Hugging Face's logo

Spaces:
saeedfarzi
/
MediLingua_Leaderboard
Running

App Files Community
Sfarzi commited on
Commit
43a9ad1
·
1 Parent(s): 0591107

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. Gen_llm_eval_output.py +1 -1
  2. csv_files/outputs/.ipynb_checkpoints/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__en__0shot-checkpoint.txt +11 -0
  3. csv_files/outputs/Henrychur__MMed-Llama-3-8B__en__0shot.txt +2 -2
  4. csv_files/outputs/Henrychur__MMed-Llama-3-8B__en__10shot.txt +2 -2
  5. csv_files/outputs/Henrychur__MMed-Llama-3-8B__gr__0shot.txt +2 -2
  6. csv_files/outputs/Henrychur__MMed-Llama-3-8B__gr__10shot.txt +2 -2
  7. csv_files/outputs/Henrychur__MMed-Llama-3-8B__it__0shot.txt +2 -2
  8. csv_files/outputs/Henrychur__MMed-Llama-3-8B__it__10shot.txt +2 -2
  9. csv_files/outputs/Henrychur__MMed-Llama-3-8B__pl__0shot.txt +2 -2
  10. csv_files/outputs/Henrychur__MMed-Llama-3-8B__pl__10shot.txt +2 -2
  11. csv_files/outputs/Henrychur__MMed-Llama-3-8B__sk__0shot.txt +2 -2
  12. csv_files/outputs/Henrychur__MMed-Llama-3-8B__sk__10shot.txt +2 -2
  13. csv_files/outputs/Henrychur__MMed-Llama-3-8B__sl__0shot.txt +2 -2
  14. csv_files/outputs/Henrychur__MMed-Llama-3-8B__sl__10shot.txt +2 -2
  15. csv_files/outputs/HiTZ__Medical-mT5-large__en__0shot.txt +2 -2
  16. csv_files/outputs/HiTZ__Medical-mT5-large__en__10shot.txt +2 -2
  17. csv_files/outputs/HiTZ__Medical-mT5-large__gr__0shot.txt +2 -2
  18. csv_files/outputs/HiTZ__Medical-mT5-large__gr__10shot.txt +2 -2
  19. csv_files/outputs/HiTZ__Medical-mT5-large__it__0shot.txt +2 -2
  20. csv_files/outputs/HiTZ__Medical-mT5-large__it__10shot.txt +2 -2
  21. csv_files/outputs/HiTZ__Medical-mT5-large__pl__0shot.txt +2 -2
  22. csv_files/outputs/HiTZ__Medical-mT5-large__pl__10shot.txt +2 -2
  23. csv_files/outputs/HiTZ__Medical-mT5-large__sk__0shot.txt +2 -2
  24. csv_files/outputs/HiTZ__Medical-mT5-large__sk__10shot.txt +2 -2
  25. csv_files/outputs/HiTZ__Medical-mT5-large__sl__0shot.txt +2 -2
  26. csv_files/outputs/HiTZ__Medical-mT5-large__sl__10shot.txt +2 -2
  27. csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__en__0shot.txt +2 -2
  28. csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__en__10shot.txt +2 -2
  29. csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__gr__0shot.txt +2 -2
  30. csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__gr__10shot.txt +2 -2
  31. csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__it__0shot.txt +2 -2
  32. csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__it__10shot.txt +2 -2
  33. csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__pl__0shot.txt +2 -2
  34. csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__pl__10shot.txt +2 -2
  35. csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__sk__0shot.txt +2 -2
  36. csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__sk__10shot.txt +2 -2
  37. csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__sl__0shot.txt +2 -2
  38. csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__sl__10shot.txt +2 -2
  39. csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__en__0shot.txt +2 -2
  40. csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__en__10shot.txt +2 -2
  41. csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__gr__0shot.txt +2 -2
  42. csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__gr__10shot.txt +2 -2
  43. csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__it__0shot.txt +2 -2
  44. csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__it__10shot.txt +2 -2
  45. csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__pl__0shot.txt +2 -2
  46. csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__pl__10shot.txt +2 -2
  47. csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__sk__0shot.txt +2 -2
  48. csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__sk__10shot.txt +2 -2
  49. csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__sl__0shot.txt +2 -2
  50. csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__sl__10shot.txt +2 -2
Gen_llm_eval_output.py CHANGED
@@ -81,7 +81,7 @@ def render_group_table(g: pd.DataFrame, model: str, language: str, configuration
81
  for task, df_task in g.groupby("task", sort=False):
82
  f1s = df_task["f1"].to_numpy(dtype=float)
83
  task_mean = float(np.mean(f1s)) if f1s.size else float("nan")
84
- lines.append(f"| - {task} | | | |f1 | | {format_float(task_mean)} | |0 |")
85
 
