{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9646365422396856,
  "eval_steps": 50000,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03929273084479371,
      "grad_norm": 4.250463008880615,
      "learning_rate": 1.6129032258064516e-06,
      "loss": 0.8414,
      "step": 10
    },
    {
      "epoch": 0.07858546168958742,
      "grad_norm": 2.718027114868164,
      "learning_rate": 3.225806451612903e-06,
      "loss": 0.8388,
      "step": 20
    },
    {
      "epoch": 0.11787819253438114,
      "grad_norm": 1.6809030771255493,
      "learning_rate": 4.838709677419355e-06,
      "loss": 0.6738,
      "step": 30
    },
    {
      "epoch": 0.15717092337917485,
      "grad_norm": 1.230251431465149,
      "learning_rate": 4.998970106077018e-06,
      "loss": 0.5541,
      "step": 40
    },
    {
      "epoch": 0.19646365422396855,
      "grad_norm": 1.1485263109207153,
      "learning_rate": 4.99541106832608e-06,
      "loss": 0.5261,
      "step": 50
    },
    {
      "epoch": 0.2357563850687623,
      "grad_norm": 1.0606619119644165,
      "learning_rate": 4.989313791265896e-06,
      "loss": 0.6025,
      "step": 60
    },
    {
      "epoch": 0.275049115913556,
      "grad_norm": 1.3169667720794678,
      "learning_rate": 4.9806844768198724e-06,
      "loss": 0.571,
      "step": 70
    },
    {
      "epoch": 0.3143418467583497,
      "grad_norm": 1.87986159324646,
      "learning_rate": 4.969531902405652e-06,
      "loss": 0.5795,
      "step": 80
    },
    {
      "epoch": 0.35363457760314343,
      "grad_norm": 1.7818858623504639,
      "learning_rate": 4.955867412007052e-06,
      "loss": 0.5766,
      "step": 90
    },
    {
      "epoch": 0.3929273084479371,
      "grad_norm": 1.3598214387893677,
      "learning_rate": 4.939704904635388e-06,
      "loss": 0.5421,
      "step": 100
    },
    {
      "epoch": 0.43222003929273084,
      "grad_norm": 1.1836585998535156,
      "learning_rate": 4.921060820191909e-06,
      "loss": 0.5133,
      "step": 110
    },
    {
      "epoch": 0.4715127701375246,
      "grad_norm": 1.4962817430496216,
      "learning_rate": 4.8999541227457514e-06,
      "loss": 0.5643,
      "step": 120
    },
    {
      "epoch": 0.5108055009823183,
      "grad_norm": 1.0972118377685547,
      "learning_rate": 4.8764062812443875e-06,
      "loss": 0.5117,
      "step": 130
    },
    {
      "epoch": 0.550098231827112,
      "grad_norm": 1.249541997909546,
      "learning_rate": 4.8504412476762105e-06,
      "loss": 0.5394,
      "step": 140
    },
    {
      "epoch": 0.5893909626719057,
      "grad_norm": 1.2363935708999634,
      "learning_rate": 4.822085432707465e-06,
      "loss": 0.5244,
      "step": 150
    },
    {
      "epoch": 0.6286836935166994,
      "grad_norm": 0.9700586199760437,
      "learning_rate": 4.791367678818299e-06,
      "loss": 0.4974,
      "step": 160
    },
    {
      "epoch": 0.6679764243614931,
      "grad_norm": 1.324613332748413,
      "learning_rate": 4.758319230965267e-06,
      "loss": 0.51,
      "step": 170
    },
    {
      "epoch": 0.7072691552062869,
      "grad_norm": 1.7756155729293823,
      "learning_rate": 4.72297370480012e-06,
      "loss": 0.4972,
      "step": 180
    },
    {
      "epoch": 0.7465618860510805,
      "grad_norm": 1.4743613004684448,
      "learning_rate": 4.685367052477218e-06,
      "loss": 0.4932,
      "step": 190
    },
    {
      "epoch": 0.7858546168958742,
      "grad_norm": 1.4711652994155884,
      "learning_rate": 4.645537526084331e-06,
      "loss": 0.472,
      "step": 200
    },
    {
      "epoch": 0.825147347740668,
      "grad_norm": 1.2896119356155396,
      "learning_rate": 4.603525638734049e-06,
      "loss": 0.5046,
      "step": 210
    },
    {
      "epoch": 0.8644400785854617,
      "grad_norm": 1.195989966392517,
      "learning_rate": 4.559374123355337e-06,
      "loss": 0.5002,
      "step": 220
    },
    {
      "epoch": 0.9037328094302554,
      "grad_norm": 1.3485041856765747,
      "learning_rate": 4.5131278892272e-06,
      "loss": 0.4411,
      "step": 230
    },
    {
      "epoch": 0.9430255402750491,
      "grad_norm": 1.3075335025787354,
      "learning_rate": 4.46483397629863e-06,
      "loss": 0.4711,
      "step": 240
    },
    {
      "epoch": 0.9823182711198428,
      "grad_norm": 1.2377111911773682,
      "learning_rate": 4.414541507341323e-06,
      "loss": 0.4635,
      "step": 250
    },
    {
