Hi, I am training a MCQA dataset with LLAMA model. I am restricting the output space of LLAMA to 4 tokens. I am getting this error upon running the code
shift_logits = shift_logits.view(-1, self.config.vocab_size)
RuntimeError: shape '[-1, 32000]' is invalid for input of size 1052
0%| | 0/927 [00:00<?, ?it/s]
Could you please help.
Thanks
Hi, I am training a MCQA dataset with LLAMA model. I am restricting the output space of LLAMA to 4 tokens. I am getting this error upon running the code
shift_logits = shift_logits.view(-1, self.config.vocab_size)
RuntimeError: shape '[-1, 32000]' is invalid for input of size 1052
0%| | 0/927 [00:00<?, ?it/s]
Could you please help.
Thanks