{
  "best_metric": 2.0435657501220703,
  "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": 2.2671,
      "step": 100
    },
    {
      "epoch": 0.07,
      "eval_loss": 2.1813676357269287,
      "eval_runtime": 549.6637,
      "eval_samples_per_second": 11.414,
      "eval_steps_per_second": 1.428,
      "step": 100
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 2.1547,
      "step": 200
    },
    {
      "epoch": 0.15,
      "eval_loss": 2.131509304046631,
      "eval_runtime": 549.883,
      "eval_samples_per_second": 11.41,
      "eval_steps_per_second": 1.428,
      "step": 200
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 2.1088,
      "step": 300
    },
    {
      "epoch": 0.22,
      "eval_loss": 2.0894575119018555,
      "eval_runtime": 550.3941,
      "eval_samples_per_second": 11.399,
      "eval_steps_per_second": 1.426,
      "step": 300
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 2.0681,
      "step": 400
    },
    {
      "epoch": 0.29,
      "eval_loss": 2.0435657501220703,
      "eval_runtime": 550.6916,
      "eval_samples_per_second": 11.393,
      "eval_steps_per_second": 1.425,
      "step": 400
    }
  ],
  "logging_steps": 100,
  "max_steps": 4116,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 1.0422007089758208e+17,
  "trial_name": null,
  "trial_params": null
}