Sfarzi commited on
Commit
abd4700
·
1 Parent(s): 43a9ad1

Initial clone with modifications

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. csv_files/llm_scores_p3.xlsx +0 -0
  2. csv_files/outputs/.ipynb_checkpoints/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__en__0shot-checkpoint.txt +0 -11
  3. csv_files/outputs/Henrychur__MMed-Llama-3-8B__en__10shot.txt +2 -1
  4. csv_files/outputs/Henrychur__MMed-Llama-3-8B__gr__10shot.txt +2 -1
  5. csv_files/outputs/Henrychur__MMed-Llama-3-8B__it__10shot.txt +2 -1
  6. csv_files/outputs/Henrychur__MMed-Llama-3-8B__pl__10shot.txt +2 -1
  7. csv_files/outputs/Henrychur__MMed-Llama-3-8B__sk__10shot.txt +2 -1
  8. csv_files/outputs/Henrychur__MMed-Llama-3-8B__sl__10shot.txt +2 -1
  9. csv_files/outputs/HiTZ__Medical-mT5-large__en__10shot.txt +2 -1
  10. csv_files/outputs/HiTZ__Medical-mT5-large__gr__10shot.txt +2 -1
  11. csv_files/outputs/HiTZ__Medical-mT5-large__it__10shot.txt +2 -1
  12. csv_files/outputs/HiTZ__Medical-mT5-large__pl__10shot.txt +2 -1
  13. csv_files/outputs/HiTZ__Medical-mT5-large__sk__10shot.txt +2 -1
  14. csv_files/outputs/HiTZ__Medical-mT5-large__sl__10shot.txt +2 -1
  15. csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__en__10shot.txt +2 -1
  16. csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__gr__10shot.txt +2 -1
  17. csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__it__10shot.txt +2 -1
  18. csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__pl__10shot.txt +2 -1
  19. csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__sk__10shot.txt +2 -1
  20. csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__sl__10shot.txt +2 -1
  21. csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__en__10shot.txt +2 -1
  22. csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__gr__10shot.txt +2 -1
  23. csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__it__10shot.txt +2 -1
  24. csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__pl__10shot.txt +2 -1
  25. csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__sk__10shot.txt +2 -1
  26. csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__sl__10shot.txt +2 -1
  27. csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__en__10shot.txt +2 -1
  28. csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__gr__10shot.txt +2 -1
  29. csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__it__10shot.txt +2 -1
  30. csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__pl__10shot.txt +2 -1
  31. csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__sk__10shot.txt +2 -1
  32. csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__sl__10shot.txt +2 -1
  33. csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__en__10shot.txt +2 -1
  34. csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__gr__10shot.txt +2 -1
  35. csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__it__10shot.txt +2 -1
  36. csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__pl__10shot.txt +2 -1
  37. csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__sk__10shot.txt +2 -1
  38. csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__sl__10shot.txt +2 -1
  39. csv_files/outputs/epfl-llm__meditron-7b__en__10shot.txt +2 -1
  40. csv_files/outputs/epfl-llm__meditron-7b__gr__10shot.txt +1 -0
  41. csv_files/outputs/epfl-llm__meditron-7b__it__10shot.txt +2 -1
  42. csv_files/outputs/epfl-llm__meditron-7b__pl__10shot.txt +2 -1
  43. csv_files/outputs/epfl-llm__meditron-7b__sk__10shot.txt +2 -1
  44. csv_files/outputs/epfl-llm__meditron-7b__sl__10shot.txt +2 -1
  45. csv_files/outputs/google__gemma-2-9b-it__en__10shot.txt +2 -1
  46. csv_files/outputs/google__gemma-2-9b-it__gr__10shot.txt +2 -1
  47. csv_files/outputs/google__gemma-2-9b-it__it__10shot.txt +2 -1
  48. csv_files/outputs/google__gemma-2-9b-it__pl__10shot.txt +2 -1
  49. csv_files/outputs/google__gemma-2-9b-it__sk__10shot.txt +2 -1
  50. csv_files/outputs/google__gemma-2-9b-it__sl__10shot.txt +2 -1
csv_files/llm_scores_p3.xlsx CHANGED
Binary files a/csv_files/llm_scores_p3.xlsx and b/csv_files/llm_scores_p3.xlsx differ
 
csv_files/outputs/.ipynb_checkpoints/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__en__0shot-checkpoint.txt DELETED
@@ -1,11 +0,0 @@
1
- hf (pretrained=deepseek-ai/DeepSeek-R1-Distill-Qwen-32B ), num_fewshot: 0, batch_size: 1
2
- |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
- |-------|-------|------|------|------|----|------|---|------|
4
- | - NER | | | |f1 | | 0.2877 | |0 |
5
- | - p1 | | | |f1 | | 0.1963 | | 0 |
6
- | - p2 | | | |f1 | | 0.3459 | | 0 |
7
- | - p3 | | | |f1 | | 0.3208 | | 0 |
8
- | - RE | | | |f1 | | 0.4430 | |0 |
9
