{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 215.3846153846154,
  "eval_steps": 500,
  "global_step": 700,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.08,
      "learning_rate": 0.0002,
      "loss": 1.1505,
      "step": 10
    },
    {
      "epoch": 6.15,
      "learning_rate": 0.0002,
      "loss": 0.753,
      "step": 20
    },
    {
      "epoch": 9.23,
      "learning_rate": 0.0002,
      "loss": 0.568,
      "step": 30
    },
    {
      "epoch": 12.31,
      "learning_rate": 0.0002,
      "loss": 0.3911,
      "step": 40
    },
    {
      "epoch": 15.38,
      "learning_rate": 0.0002,
      "loss": 0.2373,
      "step": 50
    },
    {
      "epoch": 18.46,
      "learning_rate": 0.0002,
      "loss": 0.1112,
      "step": 60
    },
    {
      "epoch": 21.54,
      "learning_rate": 0.0002,
      "loss": 0.0842,
      "step": 70
    },
    {
      "epoch": 24.62,
      "learning_rate": 0.0002,
      "loss": 0.0736,
      "step": 80
    },
    {
      "epoch": 27.69,
      "learning_rate": 0.0002,
      "loss": 0.0662,
      "step": 90
    },
    {
      "epoch": 30.77,
      "learning_rate": 0.0002,
      "loss": 0.0676,
      "step": 100
    },
    {
      "epoch": 33.85,
      "learning_rate": 0.0002,
      "loss": 0.0632,
      "step": 110
    },
    {
      "epoch": 36.92,
      "learning_rate": 0.0002,
      "loss": 0.0639,
      "step": 120
    },
    {
      "epoch": 40.0,
      "learning_rate": 0.0002,
      "loss": 0.0605,
      "step": 130
    },
    {
      "epoch": 43.08,
      "learning_rate": 0.0002,
      "loss": 0.0605,
      "step": 140
    },
    {
      "epoch": 46.15,
      "learning_rate": 0.0002,
      "loss": 0.0608,
      "step": 150
    },
    {
      "epoch": 49.23,
      "learning_rate": 0.0002,
      "loss": 0.0606,
      "step": 160
    },
    {
      "epoch": 52.31,
      "learning_rate": 0.0002,
      "loss": 0.0614,
      "step": 170
    },
    {
      "epoch": 55.38,
      "learning_rate": 0.0002,
      "loss": 0.0602,
      "step": 180
    },
    {
      "epoch": 58.46,
      "learning_rate": 0.0002,
      "loss": 0.0603,
      "step": 190
    },
    {
      "epoch": 61.54,
      "learning_rate": 0.0002,
      "loss": 0.06,
      "step": 200
    },
    {
      "epoch": 64.62,
      "learning_rate": 0.0002,
      "loss": 0.059,
      "step": 210
    },
    {
      "epoch": 67.69,
      "learning_rate": 0.0002,
      "loss": 0.061,
      "step": 220
    },
    {
      "epoch": 70.77,
      "learning_rate": 0.0002,
      "loss": 0.0612,
      "step": 230
    },
    {
      "epoch": 73.85,
      "learning_rate": 0.0002,
      "loss": 0.0624,
      "step": 240
    },
    {
      "epoch": 76.92,
      "learning_rate": 0.0002,
      "loss": 0.0595,
      "step": 250
    },
    {
      "epoch": 80.0,
      "learning_rate": 0.0002,
      "loss": 0.0601,
      "step": 260
    },
    {
      "epoch": 83.08,
      "learning_rate": 0.0002,
      "loss": 0.0593,
      "step": 270
    },
    {
      "epoch": 86.15,
      "learning_rate": 0.0002,
      "loss": 0.0622,
      "step": 280
    },
    {
      "epoch": 89.23,
      "learning_rate": 0.0002,
      "loss": 0.0607,
      "step": 290
    },
    {
      "epoch": 92.31,
      "learning_rate": 0.0002,
      "loss": 0.0592,
      "step": 300
    },
    {
      "epoch": 95.38,
      "learning_rate": 0.0002,
      "loss": 0.0592,
      "step": 310
    },
    {
      "epoch": 98.46,
      "learning_rate": 0.0002,
      "loss": 0.0597,
      "step": 320
    },
    {
      "epoch": 101.54,
      "learning_rate": 0.0002,
      "loss": 0.0599,
      "step": 330
    },
    {
      "epoch": 104.62,
      "learning_rate": 0.0002,
      "loss": 0.06,
      "step": 340
    },
    {
      "epoch": 107.69,
      "learning_rate": 0.0002,
      "loss": 0.0591,
      "step": 350
    },
    {
      "epoch": 110.77,