86
  # Prompt-level rows, sorted by prompt number if available
87
  df_task = df_task.copy()
 
81
  for task, df_task in g.groupby("task", sort=False):
82
  f1s = df_task["f1"].to_numpy(dtype=float)
83
  task_mean = float(np.mean(f1s)) if f1s.size else float("nan")
84
+ lines.append(f"| - {task.upper()} | | | |f1 | | {format_float(task_mean)} | |0 |")
85
 
86
  # Prompt-level rows, sorted by prompt number if available
87
  df_task = df_task.copy()
csv_files/outputs/.ipynb_checkpoints/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__en__0shot-checkpoint.txt ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
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__0shot.txt CHANGED
@@ -1,11 +1,11 @@
1
  hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.0918 | |0 |
5
  | - p1 | | | |f1 | | 0.0629 | | 0 |
6
  | - p2 | | | |f1 | | 0.1041 | | 0 |
7
  | - p3 | | | |f1 | | 0.1083 | | 0 |
8
- | - re | | | |f1 | | 0.2604 | |0 |
9
  | - p1 | | | |f1 | | 0.1287 | | 0 |
10
  | - p2 | | | |f1 | | 0.3394 | | 0 |
11
  | - p3 | | | |f1 | | 0.3131 | | 0 |
 
1
  hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.0918 | |0 |
5
  | - p1 | | | |f1 | | 0.0629 | | 0 |
6
  | - p2 | | | |f1 | | 0.1041 | | 0 |
7
  | - p3 | | | |f1 | | 0.1083 | | 0 |
8
+ | - RE | | | |f1 | | 0.2604 | |0 |
9
  | - p1 | | | |f1 | | 0.1287 | | 0 |
10
  | - p2 | | | |f1 | | 0.3394 | | 0 |
11
  | - p3 | | | |f1 | | 0.3131 | | 0 |
csv_files/outputs/Henrychur__MMed-Llama-3-8B__en__10shot.txt CHANGED
@@ -1,10 +1,10 @@
1
  hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.2142 | |0 |
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 |
 
1
  hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.2142 | |0 |
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 |
csv_files/outputs/Henrychur__MMed-Llama-3-8B__gr__0shot.txt CHANGED
@@ -1,11 +1,11 @@
1
  hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.0611 | |0 |
5
  | - p1 | | | |f1 | | 0.0620 | | 0 |
6
  | - p2 | | | |f1 | | 0.0592 | | 0 |
7
  | - p3 | | | |f1 | | 0.0620 | | 0 |
8
- | - re | | | |f1 | | 0.0863 | |0 |
9
  | - p1 | | | |f1 | | 0.1017 | | 0 |
10
  | - p2 | | | |f1 | | 0.0506 | | 0 |
11
  | - p3 | | | |f1 | | 0.1065 | | 0 |
 
1
  hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.0611 | |0 |
5
  | - p1 | | | |f1 | | 0.0620 | | 0 |
6
  | - p2 | | | |f1 | | 0.0592 | | 0 |
7
  | - p3 | | | |f1 | | 0.0620 | | 0 |
8
+ | - RE | | | |f1 | | 0.0863 | |0 |
9
  | - p1 | | | |f1 | | 0.1017 | | 0 |
10
  | - p2 | | | |f1 | | 0.0506 | | 0 |
11
  | - p3 | | | |f1 | | 0.1065 | | 0 |
csv_files/outputs/Henrychur__MMed-Llama-3-8B__gr__10shot.txt CHANGED
@@ -1,10 +1,10 @@
1
  hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.1474 | |0 |
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 |
 
1
  hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.1474 | |0 |
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 |
csv_files/outputs/Henrychur__MMed-Llama-3-8B__it__0shot.txt CHANGED
@@ -1,11 +1,11 @@
1
  hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.0416 | |0 |
5
  | - p1 | | | |f1 | | 0.0435 | | 0 |
6
  | - p2 | | | |f1 | | 0.0429 | | 0 |
7
  | - p3 | | | |f1 | | 0.0384 | | 0 |
8
- | - re | | | |f1 | | 0.1413 | |0 |
9
  | - p1 | | | |f1 | | 0.0672 | | 0 |
10
  | - p2 | | | |f1 | | 0.2266 | | 0 |
11
  | - p3 | | | |f1 | | 0.1300 | | 0 |
 
