{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.170731707317073,
  "eval_steps": 500,
  "global_step": 900,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 8e-05,
      "loss": 0.5555,
      "step": 20
    },
    {
      "epoch": 0.05,
      "learning_rate": 8e-05,
      "loss": 0.4856,
      "step": 40
    },
    {
      "epoch": 0.08,
      "learning_rate": 8e-05,
      "loss": 0.427,
      "step": 60
    },
    {
      "epoch": 0.1,
      "learning_rate": 8e-05,
      "loss": 0.4319,
      "step": 80
    },
    {
      "epoch": 0.13,
      "learning_rate": 8e-05,
      "loss": 0.4089,
      "step": 100
    },
    {
      "epoch": 0.16,
      "learning_rate": 8e-05,
      "loss": 0.3895,
      "step": 120
    },
    {
      "epoch": 0.18,
      "learning_rate": 8e-05,
      "loss": 0.3859,
      "step": 140
    },
    {
      "epoch": 0.21,
      "learning_rate": 8e-05,
      "loss": 0.3714,
      "step": 160
    },
    {
      "epoch": 0.23,
      "learning_rate": 8e-05,
      "loss": 0.3563,
      "step": 180
    },
    {
      "epoch": 0.26,
      "learning_rate": 8e-05,
      "loss": 0.3631,
      "step": 200
    },
    {
      "epoch": 0.29,
      "learning_rate": 8e-05,
      "loss": 0.3691,
      "step": 220
    },
    {
      "epoch": 0.31,
      "learning_rate": 8e-05,
      "loss": 0.3657,
      "step": 240
    },
    {
      "epoch": 0.34,
      "learning_rate": 8e-05,
      "loss": 0.3652,
      "step": 260
    },
    {
      "epoch": 0.36,
      "learning_rate": 8e-05,
      "loss": 0.3474,
      "step": 280
    },
    {
      "epoch": 0.39,
      "learning_rate": 8e-05,
      "loss": 0.3553,
      "step": 300
    },
    {
      "epoch": 0.42,
      "learning_rate": 8e-05,
      "loss": 0.3438,
      "step": 320
    },
    {
      "epoch": 0.44,
      "learning_rate": 8e-05,
      "loss": 0.3713,
      "step": 340
    },
    {
      "epoch": 0.47,
      "learning_rate": 8e-05,
      "loss": 0.3454,
      "step": 360
    },
    {
      "epoch": 0.49,
      "learning_rate": 8e-05,
      "loss": 0.3594,
      "step": 380
    },
    {
      "epoch": 0.52,
      "learning_rate": 8e-05,
      "loss": 0.3613,
      "step": 400
    },
    {
      "epoch": 0.55,
      "learning_rate": 8e-05,
      "loss": 0.3329,
      "step": 420
    },
    {
      "epoch": 0.57,
      "learning_rate": 8e-05,
      "loss": 0.3466,
      "step": 440
    },
    {
      "epoch": 0.6,
      "learning_rate": 8e-05,
      "loss": 0.3408,
      "step": 460
    },
    {
      "epoch": 0.62,
      "learning_rate": 8e-05,
      "loss": 0.3393,
      "step": 480
    },
    {
      "epoch": 0.65,
      "learning_rate": 8e-05,
      "loss": 0.338,
      "step": 500
    },
    {
      "epoch": 0.68,
      "learning_rate": 8e-05,
      "loss": 0.328,
      "step": 520
    },
    {
      "epoch": 0.7,
      "learning_rate": 8e-05,
      "loss": 0.3292,
      "step": 540
    },
    {
      "epoch": 0.73,
      "learning_rate": 8e-05,
      "loss": 0.3321,
      "step": 560
    },
    {
      "epoch": 0.75,
      "learning_rate": 8e-05,
      "loss": 0.3296,
      "step": 580
    },
    {
      "epoch": 0.78,
      "learning_rate": 8e-05,
      "loss": 0.3328,
      "step": 600
    },
    {
      "epoch": 0.81,
      "learning_rate": 8e-05,
      "loss": 0.3197,
      "step": 620
    },
    {
      "epoch": 0.83,
      "learning_rate": 8e-05,
      "loss": 0.3401,
      "step": 640
    },
    {
      "epoch": 0.86,
      "learning_rate": 8e-05,
      "loss": 0.3211,
      "step": 660
    },
    {
      "epoch": 0.88,
      "learning_rate": 8e-05,
      "loss": 0.3383,
      "step": 680
    },
    {
      "epoch": 0.91,
      "learning_rate": 8e-05,
      "loss": 0.3053,
      "step": 700
    },
    {
      "epoch": 0.94,
      "learning_rate": 8e-05,
      "loss": 0.3252,
      "step": 720
    },
    {
      "epoch": 0.96,
      "learning_rate": 8e-05,
      "loss": 0.3228,
      "step": 740
    },
    {
      "epoch": 0.99,
      "learning_rate": 8e-05,
      "loss": 0.333,
      "step": 760
    },
    {
      "epoch": 1.01,
      "learning_rate": 8e-05,
      "loss": 0.3095,
      "step": 780
    },
    {
      "epoch": 1.04,
      "learning_rate": 8e-05,
      "loss": 0.3179,
      "step": 800
    },
    {
      "epoch": 1.07,
      "learning_rate": 8e-05,
      "loss": 0.2828,
      "step": 820
    },
    {
      "epoch": 1.09,
      "learning_rate": 8e-05,
      "loss": 0.2855,
      "step": 840
    },
    {
      "epoch": 1.12,
      "learning_rate": 8e-05,
      "loss": 0.3027,
      "step": 860
    },
    {
      "epoch": 1.14,
      "learning_rate": 8e-05,
      "loss": 0.2984,
      "step": 880
    },
    {
      "epoch": 1.17,
      "learning_rate": 8e-05,
      "loss": 0.2772,
      "step": 900
    }
  ],
  "logging_steps": 20,
  "max_steps": 1536,
  "num_train_epochs": 2,
  "save_steps": 150,
  "total_flos": 2.4621551714304e+17,
  "trial_name": null,
  "trial_params": null
}