{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 2,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 14.05795955657959,
      "learning_rate": 0.0,
      "loss": 8.357421875,
      "step": 1
    },
    {
      "epoch": 1.0,
      "grad_norm": 13.892364501953125,
      "learning_rate": 2e-05,
      "loss": 8.2734375,
      "step": 2
    },
    {
      "epoch": 1.0,
      "eval_loss": 7.9375,
      "eval_runtime": 0.5609,
      "eval_samples_per_second": 1.783,
      "eval_steps_per_second": 1.783,
      "step": 2
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 2367.38916015625,
      "learning_rate": 1.9457233587073177e-05,
      "loss": 8.337890625,
      "step": 3
    },
    {
      "epoch": 2.0,
      "grad_norm": 49.54719924926758,
      "learning_rate": 1.7894399988070804e-05,
      "loss": 8.17578125,
      "step": 4
    },
    {
      "epoch": 2.0,
      "eval_loss": 7.859375,
      "eval_runtime": 0.556,
      "eval_samples_per_second": 1.799,
      "eval_steps_per_second": 1.799,
      "step": 4
    },
    {
      "checkpoint_runtime": 51.6178
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 17.21331024169922,
      "learning_rate": 1.55e-05,
      "loss": 8.212890625,
      "step": 5
    },
    {
      "epoch": 3.0,
      "grad_norm": 359.53948974609375,
      "learning_rate": 1.2562833599002376e-05,
      "loss": 8.01171875,
      "step": 6
    },
    {
      "epoch": 3.0,
      "eval_loss": 7.703125,
      "eval_runtime": 0.5663,
      "eval_samples_per_second": 1.766,
      "eval_steps_per_second": 1.766,
      "step": 6
    },
    {
      "epoch": 3.6666666666666665,
      "grad_norm": 13.611443519592285,
      "learning_rate": 9.437166400997629e-06,
      "loss": 8.029296875,
      "step": 7
    },
    {
      "checkpoint_runtime": 36.3807
    },
    {
      "epoch": 4.0,
      "grad_norm": 12.36304759979248,
      "learning_rate": 6.500000000000003e-06,
      "loss": 7.875,
      "step": 8
    },
    {
      "epoch": 4.0,
      "eval_loss": 7.59375,
      "eval_runtime": 0.5574,
      "eval_samples_per_second": 1.794,
      "eval_steps_per_second": 1.794,
      "step": 8
    },
    {
      "epoch": 4.666666666666667,
      "grad_norm": 99.58418273925781,
      "learning_rate": 4.1056000119292e-06,
      "loss": 7.8984375,
      "step": 9
    },
    {
      "epoch": 5.0,
      "grad_norm": 20.57093620300293,
      "learning_rate": 2.5427664129268253e-06,
      "loss": 7.78515625,
      "step": 10
    },
    {
      "epoch": 5.0,
      "eval_loss": 7.515625,
      "eval_runtime": 0.5734,
      "eval_samples_per_second": 1.744,
      "eval_steps_per_second": 1.744,
      "step": 10
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.3277264879616e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}