{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3735699276208265,
  "eval_steps": 500,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009339248190520663,
      "grad_norm": 6.638877692627699,
      "learning_rate": 9.345794392523364e-07,
      "loss": 9.2917,
      "step": 1
    },
    {
      "epoch": 0.009339248190520663,
      "grad_norm": 1.1560921335705272,
      "learning_rate": 9.345794392523365e-06,
      "loss": 9.0876,
      "step": 10
    },
    {
      "epoch": 0.018678496381041326,
      "grad_norm": 0.8415132296956432,
      "learning_rate": 1.869158878504673e-05,
      "loss": 8.2164,
      "step": 20
    },
    {
      "epoch": 0.02801774457156199,
      "grad_norm": 0.45381630992958155,
      "learning_rate": 2.8037383177570094e-05,
      "loss": 7.5184,
      "step": 30
    },
    {
      "epoch": 0.03735699276208265,
      "grad_norm": 0.8400636107958425,
      "learning_rate": 3.738317757009346e-05,
      "loss": 6.6507,
      "step": 40
    },
    {
      "epoch": 0.046696240952603316,
      "grad_norm": 0.557696240829066,
      "learning_rate": 4.672897196261683e-05,
      "loss": 5.8909,
      "step": 50
    },
    {
      "epoch": 0.05603548914312398,
      "grad_norm": 0.3971996057467842,
      "learning_rate": 5.607476635514019e-05,
      "loss": 5.4127,
      "step": 60
    },
    {
      "epoch": 0.06537473733364464,
      "grad_norm": 0.2932710540265688,
      "learning_rate": 6.542056074766355e-05,
      "loss": 5.0106,
      "step": 70
    },
    {
      "epoch": 0.0747139855241653,
      "grad_norm": 0.3682690443551033,
      "learning_rate": 7.476635514018692e-05,
      "loss": 4.6042,
      "step": 80
    },
    {
      "epoch": 0.08405323371468597,
      "grad_norm": 0.3132971920011515,
      "learning_rate": 8.411214953271028e-05,
      "loss": 4.2031,
      "step": 90
    },
    {
      "epoch": 0.09339248190520663,
      "grad_norm": 0.6731868159213446,
      "learning_rate": 9.345794392523365e-05,
      "loss": 3.9423,
      "step": 100
    },
    {
      "epoch": 0.1027317300957273,
      "grad_norm": 0.27848867836763197,
      "learning_rate": 0.000102803738317757,
      "loss": 3.7157,
      "step": 110
    },
    {
      "epoch": 0.11207097828624796,
      "grad_norm": 0.24642109032991807,
      "learning_rate": 0.00011214953271028037,
      "loss": 3.4516,
      "step": 120
    },
    {
      "epoch": 0.12141022647676862,
      "grad_norm": 0.25717384664029797,
      "learning_rate": 0.00012149532710280373,
      "loss": 3.2167,
      "step": 130
    },
    {
      "epoch": 0.13074947466728928,
      "grad_norm": 0.20912922668565637,
      "learning_rate": 0.0001308411214953271,
      "loss": 3.0237,
      "step": 140
    },
    {
      "epoch": 0.14008872285780993,
      "grad_norm": 0.15805888388706113,
      "learning_rate": 0.00014018691588785047,
      "loss": 2.8529,
      "step": 150
    },
    {
      "epoch": 0.1494279710483306,
      "grad_norm": 0.23370349497479534,
      "learning_rate": 0.00014953271028037384,
      "loss": 2.7078,
      "step": 160
    },
    {
      "epoch": 0.15876721923885126,
      "grad_norm": 0.1802138633012483,
      "learning_rate": 0.0001588785046728972,
      "loss": 2.6115,
      "step": 170
    },
    {
      "epoch": 0.16810646742937194,
      "grad_norm": 0.13354347610039718,
      "learning_rate": 0.00016822429906542056,
      "loss": 2.5309,
      "step": 180
    },
    {
      "epoch": 0.17744571561989259,
      "grad_norm": 0.09414865188086892,
      "learning_rate": 0.00017757009345794393,
      "loss": 2.4452,
      "step": 190
    },
    {
      "epoch": 0.18678496381041326,
      "grad_norm": 0.08333601554768896,
      "learning_rate": 0.0001869158878504673,
