Krzysztof Sopyła

icon indicating a website link https://ksopyla.com icon indicating an email [email protected]

icon company @PromptSail @Polish-ML-Community icon location Olsztyn, Poland icon location Ph.D., NLP researcher, data scientist, and entrepreneur. Polish ML Community discord https://discord.gg/a96XHkUHm5

Results 2 issues of Krzysztof Sopyła

nan in SRU output

10 comment

I try to train a RNN network (seq2seq) with GRU and SRU cells. When training is done with GRU everything is ok, loss is decreasing an accuracy steadily rise. But...

Deepspeed initialization AttributeError: 'EncoderDecoderConfig' object has no attribute 'hidden_size'

7 comment

### System Info System: Ubuntu 22.04 - `transformers` version: 4.26.1 - Platform: Linux-5.4.0-144-generic-x86_64-with-glibc2.29 - Python version: 3.8.13 - Huggingface_hub version: 0.12.1 - PyTorch version (GPU?): 1.13.1+cu117 (True) - Tensorflow version...