Closed tenggyut closed 8 months ago
Unless I'm missing something, it is?
Arguments parsed here: https://github.com/jondurbin/bagel/blob/bcac409bc61491f089ab86f8a1e4463b5ff7e86c/bagel/tune/sft.py#L1119
Model is loaded: https://github.com/jondurbin/bagel/blob/bcac409bc61491f089ab86f8a1e4463b5ff7e86c/bagel/tune/sft.py#L1137
dpo.py initialize model before the training_args
dpo.py initialize model before the training_args
Ah, I see - thanks, should be good now.
TrainingArguments should be initialized before from_pretrain call. otherwise zero3_init_flag will be ignored when using deepspeed to initialize larger models.