      "learning_rate": 0.0002,
      "loss": 0.0593,
      "step": 360
    },
    {
      "epoch": 113.85,
      "learning_rate": 0.0002,
      "loss": 0.0594,
      "step": 370
    },
    {
      "epoch": 116.92,
      "learning_rate": 0.0002,
      "loss": 0.0608,
      "step": 380
    },
    {
      "epoch": 120.0,
      "learning_rate": 0.0002,
      "loss": 0.0597,
      "step": 390
    },
    {
      "epoch": 123.08,
      "learning_rate": 0.0002,
      "loss": 0.06,
      "step": 400
    },
    {
      "epoch": 126.15,
      "learning_rate": 0.0002,
      "loss": 0.0591,
      "step": 410
    },
    {
      "epoch": 129.23,
      "learning_rate": 0.0002,
      "loss": 0.0606,
      "step": 420
    },
    {
      "epoch": 132.31,
      "learning_rate": 0.0002,
      "loss": 0.0609,
      "step": 430
    },
    {
      "epoch": 135.38,
      "learning_rate": 0.0002,
      "loss": 0.0585,
      "step": 440
    },
    {
      "epoch": 138.46,
      "learning_rate": 0.0002,
      "loss": 0.0597,
      "step": 450
    },
    {
      "epoch": 141.54,
      "learning_rate": 0.0002,
      "loss": 0.0609,
      "step": 460
    },
    {
      "epoch": 144.62,
      "learning_rate": 0.0002,
      "loss": 0.0609,
      "step": 470
    },
    {
      "epoch": 147.69,
      "learning_rate": 0.0002,
      "loss": 0.0598,
      "step": 480
    },
    {
      "epoch": 150.77,
      "learning_rate": 0.0002,
      "loss": 0.061,
      "step": 490
    },
    {
      "epoch": 153.85,
      "learning_rate": 0.0002,
      "loss": 0.0606,
      "step": 500
    },
    {
      "epoch": 156.92,
      "learning_rate": 0.0002,
      "loss": 0.0634,
      "step": 510
    },
    {
      "epoch": 160.0,
      "learning_rate": 0.0002,
      "loss": 0.0599,
      "step": 520
    },
    {
      "epoch": 163.08,
      "learning_rate": 0.0002,
      "loss": 0.0611,
      "step": 530
    },
    {
      "epoch": 166.15,
      "learning_rate": 0.0002,
      "loss": 0.0652,
      "step": 540
    },
    {
      "epoch": 169.23,
      "learning_rate": 0.0002,
      "loss": 0.0619,
      "step": 550
    },
    {
      "epoch": 172.31,
      "learning_rate": 0.0002,
      "loss": 0.0618,
      "step": 560
    },
    {
      "epoch": 175.38,
      "learning_rate": 0.0002,
      "loss": 0.0609,
      "step": 570
    },
    {
      "epoch": 178.46,
      "learning_rate": 0.0002,
      "loss": 0.0597,
      "step": 580
    },
    {
      "epoch": 181.54,
      "learning_rate": 0.0002,
      "loss": 0.0607,
      "step": 590
    },
    {
      "epoch": 184.62,
      "learning_rate": 0.0002,
      "loss": 0.06,
      "step": 600
    },
    {
      "epoch": 187.69,
      "learning_rate": 0.0002,
      "loss": 0.0587,
      "step": 610
    },
    {
      "epoch": 190.77,
      "learning_rate": 0.0002,
      "loss": 0.0595,
      "step": 620
    },
    {
      "epoch": 193.85,
      "learning_rate": 0.0002,
      "loss": 0.0592,
      "step": 630
    },
    {
      "epoch": 196.92,
      "learning_rate": 0.0002,
      "loss": 0.0605,
      "step": 640
    },
    {
      "epoch": 200.0,
      "learning_rate": 0.0002,
      "loss": 0.0592,
      "step": 650
    },
    {
      "epoch": 203.08,
      "learning_rate": 0.0002,
      "loss": 0.0616,
      "step": 660
    },
    {
      "epoch": 206.15,
      "learning_rate": 0.0002,
      "loss": 0.0596,
      "step": 670
    },
    {
      "epoch": 209.23,
      "learning_rate": 0.0002,
      "loss": 0.0587,
      "step": 680
    },
    {
      "epoch": 212.31,
      "learning_rate": 0.0002,
      "loss": 0.0614,
      "step": 690
    },
    {
      "epoch": 215.38,
      "learning_rate": 0.0002,
      "loss": 0.0591,
      "step": 700
    }
  ],
  "logging_steps": 10,
  "max_steps": 10000,
  "num_train_epochs": 3334,
  "save_steps": 10,
  "total_flos": 1586920711709184.0,
  "trial_name": null,
  "trial_params": null
}