      "loss": 2.3832,
      "step": 200
    },
    {
      "epoch": 0.1961242120009339,
      "grad_norm": 0.15926414699806835,
      "learning_rate": 0.00019626168224299065,
      "loss": 2.3492,
      "step": 210
    },
    {
      "epoch": 0.2054634601914546,
      "grad_norm": 0.09492820761057012,
      "learning_rate": 0.0001999989254250208,
      "loss": 2.323,
      "step": 220
    },
    {
      "epoch": 0.21480270838197524,
      "grad_norm": 0.0801349259356147,
      "learning_rate": 0.00019999235866155886,
      "loss": 2.2731,
      "step": 230
    },
    {
      "epoch": 0.22414195657249592,
      "grad_norm": 0.12210960524693895,
      "learning_rate": 0.00019997982251228469,
      "loss": 2.2433,
      "step": 240
    },
    {
      "epoch": 0.23348120476301656,
      "grad_norm": 3.14289498732125,
      "learning_rate": 0.00019996131772558666,
      "loss": 3.2769,
      "step": 250
    },
    {
      "epoch": 0.24282045295353724,
      "grad_norm": 1.632940983166179,
      "learning_rate": 0.00019993684540617132,
      "loss": 4.9343,
      "step": 260
    },
    {
      "epoch": 0.2521597011440579,
      "grad_norm": 3.4831252230225416,
      "learning_rate": 0.00019990640701499736,
      "loss": 4.2768,
      "step": 270
    },
    {
      "epoch": 0.26149894933457857,
      "grad_norm": 1.6069045920523788,
      "learning_rate": 0.00019987000436918874,
      "loss": 5.9581,
      "step": 280
    },
    {
      "epoch": 0.27083819752509924,
      "grad_norm": 0.2220907936615993,
      "learning_rate": 0.00019982763964192585,
      "loss": 3.8228,
      "step": 290
    },
    {
      "epoch": 0.28017744571561987,
      "grad_norm": 0.24737284913291765,
      "learning_rate": 0.00019977931536231596,
      "loss": 3.1413,
      "step": 300
    },
    {
      "epoch": 0.28951669390614054,
      "grad_norm": 4.010404518241152,
      "learning_rate": 0.00019972503441524224,
      "loss": 2.8432,
      "step": 310
    },
    {
      "epoch": 0.2988559420966612,
      "grad_norm": 0.1515583580811596,
      "learning_rate": 0.00019966480004119142,
      "loss": 2.7859,
      "step": 320
    },
    {
      "epoch": 0.3081951902871819,
      "grad_norm": 0.11259395750650594,
      "learning_rate": 0.00019959861583606045,
      "loss": 2.5821,
      "step": 330
    },
    {
      "epoch": 0.3175344384777025,
      "grad_norm": 0.22514797814956813,
      "learning_rate": 0.00019952648575094183,
      "loss": 2.4517,
      "step": 340
    },
    {
      "epoch": 0.3268736866682232,
      "grad_norm": 0.08040136172033542,
      "learning_rate": 0.00019944841409188767,
      "loss": 2.3794,
      "step": 350
    },
    {
      "epoch": 0.3362129348587439,
      "grad_norm": 0.054758073593565354,
      "learning_rate": 0.00019936440551965263,
      "loss": 2.3232,
      "step": 360
    },
    {
      "epoch": 0.34555218304926455,
      "grad_norm": 0.06742998909645591,
      "learning_rate": 0.00019927446504941577,
      "loss": 2.2776,
      "step": 370
    },
    {
      "epoch": 0.35489143123978517,
      "grad_norm": 0.048780907584876736,
      "learning_rate": 0.00019917859805048096,
      "loss": 2.2376,
      "step": 380
    },
    {
      "epoch": 0.36423067943030585,
      "grad_norm": 0.0475325963052214,
      "learning_rate": 0.00019907681024595663,
      "loss": 2.2191,
      "step": 390
    },
    {
      "epoch": 0.3735699276208265,
      "grad_norm": 0.054089563211590065,
      "learning_rate": 0.00019896910771241387,
      "loss": 2.1961,
      "step": 400
    }
  ],
  "logging_steps": 10,
  "max_steps": 4280,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.2388055677114778e+19,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}