{
  "best_metric": 2.6048855781555176,
  "best_model_checkpoint": "./outputs/checkpoint-400",
  "epoch": 0.29143897996357016,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 2.8181,
      "step": 100
    },
    {
      "epoch": 0.07,
      "eval_loss": 2.7240540981292725,
      "eval_runtime": 204.8489,
      "eval_samples_per_second": 30.627,
      "eval_steps_per_second": 3.832,
      "step": 100
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 2.6957,
      "step": 200
    },
    {
      "epoch": 0.15,
      "eval_loss": 2.6725997924804688,
      "eval_runtime": 204.875,
      "eval_samples_per_second": 30.624,
      "eval_steps_per_second": 3.832,
      "step": 200
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 2.6509,
      "step": 300
    },
    {
      "epoch": 0.22,
      "eval_loss": 2.6377696990966797,
      "eval_runtime": 204.8779,
      "eval_samples_per_second": 30.623,
      "eval_steps_per_second": 3.832,
      "step": 300
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 2.6248,
      "step": 400
    },
    {
      "epoch": 0.29,
      "eval_loss": 2.6048855781555176,
      "eval_runtime": 204.7551,
      "eval_samples_per_second": 30.641,
      "eval_steps_per_second": 3.834,
      "step": 400
    }
  ],
  "logging_steps": 100,
  "max_steps": 4116,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 1.139596603342848e+16,
  "trial_name": null,
  "trial_params": null
}