Polish README: all 15 benchmarks reported at 3-decimal precision + overall eval_accuracy=0.710
Browse files
README.md
CHANGED
|
@@ -57,7 +57,10 @@ Beyond its improved reasoning capabilities, this version also offers a reduced h
|
|
| 57 |
</div>
|
| 58 |
|
| 59 |
### Overall Performance Summary
|
| 60 |
-
|
|
|
|
|
|
|
|
|
|
| 61 |
|
| 62 |
## 3. Chat Website & API Platform
|
| 63 |
We offer a chat interface and API for you to interact with MyAwesomeModel. Please check our official website for more details.
|
|
|
|
| 57 |
</div>
|
| 58 |
|
| 59 |
### Overall Performance Summary
|
| 60 |
+
|
| 61 |
+
**Overall `eval_accuracy` (weighted):** **0.710** (checkpoint `step_1000`).
|
| 62 |
+
|
| 63 |
+
The MyAwesomeModel demonstrates strong performance across all evaluated benchmark categories (all 15 tasks reported at 3-decimal precision above), with particularly notable results in reasoning and generation tasks.
|
| 64 |
|
| 65 |
## 3. Chat Website & API Platform
|
| 66 |
We offer a chat interface and API for you to interact with MyAwesomeModel. Please check our official website for more details.
|