1
  hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.0416 | |0 |
5
  | - p1 | | | |f1 | | 0.0435 | | 0 |
6
  | - p2 | | | |f1 | | 0.0429 | | 0 |
7
  | - p3 | | | |f1 | | 0.0384 | | 0 |
8
+ | - RE | | | |f1 | | 0.1413 | |0 |
9
  | - p1 | | | |f1 | | 0.0672 | | 0 |
10
  | - p2 | | | |f1 | | 0.2266 | | 0 |
11
  | - p3 | | | |f1 | | 0.1300 | | 0 |
csv_files/outputs/Henrychur__MMed-Llama-3-8B__it__10shot.txt CHANGED
@@ -1,10 +1,10 @@
1
  hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.3753 | |0 |
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 |
 
1
  hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.3753 | |0 |
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 |
csv_files/outputs/Henrychur__MMed-Llama-3-8B__pl__0shot.txt CHANGED
@@ -1,11 +1,11 @@
1
  hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.0379 | |0 |
5
  | - p1 | | | |f1 | | 0.0379 | | 0 |
6
  | - p2 | | | |f1 | | 0.0378 | | 0 |
7
  | - p3 | | | |f1 | | 0.0379 | | 0 |
8
- | - re | | | |f1 | | 0.0891 | |0 |
9
  | - p1 | | | |f1 | | 0.0602 | | 0 |
10
  | - p2 | | | |f1 | | 0.1293 | | 0 |
11
  | - p3 | | | |f1 | | 0.0778 | | 0 |
 
1
  hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.0379 | |0 |
5
  | - p1 | | | |f1 | | 0.0379 | | 0 |
6
  | - p2 | | | |f1 | | 0.0378 | | 0 |
7
  | - p3 | | | |f1 | | 0.0379 | | 0 |
8
+ | - RE | | | |f1 | | 0.0891 | |0 |
9
  | - p1 | | | |f1 | | 0.0602 | | 0 |
10
  | - p2 | | | |f1 | | 0.1293 | | 0 |
11
  | - p3 | | | |f1 | | 0.0778 | | 0 |
csv_files/outputs/Henrychur__MMed-Llama-3-8B__pl__10shot.txt CHANGED
@@ -1,10 +1,10 @@
1
  hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.3966 | |0 |
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 |
 
1
  hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.3966 | |0 |
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 |
csv_files/outputs/Henrychur__MMed-Llama-3-8B__sk__0shot.txt CHANGED
@@ -1,11 +1,11 @@
1
  hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.0385 | |0 |
5
  | - p1 | | | |f1 | | 0.0387 | | 0 |
6
  | - p2 | | | |f1 | | 0.0380 | | 0 |
7
  | - p3 | | | |f1 | | 0.0387 | | 0 |
8
- | - re | | | |f1 | | 0.0174 | |0 |
9
  | - p1 | | | |f1 | | 0.0121 | | 0 |
10
  | - p2 | | | |f1 | | 0.0280 | | 0 |
11
  | - p3 | | | |f1 | | 0.0121 | | 0 |
 
1
  hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.0385 | |0 |
5
  | - p1 | | | |f1 | | 0.0387 | | 0 |
6
  | - p2 | | | |f1 | | 0.0380 | | 0 |
7
  | - p3 | | | |f1 | | 0.0387 | | 0 |
8
+ | - RE | | | |f1 | | 0.0174 | |0 |
9
  | - p1 | | | |f1 | | 0.0121 | | 0 |
10
  | - p2 | | | |f1 | | 0.0280 | | 0 |
11
  | - p3 | | | |f1 | | 0.0121 | | 0 |
csv_files/outputs/Henrychur__MMed-Llama-3-8B__sk__10shot.txt CHANGED
@@ -1,10 +1,10 @@
1
  hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.3507 | |0 |
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 |
 
1
  hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.3507 | |0 |
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 |
csv_files/outputs/Henrychur__MMed-Llama-3-8B__sl__0shot.txt CHANGED
@@ -1,11 +1,11 @@
1
  hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.0438 | |0 |
5
  | - p1 | | | |f1 | | 0.0429 | | 0 |
6
  | - p2 | | | |f1 | | 0.0456 | | 0 |
7
  | - p3 | | | |f1 | | 0.0429 | | 0 |
8
- | - re | | | |f1 | | 0.1278 | |0 |
9
  | - p1 | | | |f1 | | 0.0967 | | 0 |
10
  | - p2 | | | |f1 | | 0.1900 | | 0 |
11
  | - p3 | | | |f1 | | 0.0967 | | 0 |
 
