{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9958081043316254,
  "eval_steps": 500,
  "global_step": 804,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.037261294829995344,
      "grad_norm": 3.177923185690651,
      "learning_rate": 5e-06,
      "loss": 1.0446,
      "step": 10
    },
    {
      "epoch": 0.07452258965999069,
      "grad_norm": 1.5655148840692104,
      "learning_rate": 5e-06,
      "loss": 0.9101,
      "step": 20
    },
    {
      "epoch": 0.11178388448998602,
      "grad_norm": 1.2741458134596388,
      "learning_rate": 5e-06,
      "loss": 0.8739,
      "step": 30
    },
    {
      "epoch": 0.14904517931998137,
      "grad_norm": 1.1521931357563782,
      "learning_rate": 5e-06,
      "loss": 0.8458,
      "step": 40
    },
    {
      "epoch": 0.18630647414997673,
      "grad_norm": 1.1371625192876917,
      "learning_rate": 5e-06,
      "loss": 0.8221,
      "step": 50
    },
    {
      "epoch": 0.22356776897997205,
      "grad_norm": 0.9080984413465669,
      "learning_rate": 5e-06,
      "loss": 0.8159,
      "step": 60
    },
    {
      "epoch": 0.2608290638099674,
      "grad_norm": 0.9330400679788563,
      "learning_rate": 5e-06,
      "loss": 0.8017,
      "step": 70
    },
    {
      "epoch": 0.29809035863996275,
      "grad_norm": 0.7711080271829996,
      "learning_rate": 5e-06,
      "loss": 0.7893,
      "step": 80
    },
    {
      "epoch": 0.3353516534699581,
      "grad_norm": 0.7516775112714674,
      "learning_rate": 5e-06,
      "loss": 0.792,
      "step": 90
    },
    {
      "epoch": 0.37261294829995345,
      "grad_norm": 0.6720880112699107,
      "learning_rate": 5e-06,
      "loss": 0.7807,
      "step": 100
    },
    {
      "epoch": 0.40987424312994875,
      "grad_norm": 1.0015408115889342,
      "learning_rate": 5e-06,
      "loss": 0.7739,
      "step": 110
    },
    {
      "epoch": 0.4471355379599441,
      "grad_norm": 0.7967270535006579,
      "learning_rate": 5e-06,
      "loss": 0.7753,
      "step": 120
    },
    {
      "epoch": 0.48439683278993945,
      "grad_norm": 0.7992952214381639,
      "learning_rate": 5e-06,
      "loss": 0.7685,
      "step": 130
    },
    {
      "epoch": 0.5216581276199348,
      "grad_norm": 0.822692265972509,
      "learning_rate": 5e-06,
      "loss": 0.7664,
      "step": 140
    },
    {
      "epoch": 0.5589194224499301,
      "grad_norm": 0.6248743169023847,
      "learning_rate": 5e-06,
      "loss": 0.7619,
      "step": 150
    },
    {
      "epoch": 0.5961807172799255,
      "grad_norm": 0.7681721127721153,
      "learning_rate": 5e-06,
      "loss": 0.7601,
      "step": 160
    },
    {
      "epoch": 0.6334420121099208,
      "grad_norm": 0.6670980060596134,
      "learning_rate": 5e-06,
      "loss": 0.7594,
      "step": 170
    },
    {
      "epoch": 0.6707033069399162,
      "grad_norm": 1.6054759679741344,
      "learning_rate": 5e-06,
      "loss": 0.7627,
      "step": 180
    },
    {
      "epoch": 0.7079646017699115,
      "grad_norm": 1.0157126085127113,
      "learning_rate": 5e-06,
      "loss": 0.7612,
      "step": 190
    },
    {
      "epoch": 0.7452258965999069,
      "grad_norm": 1.0987509598845462,
      "learning_rate": 5e-06,
      "loss": 0.7566,
      "step": 200
    },
    {
      "epoch": 0.7824871914299022,
      "grad_norm": 0.8874349124844947,
      "learning_rate": 5e-06,
      "loss": 0.7578,
      "step": 210
    },
