Commit
•
8201db0
1
Parent(s):
aa2b602
Update README.md
Browse files
README.md
CHANGED
|
@@ -11,4 +11,8 @@ thumbnail: "https://github.com/sberbank-ai/ru-gpts"
|
|
| 11 |
Model was trained with sequence length 1024 using transformers lib by [SberDevices](https://sberdevices.ru/) team on 80B tokens for 3 epochs. After that model was finetuned 1 epoch with sequence length 2048.
|
| 12 |
|
| 13 |
Total training time was around 14 days on 128 GPUs for 1024 context and few days on 16 GPUs for 2048 context.
|
| 14 |
-
Final perplexity on test set is `13.6`.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
Model was trained with sequence length 1024 using transformers lib by [SberDevices](https://sberdevices.ru/) team on 80B tokens for 3 epochs. After that model was finetuned 1 epoch with sequence length 2048.
|
| 12 |
|
| 13 |
Total training time was around 14 days on 128 GPUs for 1024 context and few days on 16 GPUs for 2048 context.
|
| 14 |
+
Final perplexity on test set is `13.6`.
|
| 15 |
+
|
| 16 |
+
# Authors
|
| 17 |
+
+ NLP core team RnD [Telegram channel](https://t.me/nlpcoreteam):
|
| 18 |
+
+ Dmitry Zmitrovich
|