What could be the cause for the slow speed of xgboost?

Question

I am using xgboost in python to solve an multi-classification problem. The number of input training data is about 500000. Here is my python code which executes quite slow:

param = {'max_depth':23, 'eta':0.1, 'objective':'multi:softprob','num_class':24 }
num_round = 10
watchlist = [(dtrain, 'train')]    
bst = xgb.train(param, dtrain, num_round, watchlist)
preds = bst.predict(dtest)

It takes me about 2 hours to run the training and predicting phrase. However, some other guys' program only take about 5 minutes to train and predict. Their codes are almost totally same as mine. What could be the reason for the extremely slow speed? I am using 64 bit anaconda python 2.7. Is there any possibility that the different versions of python or xgboost cause huge difference in speed?

Answer 1

It's because of the version of xgboost I used. Now Everything is Fine.