{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0005316085588977983,
  "eval_steps": 3,
  "global_step": 3,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00017720285296593275,
      "grad_norm": 68.23906707763672,
      "learning_rate": 2e-05,
      "loss": 20.6003,
      "step": 1
    },
    {
      "epoch": 0.00017720285296593275,
      "eval_loss": 4.623178482055664,
      "eval_runtime": 34.268,
      "eval_samples_per_second": 69.365,
      "eval_steps_per_second": 34.697,
      "step": 1
    },
    {
      "epoch": 0.0003544057059318655,
      "grad_norm": 47.974525451660156,
      "learning_rate": 4e-05,
      "loss": 18.135,
      "step": 2
    },
    {
      "epoch": 0.0005316085588977983,
      "grad_norm": 67.08570861816406,
      "learning_rate": 6e-05,
      "loss": 18.75,
      "step": 3
    },
    {
      "epoch": 0.0005316085588977983,
      "eval_loss": 4.618465423583984,
      "eval_runtime": 32.7311,
      "eval_samples_per_second": 72.622,
      "eval_steps_per_second": 36.326,
      "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": 39477854601216.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}