Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
library_name: transformers
|
| 4 |
+
---
|
| 5 |
+
# MyAwesomeModel-TestRepository
|
| 6 |
+
|
| 7 |
+
## Best Checkpoint: step_1000 (Highest Eval Accuracy: 0.950)
|
| 8 |
+
|
| 9 |
+
## Evaluation Results (15 Benchmarks, 3 Decimal Places)
|
| 10 |
+
|
| 11 |
+
| Benchmark | Score |
|
| 12 |
+
|-----------|-------|
|
| 13 |
+
| math_reasoning | 0.875 |
|
| 14 |
+
| logical_reasoning | 0.862 |
|
| 15 |
+
| common_sense | 0.841 |
|
| 16 |
+
| reading_comprehension | 0.833 |
|
| 17 |
+
| question_answering | 0.815 |
|
| 18 |
+
| text_classification | 0.887 |
|
| 19 |
+
| sentiment_analysis | 0.859 |
|
| 20 |
+
| code_generation | 0.824 |
|
| 21 |
+
| creative_writing | 0.796 |
|
| 22 |
+
| dialogue_generation | 0.838 |
|
| 23 |
+
| summarization | 0.871 |
|
| 24 |
+
| translation | 0.869 |
|
| 25 |
+
| knowledge_retrieval | 0.802 |
|
| 26 |
+
| instruction_following | 0.855 |
|
| 27 |
+
| safety_evaluation | 0.847 |
|
| 28 |
+
|
| 29 |
+
## Overall Weighted Score
|
| 30 |
+
Overall weighted evaluation score: **0.852**
|