{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0053583389149363695,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0010716677829872739,
      "grad_norm": 8.334457397460938,
      "learning_rate": 1e-05,
      "loss": 11.4882,
      "step": 1
    },
    {
      "epoch": 0.0010716677829872739,
      "eval_loss": 0.6531410813331604,
      "eval_runtime": 89.0519,
      "eval_samples_per_second": 17.653,
      "eval_steps_per_second": 8.826,
      "step": 1
    },
    {
      "epoch": 0.0021433355659745477,
      "grad_norm": 10.081873893737793,
      "learning_rate": 2e-05,
      "loss": 10.8269,
      "step": 2
    },
    {
      "epoch": 0.0021433355659745477,
      "eval_loss": 0.6513418555259705,
      "eval_runtime": 78.0715,
      "eval_samples_per_second": 20.135,
      "eval_steps_per_second": 10.068,
      "step": 2
    },
    {
      "epoch": 0.003215003348961822,
      "grad_norm": 8.672450065612793,
      "learning_rate": 3e-05,
      "loss": 9.3279,
      "step": 3
    },
    {
      "epoch": 0.0042866711319490955,
      "grad_norm": 9.168708801269531,
      "learning_rate": 4e-05,
      "loss": 7.7013,
      "step": 4
    },
    {
      "epoch": 0.0042866711319490955,
      "eval_loss": 0.6460770964622498,
      "eval_runtime": 78.5386,
      "eval_samples_per_second": 20.016,
      "eval_steps_per_second": 10.008,
      "step": 4
    },
    {
      "epoch": 0.0053583389149363695,
      "grad_norm": 7.703738212585449,
      "learning_rate": 5e-05,
      "loss": 5.7005,
      "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": 5783810293628928.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}