- | - p1 | | | |f1 | | 0.4487 | | 0 |
10
- | - p2 | | | |f1 | | 0.4492 | | 0 |
11
- | - p3 | | | |f1 | | 0.4311 | | 0 |
 
 
 
 
 
 
 
 
 
 
 
 
csv_files/outputs/Henrychur__MMed-Llama-3-8B__en__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 10, batch_size: 1
5
  | - p1 | | | |f1 | | 0.2189 | | 0 |
6
  | - p2 | | | |f1 | | 0.2243 | | 0 |
7
  | - p3 | | | |f1 | | 0.1994 | | 0 |
8
- | - RE | | | |f1 | | 0.1429 | |0 |
9
  | - p1 | | | |f1 | | 0.1189 | | 0 |
10
  | - p2 | | | |f1 | | 0.1668 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.2189 | | 0 |
6
  | - p2 | | | |f1 | | 0.2243 | | 0 |
7
  | - p3 | | | |f1 | | 0.1994 | | 0 |
8
+ | - RE | | | |f1 | | 0.1681 | |0 |
9
  | - p1 | | | |f1 | | 0.1189 | | 0 |
10
  | - p2 | | | |f1 | | 0.1668 | | 0 |
11
+ | - p3 | | | |f1 | | 0.2185 | | 0 |
csv_files/outputs/Henrychur__MMed-Llama-3-8B__gr__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 10, batch_size: 1
5
  | - p1 | | | |f1 | | 0.1667 | | 0 |
6
  | - p2 | | | |f1 | | 0.1089 | | 0 |
7
  | - p3 | | | |f1 | | 0.1667 | | 0 |
8
- | - RE | | | |f1 | | 0.0937 | |0 |
9
  | - p1 | | | |f1 | | 0.0821 | | 0 |
10
  | - p2 | | | |f1 | | 0.1053 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.1667 | | 0 |
6
  | - p2 | | | |f1 | | 0.1089 | | 0 |
7
  | - p3 | | | |f1 | | 0.1667 | | 0 |
8
+ | - RE | | | |f1 | | 0.0970 | |0 |
9
  | - p1 | | | |f1 | | 0.0821 | | 0 |
10
  | - p2 | | | |f1 | | 0.1053 | | 0 |
11
+ | - p3 | | | |f1 | | 0.1036 | | 0 |
csv_files/outputs/Henrychur__MMed-Llama-3-8B__it__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 10, batch_size: 1
5
  | - p1 | | | |f1 | | 0.3299 | | 0 |
6
  | - p2 | | | |f1 | | 0.4023 | | 0 |
7
  | - p3 | | | |f1 | | 0.3938 | | 0 |
8
- | - RE | | | |f1 | | 0.1102 | |0 |
9
  | - p1 | | | |f1 | | 0.0977 | | 0 |
10
  | - p2 | | | |f1 | | 0.1226 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.3299 | | 0 |
6
  | - p2 | | | |f1 | | 0.4023 | | 0 |
7
  | - p3 | | | |f1 | | 0.3938 | | 0 |
8
+ | - RE | | | |f1 | | 0.1331 | |0 |
9
  | - p1 | | | |f1 | | 0.0977 | | 0 |
10
  | - p2 | | | |f1 | | 0.1226 | | 0 |
11
+ | - p3 | | | |f1 | | 0.1789 | | 0 |
csv_files/outputs/Henrychur__MMed-Llama-3-8B__pl__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 10, batch_size: 1
5
  | - p1 | | | |f1 | | 0.3992 | | 0 |
6
  | - p2 | | | |f1 | | 0.3916 | | 0 |
7
  | - p3 | | | |f1 | | 0.3992 | | 0 |
8
- | - RE | | | |f1 | | 0.1026 | |0 |
9
  | - p1 | | | |f1 | | 0.0998 | | 0 |
10
  | - p2 | | | |f1 | | 0.1055 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.3992 | | 0 |
6
  | - p2 | | | |f1 | | 0.3916 | | 0 |
7
  | - p3 | | | |f1 | | 0.3992 | | 0 |
8
+ | - RE | | | |f1 | | 0.1003 | |0 |
9
  | - p1 | | | |f1 | | 0.0998 | | 0 |
10
  | - p2 | | | |f1 | | 0.1055 | | 0 |
11
+ | - p3 | | | |f1 | | 0.0956 | | 0 |
csv_files/outputs/Henrychur__MMed-Llama-3-8B__sk__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 10, batch_size: 1
5
  | - p1 | | | |f1 | | 0.3444 | | 0 |
6
  | - p2 | | | |f1 | | 0.3632 | | 0 |
7
  | - p3 | | | |f1 | | 0.3444 | | 0 |
8
- | - RE | | | |f1 | | 0.0889 | |0 |
9
  | - p1 | | | |f1 | | 0.0734 | | 0 |
10
  | - p2 | | | |f1 | | 0.1045 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.3444 | | 0 |
6
  | - p2 | | | |f1 | | 0.3632 | | 0 |
7
  | - p3 | | | |f1 | | 0.3444 | | 0 |
8
+ | - RE | | | |f1 | | 0.0884 | |0 |
9
  | - p1 | | | |f1 | | 0.0734 | | 0 |
10
  | - p2 | | | |f1 | | 0.1045 | | 0 |
11
+ | - p3 | | | |f1 | | 0.0875 | | 0 |
csv_files/outputs/Henrychur__MMed-Llama-3-8B__sl__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 10, batch_size: 1
5
  | - p1 | | | |f1 | | 0.3558 | | 0 |
6
  | - p2 | | | |f1 | | 0.4045 | | 0 |
7
  | - p3 | | | |f1 | | 0.3558 | | 0 |
8
- | - RE | | | |f1 | | 0.0784 | |0 |
9
  | - p1 | | | |f1 | | 0.0787 | | 0 |
10
  | - p2 | | | |f1 | | 0.0781 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.3558 | | 0 |
6
  | - p2 | | | |f1 | | 0.4045 | | 0 |
7
  | - p3 | | | |f1 | | 0.3558 | | 0 |
8
+ | - RE | | | |f1 | | 0.0762 | |0 |
9
  | - p1 | | | |f1 | | 0.0787 | | 0 |
10
  | - p2 | | | |f1 | | 0.0781 | | 0 |
11
+ | - p3 | | | |f1 | | 0.0719 | | 0 |
csv_files/outputs/HiTZ__Medical-mT5-large__en__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 10, batch_size: 1
5
  | - p1 | | | |f1 | | 0.1215 | | 0 |
6
  | - p2 | | | |f1 | | 0.1415 | | 0 |
7
  | - p3 | | | |f1 | | 0.1322 | | 0 |
8
- | - RE | | | |f1 | | 0.0022 | |0 |
9
  | - p1 | | | |f1 | | 0.0028 | | 0 |
10
  | - p2 | | | |f1 | | 0.0016 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.1215 | | 0 |
6
  | - p2 | | | |f1 | | 0.1415 | | 0 |
7
  | - p3 | | | |f1 | | 0.1322 | | 0 |
8
+ | - RE | | | |f1 | | 0.0031 | |0 |
9
  | - p1 | | | |f1 | | 0.0028 | | 0 |
10
