{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.2,
  "eval_steps": 25,
  "global_step": 6,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.05394430458545685,
      "learning_rate": 9.330127018922194e-05,
      "loss": 11.9203,
      "step": 1
    },
    {
      "epoch": 0.5333333333333333,
      "eval_loss": 11.916996955871582,
      "eval_runtime": 0.0693,
      "eval_samples_per_second": 187.696,
      "eval_steps_per_second": 28.876,
      "step": 1
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.050260093063116074,
      "learning_rate": 7.500000000000001e-05,
      "loss": 13.698,
      "step": 2
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.048914991319179535,
      "learning_rate": 5e-05,
      "loss": 11.95,
      "step": 3
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.0473925806581974,
      "learning_rate": 2.500000000000001e-05,
      "loss": 13.0734,
      "step": 4
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.046185776591300964,
      "learning_rate": 6.698729810778065e-06,
      "loss": 12.4052,
      "step": 5
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.04737290367484093,
      "learning_rate": 0.0,
      "loss": 13.1671,
      "step": 6
    }
  ],
  "logging_steps": 1,
  "max_steps": 6,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 125099311104.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}