1
  hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.0438 | |0 |
5
  | - p1 | | | |f1 | | 0.0429 | | 0 |
6
  | - p2 | | | |f1 | | 0.0456 | | 0 |
7
  | - p3 | | | |f1 | | 0.0429 | | 0 |
8
+ | - RE | | | |f1 | | 0.1278 | |0 |
9
  | - p1 | | | |f1 | | 0.0967 | | 0 |
10
  | - p2 | | | |f1 | | 0.1900 | | 0 |
11
  | - p3 | | | |f1 | | 0.0967 | | 0 |
csv_files/outputs/Henrychur__MMed-Llama-3-8B__sl__10shot.txt CHANGED
@@ -1,10 +1,10 @@
1
  hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.3720 | |0 |
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 |
 
1
  hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.3720 | |0 |
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 |
csv_files/outputs/HiTZ__Medical-mT5-large__en__0shot.txt CHANGED
@@ -1,11 +1,11 @@
1
  hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.0578 | |0 |
5
  | - p1 | | | |f1 | | 0.0940 | | 0 |
6
  | - p2 | | | |f1 | | 0.0331 | | 0 |
7
  | - p3 | | | |f1 | | 0.0464 | | 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 |
 
1
  hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.0578 | |0 |
5
  | - p1 | | | |f1 | | 0.0940 | | 0 |
6
  | - p2 | | | |f1 | | 0.0331 | | 0 |
7
  | - p3 | | | |f1 | | 0.0464 | | 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/HiTZ__Medical-mT5-large__en__10shot.txt CHANGED
@@ -1,10 +1,10 @@
1
  hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.1317 | |0 |
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 |
 
1
  hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.1317 | |0 |
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 |
csv_files/outputs/HiTZ__Medical-mT5-large__gr__0shot.txt CHANGED
@@ -1,11 +1,11 @@
1
  hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.0769 | |0 |
5
  | - p1 | | | |f1 | | 0.0859 | | 0 |
6
  | - p2 | | | |f1 | | 0.0591 | | 0 |
7
  | - p3 | | | |f1 | | 0.0859 | | 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 |
 
1
  hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.0769 | |0 |
5
  | - p1 | | | |f1 | | 0.0859 | | 0 |
6
  | - p2 | | | |f1 | | 0.0591 | | 0 |
7
  | - p3 | | | |f1 | | 0.0859 | | 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/HiTZ__Medical-mT5-large__gr__10shot.txt CHANGED
@@ -1,10 +1,10 @@
1
  hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.1448 | |0 |
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 |
 
1
  hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.1448 | |0 |
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 |
csv_files/outputs/HiTZ__Medical-mT5-large__it__0shot.txt CHANGED
@@ -1,10 +1,10 @@
1
  hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.0812 | |0 |
5
  | - p1 | | | |f1 | | 0.0770 | | 0 |
6
  | - p2 | | | |f1 | | 0.0920 | | 0 |
7
  | - p3 | | | |f1 | | 0.0747 | | 0 |
8
- | - re | | | |f1 | | 0.0000 | |0 |
9
  | - p2 | | | |f1 | | 0.0000 | | 0 |
10
  | - p3 | | | |f1 | | 0.0000 | | 0 |
 
1
  hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.0812 | |0 |
5
  | - p1 | | | |f1 | | 0.0770 | | 0 |
6
  | - p2 | | | |f1 | | 0.0920 | | 0 |
7
  | - p3 | | | |f1 | | 0.0747 | | 0 |
8
+ | - RE | | | |f1 | | 0.0000 | |0 |
9
  | - p2 | | | |f1 | | 0.0000 | | 0 |
10
  | - p3 | | | |f1 | | 0.0000 | | 0 |
csv_files/outputs/HiTZ__Medical-mT5-large__it__10shot.txt CHANGED
@@ -1,10 +1,10 @@
1
  hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.1694 | |0 |
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 |
 
1
  hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.1694 | |0 |
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 |
csv_files/outputs/HiTZ__Medical-mT5-large__pl__0shot.txt CHANGED
@@ -1,11 +1,11 @@
1
  hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.0308 | |0 |
5
  | - p1 | | | |f1 | | 0.0244 | | 0 |
6
  | - p2 | | | |f1 | | 0.0436 | | 0 |
7
  | - p3 | | | |f1 | | 0.0244 | | 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 |
 
1
  hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.0308 | |0 |
5
  | - p1 | | | |f1 | | 0.0244 | | 0 |
6
  | - p2 | | | |f1 | | 0.0436 | | 0 |
7
  | - p3 | | | |f1 | | 0.0244 | | 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/HiTZ__Medical-mT5-large__pl__10shot.txt CHANGED
@@ -1,10 +1,10 @@
1
  hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.1516 | |0 |
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 |
 