  | - p2 | | | |f1 | | 0.0016 | | 0 |
11
+ | - p3 | | | |f1 | | 0.0049 | | 0 |
csv_files/outputs/HiTZ__Medical-mT5-large__gr__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 10, batch_size: 1
5
  | - p1 | | | |f1 | | 0.1455 | | 0 |
6
  | - p2 | | | |f1 | | 0.1434 | | 0 |
7
  | - p3 | | | |f1 | | 0.1455 | | 0 |
8
- | - RE | | | |f1 | | 0.0015 | |0 |
9
  | - p1 | | | |f1 | | 0.0024 | | 0 |
10
  | - p2 | | | |f1 | | 0.0007 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.1455 | | 0 |
6
  | - p2 | | | |f1 | | 0.1434 | | 0 |
7
  | - p3 | | | |f1 | | 0.1455 | | 0 |
8
+ | - RE | | | |f1 | | 0.0010 | |0 |
9
  | - p1 | | | |f1 | | 0.0024 | | 0 |
10
  | - p2 | | | |f1 | | 0.0007 | | 0 |
11
+ | - p3 | | | |f1 | | 0.0000 | | 0 |
csv_files/outputs/HiTZ__Medical-mT5-large__it__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 10, batch_size: 1
5
  | - p1 | | | |f1 | | 0.1616 | | 0 |
6
  | - p2 | | | |f1 | | 0.1774 | | 0 |
7
  | - p3 | | | |f1 | | 0.1690 | | 0 |
8
- | - RE | | | |f1 | | 0.0050 | |0 |
9
  | - p1 | | | |f1 | | 0.0035 | | 0 |
10
  | - p2 | | | |f1 | | 0.0064 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.1616 | | 0 |
6
  | - p2 | | | |f1 | | 0.1774 | | 0 |
7
  | - p3 | | | |f1 | | 0.1690 | | 0 |
8
+ | - RE | | | |f1 | | 0.0048 | |0 |
9
  | - p1 | | | |f1 | | 0.0035 | | 0 |
10
  | - p2 | | | |f1 | | 0.0064 | | 0 |
11
+ | - p3 | | | |f1 | | 0.0046 | | 0 |
csv_files/outputs/HiTZ__Medical-mT5-large__pl__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 10, batch_size: 1
5
  | - p1 | | | |f1 | | 0.1500 | | 0 |
6
  | - p2 | | | |f1 | | 0.1548 | | 0 |
7
  | - p3 | | | |f1 | | 0.1500 | | 0 |
8
- | - RE | | | |f1 | | 0.0031 | |0 |
9
  | - p1 | | | |f1 | | 0.0040 | | 0 |
10
  | - p2 | | | |f1 | | 0.0023 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.1500 | | 0 |
6
  | - p2 | | | |f1 | | 0.1548 | | 0 |
7
  | - p3 | | | |f1 | | 0.1500 | | 0 |
8
+ | - RE | | | |f1 | | 0.0032 | |0 |
9
  | - p1 | | | |f1 | | 0.0040 | | 0 |
10
  | - p2 | | | |f1 | | 0.0023 | | 0 |
11
+ | - p3 | | | |f1 | | 0.0034 | | 0 |
csv_files/outputs/HiTZ__Medical-mT5-large__sk__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 10, batch_size: 1
5
  | - p1 | | | |f1 | | 0.1485 | | 0 |
6
  | - p2 | | | |f1 | | 0.1360 | | 0 |
7
  | - p3 | | | |f1 | | 0.1485 | | 0 |
8
- | - RE | | | |f1 | | 0.0031 | |0 |
9
  | - p1 | | | |f1 | | 0.0038 | | 0 |
10
  | - p2 | | | |f1 | | 0.0024 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.1485 | | 0 |
6
  | - p2 | | | |f1 | | 0.1360 | | 0 |
7
  | - p3 | | | |f1 | | 0.1485 | | 0 |
8
+ | - RE | | | |f1 | | 0.0027 | |0 |
9
  | - p1 | | | |f1 | | 0.0038 | | 0 |
10
  | - p2 | | | |f1 | | 0.0024 | | 0 |
11
+ | - p3 | | | |f1 | | 0.0020 | | 0 |
csv_files/outputs/HiTZ__Medical-mT5-large__sl__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 10, batch_size: 1
5
  | - p1 | | | |f1 | | 0.1470 | | 0 |
6
  | - p2 | | | |f1 | | 0.1325 | | 0 |
7
  | - p3 | | | |f1 | | 0.1470 | | 0 |
8
- | - RE | | | |f1 | | 0.0073 | |0 |
9
  | - p1 | | | |f1 | | 0.0073 | | 0 |
10
  | - p2 | | | |f1 | | 0.0074 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.1470 | | 0 |
6
  | - p2 | | | |f1 | | 0.1325 | | 0 |
7
  | - p3 | | | |f1 | | 0.1470 | | 0 |
8
+ | - RE | | | |f1 | | 0.0080 | |0 |
9
  | - p1 | | | |f1 | | 0.0073 | | 0 |
10
  | - p2 | | | |f1 | | 0.0074 | | 0 |
11
+ | - p3 | | | |f1 | | 0.0093 | | 0 |
csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__en__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 10, batch_size: 1
5
  | - p1 | | | |f1 | | 0.6091 | | 0 |
6
  | - p2 | | | |f1 | | 0.5646 | | 0 |
7
  | - p3 | | | |f1 | | 0.6243 | | 0 |
8
- | - RE | | | |f1 | | 0.6179 | |0 |
9
  | - p1 | | | |f1 | | 0.6332 | | 0 |
10
  | - p2 | | | |f1 | | 0.6025 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.6091 | | 0 |
6
  | - p2 | | | |f1 | | 0.5646 | | 0 |
7
  | - p3 | | | |f1 | | 0.6243 | | 0 |
8
+ | - RE | | | |f1 | | 0.6164 | |0 |
9
  | - p1 | | | |f1 | | 0.6332 | | 0 |
10
  | - p2 | | | |f1 | | 0.6025 | | 0 |
11
+ | - p3 | | | |f1 | | 0.6133 | | 0 |
csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__gr__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 10, batch_size: 1
5
  | - p1 | | | |f1 | | 0.6119 | | 0 |
6
  | - p2 | | | |f1 | | 0.5847 | | 0 |
7
  | - p3 | | | |f1 | | 0.6119 | | 0 |
8
- | - RE | | | |f1 | | 0.5993 | |0 |
9
  | - p1 | | | |f1 | | 0.5962 | | 0 |
10
  | - p2 | | | |f1 | | 0.6024 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.6119 | | 0 |
6
  | - p2 | | | |f1 | | 0.5847 | | 0 |
7
  | - p3 | | | |f1 | | 0.6119 | | 0 |
8
+ | - RE | | | |f1 | | 0.6056 | |0 |
9
  | - p1 | | | |f1 | | 0.5962 | | 0 |
10
  | - p2 | | | |f1 | | 0.6024 | | 0 |
11
