{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004345228396067568,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008690456792135137,
      "grad_norm": 3.762120246887207,
      "learning_rate": 1e-05,
      "loss": 37.3255,
      "step": 1
    },
    {
      "epoch": 0.0008690456792135137,
      "eval_loss": NaN,
      "eval_runtime": 408.0322,
      "eval_samples_per_second": 4.752,
      "eval_steps_per_second": 2.377,
      "step": 1
    },
    {
      "epoch": 0.0017380913584270274,
      "grad_norm": 3.544394016265869,
      "learning_rate": 2e-05,
      "loss": 36.8874,
      "step": 2
    },
    {
      "epoch": 0.0017380913584270274,
      "eval_loss": NaN,
      "eval_runtime": 185.9726,
      "eval_samples_per_second": 10.426,
      "eval_steps_per_second": 5.216,
      "step": 2
    },
    {
      "epoch": 0.002607137037640541,
      "grad_norm": 3.399097204208374,
      "learning_rate": 3e-05,
      "loss": 36.1743,
      "step": 3
    },
    {
      "epoch": 0.003476182716854055,
      "grad_norm": 3.5507702827453613,
      "learning_rate": 4e-05,
      "loss": 36.4031,
      "step": 4
    },
    {
      "epoch": 0.003476182716854055,
      "eval_loss": NaN,
      "eval_runtime": 181.7467,
      "eval_samples_per_second": 10.669,
      "eval_steps_per_second": 5.337,
      "step": 4
    },
    {
      "epoch": 0.004345228396067568,
      "grad_norm": 4.279851913452148,
      "learning_rate": 5e-05,
      "loss": 35.8074,
      "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": 1.10817850687488e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}