Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
datasets:
|
| 3 |
+
- roneneldan/TinyStories
|
| 4 |
+
metrics:
|
| 5 |
+
- babylm
|
| 6 |
+
---
|
| 7 |
+
Basemodel: roBERTa
|
| 8 |
+
|
| 9 |
+
Configs:
|
| 10 |
+
Vocab size: 10,000
|
| 11 |
+
Hidden size: 512
|
| 12 |
+
Max position embeddings: 512
|
| 13 |
+
Number of layers: 2
|
| 14 |
+
Number of heads: 4
|
| 15 |
+
Window size: 256
|
| 16 |
+
Intermediate-size: 1024
|
| 17 |
+
|
| 18 |
+
Results:
|
| 19 |
+
- Task: glue
|
| 20 |
+
Score: 57.54
|
| 21 |
+
Confidence Interval: [57.15, 58.1]
|
| 22 |
+
- Task: blimp
|
| 23 |
+
Score: 59.16
|
| 24 |
+
Confidence Interval: [58.75, 59.53]
|