{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5140507196710076,
  "eval_steps": 100,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 8.993468091981983e-06,
      "loss": 0.6658,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 8.973891330515647e-06,
      "loss": 0.4496,
      "step": 20
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.941326548314408e-06,
      "loss": 0.3875,
      "step": 30
    },
    {
      "epoch": 0.07,
      "learning_rate": 8.895868283228027e-06,
      "loss": 0.3646,
      "step": 40
    },
    {
      "epoch": 0.09,
      "learning_rate": 8.837648503792598e-06,
      "loss": 0.3664,
      "step": 50
    },
    {
      "epoch": 0.1,
      "learning_rate": 8.766836226116608e-06,
      "loss": 0.3676,
      "step": 60
    },
    {
      "epoch": 0.12,
      "learning_rate": 8.683637023215312e-06,
      "loss": 0.3075,
      "step": 70
    },
    {
      "epoch": 0.14,
      "learning_rate": 8.588292428217834e-06,
      "loss": 0.2945,
      "step": 80
    },
    {
      "epoch": 0.15,
      "learning_rate": 8.481079233179522e-06,
      "loss": 0.3539,
      "step": 90
    },
    {
      "epoch": 0.17,
      "learning_rate": 8.362308685535184e-06,
      "loss": 0.2699,
      "step": 100
    },
    {
      "epoch": 0.17,
      "eval_accuracy": 0.0,
      "eval_loss": 0.27337193489074707,
      "eval_runtime": 53.8814,
      "eval_samples_per_second": 72.214,
      "eval_steps_per_second": 12.045,
      "step": 100
    },
    {
      "epoch": 0.19,
      "learning_rate": 8.232325584525908e-06,
      "loss": 0.2544,
      "step": 110
    },
    {
      "epoch": 0.21,
      "learning_rate": 8.091507280222673e-06,
      "loss": 0.2776,
      "step": 120
    },
    {
      "epoch": 0.22,
      "learning_rate": 7.940262578052568e-06,
      "loss": 0.2941,
      "step": 130
    },
    {
      "epoch": 0.24,
      "learning_rate": 7.779030552007946e-06,
      "loss": 0.2615,
      "step": 140
    },
    {
      "epoch": 0.26,
      "learning_rate": 7.608279269983776e-06,
      "loss": 0.2673,
      "step": 150
    },
    {
      "epoch": 0.27,
      "learning_rate": 7.428504434943677e-06,
      "loss": 0.2524,
      "step": 160
    },
    {
      "epoch": 0.29,
      "learning_rate": 7.240227945859397e-06,
      "loss": 0.2732,
      "step": 170
    },
    {
      "epoch": 0.31,
      "learning_rate": 7.043996382601448e-06,
      "loss": 0.2184,
      "step": 180
    },
    {
      "epoch": 0.33,
      "learning_rate": 6.840379419179357e-06,
      "loss": 0.2578,
      "step": 190
    },
    {
      "epoch": 0.34,
      "learning_rate": 6.629968169938005e-06,
      "loss": 0.2827,
      "step": 200
    },
    {
      "epoch": 0.34,
      "eval_accuracy": 0.0,
      "eval_loss": 0.2310507595539093,
      "eval_runtime": 54.2245,
      "eval_samples_per_second": 71.757,
      "eval_steps_per_second": 11.969,
      "step": 200
    },
    {
      "epoch": 0.36,
      "learning_rate": 6.41337347351117e-06,
      "loss": 0.2426,
      "step": 210
    },
    {
      "epoch": 0.38,
      "learning_rate": 6.191224119514071e-06,
      "loss": 0.2142,
      "step": 220
    },
    {
      "epoch": 0.39,
      "learning_rate": 5.964165023122967e-06,
      "loss": 0.264,
      "step": 230
    },
    {
      "epoch": 0.41,
      "learning_rate": 5.73285535284109e-06,
      "loss": 0.2039,
      "step": 240
    },
    {
      "epoch": 0.43,
      "learning_rate": 5.4979666168862e-06,
      "loss": 0.2163,
      "step": 250
    },
    {
      "epoch": 0.45,
      "learning_rate": 5.260180713755066e-06,
      "loss": 0.2363,
      "step": 260
    },
    {
      "epoch": 0.46,
      "learning_rate": 5.020187952624234e-06,
      "loss": 0.21,
      "step": 270
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.7786850493340155e-06,
      "loss": 0.235,
      "step": 280
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.536373103773464e-06,
      "loss": 0.2067,
      "step": 290
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.2939555645381675e-06,
      "loss": 0.2001,
      "step": 300
    },
    {
      "epoch": 0.51,
      "eval_accuracy": 0.0,
      "eval_loss": 0.19201719760894775,
      "eval_runtime": 53.8375,
      "eval_samples_per_second": 72.273,
      "eval_steps_per_second": 12.055,
      "step": 300
    }
  ],
  "logging_steps": 10,
  "max_steps": 583,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 0.0,
  "trial_name": null,
  "trial_params": null
}