{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0003318001401855592,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.636002803711185e-05,
      "grad_norm": 14.25332260131836,
      "learning_rate": 1e-05,
      "loss": 66.6815,
      "step": 1
    },
    {
      "epoch": 6.636002803711185e-05,
      "eval_loss": 4.063070774078369,
      "eval_runtime": 1133.41,
      "eval_samples_per_second": 22.393,
      "eval_steps_per_second": 11.196,
      "step": 1
    },
    {
      "epoch": 0.0001327200560742237,
      "grad_norm": 15.431291580200195,
      "learning_rate": 2e-05,
      "loss": 65.0114,
      "step": 2
    },
    {
      "epoch": 0.0001327200560742237,
      "eval_loss": 3.975684642791748,
      "eval_runtime": 1581.6506,
      "eval_samples_per_second": 16.047,
      "eval_steps_per_second": 8.023,
      "step": 2
    },
    {
      "epoch": 0.00019908008411133554,
      "grad_norm": 13.938434600830078,
      "learning_rate": 3e-05,
      "loss": 63.2586,
      "step": 3
    },
    {
      "epoch": 0.0002654401121484474,
      "grad_norm": 14.810583114624023,
      "learning_rate": 4e-05,
      "loss": 64.673,
      "step": 4
    },
    {
      "epoch": 0.0002654401121484474,
      "eval_loss": 3.9286255836486816,
      "eval_runtime": 2219.5561,
      "eval_samples_per_second": 11.435,
      "eval_steps_per_second": 5.717,
      "step": 4
    },
    {
      "epoch": 0.0003318001401855592,
      "grad_norm": 16.49462890625,
      "learning_rate": 5e-05,
      "loss": 64.0999,
      "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": 6728226648883200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}