{
  "best_global_step": 360,
  "best_metric": 0.0664404109120369,
  "best_model_checkpoint": "output/checkpoint-360",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 360,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 2.006798028945923,
      "learning_rate": 1.9016666666666667e-05,
      "loss": 0.2231,
      "step": 60
    },
    {
      "epoch": 1.0,
      "eval_Choice Accuracy": 0.5462184873949579,
      "eval_accuracy": 0.9513395297977036,
      "eval_f1": 0.2898550724637681,
      "eval_loss": 0.17154821753501892,
      "eval_precision": 0.9459459459459459,
      "eval_recall": 0.17114914425427874,
      "eval_runtime": 1.5905,
      "eval_samples_per_second": 149.643,
      "eval_steps_per_second": 9.431,
      "step": 60
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.6001079082489014,
      "learning_rate": 1.801666666666667e-05,
      "loss": 0.1307,
      "step": 120
    },
    {
      "epoch": 2.0,
      "eval_Choice Accuracy": 0.7436974789915967,
      "eval_accuracy": 0.9628212137780208,
      "eval_f1": 0.4742268041237114,
      "eval_loss": 0.10555455088615417,
      "eval_precision": 0.7976878612716763,
      "eval_recall": 0.3374083129584352,
      "eval_runtime": 1.8397,
      "eval_samples_per_second": 129.371,
      "eval_steps_per_second": 8.154,
      "step": 120
    },
    {
      "epoch": 3.0,
      "grad_norm": 3.015130043029785,
      "learning_rate": 1.701666666666667e-05,
      "loss": 0.0815,
      "step": 180
    },
    {
      "epoch": 3.0,
      "eval_Choice Accuracy": 0.819327731092437,
      "eval_accuracy": 0.9652815746309459,
      "eval_f1": 0.5742821473158551,
      "eval_loss": 0.09736118465662003,
      "eval_precision": 0.5867346938775511,
      "eval_recall": 0.5623471882640587,
      "eval_runtime": 1.8771,
      "eval_samples_per_second": 126.794,
      "eval_steps_per_second": 7.991,
      "step": 180
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.7551047801971436,
      "learning_rate": 1.601666666666667e-05,
      "loss": 0.0613,
      "step": 240
    },
    {
      "epoch": 4.0,
      "eval_Choice Accuracy": 0.8487394957983193,
      "eval_accuracy": 0.9748496446145435,
      "eval_f1": 0.6547945205479452,
      "eval_loss": 0.07617025822401047,
      "eval_precision": 0.7445482866043613,
      "eval_recall": 0.5843520782396088,
      "eval_runtime": 1.3794,
      "eval_samples_per_second": 172.543,
      "eval_steps_per_second": 10.875,
      "step": 240
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.2184863090515137,
      "learning_rate": 1.5016666666666668e-05,
      "loss": 0.0439,
      "step": 300
    },
    {
      "epoch": 5.0,
      "eval_Choice Accuracy": 0.8445378151260504,
      "eval_accuracy": 0.9778567523236742,
      "eval_f1": 0.6936114732724903,
      "eval_loss": 0.0754736065864563,
      "eval_precision": 0.7430167597765364,
      "eval_recall": 0.6503667481662592,
      "eval_runtime": 1.4094,
      "eval_samples_per_second": 168.868,
      "eval_steps_per_second": 10.643,
      "step": 300
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.8118876814842224,
      "learning_rate": 1.4016666666666667e-05,
      "loss": 0.0341,
      "step": 360
    },
    {
      "epoch": 6.0,
      "eval_Choice Accuracy": 0.8739495798319328,
      "eval_accuracy": 0.9784034991798797,
      "eval_f1": 0.7108886107634543,
      "eval_loss": 0.0664404109120369,
      "eval_precision": 0.7282051282051282,
      "eval_recall": 0.6943765281173594,
      "eval_runtime": 1.9941,
      "eval_samples_per_second": 119.35,
      "eval_steps_per_second": 7.522,
      "step": 360
    }
  ],
  "logging_steps": 500,
  "max_steps": 1200,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 287523837076476.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}