+ | - p3 | | | |f1 | | 0.6183 | | 0 |
csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__it__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 10, batch_size: 1
5
  | - p1 | | | |f1 | | 0.6719 | | 0 |
6
  | - p2 | | | |f1 | | 0.6327 | | 0 |
7
  | - p3 | | | |f1 | | 0.6661 | | 0 |
8
- | - RE | | | |f1 | | 0.5882 | |0 |
9
  | - p1 | | | |f1 | | 0.5767 | | 0 |
10
  | - p2 | | | |f1 | | 0.5998 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.6719 | | 0 |
6
  | - p2 | | | |f1 | | 0.6327 | | 0 |
7
  | - p3 | | | |f1 | | 0.6661 | | 0 |
8
+ | - RE | | | |f1 | | 0.5952 | |0 |
9
  | - p1 | | | |f1 | | 0.5767 | | 0 |
10
  | - p2 | | | |f1 | | 0.5998 | | 0 |
11
+ | - p3 | | | |f1 | | 0.6093 | | 0 |
csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__pl__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 10, batch_size: 1
5
  | - p1 | | | |f1 | | 0.6226 | | 0 |
6
  | - p2 | | | |f1 | | 0.5824 | | 0 |
7
  | - p3 | | | |f1 | | 0.6226 | | 0 |
8
- | - RE | | | |f1 | | 0.5729 | |0 |
9
  | - p1 | | | |f1 | | 0.5991 | | 0 |
10
  | - p2 | | | |f1 | | 0.5466 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.6226 | | 0 |
6
  | - p2 | | | |f1 | | 0.5824 | | 0 |
7
  | - p3 | | | |f1 | | 0.6226 | | 0 |
8
+ | - RE | | | |f1 | | 0.5944 | |0 |
9
  | - p1 | | | |f1 | | 0.5991 | | 0 |
10
  | - p2 | | | |f1 | | 0.5466 | | 0 |
11
+ | - p3 | | | |f1 | | 0.6375 | | 0 |
csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__sk__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 10, batch_size: 1
5
  | - p1 | | | |f1 | | 0.6386 | | 0 |
6
  | - p2 | | | |f1 | | 0.6486 | | 0 |
7
  | - p3 | | | |f1 | | 0.6386 | | 0 |
8
- | - RE | | | |f1 | | 0.5869 | |0 |
9
  | - p1 | | | |f1 | | 0.5894 | | 0 |
10
  | - p2 | | | |f1 | | 0.5845 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.6386 | | 0 |
6
  | - p2 | | | |f1 | | 0.6486 | | 0 |
7
  | - p3 | | | |f1 | | 0.6386 | | 0 |
8
+ | - RE | | | |f1 | | 0.5899 | |0 |
9
  | - p1 | | | |f1 | | 0.5894 | | 0 |
10
  | - p2 | | | |f1 | | 0.5845 | | 0 |
11
+ | - p3 | | | |f1 | | 0.5959 | | 0 |
csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__sl__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 10, batch_size: 1
5
  | - p1 | | | |f1 | | 0.6467 | | 0 |
6
  | - p2 | | | |f1 | | 0.6178 | | 0 |
7
  | - p3 | | | |f1 | | 0.6467 | | 0 |
8
- | - RE | | | |f1 | | 0.5865 | |0 |
9
  | - p1 | | | |f1 | | 0.5949 | | 0 |
10
  | - p2 | | | |f1 | | 0.5782 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.6467 | | 0 |
6
  | - p2 | | | |f1 | | 0.6178 | | 0 |
7
  | - p3 | | | |f1 | | 0.6467 | | 0 |
8
+ | - RE | | | |f1 | | 0.5837 | |0 |
9
  | - p1 | | | |f1 | | 0.5949 | | 0 |
10
  | - p2 | | | |f1 | | 0.5782 | | 0 |
11
+ | - p3 | | | |f1 | | 0.5781 | | 0 |
csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__en__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 10, batch_size: 1
5
  | - p1 | | | |f1 | | 0.5970 | | 0 |
6
  | - p2 | | | |f1 | | 0.5602 | | 0 |
7
  | - p3 | | | |f1 | | 0.6113 | | 0 |
8
- | - RE | | | |f1 | | 0.6475 | |0 |
9
  | - p1 | | | |f1 | | 0.6482 | | 0 |
10
  | - p2 | | | |f1 | | 0.6469 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.5970 | | 0 |
6
  | - p2 | | | |f1 | | 0.5602 | | 0 |
7
  | - p3 | | | |f1 | | 0.6113 | | 0 |
8
+ | - RE | | | |f1 | | 0.6440 | |0 |
9
  | - p1 | | | |f1 | | 0.6482 | | 0 |
10
  | - p2 | | | |f1 | | 0.6469 | | 0 |
11
+ | - p3 | | | |f1 | | 0.6370 | | 0 |
csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__gr__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 10, batch_size: 1
5
  | - p1 | | | |f1 | | 0.6196 | | 0 |
6
  | - p2 | | | |f1 | | 0.6131 | | 0 |
7
  | - p3 | | | |f1 | | 0.6196 | | 0 |
8
- | - RE | | | |f1 | | 0.5905 | |0 |
9
  | - p1 | | | |f1 | | 0.5913 | | 0 |
10
  | - p2 | | | |f1 | | 0.5896 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.6196 | | 0 |
6
  | - p2 | | | |f1 | | 0.6131 | | 0 |
7
  | - p3 | | | |f1 | | 0.6196 | | 0 |
8
+ | - RE | | | |f1 | | 0.5840 | |0 |
9
  | - p1 | | | |f1 | | 0.5913 | | 0 |
10
  | - p2 | | | |f1 | | 0.5896 | | 0 |
11
+ | - p3 | | | |f1 | | 0.5710 | | 0 |
csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__it__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 10, batch_size: 1
5
  | - p1 | | | |f1 | | 0.6934 | | 0 |
6
  | - p2 | | | |f1 | | 0.7152 | | 0 |
7
  | - p3 | | | |f1 | | 0.6930 | | 0 |
8
- | - RE | | | |f1 | | 0.5698 | |0 |
9
  | - p1 | | | |f1 | | 0.5801 | | 0 |
10
  | - p2 | | | |f1 | | 0.5595 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.6934 | | 0 |
6
  | - p2 | | | |f1 | | 0.7152 | | 0 |
7
  | - p3 | | | |f1 | | 0.6930 | | 0 |
8
+ | - RE | | | |f1 | | 0.5641 | |0 |
9
  | - p1 | | | |f1 | | 0.5801 | | 0 |
10
  | - p2 | | | |f1 | | 0.5595 | | 0 |