1
  hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.1516 | |0 |
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 |
csv_files/outputs/HiTZ__Medical-mT5-large__sk__0shot.txt CHANGED
@@ -1,11 +1,11 @@
1
  hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.0712 | |0 |
5
  | - p1 | | | |f1 | | 0.0880 | | 0 |
6
  | - p2 | | | |f1 | | 0.0375 | | 0 |
7
  | - p3 | | | |f1 | | 0.0880 | | 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 |
 
1
  hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.0712 | |0 |
5
  | - p1 | | | |f1 | | 0.0880 | | 0 |
6
  | - p2 | | | |f1 | | 0.0375 | | 0 |
7
  | - p3 | | | |f1 | | 0.0880 | | 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/HiTZ__Medical-mT5-large__sk__10shot.txt CHANGED
@@ -1,10 +1,10 @@
1
  hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.1444 | |0 |
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 |
 
1
  hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.1444 | |0 |
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 |
csv_files/outputs/HiTZ__Medical-mT5-large__sl__0shot.txt CHANGED
@@ -1,11 +1,11 @@
1
  hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.0711 | |0 |
5
  | - p1 | | | |f1 | | 0.0777 | | 0 |
6
  | - p2 | | | |f1 | | 0.0579 | | 0 |
7
  | - p3 | | | |f1 | | 0.0777 | | 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 |
 
1
  hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.0711 | |0 |
5
  | - p1 | | | |f1 | | 0.0777 | | 0 |
6
  | - p2 | | | |f1 | | 0.0579 | | 0 |
7
  | - p3 | | | |f1 | | 0.0777 | | 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/HiTZ__Medical-mT5-large__sl__10shot.txt CHANGED
@@ -1,10 +1,10 @@
1
  hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.1422 | |0 |
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 |
 
1
  hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.1422 | |0 |
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 |
csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__en__0shot.txt CHANGED
@@ -1,11 +1,11 @@
1
  hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.2500 | |0 |
5
  | - p1 | | | |f1 | | 0.3425 | | 0 |
6
  | - p2 | | | |f1 | | 0.1181 | | 0 |
7
  | - p3 | | | |f1 | | 0.2893 | | 0 |
8
- | - re | | | |f1 | | 0.4075 | |0 |
9
  | - p1 | | | |f1 | | 0.4135 | | 0 |
10
  | - p2 | | | |f1 | | 0.3917 | | 0 |
11
  | - p3 | | | |f1 | | 0.4172 | | 0 |
 
1
  hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.2500 | |0 |
5
  | - p1 | | | |f1 | | 0.3425 | | 0 |
6
  | - p2 | | | |f1 | | 0.1181 | | 0 |
7
  | - p3 | | | |f1 | | 0.2893 | | 0 |
8
+ | - RE | | | |f1 | | 0.4075 | |0 |
9
  | - p1 | | | |f1 | | 0.4135 | | 0 |
10
  | - p2 | | | |f1 | | 0.3917 | | 0 |
11
  | - p3 | | | |f1 | | 0.4172 | | 0 |
csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__en__10shot.txt CHANGED
@@ -1,10 +1,10 @@
1
  hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.5993 | |0 |
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 |
 
1
  hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.5993 | |0 |
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 |
csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__gr__0shot.txt CHANGED
@@ -1,11 +1,11 @@
1
  hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.1290 | |0 |
5
  | - p1 | | | |f1 | | 0.1339 | | 0 |
6
  | - p2 | | | |f1 | | 0.1191 | | 0 |
7
  | - p3 | | | |f1 | | 0.1339 | | 0 |
8
- | - re | | | |f1 | | 0.3957 | |0 |
9
  | - p1 | | | |f1 | | 0.3796 | | 0 |
10
  | - p2 | | | |f1 | | 0.4266 | | 0 |
11
  | - p3 | | | |f1 | | 0.3810 | | 0 |
 
1
  hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.1290 | |0 |
5
  | - p1 | | | |f1 | | 0.1339 | | 0 |
6
  | - p2 | | | |f1 | | 0.1191 | | 0 |
7
  | - p3 | | | |f1 | | 0.1339 | | 0 |
8
+ | - RE | | | |f1 | | 0.3957 | |0 |
9
  | - p1 | | | |f1 | | 0.3796 | | 0 |
10
  | - p2 | | | |f1 | | 0.4266 | | 0 |
11
  | - p3 | | | |f1 | | 0.3810 | | 0 |
csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__gr__10shot.txt CHANGED
@@ -1,10 +1,10 @@
1
  hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.6028 | |0 |
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 |
 
