Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
| 1 |
| Model Name | Parameters | Class | Ratio | Tokens | Batch Size (Tokens) | Training Loss ↓ | hellaswag acc ↑ | lambada ppl ↓ | lambada acc ↑ | winogrande acc ↑
|
| 2 |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
|
| 3 |
| [GerbilLab/GerbilBlender-A-15m](https://hf.co/GerbilLab/GerbilBlender-A-15m) | 15m | A-Class | 20 | 280M | 131k | 4.9642 |
|
|
@@ -16,4 +19,4 @@
|
|
| 16 |
# Example masked language modelling
|
| 17 |
'<mlm_start> this is an <single_tok_mask> text for masked language modelling <mlm_end> example <|endoftext|>'
|
| 18 |
|
| 19 |
-
```
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
---
|
| 4 |
| Model Name | Parameters | Class | Ratio | Tokens | Batch Size (Tokens) | Training Loss ↓ | hellaswag acc ↑ | lambada ppl ↓ | lambada acc ↑ | winogrande acc ↑
|
| 5 |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
|
| 6 |
| [GerbilLab/GerbilBlender-A-15m](https://hf.co/GerbilLab/GerbilBlender-A-15m) | 15m | A-Class | 20 | 280M | 131k | 4.9642 |
|
|
|
|
| 19 |
# Example masked language modelling
|
| 20 |
'<mlm_start> this is an <single_tok_mask> text for masked language modelling <mlm_end> example <|endoftext|>'
|
| 21 |
|
| 22 |
+
```
|