TypeError: cross_entropy() got an unexpected keyword argument 'reduction'

[Julisa-test]

Hi, @glample

I trained with a single GPU and got an err just like the them shown.
Running command:
First: ./get-data-nmt.sh --src en --tgt fr
got:
===== Data summary
Monolingual training data:
en: ./data/processed/en-fr/train.en.pth
fr: ./data/processed/en-fr/train.fr.pth
Monolingual validation data:
en: ./data/processed/en-fr/valid.en.pth
fr: ./data/processed/en-fr/valid.fr.pth
Monolingual test data:
en: ./data/processed/en-fr/test.en.pth
fr: ./data/processed/en-fr/test.fr.pth
Parallel validation data:
en: ./data/processed/en-fr/valid.en-fr.en.pth
fr: ./data/processed/en-fr/valid.en-fr.fr.pth
Parallel test data:
en: ./data/processed/en-fr/test.en-fr.en.pth
fr: ./data/processed/en-fr/test.en-fr.fr.pth
And then run: python train.py --exp_name 'my_enfr_mlm' --dump_path './dumped/' --exp_id 'bs.20' --data_path './data/processed/en-fr/' --lgs 'en-fr' --clm_steps '' --mlm_steps 'en,fr' --emb_dim '1024' --n_layers '6' --n_heads '8' --dropout '0.1' --attention_dropout '0.1' --gelu_activation 'true' --batch_size '8' --bptt '256' --optimizer 'adam,lr=0.0001' --epoch_size '300000' --validation_metrics '_valid_mlm_ppl' --stopping_criterion '_valid_mlm_ppl,10'

got the err.

[glample]

Hi,

Can you copy paste the full error traceback that includes the line where the error occurs?

In any case, it looks like the error happens when a F.cross_entropy is called. Which version of PyTorch are you using? The code is compatible with PyTorch 1.0.1 and PyTorch 0.4.3 so you may be using a quite old. Could you try to update PyTorch and rerun the code?

[Julisa-test]

The version of PyTorch I used is 0.4.1, which is exactly caused by the version being too low. Thank you for your reply.