1
  hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.6028 | |0 |
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 |
csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__it__0shot.txt CHANGED
@@ -1,11 +1,11 @@
1
  hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.2137 | |0 |
5
  | - p1 | | | |f1 | | 0.2467 | | 0 |
6
  | - p2 | | | |f1 | | 0.1709 | | 0 |
7
  | - p3 | | | |f1 | | 0.2234 | | 0 |
8
- | - re | | | |f1 | | 0.4016 | |0 |
9
  | - p1 | | | |f1 | | 0.4173 | | 0 |
10
  | - p2 | | | |f1 | | 0.3770 | | 0 |
11
  | - p3 | | | |f1 | | 0.4106 | | 0 |
 
1
  hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.2137 | |0 |
5
  | - p1 | | | |f1 | | 0.2467 | | 0 |
6
  | - p2 | | | |f1 | | 0.1709 | | 0 |
7
  | - p3 | | | |f1 | | 0.2234 | | 0 |
8
+ | - RE | | | |f1 | | 0.4016 | |0 |
9
  | - p1 | | | |f1 | | 0.4173 | | 0 |
10
  | - p2 | | | |f1 | | 0.3770 | | 0 |
11
  | - p3 | | | |f1 | | 0.4106 | | 0 |
csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__it__10shot.txt CHANGED
@@ -1,10 +1,10 @@
1
  hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.6569 | |0 |
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 |
 
1
  hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.6569 | |0 |
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 |
csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__pl__0shot.txt CHANGED
@@ -1,11 +1,11 @@
1
  hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.0586 | |0 |
5
  | - p1 | | | |f1 | | 0.0697 | | 0 |
6
  | - p2 | | | |f1 | | 0.0364 | | 0 |
7
  | - p3 | | | |f1 | | 0.0697 | | 0 |
8
- | - re | | | |f1 | | 0.4022 | |0 |
9
  | - p1 | | | |f1 | | 0.3803 | | 0 |
10
  | - p2 | | | |f1 | | 0.4464 | | 0 |
11
  | - p3 | | | |f1 | | 0.3800 | | 0 |
 
1
  hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.0586 | |0 |
5
  | - p1 | | | |f1 | | 0.0697 | | 0 |
6
  | - p2 | | | |f1 | | 0.0364 | | 0 |
7
  | - p3 | | | |f1 | | 0.0697 | | 0 |
8
+ | - RE | | | |f1 | | 0.4022 | |0 |
9
  | - p1 | | | |f1 | | 0.3803 | | 0 |
10
  | - p2 | | | |f1 | | 0.4464 | | 0 |
11
  | - p3 | | | |f1 | | 0.3800 | | 0 |
csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__pl__10shot.txt CHANGED
@@ -1,10 +1,10 @@
1
  hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.6092 | |0 |
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 |
 
1
  hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.6092 | |0 |
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 |
csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__sk__0shot.txt CHANGED
@@ -1,11 +1,11 @@
1
  hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.0955 | |0 |
5
  | - p1 | | | |f1 | | 0.1220 | | 0 |
6
  | - p2 | | | |f1 | | 0.0426 | | 0 |
7
  | - p3 | | | |f1 | | 0.1220 | | 0 |
8
- | - re | | | |f1 | | 0.4116 | |0 |
9
  | - p1 | | | |f1 | | 0.4027 | | 0 |
10
  | - p2 | | | |f1 | | 0.4294 | | 0 |
11
  | - p3 | | | |f1 | | 0.4027 | | 0 |
 
1
  hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.0955 | |0 |
5
  | - p1 | | | |f1 | | 0.1220 | | 0 |
6
  | - p2 | | | |f1 | | 0.0426 | | 0 |
7
  | - p3 | | | |f1 | | 0.1220 | | 0 |
8
+ | - RE | | | |f1 | | 0.4116 | |0 |
9
  | - p1 | | | |f1 | | 0.4027 | | 0 |
10
  | - p2 | | | |f1 | | 0.4294 | | 0 |
11
  | - p3 | | | |f1 | | 0.4027 | | 0 |
csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__sk__10shot.txt CHANGED
@@ -1,10 +1,10 @@
1
  hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.6419 | |0 |
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 |
 
1
  hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.6419 | |0 |
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 |
csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__sl__0shot.txt CHANGED
@@ -1,11 +1,11 @@
1
  hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.3398 | |0 |
5
  | - p1 | | | |f1 | | 0.3910 | | 0 |
6
  | - p2 | | | |f1 | | 0.2375 | | 0 |
7
  | - p3 | | | |f1 | | 0.3910 | | 0 |
8
- | - re | | | |f1 | | 0.3777 | |0 |
9
  | - p1 | | | |f1 | | 0.3775 | | 0 |
10
  | - p2 | | | |f1 | | 0.3783 | | 0 |
11
  | - p3 | | | |f1 | | 0.3775 | | 0 |
 
