Merge pull request #96 from eltociear/patch-1

Fix typo in TRAINING_LOG.md
This commit is contained in:
Andriy Mulyar 2023-04-03 17:18:11 -04:00 committed by GitHub
commit 8e7ce1f7c7
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

View File

@ -160,7 +160,7 @@ We realized that we had two bugs however:
- We accidentally duplicated data and effectively trained for 2 epochs instead of 1
- We added an eos token to every sequence, even those that we truncated (e.g. long code that exceeds the 1024).
## Conditonal EOS and 1 Epoch
## Conditional EOS and 1 Epoch
Using the same parameters, we then trained a model using a "conditional" eos token where we only add an `eos` when the inputs are less than the maximum sequence length for one epoch.