{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9976507439310884,
  "eval_steps": 500,
  "global_step": 957,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.031323414252153486,
      "grad_norm": 2.8610078308107854,
      "learning_rate": 5e-06,
      "loss": 0.9785,
      "step": 10
    },
    {
      "epoch": 0.06264682850430697,
      "grad_norm": 1.7702609085485501,
      "learning_rate": 5e-06,
      "loss": 0.8565,
      "step": 20
    },
    {
      "epoch": 0.09397024275646046,
      "grad_norm": 1.0245069679485275,
      "learning_rate": 5e-06,
      "loss": 0.8274,
      "step": 30
    },
    {
      "epoch": 0.12529365700861395,
      "grad_norm": 1.3708437833993996,
      "learning_rate": 5e-06,
      "loss": 0.799,
      "step": 40
    },
    {
      "epoch": 0.15661707126076743,
      "grad_norm": 0.8356008055369265,
      "learning_rate": 5e-06,
      "loss": 0.7847,
      "step": 50
    },
    {
      "epoch": 0.18794048551292092,
      "grad_norm": 1.0931171880514496,
      "learning_rate": 5e-06,
      "loss": 0.7733,
      "step": 60
    },
    {
      "epoch": 0.2192638997650744,
      "grad_norm": 0.8028201655311987,
      "learning_rate": 5e-06,
      "loss": 0.7543,
      "step": 70
    },
    {
      "epoch": 0.2505873140172279,
      "grad_norm": 0.7488845273909638,
      "learning_rate": 5e-06,
      "loss": 0.7505,
      "step": 80
    },
    {
      "epoch": 0.28191072826938135,
      "grad_norm": 0.6273923877919437,
      "learning_rate": 5e-06,
      "loss": 0.7414,
      "step": 90
    },
    {
      "epoch": 0.31323414252153486,
      "grad_norm": 0.5605687620675001,
      "learning_rate": 5e-06,
      "loss": 0.741,
      "step": 100
    },
    {
      "epoch": 0.3445575567736883,
      "grad_norm": 0.6510334014280172,
      "learning_rate": 5e-06,
      "loss": 0.7386,
      "step": 110
    },
    {
      "epoch": 0.37588097102584184,
      "grad_norm": 0.6570705408467123,
      "learning_rate": 5e-06,
      "loss": 0.7283,
      "step": 120
    },
    {
      "epoch": 0.4072043852779953,
      "grad_norm": 0.6492497055594569,
      "learning_rate": 5e-06,
      "loss": 0.7326,
      "step": 130
    },
    {
      "epoch": 0.4385277995301488,
      "grad_norm": 0.8036703292766153,
      "learning_rate": 5e-06,
      "loss": 0.7239,
      "step": 140
    },
    {
      "epoch": 0.46985121378230227,
      "grad_norm": 0.5816796226058352,
      "learning_rate": 5e-06,
      "loss": 0.7294,
      "step": 150
    },
    {
      "epoch": 0.5011746280344558,
      "grad_norm": 0.6877992121274088,
      "learning_rate": 5e-06,
      "loss": 0.7287,
      "step": 160
    },
    {
      "epoch": 0.5324980422866092,
      "grad_norm": 0.7272574314246748,
      "learning_rate": 5e-06,
      "loss": 0.7208,
      "step": 170
    },
    {
      "epoch": 0.5638214565387627,
      "grad_norm": 0.5709516023324598,
      "learning_rate": 5e-06,
      "loss": 0.7194,
      "step": 180
    },
    {
      "epoch": 0.5951448707909162,
      "grad_norm": 0.5707557600894976,
      "learning_rate": 5e-06,
      "loss": 0.7209,
      "step": 190
    },
    {
      "epoch": 0.6264682850430697,
      "grad_norm": 0.6274568023357758,
      "learning_rate": 5e-06,
      "loss": 0.719,
      "step": 200
    },
    {
      "epoch": 0.6577916992952232,
      "grad_norm": 0.5482714368683154,
      "learning_rate": 5e-06,
      "loss": 0.7155,
      "step": 210
    },
    {
      "epoch": 0.6891151135473766,
      "grad_norm": 0.5435355545098447,
      "learning_rate": 5e-06,
      "loss": 0.7137,
      "step": 220
    },
    {
      "epoch": 0.7204385277995301,
      "grad_norm": 0.5549463909209981,
      "learning_rate": 5e-06,
      "loss": 0.7145,
      "step": 230
    },
    {
      "epoch": 0.7517619420516837,
      "grad_norm": 0.5872929591126732,
      "learning_rate": 5e-06,
      "loss": 0.7151,
      "step": 240
    },
    {
      "epoch": 0.7830853563038371,
      "grad_norm": 0.6595124362809732,
      "learning_rate": 5e-06,
