{
  "best_metric": 0.6955057953127977,
  "best_model_checkpoint": "training_dir/checkpoint-3193",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 12772,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 18.625484466552734,
      "learning_rate": 8.556651302390396e-05,
      "loss": 0.5434,
      "step": 3193
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7032342657342657,
      "eval_f1": 0.6955057953127977,
      "eval_loss": 0.7975703477859497,
      "eval_precision": 0.7041608210709965,
      "eval_recall": 0.7032342657342657,
      "eval_runtime": 28.1505,
      "eval_samples_per_second": 81.277,
      "eval_steps_per_second": 10.16,
      "step": 3193
    },
    {
      "epoch": 2.0,
      "grad_norm": 5.77304220199585,
      "learning_rate": 6.845321041912317e-05,
      "loss": 0.4074,
      "step": 6386
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6949300699300699,
      "eval_f1": 0.6823610266682923,
      "eval_loss": 0.924788236618042,
      "eval_precision": 0.7103822719661986,
      "eval_recall": 0.6949300699300699,
      "eval_runtime": 27.588,
      "eval_samples_per_second": 82.935,
      "eval_steps_per_second": 10.367,
      "step": 6386
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.819491386413574,
      "learning_rate": 5.133990781434238e-05,
      "loss": 0.3055,
      "step": 9579
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.701486013986014,
      "eval_f1": 0.6919818652606103,
      "eval_loss": 1.0237421989440918,
      "eval_precision": 0.7083863484072258,
      "eval_recall": 0.701486013986014,
      "eval_runtime": 27.7356,
      "eval_samples_per_second": 82.493,
      "eval_steps_per_second": 10.312,
      "step": 9579
    },
    {
      "epoch": 4.0,
      "grad_norm": 7.0213212966918945,
      "learning_rate": 6.0954502068087814e-05,
      "loss": 0.2568,
      "step": 12772
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6853146853146853,
      "eval_f1": 0.6752368731633129,
      "eval_loss": 1.3729437589645386,
      "eval_precision": 0.6983670162522349,
      "eval_recall": 0.6853146853146853,
      "eval_runtime": 30.1468,
      "eval_samples_per_second": 75.895,
      "eval_steps_per_second": 9.487,
      "step": 12772
    }
  ],
  "logging_steps": 500,
  "max_steps": 31930,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.6676379106990172e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}