{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 100,
  "global_step": 26,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 3.7109829054102934,
      "learning_rate": 2.5e-05,
      "loss": 1.1307,
      "step": 10
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 2.4317161254882587,
      "learning_rate": 5e-05,
      "loss": 0.8852,
      "step": 20
    },
    {
      "epoch": 2.0,
      "step": 26,
      "total_flos": 6164400701440.0,
      "train_loss": 0.9994903894571158,
      "train_runtime": 76.0045,
      "train_samples_per_second": 5.421,
      "train_steps_per_second": 0.342
    }
  ],
  "logging_steps": 10,
  "max_steps": 26,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6164400701440.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}