CatBoost issue with solar flare dataset

[duncanmcelfresh]

only occurs with dataset openml__solar-flare__2068

traceback:

Traceback (most recent call last):
  File "/home/shared/tabzilla/TabSurvey/tabzilla_experiment.py", line 137, in __call__
    result = cross_validation(model, self.dataset, self.time_limit)
  File "/home/shared/tabzilla/TabSurvey/tabzilla_utils.py", line 236, in cross_validation
    loss_history, val_loss_history = curr_model.fit(
  File "/home/shared/tabzilla/TabSurvey/models/tree_models.py", line 151, in fit
    self.model.fit(X, y, eval_set=(X_val, y_val))
  File "/opt/conda/envs/gbdt/lib/python3.9/site-packages/catboost/core.py", line 4716, in fit
    self._fit(X, y, cat_features, text_features, embedding_features, None, sample_weight, None, None, None, None, baseline, use_best_model,
  File "/opt/conda/envs/gbdt/lib/python3.9/site-packages/catboost/core.py", line 2021, in _fit
    train_params = self._prepare_train_params(
  File "/opt/conda/envs/gbdt/lib/python3.9/site-packages/catboost/core.py", line 1953, in _prepare_train_params
    _check_train_params(params)
  File "_catboost.pyx", line 5839, in _catboost._check_train_params
  File "_catboost.pyx", line 5858, in _catboost._check_train_params
_catboost.CatBoostError: catboost/private/libs/options/catboost_options.cpp:587: classes_count parameter takes effect only with MultiClass/MultiClassOneVsAll and user-defined loss functions