{
  "best_global_step": 4356,
  "best_metric": 0.04141305759549141,
  "best_model_checkpoint": "output/checkpoint-4356",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 6534,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.8349515795707703,
      "learning_rate": 1.8334863789409247e-05,
      "loss": 0.0973,
      "step": 1089
    },
    {
      "epoch": 1.0,
      "eval_Choice Accuracy": 0.7571166207529844,
      "eval_accuracy": 0.9789211517434091,
      "eval_f1": 0.6277777777777778,
      "eval_loss": 0.05998045206069946,
      "eval_precision": 0.6979511901175053,
      "eval_recall": 0.5704260034474268,
      "eval_runtime": 33.2607,
      "eval_samples_per_second": 130.965,
      "eval_steps_per_second": 8.208,
      "step": 1089
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.04014253616333,
      "learning_rate": 1.6668197122742578e-05,
      "loss": 0.0534,
      "step": 2178
    },
    {
      "epoch": 2.0,
      "eval_Choice Accuracy": 0.7947658402203857,
      "eval_accuracy": 0.9815433523670676,
      "eval_f1": 0.696259963212753,
      "eval_loss": 0.04922398552298546,
      "eval_precision": 0.6934538348803126,
      "eval_recall": 0.6990888943609949,
      "eval_runtime": 32.3161,
      "eval_samples_per_second": 134.793,
      "eval_steps_per_second": 8.448,
      "step": 2178
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.5665336847305298,
      "learning_rate": 1.5001530456075913e-05,
      "loss": 0.0366,
      "step": 3267
    },
    {
      "epoch": 3.0,
      "eval_Choice Accuracy": 0.8255280073461891,
      "eval_accuracy": 0.9850868667233629,
      "eval_f1": 0.7400103119360659,
      "eval_loss": 0.0441485196352005,
      "eval_precision": 0.7764403570462537,
      "eval_recall": 0.7068456045309037,
      "eval_runtime": 32.1699,
      "eval_samples_per_second": 135.406,
      "eval_steps_per_second": 8.486,
      "step": 3267
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.3968222141265869,
      "learning_rate": 1.3334863789409246e-05,
      "loss": 0.0254,
      "step": 4356
    },
    {
      "epoch": 4.0,
      "eval_Choice Accuracy": 0.8438934802571166,
      "eval_accuracy": 0.9864738994856842,
      "eval_f1": 0.7683744465528147,
      "eval_loss": 0.04141305759549141,
      "eval_precision": 0.7900624349635796,
      "eval_recall": 0.7478453582861364,
      "eval_runtime": 32.2848,
      "eval_samples_per_second": 134.924,
      "eval_steps_per_second": 8.456,
      "step": 4356
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.5384565591812134,
      "learning_rate": 1.1668197122742577e-05,
      "loss": 0.0184,
      "step": 5445
    },
    {
      "epoch": 5.0,
      "eval_Choice Accuracy": 0.8455004591368228,
      "eval_accuracy": 0.986949742842101,
      "eval_f1": 0.7802259534361151,
      "eval_loss": 0.0461677722632885,
      "eval_precision": 0.7912393973920749,
      "eval_recall": 0.7695148978084215,
      "eval_runtime": 32.1947,
      "eval_samples_per_second": 135.302,
      "eval_steps_per_second": 8.48,
      "step": 5445
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.8446656465530396,
      "learning_rate": 1.0001530456075911e-05,
      "loss": 0.0136,
      "step": 6534
    },
    {
      "epoch": 6.0,
      "eval_Choice Accuracy": 0.8551423324150597,
      "eval_accuracy": 0.9878609322480055,
      "eval_f1": 0.7916719242902208,
      "eval_loss": 0.04199245199561119,
      "eval_precision": 0.8118530020703933,
      "eval_recall": 0.7724698350160059,
      "eval_runtime": 32.3395,
      "eval_samples_per_second": 134.696,
      "eval_steps_per_second": 8.442,
      "step": 6534
    }
  ],
  "logging_steps": 500,
  "max_steps": 13068,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 12,
  "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": 6047700295374192.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}