "step": 90
    },
    {
      "epoch": 0.3460207612456747,
      "grad_norm": 0.8541375994682312,
      "learning_rate": 5e-06,
      "loss": 0.6368,
      "step": 100
    },
    {
      "epoch": 0.3806228373702422,
      "grad_norm": 0.9289709329605103,
      "learning_rate": 5e-06,
      "loss": 0.642,
      "step": 110
    },
    {
      "epoch": 0.41522491349480967,
      "grad_norm": 0.6918668746948242,
      "learning_rate": 5e-06,
      "loss": 0.6332,
      "step": 120
    },
    {
      "epoch": 0.44982698961937717,
      "grad_norm": 0.7631871700286865,
      "learning_rate": 5e-06,
      "loss": 0.6317,
      "step": 130
    },
    {
      "epoch": 0.4844290657439446,
      "grad_norm": 0.6295446157455444,
      "learning_rate": 5e-06,
      "loss": 0.6308,
      "step": 140
    },
    {
      "epoch": 0.5190311418685121,
      "grad_norm": 0.635179340839386,
      "learning_rate": 5e-06,
      "loss": 0.6297,
      "step": 150
    },
    {
      "epoch": 0.5536332179930796,
      "grad_norm": 0.7158755660057068,
      "learning_rate": 5e-06,
      "loss": 0.6251,
      "step": 160
    },
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 0.8344781994819641,
      "learning_rate": 5e-06,
      "loss": 0.609,
      "step": 170
    },
    {
      "epoch": 0.6228373702422145,
      "grad_norm": 0.7887862324714661,
      "learning_rate": 5e-06,
      "loss": 0.6186,
      "step": 180
    },
    {
      "epoch": 0.657439446366782,
      "grad_norm": 0.7533692717552185,
      "learning_rate": 5e-06,
      "loss": 0.6201,
      "step": 190
    },
    {
      "epoch": 0.6920415224913494,
      "grad_norm": 0.7703404426574707,
      "learning_rate": 5e-06,
      "loss": 0.6176,
      "step": 200
    },
    {
      "epoch": 0.726643598615917,
      "grad_norm": 0.6667165160179138,
      "learning_rate": 5e-06,
      "loss": 0.612,
      "step": 210
    },
    {
      "epoch": 0.7612456747404844,
      "grad_norm": 0.7431259155273438,
      "learning_rate": 5e-06,
      "loss": 0.6069,
      "step": 220
    },
    {
      "epoch": 0.7958477508650519,
      "grad_norm": 0.6150693893432617,
      "learning_rate": 5e-06,
      "loss": 0.6055,
      "step": 230
    },
    {
      "epoch": 0.8304498269896193,
      "grad_norm": 1.0219345092773438,
      "learning_rate": 5e-06,
      "loss": 0.6068,
      "step": 240
    },
    {
      "epoch": 0.8650519031141869,
      "grad_norm": 0.5619581341743469,
      "learning_rate": 5e-06,
      "loss": 0.6026,
      "step": 250
    },
    {
      "epoch": 0.8996539792387543,
      "grad_norm": 0.5808368921279907,
      "learning_rate": 5e-06,
      "loss": 0.6077,
      "step": 260
    },
    {
      "epoch": 0.9342560553633218,
      "grad_norm": 0.6060568690299988,
      "learning_rate": 5e-06,
      "loss": 0.6031,
      "step": 270
    },
    {
      "epoch": 0.9688581314878892,
      "grad_norm": 0.515640139579773,
      "learning_rate": 5e-06,
      "loss": 0.6051,
      "step": 280
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.6054237484931946,
      "eval_runtime": 26.5711,
      "eval_samples_per_second": 292.988,
      "eval_steps_per_second": 1.167,
      "step": 289
    },
    {
      "epoch": 1.0034602076124568,
      "grad_norm": 1.3408666849136353,
      "learning_rate": 5e-06,
      "loss": 0.5952,
      "step": 290
    },
    {
      "epoch": 1.0380622837370241,
      "grad_norm": 1.0180834531784058,
      "learning_rate": 5e-06,
      "loss": 0.558,
      "step": 300
    },
    {
      "epoch": 1.0726643598615917,
      "grad_norm": 0.6628531217575073,
      "learning_rate": 5e-06,
      "loss": 0.5671,
      "step": 310
    },
    {
      "epoch": 1.1072664359861593,
      "grad_norm": 0.6421555876731873,
      "learning_rate": 5e-06,
      "loss": 0.5575,
      "step": 320
    },
    {
      "epoch": 1.1418685121107266,
      "grad_norm": 0.7754614353179932,
      "learning_rate": 5e-06,
      "loss": 0.5663,
      "step": 330
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 0.7297713160514832,
      "learning_rate": 5e-06,
      "loss": 0.5553,
      "step": 340
    },
    {
      "epoch": 1.2110726643598615,
      "grad_norm": 0.7665261030197144,
      "learning_rate": 5e-06,
      "loss": 0.5524,
      "step": 350
    },
    {
      "epoch": 1.245674740484429,
      "grad_norm": 0.7250308394432068,
