We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent 1fbd997 commit b7bf42dCopy full SHA for b7bf42d
PyTorch/LanguageModeling/BERT/README.md
@@ -671,8 +671,8 @@ NVIDIA DGX-2 With 32G|16|4096 and 2048 |64 and 256|-|1.52|-|2.71|-
671
###### Pre-training stability test
672
673
| Accuracy Metric | Seed 1
674
-|-|-|-|-|-|-|-|-
675
-|Final Loss | 1.52
+|-|-
+| Final Loss | 1.52
676
677
###### Fine-tuning stability test
678
@@ -838,7 +838,7 @@ The inference performance metrics used were items/second.
838
839
### Changelog
840
841
-October 2019
+August 2019
842
843
- Pretraining support with LAMB optimizer
844
0 commit comments