1
  hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.3398 | |0 |
5
  | - p1 | | | |f1 | | 0.3910 | | 0 |
6
  | - p2 | | | |f1 | | 0.2375 | | 0 |
7
  | - p3 | | | |f1 | | 0.3910 | | 0 |
8
+ | - RE | | | |f1 | | 0.3777 | |0 |
9
  | - p1 | | | |f1 | | 0.3775 | | 0 |
10
  | - p2 | | | |f1 | | 0.3783 | | 0 |
11
  | - p3 | | | |f1 | | 0.3775 | | 0 |
csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__sl__10shot.txt CHANGED
@@ -1,10 +1,10 @@
1
  hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.6371 | |0 |
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 |
 
1
  hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.6371 | |0 |
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 |
csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__en__0shot.txt CHANGED
@@ -1,11 +1,11 @@
1
  hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.3279 | |0 |
5
  | - p1 | | | |f1 | | 0.3804 | | 0 |
6
  | - p2 | | | |f1 | | 0.3068 | | 0 |
7
  | - p3 | | | |f1 | | 0.2964 | | 0 |
8
- | - re | | | |f1 | | 0.4658 | |0 |
9
  | - p1 | | | |f1 | | 0.4734 | | 0 |
10
  | - p2 | | | |f1 | | 0.4649 | | 0 |
11
  | - p3 | | | |f1 | | 0.4591 | | 0 |
 
1
  hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.3279 | |0 |
5
  | - p1 | | | |f1 | | 0.3804 | | 0 |
6
  | - p2 | | | |f1 | | 0.3068 | | 0 |
7
  | - p3 | | | |f1 | | 0.2964 | | 0 |
8
+ | - RE | | | |f1 | | 0.4658 | |0 |
9
  | - p1 | | | |f1 | | 0.4734 | | 0 |
10
  | - p2 | | | |f1 | | 0.4649 | | 0 |
11
  | - p3 | | | |f1 | | 0.4591 | | 0 |
csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__en__10shot.txt CHANGED
@@ -1,10 +1,10 @@
1
  hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.5895 | |0 |
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 |
 
1
  hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.5895 | |0 |
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 |
csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__gr__0shot.txt CHANGED
@@ -1,11 +1,11 @@
1
  hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.4506 | |0 |
5
  | - p1 | | | |f1 | | 0.5976 | | 0 |
6
  | - p2 | | | |f1 | | 0.1568 | | 0 |
7
  | - p3 | | | |f1 | | 0.5976 | | 0 |
8
- | - re | | | |f1 | | 0.4104 | |0 |
9
  | - p1 | | | |f1 | | 0.4393 | | 0 |
10
  | - p2 | | | |f1 | | 0.4083 | | 0 |
11
  | - p3 | | | |f1 | | 0.3834 | | 0 |
 
1
  hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.4506 | |0 |
5
  | - p1 | | | |f1 | | 0.5976 | | 0 |
6
  | - p2 | | | |f1 | | 0.1568 | | 0 |
7
  | - p3 | | | |f1 | | 0.5976 | | 0 |
8
+ | - RE | | | |f1 | | 0.4104 | |0 |
9
  | - p1 | | | |f1 | | 0.4393 | | 0 |
10
  | - p2 | | | |f1 | | 0.4083 | | 0 |
11
  | - p3 | | | |f1 | | 0.3834 | | 0 |
csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__gr__10shot.txt CHANGED
@@ -1,10 +1,10 @@
1
  hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.6175 | |0 |
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 |
 
1
  hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.6175 | |0 |
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 |
csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__it__0shot.txt CHANGED
@@ -1,11 +1,11 @@
1
  hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.2734 | |0 |
5
  | - p1 | | | |f1 | | 0.3758 | | 0 |
6
  | - p2 | | | |f1 | | 0.1647 | | 0 |
7
  | - p3 | | | |f1 | | 0.2796 | | 0 |
8
- | - re | | | |f1 | | 0.4370 | |0 |
9
  | - p1 | | | |f1 | | 0.4505 | | 0 |
10
  | - p2 | | | |f1 | | 0.4159 | | 0 |
11
  | - p3 | | | |f1 | | 0.4447 | | 0 |
 
1
  hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.2734 | |0 |
5
  | - p1 | | | |f1 | | 0.3758 | | 0 |
6
  | - p2 | | | |f1 | | 0.1647 | | 0 |
7
  | - p3 | | | |f1 | | 0.2796 | | 0 |
8
+ | - RE | | | |f1 | | 0.4370 | |0 |
9
  | - p1 | | | |f1 | | 0.4505 | | 0 |
10
  | - p2 | | | |f1 | | 0.4159 | | 0 |
11
  | - p3 | | | |f1 | | 0.4447 | | 0 |
csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__it__10shot.txt CHANGED
@@ -1,10 +1,10 @@
1
  hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.7005 | |0 |
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 |
 
