{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01011804384485666,
  "eval_steps": 3,
  "global_step": 3,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003372681281618887,
      "grad_norm": 1.5322465896606445,
      "learning_rate": 2e-05,
      "loss": 3.6562,
      "step": 1
    },
    {
      "epoch": 0.003372681281618887,
      "eval_loss": 3.238746166229248,
      "eval_runtime": 5.1939,
      "eval_samples_per_second": 24.067,
      "eval_steps_per_second": 12.13,
      "step": 1
    },
    {
      "epoch": 0.006745362563237774,
      "grad_norm": 1.212786078453064,
      "learning_rate": 4e-05,
      "loss": 2.7946,
      "step": 2
    },
    {
      "epoch": 0.01011804384485666,
      "grad_norm": 1.168325662612915,
      "learning_rate": 6e-05,
      "loss": 2.9507,
      "step": 3
    },
    {
      "epoch": 0.01011804384485666,
      "eval_loss": 3.235896348953247,
      "eval_runtime": 3.8081,
      "eval_samples_per_second": 32.824,
      "eval_steps_per_second": 16.544,
      "step": 3
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 554869274443776.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}