{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4835589941972921,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "learning_rate": 4.8388136686009026e-05,
      "loss": 0.6868,
      "step": 100
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.677627337201805e-05,
      "loss": 0.5552,
      "step": 200
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.516441005802708e-05,
      "loss": 0.5657,
      "step": 300
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.355254674403611e-05,
      "loss": 0.4919,
      "step": 400
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.1940683430045136e-05,
      "loss": 0.4673,
      "step": 500
    },
    {
      "epoch": 0.48,
      "eval_loss": 0.4286854565143585,
      "eval_runtime": 157.876,
      "eval_samples_per_second": 13.093,
      "eval_steps_per_second": 1.641,
      "step": 500
    }
  ],
  "logging_steps": 100,
  "max_steps": 3102,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 199388846640000.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}