      "loss": 0.7145,
      "step": 250
    },
    {
      "epoch": 0.8144087705559906,
      "grad_norm": 0.5459174781598405,
      "learning_rate": 5e-06,
      "loss": 0.7174,
      "step": 260
    },
    {
      "epoch": 0.845732184808144,
      "grad_norm": 0.659643905818339,
      "learning_rate": 5e-06,
      "loss": 0.7089,
      "step": 270
    },
    {
      "epoch": 0.8770555990602976,
      "grad_norm": 0.686424151578199,
      "learning_rate": 5e-06,
      "loss": 0.7113,
      "step": 280
    },
    {
      "epoch": 0.9083790133124511,
      "grad_norm": 0.7152116087909246,
      "learning_rate": 5e-06,
      "loss": 0.7087,
      "step": 290
    },
    {
      "epoch": 0.9397024275646045,
      "grad_norm": 0.5755513442821608,
      "learning_rate": 5e-06,
      "loss": 0.7035,
      "step": 300
    },
    {
      "epoch": 0.971025841816758,
      "grad_norm": 0.49802238359887663,
      "learning_rate": 5e-06,
      "loss": 0.7101,
      "step": 310
    },
    {
      "epoch": 0.9992169146436961,
      "eval_loss": 0.7040486931800842,
      "eval_runtime": 340.4664,
      "eval_samples_per_second": 25.265,
      "eval_steps_per_second": 0.397,
      "step": 319
    },
    {
      "epoch": 1.0023492560689116,
      "grad_norm": 1.39557569608369,
      "learning_rate": 5e-06,
      "loss": 0.7543,
      "step": 320
    },
    {
      "epoch": 1.033672670321065,
      "grad_norm": 0.7048516666631669,
      "learning_rate": 5e-06,
      "loss": 0.6574,
      "step": 330
    },
    {
      "epoch": 1.0649960845732185,
      "grad_norm": 0.7154001922458556,
      "learning_rate": 5e-06,
      "loss": 0.6596,
      "step": 340
    },
    {
      "epoch": 1.096319498825372,
      "grad_norm": 0.8075870470182475,
      "learning_rate": 5e-06,
      "loss": 0.6634,
      "step": 350
    },
    {
      "epoch": 1.1276429130775254,
      "grad_norm": 0.6958604595694347,
      "learning_rate": 5e-06,
      "loss": 0.6588,
      "step": 360
    },
    {
      "epoch": 1.1589663273296789,
      "grad_norm": 0.6457902283198051,
      "learning_rate": 5e-06,
      "loss": 0.6627,
      "step": 370
    },
    {
      "epoch": 1.1902897415818323,
      "grad_norm": 0.7060779787846581,
      "learning_rate": 5e-06,
      "loss": 0.6623,
      "step": 380
    },
    {
      "epoch": 1.221613155833986,
      "grad_norm": 0.7178631366122828,
      "learning_rate": 5e-06,
      "loss": 0.6595,
      "step": 390
    },
    {
      "epoch": 1.2529365700861395,
      "grad_norm": 0.7303589998987047,
      "learning_rate": 5e-06,
      "loss": 0.6602,
      "step": 400
    },
    {
      "epoch": 1.284259984338293,
      "grad_norm": 0.614614426793837,
      "learning_rate": 5e-06,
      "loss": 0.6623,
      "step": 410
    },
    {
      "epoch": 1.3155833985904464,
      "grad_norm": 0.5603517373438384,
      "learning_rate": 5e-06,
      "loss": 0.6623,
      "step": 420
    },
    {
      "epoch": 1.3469068128425998,
      "grad_norm": 0.5439036905330217,
      "learning_rate": 5e-06,
      "loss": 0.6624,
      "step": 430
    },
    {
      "epoch": 1.3782302270947533,
      "grad_norm": 0.5345730868641901,
      "learning_rate": 5e-06,
      "loss": 0.6597,
      "step": 440
    },
    {
      "epoch": 1.4095536413469067,
      "grad_norm": 0.6120306566548636,
      "learning_rate": 5e-06,
      "loss": 0.6601,
      "step": 450
    },
    {
      "epoch": 1.4408770555990604,
      "grad_norm": 0.7662777275751876,
      "learning_rate": 5e-06,
      "loss": 0.6579,
      "step": 460
    },
    {
      "epoch": 1.4722004698512139,
      "grad_norm": 0.5861171635982056,
      "learning_rate": 5e-06,
      "loss": 0.6617,
      "step": 470
    },
    {
      "epoch": 1.5035238841033673,
      "grad_norm": 0.550703096699278,
      "learning_rate": 5e-06,
      "loss": 0.6575,
      "step": 480
    },
    {
      "epoch": 1.5348472983555208,
      "grad_norm": 0.8724124589877997,
      "learning_rate": 5e-06,
      "loss": 0.6619,
      "step": 490
    },
    {
