@SWivid Thank you for checking in. I have merged the latest changes and adapted the code to maintain the compatibility with HuggingFace space. I will try to maintain my fork as a package, and hopef...
Hello, and thanks a lot for open sourcing this work.
I am using the `finetune-cli.py` script, which works great! I'm only able to track the training loss, and don't see validation loss being cal...
@lpscr we actually use tensorboard earlier, as you can see there is `/runs` in `.gitignore` lol
though we have wandb now but I actually not see it anymore for reasons in #9 (no significant signals...
@SWivid yes thank you working ! one think i know it's not the place to talk about but
something quick i make also train working with tensorboard , so you can change easy wandb or tensorboard ,
...