Closed Darren-greenhand closed 1 year ago
You may refer the PR #217 and checkout to the new fixed branch~
--train_config_ic_path /tf/data/SD/SD_train.json \
should be --train_config_path /tf/data/SD/SD_train.json \
It's our bug since we are aiming to divide the training datasets into different groups. But missing to add train_config_path
.
thanks a lot for your help!
Hello Otter team!
When I try to train the luodian/OTTER-9B-INIT model with SN and SD datasets using the
instruction_following.py
I met some problemsI can't use the SN datasets because image_ids int SN_instructions.json don't match SN.json
In SD datasets I didn't meet this problem but
RuntimeError: CUDA error: device-side assert triggered
occursI turn to stackoverfollow but most of the solutions are for classification problem QAQ I check the vocab_size and it is correct
how i start training:
the detailed stack: