{
  "best_global_step": 2256,
  "best_metric": 0.48205676927669955,
  "best_model_checkpoint": "./results-seed-42-freezed/checkpoint-2256",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 2256,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8229790419161677,
      "eval_f1": 0.32451264950625497,
      "eval_loss": 0.5109156370162964,
      "eval_precision": 0.53082419648798,
      "eval_recall": 0.3455268053441569,
      "eval_runtime": 4.554,
      "eval_samples_per_second": 586.731,
      "eval_steps_per_second": 9.223,
      "step": 376
    },
    {
      "epoch": 1.3297872340425532,
      "grad_norm": 0.5691885352134705,
      "learning_rate": 9.98e-05,
      "loss": 0.5995,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8267215568862275,
      "eval_f1": 0.36801346394529455,
      "eval_loss": 0.48643776774406433,
      "eval_precision": 0.6442717905875801,
      "eval_recall": 0.36896476902507747,
      "eval_runtime": 4.5296,
      "eval_samples_per_second": 589.891,
      "eval_steps_per_second": 9.272,
      "step": 752
    },
    {
      "epoch": 2.6595744680851063,
      "grad_norm": 0.6735982894897461,
      "learning_rate": 9.727322404371585e-05,
      "loss": 0.4754,
      "step": 1000
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8353293413173652,
      "eval_f1": 0.4467028973064551,
      "eval_loss": 0.4657866954803467,
      "eval_precision": 0.6754830477579293,
      "eval_recall": 0.42942381513071615,
      "eval_runtime": 4.5711,
      "eval_samples_per_second": 584.539,
      "eval_steps_per_second": 9.188,
      "step": 1128
    },
    {
      "epoch": 3.9893617021276597,
      "grad_norm": 0.703115701675415,
      "learning_rate": 9.454098360655738e-05,
      "loss": 0.4737,
      "step": 1500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8383233532934131,
      "eval_f1": 0.4672235493347785,
      "eval_loss": 0.453623503446579,
      "eval_precision": 0.6593676995267452,
      "eval_recall": 0.44240927409704867,
      "eval_runtime": 4.5667,
      "eval_samples_per_second": 585.1,
      "eval_steps_per_second": 9.197,
      "step": 1504
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8383233532934131,
      "eval_f1": 0.48181467839597186,
      "eval_loss": 0.45717039704322815,
      "eval_precision": 0.6458404196784598,
      "eval_recall": 0.46446333470542994,
      "eval_runtime": 4.5653,
      "eval_samples_per_second": 585.282,
      "eval_steps_per_second": 9.2,
      "step": 1880
    },
    {
      "epoch": 5.319148936170213,
      "grad_norm": 0.7036514282226562,
      "learning_rate": 9.180874316939892e-05,
      "loss": 0.4664,
      "step": 2000
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8394461077844312,
      "eval_f1": 0.48205676927669955,
      "eval_loss": 0.45077577233314514,
      "eval_precision": 0.6532546572131603,
      "eval_recall": 0.44658124567231144,
      "eval_runtime": 4.5712,
      "eval_samples_per_second": 584.533,
      "eval_steps_per_second": 9.188,
      "step": 2256
    }
  ],
  "logging_steps": 500,
  "max_steps": 18800,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4743934921635840.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}