diff --git a/Gen_llm_eval_output.py b/Gen_llm_eval_output.py index 9b430b7fe2ba0e890000b87db82549f049a4b270..7c75d62b2c324c2cd142ff728af991ef9cdab188 100644 --- a/Gen_llm_eval_output.py +++ b/Gen_llm_eval_output.py @@ -81,7 +81,7 @@ def render_group_table(g: pd.DataFrame, model: str, language: str, configuration for task, df_task in g.groupby("task", sort=False): f1s = df_task["f1"].to_numpy(dtype=float) task_mean = float(np.mean(f1s)) if f1s.size else float("nan") - lines.append(f"| - {task} | | | |f1 | | {format_float(task_mean)} | |0 |") + lines.append(f"| - {task.upper()} | | | |f1 | | {format_float(task_mean)} | |0 |") # Prompt-level rows, sorted by prompt number if available df_task = df_task.copy() diff --git a/csv_files/outputs/.ipynb_checkpoints/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__en__0shot-checkpoint.txt b/csv_files/outputs/.ipynb_checkpoints/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__en__0shot-checkpoint.txt new file mode 100644 index 0000000000000000000000000000000000000000..37a0a0b3fcec4413d915fb8b17302fe6c93286c4 --- /dev/null +++ b/csv_files/outputs/.ipynb_checkpoints/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__en__0shot-checkpoint.txt @@ -0,0 +1,11 @@ +hf (pretrained=deepseek-ai/DeepSeek-R1-Distill-Qwen-32B ), num_fewshot: 0, batch_size: 1 +|Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| +|-------|-------|------|------|------|----|------|---|------| +| - NER | | | |f1 | | 0.2877 | |0 | +| - p1 | | | |f1 | | 0.1963 | | 0 | +| - p2 | | | |f1 | | 0.3459 | | 0 | +| - p3 | | | |f1 | | 0.3208 | | 0 | +| - RE | | | |f1 | | 0.4430 | |0 | +| - p1 | | | |f1 | | 0.4487 | | 0 | +| - p2 | | | |f1 | | 0.4492 | | 0 | +| - p3 | | | |f1 | | 0.4311 | | 0 | diff --git a/csv_files/outputs/Henrychur__MMed-Llama-3-8B__en__0shot.txt b/csv_files/outputs/Henrychur__MMed-Llama-3-8B__en__0shot.txt index e05928730646b5bbe21f9238db4c5f0a0d80aeb1..adb6649f69212f89096131405d496954e948d037 100644 --- a/csv_files/outputs/Henrychur__MMed-Llama-3-8B__en__0shot.txt +++ b/csv_files/outputs/Henrychur__MMed-Llama-3-8B__en__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.0918 | |0 | +| - NER | | | |f1 | | 0.0918 | |0 | | - p1 | | | |f1 | | 0.0629 | | 0 | | - p2 | | | |f1 | | 0.1041 | | 0 | | - p3 | | | |f1 | | 0.1083 | | 0 | -| - re | | | |f1 | | 0.2604 | |0 | +| - RE | | | |f1 | | 0.2604 | |0 | | - p1 | | | |f1 | | 0.1287 | | 0 | | - p2 | | | |f1 | | 0.3394 | | 0 | | - p3 | | | |f1 | | 0.3131 | | 0 | diff --git a/csv_files/outputs/Henrychur__MMed-Llama-3-8B__en__10shot.txt b/csv_files/outputs/Henrychur__MMed-Llama-3-8B__en__10shot.txt index 8524c34316a59100e3a1b7fe29f11627397324e2..61582a2a92516a6c5547648b28d3f1e909d0067d 100644 --- a/csv_files/outputs/Henrychur__MMed-Llama-3-8B__en__10shot.txt +++ b/csv_files/outputs/Henrychur__MMed-Llama-3-8B__en__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.2142 | |0 | +| - NER | | | |f1 | | 0.2142 | |0 | | - p1 | | | |f1 | | 0.2189 | | 0 | | - p2 | | | |f1 | | 0.2243 | | 0 | | - p3 | | | |f1 | | 0.1994 | | 0 | -| - re | | | |f1 | | 0.1429 | |0 | +| - RE | | | |f1 | | 0.1429 | |0 | | - p1 | | | |f1 | | 0.1189 | | 0 | | - p2 | | | |f1 | | 0.1668 | | 0 | diff --git a/csv_files/outputs/Henrychur__MMed-Llama-3-8B__gr__0shot.txt b/csv_files/outputs/Henrychur__MMed-Llama-3-8B__gr__0shot.txt index 060db5c37f5e74766dafb07e5bd52433091e0e1f..256806ae1aae91613bb15e7f61973bb2c3d373e9 100644 --- a/csv_files/outputs/Henrychur__MMed-Llama-3-8B__gr__0shot.txt +++ b/csv_files/outputs/Henrychur__MMed-Llama-3-8B__gr__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.0611 | |0 | +| - NER | | | |f1 | | 0.0611 | |0 | | - p1 | | | |f1 | | 0.0620 | | 0 | | - p2 | | | |f1 | | 0.0592 | | 0 | | - p3 | | | |f1 | | 0.0620 | | 0 | -| - re | | | |f1 | | 0.0863 | |0 | +| - RE | | | |f1 | | 0.0863 | |0 | | - p1 | | | |f1 | | 0.1017 | | 0 | | - p2 | | | |f1 | | 0.0506 | | 0 | | - p3 | | | |f1 | | 0.1065 | | 0 | diff --git a/csv_files/outputs/Henrychur__MMed-Llama-3-8B__gr__10shot.txt b/csv_files/outputs/Henrychur__MMed-Llama-3-8B__gr__10shot.txt index 11f686a3d7c0dcd6950a0fb8f89dd76050e16c83..29ae4e0eed887a125d86ca5fca2d2fd3146689cf 100644 --- a/csv_files/outputs/Henrychur__MMed-Llama-3-8B__gr__10shot.txt +++ b/csv_files/outputs/Henrychur__MMed-Llama-3-8B__gr__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.1474 | |0 | +| - NER | | | |f1 | | 0.1474 | |0 | | - p1 | | | |f1 | | 0.1667 | | 0 | | - p2 | | | |f1 | | 0.1089 | | 0 | | - p3 | | | |f1 | | 0.1667 | | 0 | -| - re | | | |f1 | | 0.0937 | |0 | +| - RE | | | |f1 | | 0.0937 | |0 | | - p1 | | | |f1 | | 0.0821 | | 0 | | - p2 | | | |f1 | | 0.1053 | | 0 | diff --git a/csv_files/outputs/Henrychur__MMed-Llama-3-8B__it__0shot.txt b/csv_files/outputs/Henrychur__MMed-Llama-3-8B__it__0shot.txt index 79142bf6a355f4c1b35bed6c13b7f881099a0dc1..de76936f997964ba608d49c32bded3be64711fed 100644 --- a/csv_files/outputs/Henrychur__MMed-Llama-3-8B__it__0shot.txt +++ b/csv_files/outputs/Henrychur__MMed-Llama-3-8B__it__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.0416 | |0 | +| - NER | | | |f1 | | 0.0416 | |0 | | - p1 | | | |f1 | | 0.0435 | | 0 | | - p2 | | | |f1 | | 0.0429 | | 0 | | - p3 | | | |f1 | | 0.0384 | | 0 | -| - re | | | |f1 | | 0.1413 | |0 | +| - RE | | | |f1 | | 0.1413 | |0 | | - p1 | | | |f1 | | 0.0672 | | 0 | | - p2 | | | |f1 | | 0.2266 | | 0 | | - p3 | | | |f1 | | 0.1300 | | 0 | diff --git a/csv_files/outputs/Henrychur__MMed-Llama-3-8B__it__10shot.txt b/csv_files/outputs/Henrychur__MMed-Llama-3-8B__it__10shot.txt index a6f2990ce3c55074691eb8bd620702df9f4473b4..ae779703662ed0449b631e8a70a4b116bcc8b8d1 100644 --- a/csv_files/outputs/Henrychur__MMed-Llama-3-8B__it__10shot.txt +++ b/csv_files/outputs/Henrychur__MMed-Llama-3-8B__it__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.3753 | |0 | +| - NER | | | |f1 | | 0.3753 | |0 | | - p1 | | | |f1 | | 0.3299 | | 0 | | - p2 | | | |f1 | | 0.4023 | | 0 | | - p3 | | | |f1 | | 0.3938 | | 0 | -| - re | | | |f1 | | 0.1102 | |0 | +| - RE | | | |f1 | | 0.1102 | |0 | | - p1 | | | |f1 | | 0.0977 | | 0 | | - p2 | | | |f1 | | 0.1226 | | 0 | diff --git a/csv_files/outputs/Henrychur__MMed-Llama-3-8B__pl__0shot.txt b/csv_files/outputs/Henrychur__MMed-Llama-3-8B__pl__0shot.txt index f77ba6027c7c615df2d261d1d686f39a2c89c34d..922dce80469337edc75e7835aa6a600369523091 100644 --- a/csv_files/outputs/Henrychur__MMed-Llama-3-8B__pl__0shot.txt +++ b/csv_files/outputs/Henrychur__MMed-Llama-3-8B__pl__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.0379 | |0 | +| - NER | | | |f1 | | 0.0379 | |0 | | - p1 | | | |f1 | | 0.0379 | | 0 | | - p2 | | | |f1 | | 0.0378 | | 0 | | - p3 | | | |f1 | | 0.0379 | | 0 | -| - re | | | |f1 | | 0.0891 | |0 | +| - RE | | | |f1 | | 0.0891 | |0 | | - p1 | | | |f1 | | 0.0602 | | 0 | | - p2 | | | |f1 | | 0.1293 | | 0 | | - p3 | | | |f1 | | 0.0778 | | 0 | diff --git a/csv_files/outputs/Henrychur__MMed-Llama-3-8B__pl__10shot.txt b/csv_files/outputs/Henrychur__MMed-Llama-3-8B__pl__10shot.txt index f0c3def3445572250475395490871abca32b311e..acd4a7476db8ef3ad2bf489c194693722148311b 100644 --- a/csv_files/outputs/Henrychur__MMed-Llama-3-8B__pl__10shot.txt +++ b/csv_files/outputs/Henrychur__MMed-Llama-3-8B__pl__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.3966 | |0 | +| - NER | | | |f1 | | 0.3966 | |0 | | - p1 | | | |f1 | | 0.3992 | | 0 | | - p2 | | | |f1 | | 0.3916 | | 0 | | - p3 | | | |f1 | | 0.3992 | | 0 | -| - re | | | |f1 | | 0.1026 | |0 | +| - RE | | | |f1 | | 0.1026 | |0 | | - p1 | | | |f1 | | 0.0998 | | 0 | | - p2 | | | |f1 | | 0.1055 | | 0 | diff --git a/csv_files/outputs/Henrychur__MMed-Llama-3-8B__sk__0shot.txt b/csv_files/outputs/Henrychur__MMed-Llama-3-8B__sk__0shot.txt index 77e42bb661f69d4f83bdff576a0a1fd1ce9f6b66..8a25091bbb80e0a2681548322565c52cb0858b07 100644 --- a/csv_files/outputs/Henrychur__MMed-Llama-3-8B__sk__0shot.txt +++ b/csv_files/outputs/Henrychur__MMed-Llama-3-8B__sk__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.0385 | |0 | +| - NER | | | |f1 | | 0.0385 | |0 | | - p1 | | | |f1 | | 0.0387 | | 0 | | - p2 | | | |f1 | | 0.0380 | | 0 | | - p3 | | | |f1 | | 0.0387 | | 0 | -| - re | | | |f1 | | 0.0174 | |0 | +| - RE | | | |f1 | | 0.0174 | |0 | | - p1 | | | |f1 | | 0.0121 | | 0 | | - p2 | | | |f1 | | 0.0280 | | 0 | | - p3 | | | |f1 | | 0.0121 | | 0 | diff --git a/csv_files/outputs/Henrychur__MMed-Llama-3-8B__sk__10shot.txt b/csv_files/outputs/Henrychur__MMed-Llama-3-8B__sk__10shot.txt index 15a0ace9ef2a7ac547c13784312b2d11cbb1972c..9b45fb0567534355d82b8b2d43856a0bfb581c56 100644 --- a/csv_files/outputs/Henrychur__MMed-Llama-3-8B__sk__10shot.txt +++ b/csv_files/outputs/Henrychur__MMed-Llama-3-8B__sk__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.3507 | |0 | +| - NER | | | |f1 | | 0.3507 | |0 | | - p1 | | | |f1 | | 0.3444 | | 0 | | - p2 | | | |f1 | | 0.3632 | | 0 | | - p3 | | | |f1 | | 0.3444 | | 0 | -| - re | | | |f1 | | 0.0889 | |0 | +| - RE | | | |f1 | | 0.0889 | |0 | | - p1 | | | |f1 | | 0.0734 | | 0 | | - p2 | | | |f1 | | 0.1045 | | 0 | diff --git a/csv_files/outputs/Henrychur__MMed-Llama-3-8B__sl__0shot.txt b/csv_files/outputs/Henrychur__MMed-Llama-3-8B__sl__0shot.txt index 45005591fb2829f67890b8537514d09a7dc4dbd9..af66f9c26430a2440fce61f08cdf1c00204b2cf0 100644 --- a/csv_files/outputs/Henrychur__MMed-Llama-3-8B__sl__0shot.txt +++ b/csv_files/outputs/Henrychur__MMed-Llama-3-8B__sl__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.0438 | |0 | +| - NER | | | |f1 | | 0.0438 | |0 | | - p1 | | | |f1 | | 0.0429 | | 0 | | - p2 | | | |f1 | | 0.0456 | | 0 | | - p3 | | | |f1 | | 0.0429 | | 0 | -| - re | | | |f1 | | 0.1278 | |0 | +| - RE | | | |f1 | | 0.1278 | |0 | | - p1 | | | |f1 | | 0.0967 | | 0 | | - p2 | | | |f1 | | 0.1900 | | 0 | | - p3 | | | |f1 | | 0.0967 | | 0 | diff --git a/csv_files/outputs/Henrychur__MMed-Llama-3-8B__sl__10shot.txt b/csv_files/outputs/Henrychur__MMed-Llama-3-8B__sl__10shot.txt index 5f374b71d20e644f0671d320fec3ebab424a9b3c..7b07a94f1ebd78d5e08c541a05bfdc7ed1019b8f 100644 --- a/csv_files/outputs/Henrychur__MMed-Llama-3-8B__sl__10shot.txt +++ b/csv_files/outputs/Henrychur__MMed-Llama-3-8B__sl__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=Henrychur/MMed-Llama-3-8B ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.3720 | |0 | +| - NER | | | |f1 | | 0.3720 | |0 | | - p1 | | | |f1 | | 0.3558 | | 0 | | - p2 | | | |f1 | | 0.4045 | | 0 | | - p3 | | | |f1 | | 0.3558 | | 0 | -| - re | | | |f1 | | 0.0784 | |0 | +| - RE | | | |f1 | | 0.0784 | |0 | | - p1 | | | |f1 | | 0.0787 | | 0 | | - p2 | | | |f1 | | 0.0781 | | 0 | diff --git a/csv_files/outputs/HiTZ__Medical-mT5-large__en__0shot.txt b/csv_files/outputs/HiTZ__Medical-mT5-large__en__0shot.txt index 94e2aee8ae1f1577bf03eb67d3b30e97a960a4cf..6f2276bf179a07b2a459292322afb0dd5fbc5788 100644 --- a/csv_files/outputs/HiTZ__Medical-mT5-large__en__0shot.txt +++ b/csv_files/outputs/HiTZ__Medical-mT5-large__en__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.0578 | |0 | +| - NER | | | |f1 | | 0.0578 | |0 | | - p1 | | | |f1 | | 0.0940 | | 0 | | - p2 | | | |f1 | | 0.0331 | | 0 | | - p3 | | | |f1 | | 0.0464 | | 0 | -| - re | | | |f1 | | 0.0000 | |0 | +| - RE | | | |f1 | | 0.0000 | |0 | | - p1 | | | |f1 | | 0.0000 | | 0 | | - p2 | | | |f1 | | 0.0000 | | 0 | | - p3 | | | |f1 | | 0.0000 | | 0 | diff --git a/csv_files/outputs/HiTZ__Medical-mT5-large__en__10shot.txt b/csv_files/outputs/HiTZ__Medical-mT5-large__en__10shot.txt index 4f9360b72c56f3110b77d1b06a158c3c6ecca91c..0643402ba5ae01bc4e4c6bd7daf9feef2b3db365 100644 --- a/csv_files/outputs/HiTZ__Medical-mT5-large__en__10shot.txt +++ b/csv_files/outputs/HiTZ__Medical-mT5-large__en__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.1317 | |0 | +| - NER | | | |f1 | | 0.1317 | |0 | | - p1 | | | |f1 | | 0.1215 | | 0 | | - p2 | | | |f1 | | 0.1415 | | 0 | | - p3 | | | |f1 | | 0.1322 | | 0 | -| - re | | | |f1 | | 0.0022 | |0 | +| - RE | | | |f1 | | 0.0022 | |0 | | - p1 | | | |f1 | | 0.0028 | | 0 | | - p2 | | | |f1 | | 0.0016 | | 0 | diff --git a/csv_files/outputs/HiTZ__Medical-mT5-large__gr__0shot.txt b/csv_files/outputs/HiTZ__Medical-mT5-large__gr__0shot.txt index 1f9afed0d2736add07bd96741b281b9502a70539..4cc7d4a784cb754ed058341765da74fe59e4950e 100644 --- a/csv_files/outputs/HiTZ__Medical-mT5-large__gr__0shot.txt +++ b/csv_files/outputs/HiTZ__Medical-mT5-large__gr__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.0769 | |0 | +| - NER | | | |f1 | | 0.0769 | |0 | | - p1 | | | |f1 | | 0.0859 | | 0 | | - p2 | | | |f1 | | 0.0591 | | 0 | | - p3 | | | |f1 | | 0.0859 | | 0 | -| - re | | | |f1 | | 0.0000 | |0 | +| - RE | | | |f1 | | 0.0000 | |0 | | - p1 | | | |f1 | | 0.0000 | | 0 | | - p2 | | | |f1 | | 0.0000 | | 0 | | - p3 | | | |f1 | | 0.0000 | | 0 | diff --git a/csv_files/outputs/HiTZ__Medical-mT5-large__gr__10shot.txt b/csv_files/outputs/HiTZ__Medical-mT5-large__gr__10shot.txt index 2e844447cbaeb4035cc3afc6dbb0324986c8d42f..ff8fefd9156034f31a413c0ab9054739db228357 100644 --- a/csv_files/outputs/HiTZ__Medical-mT5-large__gr__10shot.txt +++ b/csv_files/outputs/HiTZ__Medical-mT5-large__gr__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.1448 | |0 | +| - NER | | | |f1 | | 0.1448 | |0 | | - p1 | | | |f1 | | 0.1455 | | 0 | | - p2 | | | |f1 | | 0.1434 | | 0 | | - p3 | | | |f1 | | 0.1455 | | 0 | -| - re | | | |f1 | | 0.0015 | |0 | +| - RE | | | |f1 | | 0.0015 | |0 | | - p1 | | | |f1 | | 0.0024 | | 0 | | - p2 | | | |f1 | | 0.0007 | | 0 | diff --git a/csv_files/outputs/HiTZ__Medical-mT5-large__it__0shot.txt b/csv_files/outputs/HiTZ__Medical-mT5-large__it__0shot.txt index 822472aab17e5a54c699eb0299168e25ce68eff7..89aa974a3e785f05de8765a3214c2c1b54683fa4 100644 --- a/csv_files/outputs/HiTZ__Medical-mT5-large__it__0shot.txt +++ b/csv_files/outputs/HiTZ__Medical-mT5-large__it__0shot.txt @@ -1,10 +1,10 @@ hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.0812 | |0 | +| - NER | | | |f1 | | 0.0812 | |0 | | - p1 | | | |f1 | | 0.0770 | | 0 | | - p2 | | | |f1 | | 0.0920 | | 0 | | - p3 | | | |f1 | | 0.0747 | | 0 | -| - re | | | |f1 | | 0.0000 | |0 | +| - RE | | | |f1 | | 0.0000 | |0 | | - p2 | | | |f1 | | 0.0000 | | 0 | | - p3 | | | |f1 | | 0.0000 | | 0 | diff --git a/csv_files/outputs/HiTZ__Medical-mT5-large__it__10shot.txt b/csv_files/outputs/HiTZ__Medical-mT5-large__it__10shot.txt index 1af9a4668db160d1341a685de4bbe1e2ba89c092..b5cbc685ecfb0eb297165a388593a27f47e6ca5a 100644 --- a/csv_files/outputs/HiTZ__Medical-mT5-large__it__10shot.txt +++ b/csv_files/outputs/HiTZ__Medical-mT5-large__it__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.1694 | |0 | +| - NER | | | |f1 | | 0.1694 | |0 | | - p1 | | | |f1 | | 0.1616 | | 0 | | - p2 | | | |f1 | | 0.1774 | | 0 | | - p3 | | | |f1 | | 0.1690 | | 0 | -| - re | | | |f1 | | 0.0050 | |0 | +| - RE | | | |f1 | | 0.0050 | |0 | | - p1 | | | |f1 | | 0.0035 | | 0 | | - p2 | | | |f1 | | 0.0064 | | 0 | diff --git a/csv_files/outputs/HiTZ__Medical-mT5-large__pl__0shot.txt b/csv_files/outputs/HiTZ__Medical-mT5-large__pl__0shot.txt index 372f91a2ce5382b434fbeee549424ceb5717daf6..b3febb68ea3e21f9230cb485500075ba859f318f 100644 --- a/csv_files/outputs/HiTZ__Medical-mT5-large__pl__0shot.txt +++ b/csv_files/outputs/HiTZ__Medical-mT5-large__pl__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.0308 | |0 | +| - NER | | | |f1 | | 0.0308 | |0 | | - p1 | | | |f1 | | 0.0244 | | 0 | | - p2 | | | |f1 | | 0.0436 | | 0 | | - p3 | | | |f1 | | 0.0244 | | 0 | -| - re | | | |f1 | | 0.0000 | |0 | +| - RE | | | |f1 | | 0.0000 | |0 | | - p1 | | | |f1 | | 0.0000 | | 0 | | - p2 | | | |f1 | | 0.0000 | | 0 | | - p3 | | | |f1 | | 0.0000 | | 0 | diff --git a/csv_files/outputs/HiTZ__Medical-mT5-large__pl__10shot.txt b/csv_files/outputs/HiTZ__Medical-mT5-large__pl__10shot.txt index 1d6a4ccbeef1fef677e1a9104fd7232605eb8113..75efbbc4704662e68e763f29da40673f2cc3de53 100644 --- a/csv_files/outputs/HiTZ__Medical-mT5-large__pl__10shot.txt +++ b/csv_files/outputs/HiTZ__Medical-mT5-large__pl__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.1516 | |0 | +| - NER | | | |f1 | | 0.1516 | |0 | | - p1 | | | |f1 | | 0.1500 | | 0 | | - p2 | | | |f1 | | 0.1548 | | 0 | | - p3 | | | |f1 | | 0.1500 | | 0 | -| - re | | | |f1 | | 0.0031 | |0 | +| - RE | | | |f1 | | 0.0031 | |0 | | - p1 | | | |f1 | | 0.0040 | | 0 | | - p2 | | | |f1 | | 0.0023 | | 0 | diff --git a/csv_files/outputs/HiTZ__Medical-mT5-large__sk__0shot.txt b/csv_files/outputs/HiTZ__Medical-mT5-large__sk__0shot.txt index 6d8451e3fdfc0093ad807d5613fddf15e4d63446..75cf3c4ce337fe7f13221bf8b230f9c267ae3639 100644 --- a/csv_files/outputs/HiTZ__Medical-mT5-large__sk__0shot.txt +++ b/csv_files/outputs/HiTZ__Medical-mT5-large__sk__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.0712 | |0 | +| - NER | | | |f1 | | 0.0712 | |0 | | - p1 | | | |f1 | | 0.0880 | | 0 | | - p2 | | | |f1 | | 0.0375 | | 0 | | - p3 | | | |f1 | | 0.0880 | | 0 | -| - re | | | |f1 | | 0.0000 | |0 | +| - RE | | | |f1 | | 0.0000 | |0 | | - p1 | | | |f1 | | 0.0000 | | 0 | | - p2 | | | |f1 | | 0.0000 | | 0 | | - p3 | | | |f1 | | 0.0000 | | 0 | diff --git a/csv_files/outputs/HiTZ__Medical-mT5-large__sk__10shot.txt b/csv_files/outputs/HiTZ__Medical-mT5-large__sk__10shot.txt index 2b69b27b4369aa5ddf3032f60ca53684cd2ce4f4..13f060a2b8a3074c4ca8104730c886f8ea6febbd 100644 --- a/csv_files/outputs/HiTZ__Medical-mT5-large__sk__10shot.txt +++ b/csv_files/outputs/HiTZ__Medical-mT5-large__sk__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.1444 | |0 | +| - NER | | | |f1 | | 0.1444 | |0 | | - p1 | | | |f1 | | 0.1485 | | 0 | | - p2 | | | |f1 | | 0.1360 | | 0 | | - p3 | | | |f1 | | 0.1485 | | 0 | -| - re | | | |f1 | | 0.0031 | |0 | +| - RE | | | |f1 | | 0.0031 | |0 | | - p1 | | | |f1 | | 0.0038 | | 0 | | - p2 | | | |f1 | | 0.0024 | | 0 | diff --git a/csv_files/outputs/HiTZ__Medical-mT5-large__sl__0shot.txt b/csv_files/outputs/HiTZ__Medical-mT5-large__sl__0shot.txt index 6279ec191b39a30feefe58b94e3b6aecdb33d129..8811248dde3d8e1e5d3e5bd0c4d11888b8adad09 100644 --- a/csv_files/outputs/HiTZ__Medical-mT5-large__sl__0shot.txt +++ b/csv_files/outputs/HiTZ__Medical-mT5-large__sl__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.0711 | |0 | +| - NER | | | |f1 | | 0.0711 | |0 | | - p1 | | | |f1 | | 0.0777 | | 0 | | - p2 | | | |f1 | | 0.0579 | | 0 | | - p3 | | | |f1 | | 0.0777 | | 0 | -| - re | | | |f1 | | 0.0000 | |0 | +| - RE | | | |f1 | | 0.0000 | |0 | | - p1 | | | |f1 | | 0.0000 | | 0 | | - p2 | | | |f1 | | 0.0000 | | 0 | | - p3 | | | |f1 | | 0.0000 | | 0 | diff --git a/csv_files/outputs/HiTZ__Medical-mT5-large__sl__10shot.txt b/csv_files/outputs/HiTZ__Medical-mT5-large__sl__10shot.txt index abeb73b685970065381ae98fa4cb8ba945ebb468..48b63bcc55dff5d33703118e50cac12638711b11 100644 --- a/csv_files/outputs/HiTZ__Medical-mT5-large__sl__10shot.txt +++ b/csv_files/outputs/HiTZ__Medical-mT5-large__sl__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=HiTZ/Medical-mT5-large ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.1422 | |0 | +| - NER | | | |f1 | | 0.1422 | |0 | | - p1 | | | |f1 | | 0.1470 | | 0 | | - p2 | | | |f1 | | 0.1325 | | 0 | | - p3 | | | |f1 | | 0.1470 | | 0 | -| - re | | | |f1 | | 0.0073 | |0 | +| - RE | | | |f1 | | 0.0073 | |0 | | - p1 | | | |f1 | | 0.0073 | | 0 | | - p2 | | | |f1 | | 0.0074 | | 0 | diff --git a/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__en__0shot.txt b/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__en__0shot.txt index 8ea6919fab287107f11b133a6f4f393a8742e6e5..1e6243a974bbae1a9614d27b4d2e11522417cb4d 100644 --- a/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__en__0shot.txt +++ b/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__en__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.2500 | |0 | +| - NER | | | |f1 | | 0.2500 | |0 | | - p1 | | | |f1 | | 0.3425 | | 0 | | - p2 | | | |f1 | | 0.1181 | | 0 | | - p3 | | | |f1 | | 0.2893 | | 0 | -| - re | | | |f1 | | 0.4075 | |0 | +| - RE | | | |f1 | | 0.4075 | |0 | | - p1 | | | |f1 | | 0.4135 | | 0 | | - p2 | | | |f1 | | 0.3917 | | 0 | | - p3 | | | |f1 | | 0.4172 | | 0 | diff --git a/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__en__10shot.txt b/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__en__10shot.txt index 8271ede54c280963d5edbe250ee11c0bb7b431fb..2204043f611ed143de085c6daebb131f2cf429a0 100644 --- a/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__en__10shot.txt +++ b/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__en__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.5993 | |0 | +| - NER | | | |f1 | | 0.5993 | |0 | | - p1 | | | |f1 | | 0.6091 | | 0 | | - p2 | | | |f1 | | 0.5646 | | 0 | | - p3 | | | |f1 | | 0.6243 | | 0 | -| - re | | | |f1 | | 0.6179 | |0 | +| - RE | | | |f1 | | 0.6179 | |0 | | - p1 | | | |f1 | | 0.6332 | | 0 | | - p2 | | | |f1 | | 0.6025 | | 0 | diff --git a/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__gr__0shot.txt b/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__gr__0shot.txt index 3a72d0a6eb08700f9441ae748027f10d73015687..32e68359dde026f73f4bdc753c7293e1d097dd76 100644 --- a/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__gr__0shot.txt +++ b/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__gr__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.1290 | |0 | +| - NER | | | |f1 | | 0.1290 | |0 | | - p1 | | | |f1 | | 0.1339 | | 0 | | - p2 | | | |f1 | | 0.1191 | | 0 | | - p3 | | | |f1 | | 0.1339 | | 0 | -| - re | | | |f1 | | 0.3957 | |0 | +| - RE | | | |f1 | | 0.3957 | |0 | | - p1 | | | |f1 | | 0.3796 | | 0 | | - p2 | | | |f1 | | 0.4266 | | 0 | | - p3 | | | |f1 | | 0.3810 | | 0 | diff --git a/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__gr__10shot.txt b/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__gr__10shot.txt index ce16010a359dbdd63efc64adc978c235ecc87764..42934e85489839621e98169698fe948e952c8c6c 100644 --- a/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__gr__10shot.txt +++ b/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__gr__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.6028 | |0 | +| - NER | | | |f1 | | 0.6028 | |0 | | - p1 | | | |f1 | | 0.6119 | | 0 | | - p2 | | | |f1 | | 0.5847 | | 0 | | - p3 | | | |f1 | | 0.6119 | | 0 | -| - re | | | |f1 | | 0.5993 | |0 | +| - RE | | | |f1 | | 0.5993 | |0 | | - p1 | | | |f1 | | 0.5962 | | 0 | | - p2 | | | |f1 | | 0.6024 | | 0 | diff --git a/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__it__0shot.txt b/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__it__0shot.txt index 0564d5bfe6a8a54aec02c9377516537b66eff33e..273a22dfa278f3ac9935c7789f1efc8bc0c51068 100644 --- a/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__it__0shot.txt +++ b/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__it__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.2137 | |0 | +| - NER | | | |f1 | | 0.2137 | |0 | | - p1 | | | |f1 | | 0.2467 | | 0 | | - p2 | | | |f1 | | 0.1709 | | 0 | | - p3 | | | |f1 | | 0.2234 | | 0 | -| - re | | | |f1 | | 0.4016 | |0 | +| - RE | | | |f1 | | 0.4016 | |0 | | - p1 | | | |f1 | | 0.4173 | | 0 | | - p2 | | | |f1 | | 0.3770 | | 0 | | - p3 | | | |f1 | | 0.4106 | | 0 | diff --git a/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__it__10shot.txt b/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__it__10shot.txt index 1ee4c0b5a7e89753a9acf1141ebf450a99b7c92b..8d663f2e51718e681b0e5a34673c3eca6472d5fa 100644 --- a/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__it__10shot.txt +++ b/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__it__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.6569 | |0 | +| - NER | | | |f1 | | 0.6569 | |0 | | - p1 | | | |f1 | | 0.6719 | | 0 | | - p2 | | | |f1 | | 0.6327 | | 0 | | - p3 | | | |f1 | | 0.6661 | | 0 | -| - re | | | |f1 | | 0.5882 | |0 | +| - RE | | | |f1 | | 0.5882 | |0 | | - p1 | | | |f1 | | 0.5767 | | 0 | | - p2 | | | |f1 | | 0.5998 | | 0 | diff --git a/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__pl__0shot.txt b/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__pl__0shot.txt index ae1fccd474c06d066ad5f6113cf27772e8cf3e7d..2bbaa4e441dac6b8c9ed99f717bd896a34a45e3d 100644 --- a/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__pl__0shot.txt +++ b/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__pl__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.0586 | |0 | +| - NER | | | |f1 | | 0.0586 | |0 | | - p1 | | | |f1 | | 0.0697 | | 0 | | - p2 | | | |f1 | | 0.0364 | | 0 | | - p3 | | | |f1 | | 0.0697 | | 0 | -| - re | | | |f1 | | 0.4022 | |0 | +| - RE | | | |f1 | | 0.4022 | |0 | | - p1 | | | |f1 | | 0.3803 | | 0 | | - p2 | | | |f1 | | 0.4464 | | 0 | | - p3 | | | |f1 | | 0.3800 | | 0 | diff --git a/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__pl__10shot.txt b/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__pl__10shot.txt index 7d08d53f7f8da84ee76b1ccef550be7d0137bacc..d66d9aea480496a8e2a891abce6603d76f5260a4 100644 --- a/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__pl__10shot.txt +++ b/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__pl__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.6092 | |0 | +| - NER | | | |f1 | | 0.6092 | |0 | | - p1 | | | |f1 | | 0.6226 | | 0 | | - p2 | | | |f1 | | 0.5824 | | 0 | | - p3 | | | |f1 | | 0.6226 | | 0 | -| - re | | | |f1 | | 0.5729 | |0 | +| - RE | | | |f1 | | 0.5729 | |0 | | - p1 | | | |f1 | | 0.5991 | | 0 | | - p2 | | | |f1 | | 0.5466 | | 0 | diff --git a/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__sk__0shot.txt b/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__sk__0shot.txt index a4e8edce7f1cc06218baf35e09e089db7a3aac7c..8660df7e3f0f119e44cf5a67e7a942f913b8aa4d 100644 --- a/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__sk__0shot.txt +++ b/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__sk__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.0955 | |0 | +| - NER | | | |f1 | | 0.0955 | |0 | | - p1 | | | |f1 | | 0.1220 | | 0 | | - p2 | | | |f1 | | 0.0426 | | 0 | | - p3 | | | |f1 | | 0.1220 | | 0 | -| - re | | | |f1 | | 0.4116 | |0 | +| - RE | | | |f1 | | 0.4116 | |0 | | - p1 | | | |f1 | | 0.4027 | | 0 | | - p2 | | | |f1 | | 0.4294 | | 0 | | - p3 | | | |f1 | | 0.4027 | | 0 | diff --git a/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__sk__10shot.txt b/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__sk__10shot.txt index 55c60843461a0fb906dded1f9d91cbd69d051d89..d53ea8895c02919662864752ad71582c884d2238 100644 --- a/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__sk__10shot.txt +++ b/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__sk__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.6419 | |0 | +| - NER | | | |f1 | | 0.6419 | |0 | | - p1 | | | |f1 | | 0.6386 | | 0 | | - p2 | | | |f1 | | 0.6486 | | 0 | | - p3 | | | |f1 | | 0.6386 | | 0 | -| - re | | | |f1 | | 0.5869 | |0 | +| - RE | | | |f1 | | 0.5869 | |0 | | - p1 | | | |f1 | | 0.5894 | | 0 | | - p2 | | | |f1 | | 0.5845 | | 0 | diff --git a/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__sl__0shot.txt b/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__sl__0shot.txt index 91942eaddebd802b373ccbcc131ea59cecb06f2a..52a254555d051acdd5ed2169b161e4db6559e7f6 100644 --- a/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__sl__0shot.txt +++ b/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__sl__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.3398 | |0 | +| - NER | | | |f1 | | 0.3398 | |0 | | - p1 | | | |f1 | | 0.3910 | | 0 | | - p2 | | | |f1 | | 0.2375 | | 0 | | - p3 | | | |f1 | | 0.3910 | | 0 | -| - re | | | |f1 | | 0.3777 | |0 | +| - RE | | | |f1 | | 0.3777 | |0 | | - p1 | | | |f1 | | 0.3775 | | 0 | | - p2 | | | |f1 | | 0.3783 | | 0 | | - p3 | | | |f1 | | 0.3775 | | 0 | diff --git a/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__sl__10shot.txt b/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__sl__10shot.txt index d29c5ef26ed259e4a5c4f37fe042a47532bf0bca..958c2adc849a31b48cc656569846de4ca06227da 100644 --- a/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__sl__10shot.txt +++ b/csv_files/outputs/Qwen__Qwen2.5-14B-Instruct-1M__sl__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=Qwen/Qwen2.5-14B-Instruct-1M ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.6371 | |0 | +| - NER | | | |f1 | | 0.6371 | |0 | | - p1 | | | |f1 | | 0.6467 | | 0 | | - p2 | | | |f1 | | 0.6178 | | 0 | | - p3 | | | |f1 | | 0.6467 | | 0 | -| - re | | | |f1 | | 0.5865 | |0 | +| - RE | | | |f1 | | 0.5865 | |0 | | - p1 | | | |f1 | | 0.5949 | | 0 | | - p2 | | | |f1 | | 0.5782 | | 0 | diff --git a/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__en__0shot.txt b/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__en__0shot.txt index 67cd229daf9590c732ecee234ea4ff29e1fb915a..6d46997ae1107c126bb8219af5d19f4b69f60a6d 100644 --- a/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__en__0shot.txt +++ b/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__en__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.3279 | |0 | +| - NER | | | |f1 | | 0.3279 | |0 | | - p1 | | | |f1 | | 0.3804 | | 0 | | - p2 | | | |f1 | | 0.3068 | | 0 | | - p3 | | | |f1 | | 0.2964 | | 0 | -| - re | | | |f1 | | 0.4658 | |0 | +| - RE | | | |f1 | | 0.4658 | |0 | | - p1 | | | |f1 | | 0.4734 | | 0 | | - p2 | | | |f1 | | 0.4649 | | 0 | | - p3 | | | |f1 | | 0.4591 | | 0 | diff --git a/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__en__10shot.txt b/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__en__10shot.txt index 98c263a0ce8135387f875e16815b08f66bc70bc9..b001d05a9e26c936952ee1013dcf2a2443277641 100644 --- a/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__en__10shot.txt +++ b/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__en__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.5895 | |0 | +| - NER | | | |f1 | | 0.5895 | |0 | | - p1 | | | |f1 | | 0.5970 | | 0 | | - p2 | | | |f1 | | 0.5602 | | 0 | | - p3 | | | |f1 | | 0.6113 | | 0 | -| - re | | | |f1 | | 0.6475 | |0 | +| - RE | | | |f1 | | 0.6475 | |0 | | - p1 | | | |f1 | | 0.6482 | | 0 | | - p2 | | | |f1 | | 0.6469 | | 0 | diff --git a/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__gr__0shot.txt b/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__gr__0shot.txt index 05cb7403b2abda67e1498c0a9acb091c5a6657cd..7d091d2dd0d08ddd7d9ae2f74d581e4787f4ebf9 100644 --- a/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__gr__0shot.txt +++ b/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__gr__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.4506 | |0 | +| - NER | | | |f1 | | 0.4506 | |0 | | - p1 | | | |f1 | | 0.5976 | | 0 | | - p2 | | | |f1 | | 0.1568 | | 0 | | - p3 | | | |f1 | | 0.5976 | | 0 | -| - re | | | |f1 | | 0.4104 | |0 | +| - RE | | | |f1 | | 0.4104 | |0 | | - p1 | | | |f1 | | 0.4393 | | 0 | | - p2 | | | |f1 | | 0.4083 | | 0 | | - p3 | | | |f1 | | 0.3834 | | 0 | diff --git a/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__gr__10shot.txt b/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__gr__10shot.txt index 39118aac5734199451ebf0092c3f66c2a027e293..9087ff1ca50e0b67c158dad6587614e551149e8a 100644 --- a/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__gr__10shot.txt +++ b/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__gr__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.6175 | |0 | +| - NER | | | |f1 | | 0.6175 | |0 | | - p1 | | | |f1 | | 0.6196 | | 0 | | - p2 | | | |f1 | | 0.6131 | | 0 | | - p3 | | | |f1 | | 0.6196 | | 0 | -| - re | | | |f1 | | 0.5905 | |0 | +| - RE | | | |f1 | | 0.5905 | |0 | | - p1 | | | |f1 | | 0.5913 | | 0 | | - p2 | | | |f1 | | 0.5896 | | 0 | diff --git a/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__it__0shot.txt b/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__it__0shot.txt index 140b11ef154cb225fce693e5d9a1e1b236ff2aae..cb5936448f68978fe3b04ed6fcf29377b929e3d0 100644 --- a/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__it__0shot.txt +++ b/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__it__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.2734 | |0 | +| - NER | | | |f1 | | 0.2734 | |0 | | - p1 | | | |f1 | | 0.3758 | | 0 | | - p2 | | | |f1 | | 0.1647 | | 0 | | - p3 | | | |f1 | | 0.2796 | | 0 | -| - re | | | |f1 | | 0.4370 | |0 | +| - RE | | | |f1 | | 0.4370 | |0 | | - p1 | | | |f1 | | 0.4505 | | 0 | | - p2 | | | |f1 | | 0.4159 | | 0 | | - p3 | | | |f1 | | 0.4447 | | 0 | diff --git a/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__it__10shot.txt b/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__it__10shot.txt index 8abf4953ca9e869eaadd34cd7b1b71f0564fe64d..cc9811aa482472e85ccae9731c4d4718a8f562f1 100644 --- a/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__it__10shot.txt +++ b/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__it__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.7005 | |0 | +| - NER | | | |f1 | | 0.7005 | |0 | | - p1 | | | |f1 | | 0.6934 | | 0 | | - p2 | | | |f1 | | 0.7152 | | 0 | | - p3 | | | |f1 | | 0.6930 | | 0 | -| - re | | | |f1 | | 0.5698 | |0 | +| - RE | | | |f1 | | 0.5698 | |0 | | - p1 | | | |f1 | | 0.5801 | | 0 | | - p2 | | | |f1 | | 0.5595 | | 0 | diff --git a/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__pl__0shot.txt b/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__pl__0shot.txt index 74e43fcb74eaf8965a95c4edda457f3dfd9e7bb9..d4f8030e0178b97b248945b2973d52689441048e 100644 --- a/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__pl__0shot.txt +++ b/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__pl__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.2428 | |0 | +| - NER | | | |f1 | | 0.2428 | |0 | | - p1 | | | |f1 | | 0.2486 | | 0 | | - p2 | | | |f1 | | 0.2311 | | 0 | | - p3 | | | |f1 | | 0.2486 | | 0 | -| - re | | | |f1 | | 0.4074 | |0 | +| - RE | | | |f1 | | 0.4074 | |0 | | - p1 | | | |f1 | | 0.3865 | | 0 | | - p2 | | | |f1 | | 0.4569 | | 0 | | - p3 | | | |f1 | | 0.3788 | | 0 | diff --git a/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__pl__10shot.txt b/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__pl__10shot.txt index 4c15da5a66a4a537cb948eac8895ab2afa19b229..daa0b650060090e245eac4326b244e808fc2630b 100644 --- a/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__pl__10shot.txt +++ b/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__pl__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.6006 | |0 | +| - NER | | | |f1 | | 0.6006 | |0 | | - p1 | | | |f1 | | 0.6008 | | 0 | | - p2 | | | |f1 | | 0.6004 | | 0 | | - p3 | | | |f1 | | 0.6008 | | 0 | -| - re | | | |f1 | | 0.5863 | |0 | +| - RE | | | |f1 | | 0.5863 | |0 | | - p1 | | | |f1 | | 0.5858 | | 0 | | - p2 | | | |f1 | | 0.5868 | | 0 | diff --git a/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__sk__0shot.txt b/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__sk__0shot.txt index f4b349425adec625295b2bc60e755750d9ab7a12..8c2c921f81dfd861433916d7a82eae8f0794ee40 100644 --- a/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__sk__0shot.txt +++ b/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__sk__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.3375 | |0 | +| - NER | | | |f1 | | 0.3375 | |0 | | - p1 | | | |f1 | | 0.3578 | | 0 | | - p2 | | | |f1 | | 0.2968 | | 0 | | - p3 | | | |f1 | | 0.3578 | | 0 | -| - re | | | |f1 | | 0.4031 | |0 | +| - RE | | | |f1 | | 0.4031 | |0 | | - p1 | | | |f1 | | 0.3971 | | 0 | | - p2 | | | |f1 | | 0.4152 | | 0 | | - p3 | | | |f1 | | 0.3971 | | 0 | diff --git a/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__sk__10shot.txt b/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__sk__10shot.txt index dcbfcb3c84c61260eda9f92c142b11c06833a8e0..1ccda420b821daf609bb5cd16171ae53df52940e 100644 --- a/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__sk__10shot.txt +++ b/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__sk__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.6720 | |0 | +| - NER | | | |f1 | | 0.6720 | |0 | | - p1 | | | |f1 | | 0.6743 | | 0 | | - p2 | | | |f1 | | 0.6673 | | 0 | | - p3 | | | |f1 | | 0.6743 | | 0 | -| - re | | | |f1 | | 0.5659 | |0 | +| - RE | | | |f1 | | 0.5659 | |0 | | - p1 | | | |f1 | | 0.5733 | | 0 | | - p2 | | | |f1 | | 0.5586 | | 0 | diff --git a/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__sl__0shot.txt b/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__sl__0shot.txt index 727e1f367a9ba18d2d48d8535269ed56ab992195..12d98d519252a33b36dae0af4719974c3d12e5c2 100644 --- a/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__sl__0shot.txt +++ b/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__sl__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.3183 | |0 | +| - NER | | | |f1 | | 0.3183 | |0 | | - p1 | | | |f1 | | 0.3344 | | 0 | | - p2 | | | |f1 | | 0.2863 | | 0 | | - p3 | | | |f1 | | 0.3344 | | 0 | -| - re | | | |f1 | | 0.4048 | |0 | +| - RE | | | |f1 | | 0.4048 | |0 | | - p1 | | | |f1 | | 0.3979 | | 0 | | - p2 | | | |f1 | | 0.4186 | | 0 | | - p3 | | | |f1 | | 0.3979 | | 0 | diff --git a/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__sl__10shot.txt b/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__sl__10shot.txt index 6a189a78b7994ae2175efe2d4f3f45fd3750a7d1..278cd40a91ad4620e4b27495dedde513b441a8b9 100644 --- a/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__sl__10shot.txt +++ b/csv_files/outputs/Qwen__Qwen2.5-32B-Instruct__sl__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=Qwen/Qwen2.5-32B-Instruct ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.6373 | |0 | +| - NER | | | |f1 | | 0.6373 | |0 | | - p1 | | | |f1 | | 0.6253 | | 0 | | - p2 | | | |f1 | | 0.6615 | | 0 | | - p3 | | | |f1 | | 0.6253 | | 0 | -| - re | | | |f1 | | 0.5921 | |0 | +| - RE | | | |f1 | | 0.5921 | |0 | | - p1 | | | |f1 | | 0.5992 | | 0 | | - p2 | | | |f1 | | 0.5849 | | 0 | diff --git a/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__en__0shot.txt b/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__en__0shot.txt index c7a31b115206073f648d171a641a1e9adb9f0395..6420cfe9d439aeff3b1a1d5a016a08fc48833326 100644 --- a/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__en__0shot.txt +++ b/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__en__0shot.txt @@ -1,10 +1,10 @@ hf (pretrained=Qwen/Qwen3-30B-A3B-Instruct-2507 ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - re | | | |f1 | | 0.4141 | |0 | +| - RE | | | |f1 | | 0.4141 | |0 | | - p1 | | | |f1 | | 0.4394 | | 0 | | - p2 | | | |f1 | | 0.4031 | | 0 | | - p3 | | | |f1 | | 0.3997 | | 0 | -| - ner | | | |f1 | | 0.4445 | |0 | +| - NER | | | |f1 | | 0.4445 | |0 | | - p2 | | | |f1 | | 0.4162 | | 0 | | - p3 | | | |f1 | | 0.4729 | | 0 | diff --git a/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__en__10shot.txt b/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__en__10shot.txt index 22d1b67e335ec0c6e0d18331be46a57669999465..fc37c2a39be557639c52f60a8ec6ae1da9e32322 100644 --- a/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__en__10shot.txt +++ b/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__en__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=Qwen/Qwen3-30B-A3B-Instruct-2507 ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.5907 | |0 | +| - NER | | | |f1 | | 0.5907 | |0 | | - p1 | | | |f1 | | 0.5986 | | 0 | | - p2 | | | |f1 | | 0.5593 | | 0 | | - p3 | | | |f1 | | 0.6143 | | 0 | -| - re | | | |f1 | | 0.5206 | |0 | +| - RE | | | |f1 | | 0.5206 | |0 | | - p1 | | | |f1 | | 0.5150 | | 0 | | - p2 | | | |f1 | | 0.5261 | | 0 | diff --git a/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__gr__0shot.txt b/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__gr__0shot.txt index 7c0489ce88c04df68da7d52a58b5b2cea1ca8fcb..9679a42ef05e59d1976f28f381ab016e9bd01f2b 100644 --- a/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__gr__0shot.txt +++ b/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__gr__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=Qwen/Qwen3-30B-A3B-Instruct-2507 ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.4368 | |0 | +| - NER | | | |f1 | | 0.4368 | |0 | | - p1 | | | |f1 | | 0.4291 | | 0 | | - p2 | | | |f1 | | 0.4521 | | 0 | | - p3 | | | |f1 | | 0.4291 | | 0 | -| - re | | | |f1 | | 0.3776 | |0 | +| - RE | | | |f1 | | 0.3776 | |0 | | - p1 | | | |f1 | | 0.3733 | | 0 | | - p2 | | | |f1 | | 0.3799 | | 0 | | - p3 | | | |f1 | | 0.3798 | | 0 | diff --git a/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__gr__10shot.txt b/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__gr__10shot.txt index 3508c1e76ad1b9919674ab452e90707ae71cf34c..5d8438e1126afa00ac9f53c06974a76c9723dd0e 100644 --- a/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__gr__10shot.txt +++ b/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__gr__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=Qwen/Qwen3-30B-A3B-Instruct-2507 ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.5999 | |0 | +| - NER | | | |f1 | | 0.5999 | |0 | | - p1 | | | |f1 | | 0.6164 | | 0 | | - p2 | | | |f1 | | 0.5669 | | 0 | | - p3 | | | |f1 | | 0.6164 | | 0 | -| - re | | | |f1 | | 0.5112 | |0 | +| - RE | | | |f1 | | 0.5112 | |0 | | - p1 | | | |f1 | | 0.5015 | | 0 | | - p2 | | | |f1 | | 0.5209 | | 0 | diff --git a/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__it__0shot.txt b/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__it__0shot.txt index e4971eb61a49dd67508ed082c97db8f1c2abf7d7..d32b05f0de3224777b7aae2d6385c38711a575a8 100644 --- a/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__it__0shot.txt +++ b/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__it__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=Qwen/Qwen3-30B-A3B-Instruct-2507 ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.3572 | |0 | +| - NER | | | |f1 | | 0.3572 | |0 | | - p1 | | | |f1 | | 0.0885 | | 0 | | - p2 | | | |f1 | | 0.5316 | | 0 | | - p3 | | | |f1 | | 0.4514 | | 0 | -| - re | | | |f1 | | 0.3959 | |0 | +| - RE | | | |f1 | | 0.3959 | |0 | | - p1 | | | |f1 | | 0.3784 | | 0 | | - p2 | | | |f1 | | 0.4123 | | 0 | | - p3 | | | |f1 | | 0.3972 | | 0 | diff --git a/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__it__10shot.txt b/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__it__10shot.txt index 92a7b91f95d2c5d73e4fa25813a905aadb2e20b9..bcd6e22ceb291e8b04051163bb61adbe6a7b4a6d 100644 --- a/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__it__10shot.txt +++ b/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__it__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=Qwen/Qwen3-30B-A3B-Instruct-2507 ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.6673 | |0 | +| - NER | | | |f1 | | 0.6673 | |0 | | - p1 | | | |f1 | | 0.6793 | | 0 | | - p2 | | | |f1 | | 0.6447 | | 0 | | - p3 | | | |f1 | | 0.6778 | | 0 | -| - re | | | |f1 | | 0.5940 | |0 | +| - RE | | | |f1 | | 0.5940 | |0 | | - p1 | | | |f1 | | 0.6041 | | 0 | | - p2 | | | |f1 | | 0.5838 | | 0 | diff --git a/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__pl__0shot.txt b/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__pl__0shot.txt index bb0b6e78f15d6744550214a39f1ec2b912ae6e4e..a6358c6bb902fb22713a21ed802c947dd78e7ea6 100644 --- a/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__pl__0shot.txt +++ b/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__pl__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=Qwen/Qwen3-30B-A3B-Instruct-2507 ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.4235 | |0 | +| - NER | | | |f1 | | 0.4235 | |0 | | - p1 | | | |f1 | | 0.4332 | | 0 | | - p2 | | | |f1 | | 0.4043 | | 0 | | - p3 | | | |f1 | | 0.4332 | | 0 | -| - re | | | |f1 | | 0.4186 | |0 | +| - RE | | | |f1 | | 0.4186 | |0 | | - p1 | | | |f1 | | 0.4152 | | 0 | | - p2 | | | |f1 | | 0.4220 | | 0 | | - p3 | | | |f1 | | 0.4187 | | 0 | diff --git a/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__pl__10shot.txt b/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__pl__10shot.txt index 2eab77cf504508cdd676550c15f1ef50adcfc17e..cb0f5ba822a9b89ddfa3fd007d30529c8bc1a93d 100644 --- a/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__pl__10shot.txt +++ b/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__pl__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=Qwen/Qwen3-30B-A3B-Instruct-2507 ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.6118 | |0 | +| - NER | | | |f1 | | 0.6118 | |0 | | - p1 | | | |f1 | | 0.6276 | | 0 | | - p2 | | | |f1 | | 0.5803 | | 0 | | - p3 | | | |f1 | | 0.6276 | | 0 | -| - re | | | |f1 | | 0.5151 | |0 | +| - RE | | | |f1 | | 0.5151 | |0 | | - p1 | | | |f1 | | 0.5103 | | 0 | | - p2 | | | |f1 | | 0.5200 | | 0 | diff --git a/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__sk__0shot.txt b/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__sk__0shot.txt index 8f1aa20ba1b8dbdfbbdd9c3765af245f7dc02003..82f30fd004efa2674df97a1dae911f0a92ff3e26 100644 --- a/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__sk__0shot.txt +++ b/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__sk__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=Qwen/Qwen3-30B-A3B-Instruct-2507 ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.3287 | |0 | +| - NER | | | |f1 | | 0.3287 | |0 | | - p1 | | | |f1 | | 0.3231 | | 0 | | - p2 | | | |f1 | | 0.3398 | | 0 | | - p3 | | | |f1 | | 0.3231 | | 0 | -| - re | | | |f1 | | 0.3943 | |0 | +| - RE | | | |f1 | | 0.3943 | |0 | | - p1 | | | |f1 | | 0.3980 | | 0 | | - p2 | | | |f1 | | 0.3867 | | 0 | | - p3 | | | |f1 | | 0.3980 | | 0 | diff --git a/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__sk__10shot.txt b/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__sk__10shot.txt index 1b4fdd31716963a589ea32146ec079a51ae8228d..1f65d2dec6b3e36d1d623e101a901e98be8a42ee 100644 --- a/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__sk__10shot.txt +++ b/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__sk__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=Qwen/Qwen3-30B-A3B-Instruct-2507 ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.6030 | |0 | +| - NER | | | |f1 | | 0.6030 | |0 | | - p1 | | | |f1 | | 0.6085 | | 0 | | - p2 | | | |f1 | | 0.5919 | | 0 | | - p3 | | | |f1 | | 0.6085 | | 0 | -| - re | | | |f1 | | 0.4972 | |0 | +| - RE | | | |f1 | | 0.4972 | |0 | | - p1 | | | |f1 | | 0.4920 | | 0 | | - p2 | | | |f1 | | 0.5025 | | 0 | diff --git a/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__sl__0shot.txt b/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__sl__0shot.txt index 2991b4e7e5703738318d4d20a5d41b03aa8fb72a..126b784a0d6414a7ebb39eb6954f1444f9a726e9 100644 --- a/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__sl__0shot.txt +++ b/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__sl__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=Qwen/Qwen3-30B-A3B-Instruct-2507 ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.4501 | |0 | +| - NER | | | |f1 | | 0.4501 | |0 | | - p1 | | | |f1 | | 0.4486 | | 0 | | - p2 | | | |f1 | | 0.4531 | | 0 | | - p3 | | | |f1 | | 0.4486 | | 0 | -| - re | | | |f1 | | 0.4118 | |0 | +| - RE | | | |f1 | | 0.4118 | |0 | | - p1 | | | |f1 | | 0.4115 | | 0 | | - p2 | | | |f1 | | 0.4126 | | 0 | | - p3 | | | |f1 | | 0.4115 | | 0 | diff --git a/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__sl__10shot.txt b/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__sl__10shot.txt index e8eb40f0ec1a84778272aaa7d38475c55c5c9b6d..ab62dfffd44ae57f61f2f3a699bdbaf5e4c965da 100644 --- a/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__sl__10shot.txt +++ b/csv_files/outputs/Qwen__Qwen3-30B-A3B-Instruct-2507__sl__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=Qwen/Qwen3-30B-A3B-Instruct-2507 ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.6391 | |0 | +| - NER | | | |f1 | | 0.6391 | |0 | | - p1 | | | |f1 | | 0.6615 | | 0 | | - p2 | | | |f1 | | 0.5944 | | 0 | | - p3 | | | |f1 | | 0.6615 | | 0 | -| - re | | | |f1 | | 0.5319 | |0 | +| - RE | | | |f1 | | 0.5319 | |0 | | - p1 | | | |f1 | | 0.5062 | | 0 | | - p2 | | | |f1 | | 0.5576 | | 0 | diff --git a/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__en__0shot.txt b/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__en__0shot.txt index 4ef01af5dd78b8e2fb940fa106903fbc0a6bb424..37a0a0b3fcec4413d915fb8b17302fe6c93286c4 100644 --- a/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__en__0shot.txt +++ b/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__en__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=deepseek-ai/DeepSeek-R1-Distill-Qwen-32B ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.2877 | |0 | +| - NER | | | |f1 | | 0.2877 | |0 | | - p1 | | | |f1 | | 0.1963 | | 0 | | - p2 | | | |f1 | | 0.3459 | | 0 | | - p3 | | | |f1 | | 0.3208 | | 0 | -| - re | | | |f1 | | 0.4430 | |0 | +| - RE | | | |f1 | | 0.4430 | |0 | | - p1 | | | |f1 | | 0.4487 | | 0 | | - p2 | | | |f1 | | 0.4492 | | 0 | | - p3 | | | |f1 | | 0.4311 | | 0 | diff --git a/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__en__10shot.txt b/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__en__10shot.txt index 23149b9c36e767ce074bb8aaf7a68c7dc2c372d1..023290e171283c80a01550d0c36944a84da64c7c 100644 --- a/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__en__10shot.txt +++ b/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__en__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=deepseek-ai/DeepSeek-R1-Distill-Qwen-32B ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.5963 | |0 | +| - NER | | | |f1 | | 0.5963 | |0 | | - p1 | | | |f1 | | 0.6024 | | 0 | | - p2 | | | |f1 | | 0.5929 | | 0 | | - p3 | | | |f1 | | 0.5935 | | 0 | -| - re | | | |f1 | | 0.5195 | |0 | +| - RE | | | |f1 | | 0.5195 | |0 | | - p1 | | | |f1 | | 0.5191 | | 0 | | - p2 | | | |f1 | | 0.5199 | | 0 | diff --git a/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__gr__0shot.txt b/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__gr__0shot.txt index bfab0d152cb46ac0c16e55f18dbed709ae1bf3b1..79aa97329e86a168483edd679e8cc64109aed7a6 100644 --- a/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__gr__0shot.txt +++ b/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__gr__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=deepseek-ai/DeepSeek-R1-Distill-Qwen-32B ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.3421 | |0 | +| - NER | | | |f1 | | 0.3421 | |0 | | - p1 | | | |f1 | | 0.3455 | | 0 | | - p2 | | | |f1 | | 0.3354 | | 0 | | - p3 | | | |f1 | | 0.3455 | | 0 | -| - re | | | |f1 | | 0.3485 | |0 | +| - RE | | | |f1 | | 0.3485 | |0 | | - p1 | | | |f1 | | 0.2406 | | 0 | | - p2 | | | |f1 | | 0.3947 | | 0 | | - p3 | | | |f1 | | 0.4102 | | 0 | diff --git a/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__gr__10shot.txt b/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__gr__10shot.txt index 6c7abe0157fa639540010105a73dbf83d88a949e..c0a0adcf0ce098d34161ff1141bd34bb2575d3f5 100644 --- a/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__gr__10shot.txt +++ b/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__gr__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=deepseek-ai/DeepSeek-R1-Distill-Qwen-32B ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.5884 | |0 | +| - NER | | | |f1 | | 0.5884 | |0 | | - p1 | | | |f1 | | 0.5928 | | 0 | | - p2 | | | |f1 | | 0.5796 | | 0 | | - p3 | | | |f1 | | 0.5928 | | 0 | -| - re | | | |f1 | | 0.4338 | |0 | +| - RE | | | |f1 | | 0.4338 | |0 | | - p1 | | | |f1 | | 0.4467 | | 0 | | - p2 | | | |f1 | | 0.4210 | | 0 | diff --git a/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__it__0shot.txt b/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__it__0shot.txt index f1126637dc0654e0c02eb034afe79b2134085404..5db52b32f4fc4b7478fd7b3ec2f0063bd67713ec 100644 --- a/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__it__0shot.txt +++ b/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__it__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=deepseek-ai/DeepSeek-R1-Distill-Qwen-32B ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.3220 | |0 | +| - NER | | | |f1 | | 0.3220 | |0 | | - p1 | | | |f1 | | 0.2678 | | 0 | | - p2 | | | |f1 | | 0.3568 | | 0 | | - p3 | | | |f1 | | 0.3414 | | 0 | -| - re | | | |f1 | | 0.4452 | |0 | +| - RE | | | |f1 | | 0.4452 | |0 | | - p1 | | | |f1 | | 0.4519 | | 0 | | - p2 | | | |f1 | | 0.4611 | | 0 | | - p3 | | | |f1 | | 0.4227 | | 0 | diff --git a/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__it__10shot.txt b/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__it__10shot.txt index 4d08ae36f5f6ac1af02fb2539d068cd315347ce2..96e35e56e52b93e51041be086d3cf5cba46d9906 100644 --- a/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__it__10shot.txt +++ b/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__it__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=deepseek-ai/DeepSeek-R1-Distill-Qwen-32B ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.6864 | |0 | +| - NER | | | |f1 | | 0.6864 | |0 | | - p1 | | | |f1 | | 0.6982 | | 0 | | - p2 | | | |f1 | | 0.6679 | | 0 | | - p3 | | | |f1 | | 0.6930 | | 0 | -| - re | | | |f1 | | 0.5536 | |0 | +| - RE | | | |f1 | | 0.5536 | |0 | | - p1 | | | |f1 | | 0.5546 | | 0 | | - p2 | | | |f1 | | 0.5526 | | 0 | diff --git a/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__pl__0shot.txt b/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__pl__0shot.txt index c364ad8dc8a3694cab13535c8d872a7d8267216f..16a21b3d60d0b28e03e3f22502e906d4f9d2586d 100644 --- a/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__pl__0shot.txt +++ b/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__pl__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=deepseek-ai/DeepSeek-R1-Distill-Qwen-32B ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.3379 | |0 | +| - NER | | | |f1 | | 0.3379 | |0 | | - p1 | | | |f1 | | 0.3204 | | 0 | | - p2 | | | |f1 | | 0.3728 | | 0 | | - p3 | | | |f1 | | 0.3204 | | 0 | -| - re | | | |f1 | | 0.4131 | |0 | +| - RE | | | |f1 | | 0.4131 | |0 | | - p1 | | | |f1 | | 0.3983 | | 0 | | - p2 | | | |f1 | | 0.4327 | | 0 | | - p3 | | | |f1 | | 0.4083 | | 0 | diff --git a/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__pl__10shot.txt b/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__pl__10shot.txt index 2005f21143be43b07c295266c38acb45f2fa6f0f..cade308716b27c7c7d58a10a3bcce1456d819301 100644 --- a/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__pl__10shot.txt +++ b/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__pl__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=deepseek-ai/DeepSeek-R1-Distill-Qwen-32B ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.6189 | |0 | +| - NER | | | |f1 | | 0.6189 | |0 | | - p1 | | | |f1 | | 0.6214 | | 0 | | - p2 | | | |f1 | | 0.6140 | | 0 | | - p3 | | | |f1 | | 0.6214 | | 0 | -| - re | | | |f1 | | 0.4996 | |0 | +| - RE | | | |f1 | | 0.4996 | |0 | | - p1 | | | |f1 | | 0.4863 | | 0 | | - p2 | | | |f1 | | 0.5129 | | 0 | diff --git a/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__sk__0shot.txt b/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__sk__0shot.txt index 2152a7395c9729a83259ff1083694393d220f9df..ffa46c1c5e22e9d8e038069c447c1f026cfc61f6 100644 --- a/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__sk__0shot.txt +++ b/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__sk__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=deepseek-ai/DeepSeek-R1-Distill-Qwen-32B ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.2521 | |0 | +| - NER | | | |f1 | | 0.2521 | |0 | | - p1 | | | |f1 | | 0.2829 | | 0 | | - p2 | | | |f1 | | 0.1905 | | 0 | | - p3 | | | |f1 | | 0.2829 | | 0 | -| - re | | | |f1 | | 0.3959 | |0 | +| - RE | | | |f1 | | 0.3959 | |0 | | - p1 | | | |f1 | | 0.3893 | | 0 | | - p2 | | | |f1 | | 0.4091 | | 0 | | - p3 | | | |f1 | | 0.3893 | | 0 | diff --git a/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__sk__10shot.txt b/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__sk__10shot.txt index 53dc3135f30992f59dba56e73962bb6811c03381..ae309c6d90bb3718e41b93015b2729d95d7432a0 100644 --- a/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__sk__10shot.txt +++ b/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__sk__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=deepseek-ai/DeepSeek-R1-Distill-Qwen-32B ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.6302 | |0 | +| - NER | | | |f1 | | 0.6302 | |0 | | - p1 | | | |f1 | | 0.6347 | | 0 | | - p2 | | | |f1 | | 0.6211 | | 0 | | - p3 | | | |f1 | | 0.6347 | | 0 | -| - re | | | |f1 | | 0.4625 | |0 | +| - RE | | | |f1 | | 0.4625 | |0 | | - p1 | | | |f1 | | 0.4799 | | 0 | | - p2 | | | |f1 | | 0.4451 | | 0 | diff --git a/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__sl__0shot.txt b/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__sl__0shot.txt index 2748426dd1af84f0045d8336e22925b40cc24078..c0a0fe07a3970ef5a820c76cb9751944d12fdab2 100644 --- a/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__sl__0shot.txt +++ b/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__sl__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=deepseek-ai/DeepSeek-R1-Distill-Qwen-32B ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.2604 | |0 | +| - NER | | | |f1 | | 0.2604 | |0 | | - p1 | | | |f1 | | 0.2810 | | 0 | | - p2 | | | |f1 | | 0.2192 | | 0 | | - p3 | | | |f1 | | 0.2810 | | 0 | -| - re | | | |f1 | | 0.4116 | |0 | +| - RE | | | |f1 | | 0.4116 | |0 | | - p1 | | | |f1 | | 0.4116 | | 0 | | - p2 | | | |f1 | | 0.4115 | | 0 | | - p3 | | | |f1 | | 0.4116 | | 0 | diff --git a/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__sl__10shot.txt b/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__sl__10shot.txt index b23c800a9f3a3e4608a30f4ce34c2de4daac3546..90e4a5b6c1e518cabb5f827b9b9773f921f5a271 100644 --- a/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__sl__10shot.txt +++ b/csv_files/outputs/deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__sl__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=deepseek-ai/DeepSeek-R1-Distill-Qwen-32B ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.6026 | |0 | +| - NER | | | |f1 | | 0.6026 | |0 | | - p1 | | | |f1 | | 0.6015 | | 0 | | - p2 | | | |f1 | | 0.6049 | | 0 | | - p3 | | | |f1 | | 0.6015 | | 0 | -| - re | | | |f1 | | 0.4905 | |0 | +| - RE | | | |f1 | | 0.4905 | |0 | | - p1 | | | |f1 | | 0.5137 | | 0 | | - p2 | | | |f1 | | 0.4674 | | 0 | diff --git a/csv_files/outputs/epfl-llm__meditron-7b__en__0shot.txt b/csv_files/outputs/epfl-llm__meditron-7b__en__0shot.txt index 78db8a8821fd840feb3329f0360cc1ee8ee09efb..a378a1ac602f249f8f7988c361155b300f3edd65 100644 --- a/csv_files/outputs/epfl-llm__meditron-7b__en__0shot.txt +++ b/csv_files/outputs/epfl-llm__meditron-7b__en__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=epfl-llm/meditron-7b ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.0612 | |0 | +| - NER | | | |f1 | | 0.0612 | |0 | | - p1 | | | |f1 | | 0.0578 | | 0 | | - p2 | | | |f1 | | 0.0410 | | 0 | | - p3 | | | |f1 | | 0.0848 | | 0 | -| - re | | | |f1 | | 0.0313 | |0 | +| - RE | | | |f1 | | 0.0313 | |0 | | - p1 | | | |f1 | | 0.0000 | | 0 | | - p2 | | | |f1 | | 0.0442 | | 0 | | - p3 | | | |f1 | | 0.0497 | | 0 | diff --git a/csv_files/outputs/epfl-llm__meditron-7b__en__10shot.txt b/csv_files/outputs/epfl-llm__meditron-7b__en__10shot.txt index 8a24c1cdf686f8f22339741eea15c847a529ff4b..c78145b726a3287ad71bdbf95898e5bcf690cec5 100644 --- a/csv_files/outputs/epfl-llm__meditron-7b__en__10shot.txt +++ b/csv_files/outputs/epfl-llm__meditron-7b__en__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=epfl-llm/meditron-7b ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.1245 | |0 | +| - NER | | | |f1 | | 0.1245 | |0 | | - p1 | | | |f1 | | 0.0803 | | 0 | | - p2 | | | |f1 | | 0.1479 | | 0 | | - p3 | | | |f1 | | 0.1454 | | 0 | -| - re | | | |f1 | | 0.0707 | |0 | +| - RE | | | |f1 | | 0.0707 | |0 | | - p1 | | | |f1 | | 0.0722 | | 0 | | - p2 | | | |f1 | | 0.0692 | | 0 | diff --git a/csv_files/outputs/epfl-llm__meditron-7b__gr__0shot.txt b/csv_files/outputs/epfl-llm__meditron-7b__gr__0shot.txt index 90f380aafaa9694b769f94a1f4c39bda959769a0..b733c326cb013320727e13c717645ad3b4ff775e 100644 --- a/csv_files/outputs/epfl-llm__meditron-7b__gr__0shot.txt +++ b/csv_files/outputs/epfl-llm__meditron-7b__gr__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=epfl-llm/meditron-7b ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.2426 | |0 | +| - NER | | | |f1 | | 0.2426 | |0 | | - p1 | | | |f1 | | 0.2417 | | 0 | | - p2 | | | |f1 | | 0.2443 | | 0 | | - p3 | | | |f1 | | 0.2417 | | 0 | -| - re | | | |f1 | | 0.0592 | |0 | +| - RE | | | |f1 | | 0.0592 | |0 | | - p1 | | | |f1 | | 0.1556 | | 0 | | - p2 | | | |f1 | | 0.0161 | | 0 | | - p3 | | | |f1 | | 0.0058 | | 0 | diff --git a/csv_files/outputs/epfl-llm__meditron-7b__gr__10shot.txt b/csv_files/outputs/epfl-llm__meditron-7b__gr__10shot.txt index 3fcaa1628b92a900182158ef40a0f79e7f2da7e7..f84248bfeea07c329a9316ef806317b13694de28 100644 --- a/csv_files/outputs/epfl-llm__meditron-7b__gr__10shot.txt +++ b/csv_files/outputs/epfl-llm__meditron-7b__gr__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=epfl-llm/meditron-7b ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.0000 | |0 | +| - NER | | | |f1 | | 0.0000 | |0 | | - p1 | | | |f1 | | 0.0000 | | 0 | | - p2 | | | |f1 | | 0.0000 | | 0 | | - p3 | | | |f1 | | 0.0000 | | 0 | -| - re | | | |f1 | | 0.0000 | |0 | +| - RE | | | |f1 | | 0.0000 | |0 | | - p1 | | | |f1 | | 0.0000 | | 0 | | - p2 | | | |f1 | | 0.0000 | | 0 | diff --git a/csv_files/outputs/epfl-llm__meditron-7b__it__0shot.txt b/csv_files/outputs/epfl-llm__meditron-7b__it__0shot.txt index 477407b0788a1fd7b0424b9bfbe8e8ec2b5027d1..2a0d1cb5b5e49884090c31b808c2bc2a7f01cf4c 100644 --- a/csv_files/outputs/epfl-llm__meditron-7b__it__0shot.txt +++ b/csv_files/outputs/epfl-llm__meditron-7b__it__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=epfl-llm/meditron-7b ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.0639 | |0 | +| - NER | | | |f1 | | 0.0639 | |0 | | - p1 | | | |f1 | | 0.0773 | | 0 | | - p2 | | | |f1 | | 0.0612 | | 0 | | - p3 | | | |f1 | | 0.0531 | | 0 | -| - re | | | |f1 | | 0.1072 | |0 | +| - RE | | | |f1 | | 0.1072 | |0 | | - p1 | | | |f1 | | 0.0020 | | 0 | | - p2 | | | |f1 | | 0.1929 | | 0 | | - p3 | | | |f1 | | 0.1268 | | 0 | diff --git a/csv_files/outputs/epfl-llm__meditron-7b__it__10shot.txt b/csv_files/outputs/epfl-llm__meditron-7b__it__10shot.txt index 70f1ca5e4a9cd49b89f1cffb9a2514616006cbfc..e4f711b8934a50927b9c80e4173b530029a20a83 100644 --- a/csv_files/outputs/epfl-llm__meditron-7b__it__10shot.txt +++ b/csv_files/outputs/epfl-llm__meditron-7b__it__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=epfl-llm/meditron-7b ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.3288 | |0 | +| - NER | | | |f1 | | 0.3288 | |0 | | - p1 | | | |f1 | | 0.2991 | | 0 | | - p2 | | | |f1 | | 0.3563 | | 0 | | - p3 | | | |f1 | | 0.3311 | | 0 | -| - re | | | |f1 | | 0.0859 | |0 | +| - RE | | | |f1 | | 0.0859 | |0 | | - p1 | | | |f1 | | 0.0832 | | 0 | | - p2 | | | |f1 | | 0.0887 | | 0 | diff --git a/csv_files/outputs/epfl-llm__meditron-7b__pl__0shot.txt b/csv_files/outputs/epfl-llm__meditron-7b__pl__0shot.txt index fc17086240d17d361a344298c66abb3a31227ff9..7c763fab18fe2af421c37a99965e57159fb9f0dd 100644 --- a/csv_files/outputs/epfl-llm__meditron-7b__pl__0shot.txt +++ b/csv_files/outputs/epfl-llm__meditron-7b__pl__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=epfl-llm/meditron-7b ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.1161 | |0 | +| - NER | | | |f1 | | 0.1161 | |0 | | - p1 | | | |f1 | | 0.1140 | | 0 | | - p2 | | | |f1 | | 0.1203 | | 0 | | - p3 | | | |f1 | | 0.1140 | | 0 | -| - re | | | |f1 | | 0.0025 | |0 | +| - RE | | | |f1 | | 0.0025 | |0 | | - p1 | | | |f1 | | 0.0000 | | 0 | | - p2 | | | |f1 | | 0.0000 | | 0 | | - p3 | | | |f1 | | 0.0076 | | 0 | diff --git a/csv_files/outputs/epfl-llm__meditron-7b__pl__10shot.txt b/csv_files/outputs/epfl-llm__meditron-7b__pl__10shot.txt index b49704f897b67e8bbfbfda2d599a9cea322c0e6d..8a5ce7fd170f07cb5e4701da5f07a94823b77556 100644 --- a/csv_files/outputs/epfl-llm__meditron-7b__pl__10shot.txt +++ b/csv_files/outputs/epfl-llm__meditron-7b__pl__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=epfl-llm/meditron-7b ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.3222 | |0 | +| - NER | | | |f1 | | 0.3222 | |0 | | - p1 | | | |f1 | | 0.3184 | | 0 | | - p2 | | | |f1 | | 0.3297 | | 0 | | - p3 | | | |f1 | | 0.3184 | | 0 | -| - re | | | |f1 | | 0.0497 | |0 | +| - RE | | | |f1 | | 0.0497 | |0 | | - p1 | | | |f1 | | 0.0533 | | 0 | | - p2 | | | |f1 | | 0.0461 | | 0 | diff --git a/csv_files/outputs/epfl-llm__meditron-7b__sk__0shot.txt b/csv_files/outputs/epfl-llm__meditron-7b__sk__0shot.txt index 2992e79edb39887634ef426287d1a8de4142fb50..93e3d58f1c091c0ef7928d528ba2d95cfc046831 100644 --- a/csv_files/outputs/epfl-llm__meditron-7b__sk__0shot.txt +++ b/csv_files/outputs/epfl-llm__meditron-7b__sk__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=epfl-llm/meditron-7b ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.0778 | |0 | +| - NER | | | |f1 | | 0.0778 | |0 | | - p1 | | | |f1 | | 0.0874 | | 0 | | - p2 | | | |f1 | | 0.0586 | | 0 | | - p3 | | | |f1 | | 0.0874 | | 0 | -| - re | | | |f1 | | 0.0034 | |0 | +| - RE | | | |f1 | | 0.0034 | |0 | | - p1 | | | |f1 | | 0.0036 | | 0 | | - p2 | | | |f1 | | 0.0031 | | 0 | | - p3 | | | |f1 | | 0.0036 | | 0 | diff --git a/csv_files/outputs/epfl-llm__meditron-7b__sk__10shot.txt b/csv_files/outputs/epfl-llm__meditron-7b__sk__10shot.txt index 28126a48bf5fc2bcc223674fae2771730fdbfb54..ab4b2789448393a410110ed0c9552f2282a33d44 100644 --- a/csv_files/outputs/epfl-llm__meditron-7b__sk__10shot.txt +++ b/csv_files/outputs/epfl-llm__meditron-7b__sk__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=epfl-llm/meditron-7b ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.2993 | |0 | +| - NER | | | |f1 | | 0.2993 | |0 | | - p1 | | | |f1 | | 0.3004 | | 0 | | - p2 | | | |f1 | | 0.2970 | | 0 | | - p3 | | | |f1 | | 0.3004 | | 0 | -| - re | | | |f1 | | 0.0419 | |0 | +| - RE | | | |f1 | | 0.0419 | |0 | | - p1 | | | |f1 | | 0.0445 | | 0 | | - p2 | | | |f1 | | 0.0393 | | 0 | diff --git a/csv_files/outputs/epfl-llm__meditron-7b__sl__0shot.txt b/csv_files/outputs/epfl-llm__meditron-7b__sl__0shot.txt index 0e6829ac6b5697fbe26df6ba9884b9378fb79fca..cfb36aa25fe8478844f4e4741701e7cd84df3e6c 100644 --- a/csv_files/outputs/epfl-llm__meditron-7b__sl__0shot.txt +++ b/csv_files/outputs/epfl-llm__meditron-7b__sl__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=epfl-llm/meditron-7b ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.0951 | |0 | +| - NER | | | |f1 | | 0.0951 | |0 | | - p1 | | | |f1 | | 0.1197 | | 0 | | - p2 | | | |f1 | | 0.0460 | | 0 | | - p3 | | | |f1 | | 0.1197 | | 0 | -| - re | | | |f1 | | 0.0445 | |0 | +| - RE | | | |f1 | | 0.0445 | |0 | | - p1 | | | |f1 | | 0.0598 | | 0 | | - p2 | | | |f1 | | 0.0137 | | 0 | | - p3 | | | |f1 | | 0.0598 | | 0 | diff --git a/csv_files/outputs/epfl-llm__meditron-7b__sl__10shot.txt b/csv_files/outputs/epfl-llm__meditron-7b__sl__10shot.txt index 48a1c3857e71b30d72bff58a732d669cae455200..d715ee1da72e5acea32d9826df9b4a6f158e0133 100644 --- a/csv_files/outputs/epfl-llm__meditron-7b__sl__10shot.txt +++ b/csv_files/outputs/epfl-llm__meditron-7b__sl__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=epfl-llm/meditron-7b ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.3052 | |0 | +| - NER | | | |f1 | | 0.3052 | |0 | | - p1 | | | |f1 | | 0.3119 | | 0 | | - p2 | | | |f1 | | 0.2916 | | 0 | | - p3 | | | |f1 | | 0.3119 | | 0 | -| - re | | | |f1 | | 0.0489 | |0 | +| - RE | | | |f1 | | 0.0489 | |0 | | - p1 | | | |f1 | | 0.0477 | | 0 | | - p2 | | | |f1 | | 0.0501 | | 0 | diff --git a/csv_files/outputs/google__gemma-2-9b-it__en__0shot.txt b/csv_files/outputs/google__gemma-2-9b-it__en__0shot.txt index e19636f5cb99384931c747797c8af46f51f3d6db..568fb0bef70896f666a03925b261a19ecc918295 100644 --- a/csv_files/outputs/google__gemma-2-9b-it__en__0shot.txt +++ b/csv_files/outputs/google__gemma-2-9b-it__en__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=google/gemma-2-9b-it ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.4603 | |0 | +| - NER | | | |f1 | | 0.4603 | |0 | | - p1 | | | |f1 | | 0.3267 | | 0 | | - p2 | | | |f1 | | 0.5174 | | 0 | | - p3 | | | |f1 | | 0.5370 | | 0 | -| - re | | | |f1 | | 0.4211 | |0 | +| - RE | | | |f1 | | 0.4211 | |0 | | - p1 | | | |f1 | | 0.4360 | | 0 | | - p2 | | | |f1 | | 0.4205 | | 0 | | - p3 | | | |f1 | | 0.4067 | | 0 | diff --git a/csv_files/outputs/google__gemma-2-9b-it__en__10shot.txt b/csv_files/outputs/google__gemma-2-9b-it__en__10shot.txt index 7ec0a5068d2d9de19d471da673153ba727f16b87..351987c72f1460be7fa2757c9bab541d58d86046 100644 --- a/csv_files/outputs/google__gemma-2-9b-it__en__10shot.txt +++ b/csv_files/outputs/google__gemma-2-9b-it__en__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=google/gemma-2-9b-it ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.5919 | |0 | +| - NER | | | |f1 | | 0.5919 | |0 | | - p1 | | | |f1 | | 0.6200 | | 0 | | - p2 | | | |f1 | | 0.5639 | | 0 | | - p3 | | | |f1 | | 0.5918 | | 0 | -| - re | | | |f1 | | 0.5250 | |0 | +| - RE | | | |f1 | | 0.5250 | |0 | | - p1 | | | |f1 | | 0.5163 | | 0 | | - p2 | | | |f1 | | 0.5337 | | 0 | diff --git a/csv_files/outputs/google__gemma-2-9b-it__gr__0shot.txt b/csv_files/outputs/google__gemma-2-9b-it__gr__0shot.txt index 048dfca18dd05e8044de8048244a8584f4827f55..87226c5046c2278e0f2a6e57fa83aa395a61ca52 100644 --- a/csv_files/outputs/google__gemma-2-9b-it__gr__0shot.txt +++ b/csv_files/outputs/google__gemma-2-9b-it__gr__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=google/gemma-2-9b-it ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.5292 | |0 | +| - NER | | | |f1 | | 0.5292 | |0 | | - p1 | | | |f1 | | 0.5549 | | 0 | | - p2 | | | |f1 | | 0.4777 | | 0 | | - p3 | | | |f1 | | 0.5549 | | 0 | -| - re | | | |f1 | | 0.4008 | |0 | +| - RE | | | |f1 | | 0.4008 | |0 | | - p1 | | | |f1 | | 0.4124 | | 0 | | - p2 | | | |f1 | | 0.3957 | | 0 | | - p3 | | | |f1 | | 0.3943 | | 0 | diff --git a/csv_files/outputs/google__gemma-2-9b-it__gr__10shot.txt b/csv_files/outputs/google__gemma-2-9b-it__gr__10shot.txt index acda7e64b8db71bd62f4747ef0e6e75ceba2fda9..ab0b09b144a5d00d514bc49444e9f2f2ede3b715 100644 --- a/csv_files/outputs/google__gemma-2-9b-it__gr__10shot.txt +++ b/csv_files/outputs/google__gemma-2-9b-it__gr__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=google/gemma-2-9b-it ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.5943 | |0 | +| - NER | | | |f1 | | 0.5943 | |0 | | - p1 | | | |f1 | | 0.6083 | | 0 | | - p2 | | | |f1 | | 0.5663 | | 0 | | - p3 | | | |f1 | | 0.6083 | | 0 | -| - re | | | |f1 | | 0.5020 | |0 | +| - RE | | | |f1 | | 0.5020 | |0 | | - p1 | | | |f1 | | 0.5070 | | 0 | | - p2 | | | |f1 | | 0.4971 | | 0 | diff --git a/csv_files/outputs/google__gemma-2-9b-it__it__0shot.txt b/csv_files/outputs/google__gemma-2-9b-it__it__0shot.txt index 257bab96b1cdba6c3e1750389c0becb81478fd17..8c1e51ad7fa14eeadd44b3fdc9a10c6ff1ae5784 100644 --- a/csv_files/outputs/google__gemma-2-9b-it__it__0shot.txt +++ b/csv_files/outputs/google__gemma-2-9b-it__it__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=google/gemma-2-9b-it ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.6158 | |0 | +| - NER | | | |f1 | | 0.6158 | |0 | | - p1 | | | |f1 | | 0.5739 | | 0 | | - p2 | | | |f1 | | 0.6524 | | 0 | | - p3 | | | |f1 | | 0.6210 | | 0 | -| - re | | | |f1 | | 0.4298 | |0 | +| - RE | | | |f1 | | 0.4298 | |0 | | - p1 | | | |f1 | | 0.4585 | | 0 | | - p2 | | | |f1 | | 0.4113 | | 0 | | - p3 | | | |f1 | | 0.4196 | | 0 | diff --git a/csv_files/outputs/google__gemma-2-9b-it__it__10shot.txt b/csv_files/outputs/google__gemma-2-9b-it__it__10shot.txt index 0632325531b1375a8db66e753ac57fe9f67aa6c3..8f5b46311c3fb129a2ef013321002e72081ad6dc 100644 --- a/csv_files/outputs/google__gemma-2-9b-it__it__10shot.txt +++ b/csv_files/outputs/google__gemma-2-9b-it__it__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=google/gemma-2-9b-it ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.6707 | |0 | +| - NER | | | |f1 | | 0.6707 | |0 | | - p1 | | | |f1 | | 0.6910 | | 0 | | - p2 | | | |f1 | | 0.6643 | | 0 | | - p3 | | | |f1 | | 0.6569 | | 0 | -| - re | | | |f1 | | 0.5162 | |0 | +| - RE | | | |f1 | | 0.5162 | |0 | | - p1 | | | |f1 | | 0.4958 | | 0 | | - p2 | | | |f1 | | 0.5365 | | 0 | diff --git a/csv_files/outputs/google__gemma-2-9b-it__pl__0shot.txt b/csv_files/outputs/google__gemma-2-9b-it__pl__0shot.txt index f0dd544b253e5cfec98214be12bd48f0ad373669..f187b39ad69bd8bb0dbf697be691b129eadee340 100644 --- a/csv_files/outputs/google__gemma-2-9b-it__pl__0shot.txt +++ b/csv_files/outputs/google__gemma-2-9b-it__pl__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=google/gemma-2-9b-it ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.4092 | |0 | +| - NER | | | |f1 | | 0.4092 | |0 | | - p1 | | | |f1 | | 0.4060 | | 0 | | - p2 | | | |f1 | | 0.4155 | | 0 | | - p3 | | | |f1 | | 0.4060 | | 0 | -| - re | | | |f1 | | 0.3891 | |0 | +| - RE | | | |f1 | | 0.3891 | |0 | | - p1 | | | |f1 | | 0.3674 | | 0 | | - p2 | | | |f1 | | 0.4271 | | 0 | | - p3 | | | |f1 | | 0.3729 | | 0 | diff --git a/csv_files/outputs/google__gemma-2-9b-it__pl__10shot.txt b/csv_files/outputs/google__gemma-2-9b-it__pl__10shot.txt index dce8e217433d79bf5a23a3bbbfc88de644f5db4d..76dc18d9929e7897f0ced0ae101718ebb60d6228 100644 --- a/csv_files/outputs/google__gemma-2-9b-it__pl__10shot.txt +++ b/csv_files/outputs/google__gemma-2-9b-it__pl__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=google/gemma-2-9b-it ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.5893 | |0 | +| - NER | | | |f1 | | 0.5893 | |0 | | - p1 | | | |f1 | | 0.5908 | | 0 | | - p2 | | | |f1 | | 0.5862 | | 0 | | - p3 | | | |f1 | | 0.5908 | | 0 | -| - re | | | |f1 | | 0.4988 | |0 | +| - RE | | | |f1 | | 0.4988 | |0 | | - p1 | | | |f1 | | 0.5168 | | 0 | | - p2 | | | |f1 | | 0.4808 | | 0 | diff --git a/csv_files/outputs/google__gemma-2-9b-it__sk__0shot.txt b/csv_files/outputs/google__gemma-2-9b-it__sk__0shot.txt index fd0dcda59f3d4db2ccb3c171b9673cc8777a7dbd..8f0bc370ed50b39ebc88b5e7e85f8a110f45a283 100644 --- a/csv_files/outputs/google__gemma-2-9b-it__sk__0shot.txt +++ b/csv_files/outputs/google__gemma-2-9b-it__sk__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=google/gemma-2-9b-it ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.4775 | |0 | +| - NER | | | |f1 | | 0.4775 | |0 | | - p1 | | | |f1 | | 0.4875 | | 0 | | - p2 | | | |f1 | | 0.4575 | | 0 | | - p3 | | | |f1 | | 0.4875 | | 0 | -| - re | | | |f1 | | 0.4106 | |0 | +| - RE | | | |f1 | | 0.4106 | |0 | | - p1 | | | |f1 | | 0.3989 | | 0 | | - p2 | | | |f1 | | 0.4340 | | 0 | | - p3 | | | |f1 | | 0.3989 | | 0 | diff --git a/csv_files/outputs/google__gemma-2-9b-it__sk__10shot.txt b/csv_files/outputs/google__gemma-2-9b-it__sk__10shot.txt index d861112dbb48892d26a8c978c99e01b89e5eeef3..b0e88ea7e76efcab0b135cd8a95fc77858475755 100644 --- a/csv_files/outputs/google__gemma-2-9b-it__sk__10shot.txt +++ b/csv_files/outputs/google__gemma-2-9b-it__sk__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=google/gemma-2-9b-it ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.6135 | |0 | +| - NER | | | |f1 | | 0.6135 | |0 | | - p1 | | | |f1 | | 0.6141 | | 0 | | - p2 | | | |f1 | | 0.6122 | | 0 | | - p3 | | | |f1 | | 0.6141 | | 0 | -| - re | | | |f1 | | 0.4953 | |0 | +| - RE | | | |f1 | | 0.4953 | |0 | | - p1 | | | |f1 | | 0.5153 | | 0 | | - p2 | | | |f1 | | 0.4754 | | 0 | diff --git a/csv_files/outputs/google__gemma-2-9b-it__sl__0shot.txt b/csv_files/outputs/google__gemma-2-9b-it__sl__0shot.txt index 7dbedbb5cba1e8cbcff506c960d746ce4fd56b4d..98ce20cc51f351ff18c9e416c89a29a920d6bacd 100644 --- a/csv_files/outputs/google__gemma-2-9b-it__sl__0shot.txt +++ b/csv_files/outputs/google__gemma-2-9b-it__sl__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=google/gemma-2-9b-it ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.4487 | |0 | +| - NER | | | |f1 | | 0.4487 | |0 | | - p1 | | | |f1 | | 0.4707 | | 0 | | - p2 | | | |f1 | | 0.4046 | | 0 | | - p3 | | | |f1 | | 0.4707 | | 0 | -| - re | | | |f1 | | 0.4058 | |0 | +| - RE | | | |f1 | | 0.4058 | |0 | | - p1 | | | |f1 | | 0.4079 | | 0 | | - p2 | | | |f1 | | 0.4016 | | 0 | | - p3 | | | |f1 | | 0.4079 | | 0 | diff --git a/csv_files/outputs/google__gemma-2-9b-it__sl__10shot.txt b/csv_files/outputs/google__gemma-2-9b-it__sl__10shot.txt index 4971239c4c88c5c27f915bb8144431389bc77bd6..e61099f796ffbeb0600dc326a97cf20aed09ea52 100644 --- a/csv_files/outputs/google__gemma-2-9b-it__sl__10shot.txt +++ b/csv_files/outputs/google__gemma-2-9b-it__sl__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=google/gemma-2-9b-it ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.6156 | |0 | +| - NER | | | |f1 | | 0.6156 | |0 | | - p1 | | | |f1 | | 0.6365 | | 0 | | - p2 | | | |f1 | | 0.5737 | | 0 | | - p3 | | | |f1 | | 0.6365 | | 0 | -| - re | | | |f1 | | 0.4839 | |0 | +| - RE | | | |f1 | | 0.4839 | |0 | | - p1 | | | |f1 | | 0.4801 | | 0 | | - p2 | | | |f1 | | 0.4878 | | 0 | diff --git a/csv_files/outputs/google__gemma-3-27b-it__en__0shot.txt b/csv_files/outputs/google__gemma-3-27b-it__en__0shot.txt index 31b15abdd5c41472d9458080c7abcad9d60923a0..11bb43caf4d6194fe781b6d25ed4e6d8ba98ec60 100644 --- a/csv_files/outputs/google__gemma-3-27b-it__en__0shot.txt +++ b/csv_files/outputs/google__gemma-3-27b-it__en__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=google/gemma-3-27b-it ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.5490 | |0 | +| - NER | | | |f1 | | 0.5490 | |0 | | - p1 | | | |f1 | | 0.5446 | | 0 | | - p2 | | | |f1 | | 0.5830 | | 0 | | - p3 | | | |f1 | | 0.5194 | | 0 | -| - re | | | |f1 | | 0.4623 | |0 | +| - RE | | | |f1 | | 0.4623 | |0 | | - p1 | | | |f1 | | 0.4543 | | 0 | | - p2 | | | |f1 | | 0.4582 | | 0 | | - p3 | | | |f1 | | 0.4743 | | 0 | diff --git a/csv_files/outputs/google__gemma-3-27b-it__en__10shot.txt b/csv_files/outputs/google__gemma-3-27b-it__en__10shot.txt index 4c211585d3bad9b76f69797b829c4ce01b1d4eef..43fe469ea2dced95ed141070f26d70b56e807bab 100644 --- a/csv_files/outputs/google__gemma-3-27b-it__en__10shot.txt +++ b/csv_files/outputs/google__gemma-3-27b-it__en__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=google/gemma-3-27b-it ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.6187 | |0 | +| - NER | | | |f1 | | 0.6187 | |0 | | - p1 | | | |f1 | | 0.6160 | | 0 | | - p2 | | | |f1 | | 0.6308 | | 0 | | - p3 | | | |f1 | | 0.6094 | | 0 | -| - re | | | |f1 | | 0.5395 | |0 | +| - RE | | | |f1 | | 0.5395 | |0 | | - p1 | | | |f1 | | 0.5191 | | 0 | | - p2 | | | |f1 | | 0.5600 | | 0 | diff --git a/csv_files/outputs/google__gemma-3-27b-it__gr__0shot.txt b/csv_files/outputs/google__gemma-3-27b-it__gr__0shot.txt index 85b855c2ce31543c10a48d92f353901284140c68..93e9d713d614c2dbaa4d17389ea32a9b3021a3cf 100644 --- a/csv_files/outputs/google__gemma-3-27b-it__gr__0shot.txt +++ b/csv_files/outputs/google__gemma-3-27b-it__gr__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=google/gemma-3-27b-it ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.5151 | |0 | +| - NER | | | |f1 | | 0.5151 | |0 | | - p1 | | | |f1 | | 0.4866 | | 0 | | - p2 | | | |f1 | | 0.5721 | | 0 | | - p3 | | | |f1 | | 0.4866 | | 0 | -| - re | | | |f1 | | 0.4473 | |0 | +| - RE | | | |f1 | | 0.4473 | |0 | | - p1 | | | |f1 | | 0.3955 | | 0 | | - p2 | | | |f1 | | 0.4695 | | 0 | | - p3 | | | |f1 | | 0.4769 | | 0 | diff --git a/csv_files/outputs/google__gemma-3-27b-it__gr__10shot.txt b/csv_files/outputs/google__gemma-3-27b-it__gr__10shot.txt index f9352d7ebc748c3d31505626a53cbd79984d0345..457c5af3392b963073156197290202a23e90058a 100644 --- a/csv_files/outputs/google__gemma-3-27b-it__gr__10shot.txt +++ b/csv_files/outputs/google__gemma-3-27b-it__gr__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=google/gemma-3-27b-it ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.6570 | |0 | +| - NER | | | |f1 | | 0.6570 | |0 | | - p1 | | | |f1 | | 0.6551 | | 0 | | - p2 | | | |f1 | | 0.6608 | | 0 | | - p3 | | | |f1 | | 0.6551 | | 0 | -| - re | | | |f1 | | 0.5316 | |0 | +| - RE | | | |f1 | | 0.5316 | |0 | | - p1 | | | |f1 | | 0.5083 | | 0 | | - p2 | | | |f1 | | 0.5550 | | 0 | diff --git a/csv_files/outputs/google__gemma-3-27b-it__it__0shot.txt b/csv_files/outputs/google__gemma-3-27b-it__it__0shot.txt index 1d27d823cf04238dd6448c8d887746a77c94522c..20b323e8a1c0fdd3626eab05d6d99055375834fe 100644 --- a/csv_files/outputs/google__gemma-3-27b-it__it__0shot.txt +++ b/csv_files/outputs/google__gemma-3-27b-it__it__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=google/gemma-3-27b-it ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.6065 | |0 | +| - NER | | | |f1 | | 0.6065 | |0 | | - p1 | | | |f1 | | 0.5543 | | 0 | | - p2 | | | |f1 | | 0.6697 | | 0 | | - p3 | | | |f1 | | 0.5954 | | 0 | -| - re | | | |f1 | | 0.4737 | |0 | +| - RE | | | |f1 | | 0.4737 | |0 | | - p1 | | | |f1 | | 0.4390 | | 0 | | - p2 | | | |f1 | | 0.4895 | | 0 | | - p3 | | | |f1 | | 0.4927 | | 0 | diff --git a/csv_files/outputs/google__gemma-3-27b-it__it__10shot.txt b/csv_files/outputs/google__gemma-3-27b-it__it__10shot.txt index 324ead0872b04bf57f22a2b8eb4d48f1a28a2d29..7f1e9de6444c6822209bea393633e24162dd2816 100644 --- a/csv_files/outputs/google__gemma-3-27b-it__it__10shot.txt +++ b/csv_files/outputs/google__gemma-3-27b-it__it__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=google/gemma-3-27b-it ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.7115 | |0 | +| - NER | | | |f1 | | 0.7115 | |0 | | - p1 | | | |f1 | | 0.7142 | | 0 | | - p2 | | | |f1 | | 0.6992 | | 0 | | - p3 | | | |f1 | | 0.7212 | | 0 | -| - re | | | |f1 | | 0.5530 | |0 | +| - RE | | | |f1 | | 0.5530 | |0 | | - p1 | | | |f1 | | 0.5223 | | 0 | | - p2 | | | |f1 | | 0.5837 | | 0 | diff --git a/csv_files/outputs/google__gemma-3-27b-it__pl__0shot.txt b/csv_files/outputs/google__gemma-3-27b-it__pl__0shot.txt index 0b3aad8ed444ad79e33ecc050259e21001bc221a..e9f1519cf73039b96aee8faf352b110818910761 100644 --- a/csv_files/outputs/google__gemma-3-27b-it__pl__0shot.txt +++ b/csv_files/outputs/google__gemma-3-27b-it__pl__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=google/gemma-3-27b-it ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.4508 | |0 | +| - NER | | | |f1 | | 0.4508 | |0 | | - p1 | | | |f1 | | 0.4506 | | 0 | | - p2 | | | |f1 | | 0.4511 | | 0 | | - p3 | | | |f1 | | 0.4506 | | 0 | -| - re | | | |f1 | | 0.4307 | |0 | +| - RE | | | |f1 | | 0.4307 | |0 | | - p1 | | | |f1 | | 0.4384 | | 0 | | - p2 | | | |f1 | | 0.4267 | | 0 | | - p3 | | | |f1 | | 0.4271 | | 0 | diff --git a/csv_files/outputs/google__gemma-3-27b-it__pl__10shot.txt b/csv_files/outputs/google__gemma-3-27b-it__pl__10shot.txt index ba2ab175a07a602745838e903e5784c52ee2778d..a25d9505896b4fc63b8e9ae3f6bc0d40a45a5073 100644 --- a/csv_files/outputs/google__gemma-3-27b-it__pl__10shot.txt +++ b/csv_files/outputs/google__gemma-3-27b-it__pl__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=google/gemma-3-27b-it ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.6618 | |0 | +| - NER | | | |f1 | | 0.6618 | |0 | | - p1 | | | |f1 | | 0.6591 | | 0 | | - p2 | | | |f1 | | 0.6672 | | 0 | | - p3 | | | |f1 | | 0.6591 | | 0 | -| - re | | | |f1 | | 0.5698 | |0 | +| - RE | | | |f1 | | 0.5698 | |0 | | - p1 | | | |f1 | | 0.5795 | | 0 | | - p2 | | | |f1 | | 0.5601 | | 0 | diff --git a/csv_files/outputs/google__gemma-3-27b-it__sk__0shot.txt b/csv_files/outputs/google__gemma-3-27b-it__sk__0shot.txt index 6f23d39956ebbb09bdb54019cc382d647d59358d..27cb80b8b7a5de7165aa52e89c5f70d0ac61dc23 100644 --- a/csv_files/outputs/google__gemma-3-27b-it__sk__0shot.txt +++ b/csv_files/outputs/google__gemma-3-27b-it__sk__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=google/gemma-3-27b-it ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.2841 | |0 | +| - NER | | | |f1 | | 0.2841 | |0 | | - p1 | | | |f1 | | 0.3183 | | 0 | | - p2 | | | |f1 | | 0.2157 | | 0 | | - p3 | | | |f1 | | 0.3183 | | 0 | -| - re | | | |f1 | | 0.4369 | |0 | +| - RE | | | |f1 | | 0.4369 | |0 | | - p1 | | | |f1 | | 0.4373 | | 0 | | - p2 | | | |f1 | | 0.4360 | | 0 | | - p3 | | | |f1 | | 0.4373 | | 0 | diff --git a/csv_files/outputs/google__gemma-3-27b-it__sk__10shot.txt b/csv_files/outputs/google__gemma-3-27b-it__sk__10shot.txt index fbb70a69ac24c59928a6403337fe39bb680e3e3c..53cb93e5f16fdc5e547385866930d8dafa6007ab 100644 --- a/csv_files/outputs/google__gemma-3-27b-it__sk__10shot.txt +++ b/csv_files/outputs/google__gemma-3-27b-it__sk__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=google/gemma-3-27b-it ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.6786 | |0 | +| - NER | | | |f1 | | 0.6786 | |0 | | - p1 | | | |f1 | | 0.6737 | | 0 | | - p2 | | | |f1 | | 0.6885 | | 0 | | - p3 | | | |f1 | | 0.6737 | | 0 | -| - re | | | |f1 | | 0.5091 | |0 | +| - RE | | | |f1 | | 0.5091 | |0 | | - p1 | | | |f1 | | 0.5121 | | 0 | | - p2 | | | |f1 | | 0.5061 | | 0 | diff --git a/csv_files/outputs/google__gemma-3-27b-it__sl__0shot.txt b/csv_files/outputs/google__gemma-3-27b-it__sl__0shot.txt index c5373e7bf56c7d6beb16eb1374952f5e2c4b6499..39bd48a7d0643c98d4e640b58b7343ee908f2d64 100644 --- a/csv_files/outputs/google__gemma-3-27b-it__sl__0shot.txt +++ b/csv_files/outputs/google__gemma-3-27b-it__sl__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=google/gemma-3-27b-it ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.4508 | |0 | +| - NER | | | |f1 | | 0.4508 | |0 | | - p1 | | | |f1 | | 0.4370 | | 0 | | - p2 | | | |f1 | | 0.4783 | | 0 | | - p3 | | | |f1 | | 0.4370 | | 0 | -| - re | | | |f1 | | 0.4301 | |0 | +| - RE | | | |f1 | | 0.4301 | |0 | | - p1 | | | |f1 | | 0.4255 | | 0 | | - p2 | | | |f1 | | 0.4391 | | 0 | | - p3 | | | |f1 | | 0.4255 | | 0 | diff --git a/csv_files/outputs/google__gemma-3-27b-it__sl__10shot.txt b/csv_files/outputs/google__gemma-3-27b-it__sl__10shot.txt index 115771abd5af83727d0b2fe790099678b144b94e..5f8181907d3a7905338e8c0ad0828529f0ff2547 100644 --- a/csv_files/outputs/google__gemma-3-27b-it__sl__10shot.txt +++ b/csv_files/outputs/google__gemma-3-27b-it__sl__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=google/gemma-3-27b-it ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.6806 | |0 | +| - NER | | | |f1 | | 0.6806 | |0 | | - p1 | | | |f1 | | 0.6750 | | 0 | | - p2 | | | |f1 | | 0.6918 | | 0 | | - p3 | | | |f1 | | 0.6750 | | 0 | -| - re | | | |f1 | | 0.4926 | |0 | +| - RE | | | |f1 | | 0.4926 | |0 | | - p1 | | | |f1 | | 0.5149 | | 0 | | - p2 | | | |f1 | | 0.4703 | | 0 | diff --git a/csv_files/outputs/google__medgemma-27b-text-it__en__0shot.txt b/csv_files/outputs/google__medgemma-27b-text-it__en__0shot.txt index 1b2577292e61c9a10baa8c2540fd0a459d8c6329..15bfbd55479583afff9de0e140bb5e0cd5970dd2 100644 --- a/csv_files/outputs/google__medgemma-27b-text-it__en__0shot.txt +++ b/csv_files/outputs/google__medgemma-27b-text-it__en__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=google/medgemma-27b-text-it ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.5011 | |0 | +| - NER | | | |f1 | | 0.5011 | |0 | | - p1 | | | |f1 | | 0.3842 | | 0 | | - p2 | | | |f1 | | 0.6035 | | 0 | | - p3 | | | |f1 | | 0.5156 | | 0 | -| - re | | | |f1 | | 0.4681 | |0 | +| - RE | | | |f1 | | 0.4681 | |0 | | - p1 | | | |f1 | | 0.4836 | | 0 | | - p2 | | | |f1 | | 0.4763 | | 0 | | - p3 | | | |f1 | | 0.4443 | | 0 | diff --git a/csv_files/outputs/google__medgemma-27b-text-it__en__10shot.txt b/csv_files/outputs/google__medgemma-27b-text-it__en__10shot.txt index 7623ca72ca820866eb81231f86b3d548626a8d19..2726400de0d4cf107d5b71b31accc1dbd0d13faa 100644 --- a/csv_files/outputs/google__medgemma-27b-text-it__en__10shot.txt +++ b/csv_files/outputs/google__medgemma-27b-text-it__en__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=google/medgemma-27b-text-it ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.6324 | |0 | +| - NER | | | |f1 | | 0.6324 | |0 | | - p1 | | | |f1 | | 0.6355 | | 0 | | - p2 | | | |f1 | | 0.6161 | | 0 | | - p3 | | | |f1 | | 0.6455 | | 0 | -| - re | | | |f1 | | 0.5528 | |0 | +| - RE | | | |f1 | | 0.5528 | |0 | | - p1 | | | |f1 | | 0.5562 | | 0 | | - p2 | | | |f1 | | 0.5494 | | 0 | diff --git a/csv_files/outputs/google__medgemma-27b-text-it__gr__0shot.txt b/csv_files/outputs/google__medgemma-27b-text-it__gr__0shot.txt index 72927e1065723bce9e442c8bb5d582ff904d0b5d..d065c4984ef73926a5399a10a41f28371f93fc00 100644 --- a/csv_files/outputs/google__medgemma-27b-text-it__gr__0shot.txt +++ b/csv_files/outputs/google__medgemma-27b-text-it__gr__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=google/medgemma-27b-text-it ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.5585 | |0 | +| - NER | | | |f1 | | 0.5585 | |0 | | - p1 | | | |f1 | | 0.5314 | | 0 | | - p2 | | | |f1 | | 0.6126 | | 0 | | - p3 | | | |f1 | | 0.5314 | | 0 | -| - re | | | |f1 | | 0.4199 | |0 | +| - RE | | | |f1 | | 0.4199 | |0 | | - p1 | | | |f1 | | 0.4069 | | 0 | | - p2 | | | |f1 | | 0.4332 | | 0 | | - p3 | | | |f1 | | 0.4197 | | 0 | diff --git a/csv_files/outputs/google__medgemma-27b-text-it__gr__10shot.txt b/csv_files/outputs/google__medgemma-27b-text-it__gr__10shot.txt index 6692e6a059fce094e12834da11ea94e21e453ead..80628c6127c1c44d5afd4041186db642fd700903 100644 --- a/csv_files/outputs/google__medgemma-27b-text-it__gr__10shot.txt +++ b/csv_files/outputs/google__medgemma-27b-text-it__gr__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=google/medgemma-27b-text-it ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.6839 | |0 | +| - NER | | | |f1 | | 0.6839 | |0 | | - p1 | | | |f1 | | 0.6836 | | 0 | | - p2 | | | |f1 | | 0.6846 | | 0 | | - p3 | | | |f1 | | 0.6836 | | 0 | -| - re | | | |f1 | | 0.5629 | |0 | +| - RE | | | |f1 | | 0.5629 | |0 | | - p1 | | | |f1 | | 0.5392 | | 0 | | - p2 | | | |f1 | | 0.5867 | | 0 | diff --git a/csv_files/outputs/google__medgemma-27b-text-it__it__0shot.txt b/csv_files/outputs/google__medgemma-27b-text-it__it__0shot.txt index 5717be3b30aac245a3a2a71d19b763a9420bd321..f4af53b4a7ac4e873081dbac1012b7e5319e4714 100644 --- a/csv_files/outputs/google__medgemma-27b-text-it__it__0shot.txt +++ b/csv_files/outputs/google__medgemma-27b-text-it__it__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=google/medgemma-27b-text-it ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.5351 | |0 | +| - NER | | | |f1 | | 0.5351 | |0 | | - p1 | | | |f1 | | 0.4261 | | 0 | | - p2 | | | |f1 | | 0.6212 | | 0 | | - p3 | | | |f1 | | 0.5582 | | 0 | -| - re | | | |f1 | | 0.4521 | |0 | +| - RE | | | |f1 | | 0.4521 | |0 | | - p1 | | | |f1 | | 0.4042 | | 0 | | - p2 | | | |f1 | | 0.4916 | | 0 | | - p3 | | | |f1 | | 0.4604 | | 0 | diff --git a/csv_files/outputs/google__medgemma-27b-text-it__it__10shot.txt b/csv_files/outputs/google__medgemma-27b-text-it__it__10shot.txt index f97518ce47c0c838a28aaedac0ae202b9f93d543..0c1913d2e7a4604f2927eecbe6068fbd0bd705c0 100644 --- a/csv_files/outputs/google__medgemma-27b-text-it__it__10shot.txt +++ b/csv_files/outputs/google__medgemma-27b-text-it__it__10shot.txt @@ -1,9 +1,9 @@ hf (pretrained=google/medgemma-27b-text-it ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.7133 | |0 | +| - NER | | | |f1 | | 0.7133 | |0 | | - p1 | | | |f1 | | 0.7262 | | 0 | | - p2 | | | |f1 | | 0.7005 | | 0 | -| - re | | | |f1 | | 0.6077 | |0 | +| - RE | | | |f1 | | 0.6077 | |0 | | - p1 | | | |f1 | | 0.5919 | | 0 | | - p2 | | | |f1 | | 0.6235 | | 0 | diff --git a/csv_files/outputs/google__medgemma-27b-text-it__pl__0shot.txt b/csv_files/outputs/google__medgemma-27b-text-it__pl__0shot.txt index 96a3e0f389382f42c12871e3aaec5214e7b81ca6..f9eba07f4234c3cc6cc8a0f05a5cd8f0cd620ac8 100644 --- a/csv_files/outputs/google__medgemma-27b-text-it__pl__0shot.txt +++ b/csv_files/outputs/google__medgemma-27b-text-it__pl__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=google/medgemma-27b-text-it ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.4245 | |0 | +| - NER | | | |f1 | | 0.4245 | |0 | | - p1 | | | |f1 | | 0.4216 | | 0 | | - p2 | | | |f1 | | 0.4303 | | 0 | | - p3 | | | |f1 | | 0.4216 | | 0 | -| - re | | | |f1 | | 0.4332 | |0 | +| - RE | | | |f1 | | 0.4332 | |0 | | - p1 | | | |f1 | | 0.4325 | | 0 | | - p2 | | | |f1 | | 0.4424 | | 0 | | - p3 | | | |f1 | | 0.4246 | | 0 | diff --git a/csv_files/outputs/google__medgemma-27b-text-it__pl__10shot.txt b/csv_files/outputs/google__medgemma-27b-text-it__pl__10shot.txt index 841307e4d812da81a7fbca9681489aa1dd6b9ffd..010a5ff0b33d4b65dd13caa21d97532e037456b6 100644 --- a/csv_files/outputs/google__medgemma-27b-text-it__pl__10shot.txt +++ b/csv_files/outputs/google__medgemma-27b-text-it__pl__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=google/medgemma-27b-text-it ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.6791 | |0 | +| - NER | | | |f1 | | 0.6791 | |0 | | - p1 | | | |f1 | | 0.6829 | | 0 | | - p2 | | | |f1 | | 0.6715 | | 0 | | - p3 | | | |f1 | | 0.6829 | | 0 | -| - re | | | |f1 | | 0.6036 | |0 | +| - RE | | | |f1 | | 0.6036 | |0 | | - p1 | | | |f1 | | 0.5940 | | 0 | | - p2 | | | |f1 | | 0.6133 | | 0 | diff --git a/csv_files/outputs/google__medgemma-27b-text-it__sk__0shot.txt b/csv_files/outputs/google__medgemma-27b-text-it__sk__0shot.txt index 3a68cf5152499faafd28f303a0956f103869d574..bd8b98a582ba732f34685230d5c2af7c07ed3a59 100644 --- a/csv_files/outputs/google__medgemma-27b-text-it__sk__0shot.txt +++ b/csv_files/outputs/google__medgemma-27b-text-it__sk__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=google/medgemma-27b-text-it ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.2336 | |0 | +| - NER | | | |f1 | | 0.2336 | |0 | | - p1 | | | |f1 | | 0.2971 | | 0 | | - p2 | | | |f1 | | 0.1066 | | 0 | | - p3 | | | |f1 | | 0.2971 | | 0 | -| - re | | | |f1 | | 0.4440 | |0 | +| - RE | | | |f1 | | 0.4440 | |0 | | - p1 | | | |f1 | | 0.4395 | | 0 | | - p2 | | | |f1 | | 0.4531 | | 0 | | - p3 | | | |f1 | | 0.4395 | | 0 | diff --git a/csv_files/outputs/google__medgemma-27b-text-it__sk__10shot.txt b/csv_files/outputs/google__medgemma-27b-text-it__sk__10shot.txt index db98f396eb2efd3f8a738328dccd5f86e85a761d..b922bfdfb8933cb22685f49680d32d1c37a1bcc3 100644 --- a/csv_files/outputs/google__medgemma-27b-text-it__sk__10shot.txt +++ b/csv_files/outputs/google__medgemma-27b-text-it__sk__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=google/medgemma-27b-text-it ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.7137 | |0 | +| - NER | | | |f1 | | 0.7137 | |0 | | - p1 | | | |f1 | | 0.7143 | | 0 | | - p2 | | | |f1 | | 0.7127 | | 0 | | - p3 | | | |f1 | | 0.7143 | | 0 | -| - re | | | |f1 | | 0.5149 | |0 | +| - RE | | | |f1 | | 0.5149 | |0 | | - p1 | | | |f1 | | 0.5111 | | 0 | | - p2 | | | |f1 | | 0.5188 | | 0 | diff --git a/csv_files/outputs/google__medgemma-27b-text-it__sl__0shot.txt b/csv_files/outputs/google__medgemma-27b-text-it__sl__0shot.txt index 763eee8744af6f1d60a97ef9a00cbb098a837cf5..2c70cd19fab747d42922e7a5ecdf7736a81004f9 100644 --- a/csv_files/outputs/google__medgemma-27b-text-it__sl__0shot.txt +++ b/csv_files/outputs/google__medgemma-27b-text-it__sl__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=google/medgemma-27b-text-it ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.4863 | |0 | +| - NER | | | |f1 | | 0.4863 | |0 | | - p1 | | | |f1 | | 0.4675 | | 0 | | - p2 | | | |f1 | | 0.5238 | | 0 | | - p3 | | | |f1 | | 0.4675 | | 0 | -| - re | | | |f1 | | 0.4201 | |0 | +| - RE | | | |f1 | | 0.4201 | |0 | | - p1 | | | |f1 | | 0.4182 | | 0 | | - p2 | | | |f1 | | 0.4239 | | 0 | | - p3 | | | |f1 | | 0.4182 | | 0 | diff --git a/csv_files/outputs/google__medgemma-27b-text-it__sl__10shot.txt b/csv_files/outputs/google__medgemma-27b-text-it__sl__10shot.txt index 8d78f14f5a8ee72f5800cb860ae7867ef2121ce5..0d4a308afc878743ade464fb5bf07b97afd7eb08 100644 --- a/csv_files/outputs/google__medgemma-27b-text-it__sl__10shot.txt +++ b/csv_files/outputs/google__medgemma-27b-text-it__sl__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=google/medgemma-27b-text-it ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.6887 | |0 | +| - NER | | | |f1 | | 0.6887 | |0 | | - p1 | | | |f1 | | 0.6947 | | 0 | | - p2 | | | |f1 | | 0.6765 | | 0 | | - p3 | | | |f1 | | 0.6947 | | 0 | -| - re | | | |f1 | | 0.5457 | |0 | +| - RE | | | |f1 | | 0.5457 | |0 | | - p1 | | | |f1 | | 0.5323 | | 0 | | - p2 | | | |f1 | | 0.5590 | | 0 | diff --git a/csv_files/outputs/google__medgemma-4b-it__en__0shot.txt b/csv_files/outputs/google__medgemma-4b-it__en__0shot.txt index 2c6bf6c8db8f6569c5b34f55ef22ac9906fb386f..7d18ba6fc1bdc423039c71bd42a10e8a09e997db 100644 --- a/csv_files/outputs/google__medgemma-4b-it__en__0shot.txt +++ b/csv_files/outputs/google__medgemma-4b-it__en__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=google/medgemma-4b-it ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.2625 | |0 | +| - NER | | | |f1 | | 0.2625 | |0 | | - p1 | | | |f1 | | 0.2635 | | 0 | | - p2 | | | |f1 | | 0.2503 | | 0 | | - p3 | | | |f1 | | 0.2737 | | 0 | -| - re | | | |f1 | | 0.2851 | |0 | +| - RE | | | |f1 | | 0.2851 | |0 | | - p1 | | | |f1 | | 0.2095 | | 0 | | - p2 | | | |f1 | | 0.3257 | | 0 | | - p3 | | | |f1 | | 0.3203 | | 0 | diff --git a/csv_files/outputs/google__medgemma-4b-it__en__10shot.txt b/csv_files/outputs/google__medgemma-4b-it__en__10shot.txt index 7eb28cd4a6646d5d77b90a4ccdc39516251d0583..180216d0234f301db7e5a762d9f6a7e37cd94de1 100644 --- a/csv_files/outputs/google__medgemma-4b-it__en__10shot.txt +++ b/csv_files/outputs/google__medgemma-4b-it__en__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=google/medgemma-4b-it ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.4930 | |0 | +| - NER | | | |f1 | | 0.4930 | |0 | | - p1 | | | |f1 | | 0.4833 | | 0 | | - p2 | | | |f1 | | 0.5005 | | 0 | | - p3 | | | |f1 | | 0.4951 | | 0 | -| - re | | | |f1 | | 0.1101 | |0 | +| - RE | | | |f1 | | 0.1101 | |0 | | - p1 | | | |f1 | | 0.0964 | | 0 | | - p2 | | | |f1 | | 0.1237 | | 0 | diff --git a/csv_files/outputs/google__medgemma-4b-it__gr__0shot.txt b/csv_files/outputs/google__medgemma-4b-it__gr__0shot.txt index 88b8e821fdc2e1a20bcb011ab95ccf2024f44b33..d0f048d8fb01e8ed8352829fa0179010381f66ca 100644 --- a/csv_files/outputs/google__medgemma-4b-it__gr__0shot.txt +++ b/csv_files/outputs/google__medgemma-4b-it__gr__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=google/medgemma-4b-it ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.2688 | |0 | +| - NER | | | |f1 | | 0.2688 | |0 | | - p1 | | | |f1 | | 0.2705 | | 0 | | - p2 | | | |f1 | | 0.2654 | | 0 | | - p3 | | | |f1 | | 0.2705 | | 0 | -| - re | | | |f1 | | 0.2053 | |0 | +| - RE | | | |f1 | | 0.2053 | |0 | | - p1 | | | |f1 | | 0.2381 | | 0 | | - p2 | | | |f1 | | 0.3024 | | 0 | | - p3 | | | |f1 | | 0.0754 | | 0 | diff --git a/csv_files/outputs/google__medgemma-4b-it__gr__10shot.txt b/csv_files/outputs/google__medgemma-4b-it__gr__10shot.txt index 754c292e1e0a45a63de235cd27170c12a2da7975..bebb267aed9aaf923d6e59b0a1667ba1dfc57dec 100644 --- a/csv_files/outputs/google__medgemma-4b-it__gr__10shot.txt +++ b/csv_files/outputs/google__medgemma-4b-it__gr__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=google/medgemma-4b-it ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.4953 | |0 | +| - NER | | | |f1 | | 0.4953 | |0 | | - p1 | | | |f1 | | 0.4910 | | 0 | | - p2 | | | |f1 | | 0.5039 | | 0 | | - p3 | | | |f1 | | 0.4910 | | 0 | -| - re | | | |f1 | | 0.1404 | |0 | +| - RE | | | |f1 | | 0.1404 | |0 | | - p1 | | | |f1 | | 0.1204 | | 0 | | - p2 | | | |f1 | | 0.1605 | | 0 | diff --git a/csv_files/outputs/google__medgemma-4b-it__it__0shot.txt b/csv_files/outputs/google__medgemma-4b-it__it__0shot.txt index 1146e596eccebec747d71d3d9f1b5e42d75cb535..0726976105566a084aa8c1c51c84c700da3b7752 100644 --- a/csv_files/outputs/google__medgemma-4b-it__it__0shot.txt +++ b/csv_files/outputs/google__medgemma-4b-it__it__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=google/medgemma-4b-it ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.2929 | |0 | +| - NER | | | |f1 | | 0.2929 | |0 | | - p1 | | | |f1 | | 0.3157 | | 0 | | - p2 | | | |f1 | | 0.2627 | | 0 | | - p3 | | | |f1 | | 0.3004 | | 0 | -| - re | | | |f1 | | 0.1767 | |0 | +| - RE | | | |f1 | | 0.1767 | |0 | | - p1 | | | |f1 | | 0.2154 | | 0 | | - p2 | | | |f1 | | 0.2461 | | 0 | | - p3 | | | |f1 | | 0.0688 | | 0 | diff --git a/csv_files/outputs/google__medgemma-4b-it__it__10shot.txt b/csv_files/outputs/google__medgemma-4b-it__it__10shot.txt index d07b5dd61e8606d9f7f3eda226ef534b3aee0982..6df38e34e2c0e0494740deb52f9f431147bf03aa 