    {
      "epoch": 0.8197484862598975,
      "grad_norm": 0.8625833938546213,
      "learning_rate": 5e-06,
      "loss": 0.7472,
      "step": 220
    },
    {
      "epoch": 0.8570097810898929,
      "grad_norm": 0.6536315928798102,
      "learning_rate": 5e-06,
      "loss": 0.7499,
      "step": 230
    },
    {
      "epoch": 0.8942710759198882,
      "grad_norm": 0.5976487344814351,
      "learning_rate": 5e-06,
      "loss": 0.7493,
      "step": 240
    },
    {
      "epoch": 0.9315323707498836,
      "grad_norm": 0.6377854255157969,
      "learning_rate": 5e-06,
      "loss": 0.7449,
      "step": 250
    },
    {
      "epoch": 0.9687936655798789,
      "grad_norm": 0.6255963141536746,
      "learning_rate": 5e-06,
      "loss": 0.7463,
      "step": 260
    },
    {
      "epoch": 0.9986027014438752,
      "eval_loss": 0.753118097782135,
      "eval_runtime": 282.6878,
      "eval_samples_per_second": 25.572,
      "eval_steps_per_second": 0.4,
      "step": 268
    },
    {
      "epoch": 1.0060549604098743,
      "grad_norm": 0.7967440184692027,
      "learning_rate": 5e-06,
      "loss": 0.7858,
      "step": 270
    },
    {
      "epoch": 1.0433162552398696,
      "grad_norm": 0.6961321881435635,
      "learning_rate": 5e-06,
      "loss": 0.6975,
      "step": 280
    },
    {
      "epoch": 1.080577550069865,
      "grad_norm": 0.762772210563081,
      "learning_rate": 5e-06,
      "loss": 0.6948,
      "step": 290
    },
    {
      "epoch": 1.1178388448998602,
      "grad_norm": 0.7180309443204612,
      "learning_rate": 5e-06,
      "loss": 0.6976,
      "step": 300
    },
    {
      "epoch": 1.1551001397298557,
      "grad_norm": 0.7681051261580779,
      "learning_rate": 5e-06,
      "loss": 0.6927,
      "step": 310
    },
    {
      "epoch": 1.192361434559851,
      "grad_norm": 0.5509672175600794,
      "learning_rate": 5e-06,
      "loss": 0.6914,
      "step": 320
    },
    {
      "epoch": 1.2296227293898463,
      "grad_norm": 0.6540568092405752,
      "learning_rate": 5e-06,
      "loss": 0.7042,
      "step": 330
    },
    {
      "epoch": 1.2668840242198416,
      "grad_norm": 0.6081452030296887,
      "learning_rate": 5e-06,
      "loss": 0.6964,
      "step": 340
    },
    {
      "epoch": 1.3041453190498369,
      "grad_norm": 0.6548111894829255,
      "learning_rate": 5e-06,
      "loss": 0.6982,
      "step": 350
    },
    {
      "epoch": 1.3414066138798324,
      "grad_norm": 0.6390670197121491,
      "learning_rate": 5e-06,
      "loss": 0.6958,
      "step": 360
    },
    {
      "epoch": 1.3786679087098277,
      "grad_norm": 0.6212133244114497,
      "learning_rate": 5e-06,
      "loss": 0.6966,
      "step": 370
    },
    {
      "epoch": 1.415929203539823,
      "grad_norm": 0.5799521943921166,
      "learning_rate": 5e-06,
      "loss": 0.6891,
      "step": 380
    },
    {
      "epoch": 1.4531904983698183,
      "grad_norm": 0.6895979564472926,
      "learning_rate": 5e-06,
      "loss": 0.6961,
      "step": 390
    },
    {
      "epoch": 1.4904517931998136,
      "grad_norm": 0.7051355249345896,
      "learning_rate": 5e-06,
      "loss": 0.6937,
      "step": 400
    },
    {
      "epoch": 1.527713088029809,
      "grad_norm": 0.5848394801525845,
      "learning_rate": 5e-06,
      "loss": 0.6934,
      "step": 410
    },
    {
      "epoch": 1.5649743828598044,
      "grad_norm": 0.7559716416869524,
