{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 20.0,
  "eval_steps": 500,
  "global_step": 860,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.004207057412713766,
      "eval_runtime": 0.1578,
      "eval_samples_per_second": 190.129,
      "eval_steps_per_second": 12.675,
      "step": 43
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.002545844065025449,
      "eval_runtime": 0.1564,
      "eval_samples_per_second": 191.832,
      "eval_steps_per_second": 12.789,
      "step": 86
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.0006464835605584085,
      "eval_runtime": 0.1569,
      "eval_samples_per_second": 191.159,
      "eval_steps_per_second": 12.744,
      "step": 129
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.0002770782448351383,
      "eval_runtime": 0.1569,
      "eval_samples_per_second": 191.229,
      "eval_steps_per_second": 12.749,
      "step": 172
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.00029143711435608566,
      "eval_runtime": 0.1562,
      "eval_samples_per_second": 192.097,
      "eval_steps_per_second": 12.806,
      "step": 215
    },
    {
      "epoch": 6.0,
      "eval_loss": 6.520080205518752e-05,
      "eval_runtime": 0.1559,
      "eval_samples_per_second": 192.377,
      "eval_steps_per_second": 12.825,
      "step": 258
    },
    {
      "epoch": 7.0,
      "eval_loss": 3.7705922295572236e-05,
      "eval_runtime": 0.1561,
      "eval_samples_per_second": 192.128,
      "eval_steps_per_second": 12.809,
      "step": 301
    },
    {
      "epoch": 8.0,
      "eval_loss": 2.444017445668578e-05,
      "eval_runtime": 0.1561,
      "eval_samples_per_second": 192.181,
      "eval_steps_per_second": 12.812,
      "step": 344
    },
    {
      "epoch": 9.0,
      "eval_loss": 1.7151704014395364e-05,
      "eval_runtime": 0.1562,
      "eval_samples_per_second": 192.076,
      "eval_steps_per_second": 12.805,
      "step": 387
    },
    {
      "epoch": 10.0,
      "eval_loss": 1.1983110198343638e-05,
      "eval_runtime": 0.1562,
      "eval_samples_per_second": 192.062,
      "eval_steps_per_second": 12.804,
      "step": 430
    },
    {
      "epoch": 11.0,
      "eval_loss": 1.2086143215128686e-05,
      "eval_runtime": 0.1562,
      "eval_samples_per_second": 192.099,
      "eval_steps_per_second": 12.807,
      "step": 473
    },
    {
      "epoch": 11.627906976744185,
      "grad_norm": 0.004694207105785608,
      "learning_rate": 2.0930232558139536e-05,
      "loss": 0.0246,
      "step": 500
    },
    {
      "epoch": 12.0,
      "eval_loss": 1.0138296602235641e-05,
      "eval_runtime": 0.1562,
      "eval_samples_per_second": 192.095,
      "eval_steps_per_second": 12.806,
      "step": 516
    },
    {
      "epoch": 13.0,
      "eval_loss": 9.665574907558039e-06,
      "eval_runtime": 0.1562,
      "eval_samples_per_second": 192.112,
      "eval_steps_per_second": 12.807,
      "step": 559
    },
    {
      "epoch": 14.0,
      "eval_loss": 8.772334695095196e-06,
      "eval_runtime": 0.1561,
      "eval_samples_per_second": 192.208,
      "eval_steps_per_second": 12.814,
      "step": 602
    },
    {
      "epoch": 15.0,
      "eval_loss": 8.310395060107112e-06,
      "eval_runtime": 0.1561,
      "eval_samples_per_second": 192.195,
      "eval_steps_per_second": 12.813,
      "step": 645
    },
    {
      "epoch": 16.0,
      "eval_loss": 8.043727575568482e-06,
      "eval_runtime": 0.1559,
      "eval_samples_per_second": 192.403,
      "eval_steps_per_second": 12.827,
      "step": 688
    },
    {
      "epoch": 17.0,
      "eval_loss": 7.7005461207591e-06,
      "eval_runtime": 0.1559,
      "eval_samples_per_second": 192.372,
      "eval_steps_per_second": 12.825,
      "step": 731
    },
    {
      "epoch": 18.0,
      "eval_loss": 7.591055236844113e-06,
      "eval_runtime": 0.1561,
      "eval_samples_per_second": 192.228,
      "eval_steps_per_second": 12.815,
      "step": 774
    },
    {
      "epoch": 19.0,
      "eval_loss": 7.507063401135383e-06,
      "eval_runtime": 0.156,
      "eval_samples_per_second": 192.256,
      "eval_steps_per_second": 12.817,
      "step": 817
    },
    {
      "epoch": 20.0,
      "eval_loss": 7.481100055883871e-06,
      "eval_runtime": 0.1562,
      "eval_samples_per_second": 192.093,
      "eval_steps_per_second": 12.806,
      "step": 860
    }
  ],
  "logging_steps": 500,
  "max_steps": 860,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2214750287232000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}