{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 7.317073170731708,
  "eval_steps": 100,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.22,
      "learning_rate": 0.0002,
      "loss": 0.2474,
      "step": 100
    },
    {
      "epoch": 1.22,
      "eval_runtime": 32.4137,
      "eval_samples_per_second": 8.515,
      "eval_steps_per_second": 0.154,
      "step": 100
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.0002,
      "loss": 0.0823,
      "step": 200
    },
    {
      "epoch": 2.44,
      "eval_runtime": 32.4129,
      "eval_samples_per_second": 8.515,
      "eval_steps_per_second": 0.154,
      "step": 200
    },
    {
      "epoch": 3.66,
      "learning_rate": 0.0002,
      "loss": 0.0588,
      "step": 300
    },
    {
      "epoch": 3.66,
      "eval_runtime": 32.4061,
      "eval_samples_per_second": 8.517,
      "eval_steps_per_second": 0.154,
      "step": 300
    },
    {
      "epoch": 4.88,
      "learning_rate": 0.0002,
      "loss": 0.0416,
      "step": 400
    },
    {
      "epoch": 4.88,
      "eval_runtime": 32.39,
      "eval_samples_per_second": 8.521,
      "eval_steps_per_second": 0.154,
      "step": 400
    },
    {
      "epoch": 6.1,
      "learning_rate": 0.0002,
      "loss": 0.0326,
      "step": 500
    },
    {
      "epoch": 6.1,
      "eval_runtime": 32.3822,
      "eval_samples_per_second": 8.523,
      "eval_steps_per_second": 0.154,
      "step": 500
    },
    {
      "epoch": 7.32,
      "learning_rate": 0.0002,
      "loss": 0.0281,
      "step": 600
    },
    {
      "epoch": 7.32,
      "eval_runtime": 32.3958,
      "eval_samples_per_second": 8.52,
      "eval_steps_per_second": 0.154,
      "step": 600
    }
  ],
  "logging_steps": 100,
  "max_steps": 656,
  "num_train_epochs": 8,
  "save_steps": 100,
  "total_flos": 7.731362690236416e+17,
  "trial_name": null,
  "trial_params": null
}