100644 --- a/csv_files/outputs/google__medgemma-4b-it__it__10shot.txt +++ b/csv_files/outputs/google__medgemma-4b-it__it__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=google/medgemma-4b-it ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.5454 | |0 | +| - NER | | | |f1 | | 0.5454 | |0 | | - p1 | | | |f1 | | 0.5633 | | 0 | | - p2 | | | |f1 | | 0.5377 | | 0 | | - p3 | | | |f1 | | 0.5352 | | 0 | -| - re | | | |f1 | | 0.1754 | |0 | +| - RE | | | |f1 | | 0.1754 | |0 | | - p1 | | | |f1 | | 0.1592 | | 0 | | - p2 | | | |f1 | | 0.1917 | | 0 | diff --git a/csv_files/outputs/google__medgemma-4b-it__pl__0shot.txt b/csv_files/outputs/google__medgemma-4b-it__pl__0shot.txt index a27658a2356685999114b0b67b59a745c9f24872..1da79eb1fdbb0c791458ff4a9cce9c33a7da6497 100644 --- a/csv_files/outputs/google__medgemma-4b-it__pl__0shot.txt +++ b/csv_files/outputs/google__medgemma-4b-it__pl__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=google/medgemma-4b-it ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.2231 | |0 | +| - NER | | | |f1 | | 0.2231 | |0 | | - p1 | | | |f1 | | 0.2255 | | 0 | | - p2 | | | |f1 | | 0.2183 | | 0 | | - p3 | | | |f1 | | 0.2255 | | 0 | -| - re | | | |f1 | | 0.1173 | |0 | +| - RE | | | |f1 | | 0.1173 | |0 | | - p1 | | | |f1 | | 0.1150 | | 0 | | - p2 | | | |f1 | | 0.1314 | | 0 | | - p3 | | | |f1 | | 0.1054 | | 0 | diff --git a/csv_files/outputs/google__medgemma-4b-it__pl__10shot.txt b/csv_files/outputs/google__medgemma-4b-it__pl__10shot.txt index 00950db0ea757d5870850f97f2086d3650e46db0..117950740427fbfafee82d61b9becd177292a9ad 100644 --- a/csv_files/outputs/google__medgemma-4b-it__pl__10shot.txt +++ b/csv_files/outputs/google__medgemma-4b-it__pl__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=google/medgemma-4b-it ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.5193 | |0 | +| - NER | | | |f1 | | 0.5193 | |0 | | - p1 | | | |f1 | | 0.5186 | | 0 | | - p2 | | | |f1 | | 0.5206 | | 0 | | - p3 | | | |f1 | | 0.5186 | | 0 | -| - re | | | |f1 | | 0.1084 | |0 | +| - RE | | | |f1 | | 0.1084 | |0 | | - p1 | | | |f1 | | 0.1171 | | 0 | | - p2 | | | |f1 | | 0.0997 | | 0 | diff --git a/csv_files/outputs/google__medgemma-4b-it__sk__0shot.txt b/csv_files/outputs/google__medgemma-4b-it__sk__0shot.txt index 239962b493c557ae41d417f924fa550434337b38..1bea1720e28d395cc9d1f6ee52968a6965a98c84 100644 --- a/csv_files/outputs/google__medgemma-4b-it__sk__0shot.txt +++ b/csv_files/outputs/google__medgemma-4b-it__sk__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=google/medgemma-4b-it ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.2427 | |0 | +| - NER | | | |f1 | | 0.2427 | |0 | | - p1 | | | |f1 | | 0.2447 | | 0 | | - p2 | | | |f1 | | 0.2387 | | 0 | | - p3 | | | |f1 | | 0.2447 | | 0 | -| - re | | | |f1 | | 0.1212 | |0 | +| - RE | | | |f1 | | 0.1212 | |0 | | - p1 | | | |f1 | | 0.1119 | | 0 | | - p2 | | | |f1 | | 0.1399 | | 0 | | - p3 | | | |f1 | | 0.1119 | | 0 | diff --git a/csv_files/outputs/google__medgemma-4b-it__sk__10shot.txt b/csv_files/outputs/google__medgemma-4b-it__sk__10shot.txt index d3d195a3ff62fe98fb857bcfefa6a0131f83fcad..c4a399c079cfe7554d699384725ae9367de34a56 100644 --- a/csv_files/outputs/google__medgemma-4b-it__sk__10shot.txt +++ b/csv_files/outputs/google__medgemma-4b-it__sk__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=google/medgemma-4b-it ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.4654 | |0 | +| - NER | | | |f1 | | 0.4654 | |0 | | - p1 | | | |f1 | | 0.4756 | | 0 | | - p2 | | | |f1 | | 0.4449 | | 0 | | - p3 | | | |f1 | | 0.4756 | | 0 | -| - re | | | |f1 | | 0.1052 | |0 | +| - RE | | | |f1 | | 0.1052 | |0 | | - p1 | | | |f1 | | 0.1095 | | 0 | | - p2 | | | |f1 | | 0.1009 | | 0 | diff --git a/csv_files/outputs/google__medgemma-4b-it__sl__0shot.txt b/csv_files/outputs/google__medgemma-4b-it__sl__0shot.txt index 3a697f8a782fb9367aaef7232d34dddd2d425cf3..56dbab87e4f7fed3a562f04e90d5511d788bdc34 100644 --- a/csv_files/outputs/google__medgemma-4b-it__sl__0shot.txt +++ b/csv_files/outputs/google__medgemma-4b-it__sl__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=google/medgemma-4b-it ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.2569 | |0 | +| - NER | | | |f1 | | 0.2569 | |0 | | - p1 | | | |f1 | | 0.2574 | | 0 | | - p2 | | | |f1 | | 0.2558 | | 0 | | - p3 | | | |f1 | | 0.2574 | | 0 | -| - re | | | |f1 | | 0.1012 | |0 | +| - RE | | | |f1 | | 0.1012 | |0 | | - p1 | | | |f1 | | 0.0973 | | 0 | | - p2 | | | |f1 | | 0.1089 | | 0 | | - p3 | | | |f1 | | 0.0973 | | 0 | diff --git a/csv_files/outputs/google__medgemma-4b-it__sl__10shot.txt b/csv_files/outputs/google__medgemma-4b-it__sl__10shot.txt index e1f5609bbc5bd493634499b48a23116288685483..8df050cf3c3f47a57abad65d937574315911ddf4 100644 --- a/csv_files/outputs/google__medgemma-4b-it__sl__10shot.txt +++ b/csv_files/outputs/google__medgemma-4b-it__sl__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=google/medgemma-4b-it ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.5063 | |0 | +| - NER | | | |f1 | | 0.5063 | |0 | | - p1 | | | |f1 | | 0.5117 | | 0 | | - p2 | | | |f1 | | 0.4955 | | 0 | | - p3 | | | |f1 | | 0.5117 | | 0 | -| - re | | | |f1 | | 0.1139 | |0 | +| - RE | | | |f1 | | 0.1139 | |0 | | - p1 | | | |f1 | | 0.1178 | | 0 | | - p2 | | | |f1 | | 0.1101 | | 0 | diff --git a/csv_files/outputs/microsoft__MediPhi-Clinical__en__0shot.txt b/csv_files/outputs/microsoft__MediPhi-Clinical__en__0shot.txt index 013cdc87b441c877106718774718193dafef8e47..76cdb91c718afaf7089efd18094132a0bf5f121a 100644 --- a/csv_files/outputs/microsoft__MediPhi-Clinical__en__0shot.txt +++ b/csv_files/outputs/microsoft__MediPhi-Clinical__en__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=microsoft/MediPhi-Clinical ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.2786 | |0 | +| - NER | | | |f1 | | 0.2786 | |0 | | - p1 | | | |f1 | | 0.2502 | | 0 | | - p2 | | | |f1 | | 0.3089 | | 0 | | - p3 | | | |f1 | | 0.2768 | | 0 | -| - re | | | |f1 | | 0.3248 | |0 | +| - RE | | | |f1 | | 0.3248 | |0 | | - p1 | | | |f1 | | 0.2274 | | 0 | | - p2 | | | |f1 | | 0.3929 | | 0 | | - p3 | | | |f1 | | 0.3542 | | 0 | diff --git a/csv_files/outputs/microsoft__MediPhi-Clinical__en__10shot.txt b/csv_files/outputs/microsoft__MediPhi-Clinical__en__10shot.txt index 08a27fe55fd3552bcd5cab21470309efc0c83420..c216f0690aa0227aba457157c2a34bef6d921ac4 100644 --- a/csv_files/outputs/microsoft__MediPhi-Clinical__en__10shot.txt +++ b/csv_files/outputs/microsoft__MediPhi-Clinical__en__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=microsoft/MediPhi-Clinical ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.5008 | |0 | +| - NER | | | |f1 | | 0.5008 | |0 | | - p1 | | | |f1 | | 0.5009 | | 0 | | - p2 | | | |f1 | | 0.4966 | | 0 | | - p3 | | | |f1 | | 0.5049 | | 0 | -| - re | | | |f1 | | 0.1135 | |0 | +| - RE | | | |f1 | | 0.1135 | |0 | | - p1 | | | |f1 | | 0.1175 | | 0 | | - p2 | | | |f1 | | 0.1095 | | 0 | diff --git a/csv_files/outputs/microsoft__MediPhi-Clinical__gr__0shot.txt b/csv_files/outputs/microsoft__MediPhi-Clinical__gr__0shot.txt index 31ecf07da62ee131ebf0e5e5ebff458a367e510e..a0c5c0a5a00e2cdf36cc9f66ad99c89cd41760ac 100644 --- a/csv_files/outputs/microsoft__MediPhi-Clinical__gr__0shot.txt +++ b/csv_files/outputs/microsoft__MediPhi-Clinical__gr__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=microsoft/MediPhi-Clinical ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.1717 | |0 | +| - NER | | | |f1 | | 0.1717 | |0 | | - p1 | | | |f1 | | 0.1641 | | 0 | | - p2 | | | |f1 | | 0.1869 | | 0 | | - p3 | | | |f1 | | 0.1641 | | 0 | -| - re | | | |f1 | | 0.0977 | |0 | +| - RE | | | |f1 | | 0.0977 | |0 | | - p1 | | | |f1 | | 0.0736 | | 0 | | - p2 | | | |f1 | | 0.0778 | | 0 | | - p3 | | | |f1 | | 0.1418 | | 0 | diff --git a/csv_files/outputs/microsoft__MediPhi-Clinical__gr__10shot.txt b/csv_files/outputs/microsoft__MediPhi-Clinical__gr__10shot.txt index 0e67d7603de9b38880b82f8683d0585a4840fa8f..f85b5b01881d041a71a80c22c055b2f4f726d17b 100644 --- a/csv_files/outputs/microsoft__MediPhi-Clinical__gr__10shot.txt +++ b/csv_files/outputs/microsoft__MediPhi-Clinical__gr__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=microsoft/MediPhi-Clinical ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.3384 | |0 | +| - NER | | | |f1 | | 0.3384 | |0 | | - p1 | | | |f1 | | 0.3375 | | 0 | | - p2 | | | |f1 | | 0.3403 | | 0 | | - p3 | | | |f1 | | 0.3375 | | 0 | -| - re | | | |f1 | | 0.0554 | |0 | +| - RE | | | |f1 | | 0.0554 | |0 | | - p1 | | | |f1 | | 0.0427 | | 0 | | - p2 | | | |f1 | | 0.0681 | | 0 | diff --git a/csv_files/outputs/microsoft__MediPhi-Clinical__it__0shot.txt b/csv_files/outputs/microsoft__MediPhi-Clinical__it__0shot.txt index 7e91df597747586979868f6704d661fa4003ed78..2179db033abe54c1a3211347f00f4fb25ebca628 100644 --- a/csv_files/outputs/microsoft__MediPhi-Clinical__it__0shot.txt +++ b/csv_files/outputs/microsoft__MediPhi-Clinical__it__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=microsoft/MediPhi-Clinical ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.3307 | |0 | +| - NER | | | |f1 | | 0.3307 | |0 | | - p1 | | | |f1 | | 0.3397 | | 0 | | - p2 | | | |f1 | | 0.3300 | | 0 | | - p3 | | | |f1 | | 0.3226 | | 0 | -| - re | | | |f1 | | 0.0792 | |0 | +| - RE | | | |f1 | | 0.0792 | |0 | | - p1 | | | |f1 | | 0.1489 | | 0 | | - p2 | | | |f1 | | 0.0736 | | 0 | | - p3 | | | |f1 | | 0.0149 | | 0 | diff --git a/csv_files/outputs/microsoft__MediPhi-Clinical__it__10shot.txt b/csv_files/outputs/microsoft__MediPhi-Clinical__it__10shot.txt index 121f203a01339f5e925b9737f899607005ea9600..6e7923466ffd7382d6490aa51f180f788ee9f254 100644 --- a/csv_files/outputs/microsoft__MediPhi-Clinical__it__10shot.txt +++ b/csv_files/outputs/microsoft__MediPhi-Clinical__it__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=microsoft/MediPhi-Clinical ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.5257 | |0 | +| - NER | | | |f1 | | 0.5257 | |0 | | - p1 | | | |f1 | | 0.5195 | | 0 | | - p2 | | | |f1 | | 0.5301 | | 0 | | - p3 | | | |f1 | | 0.5275 | | 0 | -| - re | | | |f1 | | 0.1537 | |0 | +| - RE | | | |f1 | | 0.1537 | |0 | | - p1 | | | |f1 | | 0.2114 | | 0 | | - p2 | | | |f1 | | 0.0961 | | 0 | diff --git a/csv_files/outputs/microsoft__MediPhi-Clinical__pl__0shot.txt b/csv_files/outputs/microsoft__MediPhi-Clinical__pl__0shot.txt index 422658378f9a5071d891cc05d71f0b63c57792a5..398a394b401f757945eec334c5bd3723685aa80b 100644 --- a/csv_files/outputs/microsoft__MediPhi-Clinical__pl__0shot.txt +++ b/csv_files/outputs/microsoft__MediPhi-Clinical__pl__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=microsoft/MediPhi-Clinical ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.2831 | |0 | +| - NER | | | |f1 | | 0.2831 | |0 | | - p1 | | | |f1 | | 0.2815 | | 0 | | - p2 | | | |f1 | | 0.2861 | | 0 | | - p3 | | | |f1 | | 0.2815 | | 0 | -| - re | | | |f1 | | 0.2693 | |0 | +| - RE | | | |f1 | | 0.2693 | |0 | | - p1 | | | |f1 | | 0.2109 | | 0 | | - p2 | | | |f1 | | 0.2908 | | 0 | | - p3 | | | |f1 | | 0.3061 | | 0 | diff --git a/csv_files/outputs/microsoft__MediPhi-Clinical__pl__10shot.txt b/csv_files/outputs/microsoft__MediPhi-Clinical__pl__10shot.txt index f4d12a5ca302c46250b4364b11751aa53774d14c..cd0993715e778d635e21a2d48302a68e2d8fff45 100644 --- a/csv_files/outputs/microsoft__MediPhi-Clinical__pl__10shot.txt +++ b/csv_files/outputs/microsoft__MediPhi-Clinical__pl__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=microsoft/MediPhi-Clinical ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.3986 | |0 | +| - NER | | | |f1 | | 0.3986 | |0 | | - p1 | | | |f1 | | 0.3913 | | 0 | | - p2 | | | |f1 | | 0.4132 | | 0 | | - p3 | | | |f1 | | 0.3913 | | 0 | -| - re | | | |f1 | | 0.1231 | |0 | +| - RE | | | |f1 | | 0.1231 | |0 | | - p1 | | | |f1 | | 0.1255 | | 0 | | - p2 | | | |f1 | | 0.1207 | | 0 | diff --git a/csv_files/outputs/microsoft__MediPhi-Clinical__sk__0shot.txt b/csv_files/outputs/microsoft__MediPhi-Clinical__sk__0shot.txt index 5b9076bc8bc73843bc160a1befda68db75117943..9aaca4c790d98eb11b6ab172e1b2f9ba297b0a56 100644 --- a/csv_files/outputs/microsoft__MediPhi-Clinical__sk__0shot.txt +++ b/csv_files/outputs/microsoft__MediPhi-Clinical__sk__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=microsoft/MediPhi-Clinical ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.2710 | |0 | +| - NER | | | |f1 | | 0.2710 | |0 | | - p1 | | | |f1 | | 0.2571 | | 0 | | - p2 | | | |f1 | | 0.2987 | | 0 | | - p3 | | | |f1 | | 0.2571 | | 0 | -| - re | | | |f1 | | 0.1062 | |0 | +| - RE | | | |f1 | | 0.1062 | |0 | | - p1 | | | |f1 | | 0.1554 | | 0 | | - p2 | | | |f1 | | 0.0077 | | 0 | | - p3 | | | |f1 | | 0.1554 | | 0 | diff --git a/csv_files/outputs/microsoft__MediPhi-Clinical__sk__10shot.txt b/csv_files/outputs/microsoft__MediPhi-Clinical__sk__10shot.txt index b57188ffe0c2040715c0e6497ab2516ac8670233..8d86fca74d2ca6322c59aba663d1d8f45ed9574c 100644 --- a/csv_files/outputs/microsoft__MediPhi-Clinical__sk__10shot.txt +++ b/csv_files/outputs/microsoft__MediPhi-Clinical__sk__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=microsoft/MediPhi-Clinical ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.4025 | |0 | +| - NER | | | |f1 | | 0.4025 | |0 | | - p1 | | | |f1 | | 0.4106 | | 0 | | - p2 | | | |f1 | | 0.3861 | | 0 | | - p3 | | | |f1 | | 0.4106 | | 0 | -| - re | | | |f1 | | 0.0557 | |0 | +| - RE | | | |f1 | | 0.0557 | |0 | | - p1 | | | |f1 | | 0.0509 | | 0 | | - p2 | | | |f1 | | 0.0606 | | 0 | diff --git a/csv_files/outputs/microsoft__MediPhi-Clinical__sl__0shot.txt b/csv_files/outputs/microsoft__MediPhi-Clinical__sl__0shot.txt index d887894954db8e785d54f3102955aca48e0af8d0..cd2d143234ccb78abac42a387aa128d3314e802f 100644 --- a/csv_files/outputs/microsoft__MediPhi-Clinical__sl__0shot.txt +++ b/csv_files/outputs/microsoft__MediPhi-Clinical__sl__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=microsoft/MediPhi-Clinical ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.2892 | |0 | +| - NER | | | |f1 | | 0.2892 | |0 | | - p1 | | | |f1 | | 0.2998 | | 0 | | - p2 | | | |f1 | | 0.2680 | | 0 | | - p3 | | | |f1 | | 0.2998 | | 0 | -| - re | | | |f1 | | 0.0304 | |0 | +| - RE | | | |f1 | | 0.0304 | |0 | | - p1 | | | |f1 | | 0.0395 | | 0 | | - p2 | | | |f1 | | 0.0121 | | 0 | | - p3 | | | |f1 | | 0.0395 | | 0 | diff --git a/csv_files/outputs/microsoft__MediPhi-Clinical__sl__10shot.txt b/csv_files/outputs/microsoft__MediPhi-Clinical__sl__10shot.txt index a2b1dd7d9912197af51948b750974c585ef723b4..e5b15c80f43fae57630478f1bf1b89e3c6282eb5 100644 --- a/csv_files/outputs/microsoft__MediPhi-Clinical__sl__10shot.txt +++ b/csv_files/outputs/microsoft__MediPhi-Clinical__sl__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=microsoft/MediPhi-Clinical ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.4021 | |0 | +| - NER | | | |f1 | | 0.4021 | |0 | | - p1 | | | |f1 | | 0.4036 | | 0 | | - p2 | | | |f1 | | 0.3990 | | 0 | | - p3 | | | |f1 | | 0.4036 | | 0 | -| - re | | | |f1 | | 0.0752 | |0 | +| - RE | | | |f1 | | 0.0752 | |0 | | - p1 | | | |f1 | | 0.0829 | | 0 | | - p2 | | | |f1 | | 0.0674 | | 0 | diff --git a/csv_files/outputs/microsoft__MediPhi-Instruct__en__0shot.txt b/csv_files/outputs/microsoft__MediPhi-Instruct__en__0shot.txt index b0a1fea4cfc488be5c9595119965c6b6f0736525..d109d8f49c2b55f83170cc9751275a72ff6e1387 100644 --- a/csv_files/outputs/microsoft__MediPhi-Instruct__en__0shot.txt +++ b/csv_files/outputs/microsoft__MediPhi-Instruct__en__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=microsoft/MediPhi-Instruct ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.1598 | |0 | +| - NER | | | |f1 | | 0.1598 | |0 | | - p1 | | | |f1 | | 0.0761 | | 0 | | - p2 | | | |f1 | | 0.2410 | | 0 | | - p3 | | | |f1 | | 0.1625 | | 0 | -| - re | | | |f1 | | 0.2982 | |0 | +| - RE | | | |f1 | | 0.2982 | |0 | | - p1 | | | |f1 | | 0.1135 | | 0 | | - p2 | | | |f1 | | 0.4006 | | 0 | | - p3 | | | |f1 | | 0.3804 | | 0 | diff --git a/csv_files/outputs/microsoft__MediPhi-Instruct__en__10shot.txt b/csv_files/outputs/microsoft__MediPhi-Instruct__en__10shot.txt index 75d3fa27c7ce99c685520899f83d5c67397a8c6c..a20429567b560cbd1749d067fa745eba84f3e883 100644 --- a/csv_files/outputs/microsoft__MediPhi-Instruct__en__10shot.txt +++ b/csv_files/outputs/microsoft__MediPhi-Instruct__en__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=microsoft/MediPhi-Instruct ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.5216 | |0 | +| - NER | | | |f1 | | 0.5216 | |0 | | - p1 | | | |f1 | | 0.5357 | | 0 | | - p2 | | | |f1 | | 0.5227 | | 0 | | - p3 | | | |f1 | | 0.5063 | | 0 | -| - re | | | |f1 | | 0.1660 | |0 | +| - RE | | | |f1 | | 0.1660 | |0 | | - p1 | | | |f1 | | 0.1432 | | 0 | | - p2 | | | |f1 | | 0.1888 | | 0 | diff --git a/csv_files/outputs/microsoft__MediPhi-Instruct__gr__0shot.txt b/csv_files/outputs/microsoft__MediPhi-Instruct__gr__0shot.txt index 23f202e0c23d9690d048b28b3974736f3a0b7bde..033006f71175ad0e7ba4e4f9b2b91bd4b604c058 100644 --- a/csv_files/outputs/microsoft__MediPhi-Instruct__gr__0shot.txt +++ b/csv_files/outputs/microsoft__MediPhi-Instruct__gr__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=microsoft/MediPhi-Instruct ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.1159 | |0 | +| - NER | | | |f1 | | 0.1159 | |0 | | - p1 | | | |f1 | | 0.1294 | | 0 | | - p2 | | | |f1 | | 0.0890 | | 0 | | - p3 | | | |f1 | | 0.1294 | | 0 | -| - re | | | |f1 | | 0.1184 | |0 | +| - RE | | | |f1 | | 0.1184 | |0 | | - p1 | | | |f1 | | 0.0962 | | 0 | | - p2 | | | |f1 | | 0.0673 | | 0 | | - p3 | | | |f1 | | 0.1916 | | 0 | diff --git a/csv_files/outputs/microsoft__MediPhi-Instruct__gr__10shot.txt b/csv_files/outputs/microsoft__MediPhi-Instruct__gr__10shot.txt index 9e2ead33340d5e2a561d0e7037780afe79f6b98e..db8d90da14db73ebb33902ddd73b9c6076443499 100644 --- a/csv_files/outputs/microsoft__MediPhi-Instruct__gr__10shot.txt +++ b/csv_files/outputs/microsoft__MediPhi-Instruct__gr__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=microsoft/MediPhi-Instruct ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.2881 | |0 | +| - NER | | | |f1 | | 0.2881 | |0 | | - p1 | | | |f1 | | 0.2822 | | 0 | | - p2 | | | |f1 | | 0.2999 | | 0 | | - p3 | | | |f1 | | 0.2822 | | 0 | -| - re | | | |f1 | | 0.0625 | |0 | +| - RE | | | |f1 | | 0.0625 | |0 | | - p1 | | | |f1 | | 0.0576 | | 0 | | - p2 | | | |f1 | | 0.0674 | | 0 | diff --git a/csv_files/outputs/microsoft__MediPhi-Instruct__it__0shot.txt b/csv_files/outputs/microsoft__MediPhi-Instruct__it__0shot.txt index ca19f82340898a6e6cee1bcb3f62d2ab4307d0a8..dd0e6008d2a3198f8ea3a505176acf5dd7c54ac8 100644 --- a/csv_files/outputs/microsoft__MediPhi-Instruct__it__0shot.txt +++ b/csv_files/outputs/microsoft__MediPhi-Instruct__it__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=microsoft/MediPhi-Instruct ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.2023 | |0 | +| - NER | | | |f1 | | 0.2023 | |0 | | - p1 | | | |f1 | | 0.0867 | | 0 | | - p2 | | | |f1 | | 0.2484 | | 0 | | - p3 | | | |f1 | | 0.2717 | | 0 | -| - re | | | |f1 | | 0.2623 | |0 | +| - RE | | | |f1 | | 0.2623 | |0 | | - p1 | | | |f1 | | 0.1712 | | 0 | | - p2 | | | |f1 | | 0.2896 | | 0 | | - p3 | | | |f1 | | 0.3261 | | 0 | diff --git a/csv_files/outputs/microsoft__MediPhi-Instruct__it__10shot.txt b/csv_files/outputs/microsoft__MediPhi-Instruct__it__10shot.txt index 87aadc06deaedb8c71f2e5ddde03e98261c851ca..01022afe783fed1ed37573dd0f37631ccc4de471 100644 --- a/csv_files/outputs/microsoft__MediPhi-Instruct__it__10shot.txt +++ b/csv_files/outputs/microsoft__MediPhi-Instruct__it__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=microsoft/MediPhi-Instruct ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.5715 | |0 | +| - NER | | | |f1 | | 0.5715 | |0 | | - p1 | | | |f1 | | 0.5729 | | 0 | | - p2 | | | |f1 | | 0.5627 | | 0 | | - p3 | | | |f1 | | 0.5790 | | 0 | -| - re | | | |f1 | | 0.2590 | |0 | +| - RE | | | |f1 | | 0.2590 | |0 | | - p1 | | | |f1 | | 0.2873 | | 0 | | - p2 | | | |f1 | | 0.2307 | | 0 | diff --git a/csv_files/outputs/microsoft__MediPhi-Instruct__pl__0shot.txt b/csv_files/outputs/microsoft__MediPhi-Instruct__pl__0shot.txt index aebf1a17c31f3208d7ad2f0dda353780d5fd624f..9c6bc50efa744a67b9f472d4fdd237432f562068 100644 --- a/csv_files/outputs/microsoft__MediPhi-Instruct__pl__0shot.txt +++ b/csv_files/outputs/microsoft__MediPhi-Instruct__pl__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=microsoft/MediPhi-Instruct ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.1567 | |0 | +| - NER | | | |f1 | | 0.1567 | |0 | | - p1 | | | |f1 | | 0.1510 | | 0 | | - p2 | | | |f1 | | 0.1680 | | 0 | | - p3 | | | |f1 | | 0.1510 | | 0 | -| - re | | | |f1 | | 0.2881 | |0 | +| - RE | | | |f1 | | 0.2881 | |0 | | - p1 | | | |f1 | | 0.2683 | | 0 | | - p2 | | | |f1 | | 0.3126 | | 0 | | - p3 | | | |f1 | | 0.2832 | | 0 | diff --git a/csv_files/outputs/microsoft__MediPhi-Instruct__pl__10shot.txt b/csv_files/outputs/microsoft__MediPhi-Instruct__pl__10shot.txt index ee60b957d0e7fb3d63ffcd076242aeb0c2e87cf9..23e823098e1230f9205e25b581ba66d1e9604b8d 100644 --- a/csv_files/outputs/microsoft__MediPhi-Instruct__pl__10shot.txt +++ b/csv_files/outputs/microsoft__MediPhi-Instruct__pl__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=microsoft/MediPhi-Instruct ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.4447 | |0 | +| - NER | | | |f1 | | 0.4447 | |0 | | - p1 | | | |f1 | | 0.4417 | | 0 | | - p2 | | | |f1 | | 0.4506 | | 0 | | - p3 | | | |f1 | | 0.4417 | | 0 | -| - re | | | |f1 | | 0.2105 | |0 | +| - RE | | | |f1 | | 0.2105 | |0 | | - p1 | | | |f1 | | 0.1525 | | 0 | | - p2 | | | |f1 | | 0.2686 | | 0 | diff --git a/csv_files/outputs/microsoft__MediPhi-Instruct__sk__0shot.txt b/csv_files/outputs/microsoft__MediPhi-Instruct__sk__0shot.txt index 5974f7286d4850f71ec33abd4a49a15c85c1d6a8..a3c42b94084e72cbff224a863d3f392fb1b26463 100644 --- a/csv_files/outputs/microsoft__MediPhi-Instruct__sk__0shot.txt +++ b/csv_files/outputs/microsoft__MediPhi-Instruct__sk__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=microsoft/MediPhi-Instruct ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.1788 | |0 | +| - NER | | | |f1 | | 0.1788 | |0 | | - p1 | | | |f1 | | 0.1641 | | 0 | | - p2 | | | |f1 | | 0.2081 | | 0 | | - p3 | | | |f1 | | 0.1641 | | 0 | -| - re | | | |f1 | | 0.1221 | |0 | +| - RE | | | |f1 | | 0.1221 | |0 | | - p1 | | | |f1 | | 0.1776 | | 0 | | - p2 | | | |f1 | | 0.0112 | | 0 | | - p3 | | | |f1 | | 0.1776 | | 0 | diff --git a/csv_files/outputs/microsoft__MediPhi-Instruct__sk__10shot.txt b/csv_files/outputs/microsoft__MediPhi-Instruct__sk__10shot.txt index 67861309c2309406060c621903e95b4d4d36b9c4..4ca356c3fa0d0d2fbfc49bd6e1fb5c22a178641f 100644 --- a/csv_files/outputs/microsoft__MediPhi-Instruct__sk__10shot.txt +++ b/csv_files/outputs/microsoft__MediPhi-Instruct__sk__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=microsoft/MediPhi-Instruct ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.4226 | |0 | +| - NER | | | |f1 | | 0.4226 | |0 | | - p1 | | | |f1 | | 0.4327 | | 0 | | - p2 | | | |f1 | | 0.4023 | | 0 | | - p3 | | | |f1 | | 0.4327 | | 0 | -| - re | | | |f1 | | 0.1233 | |0 | +| - RE | | | |f1 | | 0.1233 | |0 | | - p1 | | | |f1 | | 0.1070 | | 0 | | - p2 | | | |f1 | | 0.1395 | | 0 | diff --git a/csv_files/outputs/microsoft__MediPhi-Instruct__sl__0shot.txt b/csv_files/outputs/microsoft__MediPhi-Instruct__sl__0shot.txt index 30eae1f944b43a56e40bfd388434c8750039220f..7d1efab70337f7f4131da606243432c236e0a589 100644 --- a/csv_files/outputs/microsoft__MediPhi-Instruct__sl__0shot.txt +++ b/csv_files/outputs/microsoft__MediPhi-Instruct__sl__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=microsoft/MediPhi-Instruct ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.1792 | |0 | +| - NER | | | |f1 | | 0.1792 | |0 | | - p1 | | | |f1 | | 0.1758 | | 0 | | - p2 | | | |f1 | | 0.1860 | | 0 | | - p3 | | | |f1 | | 0.1758 | | 0 | -| - re | | | |f1 | | 0.1325 | |0 | +| - RE | | | |f1 | | 0.1325 | |0 | | - p1 | | | |f1 | | 0.1446 | | 0 | | - p2 | | | |f1 | | 0.1084 | | 0 | | - p3 | | | |f1 | | 0.1446 | | 0 | diff --git a/csv_files/outputs/microsoft__MediPhi-Instruct__sl__10shot.txt b/csv_files/outputs/microsoft__MediPhi-Instruct__sl__10shot.txt index 450874e9bed331799c2f958afd58e7222f42b0d9..4da54e27448814e22ec38a41151303a4f516855d 100644 --- a/csv_files/outputs/microsoft__MediPhi-Instruct__sl__10shot.txt +++ b/csv_files/outputs/microsoft__MediPhi-Instruct__sl__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=microsoft/MediPhi-Instruct ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.3837 | |0 | +| - NER | | | |f1 | | 0.3837 | |0 | | - p1 | | | |f1 | | 0.3973 | | 0 | | - p2 | | | |f1 | | 0.3564 | | 0 | | - p3 | | | |f1 | | 0.3973 | | 0 | -| - re | | | |f1 | | 0.1312 | |0 | +| - RE | | | |f1 | | 0.1312 | |0 | | - p1 | | | |f1 | | 0.1155 | | 0 | | - p2 | | | |f1 | | 0.1468 | | 0 | diff --git a/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__en__0shot.txt b/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__en__0shot.txt index 8e502b0469c74a107e33036e293f44cc2fa4b63e..f4ee3894a133ddaa7d959a5cc3ee2a1e1a1647e2 100644 --- a/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__en__0shot.txt +++ b/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__en__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=mistralai/Mistral-7B-Instruct-v0.2 ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.2278 | |0 | +| - NER | | | |f1 | | 0.2278 | |0 | | - p1 | | | |f1 | | 0.2529 | | 0 | | - p2 | | | |f1 | | 0.2144 | | 0 | | - p3 | | | |f1 | | 0.2162 | | 0 | -| - re | | | |f1 | | 0.3007 | |0 | +| - RE | | | |f1 | | 0.3007 | |0 | | - p1 | | | |f1 | | 0.3688 | | 0 | | - p2 | | | |f1 | | 0.3642 | | 0 | | - p3 | | | |f1 | | 0.1693 | | 0 | diff --git a/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__en__10shot.txt b/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__en__10shot.txt index b3a5a39e1e6dba5602444c93a8a19333b259469c..c7c232863aaa58475d4e1a87093a767da7537dd1 100644 --- a/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__en__10shot.txt +++ b/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__en__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=mistralai/Mistral-7B-Instruct-v0.2 ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.4753 | |0 | +| - NER | | | |f1 | | 0.4753 | |0 | | - p1 | | | |f1 | | 0.4725 | | 0 | | - p2 | | | |f1 | | 0.4730 | | 0 | | - p3 | | | |f1 | | 0.4805 | | 0 | -| - re | | | |f1 | | 0.3314 | |0 | +| - RE | | | |f1 | | 0.3314 | |0 | | - p1 | | | |f1 | | 0.2593 | | 0 | | - p2 | | | |f1 | | 0.4034 | | 0 | diff --git a/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__gr__0shot.txt b/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__gr__0shot.txt index 16b5a9165aad174a6a36147b6996cc7fa1e6604d..0017f0d9afa0d196c05a399d60bf6b69bf801441 100644 --- a/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__gr__0shot.txt +++ b/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__gr__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=mistralai/Mistral-7B-Instruct-v0.2 ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.1705 | |0 | +| - NER | | | |f1 | | 0.1705 | |0 | | - p1 | | | |f1 | | 0.1603 | | 0 | | - p2 | | | |f1 | | 0.1909 | | 0 | | - p3 | | | |f1 | | 0.1603 | | 0 | -| - re | | | |f1 | | 0.0592 | |0 | +| - RE | | | |f1 | | 0.0592 | |0 | | - p1 | | | |f1 | | 0.0432 | | 0 | | - p2 | | | |f1 | | 0.0348 | | 0 | | - p3 | | | |f1 | | 0.0994 | | 0 | diff --git a/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__gr__10shot.txt b/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__gr__10shot.txt index 0a6d3a6d74f4e46818d3bc6b0cd9e8a03530db07..6542217f570cf2c774a5d8e6774ce8494e824f0d 100644 --- a/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__gr__10shot.txt +++ b/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__gr__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=mistralai/Mistral-7B-Instruct-v0.2 ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.3548 | |0 | +| - NER | | | |f1 | | 0.3548 | |0 | | - p1 | | | |f1 | | 0.3498 | | 0 | | - p2 | | | |f1 | | 0.3648 | | 0 | | - p3 | | | |f1 | | 0.3498 | | 0 | -| - re | | | |f1 | | 0.1699 | |0 | +| - RE | | | |f1 | | 0.1699 | |0 | | - p1 | | | |f1 | | 0.1055 | | 0 | | - p2 | | | |f1 | | 0.2343 | | 0 | diff --git a/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__it__0shot.txt b/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__it__0shot.txt index e0cf20ff46d2445183d7c850dfe015d3e0f0f3ba..b4e44b2cf5da34e762e0db150b8246e857eae345 100644 --- a/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__it__0shot.txt +++ b/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__it__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=mistralai/Mistral-7B-Instruct-v0.2 ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.2433 | |0 | +| - NER | | | |f1 | | 0.2433 | |0 | | - p1 | | | |f1 | | 0.2788 | | 0 | | - p2 | | | |f1 | | 0.2030 | | 0 | | - p3 | | | |f1 | | 0.2481 | | 0 | -| - re | | | |f1 | | 0.0561 | |0 | +| - RE | | | |f1 | | 0.0561 | |0 | | - p1 | | | |f1 | | 0.1382 | | 0 | | - p2 | | | |f1 | | 0.0163 | | 0 | | - p3 | | | |f1 | | 0.0140 | | 0 | diff --git a/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__it__10shot.txt b/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__it__10shot.txt index 5c4d23b35f6e63a6ec9591f9f4a72438fe617193..32975b7fe989ee9b90d1fe8f17345424a3c63029 100644 --- a/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__it__10shot.txt +++ b/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__it__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=mistralai/Mistral-7B-Instruct-v0.2 ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.5176 | |0 | +| - NER | | | |f1 | | 0.5176 | |0 | | - p1 | | | |f1 | | 0.5147 | | 0 | | - p2 | | | |f1 | | 0.5232 | | 0 | | - p3 | | | |f1 | | 0.5149 | | 0 | -| - re | | | |f1 | | 0.3811 | |0 | +| - RE | | | |f1 | | 0.3811 | |0 | | - p1 | | | |f1 | | 0.3092 | | 0 | | - p2 | | | |f1 | | 0.4530 | | 0 | diff --git a/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__pl__0shot.txt b/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__pl__0shot.txt index e3a6ccb53c1fbdee54552c727abc293c311e9246..77b2c7212ed034a17baff6431293cdb59c42592c 100644 --- a/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__pl__0shot.txt +++ b/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__pl__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=mistralai/Mistral-7B-Instruct-v0.2 ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.2953 | |0 | +| - NER | | | |f1 | | 0.2953 | |0 | | - p1 | | | |f1 | | 0.3024 | | 0 | | - p2 | | | |f1 | | 0.2811 | | 0 | | - p3 | | | |f1 | | 0.3024 | | 0 | -| - re | | | |f1 | | 0.1006 | |0 | +| - RE | | | |f1 | | 0.1006 | |0 | | - p1 | | | |f1 | | 0.0863 | | 0 | | - p2 | | | |f1 | | 0.1292 | | 0 | | - p3 | | | |f1 | | 0.0863 | | 0 | diff --git a/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__pl__10shot.txt b/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__pl__10shot.txt index 781a606a64f7cc4449961c855e8ee8cf0ceacd37..98999dec048efd933959ae747c011243fa195858 100644 --- a/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__pl__10shot.txt +++ b/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__pl__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=mistralai/Mistral-7B-Instruct-v0.2 ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.4956 | |0 | +| - NER | | | |f1 | | 0.4956 | |0 | | - p1 | | | |f1 | | 0.4911 | | 0 | | - p2 | | | |f1 | | 0.5046 | | 0 | | - p3 | | | |f1 | | 0.4911 | | 0 | -| - re | | | |f1 | | 0.3603 | |0 | +| - RE | | | |f1 | | 0.3603 | |0 | | - p1 | | | |f1 | | 0.3895 | | 0 | | - p2 | | | |f1 | | 0.3311 | | 0 | diff --git a/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__sk__0shot.txt b/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__sk__0shot.txt index bc1036659d5c18203c2be94655e756dba8a8c106..6eeaac48bff7f356aa2168ad7755b879c69be13a 100644 --- a/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__sk__0shot.txt +++ b/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__sk__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=mistralai/Mistral-7B-Instruct-v0.2 ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.2144 | |0 | +| - NER | | | |f1 | | 0.2144 | |0 | | - p1 | | | |f1 | | 0.2143 | | 0 | | - p2 | | | |f1 | | 0.2146 | | 0 | | - p3 | | | |f1 | | 0.2143 | | 0 | -| - re | | | |f1 | | 0.0782 | |0 | +| - RE | | | |f1 | | 0.0782 | |0 | | - p1 | | | |f1 | | 0.0756 | | 0 | | - p2 | | | |f1 | | 0.0835 | | 0 | | - p3 | | | |f1 | | 0.0756 | | 0 | diff --git a/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__sk__10shot.txt b/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__sk__10shot.txt index 81cfa0c7032d7533575224dc8c121a7e54038b71..66c2604baed07981da5e7d253b0692ca6e103aa1 100644 --- a/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__sk__10shot.txt +++ b/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__sk__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=mistralai/Mistral-7B-Instruct-v0.2 ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.3951 | |0 | +| - NER | | | |f1 | | 0.3951 | |0 | | - p1 | | | |f1 | | 0.4029 | | 0 | | - p2 | | | |f1 | | 0.3794 | | 0 | | - p3 | | | |f1 | | 0.4029 | | 0 | -| - re | | | |f1 | | 0.2051 | |0 | +| - RE | | | |f1 | | 0.2051 | |0 | | - p1 | | | |f1 | | 0.2155 | | 0 | | - p2 | | | |f1 | | 0.1948 | | 0 | diff --git a/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__sl__0shot.txt b/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__sl__0shot.txt index ee93bfc18a44967177d18c70bb865dbc6b2ab75e..e0158432acf19d26d277f1b57deb076edd05514a 100644 --- a/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__sl__0shot.txt +++ b/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__sl__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=mistralai/Mistral-7B-Instruct-v0.2 ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.1826 | |0 | +| - NER | | | |f1 | | 0.1826 | |0 | | - p1 | | | |f1 | | 0.1766 | | 0 | | - p2 | | | |f1 | | 0.1947 | | 0 | | - p3 | | | |f1 | | 0.1766 | | 0 | -| - re | | | |f1 | | 0.1076 | |0 | +| - RE | | | |f1 | | 0.1076 | |0 | | - p1 | | | |f1 | | 0.0766 | | 0 | | - p2 | | | |f1 | | 0.1695 | | 0 | | - p3 | | | |f1 | | 0.0766 | | 0 | diff --git a/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__sl__10shot.txt b/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__sl__10shot.txt index bd8a356a7c3cc706edb631e160103a2a498fa6ad..21d83809b381556619ff7e5ab51516c24dfe0864 100644 --- a/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__sl__10shot.txt +++ b/csv_files/outputs/mistralai__Mistral-7B-Instruct-v0.2__sl__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=mistralai/Mistral-7B-Instruct-v0.2 ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.4194 | |0 | +| - NER | | | |f1 | | 0.4194 | |0 | | - p1 | | | |f1 | | 0.4204 | | 0 | | - p2 | | | |f1 | | 0.4174 | | 0 | | - p3 | | | |f1 | | 0.4204 | | 0 | -| - re | | | |f1 | | 0.1970 | |0 | +| - RE | | | |f1 | | 0.1970 | |0 | | - p1 | | | |f1 | | 0.1990 | | 0 | | - p2 | | | |f1 | | 0.1950 | | 0 | diff --git a/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__en__0shot.txt b/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__en__0shot.txt index 4f9ec631fcea66bfe04d508e14ea80d723c51acb..d2af72d7f2124d9fb87aba16aa7ec5979b1490e4 100644 --- a/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__en__0shot.txt +++ b/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__en__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=mistralai/Mistral-Nemo-Instruct-2407 ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.2271 | |0 | +| - NER | | | |f1 | | 0.2271 | |0 | | - p1 | | | |f1 | | 0.2767 | | 0 | | - p2 | | | |f1 | | 0.2299 | | 0 | | - p3 | | | |f1 | | 0.1748 | | 0 | -| - re | | | |f1 | | 0.3472 | |0 | +| - RE | | | |f1 | | 0.3472 | |0 | | - p1 | | | |f1 | | 0.3694 | | 0 | | - p2 | | | |f1 | | 0.3482 | | 0 | | - p3 | | | |f1 | | 0.3241 | | 0 | diff --git a/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__en__10shot.txt b/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__en__10shot.txt index b479ea31786ab215ef11aae9395ed0e12f7d21fe..7f83d34bd21324ddddf4507bb0dfc82a46ef1910 100644 --- a/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__en__10shot.txt +++ b/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__en__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=mistralai/Mistral-Nemo-Instruct-2407 ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.5762 | |0 | +| - NER | | | |f1 | | 0.5762 | |0 | | - p1 | | | |f1 | | 0.5777 | | 0 | | - p2 | | | |f1 | | 0.5841 | | 0 | | - p3 | | | |f1 | | 0.5668 | | 0 | -| - re | | | |f1 | | 0.4245 | |0 | +| - RE | | | |f1 | | 0.4245 | |0 | | - p1 | | | |f1 | | 0.3482 | | 0 | | - p2 | | | |f1 | | 0.5008 | | 0 | diff --git a/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__gr__0shot.txt b/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__gr__0shot.txt index 29bdd0e9132787a1125ae29d9f42a6961388e7f2..a6f9827c9bfca0e3f2fe140aa5bb7f63e64551b9 100644 --- a/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__gr__0shot.txt +++ b/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__gr__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=mistralai/Mistral-Nemo-Instruct-2407 ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.0717 | |0 | +| - NER | | | |f1 | | 0.0717 | |0 | | - p1 | | | |f1 | | 0.0732 | | 0 | | - p2 | | | |f1 | | 0.0687 | | 0 | | - p3 | | | |f1 | | 0.0732 | | 0 | -| - re | | | |f1 | | 0.2326 | |0 | +| - RE | | | |f1 | | 0.2326 | |0 | | - p1 | | | |f1 | | 0.1575 | | 0 | | - p2 | | | |f1 | | 0.2117 | | 0 | | - p3 | | | |f1 | | 0.3287 | | 0 | diff --git a/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__gr__10shot.txt b/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__gr__10shot.txt index 9822eb38961b00cead5fcd9e98a85a6cad536133..5305a935ac66ea3557ea860f92a81e4b3b7e3a7f 100644 --- a/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__gr__10shot.txt +++ b/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__gr__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=mistralai/Mistral-Nemo-Instruct-2407 ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.5050 | |0 | +| - NER | | | |f1 | | 0.5050 | |0 | | - p1 | | | |f1 | | 0.5081 | | 0 | | - p2 | | | |f1 | | 0.4988 | | 0 | | - p3 | | | |f1 | | 0.5081 | | 0 | -| - re | | | |f1 | | 0.2162 | |0 | +| - RE | | | |f1 | | 0.2162 | |0 | | - p1 | | | |f1 | | 0.2029 | | 0 | | - p2 | | | |f1 | | 0.2296 | | 0 | diff --git a/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__it__0shot.txt b/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__it__0shot.txt index 67704668b629b8df7abedf42ca4d673b6a5bbc7c..94723d98b89e2a142ae06a3699ea88924444d65a 100644 --- a/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__it__0shot.txt +++ b/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__it__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=mistralai/Mistral-Nemo-Instruct-2407 ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.1960 | |0 | +| - NER | | | |f1 | | 0.1960 | |0 | | - p1 | | | |f1 | | 0.2792 | | 0 | | - p2 | | | |f1 | | 0.1772 | | 0 | | - p3 | | | |f1 | | 0.1316 | | 0 | -| - re | | | |f1 | | 0.2365 | |0 | +| - RE | | | |f1 | | 0.2365 | |0 | | - p1 | | | |f1 | | 0.2849 | | 0 | | - p2 | | | |f1 | | 0.2384 | | 0 | | - p3 | | | |f1 | | 0.1861 | | 0 | diff --git a/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__it__10shot.txt b/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__it__10shot.txt index 0b4bb613279f3b93b6e1f2cc9eb5aa447350fa8e..426c121a4b88ebed985cd20d4010f2d266160a1e 100644 --- a/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__it__10shot.txt +++ b/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__it__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=mistralai/Mistral-Nemo-Instruct-2407 ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.6441 | |0 | +| - NER | | | |f1 | | 0.6441 | |0 | | - p1 | | | |f1 | | 0.6430 | | 0 | | - p2 | | | |f1 | | 0.6437 | | 0 | | - p3 | | | |f1 | | 0.6457 | | 0 | -| - re | | | |f1 | | 0.3404 | |0 | +| - RE | | | |f1 | | 0.3404 | |0 | | - p1 | | | |f1 | | 0.2708 | | 0 | | - p2 | | | |f1 | | 0.4099 | | 0 | diff --git a/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__pl__0shot.txt b/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__pl__0shot.txt index 99b46d553f57aaed0a8017a7a5911af7bb40f6d7..9a7d8e28e086f27eb9637e6ad992ba36f0de390a 100644 --- a/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__pl__0shot.txt +++ b/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__pl__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=mistralai/Mistral-Nemo-Instruct-2407 ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.0468 | |0 | +| - NER | | | |f1 | | 0.0468 | |0 | | - p1 | | | |f1 | | 0.0483 | | 0 | | - p2 | | | |f1 | | 0.0439 | | 0 | | - p3 | | | |f1 | | 0.0483 | | 0 | -| - re | | | |f1 | | 0.1823 | |0 | +| - RE | | | |f1 | | 0.1823 | |0 | | - p1 | | | |f1 | | 0.2123 | | 0 | | - p2 | | | |f1 | | 0.1686 | | 0 | | - p3 | | | |f1 | | 0.1661 | | 0 | diff --git a/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__pl__10shot.txt b/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__pl__10shot.txt index 4909ab6216254be068a90c6f672fa19e16ba1202..aaab1bc243dd956c4437b12dcbad9c52cd405ac2 100644 --- a/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__pl__10shot.txt +++ b/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__pl__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=mistralai/Mistral-Nemo-Instruct-2407 ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.5375 | |0 | +| - NER | | | |f1 | | 0.5375 | |0 | | - p1 | | | |f1 | | 0.5352 | | 0 | | - p2 | | | |f1 | | 0.5421 | | 0 | | - p3 | | | |f1 | | 0.5352 | | 0 | -| - re | | | |f1 | | 0.1859 | |0 | +| - RE | | | |f1 | | 0.1859 | |0 | | - p1 | | | |f1 | | 0.1863 | | 0 | | - p2 | | | |f1 | | 0.1855 | | 0 | diff --git a/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__sk__0shot.txt b/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__sk__0shot.txt index cb8f25d0decd15173485364726a4ed5b5da885d0..6c38472f1e9cb2c7693144b17179e9dcfe88f159 100644 --- a/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__sk__0shot.txt +++ b/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__sk__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=mistralai/Mistral-Nemo-Instruct-2407 ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.0738 | |0 | +| - NER | | | |f1 | | 0.0738 | |0 | | - p1 | | | |f1 | | 0.0685 | | 0 | | - p2 | | | |f1 | | 0.0844 | | 0 | | - p3 | | | |f1 | | 0.0685 | | 0 | -| - re | | | |f1 | | 0.1596 | |0 | +| - RE | | | |f1 | | 0.1596 | |0 | | - p1 | | | |f1 | | 0.1696 | | 0 | | - p2 | | | |f1 | | 0.1396 | | 0 | | - p3 | | | |f1 | | 0.1696 | | 0 | diff --git a/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__sk__10shot.txt b/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__sk__10shot.txt index 026f8af475c0bd2d37a6b8ea25b4cf67c2ca0c88..1678af3e537d2be78af3049673d6f0fcd8541e12 100644 --- a/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__sk__10shot.txt +++ b/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__sk__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=mistralai/Mistral-Nemo-Instruct-2407 ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.5030 | |0 | +| - NER | | | |f1 | | 0.5030 | |0 | | - p1 | | | |f1 | | 0.5025 | | 0 | | - p2 | | | |f1 | | 0.5040 | | 0 | | - p3 | | | |f1 | | 0.5025 | | 0 | -| - re | | | |f1 | | 0.1702 | |0 | +| - RE | | | |f1 | | 0.1702 | |0 | | - p1 | | | |f1 | | 0.1237 | | 0 | | - p2 | | | |f1 | | 0.2166 | | 0 | diff --git a/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__sl__0shot.txt b/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__sl__0shot.txt index 62298f12aa29d9fea6f35a71f1cb1c7d20d1d4e5..832ca83ee26ae570b1c4e4d781100383be94e147 100644 --- a/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__sl__0shot.txt +++ b/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__sl__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=mistralai/Mistral-Nemo-Instruct-2407 ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.0842 | |0 | +| - NER | | | |f1 | | 0.0842 | |0 | | - p1 | | | |f1 | | 0.0861 | | 0 | | - p2 | | | |f1 | | 0.0805 | | 0 | | - p3 | | | |f1 | | 0.0861 | | 0 | -| - re | | | |f1 | | 0.1905 | |0 | +| - RE | | | |f1 | | 0.1905 | |0 | | - p1 | | | |f1 | | 0.2309 | | 0 | | - p2 | | | |f1 | | 0.1096 | | 0 | | - p3 | | | |f1 | | 0.2309 | | 0 | diff --git a/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__sl__10shot.txt b/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__sl__10shot.txt index 389511b1661481c55f6cca90c523c9814540a17d..09905f26ce5acd5fc32968382f2569524d922af4 100644 --- a/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__sl__10shot.txt +++ b/csv_files/outputs/mistralai__Mistral-Nemo-Instruct-2407__sl__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=mistralai/Mistral-Nemo-Instruct-2407 ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.5327 | |0 | +| - NER | | | |f1 | | 0.5327 | |0 | | - p1 | | | |f1 | | 0.5323 | | 0 | | - p2 | | | |f1 | | 0.5335 | | 0 | | - p3 | | | |f1 | | 0.5323 | | 0 | -| - re | | | |f1 | | 0.1723 | |0 | +| - RE | | | |f1 | | 0.1723 | |0 | | - p1 | | | |f1 | | 0.1390 | | 0 | | - p2 | | | |f1 | | 0.2057 | | 0 | diff --git a/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__en__0shot.txt b/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__en__0shot.txt index a0a6321951108e682662973e28de8c885a2ec6ac..0cdeef408ee3cfe2f6230ee84b4f0d454d6847c9 100644 --- a/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__en__0shot.txt +++ b/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__en__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=tiiuae/Falcon3-10B-Instruct ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.2658 | |0 | +| - NER | | | |f1 | | 0.2658 | |0 | | - p1 | | | |f1 | | 0.2270 | | 0 | | - p2 | | | |f1 | | 0.2709 | | 0 | | - p3 | | | |f1 | | 0.2996 | | 0 | -| - re | | | |f1 | | 0.3280 | |0 | +| - RE | | | |f1 | | 0.3280 | |0 | | - p1 | | | |f1 | | 0.2157 | | 0 | | - p2 | | | |f1 | | 0.3835 | | 0 | | - p3 | | | |f1 | | 0.3848 | | 0 | diff --git a/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__en__10shot.txt b/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__en__10shot.txt index 2d7afc8c15ec13c18d8b6ddc2e8179614789e85b..116461a1d68f463761c7342d95e0a6c18d209b79 100644 --- a/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__en__10shot.txt +++ b/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__en__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=tiiuae/Falcon3-10B-Instruct ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.5730 | |0 | +| - NER | | | |f1 | | 0.5730 | |0 | | - p1 | | | |f1 | | 0.5840 | | 0 | | - p2 | | | |f1 | | 0.5421 | | 0 | | - p3 | | | |f1 | | 0.5928 | | 0 | -| - re | | | |f1 | | 0.4960 | |0 | +| - RE | | | |f1 | | 0.4960 | |0 | | - p1 | | | |f1 | | 0.4335 | | 0 | | - p2 | | | |f1 | | 0.5586 | | 0 | diff --git a/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__gr__0shot.txt b/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__gr__0shot.txt index f82fdd2d52536ceb420fb68f7fdc509d1e0571ce..b7516c1517104e5be8c21dca55222faa85473fdc 100644 --- a/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__gr__0shot.txt +++ b/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__gr__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=tiiuae/Falcon3-10B-Instruct ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.1585 | |0 | +| - NER | | | |f1 | | 0.1585 | |0 | | - p1 | | | |f1 | | 0.2130 | | 0 | | - p2 | | | |f1 | | 0.0495 | | 0 | | - p3 | | | |f1 | | 0.2130 | | 0 | -| - re | | | |f1 | | 0.0506 | |0 | +| - RE | | | |f1 | | 0.0506 | |0 | | - p1 | | | |f1 | | 0.0401 | | 0 | | - p2 | | | |f1 | | 0.0250 | | 0 | | - p3 | | | |f1 | | 0.0867 | | 0 | diff --git a/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__gr__10shot.txt b/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__gr__10shot.txt index 043f6fdaf361b4449451b4723c2d212109272003..2c2e57b09937fbd9a661ea9eeea1d545a9014727 100644 --- a/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__gr__10shot.txt +++ b/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__gr__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=tiiuae/Falcon3-10B-Instruct ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.3448 | |0 | +| - NER | | | |f1 | | 0.3448 | |0 | | - p1 | | | |f1 | | 0.3345 | | 0 | | - p2 | | | |f1 | | 0.3655 | | 0 | | - p3 | | | |f1 | | 0.3345 | | 0 | -| - re | | | |f1 | | 0.3752 | |0 | +| - RE | | | |f1 | | 0.3752 | |0 | | - p1 | | | |f1 | | 0.3749 | | 0 | | - p2 | | | |f1 | | 0.3755 | | 0 | diff --git a/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__it__0shot.txt b/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__it__0shot.txt index 35603a5cf7326d49057dfc282d07cb3bcee22f05..9bfdea743aa846d49f2acc6c0ba67e678ce8c4b0 100644 --- a/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__it__0shot.txt +++ b/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__it__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=tiiuae/Falcon3-10B-Instruct ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.2011 | |0 | +| - NER | | | |f1 | | 0.2011 | |0 | | - p1 | | | |f1 | | 0.1261 | | 0 | | - p2 | | | |f1 | | 0.2327 | | 0 | | - p3 | | | |f1 | | 0.2444 | | 0 | -| - re | | | |f1 | | 0.1865 | |0 | +| - RE | | | |f1 | | 0.1865 | |0 | | - p1 | | | |f1 | | 0.2404 | | 0 | | - p2 | | | |f1 | | 0.1699 | | 0 | | - p3 | | | |f1 | | 0.1492 | | 0 | diff --git a/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__it__10shot.txt b/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__it__10shot.txt index b5c661f33ce3164c556af215c55b5594d6e6a667..a8b908469a36074fdd599b214a6de21f33687ab3 100644 --- a/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__it__10shot.txt +++ b/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__it__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=tiiuae/Falcon3-10B-Instruct ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.5625 | |0 | +| - NER | | | |f1 | | 0.5625 | |0 | | - p1 | | | |f1 | | 0.5821 | | 0 | | - p2 | | | |f1 | | 0.5432 | | 0 | | - p3 | | | |f1 | | 0.5622 | | 0 | -| - re | | | |f1 | | 0.5040 | |0 | +| - RE | | | |f1 | | 0.5040 | |0 | | - p1 | | | |f1 | | 0.4622 | | 0 | | - p2 | | | |f1 | | 0.5458 | | 0 | diff --git a/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__pl__0shot.txt b/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__pl__0shot.txt index cfe1ab055abc55ac21f308106812a31c03dd75d8..edaf86b247e1c20e0f7c4138f96ec19d5a571ae4 100644 --- a/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__pl__0shot.txt +++ b/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__pl__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=tiiuae/Falcon3-10B-Instruct ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.2414 | |0 | +| - NER | | | |f1 | | 0.2414 | |0 | | - p1 | | | |f1 | | 0.2452 | | 0 | | - p2 | | | |f1 | | 0.2338 | | 0 | | - p3 | | | |f1 | | 0.2452 | | 0 | -| - re | | | |f1 | | 0.0963 | |0 | +| - RE | | | |f1 | | 0.0963 | |0 | | - p1 | | | |f1 | | 0.1501 | | 0 | | - p2 | | | |f1 | | 0.0123 | | 0 | | - p3 | | | |f1 | | 0.1264 | | 0 | diff --git a/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__pl__10shot.txt b/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__pl__10shot.txt index cd0f486fb1b90e0b4b851363edfb01a16cebda16..8f83cc394deab4361dadca72e359dad9108165f1 100644 --- a/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__pl__10shot.txt +++ b/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__pl__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=tiiuae/Falcon3-10B-Instruct ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.4244 | |0 | +| - NER | | | |f1 | | 0.4244 | |0 | | - p1 | | | |f1 | | 0.4304 | | 0 | | - p2 | | | |f1 | | 0.4123 | | 0 | | - p3 | | | |f1 | | 0.4304 | | 0 | -| - re | | | |f1 | | 0.5350 | |0 | +| - RE | | | |f1 | | 0.5350 | |0 | | - p1 | | | |f1 | | 0.5129 | | 0 | | - p2 | | | |f1 | | 0.5571 | | 0 | diff --git a/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__sk__0shot.txt b/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__sk__0shot.txt index 70be76745b95ffbda8aac22be805f33ae11b8f0d..6caf6d188e37dd8d852231914da9bca9053abf92 100644 --- a/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__sk__0shot.txt +++ b/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__sk__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=tiiuae/Falcon3-10B-Instruct ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.2871 | |0 | +| - NER | | | |f1 | | 0.2871 | |0 | | - p1 | | | |f1 | | 0.2717 | | 0 | | - p2 | | | |f1 | | 0.3178 | | 0 | | - p3 | | | |f1 | | 0.2717 | | 0 | -| - re | | | |f1 | | 0.0182 | |0 | +| - RE | | | |f1 | | 0.0182 | |0 | | - p1 | | | |f1 | | 0.0143 | | 0 | | - p2 | | | |f1 | | 0.0260 | | 0 | | - p3 | | | |f1 | | 0.0143 | | 0 | diff --git a/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__sk__10shot.txt b/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__sk__10shot.txt index cf61cdbb7ef141477d6986bd57ffed0bdad70cbd..eba3a06478a8519e9938476f5f60a9ee4abfb883 100644 --- a/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__sk__10shot.txt +++ b/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__sk__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=tiiuae/Falcon3-10B-Instruct ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.4402 | |0 | +| - NER | | | |f1 | | 0.4402 | |0 | | - p1 | | | |f1 | | 0.4545 | | 0 | | - p2 | | | |f1 | | 0.4116 | | 0 | | - p3 | | | |f1 | | 0.4545 | | 0 | -| - re | | | |f1 | | 0.4222 | |0 | +| - RE | | | |f1 | | 0.4222 | |0 | | - p1 | | | |f1 | | 0.3750 | | 0 | | - p2 | | | |f1 | | 0.4695 | | 0 | diff --git a/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__sl__0shot.txt b/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__sl__0shot.txt index a9943589714a47225564e83a9d2210e3af8dcff2..8d586cd4e31f21369f0d3c8873dba4eb0ce073b5 100644 --- a/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__sl__0shot.txt +++ b/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__sl__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=tiiuae/Falcon3-10B-Instruct ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.2297 | |0 | +| - NER | | | |f1 | | 0.2297 | |0 | | - p1 | | | |f1 | | 0.2519 | | 0 | | - p2 | | | |f1 | | 0.1853 | | 0 | | - p3 | | | |f1 | | 0.2519 | | 0 | -| - re | | | |f1 | | 0.0050 | |0 | +| - RE | | | |f1 | | 0.0050 | |0 | | - p1 | | | |f1 | | 0.0047 | | 0 | | - p2 | | | |f1 | | 0.0058 | | 0 | | - p3 | | | |f1 | | 0.0047 | | 0 | diff --git a/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__sl__10shot.txt b/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__sl__10shot.txt index a62c9f9481ff3aeeca9ee989a959904168f62616..9c812245ecae1e255c669705ae7b71ce3942868a 100644 --- a/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__sl__10shot.txt +++ b/csv_files/outputs/tiiuae__Falcon3-10B-Instruct__sl__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=tiiuae/Falcon3-10B-Instruct ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.4050 | |0 | +| - NER | | | |f1 | | 0.4050 | |0 | | - p1 | | | |f1 | | 0.4121 | | 0 | | - p2 | | | |f1 | | 0.3909 | | 0 | | - p3 | | | |f1 | | 0.4121 | | 0 | -| - re | | | |f1 | | 0.2668 | |0 | +| - RE | | | |f1 | | 0.2668 | |0 | | - p1 | | | |f1 | | 0.2323 | | 0 | | - p2 | | | |f1 | | 0.3012 | | 0 | diff --git a/csv_files/outputs/unsloth__phi-4__en__0shot.txt b/csv_files/outputs/unsloth__phi-4__en__0shot.txt index af80bdf2b861abf5a192d75b7889b3a166394a2c..ba5d152519748cd98fa31e6e3d3083ba897a70ba 100644 --- a/csv_files/outputs/unsloth__phi-4__en__0shot.txt +++ b/csv_files/outputs/unsloth__phi-4__en__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=unsloth/phi-4 ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.0275 | |0 | +| - NER | | | |f1 | | 0.0275 | |0 | | - p1 | | | |f1 | | 0.0000 | | 0 | | - p2 | | | |f1 | | 0.0252 | | 0 | | - p3 | | | |f1 | | 0.0572 | | 0 | -| - re | | | |f1 | | 0.4090 | |0 | +| - RE | | | |f1 | | 0.4090 | |0 | | - p1 | | | |f1 | | 0.4022 | | 0 | | - p2 | | | |f1 | | 0.4219 | | 0 | | - p3 | | | |f1 | | 0.4030 | | 0 | diff --git a/csv_files/outputs/unsloth__phi-4__en__10shot.txt b/csv_files/outputs/unsloth__phi-4__en__10shot.txt index 67bac9316eb541f0cf2567e21a2c0ba8c3cd4065..2f8a87e9012589d5d26d17645155c6504e9532cf 100644 --- a/csv_files/outputs/unsloth__phi-4__en__10shot.txt +++ b/csv_files/outputs/unsloth__phi-4__en__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=unsloth/phi-4 ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.5984 | |0 | +| - NER | | | |f1 | | 0.5984 | |0 | | - p1 | | | |f1 | | 0.6098 | | 0 | | - p2 | | | |f1 | | 0.5711 | | 0 | | - p3 | | | |f1 | | 0.6141 | | 0 | -| - re | | | |f1 | | 0.5269 | |0 | +| - RE | | | |f1 | | 0.5269 | |0 | | - p1 | | | |f1 | | 0.4912 | | 0 | | - p2 | | | |f1 | | 0.5626 | | 0 | diff --git a/csv_files/outputs/unsloth__phi-4__gr__0shot.txt b/csv_files/outputs/unsloth__phi-4__gr__0shot.txt index 7969180e3473a886d42e4f4be8a510d9266856ae..a17e8d575c703b7ccebc72cd8ff6aeca0397f1cc 100644 --- a/csv_files/outputs/unsloth__phi-4__gr__0shot.txt +++ b/csv_files/outputs/unsloth__phi-4__gr__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=unsloth/phi-4 ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.0000 | |0 | +| - NER | | | |f1 | | 0.0000 | |0 | | - p1 | | | |f1 | | 0.0000 | | 0 | | - p2 | | | |f1 | | 0.0000 | | 0 | | - p3 | | | |f1 | | 0.0000 | | 0 | -| - re | | | |f1 | | 0.2011 | |0 | +| - RE | | | |f1 | | 0.2011 | |0 | | - p1 | | | |f1 | | 0.2901 | | 0 | | - p2 | | | |f1 | | 0.2208 | | 0 | | - p3 | | | |f1 | | 0.0925 | | 0 | diff --git a/csv_files/outputs/unsloth__phi-4__gr__10shot.txt b/csv_files/outputs/unsloth__phi-4__gr__10shot.txt index c69aa2d41494640e91af2c22fcd7397f5e1c3dcf..7b2fb3a553fad01c0aab153c48d877c29231fe14 100644 --- a/csv_files/outputs/unsloth__phi-4__gr__10shot.txt +++ b/csv_files/outputs/unsloth__phi-4__gr__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=unsloth/phi-4 ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.5682 | |0 | +| - NER | | | |f1 | | 0.5682 | |0 | | - p1 | | | |f1 | | 0.5717 | | 0 | | - p2 | | | |f1 | | 0.5611 | | 0 | | - p3 | | | |f1 | | 0.5717 | | 0 | -| - re | | | |f1 | | 0.5098 | |0 | +| - RE | | | |f1 | | 0.5098 | |0 | | - p1 | | | |f1 | | 0.4935 | | 0 | | - p2 | | | |f1 | | 0.5261 | | 0 | diff --git a/csv_files/outputs/unsloth__phi-4__it__0shot.txt b/csv_files/outputs/unsloth__phi-4__it__0shot.txt index 4ee83bc7873e14aefaae1669bf86dcc0e8005f95..85e165655342f1ca2d8da14464c516405b5a51c6 100644 --- a/csv_files/outputs/unsloth__phi-4__it__0shot.txt +++ b/csv_files/outputs/unsloth__phi-4__it__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=unsloth/phi-4 ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.1717 | |0 | +| - NER | | | |f1 | | 0.1717 | |0 | | - p1 | | | |f1 | | 0.0000 | | 0 | | - p2 | | | |f1 | | 0.1724 | | 0 | | - p3 | | | |f1 | | 0.3428 | | 0 | -| - re | | | |f1 | | 0.3589 | |0 | +| - RE | | | |f1 | | 0.3589 | |0 | | - p1 | | | |f1 | | 0.3354 | | 0 | | - p2 | | | |f1 | | 0.3737 | | 0 | | - p3 | | | |f1 | | 0.3677 | | 0 | diff --git a/csv_files/outputs/unsloth__phi-4__it__10shot.txt b/csv_files/outputs/unsloth__phi-4__it__10shot.txt index 9eb081ce4505d7cc1d729c40b2d9e1ee89d84318..f8334a6b52904612c998a336649a7d71a2d1193c 100644 --- a/csv_files/outputs/unsloth__phi-4__it__10shot.txt +++ b/csv_files/outputs/unsloth__phi-4__it__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=unsloth/phi-4 ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.6759 | |0 | +| - NER | | | |f1 | | 0.6759 | |0 | | - p1 | | | |f1 | | 0.6647 | | 0 | | - p2 | | | |f1 | | 0.6732 | | 0 | | - p3 | | | |f1 | | 0.6897 | | 0 | -| - re | | | |f1 | | 0.5714 | |0 | +| - RE | | | |f1 | | 0.5714 | |0 | | - p1 | | | |f1 | | 0.5608 | | 0 | | - p2 | | | |f1 | | 0.5820 | | 0 | diff --git a/csv_files/outputs/unsloth__phi-4__pl__0shot.txt b/csv_files/outputs/unsloth__phi-4__pl__0shot.txt index b0cbde5ebdb58d95bb90c08f4a5252e17f7d1a71..50d734915f57e7a4713da8e3d4cb6ae9a653a9a1 100644 --- a/csv_files/outputs/unsloth__phi-4__pl__0shot.txt +++ b/csv_files/outputs/unsloth__phi-4__pl__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=unsloth/phi-4 ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.0279 | |0 | +| - NER | | | |f1 | | 0.0279 | |0 | | - p1 | | | |f1 | | 0.0236 | | 0 | | - p2 | | | |f1 | | 0.0366 | | 0 | | - p3 | | | |f1 | | 0.0236 | | 0 | -| - re | | | |f1 | | 0.3814 | |0 | +| - RE | | | |f1 | | 0.3814 | |0 | | - p1 | | | |f1 | | 0.3799 | | 0 | | - p2 | | | |f1 | | 0.3829 | | 0 | | - p3 | | | |f1 | | 0.3813 | | 0 | diff --git a/csv_files/outputs/unsloth__phi-4__pl__10shot.txt b/csv_files/outputs/unsloth__phi-4__pl__10shot.txt index 415465038e12d91334c2f8044bb91ee130a5fb4b..4ea29a3036075f0246a37b515995fe97a4d96e05 100644 --- a/csv_files/outputs/unsloth__phi-4__pl__10shot.txt +++ b/csv_files/outputs/unsloth__phi-4__pl__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=unsloth/phi-4 ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.5474 | |0 | +| - NER | | | |f1 | | 0.5474 | |0 | | - p1 | | | |f1 | | 0.5549 | | 0 | | - p2 | | | |f1 | | 0.5324 | | 0 | | - p3 | | | |f1 | | 0.5549 | | 0 | -| - re | | | |f1 | | 0.5591 | |0 | +| - RE | | | |f1 | | 0.5591 | |0 | | - p1 | | | |f1 | | 0.5423 | | 0 | | - p2 | | | |f1 | | 0.5760 | | 0 | diff --git a/csv_files/outputs/unsloth__phi-4__sk__0shot.txt b/csv_files/outputs/unsloth__phi-4__sk__0shot.txt index 54a528becb31213a509950e7b1c281dc3f2fe23c..609bfee5abd16055de50dbbc8a5b5e54bf628dde 100644 --- a/csv_files/outputs/unsloth__phi-4__sk__0shot.txt +++ b/csv_files/outputs/unsloth__phi-4__sk__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=unsloth/phi-4 ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.0567 | |0 | +| - NER | | | |f1 | | 0.0567 | |0 | | - p1 | | | |f1 | | 0.0316 | | 0 | | - p2 | | | |f1 | | 0.1070 | | 0 | | - p3 | | | |f1 | | 0.0316 | | 0 | -| - re | | | |f1 | | 0.3277 | |0 | +| - RE | | | |f1 | | 0.3277 | |0 | | - p1 | | | |f1 | | 0.3252 | | 0 | | - p2 | | | |f1 | | 0.3326 | | 0 | | - p3 | | | |f1 | | 0.3252 | | 0 | diff --git a/csv_files/outputs/unsloth__phi-4__sk__10shot.txt b/csv_files/outputs/unsloth__phi-4__sk__10shot.txt index 830947c5e11d99fe023efdd797f9651bb1af6ff8..925b775dfbe86c7320abed9213c1b3d54ef99b36 100644 --- a/csv_files/outputs/unsloth__phi-4__sk__10shot.txt +++ b/csv_files/outputs/unsloth__phi-4__sk__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=unsloth/phi-4 ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.5524 | |0 | +| - NER | | | |f1 | | 0.5524 | |0 | | - p1 | | | |f1 | | 0.5561 | | 0 | | - p2 | | | |f1 | | 0.5449 | | 0 | | - p3 | | | |f1 | | 0.5561 | | 0 | -| - re | | | |f1 | | 0.5050 | |0 | +| - RE | | | |f1 | | 0.5050 | |0 | | - p1 | | | |f1 | | 0.5106 | | 0 | | - p2 | | | |f1 | | 0.4994 | | 0 | diff --git a/csv_files/outputs/unsloth__phi-4__sl__0shot.txt b/csv_files/outputs/unsloth__phi-4__sl__0shot.txt index 0ae5cf81614f1de4df39c8a8404617317d393f7a..29578b4d5063f990ad13a10dcac7d69a04c24725 100644 --- a/csv_files/outputs/unsloth__phi-4__sl__0shot.txt +++ b/csv_files/outputs/unsloth__phi-4__sl__0shot.txt @@ -1,11 +1,11 @@ hf (pretrained=unsloth/phi-4 ), num_fewshot: 0, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.2241 | |0 | +| - NER | | | |f1 | | 0.2241 | |0 | | - p1 | | | |f1 | | 0.2870 | | 0 | | - p2 | | | |f1 | | 0.0981 | | 0 | | - p3 | | | |f1 | | 0.2870 | | 0 | -| - re | | | |f1 | | 0.2721 | |0 | +| - RE | | | |f1 | | 0.2721 | |0 | | - p1 | | | |f1 | | 0.3209 | | 0 | | - p2 | | | |f1 | | 0.1744 | | 0 | | - p3 | | | |f1 | | 0.3209 | | 0 | diff --git a/csv_files/outputs/unsloth__phi-4__sl__10shot.txt b/csv_files/outputs/unsloth__phi-4__sl__10shot.txt index d661ccb90e76eaeaab250e84160ff590ff8c5718..f54207bae749b676ad9b3ce437dcbc6e2780d019 100644 --- a/csv_files/outputs/unsloth__phi-4__sl__10shot.txt +++ b/csv_files/outputs/unsloth__phi-4__sl__10shot.txt @@ -1,10 +1,10 @@ hf (pretrained=unsloth/phi-4 ), num_fewshot: 10, batch_size: 1 |Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |-------|-------|------|------|------|----|------|---|------| -| - ner | | | |f1 | | 0.5577 | |0 | +| - NER | | | |f1 | | 0.5577 | |0 | | - p1 | | | |f1 | | 0.5586 | | 0 | | - p2 | | | |f1 | | 0.5558 | | 0 | | - p3 | | | |f1 | | 0.5586 | | 0 | -| - re | | | |f1 | | 0.5175 | |0 | +| - RE | | | |f1 | | 0.5175 | |0 | | - p1 | | | |f1 | | 0.5117 | | 0 | | - p2 | | | |f1 | | 0.5232 | | 0 | diff --git a/e3c_llm_results/Henrychur/MMed-Llama-3-8B_0_EN.json b/e3c_llm_results/Henrychur/MMed-Llama-3-8B_0_EN.json index 2223b25d2d50eee0dbb18c844258689efb189c10..68490feaca9d8e9cad19ecf26057ce3e9a1fe436 100644 --- a/e3c_llm_results/Henrychur/MMed-Llama-3-8B_0_EN.json +++ b/e3c_llm_results/Henrychur/MMed-Llama-3-8B_0_EN.json @@ -13,7 +13,7 @@ "language": "en_zh_ja_fr_ru_es" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p3", "CPS": 10.650944 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Henrychur/MMed-Llama-3-8B_0_GR.json b/e3c_llm_results/Henrychur/MMed-Llama-3-8B_0_GR.json index ace63ca20b3d70142e4daf17f411d4b272b2534f..46934473a835ffb1b03ee0650e818e3bbf5a3592 100644 --- a/e3c_llm_results/Henrychur/MMed-Llama-3-8B_0_GR.json +++ b/e3c_llm_results/Henrychur/MMed-Llama-3-8B_0_GR.json @@ -13,7 +13,7 @@ "language": "en_zh_ja_fr_ru_es" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 6.194213333333334 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Henrychur/MMed-Llama-3-8B_0_IT.json b/e3c_llm_results/Henrychur/MMed-Llama-3-8B_0_IT.json index 751d803c11a77df8c3cb25104fc0e40e2ce49039..2c45c8327f37738538c9a2d22c561e6cce5122ba 100644 --- a/e3c_llm_results/Henrychur/MMed-Llama-3-8B_0_IT.json +++ b/e3c_llm_results/Henrychur/MMed-Llama-3-8B_0_IT.json @@ -13,7 +13,7 @@ "language": "en_zh_ja_fr_ru_es" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 4.341735 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Henrychur/MMed-Llama-3-8B_0_PL.json b/e3c_llm_results/Henrychur/MMed-Llama-3-8B_0_PL.json index 48a53fe5be2f937e408f8fe6491e4fd9cbd86421..37405e6ce398ae13f9a5ef49756ab32596976e92 100644 --- a/e3c_llm_results/Henrychur/MMed-Llama-3-8B_0_PL.json +++ b/e3c_llm_results/Henrychur/MMed-Llama-3-8B_0_PL.json @@ -13,7 +13,7 @@ "language": "en_zh_ja_fr_ru_es" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 3.7898736666666673 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Henrychur/MMed-Llama-3-8B_0_SK.json b/e3c_llm_results/Henrychur/MMed-Llama-3-8B_0_SK.json index 31975398d337d6036af1e177744f0559e63e6b23..f0540dea613db509477cd214e73035df107270b2 100644 --- a/e3c_llm_results/Henrychur/MMed-Llama-3-8B_0_SK.json +++ b/e3c_llm_results/Henrychur/MMed-Llama-3-8B_0_SK.json @@ -13,7 +13,7 @@ "language": "en_zh_ja_fr_ru_es" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 3.8690969999999996 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Henrychur/MMed-Llama-3-8B_0_SL.json b/e3c_llm_results/Henrychur/MMed-Llama-3-8B_0_SL.json index 5927ff7b3634f50ff5fb3661bfda533bd7018936..d4368cb1b572d1a4b5fbaa80fb0de48b42a9b647 100644 --- a/e3c_llm_results/Henrychur/MMed-Llama-3-8B_0_SL.json +++ b/e3c_llm_results/Henrychur/MMed-Llama-3-8B_0_SL.json @@ -13,7 +13,7 @@ "language": "en_zh_ja_fr_ru_es" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 4.551792000000001 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Henrychur/MMed-Llama-3-8B_10_EN.json b/e3c_llm_results/Henrychur/MMed-Llama-3-8B_10_EN.json index dd0d69af45a60908b4826c488192817e762b6440..ea2480978d039f1b1f7e74c77f0e125646b09c10 100644 --- a/e3c_llm_results/Henrychur/MMed-Llama-3-8B_10_EN.json +++ b/e3c_llm_results/Henrychur/MMed-Llama-3-8B_10_EN.json @@ -13,7 +13,7 @@ "language": "en_zh_ja_fr_ru_es" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 22.203457 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Henrychur/MMed-Llama-3-8B_10_GR.json b/e3c_llm_results/Henrychur/MMed-Llama-3-8B_10_GR.json index 3f20942216ac328fa6a0a7a428069b719a43064e..798fc19f73b5d02b86780d34c25500074a98f950 100644 --- a/e3c_llm_results/Henrychur/MMed-Llama-3-8B_10_GR.json +++ b/e3c_llm_results/Henrychur/MMed-Llama-3-8B_10_GR.json @@ -13,7 +13,7 @@ "language": "en_zh_ja_fr_ru_es" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 16.348824666666665 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Henrychur/MMed-Llama-3-8B_10_IT.json b/e3c_llm_results/Henrychur/MMed-Llama-3-8B_10_IT.json index 358d60201a9ae6fa373e07f60101f10d944b9298..5710e85897fdd42598eecf823cf2d276238e0e9d 100644 --- a/e3c_llm_results/Henrychur/MMed-Llama-3-8B_10_IT.json +++ b/e3c_llm_results/Henrychur/MMed-Llama-3-8B_10_IT.json @@ -13,7 +13,7 @@ "language": "en_zh_ja_fr_ru_es" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 39.145131 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Henrychur/MMed-Llama-3-8B_10_PL.json b/e3c_llm_results/Henrychur/MMed-Llama-3-8B_10_PL.json index fd9f2220c73c3d0f107be883ed542c8aa0848b7a..5525632c7e620b509384edeacb8f3270a50bf804 100644 --- a/e3c_llm_results/Henrychur/MMed-Llama-3-8B_10_PL.json +++ b/e3c_llm_results/Henrychur/MMed-Llama-3-8B_10_PL.json @@ -13,7 +13,7 @@ "language": "en_zh_ja_fr_ru_es" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 39.81886933333333 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Henrychur/MMed-Llama-3-8B_10_SK.json b/e3c_llm_results/Henrychur/MMed-Llama-3-8B_10_SK.json index 5064fd7a0db765a5fc1b37ecb99f508152229002..fcec849e5324f8bdfd26768368482acde7395f7f 100644 --- a/e3c_llm_results/Henrychur/MMed-Llama-3-8B_10_SK.json +++ b/e3c_llm_results/Henrychur/MMed-Llama-3-8B_10_SK.json @@ -13,7 +13,7 @@ "language": "en_zh_ja_fr_ru_es" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 35.864789333333334 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Henrychur/MMed-Llama-3-8B_10_SL.json b/e3c_llm_results/Henrychur/MMed-Llama-3-8B_10_SL.json index 636595445e801787847de9ab439dd6218cd3634c..4c1ebdcce253b5b57c4465de0e0584621709931d 100644 --- a/e3c_llm_results/Henrychur/MMed-Llama-3-8B_10_SL.json +++ b/e3c_llm_results/Henrychur/MMed-Llama-3-8B_10_SL.json @@ -13,7 +13,7 @@ "language": "en_zh_ja_fr_ru_es" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 39.136723333333336 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/HiTZ/Medical-mT5-large_0_EN.json b/e3c_llm_results/HiTZ/Medical-mT5-large_0_EN.json index 0f6673eff28267f3ed17fc96cdce3cdb19f23983..df2d5cef5def0f6a81024f93970902e131347a5c 100644 --- a/e3c_llm_results/HiTZ/Medical-mT5-large_0_EN.json +++ b/e3c_llm_results/HiTZ/Medical-mT5-large_0_EN.json @@ -13,7 +13,7 @@ "language": "en_es_fr_it" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 9.060033333333333 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/HiTZ/Medical-mT5-large_0_GR.json b/e3c_llm_results/HiTZ/Medical-mT5-large_0_GR.json index 9a9c25b44bfc28936ac14fc1d0b5fc61ca0e587b..d17115f37138071094310f0a6de0ce1a5ccac8af 100644 --- a/e3c_llm_results/HiTZ/Medical-mT5-large_0_GR.json +++ b/e3c_llm_results/HiTZ/Medical-mT5-large_0_GR.json @@ -13,7 +13,7 @@ "language": "en_es_fr_it" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 8.513262666666666 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/HiTZ/Medical-mT5-large_0_IT.json b/e3c_llm_results/HiTZ/Medical-mT5-large_0_IT.json index 609769757840e31031c216c83609c0fb58e68bfd..f821f49f7870f19cb1f59af29a727562295cc28f 100644 --- a/e3c_llm_results/HiTZ/Medical-mT5-large_0_IT.json +++ b/e3c_llm_results/HiTZ/Medical-mT5-large_0_IT.json @@ -13,7 +13,7 @@ "language": "en_es_fr_it" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 9.100946666666665 }, - "re": { + "RE": { "prompts": [ { "prompt": "p2", diff --git a/e3c_llm_results/HiTZ/Medical-mT5-large_0_PL.json b/e3c_llm_results/HiTZ/Medical-mT5-large_0_PL.json index b6b0fdfc2798f7d2ed8318fc57fd21219dd26dd9..895222ddaac99f8a4615bb18ed46fa7547aa8903 100644 --- a/e3c_llm_results/HiTZ/Medical-mT5-large_0_PL.json +++ b/e3c_llm_results/HiTZ/Medical-mT5-large_0_PL.json @@ -13,7 +13,7 @@ "language": "en_es_fr_it" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 4.3041920000000005 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/HiTZ/Medical-mT5-large_0_SK.json b/e3c_llm_results/HiTZ/Medical-mT5-large_0_SK.json index 76abdb62c09417382bf399e210b1a6286f4db319..218eaa52af3ebdbbcbd29265cab583d722ffdc9f 100644 --- a/e3c_llm_results/HiTZ/Medical-mT5-large_0_SK.json +++ b/e3c_llm_results/HiTZ/Medical-mT5-large_0_SK.json @@ -13,7 +13,7 @@ "language": "en_es_fr_it" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 8.651866666666665 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/HiTZ/Medical-mT5-large_0_SL.json b/e3c_llm_results/HiTZ/Medical-mT5-large_0_SL.json index 7c704fbf7b543a114e7fbd6588af79615ce5da4b..ad806afedb3905cb3e67496fc63ffb51e7520387 100644 --- a/e3c_llm_results/HiTZ/Medical-mT5-large_0_SL.json +++ b/e3c_llm_results/HiTZ/Medical-mT5-large_0_SL.json @@ -13,7 +13,7 @@ "language": "en_es_fr_it" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 7.718718 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/HiTZ/Medical-mT5-large_10_EN.json b/e3c_llm_results/HiTZ/Medical-mT5-large_10_EN.json index 0b869eb5e9b8e61c9c610546869108ebd6e6cb70..a988bb43f6ab23ba3d1f9d6292c70a43460fb0d4 100644 --- a/e3c_llm_results/HiTZ/Medical-mT5-large_10_EN.json +++ b/e3c_llm_results/HiTZ/Medical-mT5-large_10_EN.json @@ -13,7 +13,7 @@ "language": "en_es_fr_it" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 14.011801666666665 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/HiTZ/Medical-mT5-large_10_GR.json b/e3c_llm_results/HiTZ/Medical-mT5-large_10_GR.json index d64a9939172ac6520b0e1898f50ba1e4d82c7952..5076f03e4d6bee03c90dce600a468e881de065c0 100644 --- a/e3c_llm_results/HiTZ/Medical-mT5-large_10_GR.json +++ b/e3c_llm_results/HiTZ/Medical-mT5-large_10_GR.json @@ -13,7 +13,7 @@ "language": "en_es_fr_it" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 14.539814999999999 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/HiTZ/Medical-mT5-large_10_IT.json b/e3c_llm_results/HiTZ/Medical-mT5-large_10_IT.json index 95a213df07cc69129318f22ea3b28fdec2d133a0..7d68a6f7a4a7f35a89a07d7310f58dc81d6d64fa 100644 --- a/e3c_llm_results/HiTZ/Medical-mT5-large_10_IT.json +++ b/e3c_llm_results/HiTZ/Medical-mT5-large_10_IT.json @@ -13,7 +13,7 @@ "language": "en_es_fr_it" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 17.596897333333335 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/HiTZ/Medical-mT5-large_10_PL.json b/e3c_llm_results/HiTZ/Medical-mT5-large_10_PL.json index c491e33d913e9fc01bc75d043ae67e6b2b066dda..3fcb85a483bf3fd0e8debe59378c68608fe22ea3 100644 --- a/e3c_llm_results/HiTZ/Medical-mT5-large_10_PL.json +++ b/e3c_llm_results/HiTZ/Medical-mT5-large_10_PL.json @@ -13,7 +13,7 @@ "language": "en_es_fr_it" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 15.430463999999999 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/HiTZ/Medical-mT5-large_10_SK.json b/e3c_llm_results/HiTZ/Medical-mT5-large_10_SK.json index 0a7f9335270706d66ddcb363625ae35dd4800d28..0787b10790b37d461479e23937a23510088be9a9 100644 --- a/e3c_llm_results/HiTZ/Medical-mT5-large_10_SK.json +++ b/e3c_llm_results/HiTZ/Medical-mT5-large_10_SK.json @@ -13,7 +13,7 @@ "language": "en_es_fr_it" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 14.788124999999999 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/HiTZ/Medical-mT5-large_10_SL.json b/e3c_llm_results/HiTZ/Medical-mT5-large_10_SL.json index 84cb9a99e7cd6d0d20fcd5d2462344fe4145a13b..d17709a39eeba2feaacfe2e95ddbe4ef27a273db 100644 --- a/e3c_llm_results/HiTZ/Medical-mT5-large_10_SL.json +++ b/e3c_llm_results/HiTZ/Medical-mT5-large_10_SL.json @@ -13,7 +13,7 @@ "language": "en_es_fr_it" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 14.62895 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_0_EN.json b/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_0_EN.json index a706e139d17d9ff81b46001fabd5ceb7f30bdea8..1cdc54a8c2cd05b3fcfd7ce10eacdf7bb88adf2b 100644 --- a/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_0_EN.json +++ b/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_0_EN.