{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 3180,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9968553459119497,
      "grad_norm": 0.6776733994483948,
      "learning_rate": 1.8006289308176103e-05,
      "loss": 0.4584,
      "step": 317
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6125806451612903,
      "eval_loss": 0.229416161775589,
      "eval_runtime": 1.4059,
      "eval_samples_per_second": 2205.025,
      "eval_steps_per_second": 46.234,
      "step": 318
    },
    {
      "epoch": 1.9937106918238994,
      "grad_norm": 0.5552124977111816,
      "learning_rate": 1.6012578616352204e-05,
      "loss": 0.1874,
      "step": 634
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8419354838709677,
      "eval_loss": 0.10401267558336258,
      "eval_runtime": 1.4225,
      "eval_samples_per_second": 2179.306,
      "eval_steps_per_second": 45.695,
      "step": 636
    },
    {
      "epoch": 2.990566037735849,
      "grad_norm": 0.4675765037536621,
      "learning_rate": 1.4018867924528304e-05,
      "loss": 0.1109,
      "step": 951
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8874193548387097,
      "eval_loss": 0.0649406909942627,
      "eval_runtime": 1.4308,
      "eval_samples_per_second": 2166.649,
      "eval_steps_per_second": 45.43,
      "step": 954
    },
    {
      "epoch": 3.9874213836477987,
      "grad_norm": 0.41055992245674133,
      "learning_rate": 1.2025157232704403e-05,
      "loss": 0.0802,
      "step": 1268
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9067741935483871,
      "eval_loss": 0.04709634184837341,
      "eval_runtime": 1.6361,
      "eval_samples_per_second": 1894.729,
      "eval_steps_per_second": 39.728,
      "step": 1272
    },
    {
      "epoch": 4.984276729559748,
      "grad_norm": 0.31869634985923767,
      "learning_rate": 1.0031446540880504e-05,
      "loss": 0.0644,
      "step": 1585
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.915483870967742,
      "eval_loss": 0.03851104900240898,
      "eval_runtime": 1.4501,
      "eval_samples_per_second": 2137.847,
      "eval_steps_per_second": 44.826,
      "step": 1590
    },
    {
      "epoch": 5.981132075471698,
      "grad_norm": 0.3909931480884552,
      "learning_rate": 8.037735849056606e-06,
      "loss": 0.0554,
      "step": 1902
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9212903225806451,
      "eval_loss": 0.033167432993650436,
      "eval_runtime": 1.8412,
      "eval_samples_per_second": 1683.68,
      "eval_steps_per_second": 35.303,
      "step": 1908
    },
    {
      "epoch": 6.977987421383648,
      "grad_norm": 0.2565544545650482,
      "learning_rate": 6.044025157232704e-06,
      "loss": 0.05,
      "step": 2219
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.927741935483871,
      "eval_loss": 0.03042704612016678,
      "eval_runtime": 1.4492,
      "eval_samples_per_second": 2139.078,
      "eval_steps_per_second": 44.852,
      "step": 2226
    },
    {
      "epoch": 7.9748427672955975,
      "grad_norm": 0.27845093607902527,
      "learning_rate": 4.0503144654088055e-06,
      "loss": 0.0467,
      "step": 2536
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9293548387096774,
      "eval_loss": 0.028363477438688278,
      "eval_runtime": 1.6476,
      "eval_samples_per_second": 1881.537,
      "eval_steps_per_second": 39.452,
      "step": 2544
    },
    {
      "epoch": 8.971698113207546,
      "grad_norm": 0.2760983407497406,
      "learning_rate": 2.056603773584906e-06,
      "loss": 0.0443,
      "step": 2853
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9303225806451613,
      "eval_loss": 0.027360040694475174,
      "eval_runtime": 1.4532,
      "eval_samples_per_second": 2133.234,
      "eval_steps_per_second": 44.729,
      "step": 2862
    },
    {
      "epoch": 9.968553459119496,
      "grad_norm": 0.22213682532310486,
      "learning_rate": 6.289308176100629e-08,
      "loss": 0.0432,
      "step": 3170
    }
  ],
  "logging_steps": 317,
  "max_steps": 3180,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 1000000000.0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 825254092458012.0,
  "train_batch_size": 48,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.7838482405834947,
    "num_train_epochs": 10,
    "temperature": 5
  }
}