I went back to an old install I had backed up, and installed python 3.10 instead (which is what I used back then). After a bit of tweaking I managed to get it working.
Then I did a forced-updat…
I'm having the same issue. Seems Tortoise and DLAS are no longer installed and I had to manually add them in. I then end up with the 'broadcat' error that you have.
I think this repository is…
No problem, I did think it seemed weird!
How's the vall-e experience going? Is it proving to be better?
Your gradient accumulation size is either too large or not divisible enough by your batch size.
Really? I'm using the same gradient size for both attempts, and the default scheduling will…
I'm sure I tested the same dataset but with the default schedule, and it worked. but now it wont work even with the default schedule, so maybe something else is wrong... but I can't see anything else!