Update README.md
Browse files
README.md
CHANGED
|
@@ -9,6 +9,31 @@ tags: []
|
|
| 9 |
|
| 10 |
|
| 11 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
## Model Details
|
| 13 |
|
| 14 |
### Model Description
|
|
|
|
| 9 |
|
| 10 |
|
| 11 |
|
| 12 |
+
# Experiemento 1
|
| 13 |
+
|
| 14 |
+
| | model_name | final_score | task_coverage@1 | relative_quality@1 | hallucination@1 | task_coverage@2 | relative_quality@2 | hallucination@2 | task_coverage@4 | relative_quality@4 | hallucination@4 | task_coverage@8 | relative_quality@8 | hallucination@8 |
|
| 15 |
+
|---:|:-----------------------|--------------:|------------------:|---------------------:|------------------:|------------------:|---------------------:|------------------:|------------------:|---------------------:|------------------:|------------------:|---------------------:|------------------:|
|
| 16 |
+
| 6 | Qwen3-4B-It_step_100 | 1.71427 | 0.964928 | 0.880293 | 0.130947 | 0.978359 | 0.903613 | 0.102231 | 0.984942 | 0.919117 | 0.0858685 | 0.98846 | 0.929453 | 0.0716891 |
|
| 17 |
+
| 1 | Qwen3-4B | 1.62081 | 0.955043 | 0.859573 | 0.193807 | 0.979347 | 0.907198 | 0.10763 | 0.990235 | 0.93047 | 0.0674664 | 0.995178 | 0.949136 | 0.0417946 |
|
| 18 |
+
| 5 | step_280 | 1.60467 | 0.955422 | 0.852986 | 0.203737 | 0.979779 | 0.903061 | 0.11833 | 0.988944 | 0.930389 | 0.0714251 | 0.994842 | 0.950139 | 0.0509117 |
|
| 19 |
+
| 3 | step_100 | 1.59409 | 0.94798 | 0.84465 | 0.198544 | 0.974698 | 0.898805 | 0.114971 | 0.986699 | 0.926536 | 0.0783589 | 0.992001 | 0.944597 | 0.0547505 |
|
| 20 |
+
| 4 | step_160 | 1.5739 | 0.956219 | 0.851703 | 0.234023 | 0.98095 | 0.903757 | 0.126862 | 0.989395 | 0.929453 | 0.079285 | 0.995441 | 0.947131 | 0.0557246 |
|
| 21 |
+
| 0 | Qwen3-4B-Instruct-2507 | 1.55738 | 0.946771 | 0.831468 | 0.220855 | 0.960571 | 0.864074 | 0.171569 | 0.973853 | 0.888018 | 0.137706 | 0.981881 | 0.904151 | 0.114794 |
|
| 22 |
+
| 2 | qwen3-4b-dw-lr | 1.23079 | 0.906166 | 0.734621 | 0.41 | 0.96346 | 0.833205 | 0.265427 | 0.984189 | 0.889002 | 0.171123 | 0.99345 | 0.925326 | 0.112644 |
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
|
| 28 |
+
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
|
| 34 |
+
|
| 35 |
+
|
| 36 |
+
|
| 37 |
## Model Details
|
| 38 |
|
| 39 |
### Model Description
|