11
+ | - p3 | | | |f1 | | 0.5526 | | 0 |
csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__pl__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 10, batch_size: 1
5
  | - p1 | | | |f1 | | 0.6008 | | 0 |
6
  | - p2 | | | |f1 | | 0.6004 | | 0 |
7
  | - p3 | | | |f1 | | 0.6008 | | 0 |
8
- | - RE | | | |f1 | | 0.5863 | |0 |
9
  | - p1 | | | |f1 | | 0.5858 | | 0 |
10
  | - p2 | | | |f1 | | 0.5868 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.6008 | | 0 |
6
  | - p2 | | | |f1 | | 0.6004 | | 0 |
7
  | - p3 | | | |f1 | | 0.6008 | | 0 |
8
+ | - RE | | | |f1 | | 0.5888 | |0 |
9
  | - p1 | | | |f1 | | 0.5858 | | 0 |
10
  | - p2 | | | |f1 | | 0.5868 | | 0 |
11
+ | - p3 | | | |f1 | | 0.5938 | | 0 |
csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__sk__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 10, batch_size: 1
5
  | - p1 | | | |f1 | | 0.6743 | | 0 |
6
  | - p2 | | | |f1 | | 0.6673 | | 0 |
7
  | - p3 | | | |f1 | | 0.6743 | | 0 |
8
- | - RE | | | |f1 | | 0.5659 | |0 |
9
  | - p1 | | | |f1 | | 0.5733 | | 0 |
10
  | - p2 | | | |f1 | | 0.5586 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.6743 | | 0 |
6
  | - p2 | | | |f1 | | 0.6673 | | 0 |
7
  | - p3 | | | |f1 | | 0.6743 | | 0 |
8
+ | - RE | | | |f1 | | 0.5643 | |0 |
9
  | - p1 | | | |f1 | | 0.5733 | | 0 |
10
  | - p2 | | | |f1 | | 0.5586 | | 0 |
11
+ | - p3 | | | |f1 | | 0.5609 | | 0 |
csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__sl__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 10, batch_size: 1
5
  | - p1 | | | |f1 | | 0.6253 | | 0 |
6
  | - p2 | | | |f1 | | 0.6615 | | 0 |
7
  | - p3 | | | |f1 | | 0.6253 | | 0 |
8
- | - RE | | | |f1 | | 0.5921 | |0 |
9
  | - p1 | | | |f1 | | 0.5992 | | 0 |
10
  | - p2 | | | |f1 | | 0.5849 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.6253 | | 0 |
6
  | - p2 | | | |f1 | | 0.6615 | | 0 |
7
  | - p3 | | | |f1 | | 0.6253 | | 0 |
8
+ | - RE | | | |f1 | | 0.5727 | |0 |
9
  | - p1 | | | |f1 | | 0.5992 | | 0 |
10
  | - p2 | | | |f1 | | 0.5849 | | 0 |
11
+ | - p3 | | | |f1 | | 0.5339 | | 0 |
csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__en__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=Qwen/Qwen3-30B-A3B-Instruct-2507 ), num_fewshot: 10, batch_size:
5
  | - p1 | | | |f1 | | 0.5986 | | 0 |
6
  | - p2 | | | |f1 | | 0.5593 | | 0 |
7
  | - p3 | | | |f1 | | 0.6143 | | 0 |
8
- | - RE | | | |f1 | | 0.5206 | |0 |
9
  | - p1 | | | |f1 | | 0.5150 | | 0 |
10
  | - p2 | | | |f1 | | 0.5261 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.5986 | | 0 |
6
  | - p2 | | | |f1 | | 0.5593 | | 0 |
7
  | - p3 | | | |f1 | | 0.6143 | | 0 |
8
+ | - RE | | | |f1 | | 0.5259 | |0 |
9
  | - p1 | | | |f1 | | 0.5150 | | 0 |
10
  | - p2 | | | |f1 | | 0.5261 | | 0 |
11
+ | - p3 | | | |f1 | | 0.5364 | | 0 |
csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__gr__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=Qwen/Qwen3-30B-A3B-Instruct-2507 ), num_fewshot: 10, batch_size:
5
  | - p1 | | | |f1 | | 0.6164 | | 0 |
6
  | - p2 | | | |f1 | | 0.5669 | | 0 |
7
  | - p3 | | | |f1 | | 0.6164 | | 0 |
8
- | - RE | | | |f1 | | 0.5112 | |0 |
9
  | - p1 | | | |f1 | | 0.5015 | | 0 |
10
  | - p2 | | | |f1 | | 0.5209 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.6164 | | 0 |
6
  | - p2 | | | |f1 | | 0.5669 | | 0 |
7
  | - p3 | | | |f1 | | 0.6164 | | 0 |
8
+ | - RE | | | |f1 | | 0.5149 | |0 |
9
  | - p1 | | | |f1 | | 0.5015 | | 0 |
10
  | - p2 | | | |f1 | | 0.5209 | | 0 |
11
+ | - p3 | | | |f1 | | 0.5223 | | 0 |
csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__it__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=Qwen/Qwen3-30B-A3B-Instruct-2507 ), num_fewshot: 10, batch_size:
5
  | - p1 | | | |f1 | | 0.6793 | | 0 |
6
  | - p2 | | | |f1 | | 0.6447 | | 0 |
7
  | - p3 | | | |f1 | | 0.6778 | | 0 |
8
- | - RE | | | |f1 | | 0.5940 | |0 |
9
  | - p1 | | | |f1 | | 0.6041 | | 0 |
10
  | - p2 | | | |f1 | | 0.5838 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.6793 | | 0 |
6
  | - p2 | | | |f1 | | 0.6447 | | 0 |
7
  | - p3 | | | |f1 | | 0.6778 | | 0 |
8
+ | - RE | | | |f1 | | 0.5982 | |0 |
9
  | - p1 | | | |f1 | | 0.6041 | | 0 |
10
  | - p2 | | | |f1 | | 0.5838 | | 0 |
11
+ | - p3 | | | |f1 | | 0.6065 | | 0 |
csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__pl__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=Qwen/Qwen3-30B-A3B-Instruct-2507 ), num_fewshot: 10, batch_size:
5
  | - p1 | | | |f1 | | 0.6276 | | 0 |
6
  | - p2 | | | |f1 | | 0.5803 | | 0 |
7
  | - p3 | | | |f1 | | 0.6276 | | 0 |
8
- | - RE | | | |f1 | | 0.5151 | |0 |
9
  | - p1 | | | |f1 | | 0.5103 | | 0 |
10
  | - p2 | | | |f1 | | 0.5200 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.6276 | | 0 |
