ValueError: need more than 1 value to unpack

[rraabb]

Hi, I compile the code, and there is a error in learn.py, I can't figure out how to fix it.
Here is the traceback

OS: OS X 10.11.6
XGBoost: 0.6

Training classifier [0]: PropertyInspectionXGBRegressor(base_score=0.5, colsample_bytree=0.7,
div69=False, early_stopping_rounds=360, eval_set_size=4000,
gamma=0, learning_rate=0.005, max_delta_step=0,
max_depth=9, min_child_weight=6, missing=None,
n_estimators=10000, nthread=10, objective='reg:linear',
seed=0, silent=1, subsample=0.7, take_log=False,
take_pow2=False, take_root3=False, take_sqrt=False)
Traceback (most recent call last):
File "learn.py", line 168, in
clf.fit_cv(X_train, Y_train, [(X_cv, Y_cv)])
File "/Users/able/Contest/Liberty/kaggle-lmgpip-master/xgbex.py", line 87, in fit_cv
return self.fit(X, y, eval_set)
File "/Users/able/Contest/Liberty/kaggle-lmgpip-master/xgbex.py", line 82, in fit
early_stopping_rounds=self.early_stopping_rounds, verbose=0)
File "//anaconda/lib/python2.7/site-packages/xgboost/sklearn.py", line 251, in fit
verbose_eval=verbose)
File "//anaconda/lib/python2.7/site-packages/xgboost/training.py", line 205, in train
xgb_model=xgb_model, callbacks=callbacks)
File "//anaconda/lib/python2.7/site-packages/xgboost/training.py", line 92, in _train_internal
evaluation_result_list = [(k, float(v)) for k, v in res[1:]]
ValueError: need more than 1 value to unpack