      "learning_rate": 5e-06,
      "loss": 0.6895,
      "step": 420
    },
    {
      "epoch": 1.6022356776897997,
      "grad_norm": 0.6232619179980586,
      "learning_rate": 5e-06,
      "loss": 0.6982,
      "step": 430
    },
    {
      "epoch": 1.6394969725197952,
      "grad_norm": 0.5824898687040235,
      "learning_rate": 5e-06,
      "loss": 0.6952,
      "step": 440
    },
    {
      "epoch": 1.6767582673497903,
      "grad_norm": 0.6210814650937644,
      "learning_rate": 5e-06,
      "loss": 0.6973,
      "step": 450
    },
    {
      "epoch": 1.7140195621797858,
      "grad_norm": 0.6197587117855798,
      "learning_rate": 5e-06,
      "loss": 0.6941,
      "step": 460
    },
    {
      "epoch": 1.751280857009781,
      "grad_norm": 0.5610090469048251,
      "learning_rate": 5e-06,
      "loss": 0.6918,
      "step": 470
    },
    {
      "epoch": 1.7885421518397764,
      "grad_norm": 0.6397472245527632,
      "learning_rate": 5e-06,
      "loss": 0.6896,
      "step": 480
    },
    {
      "epoch": 1.825803446669772,
      "grad_norm": 0.8540795729270456,
      "learning_rate": 5e-06,
      "loss": 0.6949,
      "step": 490
    },
    {
      "epoch": 1.863064741499767,
      "grad_norm": 0.5933184699793366,
      "learning_rate": 5e-06,
      "loss": 0.6941,
      "step": 500
    },
    {
      "epoch": 1.9003260363297625,
      "grad_norm": 0.5702682781752477,
      "learning_rate": 5e-06,
      "loss": 0.6947,
      "step": 510
    },
    {
      "epoch": 1.9375873311597578,
      "grad_norm": 0.6485728293989254,
      "learning_rate": 5e-06,
      "loss": 0.6934,
      "step": 520
    },
    {
      "epoch": 1.974848625989753,
      "grad_norm": 0.658819869120822,
      "learning_rate": 5e-06,
      "loss": 0.6935,
      "step": 530
    },
    {
      "epoch": 1.9972054028877504,
      "eval_loss": 0.7391706705093384,
      "eval_runtime": 284.9966,
      "eval_samples_per_second": 25.365,
      "eval_steps_per_second": 0.396,
      "step": 536
    },
    {
      "epoch": 2.0121099208197486,
      "grad_norm": 0.8176370133975521,
      "learning_rate": 5e-06,
      "loss": 0.7119,
      "step": 540
    },
    {
      "epoch": 2.0493712156497437,
      "grad_norm": 1.0394836748871732,
      "learning_rate": 5e-06,
      "loss": 0.6404,
      "step": 550
    },
    {
      "epoch": 2.086632510479739,
      "grad_norm": 0.7102912397553353,
      "learning_rate": 5e-06,
      "loss": 0.6384,
      "step": 560
    },
    {
      "epoch": 2.1238938053097347,
      "grad_norm": 0.6303371150790377,
      "learning_rate": 5e-06,
      "loss": 0.6368,
      "step": 570
    },
    {
      "epoch": 2.16115510013973,
      "grad_norm": 0.7194505328759309,
      "learning_rate": 5e-06,
      "loss": 0.6331,
      "step": 580
    },
    {
      "epoch": 2.1984163949697253,
      "grad_norm": 0.8581082758870584,
      "learning_rate": 5e-06,
      "loss": 0.6414,
      "step": 590
    },
    {
      "epoch": 2.2356776897997204,
      "grad_norm": 0.7882079908607245,
      "learning_rate": 5e-06,
      "loss": 0.642,
      "step": 600
    },
    {
      "epoch": 2.272938984629716,
      "grad_norm": 0.7493026584846839,
      "learning_rate": 5e-06,
      "loss": 0.644,
      "step": 610
    },
    {
      "epoch": 2.3102002794597114,
      "grad_norm": 0.6779697760274137,
      "learning_rate": 5e-06,
      "loss": 0.6446,
      "step": 620
    },
    {