6
  | - p2 | | | |f1 | | 0.5803 | | 0 |
7
  | - p3 | | | |f1 | | 0.6276 | | 0 |
8
+ | - RE | | | |f1 | | 0.5166 | |0 |
9
  | - p1 | | | |f1 | | 0.5103 | | 0 |
10
  | - p2 | | | |f1 | | 0.5200 | | 0 |
11
+ | - p3 | | | |f1 | | 0.5195 | | 0 |
csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__sk__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=Qwen/Qwen3-30B-A3B-Instruct-2507 ), num_fewshot: 10, batch_size:
5
  | - p1 | | | |f1 | | 0.6085 | | 0 |
6
  | - p2 | | | |f1 | | 0.5919 | | 0 |
7
  | - p3 | | | |f1 | | 0.6085 | | 0 |
8
- | - RE | | | |f1 | | 0.4972 | |0 |
9
  | - p1 | | | |f1 | | 0.4920 | | 0 |
10
  | - p2 | | | |f1 | | 0.5025 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.6085 | | 0 |
6
  | - p2 | | | |f1 | | 0.5919 | | 0 |
7
  | - p3 | | | |f1 | | 0.6085 | | 0 |
8
+ | - RE | | | |f1 | | 0.5106 | |0 |
9
  | - p1 | | | |f1 | | 0.4920 | | 0 |
10
  | - p2 | | | |f1 | | 0.5025 | | 0 |
11
+ | - p3 | | | |f1 | | 0.5373 | | 0 |
csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__sl__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=Qwen/Qwen3-30B-A3B-Instruct-2507 ), num_fewshot: 10, batch_size:
5
  | - p1 | | | |f1 | | 0.6615 | | 0 |
6
  | - p2 | | | |f1 | | 0.5944 | | 0 |
7
  | - p3 | | | |f1 | | 0.6615 | | 0 |
8
- | - RE | | | |f1 | | 0.5319 | |0 |
9
  | - p1 | | | |f1 | | 0.5062 | | 0 |
10
  | - p2 | | | |f1 | | 0.5576 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.6615 | | 0 |
6
  | - p2 | | | |f1 | | 0.5944 | | 0 |
7
  | - p3 | | | |f1 | | 0.6615 | | 0 |
8
+ | - RE | | | |f1 | | 0.5356 | |0 |
9
  | - p1 | | | |f1 | | 0.5062 | | 0 |
10
  | - p2 | | | |f1 | | 0.5576 | | 0 |
11
+ | - p3 | | | |f1 | | 0.5429 | | 0 |
csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__en__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=deepseek-ai/DeepSeek-R1-Distill-Qwen-32B ), num_fewshot: 10, batc
5
  | - p1 | | | |f1 | | 0.6024 | | 0 |
6
  | - p2 | | | |f1 | | 0.5929 | | 0 |
7
  | - p3 | | | |f1 | | 0.5935 | | 0 |
8
- | - RE | | | |f1 | | 0.5195 | |0 |
9
  | - p1 | | | |f1 | | 0.5191 | | 0 |
10
  | - p2 | | | |f1 | | 0.5199 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.6024 | | 0 |
6
  | - p2 | | | |f1 | | 0.5929 | | 0 |
7
  | - p3 | | | |f1 | | 0.5935 | | 0 |
8
+ | - RE | | | |f1 | | 0.5221 | |0 |
9
  | - p1 | | | |f1 | | 0.5191 | | 0 |
10
  | - p2 | | | |f1 | | 0.5199 | | 0 |
11
+ | - p3 | | | |f1 | | 0.5273 | | 0 |
csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__gr__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=deepseek-ai/DeepSeek-R1-Distill-Qwen-32B ), num_fewshot: 10, batc
5
  | - p1 | | | |f1 | | 0.5928 | | 0 |
6
  | - p2 | | | |f1 | | 0.5796 | | 0 |
7
  | - p3 | | | |f1 | | 0.5928 | | 0 |
8
- | - RE | | | |f1 | | 0.4338 | |0 |
9
  | - p1 | | | |f1 | | 0.4467 | | 0 |
10
  | - p2 | | | |f1 | | 0.4210 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.5928 | | 0 |
6
  | - p2 | | | |f1 | | 0.5796 | | 0 |
7
  | - p3 | | | |f1 | | 0.5928 | | 0 |
8
+ | - RE | | | |f1 | | 0.4415 | |0 |
9
  | - p1 | | | |f1 | | 0.4467 | | 0 |
10
  | - p2 | | | |f1 | | 0.4210 | | 0 |
11
+ | - p3 | | | |f1 | | 0.4569 | | 0 |
csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__it__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=deepseek-ai/DeepSeek-R1-Distill-Qwen-32B ), num_fewshot: 10, batc
5
  | - p1 | | | |f1 | | 0.6982 | | 0 |
6
  | - p2 | | | |f1 | | 0.6679 | | 0 |
7
  | - p3 | | | |f1 | | 0.6930 | | 0 |
8
- | - RE | | | |f1 | | 0.5536 | |0 |
9
  | - p1 | | | |f1 | | 0.5546 | | 0 |
10
  | - p2 | | | |f1 | | 0.5526 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.6982 | | 0 |
6
  | - p2 | | | |f1 | | 0.6679 | | 0 |
7
  | - p3 | | | |f1 | | 0.6930 | | 0 |
8
+ | - RE | | | |f1 | | 0.5530 | |0 |
9
  | - p1 | | | |f1 | | 0.5546 | | 0 |
10
  | - p2 | | | |f1 | | 0.5526 | | 0 |
11
+ | - p3 | | | |f1 | | 0.5518 | | 0 |
csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__pl__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=deepseek-ai/DeepSeek-R1-Distill-Qwen-32B ), num_fewshot: 10, batc
5
  | - p1 | | | |f1 | | 0.6214 | | 0 |
6
  | - p2 | | | |f1 | | 0.6140 | | 0 |
7
  | - p3 | | | |f1 | | 0.6214 | | 0 |
8
- | - RE | | | |f1 | | 0.4996 | |0 |
9
  | - p1 | | | |f1 | | 0.4863 | | 0 |
10
  | - p2 | | | |f1 | | 0.5129 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.6214 | | 0 |
6
  | - p2 | | | |f1 | | 0.6140 | | 0 |
7
  | - p3 | | | |f1 | | 0.6214 | | 0 |
8
+ | - RE | | | |f1 | | 0.5023 | |0 |
9
  | - p1 | | | |f1 | | 0.4863 | | 0 |
10
  | - p2 | | | |f1 | | 0.5129 | | 0 |
11
+ | - p3 | | | |f1 | | 0.5076 | | 0 |
csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__sk__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=deepseek-ai/DeepSeek-R1-Distill-Qwen-32B ), num_fewshot: 10, batc