      "learning_rate": 5e-06,
      "loss": 0.5648,
      "step": 360
    },
    {
      "epoch": 1.2802768166089966,
      "grad_norm": 0.6479423642158508,
      "learning_rate": 5e-06,
      "loss": 0.5566,
      "step": 370
    },
    {
      "epoch": 1.314878892733564,
      "grad_norm": 0.6422529220581055,
      "learning_rate": 5e-06,
      "loss": 0.5596,
      "step": 380
    },
    {
      "epoch": 1.3494809688581315,
      "grad_norm": 0.747588038444519,
      "learning_rate": 5e-06,
      "loss": 0.5566,
      "step": 390
    },
    {
      "epoch": 1.3840830449826989,
      "grad_norm": 0.6396523714065552,
      "learning_rate": 5e-06,
      "loss": 0.5582,
      "step": 400
    },
    {
      "epoch": 1.4186851211072664,
      "grad_norm": 0.6916091442108154,
      "learning_rate": 5e-06,
      "loss": 0.5611,
      "step": 410
    },
    {
      "epoch": 1.453287197231834,
      "grad_norm": 0.5232684016227722,
      "learning_rate": 5e-06,
      "loss": 0.5552,
      "step": 420
    },
    {
      "epoch": 1.4878892733564013,
      "grad_norm": 0.6718825101852417,
      "learning_rate": 5e-06,
      "loss": 0.5688,
      "step": 430
    },
    {
      "epoch": 1.5224913494809689,
      "grad_norm": 0.5741140842437744,
      "learning_rate": 5e-06,
      "loss": 0.5525,
      "step": 440
    },
    {
      "epoch": 1.5570934256055362,
      "grad_norm": 0.643785834312439,
      "learning_rate": 5e-06,
      "loss": 0.5617,
      "step": 450
    },
    {
      "epoch": 1.5916955017301038,
      "grad_norm": 0.7157655954360962,
      "learning_rate": 5e-06,
      "loss": 0.5678,
      "step": 460
    },
    {
      "epoch": 1.6262975778546713,
      "grad_norm": 0.6625480055809021,
      "learning_rate": 5e-06,
      "loss": 0.5608,
      "step": 470
    },
    {
      "epoch": 1.6608996539792389,
      "grad_norm": 0.871629536151886,
      "learning_rate": 5e-06,
      "loss": 0.5622,
      "step": 480
    },
    {
      "epoch": 1.6955017301038062,
      "grad_norm": 0.6766714453697205,
      "learning_rate": 5e-06,
      "loss": 0.5498,
      "step": 490
    },
    {
      "epoch": 1.7301038062283736,
      "grad_norm": 0.5903865694999695,
      "learning_rate": 5e-06,
      "loss": 0.5514,
      "step": 500
    },
    {
      "epoch": 1.7647058823529411,
      "grad_norm": 0.7858901023864746,
      "learning_rate": 5e-06,
      "loss": 0.5632,
      "step": 510
    },
    {
      "epoch": 1.7993079584775087,
      "grad_norm": 0.509254515171051,
      "learning_rate": 5e-06,
      "loss": 0.559,
      "step": 520
    },
    {
      "epoch": 1.8339100346020762,
      "grad_norm": 0.635212779045105,
      "learning_rate": 5e-06,
      "loss": 0.5522,
      "step": 530
    },
    {
      "epoch": 1.8685121107266436,
      "grad_norm": 0.5043730735778809,
      "learning_rate": 5e-06,
      "loss": 0.5537,
      "step": 540
    },
    {
      "epoch": 1.903114186851211,
      "grad_norm": 0.7371939420700073,
      "learning_rate": 5e-06,
      "loss": 0.5557,
      "step": 550
    },
    {
      "epoch": 1.9377162629757785,
      "grad_norm": 0.5097610354423523,
      "learning_rate": 5e-06,
      "loss": 0.5481,
      "step": 560
    },
    {
      "epoch": 1.972318339100346,
      "grad_norm": 0.6075087785720825,
      "learning_rate": 5e-06,
      "loss": 0.5546,
      "step": 570
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.5923461318016052,
      "eval_runtime": 26.1049,
      "eval_samples_per_second": 298.22,
      "eval_steps_per_second": 1.188,
      "step": 578
    },
    {
      "epoch": 2.0069204152249136,
      "grad_norm": 1.147298812866211,
      "learning_rate": 5e-06,
      "loss": 0.5407,
      "step": 580
    },
    {
      "epoch": 2.041522491349481,
      "grad_norm": 0.7817992568016052,
      "learning_rate": 5e-06,
      "loss": 0.51,
      "step": 590
    },
    {
      "epoch": 2.0761245674740483,
      "grad_norm": 0.6091957092285156,
      "learning_rate": 5e-06,
      "loss": 0.5043,
      "step": 600
    },
    {
      "epoch": 2.110726643598616,
      "grad_norm": 0.734910786151886,
      "learning_rate": 5e-06,
      "loss": 0.508,
      "step": 610
    },
    {
      "epoch": 2.1453287197231834,
      "grad_norm": 0.6779142618179321,
      "learning_rate": 5e-06,
      "loss": 0.5109,
      "step": 620
    },
    {
      "epoch": 2.179930795847751,
