Best checkpoint (step_1000) - eval_accuracy=0.710, w/ all 15 benchmark scores
Browse files
README.md
CHANGED
|
@@ -43,11 +43,11 @@ Beyond its improved reasoning capabilities, this version also offers a reduced h
|
|
| 43 |
| | Common Sense | 0.716 | 0.702 | 0.725 | 0.736 |
|
| 44 |
| **Language Understanding** | Reading Comprehension | 0.671 | 0.685 | 0.690 | 0.700 |
|
| 45 |
| | Question Answering | 0.582 | 0.599 | 0.601 | 0.607 |
|
| 46 |
-
| | Text Classification | 0.803 | 0.811 | 0.820 |
|
| 47 |
| | Sentiment Analysis | 0.777 | 0.781 | 0.790 | 0.792 |
|
| 48 |
-
| **Generation Tasks** | Code Generation | 0.615 | 0.631 | 0.640 |
|
| 49 |
| | Creative Writing | 0.588 | 0.579 | 0.601 | 0.610 |
|
| 50 |
-
| | Dialogue Generation | 0.621 | 0.635 | 0.639 |
|
| 51 |
| | Summarization | 0.745 | 0.755 | 0.760 | 0.767 |
|
| 52 |
| **Specialized Capabilities**| Translation | 0.782 | 0.799 | 0.801 | 0.804 |
|
| 53 |
| | Knowledge Retrieval | 0.651 | 0.668 | 0.670 | 0.676 |
|
|
|
|
| 43 |
| | Common Sense | 0.716 | 0.702 | 0.725 | 0.736 |
|
| 44 |
| **Language Understanding** | Reading Comprehension | 0.671 | 0.685 | 0.690 | 0.700 |
|
| 45 |
| | Question Answering | 0.582 | 0.599 | 0.601 | 0.607 |
|
| 46 |
+
| | Text Classification | 0.803 | 0.811 | 0.820 | 0.828 |
|
| 47 |
| | Sentiment Analysis | 0.777 | 0.781 | 0.790 | 0.792 |
|
| 48 |
+
| **Generation Tasks** | Code Generation | 0.615 | 0.631 | 0.640 | 0.650 |
|
| 49 |
| | Creative Writing | 0.588 | 0.579 | 0.601 | 0.610 |
|
| 50 |
+
| | Dialogue Generation | 0.621 | 0.635 | 0.639 | 0.644 |
|
| 51 |
| | Summarization | 0.745 | 0.755 | 0.760 | 0.767 |
|
| 52 |
| **Specialized Capabilities**| Translation | 0.782 | 0.799 | 0.801 | 0.804 |
|
| 53 |
| | Knowledge Retrieval | 0.651 | 0.668 | 0.670 | 0.676 |
|