{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0034381983840467596,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00034381983840467596,
      "eval_loss": 5.879480838775635,
      "eval_runtime": 170.3546,
      "eval_samples_per_second": 28.758,
      "eval_steps_per_second": 3.598,
      "step": 1
    },
    {
      "epoch": 0.0010314595152140279,
      "grad_norm": 41.21235275268555,
      "learning_rate": 3e-05,
      "loss": 5.2239,
      "step": 3
    },
    {
      "epoch": 0.0017190991920233798,
      "eval_loss": 1.8665575981140137,
      "eval_runtime": 171.959,
      "eval_samples_per_second": 28.489,
      "eval_steps_per_second": 3.565,
      "step": 5
    },
    {
      "epoch": 0.0020629190304280558,
      "grad_norm": 10.785271644592285,
      "learning_rate": 6e-05,
      "loss": 2.5669,
      "step": 6
    },
    {
      "epoch": 0.0030943785456420837,
      "grad_norm": 4.260767459869385,
      "learning_rate": 9e-05,
      "loss": 1.0414,
      "step": 9
    },
    {
      "epoch": 0.0034381983840467596,
      "eval_loss": 0.7525524497032166,
      "eval_runtime": 171.9965,
      "eval_samples_per_second": 28.483,
      "eval_steps_per_second": 3.564,
      "step": 10
    }
  ],
  "logging_steps": 3,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4050775588208640.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}