Update README.md
Browse files
README.md
CHANGED
|
@@ -145,4 +145,18 @@ weight_decay: 0.0
|
|
| 145 |
fsdp:
|
| 146 |
fsdp_config:
|
| 147 |
special_tokens:
|
| 148 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 145 |
fsdp:
|
| 146 |
fsdp_config:
|
| 147 |
special_tokens:
|
| 148 |
+
```
|
| 149 |
+
|
| 150 |
+
### Training results:
|
| 151 |
+
|
| 152 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 153 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 154 |
+
| 1.7881 | 0.0017 | 1 | 2.5329 |
|
| 155 |
+
| 1.6899 | 0.4996 | 287 | 1.9272 |
|
| 156 |
+
| 1.5511 | 0.9991 | 574 | 1.8750 |
|
| 157 |
+
| 1.4797 | 1.4861 | 861 | 1.8476 |
|
| 158 |
+
| 1.5279 | 1.9856 | 1148 | 1.8270 |
|
| 159 |
+
| 1.4583 | 2.4726 | 1435 | 1.8275 |
|
| 160 |
+
| 1.5044 | 2.9721 | 1722 | 1.8215 |
|
| 161 |
+
| 1.3051 | 3.4582 | 2009 | 1.8243 |
|
| 162 |
+
| 1.5619 | 3.9578 | 2296 | 1.8245 |
|