      "epoch": 1.5661707126076743,
      "grad_norm": 0.5466331808335562,
      "learning_rate": 5e-06,
      "loss": 0.6582,
      "step": 500
    },
    {
      "epoch": 1.5974941268598277,
      "grad_norm": 0.5658899060560815,
      "learning_rate": 5e-06,
      "loss": 0.6606,
      "step": 510
    },
    {
      "epoch": 1.6288175411119812,
      "grad_norm": 0.5924530569896768,
      "learning_rate": 5e-06,
      "loss": 0.6591,
      "step": 520
    },
    {
      "epoch": 1.6601409553641346,
      "grad_norm": 0.6898298377267612,
      "learning_rate": 5e-06,
      "loss": 0.6567,
      "step": 530
    },
    {
      "epoch": 1.691464369616288,
      "grad_norm": 0.5747921428491914,
      "learning_rate": 5e-06,
      "loss": 0.6558,
      "step": 540
    },
    {
      "epoch": 1.7227877838684416,
      "grad_norm": 0.5318671363061512,
      "learning_rate": 5e-06,
      "loss": 0.6552,
      "step": 550
    },
    {
      "epoch": 1.754111198120595,
      "grad_norm": 0.6440423203167484,
      "learning_rate": 5e-06,
      "loss": 0.6569,
      "step": 560
    },
    {
      "epoch": 1.7854346123727485,
      "grad_norm": 0.6871334064396125,
      "learning_rate": 5e-06,
      "loss": 0.6579,
      "step": 570
    },
    {
      "epoch": 1.8167580266249022,
      "grad_norm": 0.6410119301707079,
      "learning_rate": 5e-06,
      "loss": 0.6586,
      "step": 580
    },
    {
      "epoch": 1.8480814408770556,
      "grad_norm": 0.5225004293954756,
      "learning_rate": 5e-06,
      "loss": 0.6602,
      "step": 590
    },
    {
      "epoch": 1.879404855129209,
      "grad_norm": 0.5478451699362562,
      "learning_rate": 5e-06,
      "loss": 0.6562,
      "step": 600
    },
    {
      "epoch": 1.9107282693813625,
      "grad_norm": 0.6535107349232507,
      "learning_rate": 5e-06,
      "loss": 0.6598,
      "step": 610
    },
    {
      "epoch": 1.9420516836335162,
      "grad_norm": 0.5332260801259929,
      "learning_rate": 5e-06,
      "loss": 0.6577,
      "step": 620
    },
    {
      "epoch": 1.9733750978856697,
      "grad_norm": 0.6351126336858737,
      "learning_rate": 5e-06,
      "loss": 0.6588,
      "step": 630
    },
    {
      "epoch": 1.9984338292873924,
      "eval_loss": 0.6915597319602966,
      "eval_runtime": 342.8543,
      "eval_samples_per_second": 25.089,
      "eval_steps_per_second": 0.394,
      "step": 638
    },
    {
      "epoch": 2.004698512137823,
      "grad_norm": 0.9348794210283986,
      "learning_rate": 5e-06,
      "loss": 0.7005,
      "step": 640
    },
    {
      "epoch": 2.0360219263899766,
      "grad_norm": 0.6116207803075494,
      "learning_rate": 5e-06,
      "loss": 0.61,
      "step": 650
    },
    {
      "epoch": 2.06734534064213,
      "grad_norm": 0.7136818100838924,
      "learning_rate": 5e-06,
      "loss": 0.6129,
      "step": 660
    },
    {
      "epoch": 2.0986687548942835,
      "grad_norm": 0.6893268088593335,
      "learning_rate": 5e-06,
      "loss": 0.6073,
      "step": 670
    },
    {
      "epoch": 2.129992169146437,
      "grad_norm": 0.5885891280735964,
      "learning_rate": 5e-06,
      "loss": 0.6069,
      "step": 680
    },
    {
      "epoch": 2.1613155833985904,
      "grad_norm": 0.5966990660667627,
      "learning_rate": 5e-06,
      "loss": 0.6115,
      "step": 690
    },
    {
      "epoch": 2.192638997650744,
      "grad_norm": 0.5903227979936005,
      "learning_rate": 5e-06,
      "loss": 0.6083,
      "step": 700
    },
    {
      "epoch": 2.2239624119028973,
      "grad_norm": 0.5378339870907247,
      "learning_rate": 5e-06,
      "loss": 0.6055,
      "step": 710
    },
    {
      "epoch": 2.255285826155051,
      "grad_norm": 0.7262899779231057,
      "learning_rate": 5e-06,
      "loss": 0.612,
      "step": 720
    },
    {
      "epoch": 2.2866092404072043,
      "grad_norm": 0.5969529088102685,
      "learning_rate": 5e-06,
      "loss": 0.6119,
      "step": 730
    },
    {
      "epoch": 2.3179326546593577,
      "grad_norm": 0.6265310864883772,