      "epoch": 2.3474615742897065,
      "grad_norm": 0.7469773522523896,
      "learning_rate": 5e-06,
      "loss": 0.6413,
      "step": 630
    },
    {
      "epoch": 2.384722869119702,
      "grad_norm": 0.8234476990672971,
      "learning_rate": 5e-06,
      "loss": 0.6383,
      "step": 640
    },
    {
      "epoch": 2.421984163949697,
      "grad_norm": 0.6740528425843195,
      "learning_rate": 5e-06,
      "loss": 0.6403,
      "step": 650
    },
    {
      "epoch": 2.4592454587796926,
      "grad_norm": 0.8699308162958452,
      "learning_rate": 5e-06,
      "loss": 0.6424,
      "step": 660
    },
    {
      "epoch": 2.496506753609688,
      "grad_norm": 0.7201278110102733,
      "learning_rate": 5e-06,
      "loss": 0.645,
      "step": 670
    },
    {
      "epoch": 2.533768048439683,
      "grad_norm": 0.6724034506353075,
      "learning_rate": 5e-06,
      "loss": 0.6432,
      "step": 680
    },
    {
      "epoch": 2.5710293432696787,
      "grad_norm": 0.69360608529311,
      "learning_rate": 5e-06,
      "loss": 0.6396,
      "step": 690
    },
    {
      "epoch": 2.6082906380996738,
      "grad_norm": 0.8274824206163831,
      "learning_rate": 5e-06,
      "loss": 0.6392,
      "step": 700
    },
    {
      "epoch": 2.6455519329296693,
      "grad_norm": 0.6599355927406194,
      "learning_rate": 5e-06,
      "loss": 0.6376,
      "step": 710
    },
    {
      "epoch": 2.682813227759665,
      "grad_norm": 0.6028719649182044,
      "learning_rate": 5e-06,
      "loss": 0.6426,
      "step": 720
    },
    {
      "epoch": 2.72007452258966,
      "grad_norm": 0.8529220528875564,
      "learning_rate": 5e-06,
      "loss": 0.6442,
      "step": 730
    },
    {
      "epoch": 2.7573358174196554,
      "grad_norm": 0.5833740770838279,
      "learning_rate": 5e-06,
      "loss": 0.6435,
      "step": 740
    },
    {
      "epoch": 2.794597112249651,
      "grad_norm": 0.75585676373348,
      "learning_rate": 5e-06,
      "loss": 0.643,
      "step": 750
    },
    {
      "epoch": 2.831858407079646,
      "grad_norm": 0.7316206001732912,
      "learning_rate": 5e-06,
      "loss": 0.645,
      "step": 760
    },
    {
      "epoch": 2.8691197019096415,
      "grad_norm": 0.6022571096523994,
      "learning_rate": 5e-06,
      "loss": 0.643,
      "step": 770
    },
    {
      "epoch": 2.9063809967396366,
      "grad_norm": 0.6980539018883889,
      "learning_rate": 5e-06,
      "loss": 0.6444,
      "step": 780
    },
    {
      "epoch": 2.943642291569632,
      "grad_norm": 0.6379664123364885,
      "learning_rate": 5e-06,
      "loss": 0.6418,
      "step": 790
    },
    {
      "epoch": 2.980903586399627,
      "grad_norm": 0.617861393266688,
      "learning_rate": 5e-06,
      "loss": 0.6473,
      "step": 800
    },
    {
      "epoch": 2.9958081043316254,
      "eval_loss": 0.7408209443092346,
      "eval_runtime": 283.5662,
      "eval_samples_per_second": 25.493,
      "eval_steps_per_second": 0.398,
      "step": 804
    },
    {
      "epoch": 2.9958081043316254,
      "step": 804,
      "total_flos": 1346520565678080.0,
      "train_loss": 0.7105088189466676,
      "train_runtime": 47269.4774,
      "train_samples_per_second": 8.717,
      "train_steps_per_second": 0.017
    }
  ],
  "logging_steps": 10,
  "max_steps": 804,
  "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": 1346520565678080.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}