{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.7799511002445,
  "eval_steps": 2000,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "learning_rate": 8e-05,
      "loss": 0.8756,
      "step": 10
    },
    {
      "epoch": 0.39,
      "learning_rate": 8e-05,
      "loss": 0.8401,
      "step": 20
    },
    {
      "epoch": 0.59,
      "learning_rate": 8e-05,
      "loss": 0.8574,
      "step": 30
    },
    {
      "epoch": 0.78,
      "learning_rate": 8e-05,
      "loss": 0.8282,
      "step": 40
    },
    {
      "epoch": 0.98,
      "learning_rate": 8e-05,
      "loss": 0.7797,
      "step": 50
    },
    {
      "epoch": 1.17,
      "learning_rate": 8e-05,
      "loss": 0.7198,
      "step": 60
    },
    {
      "epoch": 1.37,
      "learning_rate": 8e-05,
      "loss": 0.6546,
      "step": 70
    },
    {
      "epoch": 1.56,
      "learning_rate": 8e-05,
      "loss": 0.6477,
      "step": 80
    },
    {
      "epoch": 1.76,
      "learning_rate": 8e-05,
      "loss": 0.6173,
      "step": 90
    },
    {
      "epoch": 1.96,
      "learning_rate": 8e-05,
      "loss": 0.6119,
      "step": 100
    },
    {
      "epoch": 2.15,
      "learning_rate": 8e-05,
      "loss": 0.5535,
      "step": 110
    },
    {
      "epoch": 2.35,
      "learning_rate": 8e-05,
      "loss": 0.4959,
      "step": 120
    },
    {
      "epoch": 2.54,
      "learning_rate": 8e-05,
      "loss": 0.5077,
      "step": 130
    },
    {
      "epoch": 2.74,
      "learning_rate": 8e-05,
      "loss": 0.5021,
      "step": 140
    },
    {
      "epoch": 2.93,
      "learning_rate": 8e-05,
      "loss": 0.4717,
      "step": 150
    },
    {
      "epoch": 3.13,
      "learning_rate": 8e-05,
      "loss": 0.427,
      "step": 160
    },
    {
      "epoch": 3.33,
      "learning_rate": 8e-05,
      "loss": 0.361,
      "step": 170
    },
    {
      "epoch": 3.52,
      "learning_rate": 8e-05,
      "loss": 0.3622,
      "step": 180
    },
    {
      "epoch": 3.72,
      "learning_rate": 8e-05,
      "loss": 0.3425,
      "step": 190
    },
    {
      "epoch": 3.91,
      "learning_rate": 8e-05,
      "loss": 0.3531,
      "step": 200
    },
    {
      "epoch": 4.11,
      "learning_rate": 8e-05,
      "loss": 0.3376,
      "step": 210
    },
    {
      "epoch": 4.3,
      "learning_rate": 8e-05,
      "loss": 0.2356,
      "step": 220
    },
    {
      "epoch": 4.5,
      "learning_rate": 8e-05,
      "loss": 0.2514,
      "step": 230
    },
    {
      "epoch": 4.69,
      "learning_rate": 8e-05,
      "loss": 0.2369,
      "step": 240
    },
    {
      "epoch": 4.89,
      "learning_rate": 8e-05,
      "loss": 0.2485,
      "step": 250
    },
    {
      "epoch": 5.09,
      "learning_rate": 8e-05,
      "loss": 0.2164,
      "step": 260
    },
    {
      "epoch": 5.28,
      "learning_rate": 8e-05,
      "loss": 0.1498,
      "step": 270
    },
    {
      "epoch": 5.48,
      "learning_rate": 8e-05,
      "loss": 0.1495,
      "step": 280
    },
    {
      "epoch": 5.67,
      "learning_rate": 8e-05,
      "loss": 0.166,
      "step": 290
    },
    {
      "epoch": 5.87,
      "learning_rate": 8e-05,
      "loss": 0.2012,
      "step": 300
    },
    {
      "epoch": 6.06,
      "learning_rate": 8e-05,
      "loss": 0.1569,
      "step": 310
    },
    {
      "epoch": 6.26,
      "learning_rate": 8e-05,
      "loss": 0.0878,
      "step": 320
    },
    {
      "epoch": 6.45,
      "learning_rate": 8e-05,
      "loss": 0.0969,
      "step": 330
    },
    {
      "epoch": 6.65,
      "learning_rate": 8e-05,
      "loss": 0.1229,
      "step": 340
    },
    {
      "epoch": 6.85,
      "learning_rate": 8e-05,
      "loss": 0.1199,
      "step": 350
    },
    {
      "epoch": 7.04,
      "learning_rate": 8e-05,
      "loss": 0.0996,
      "step": 360
    },
    {
      "epoch": 7.24,
      "learning_rate": 8e-05,
      "loss": 0.0568,
      "step": 370
    },
    {
      "epoch": 7.43,
      "learning_rate": 8e-05,
      "loss": 0.0792,
      "step": 380
    },
    {
      "epoch": 7.63,
      "learning_rate": 8e-05,
      "loss": 0.0781,
      "step": 390
    },
    {
      "epoch": 7.82,
      "learning_rate": 8e-05,
      "loss": 0.0852,
      "step": 400
    },
    {
      "epoch": 8.02,
      "learning_rate": 8e-05,
      "loss": 0.0611,
      "step": 410
    },
    {
      "epoch": 8.22,
      "learning_rate": 8e-05,
      "loss": 0.0399,
      "step": 420
    },
    {
      "epoch": 8.41,
      "learning_rate": 8e-05,
      "loss": 0.0597,
      "step": 430
    },
    {
      "epoch": 8.61,
      "learning_rate": 8e-05,
      "loss": 0.0502,
      "step": 440
    },
    {
      "epoch": 8.8,
      "learning_rate": 8e-05,
      "loss": 0.0535,
      "step": 450
    },
    {
      "epoch": 9.0,
      "learning_rate": 8e-05,
      "loss": 0.0347,
      "step": 460
    },
    {
      "epoch": 9.19,
      "learning_rate": 8e-05,
      "loss": 0.0323,
      "step": 470
    },
    {
      "epoch": 9.39,
      "learning_rate": 8e-05,
      "loss": 0.039,
      "step": 480
    },
    {
      "epoch": 9.58,
      "learning_rate": 8e-05,
      "loss": 0.0335,
      "step": 490
    },
    {
      "epoch": 9.78,
      "learning_rate": 8e-05,
      "loss": 0.0364,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 100000,
  "num_train_epochs": 1961,
  "save_steps": 500,
  "total_flos": 3.9296655213613056e+17,
  "trial_name": null,
  "trial_params": null
}