      "learning_rate": 5e-06,
      "loss": 0.6113,
      "step": 740
    },
    {
      "epoch": 2.349256068911511,
      "grad_norm": 0.6715123614069597,
      "learning_rate": 5e-06,
      "loss": 0.6111,
      "step": 750
    },
    {
      "epoch": 2.3805794831636646,
      "grad_norm": 0.5903854838476866,
      "learning_rate": 5e-06,
      "loss": 0.6121,
      "step": 760
    },
    {
      "epoch": 2.4119028974158185,
      "grad_norm": 0.7108455834296159,
      "learning_rate": 5e-06,
      "loss": 0.6159,
      "step": 770
    },
    {
      "epoch": 2.443226311667972,
      "grad_norm": 0.5396295194681806,
      "learning_rate": 5e-06,
      "loss": 0.6142,
      "step": 780
    },
    {
      "epoch": 2.4745497259201255,
      "grad_norm": 0.6709263277652183,
      "learning_rate": 5e-06,
      "loss": 0.6181,
      "step": 790
    },
    {
      "epoch": 2.505873140172279,
      "grad_norm": 0.6922212368293488,
      "learning_rate": 5e-06,
      "loss": 0.6127,
      "step": 800
    },
    {
      "epoch": 2.5371965544244324,
      "grad_norm": 0.802266836685208,
      "learning_rate": 5e-06,
      "loss": 0.6192,
      "step": 810
    },
    {
      "epoch": 2.568519968676586,
      "grad_norm": 0.7055921712823672,
      "learning_rate": 5e-06,
      "loss": 0.6098,
      "step": 820
    },
    {
      "epoch": 2.5998433829287393,
      "grad_norm": 0.6549155076226189,
      "learning_rate": 5e-06,
      "loss": 0.6126,
      "step": 830
    },
    {
      "epoch": 2.6311667971808927,
      "grad_norm": 0.6145335107184124,
      "learning_rate": 5e-06,
      "loss": 0.618,
      "step": 840
    },
    {
      "epoch": 2.662490211433046,
      "grad_norm": 0.6520405733421761,
      "learning_rate": 5e-06,
      "loss": 0.6132,
      "step": 850
    },
    {
      "epoch": 2.6938136256851997,
      "grad_norm": 0.5955304451757282,
      "learning_rate": 5e-06,
      "loss": 0.6211,
      "step": 860
    },
    {
      "epoch": 2.725137039937353,
      "grad_norm": 0.6957752696961866,
      "learning_rate": 5e-06,
      "loss": 0.6072,
      "step": 870
    },
    {
      "epoch": 2.7564604541895066,
      "grad_norm": 0.7212196624619537,
      "learning_rate": 5e-06,
      "loss": 0.6181,
      "step": 880
    },
    {
      "epoch": 2.78778386844166,
      "grad_norm": 0.6362474481595267,
      "learning_rate": 5e-06,
      "loss": 0.6183,
      "step": 890
    },
    {
      "epoch": 2.8191072826938135,
      "grad_norm": 0.6043748136471383,
      "learning_rate": 5e-06,
      "loss": 0.6185,
      "step": 900
    },
    {
      "epoch": 2.850430696945967,
      "grad_norm": 0.6293339433347603,
      "learning_rate": 5e-06,
      "loss": 0.6113,
      "step": 910
    },
    {
      "epoch": 2.881754111198121,
      "grad_norm": 0.5487837401420806,
      "learning_rate": 5e-06,
      "loss": 0.613,
      "step": 920
    },
    {
      "epoch": 2.913077525450274,
      "grad_norm": 0.6366669947057394,
      "learning_rate": 5e-06,
      "loss": 0.6178,
      "step": 930
    },
    {
      "epoch": 2.9444009397024278,
      "grad_norm": 0.6539470297076938,
      "learning_rate": 5e-06,
      "loss": 0.6157,
      "step": 940
    },
    {
      "epoch": 2.975724353954581,
      "grad_norm": 0.7862259105525281,
      "learning_rate": 5e-06,
      "loss": 0.6176,
      "step": 950
    },
    {
      "epoch": 2.9976507439310884,
      "eval_loss": 0.6914501786231995,
      "eval_runtime": 343.0486,
      "eval_samples_per_second": 25.075,
      "eval_steps_per_second": 0.394,
      "step": 957
    },
    {
      "epoch": 2.9976507439310884,
      "step": 957,
      "total_flos": 1602801264230400.0,
      "train_loss": 0.6732874076069958,
      "train_runtime": 56787.3035,
      "train_samples_per_second": 8.633,
      "train_steps_per_second": 0.017
    }
  ],
  "logging_steps": 10,
  "max_steps": 957,
  "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": 1602801264230400.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}