{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7476635514018691,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.14953271028037382,
      "grad_norm": 24.70459747314453,
      "learning_rate": 1e-05,
      "loss": 6.3688,
      "step": 1
    },
    {
      "epoch": 0.14953271028037382,
      "eval_loss": 6.407728672027588,
      "eval_runtime": 50.3108,
      "eval_samples_per_second": 0.239,
      "eval_steps_per_second": 0.119,
      "step": 1
    },
    {
      "epoch": 0.29906542056074764,
      "grad_norm": 23.470563888549805,
      "learning_rate": 2e-05,
      "loss": 6.6152,
      "step": 2
    },
    {
      "epoch": 0.29906542056074764,
      "eval_loss": 6.1522393226623535,
      "eval_runtime": 0.2343,
      "eval_samples_per_second": 51.22,
      "eval_steps_per_second": 25.61,
      "step": 2
    },
    {
      "epoch": 0.4485981308411215,
      "grad_norm": 24.869779586791992,
      "learning_rate": 3e-05,
      "loss": 6.523,
      "step": 3
    },
    {
      "epoch": 0.5981308411214953,
      "grad_norm": 24.235937118530273,
      "learning_rate": 4e-05,
      "loss": 6.1442,
      "step": 4
    },
    {
      "epoch": 0.5981308411214953,
      "eval_loss": 5.642405033111572,
      "eval_runtime": 0.2584,
      "eval_samples_per_second": 46.445,
      "eval_steps_per_second": 23.223,
      "step": 4
    },
    {
      "epoch": 0.7476635514018691,
      "grad_norm": 26.761653900146484,
      "learning_rate": 5e-05,
      "loss": 5.6265,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 178076327608320.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}