{
  "best_metric": 2.0298001766204834,
  "best_model_checkpoint": "./outputs/checkpoint-400",
  "epoch": 0.5681818181818182,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 2.4473,
      "step": 100
    },
    {
      "epoch": 0.14,
      "eval_loss": 2.1156835556030273,
      "eval_runtime": 56.5007,
      "eval_samples_per_second": 26.407,
      "eval_steps_per_second": 3.31,
      "step": 100
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 2.253,
      "step": 200
    },
    {
      "epoch": 0.28,
      "eval_loss": 2.073469877243042,
      "eval_runtime": 54.097,
      "eval_samples_per_second": 27.58,
      "eval_steps_per_second": 3.457,
      "step": 200
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 2.2236,
      "step": 300
    },
    {
      "epoch": 0.43,
      "eval_loss": 2.046644687652588,
      "eval_runtime": 53.9984,
      "eval_samples_per_second": 27.63,
      "eval_steps_per_second": 3.463,
      "step": 300
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 2.1911,
      "step": 400
    },
    {
      "epoch": 0.57,
      "eval_loss": 2.0298001766204834,
      "eval_runtime": 54.0695,
      "eval_samples_per_second": 27.594,
      "eval_steps_per_second": 3.459,
      "step": 400
    }
  ],
  "logging_steps": 100,
  "max_steps": 2112,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 1.21510343872512e+16,
  "trial_name": null,
  "trial_params": null
}