      "epoch": 1.0216110019646365,
      "grad_norm": 1.4121922254562378,
      "learning_rate": 4.362301637983815e-06,
      "loss": 0.4179,
      "step": 260
    },
    {
      "epoch": 1.0609037328094302,
      "grad_norm": 1.6095746755599976,
      "learning_rate": 4.308167504677893e-06,
      "loss": 0.4041,
      "step": 270
    },
    {
      "epoch": 1.1001964636542239,
      "grad_norm": 1.8479869365692139,
      "learning_rate": 4.2521941706501625e-06,
      "loss": 0.3847,
      "step": 280
    },
    {
      "epoch": 1.1394891944990178,
      "grad_norm": 1.4423387050628662,
      "learning_rate": 4.194438569893784e-06,
      "loss": 0.3876,
      "step": 290
    },
    {
      "epoch": 1.1787819253438114,
      "grad_norm": 1.4060430526733398,
      "learning_rate": 4.134959449257335e-06,
      "loss": 0.3743,
      "step": 300
    },
    {
      "epoch": 1.218074656188605,
      "grad_norm": 1.1776665449142456,
      "learning_rate": 4.0738173086896995e-06,
      "loss": 0.3689,
      "step": 310
    },
    {
      "epoch": 1.2573673870333988,
      "grad_norm": 1.248273491859436,
      "learning_rate": 4.011074339701772e-06,
      "loss": 0.3813,
      "step": 320
    },
    {
      "epoch": 1.2966601178781925,
      "grad_norm": 1.229260802268982,
      "learning_rate": 3.946794362107564e-06,
      "loss": 0.3786,
      "step": 330
    },
    {
      "epoch": 1.3359528487229864,
      "grad_norm": 1.7943792343139648,
      "learning_rate": 3.8810427591090635e-06,
      "loss": 0.4117,
      "step": 340
    },
    {
      "epoch": 1.37524557956778,
      "grad_norm": 1.9054116010665894,
      "learning_rate": 3.813886410790879e-06,
      "loss": 0.3861,
      "step": 350
    },
    {
      "epoch": 1.4145383104125737,
      "grad_norm": 1.1942715644836426,
      "learning_rate": 3.7453936260922983e-06,
      "loss": 0.3636,
      "step": 360
    },
    {
      "epoch": 1.4538310412573674,
      "grad_norm": 1.5429688692092896,
      "learning_rate": 3.675634073325981e-06,
      "loss": 0.4099,
      "step": 370
    },
    {
      "epoch": 1.493123772102161,
      "grad_norm": 1.4392579793930054,
      "learning_rate": 3.6046787093139415e-06,
      "loss": 0.381,
      "step": 380
    },
    {
      "epoch": 1.5324165029469548,
      "grad_norm": 1.8450443744659424,
      "learning_rate": 3.5325997072129066e-06,
      "loss": 0.3769,
      "step": 390
    },
    {
      "epoch": 1.5717092337917484,
      "grad_norm": 1.5081740617752075,
      "learning_rate": 3.4594703831024723e-06,
      "loss": 0.3923,
      "step": 400
    },
    {
      "epoch": 1.611001964636542,
      "grad_norm": 1.912083387374878,
      "learning_rate": 3.385365121410706e-06,
      "loss": 0.3653,
      "step": 410
    },
    {
      "epoch": 1.650294695481336,
      "grad_norm": 1.4762853384017944,
      "learning_rate": 3.310359299253082e-06,
      "loss": 0.3544,
      "step": 420
    },
    {
      "epoch": 1.6895874263261297,
      "grad_norm": 1.6862307786941528,
      "learning_rate": 3.234529209761676e-06,
      "loss": 0.3878,
      "step": 430
    },
    {
      "epoch": 1.7288801571709234,
      "grad_norm": 1.4678353071212769,
      "learning_rate": 3.157951984482635e-06,
      "loss": 0.3846,
      "step": 440
    },
    {
      "epoch": 1.768172888015717,
      "grad_norm": 1.1692405939102173,
      "learning_rate": 3.080705514920836e-06,
      "loss": 0.4512,
      "step": 450
    },
    {
      "epoch": 1.807465618860511,
      "grad_norm": 1.5150586366653442,
      "learning_rate": 3.0028683733115417e-06,
      "loss": 0.3761,
      "step": 460
    },
    {
      "epoch": 1.8467583497053046,
      "grad_norm": 1.101525902748108,
      "learning_rate": 2.9245197326996515e-06,
      "loss": 0.3673,
      "step": 470
    },
    {
      "epoch": 1.8860510805500983,
      "grad_norm": 1.644962191581726,
      "learning_rate": 2.845739286407821e-06,
      "loss": 0.3874,
      "step": 480
    },
    {
      "epoch": 1.925343811394892,
      "grad_norm": 1.2484012842178345,
      "learning_rate": 2.7666071669753807e-06,
      "loss": 0.3562,
      "step": 490
    },
    {
      "epoch": 1.9646365422396856,
      "grad_norm": 1.538386583328247,
      "learning_rate": 2.687203864650497e-06,
      "loss": 0.3739,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 1016,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9.214305235265126e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}