We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent ca56b93 commit a8408b4Copy full SHA for a8408b4
colossalai/shardformer/modeling/opt.py
@@ -989,8 +989,6 @@ def forward(
989
process_group=shard_config.tensor_parallel_process_group,
990
vocab_size=self.lm_head.out_features,
991
)
992
- # loss_fct = CrossEntropyLoss()
993
- # loss = loss_fct(shift_logits.view(-1, self.config.vocab_size), shift_labels.view(-1))
994
995
if not return_dict:
996
output = (logits,) + outputs[1:]
0 commit comments