Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
datasets:
|
| 3 |
+
- wikitext
|
| 4 |
+
- wikitext-103-v1
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
metrics:
|
| 8 |
+
- perplexity
|
| 9 |
+
- cross_entropy
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
|
| 13 |
+
**Dependence of the cross entropy loss on the length of the context for prediction**
|
| 14 |
+
|
| 15 |
+
- x-axis*128 = context length
|
| 16 |
+
- y-axis = cross entropy
|
| 17 |
+
|
| 18 |
+
|