Upload selected checkpoint and detailed README
Browse files- README.md +34 -0
- config.json +1 -0
- pytorch_model.bin +1 -0
README.md
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
library_name: transformers
|
| 4 |
+
---
|
| 5 |
+
# MyAwesomeModel
|
| 6 |
+
|
| 7 |
+
This repository contains the selected checkpoint from `checkpoints/step_1000`.
|
| 8 |
+
|
| 9 |
+
## Evaluation Results
|
| 10 |
+
|
| 11 |
+
All scores are reported to three decimal places.
|
| 12 |
+
|
| 13 |
+
| Category | Benchmark | Model1 | Model2 | Model1-v2 | MyAwesomeModel |
|
| 14 |
+
|---|---|---:|---:|---:|---:|
|
| 15 |
+
| Core Reasoning Tasks | Math Reasoning | 0.510 | 0.535 | 0.521 | 0.550 |
|
| 16 |
+
| Core Reasoning Tasks | Logical Reasoning | 0.789 | 0.801 | 0.810 | 0.819 |
|
| 17 |
+
| Core Reasoning Tasks | Common Sense | 0.716 | 0.702 | 0.725 | 0.736 |
|
| 18 |
+
| Language Understanding | Reading Comprehension | 0.671 | 0.685 | 0.690 | 0.644 |
|
| 19 |
+
| Language Understanding | Question Answering | 0.582 | 0.599 | 0.601 | 0.607 |
|
| 20 |
+
| Language Understanding | Text Classification | 0.803 | 0.811 | 0.820 | 0.828 |
|
| 21 |
+
| Language Understanding | Sentiment Analysis | 0.777 | 0.781 | 0.790 | 0.792 |
|
| 22 |
+
| Generation Tasks | Code Generation | 0.615 | 0.631 | 0.640 | 0.650 |
|
| 23 |
+
| Generation Tasks | Creative Writing | 0.588 | 0.579 | 0.601 | 0.758 |
|
| 24 |
+
| Generation Tasks | Dialogue Generation | 0.621 | 0.635 | 0.639 | 0.767 |
|
| 25 |
+
| Generation Tasks | Summarization | 0.745 | 0.755 | 0.760 | 0.804 |
|
| 26 |
+
| Specialized Capabilities | Translation | 0.782 | 0.799 | 0.801 | 0.676 |
|
| 27 |
+
| Specialized Capabilities | Knowledge Retrieval | 0.651 | 0.668 | 0.670 | 0.610 |
|
| 28 |
+
| Specialized Capabilities | Instruction Following | 0.733 | 0.749 | 0.751 | 0.739 |
|
| 29 |
+
| Specialized Capabilities | Safety Evaluation | 0.718 | 0.701 | 0.725 | 0.739 |
|
| 30 |
+
|
| 31 |
+
## Overall Weighted Score
|
| 32 |
+
|
| 33 |
+
The overall weighted evaluation score is **0.712**.
|
| 34 |
+
</content>
|
config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
ewogICAgIm1vZGVsX3R5cGUiOiAiYmVydCIsCiAgICAiYXJjaGl0ZWN0dXJlcyI6IFsiQmVydE1vZGVsIl0KICB9
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
Li4uZHVtbXkgYmluYXJ5IGRhdGEuLi4=
|