5
  | - p1 | | | |f1 | | 0.6347 | | 0 |
6
  | - p2 | | | |f1 | | 0.6211 | | 0 |
7
  | - p3 | | | |f1 | | 0.6347 | | 0 |
8
- | - RE | | | |f1 | | 0.4625 | |0 |
9
  | - p1 | | | |f1 | | 0.4799 | | 0 |
10
  | - p2 | | | |f1 | | 0.4451 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.6347 | | 0 |
6
  | - p2 | | | |f1 | | 0.6211 | | 0 |
7
  | - p3 | | | |f1 | | 0.6347 | | 0 |
8
+ | - RE | | | |f1 | | 0.4646 | |0 |
9
  | - p1 | | | |f1 | | 0.4799 | | 0 |
10
  | - p2 | | | |f1 | | 0.4451 | | 0 |
11
+ | - p3 | | | |f1 | | 0.4689 | | 0 |
csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__sl__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=deepseek-ai/DeepSeek-R1-Distill-Qwen-32B ), num_fewshot: 10, batc
5
  | - p1 | | | |f1 | | 0.6015 | | 0 |
6
  | - p2 | | | |f1 | | 0.6049 | | 0 |
7
  | - p3 | | | |f1 | | 0.6015 | | 0 |
8
- | - RE | | | |f1 | | 0.4905 | |0 |
9
  | - p1 | | | |f1 | | 0.5137 | | 0 |
10
  | - p2 | | | |f1 | | 0.4674 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.6015 | | 0 |
6
  | - p2 | | | |f1 | | 0.6049 | | 0 |
7
  | - p3 | | | |f1 | | 0.6015 | | 0 |
8
+ | - RE | | | |f1 | | 0.4911 | |0 |
9
  | - p1 | | | |f1 | | 0.5137 | | 0 |
10
  | - p2 | | | |f1 | | 0.4674 | | 0 |
11
+ | - p3 | | | |f1 | | 0.4923 | | 0 |
csv_files/outputs/epfl-llm__meditron-7b__en__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=epfl-llm/meditron-7b ), num_fewshot: 10, batch_size: 1
5
  | - p1 | | | |f1 | | 0.0803 | | 0 |
6
  | - p2 | | | |f1 | | 0.1479 | | 0 |
7
  | - p3 | | | |f1 | | 0.1454 | | 0 |
8
- | - RE | | | |f1 | | 0.0707 | |0 |
9
  | - p1 | | | |f1 | | 0.0722 | | 0 |
10
  | - p2 | | | |f1 | | 0.0692 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.0803 | | 0 |
6
  | - p2 | | | |f1 | | 0.1479 | | 0 |
7
  | - p3 | | | |f1 | | 0.1454 | | 0 |
8
+ | - RE | | | |f1 | | 0.0692 | |0 |
9
  | - p1 | | | |f1 | | 0.0722 | | 0 |
10
  | - p2 | | | |f1 | | 0.0692 | | 0 |
11
+ | - p3 | | | |f1 | | 0.0663 | | 0 |
csv_files/outputs/epfl-llm__meditron-7b__gr__10shot.txt CHANGED
@@ -8,3 +8,4 @@ hf (pretrained=epfl-llm/meditron-7b ), num_fewshot: 10, batch_size: 1
8
  | - RE | | | |f1 | | 0.0000 | |0 |
9
  | - p1 | | | |f1 | | 0.0000 | | 0 |
10
  | - p2 | | | |f1 | | 0.0000 | | 0 |
 
 
8
  | - RE | | | |f1 | | 0.0000 | |0 |
9
  | - p1 | | | |f1 | | 0.0000 | | 0 |
10
  | - p2 | | | |f1 | | 0.0000 | | 0 |
11
+ | - p3 | | | |f1 | | 0.0000 | | 0 |
csv_files/outputs/epfl-llm__meditron-7b__it__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=epfl-llm/meditron-7b ), num_fewshot: 10, batch_size: 1
5
  | - p1 | | | |f1 | | 0.2991 | | 0 |
6
  | - p2 | | | |f1 | | 0.3563 | | 0 |
7
  | - p3 | | | |f1 | | 0.3311 | | 0 |
8
- | - RE | | | |f1 | | 0.0859 | |0 |
9
  | - p1 | | | |f1 | | 0.0832 | | 0 |
10
  | - p2 | | | |f1 | | 0.0887 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.2991 | | 0 |
6
  | - p2 | | | |f1 | | 0.3563 | | 0 |
7
  | - p3 | | | |f1 | | 0.3311 | | 0 |
8
+ | - RE | | | |f1 | | 0.0896 | |0 |
9
  | - p1 | | | |f1 | | 0.0832 | | 0 |
10
  | - p2 | | | |f1 | | 0.0887 | | 0 |
11
+ | - p3 | | | |f1 | | 0.0968 | | 0 |
csv_files/outputs/epfl-llm__meditron-7b__pl__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=epfl-llm/meditron-7b ), num_fewshot: 10, batch_size: 1
5
  | - p1 | | | |f1 | | 0.3184 | | 0 |
6
  | - p2 | | | |f1 | | 0.3297 | | 0 |
7
  | - p3 | | | |f1 | | 0.3184 | | 0 |
8
- | - RE | | | |f1 | | 0.0497 | |0 |
9
  | - p1 | | | |f1 | | 0.0533 | | 0 |
10
  | - p2 | | | |f1 | | 0.0461 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.3184 | | 0 |
6
  | - p2 | | | |f1 | | 0.3297 | | 0 |
7
  | - p3 | | | |f1 | | 0.3184 | | 0 |
8
+ | - RE | | | |f1 | | 0.0510 | |0 |
9
  | - p1 | | | |f1 | | 0.0533 | | 0 |
10
  | - p2 | | | |f1 | | 0.0461 | | 0 |
11
+ | - p3 | | | |f1 | | 0.0535 | | 0 |
csv_files/outputs/epfl-llm__meditron-7b__sk__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=epfl-llm/meditron-7b ), num_fewshot: 10, batch_size: 1
5
  | - p1 | | | |f1 | | 0.3004 | | 0 |
6
  | - p2 | | | |f1 | | 0.2970 | | 0 |
7
  | - p3 | | | |f1 | | 0.3004 | | 0 |
8
- | - RE | | | |f1 | | 0.0419 | |0 |
9
  | - p1 | | | |f1 | | 0.0445 | | 0 |
10
  | - p2 | | | |f1 | | 0.0393 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.3004 | | 0 |
6
  | - p2 | | | |f1 | | 0.2970 | | 0 |
7
  | - p3 | | | |f1 | | 0.3004 | | 0 |
8
+ | - RE | | | |f1 | | 0.0404 | |0 |
9
  | - p1 | | | |f1 | | 0.0445 | | 0 |
10
  | - p2 | | | |f1 | | 0.0393 | | 0 |
11
+ | - p3 | | | |f1 | | 0.0375 | | 0 |
csv_files/outputs/epfl-llm__meditron-7b__sl__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=epfl-llm/meditron-7b ), num_fewshot: 10, batch_size: 1