1
  hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.7005 | |0 |
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 |
csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__pl__0shot.txt CHANGED
@@ -1,11 +1,11 @@
1
  hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.2428 | |0 |
5
  | - p1 | | | |f1 | | 0.2486 | | 0 |
6
  | - p2 | | | |f1 | | 0.2311 | | 0 |
7
  | - p3 | | | |f1 | | 0.2486 | | 0 |
8
- | - re | | | |f1 | | 0.4074 | |0 |
9
  | - p1 | | | |f1 | | 0.3865 | | 0 |
10
  | - p2 | | | |f1 | | 0.4569 | | 0 |
11
  | - p3 | | | |f1 | | 0.3788 | | 0 |
 
1
  hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.2428 | |0 |
5
  | - p1 | | | |f1 | | 0.2486 | | 0 |
6
  | - p2 | | | |f1 | | 0.2311 | | 0 |
7
  | - p3 | | | |f1 | | 0.2486 | | 0 |
8
+ | - RE | | | |f1 | | 0.4074 | |0 |
9
  | - p1 | | | |f1 | | 0.3865 | | 0 |
10
  | - p2 | | | |f1 | | 0.4569 | | 0 |
11
  | - p3 | | | |f1 | | 0.3788 | | 0 |
csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__pl__10shot.txt CHANGED
@@ -1,10 +1,10 @@
1
  hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.6006 | |0 |
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 |
 
1
  hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.6006 | |0 |
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 |
csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__sk__0shot.txt CHANGED
@@ -1,11 +1,11 @@
1
  hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.3375 | |0 |
5
  | - p1 | | | |f1 | | 0.3578 | | 0 |
6
  | - p2 | | | |f1 | | 0.2968 | | 0 |
7
  | - p3 | | | |f1 | | 0.3578 | | 0 |
8
- | - re | | | |f1 | | 0.4031 | |0 |
9
  | - p1 | | | |f1 | | 0.3971 | | 0 |
10
  | - p2 | | | |f1 | | 0.4152 | | 0 |
11
  | - p3 | | | |f1 | | 0.3971 | | 0 |
 
1
  hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.3375 | |0 |
5
  | - p1 | | | |f1 | | 0.3578 | | 0 |
6
  | - p2 | | | |f1 | | 0.2968 | | 0 |
7
  | - p3 | | | |f1 | | 0.3578 | | 0 |
8
+ | - RE | | | |f1 | | 0.4031 | |0 |
9
  | - p1 | | | |f1 | | 0.3971 | | 0 |
10
  | - p2 | | | |f1 | | 0.4152 | | 0 |
11
  | - p3 | | | |f1 | | 0.3971 | | 0 |
csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__sk__10shot.txt CHANGED
@@ -1,10 +1,10 @@
1
  hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.6720 | |0 |
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 |
 
1
  hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.6720 | |0 |
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 |
csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__sl__0shot.txt CHANGED
@@ -1,11 +1,11 @@
1
  hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.3183 | |0 |
5
  | - p1 | | | |f1 | | 0.3344 | | 0 |
6
  | - p2 | | | |f1 | | 0.2863 | | 0 |
7
  | - p3 | | | |f1 | | 0.3344 | | 0 |
8
- | - re | | | |f1 | | 0.4048 | |0 |
9
  | - p1 | | | |f1 | | 0.3979 | | 0 |
10
  | - p2 | | | |f1 | | 0.4186 | | 0 |
11
  | - p3 | | | |f1 | | 0.3979 | | 0 |
 
1
  hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 0, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.3183 | |0 |
5
  | - p1 | | | |f1 | | 0.3344 | | 0 |
6
  | - p2 | | | |f1 | | 0.2863 | | 0 |
7
  | - p3 | | | |f1 | | 0.3344 | | 0 |
8
+ | - RE | | | |f1 | | 0.4048 | |0 |
9
  | - p1 | | | |f1 | | 0.3979 | | 0 |
10
  | - p2 | | | |f1 | | 0.4186 | | 0 |
11
  | - p3 | | | |f1 | | 0.3979 | | 0 |
csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__sl__10shot.txt CHANGED
@@ -1,10 +1,10 @@
1
  hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
- | - ner | | | |f1 | | 0.6373 | |0 |
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 |
 
1
  hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 10, batch_size: 1
2
  |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
3
  |-------|-------|------|------|------|----|------|---|------|
4
+ | - NER | | | |f1 | | 0.6373 | |0 |
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 |