{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.5602605863192185,
  "eval_steps": 200,
  "global_step": 1400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.65,
      "learning_rate": 0.0002,
      "loss": 0.5187,
      "step": 200
    },
    {
      "epoch": 0.65,
      "eval_runtime": 128.8218,
      "eval_samples_per_second": 4.006,
      "eval_steps_per_second": 0.132,
      "step": 200
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0002,
      "loss": 0.1455,
      "step": 400
    },
    {
      "epoch": 1.3,
      "eval_runtime": 128.7972,
      "eval_samples_per_second": 4.006,
      "eval_steps_per_second": 0.132,
      "step": 400
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.0002,
      "loss": 0.132,
      "step": 600
    },
    {
      "epoch": 1.95,
      "eval_runtime": 128.8118,
      "eval_samples_per_second": 4.006,
      "eval_steps_per_second": 0.132,
      "step": 600
    },
    {
      "epoch": 2.61,
      "learning_rate": 0.0002,
      "loss": 0.1054,
      "step": 800
    },
    {
      "epoch": 2.61,
      "eval_runtime": 128.7948,
      "eval_samples_per_second": 4.006,
      "eval_steps_per_second": 0.132,
      "step": 800
    },
    {
      "epoch": 3.26,
      "learning_rate": 0.0002,
      "loss": 0.0973,
      "step": 1000
    },
    {
      "epoch": 3.26,
      "eval_runtime": 128.7836,
      "eval_samples_per_second": 4.007,
      "eval_steps_per_second": 0.132,
      "step": 1000
    },
    {
      "epoch": 3.91,
      "learning_rate": 0.0002,
      "loss": 0.0858,
      "step": 1200
    },
    {
      "epoch": 3.91,
      "eval_runtime": 128.986,
      "eval_samples_per_second": 4.0,
      "eval_steps_per_second": 0.132,
      "step": 1200
    },
    {
      "epoch": 4.56,
      "learning_rate": 0.0002,
      "loss": 0.0703,
      "step": 1400
    },
    {
      "epoch": 4.56,
      "eval_runtime": 128.8001,
      "eval_samples_per_second": 4.006,
      "eval_steps_per_second": 0.132,
      "step": 1400
    }
  ],
  "logging_steps": 200,
  "max_steps": 1535,
  "num_train_epochs": 5,
  "save_steps": 200,
  "total_flos": 1.77341374660608e+18,
  "trial_name": null,
  "trial_params": null
}