{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.291139240506329,
  "eval_steps": 500,
  "global_step": 276,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.03,
      "learning_rate": 2.982415005861665e-05,
      "loss": 0.9493,
      "step": 100
    },
    {
      "epoch": 2.05,
      "learning_rate": 2.630715123094959e-05,
      "loss": 0.6097,
      "step": 200
    }
  ],
  "logging_steps": 100,
  "max_steps": 948,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 57710267596800.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}