5
  | - p1 | | | |f1 | | 0.3119 | | 0 |
6
  | - p2 | | | |f1 | | 0.2916 | | 0 |
7
  | - p3 | | | |f1 | | 0.3119 | | 0 |
8
- | - RE | | | |f1 | | 0.0489 | |0 |
9
  | - p1 | | | |f1 | | 0.0477 | | 0 |
10
  | - p2 | | | |f1 | | 0.0501 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.3119 | | 0 |
6
  | - p2 | | | |f1 | | 0.2916 | | 0 |
7
  | - p3 | | | |f1 | | 0.3119 | | 0 |
8
+ | - RE | | | |f1 | | 0.0502 | |0 |
9
  | - p1 | | | |f1 | | 0.0477 | | 0 |
10
  | - p2 | | | |f1 | | 0.0501 | | 0 |
11
+ | - p3 | | | |f1 | | 0.0528 | | 0 |
csv_files/outputs/google__gemma-2-9b-it__en__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=google/gemma-2-9b-it ), num_fewshot: 10, batch_size: 1
5
  | - p1 | | | |f1 | | 0.6200 | | 0 |
6
  | - p2 | | | |f1 | | 0.5639 | | 0 |
7
  | - p3 | | | |f1 | | 0.5918 | | 0 |
8
- | - RE | | | |f1 | | 0.5250 | |0 |
9
  | - p1 | | | |f1 | | 0.5163 | | 0 |
10
  | - p2 | | | |f1 | | 0.5337 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.6200 | | 0 |
6
  | - p2 | | | |f1 | | 0.5639 | | 0 |
7
  | - p3 | | | |f1 | | 0.5918 | | 0 |
8
+ | - RE | | | |f1 | | 0.5303 | |0 |
9
  | - p1 | | | |f1 | | 0.5163 | | 0 |
10
  | - p2 | | | |f1 | | 0.5337 | | 0 |
11
+ | - p3 | | | |f1 | | 0.5409 | | 0 |
csv_files/outputs/google__gemma-2-9b-it__gr__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=google/gemma-2-9b-it ), num_fewshot: 10, batch_size: 1
5
  | - p1 | | | |f1 | | 0.6083 | | 0 |
6
  | - p2 | | | |f1 | | 0.5663 | | 0 |
7
  | - p3 | | | |f1 | | 0.6083 | | 0 |
8
- | - RE | | | |f1 | | 0.5020 | |0 |
9
  | - p1 | | | |f1 | | 0.5070 | | 0 |
10
  | - p2 | | | |f1 | | 0.4971 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.6083 | | 0 |
6
  | - p2 | | | |f1 | | 0.5663 | | 0 |
7
  | - p3 | | | |f1 | | 0.6083 | | 0 |
8
+ | - RE | | | |f1 | | 0.5162 | |0 |
9
  | - p1 | | | |f1 | | 0.5070 | | 0 |
10
  | - p2 | | | |f1 | | 0.4971 | | 0 |
11
+ | - p3 | | | |f1 | | 0.5444 | | 0 |
csv_files/outputs/google__gemma-2-9b-it__it__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=google/gemma-2-9b-it ), num_fewshot: 10, batch_size: 1
5
  | - p1 | | | |f1 | | 0.6910 | | 0 |
6
  | - p2 | | | |f1 | | 0.6643 | | 0 |
7
  | - p3 | | | |f1 | | 0.6569 | | 0 |
8
- | - RE | | | |f1 | | 0.5162 | |0 |
9
  | - p1 | | | |f1 | | 0.4958 | | 0 |
10
  | - p2 | | | |f1 | | 0.5365 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.6910 | | 0 |
6
  | - p2 | | | |f1 | | 0.6643 | | 0 |
7
  | - p3 | | | |f1 | | 0.6569 | | 0 |
8
+ | - RE | | | |f1 | | 0.5209 | |0 |
9
  | - p1 | | | |f1 | | 0.4958 | | 0 |
10
  | - p2 | | | |f1 | | 0.5365 | | 0 |
11
+ | - p3 | | | |f1 | | 0.5305 | | 0 |
csv_files/outputs/google__gemma-2-9b-it__pl__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=google/gemma-2-9b-it ), num_fewshot: 10, batch_size: 1
5
  | - p1 | | | |f1 | | 0.5908 | | 0 |
6
  | - p2 | | | |f1 | | 0.5862 | | 0 |
7
  | - p3 | | | |f1 | | 0.5908 | | 0 |
8
- | - RE | | | |f1 | | 0.4988 | |0 |
9
  | - p1 | | | |f1 | | 0.5168 | | 0 |
10
  | - p2 | | | |f1 | | 0.4808 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.5908 | | 0 |
6
  | - p2 | | | |f1 | | 0.5862 | | 0 |
7
  | - p3 | | | |f1 | | 0.5908 | | 0 |
8
+ | - RE | | | |f1 | | 0.5033 | |0 |
9
  | - p1 | | | |f1 | | 0.5168 | | 0 |
10
  | - p2 | | | |f1 | | 0.4808 | | 0 |
11
+ | - p3 | | | |f1 | | 0.5124 | | 0 |
csv_files/outputs/google__gemma-2-9b-it__sk__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=google/gemma-2-9b-it ), num_fewshot: 10, batch_size: 1
5
  | - p1 | | | |f1 | | 0.6141 | | 0 |
6
  | - p2 | | | |f1 | | 0.6122 | | 0 |
7
  | - p3 | | | |f1 | | 0.6141 | | 0 |
8
- | - RE | | | |f1 | | 0.4953 | |0 |
9
  | - p1 | | | |f1 | | 0.5153 | | 0 |
10
  | - p2 | | | |f1 | | 0.4754 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.6141 | | 0 |
6
  | - p2 | | | |f1 | | 0.6122 | | 0 |
7
  | - p3 | | | |f1 | | 0.6141 | | 0 |
8
+ | - RE | | | |f1 | | 0.5007 | |0 |
9
  | - p1 | | | |f1 | | 0.5153 | | 0 |
10
  | - p2 | | | |f1 | | 0.4754 | | 0 |
11
+ | - p3 | | | |f1 | | 0.5114 | | 0 |
csv_files/outputs/google__gemma-2-9b-it__sl__10shot.txt CHANGED
@@ -5,6 +5,7 @@ hf (pretrained=google/gemma-2-9b-it ), num_fewshot: 10, batch_size: 1
5
  | - p1 | | | |f1 | | 0.6365 | | 0 |
6
  | - p2 | | | |f1 | | 0.5737 | | 0 |
7
  | - p3 | | | |f1 | | 0.6365 | | 0 |
8
- | - RE | | | |f1 | | 0.4839 | |0 |
9
  | - p1 | | | |f1 | | 0.4801 | | 0 |
10
  | - p2 | | | |f1 | | 0.4878 | | 0 |
 
 
5
  | - p1 | | | |f1 | | 0.6365 | | 0 |
6
  | - p2 | | | |f1 | | 0.5737 | | 0 |
7
  | - p3 | | | |f1 | | 0.6365 | | 0 |
8
+ | - RE | | | |f1 | | 0.4883 | |0 |
9
  | - p1 | | | |f1 | | 0.4801 | | 0 |
10
  | - p2 | | | |f1 | | 0.4878 | | 0 |
11
+ | - p3 | | | |f1 | | 0.4972 | | 0 |