issues
search
bigscience-workshop
/
metadata
Experiments on including metadata such as URLs, timestamps, website descriptions and HTML tags during pretraining.
Apache License 2.0
30
stars
12
forks
source link
Eval loop
#192
Open
jordiclive
opened
1 year ago
jordiclive
commented
1 year ago
Add full perplexity evaluation into eval loop.
Minor Training code changes I have been using.
Make sure tokenizer is saved.