{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9942004971002486,
  "eval_steps": 500,
  "global_step": 1200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "grad_norm": 0.7059583067893982,
      "learning_rate": 0.0002,
      "loss": 1.1809,
      "step": 25
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.6619198322296143,
      "learning_rate": 0.0002,
      "loss": 0.5511,
      "step": 50
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.37209564447402954,
      "learning_rate": 0.0002,
      "loss": 0.833,
      "step": 75
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.5066412091255188,
      "learning_rate": 0.0002,
      "loss": 0.497,
      "step": 100
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.5964956283569336,
      "learning_rate": 0.0002,
      "loss": 0.77,
      "step": 125
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.6351748108863831,
      "learning_rate": 0.0002,
      "loss": 0.4792,
      "step": 150
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.33565786480903625,
      "learning_rate": 0.0002,
      "loss": 0.6867,
      "step": 175
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.5637449622154236,
      "learning_rate": 0.0002,
      "loss": 0.4725,
      "step": 200
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.29314109683036804,
      "learning_rate": 0.0002,
      "loss": 0.6842,
      "step": 225
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.5340172052383423,
      "learning_rate": 0.0002,
      "loss": 0.4269,
      "step": 250
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.38599228858947754,
      "learning_rate": 0.0002,
      "loss": 0.6939,
      "step": 275
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.5987310409545898,
      "learning_rate": 0.0002,
      "loss": 0.4435,
      "step": 300
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.3571007549762726,
      "learning_rate": 0.0002,
      "loss": 0.6976,
      "step": 325
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.5330923199653625,
      "learning_rate": 0.0002,
      "loss": 0.415,
      "step": 350
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.4177188277244568,
      "learning_rate": 0.0002,
      "loss": 0.6663,
      "step": 375
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.5220038890838623,
      "learning_rate": 0.0002,
      "loss": 0.4305,
      "step": 400
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.40320834517478943,
      "learning_rate": 0.0002,
      "loss": 0.6978,
      "step": 425
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.3986828625202179,
      "learning_rate": 0.0002,
      "loss": 0.392,
      "step": 450
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.3662169873714447,
      "learning_rate": 0.0002,
      "loss": 0.6647,
      "step": 475
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.4708826541900635,
      "learning_rate": 0.0002,
      "loss": 0.4119,
      "step": 500
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.3558133840560913,
      "learning_rate": 0.0002,
      "loss": 0.6364,
      "step": 525
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.5110255479812622,
      "learning_rate": 0.0002,
      "loss": 0.3949,
      "step": 550
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.4202500581741333,
      "learning_rate": 0.0002,
      "loss": 0.6034,
      "step": 575
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.7778056263923645,
      "learning_rate": 0.0002,
      "loss": 0.389,
      "step": 600
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.42499253153800964,
      "learning_rate": 0.0002,
      "loss": 0.6453,
      "step": 625
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.4130938947200775,
      "learning_rate": 0.0002,
      "loss": 0.3776,
      "step": 650
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.38256368041038513,
      "learning_rate": 0.0002,
      "loss": 0.5631,
      "step": 675
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.6242409944534302,
      "learning_rate": 0.0002,
      "loss": 0.3771,
      "step": 700
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.3617693781852722,
      "learning_rate": 0.0002,
      "loss": 0.5804,
      "step": 725
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.3799505829811096,
      "learning_rate": 0.0002,
      "loss": 0.3513,
      "step": 750
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.32906627655029297,
      "learning_rate": 0.0002,
      "loss": 0.5393,
      "step": 775
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.4239194989204407,
      "learning_rate": 0.0002,
      "loss": 0.3636,
      "step": 800
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.4123442769050598,
      "learning_rate": 0.0002,
      "loss": 0.5279,
      "step": 825
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.4623079001903534,
      "learning_rate": 0.0002,
      "loss": 0.3821,
      "step": 850
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.3831407427787781,
      "learning_rate": 0.0002,
      "loss": 0.5286,
      "step": 875
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.48481571674346924,
      "learning_rate": 0.0002,
      "loss": 0.3588,
      "step": 900
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.36328190565109253,
      "learning_rate": 0.0002,
      "loss": 0.5519,
      "step": 925
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.4488459527492523,
      "learning_rate": 0.0002,
      "loss": 0.3833,
      "step": 950
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.39116260409355164,
      "learning_rate": 0.0002,
      "loss": 0.5035,
      "step": 975
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.4923652410507202,
      "learning_rate": 0.0002,
      "loss": 0.3178,
      "step": 1000
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.38706672191619873,
      "learning_rate": 0.0002,
      "loss": 0.5357,
      "step": 1025
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.3919411897659302,
      "learning_rate": 0.0002,
      "loss": 0.3329,
      "step": 1050
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.44446566700935364,
      "learning_rate": 0.0002,
      "loss": 0.4754,
      "step": 1075
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.3222676217556,
      "learning_rate": 0.0002,
      "loss": 0.3128,
      "step": 1100
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.3832922577857971,
      "learning_rate": 0.0002,
      "loss": 0.5655,
      "step": 1125
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.5052505135536194,
      "learning_rate": 0.0002,
      "loss": 0.3673,
      "step": 1150
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.3186209797859192,
      "learning_rate": 0.0002,
      "loss": 0.4993,
      "step": 1175
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.5416242480278015,
      "learning_rate": 0.0002,
      "loss": 0.3399,
      "step": 1200
    }
  ],
  "logging_steps": 25,
  "max_steps": 1207,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "total_flos": 6.735879205561958e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}