{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.003128544053810958,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006257088107621915,
      "grad_norm": 3.1676058769226074,
      "learning_rate": 1e-05,
      "loss": 2.2992,
      "step": 1
    },
    {
      "epoch": 0.0006257088107621915,
      "eval_loss": 2.4728379249572754,
      "eval_runtime": 139.829,
      "eval_samples_per_second": 19.252,
      "eval_steps_per_second": 9.626,
      "step": 1
    },
    {
      "epoch": 0.001251417621524383,
      "grad_norm": 3.4991164207458496,
      "learning_rate": 2e-05,
      "loss": 2.2847,
      "step": 2
    },
    {
      "epoch": 0.001251417621524383,
      "eval_loss": 2.3617143630981445,
      "eval_runtime": 100.7057,
      "eval_samples_per_second": 26.731,
      "eval_steps_per_second": 13.366,
      "step": 2
    },
    {
      "epoch": 0.0018771264322865746,
      "grad_norm": 3.2327237129211426,
      "learning_rate": 3e-05,
      "loss": 2.207,
      "step": 3
    },
    {
      "epoch": 0.002502835243048766,
      "grad_norm": 2.9982106685638428,
      "learning_rate": 4e-05,
      "loss": 2.0214,
      "step": 4
    },
    {
      "epoch": 0.002502835243048766,
      "eval_loss": 2.208998441696167,
      "eval_runtime": 109.5929,
      "eval_samples_per_second": 24.564,
      "eval_steps_per_second": 12.282,
      "step": 4
    },
    {
      "epoch": 0.003128544053810958,
      "grad_norm": 3.509823799133301,
      "learning_rate": 5e-05,
      "loss": 2.1535,
      "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": 3699128496291840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}