{
  "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": 0.29284366965293884,
      "eval_runtime": 0.1577,
      "eval_samples_per_second": 190.244,
      "eval_steps_per_second": 12.683,
      "step": 43
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.2691818177700043,
      "eval_runtime": 0.1568,
      "eval_samples_per_second": 191.3,
      "eval_steps_per_second": 12.753,
      "step": 86
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.2632307708263397,
      "eval_runtime": 0.1568,
      "eval_samples_per_second": 191.27,
      "eval_steps_per_second": 12.751,
      "step": 129
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.34855788946151733,
      "eval_runtime": 0.1567,
      "eval_samples_per_second": 191.438,
      "eval_steps_per_second": 12.763,
      "step": 172
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.38889217376708984,
      "eval_runtime": 0.1565,
      "eval_samples_per_second": 191.657,
      "eval_steps_per_second": 12.777,
      "step": 215
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.39067572355270386,
      "eval_runtime": 0.1562,
      "eval_samples_per_second": 192.01,
      "eval_steps_per_second": 12.801,
      "step": 258
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.3959362208843231,
      "eval_runtime": 0.1562,
      "eval_samples_per_second": 192.037,
      "eval_steps_per_second": 12.802,
      "step": 301
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.4080127477645874,
      "eval_runtime": 0.1561,
      "eval_samples_per_second": 192.227,
      "eval_steps_per_second": 12.815,
      "step": 344
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.4569826126098633,
      "eval_runtime": 0.156,
      "eval_samples_per_second": 192.247,
      "eval_steps_per_second": 12.816,
      "step": 387
    },
    {
      "epoch": 10.0,
      "eval_loss": 0.45514822006225586,
      "eval_runtime": 0.156,
      "eval_samples_per_second": 192.333,
      "eval_steps_per_second": 12.822,
      "step": 430
    },
    {
      "epoch": 11.0,
      "eval_loss": 0.4818161725997925,
      "eval_runtime": 0.1565,
      "eval_samples_per_second": 191.665,
      "eval_steps_per_second": 12.778,
      "step": 473
    },
    {
      "epoch": 11.627906976744185,
      "grad_norm": 0.015772920101881027,
      "learning_rate": 2.0930232558139536e-05,
      "loss": 0.0277,
      "step": 500
    },
    {
      "epoch": 12.0,
      "eval_loss": 0.47729021310806274,
      "eval_runtime": 0.1563,
      "eval_samples_per_second": 191.914,
      "eval_steps_per_second": 12.794,
      "step": 516
    },
    {
      "epoch": 13.0,
      "eval_loss": 0.47969040274620056,
      "eval_runtime": 0.1561,
      "eval_samples_per_second": 192.176,
      "eval_steps_per_second": 12.812,
      "step": 559
    },
    {
      "epoch": 14.0,
      "eval_loss": 0.4873048961162567,
      "eval_runtime": 0.1564,
      "eval_samples_per_second": 191.795,
      "eval_steps_per_second": 12.786,
      "step": 602
    },
    {
      "epoch": 15.0,
      "eval_loss": 0.49304458498954773,
      "eval_runtime": 0.1567,
      "eval_samples_per_second": 191.492,
      "eval_steps_per_second": 12.766,
      "step": 645
    },
    {
      "epoch": 16.0,
      "eval_loss": 0.5004879832267761,
      "eval_runtime": 0.156,
      "eval_samples_per_second": 192.271,
      "eval_steps_per_second": 12.818,
      "step": 688
    },
    {
      "epoch": 17.0,
      "eval_loss": 0.49229252338409424,
      "eval_runtime": 0.1565,
      "eval_samples_per_second": 191.669,
      "eval_steps_per_second": 12.778,
      "step": 731
    },
    {
      "epoch": 18.0,
      "eval_loss": 0.4977598786354065,
      "eval_runtime": 0.1563,
      "eval_samples_per_second": 191.957,
      "eval_steps_per_second": 12.797,
      "step": 774
    },
    {
      "epoch": 19.0,
      "eval_loss": 0.49674493074417114,
      "eval_runtime": 0.1562,
      "eval_samples_per_second": 192.005,
      "eval_steps_per_second": 12.8,
      "step": 817
    },
    {
      "epoch": 20.0,
      "eval_loss": 0.4986058175563812,
      "eval_runtime": 0.1561,
      "eval_samples_per_second": 192.196,
      "eval_steps_per_second": 12.813,
      "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": 2214590118681600.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}