Spaces:
Sleeping
Sleeping
Update README.md
Browse files
README.md
CHANGED
|
@@ -226,7 +226,7 @@ Turn 1: message_expert → All [PENALTY: -0.3]
|
|
| 226 |
Turn 2: message_expert → All [PENALTY: -0.4 repeat]
|
| 227 |
Turn 3: submit_final → "The app should be good" [Score: 0.0]
|
| 228 |
```
|
| 229 |
-
* 📄 **[View the Before GRPO Training Metrics](
|
| 230 |
|
| 231 |
|
| 232 |

|
|
@@ -245,7 +245,7 @@ Turn 7: submit_final → "Budget capped at $50k. Biometric 2FA required.
|
|
| 245 |
|
| 246 |
---
|
| 247 |
## 🛠 Training Logs
|
| 248 |
-
* 📄 **[View the Raw GRPO Training Metrics](
|
| 249 |
|
| 250 |
<br>
|
| 251 |
|
|
|
|
| 226 |
Turn 2: message_expert → All [PENALTY: -0.4 repeat]
|
| 227 |
Turn 3: submit_final → "The app should be good" [Score: 0.0]
|
| 228 |
```
|
| 229 |
+
* 📄 **[View the Before GRPO Training Metrics](baseline_results_medium__llm.json)**
|
| 230 |
|
| 231 |
|
| 232 |

|
|
|
|
| 245 |
|
| 246 |
---
|
| 247 |
## 🛠 Training Logs
|
| 248 |
+
* 📄 **[View the Raw GRPO Training Metrics](grpo_metrics.json)**
|
| 249 |
|
| 250 |
<br>
|
| 251 |
|