Merge pull request #219 from david-thrower/218-fix-padding-token-mismatch-and-logging-tokenization-metadata

218 fix padding token mismatch. Defer logging tokenization metadata to next commit ...

Author: david-thrower

.github/workflows/automerge.yml

@@ -6,7 +6,7 @@ name: Python application
 on:
   push:
 
-    branches: [ "main", "216-add-support-for-gradient-accumulation-steps" ]
+    branches: [ "main", "218-fix-padding-token-mismatch-and-logging-tokenization-metadata" ]
 
 
 permissions:

phishing_email_detection_gpt2.py

@@ -398,7 +398,7 @@ def from_config(cls, config):
     input_dim=VOCABULARY_SIZE,
     output_dim=EMBEDDING_DIM,
     input_length=max_seq_length,
-    mask_zero=True)(inp)
+    mask_zero=False)(inp)
 
 position_embedding = InterleavedRoPE(
     dim=EMBEDDING_DIM,