      "grad_norm": 0.6702868342399597,
      "learning_rate": 5e-06,
      "loss": 0.5151,
      "step": 630
    },
    {
      "epoch": 2.2145328719723185,
      "grad_norm": 0.6096834540367126,
      "learning_rate": 5e-06,
      "loss": 0.5119,
      "step": 640
    },
    {
      "epoch": 2.2491349480968856,
      "grad_norm": 0.7306134700775146,
      "learning_rate": 5e-06,
      "loss": 0.5113,
      "step": 650
    },
    {
      "epoch": 2.283737024221453,
      "grad_norm": 0.6218770742416382,
      "learning_rate": 5e-06,
      "loss": 0.5131,
      "step": 660
    },
    {
      "epoch": 2.3183391003460208,
      "grad_norm": 0.5716001987457275,
      "learning_rate": 5e-06,
      "loss": 0.5115,
      "step": 670
    },
    {
      "epoch": 2.3529411764705883,
      "grad_norm": 0.5372514724731445,
      "learning_rate": 5e-06,
      "loss": 0.5188,
      "step": 680
    },
    {
      "epoch": 2.387543252595156,
      "grad_norm": 0.5553603172302246,
      "learning_rate": 5e-06,
      "loss": 0.5135,
      "step": 690
    },
    {
      "epoch": 2.422145328719723,
      "grad_norm": 0.6243720054626465,
      "learning_rate": 5e-06,
      "loss": 0.5182,
      "step": 700
    },
    {
      "epoch": 2.4567474048442905,
      "grad_norm": 0.6500486135482788,
      "learning_rate": 5e-06,
      "loss": 0.5085,
      "step": 710
    },
    {
      "epoch": 2.491349480968858,
      "grad_norm": 0.6719836592674255,
      "learning_rate": 5e-06,
      "loss": 0.514,
      "step": 720
    },
    {
      "epoch": 2.5259515570934257,
      "grad_norm": 0.6871230602264404,
      "learning_rate": 5e-06,
      "loss": 0.5094,
      "step": 730
    },
    {
      "epoch": 2.5605536332179932,
      "grad_norm": 0.8423399925231934,
      "learning_rate": 5e-06,
      "loss": 0.5138,
      "step": 740
    },
    {
      "epoch": 2.595155709342561,
      "grad_norm": 0.557617723941803,
      "learning_rate": 5e-06,
      "loss": 0.5192,
      "step": 750
    },
    {
      "epoch": 2.629757785467128,
      "grad_norm": 0.7015785574913025,
      "learning_rate": 5e-06,
      "loss": 0.5122,
      "step": 760
    },
    {
      "epoch": 2.6643598615916955,
      "grad_norm": 0.6643463373184204,
      "learning_rate": 5e-06,
      "loss": 0.5136,
      "step": 770
    },
    {
      "epoch": 2.698961937716263,
      "grad_norm": 0.8234036564826965,
      "learning_rate": 5e-06,
      "loss": 0.5147,
      "step": 780
    },
    {
      "epoch": 2.7335640138408306,
      "grad_norm": 0.5616887211799622,
      "learning_rate": 5e-06,
      "loss": 0.5147,
      "step": 790
    },
    {
      "epoch": 2.7681660899653977,
      "grad_norm": 0.6399916410446167,
      "learning_rate": 5e-06,
      "loss": 0.5104,
      "step": 800
    },
    {
      "epoch": 2.8027681660899653,
      "grad_norm": 0.5685309767723083,
      "learning_rate": 5e-06,
      "loss": 0.5128,
      "step": 810
    },
    {
      "epoch": 2.837370242214533,
      "grad_norm": 0.5425155758857727,
      "learning_rate": 5e-06,
      "loss": 0.5132,
      "step": 820
    },
    {
      "epoch": 2.8719723183391004,
      "grad_norm": 0.8712612986564636,
      "learning_rate": 5e-06,
      "loss": 0.5074,
      "step": 830
    },
    {
      "epoch": 2.906574394463668,
      "grad_norm": 0.8342138528823853,
      "learning_rate": 5e-06,
      "loss": 0.5215,
      "step": 840
    },
    {
      "epoch": 2.9411764705882355,
      "grad_norm": 0.7109184861183167,
      "learning_rate": 5e-06,
      "loss": 0.5102,
      "step": 850
    },
    {
      "epoch": 2.9757785467128026,
      "grad_norm": 0.6473217606544495,
      "learning_rate": 5e-06,
      "loss": 0.5168,
      "step": 860
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.5936245918273926,
      "eval_runtime": 26.2859,
      "eval_samples_per_second": 296.166,
      "eval_steps_per_second": 1.179,
      "step": 867
    },
    {
      "epoch": 3.0,
      "step": 867,
      "total_flos": 4.093705665380352e+19,
      "train_loss": 0.5755822655788893,
      "train_runtime": 6372.9887,
      "train_samples_per_second": 69.622,
      "train_steps_per_second": 0.136
    }
  ],
  "logging_steps": 10,
  "max_steps": 867,
  "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": 4.093705665380352e+19,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}