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 31.08073333333333 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_0_GR.json b/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_0_GR.json index 8b68b4988fb52492c123856b885cc73bb4f74b0d..28522394ede758380a3abe1e1db46b14a5c98299 100644 --- a/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_0_GR.json +++ b/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_0_GR.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 13.323942666666666 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_0_IT.json b/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_0_IT.json index 1438305a5f81b631d8a0ce7a110df4d757e02607..14e002b9a884094b8634b359b62d666612a6bc65 100644 --- a/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_0_IT.json +++ b/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_0_IT.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 23.855067666666667 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_0_PL.json b/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_0_PL.json index 1e8a88dd8ce4f09c1cb9f885c44df045e55df81d..b343ae5f06a17dc984b8450552fb03dd35b90914 100644 --- a/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_0_PL.json +++ b/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_0_PL.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 6.892633 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_0_SK.json b/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_0_SK.json index a8b2ba628e0d14263023f4c8c3fa847baa11d7b0..f5dfab48e9de53b704965af94b51b83e11f122ab 100644 --- a/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_0_SK.json +++ b/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_0_SK.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 11.877106666666666 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_0_SL.json b/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_0_SL.json index 4a09d6ee51209714a91c6cd104e2971306495289..923a3e368758bba9fb1739d661fb63872fc04b4b 100644 --- a/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_0_SL.json +++ b/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_0_SL.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 37.099383333333336 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_10_EN.json b/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_10_EN.json index 980d4ef11372d23cc9f73b762777115140f8dac7..688cbe3f4c7da32a0a536c318924992e30dad2f5 100644 --- a/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_10_EN.json +++ b/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_10_EN.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p3", "CPS": 60.871331000000005 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_10_GR.json b/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_10_GR.json index ff45aaadb12973ee26b2663970ee69b45b925ffa..d5cfc474ac076f71e5220048db98a00b6aefcbcf 100644 --- a/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_10_GR.json +++ b/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_10_GR.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 60.635210666666666 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_10_IT.json b/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_10_IT.json index 582c43f241edc629f90213f1df382d05da2c9513..70df8ef1bd82faacadceec318971c7b386d52768 100644 --- a/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_10_IT.json +++ b/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_10_IT.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 66.18215000000001 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_10_PL.json b/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_10_PL.json index ebbd4f0ad92f29d5842d4b6cb8b40611d66be29f..88a28b36f85352de3ec8799000a7d048b4af6678 100644 --- a/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_10_PL.json +++ b/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_10_PL.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 61.42571600000001 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_10_SK.json b/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_10_SK.json index f69ceea68cf007d4ead062f7cc21849bbae460cd..c14348cbc2d630c7b923f2d562341c048402cade 100644 --- a/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_10_SK.json +++ b/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_10_SK.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 64.4276 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_10_SL.json b/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_10_SL.json index ffb8f7ad74ac2dda6b10b542e2bb20535c6f55a1..2e8e49b9bc1e68464243b969e94f3885925d0a06 100644 --- a/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_10_SL.json +++ b/e3c_llm_results/Qwen/Qwen2.5-14B-Instruct-1M_10_SL.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 64.04701233333334 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_0_EN.json b/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_0_EN.json index 04564e846875360b719d094bf3d3ee67400dc071..abc67fe9fd83ddc5761d1b3dd386127aeaed70f9 100644 --- a/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_0_EN.json +++ b/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_0_EN.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 36.041632 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_0_GR.json b/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_0_GR.json index 166ba224c7cc65815b0e1aa019e58e49ab5d7dc5..98d395fed4d9c8581bbc3ad5ac0f11ddc2d0599d 100644 --- a/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_0_GR.json +++ b/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_0_GR.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 50.979264 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_0_IT.json b/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_0_IT.json index 031c07d7816c6ae3a50cb79289053a4a8f3545d5..4c32c65ecc079690b39748655fa9db2fd8be2f00 100644 --- a/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_0_IT.json +++ b/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_0_IT.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 33.730555333333335 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_0_PL.json b/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_0_PL.json index 4fc14f016f561c435a27524256933199f0c28220..18cb5ec800a3939b7d971eb671c5e385f18131b6 100644 --- a/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_0_PL.json +++ b/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_0_PL.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 24.714983333333333 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_0_SK.json b/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_0_SK.json index 20192716e42bbf13a2fd56c63f17a01176555830..a6f033aa4fa172cbd0557a2bcedc45049cfc7106 100644 --- a/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_0_SK.json +++ b/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_0_SK.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 35.05247333333333 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_0_SL.json b/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_0_SL.json index cb4678a9321a1e07d919ed0b840772d5d4e09ce4..ef28592ea5aca3a11de2bd06ae18a57e9f4bf594 100644 --- a/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_0_SL.json +++ b/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_0_SL.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 32.90384533333333 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_10_EN.json b/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_10_EN.json index eb6c844ebf0d4143c2dc53553d81f7c3d1fb265a..7f7c5ffc1ea40ee3e42fa6e73c3000e65da3d4c0 100644 --- a/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_10_EN.json +++ b/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_10_EN.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p3", "CPS": 59.79736599999999 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_10_GR.json b/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_10_GR.json index a4146a594d84cf4ebdcd77f1818a421df34d4160..0bae92ff5e8b97348c151dcb68efa3203adf0606 100644 --- a/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_10_GR.json +++ b/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_10_GR.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 61.82575333333334 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_10_IT.json b/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_10_IT.json index 429676352665ce1f5771e1e1ed66c1a390811909..2fa19d8261fb781a23a09ec8a146d9dd282d3a9b 100644 --- a/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_10_IT.json +++ b/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_10_IT.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 70.47103999999999 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_10_PL.json b/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_10_PL.json index deb5f66c85e0db50021374a4e1873310f5b7c1ab..863d7b50c8936944694e079960c0346a0ddb96d9 100644 --- a/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_10_PL.json +++ b/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_10_PL.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 60.071989333333335 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_10_SK.json b/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_10_SK.json index cc26f154c3f7e80b6c26dc12eb8b0424a50ff72d..2c3c383fea4b2e089c94d8512372e94d7b91f0f2 100644 --- a/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_10_SK.json +++ b/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_10_SK.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 67.27266333333334 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_10_SL.json b/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_10_SL.json index 741b9be7ed23884e80038bb99df58d42bd70f5c1..00d6d1cdc907776f6d7f2a609186251e46c95ad5 100644 --- a/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_10_SL.json +++ b/e3c_llm_results/Qwen/Qwen2.5-32B-Instruct_10_SL.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 64.55358 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_0_EN.json b/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_0_EN.json index b88657c50b39d6a4d0a9a6c730e9894895550724..3a6a7f8fca9436871a9e9bfd4b23c97795c64cf9 100644 --- a/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_0_EN.json +++ b/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_0_EN.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "re": { + "RE": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 42.82685333333333 }, - "ner": { + "NER": { "prompts": [ { "prompt": "p2", diff --git a/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_0_GR.json b/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_0_GR.json index 0d5cc50b06a1c87e13cc0d2720d09f0701a34980..5d5235692cb2b2a26acac34e0ddead6885b70bdf 100644 --- a/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_0_GR.json +++ b/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_0_GR.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 44.516780000000004 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_0_IT.json b/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_0_IT.json index 55582b6ebaff4465652b9f3d6d02a406bdbc7329..621ba9b6c5c8499b480ca0f2ff13ae3c7f8707cd 100644 --- a/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_0_IT.json +++ b/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_0_IT.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 43.887124 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_0_PL.json b/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_0_PL.json index 82a28507a049c402386737409bf573b89b5c0bd4..8ecf7f428cecbf2bd14164c023305251e7c9c940 100644 --- a/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_0_PL.json +++ b/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_0_PL.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 42.902684 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_0_SK.json b/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_0_SK.json index afc45673f792c9780bd0ab49b8c3ce1a66121e9e..8e99f3289159910ad4036974ff8522a1b6e720e7 100644 --- a/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_0_SK.json +++ b/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_0_SK.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 33.60168933333333 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_0_SL.json b/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_0_SL.json index 825a3e075a631aff84efe4658f0c10f160085f7c..7aafffedea28794cf208c08656cf0da911bb313f 100644 --- a/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_0_SL.json +++ b/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_0_SL.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 45.17407 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_10_EN.json b/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_10_EN.json index d945752b0b2f3fafdd4ccbc5f40e2b675c2d7346..5de18fbfc9ec4cdc6d944ec47a354715d45711d9 100644 --- a/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_10_EN.json +++ b/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_10_EN.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p3", "CPS": 59.98229966666666 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_10_GR.json b/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_10_GR.json index 5f9858db1245a5517bf487198d10072acca3ed03..10d2d191709b8ef5a7f7f711c97b894c42c9d2f9 100644 --- a/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_10_GR.json +++ b/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_10_GR.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 60.62293999999999 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_10_IT.json b/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_10_IT.json index 734bf0a8b86320baa08570dac56bf8fecc43169c..ffa6670eee1e4c959942239ae04e9461debaa43f 100644 --- a/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_10_IT.json +++ b/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_10_IT.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 67.11257566666667 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_10_PL.json b/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_10_PL.json index dcbfd8c20f0c7af2980f30dcb6f2ea439943ff34..a0cc99350012b603cfd7d9fd7180b322f7753354 100644 --- a/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_10_PL.json +++ b/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_10_PL.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 61.770484 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_10_SK.json b/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_10_SK.json index 704b15ee32eea9298093444a0f88131607359c59..c74cdba150a3653cec062b879731ac8ad733f12b 100644 --- a/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_10_SK.json +++ b/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_10_SK.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 60.51329666666666 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_10_SL.json b/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_10_SL.json index c6c624617bd67c5a31629add1d33abb9288b2051..73a7e15324e9b247003bd8046f28a26cadb57b53 100644 --- a/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_10_SL.json +++ b/e3c_llm_results/Qwen/Qwen3-30B-A3B-Instruct-2507_10_SL.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 64.67044499999999 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/deepseek-ai/.ipynb_checkpoints/DeepSeek-R1-Distill-Qwen-32B_0_PL-checkpoint.json b/e3c_llm_results/deepseek-ai/.ipynb_checkpoints/DeepSeek-R1-Distill-Qwen-32B_0_EN-checkpoint.json similarity index 71% rename from e3c_llm_results/deepseek-ai/.ipynb_checkpoints/DeepSeek-R1-Distill-Qwen-32B_0_PL-checkpoint.json rename to e3c_llm_results/deepseek-ai/.ipynb_checkpoints/DeepSeek-R1-Distill-Qwen-32B_0_EN-checkpoint.json index 68dccc70ad202c63fec1d9c87405a8c9b2abba98..9443fb54d23a6e830e20452f33cc1ccc3dbede21 100644 --- a/e3c_llm_results/deepseek-ai/.ipynb_checkpoints/DeepSeek-R1-Distill-Qwen-32B_0_PL-checkpoint.json +++ b/e3c_llm_results/deepseek-ai/.ipynb_checkpoints/DeepSeek-R1-Distill-Qwen-32B_0_EN-checkpoint.json @@ -1,10 +1,10 @@ { - "average_CPS": 39.199796666666664, + "average_CPS": 38.6086025, "config": { "model_name": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", "num_fewshot": "0", "batch_size": 1, - "LANG": "PL", + "LANG": "EN", "model": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", "base_model": "Qwen2ForCausalLM", "revision": "711ad2ea6aa40cfca18895e8aca02ab92df1a746", @@ -13,57 +13,57 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", "metric": "f1", - "value": 32.04, + "value": 19.63, "stderr": 0.0 }, { "prompt": "p2", "metric": "f1", - "value": 37.28, + "value": 34.589999999999996, "stderr": 0.0 }, { "prompt": "p3", "metric": "f1", - "value": 32.04, + "value": 32.08, "stderr": 0.0 } ], - "average_accuracy": 33.78666666666667, - "best_prompt": 37.28, + "average_accuracy": 28.766666666666666, + "best_prompt": 34.589999999999996, "prompt_id": "p2", - "CPS": 35.97768533333333 + "CPS": 32.575708999999996 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", "metric": "f1", - "value": 39.83, + "value": 44.87, "stderr": 0.0 }, { "prompt": "p2", "metric": "f1", - "value": 43.269999999999996, + "value": 44.92, "stderr": 0.0 }, { "prompt": "p3", "metric": "f1", - "value": 40.83, + "value": 43.11, "stderr": 0.0 } ], - "average_accuracy": 41.309999999999995, - "best_prompt": 43.269999999999996, + "average_accuracy": 44.300000000000004, + "best_prompt": 44.92, "prompt_id": "p2", - "CPS": 42.421907999999995 + "CPS": 44.641496000000004 } } } \ No newline at end of file diff --git a/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_0_EN.json b/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_0_EN.json index 1115fa70ea48e2159da9da0029bf77500d1eeacf..9443fb54d23a6e830e20452f33cc1ccc3dbede21 100644 --- a/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_0_EN.json +++ b/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_0_EN.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 32.575708999999996 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_0_GR.json b/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_0_GR.json index 26984211d447010e940703c23b7c13b204043789..ebaed835667bfa55463e8bd63065dc42e82a37e1 100644 --- a/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_0_GR.json +++ b/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_0_GR.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 34.433681666666665 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_0_IT.json b/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_0_IT.json index 817874aed3d653ea123194a098b4c69676baadf9..c623fc8b460f424bb49439700c29cbae22bfb0b4 100644 --- a/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_0_IT.json +++ b/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_0_IT.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 34.438336 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_0_PL.json b/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_0_PL.json index 68dccc70ad202c63fec1d9c87405a8c9b2abba98..2676754bc09347f8f4118a2aa9b8e4464ebc04e4 100644 --- a/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_0_PL.json +++ b/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_0_PL.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 35.97768533333333 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_0_SK.json b/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_0_SK.json index f12f032decd06a533a7c615b24ca92ee9c913d1e..0f437e9c81034e31bffd74755a079d792d8cd66c 100644 --- a/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_0_SK.json +++ b/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_0_SK.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 27.418667999999997 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_0_SL.json b/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_0_SL.json index de06a880e84bd661d7fa15e62b449db205eb358c..c2730c60754fcf3b445979e83232805eb9996ee7 100644 --- a/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_0_SL.json +++ b/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_0_SL.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 27.521140000000003 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_10_EN.json b/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_10_EN.json index c94eeacb050d30d24874bb8e98b60d2e9f07be97..2333becdd494f34a1cc9ea218685238e180c08ae 100644 --- a/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_10_EN.json +++ b/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_10_EN.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 59.870528 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_10_GR.json b/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_10_GR.json index 5c4d8c668c6d4eee0f9417d199ea0721ee501bf8..7f68ed42d5b6dc6a22dca3c2c26dfd0afc13a196 100644 --- a/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_10_GR.json +++ b/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_10_GR.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 59.019168 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_10_IT.json b/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_10_IT.json index c99f3f127ff28ed47526ce1e73e17864ab53470a..d469a75368b2a518562ccc911a0a957a722cd8b4 100644 --- a/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_10_IT.json +++ b/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_10_IT.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 68.99379666666667 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_10_PL.json b/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_10_PL.json index 34dd20506cfa325fb264db8313cfb4ffa2771791..c0781d3cf163160677e909dfa5d081124e3855d8 100644 --- a/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_10_PL.json +++ b/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_10_PL.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 61.98672133333332 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_10_SK.json b/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_10_SK.json index 012b6c30601a091071e9134aa3b0e484f453ba4b..68b7731551528182c86059495e8503c1ec21ceb5 100644 --- a/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_10_SK.json +++ b/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_10_SK.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 63.182269333333345 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_10_SL.json b/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_10_SL.json index ff670060bd8319e46bffe886a80b2b27a4a5ad37..fbb0ba642dd08cde680dad6026daa9777865b931 100644 --- a/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_10_SL.json +++ b/e3c_llm_results/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B_10_SL.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 60.35288933333334 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/epfl-llm/meditron-7b_0_EN.json b/e3c_llm_results/epfl-llm/meditron-7b_0_EN.json index 331643983228b9ce4b7e3fe2e5fc467134f796e7..e82541630f5756da51e91eae2580a9551d335a90 100644 --- a/e3c_llm_results/epfl-llm/meditron-7b_0_EN.json +++ b/e3c_llm_results/epfl-llm/meditron-7b_0_EN.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p3", "CPS": 8.279872000000001 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/epfl-llm/meditron-7b_0_GR.json b/e3c_llm_results/epfl-llm/meditron-7b_0_GR.json index d80de856369cab5f2fd8a820e7b70264003b667f..e46b2fc6098efde35dd9c59ea5a7a12c4b985e48 100644 --- a/e3c_llm_results/epfl-llm/meditron-7b_0_GR.json +++ b/e3c_llm_results/epfl-llm/meditron-7b_0_GR.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 24.387654666666666 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/epfl-llm/meditron-7b_0_IT.json b/e3c_llm_results/epfl-llm/meditron-7b_0_IT.json index db8552c2e5205148ada5a7aeabbcda9e5403c472..6b1199416d61cf7eb8da6d6bfaeae14a514bbb9a 100644 --- a/e3c_llm_results/epfl-llm/meditron-7b_0_IT.json +++ b/e3c_llm_results/epfl-llm/meditron-7b_0_IT.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 7.626160333333333 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/epfl-llm/meditron-7b_0_PL.json b/e3c_llm_results/epfl-llm/meditron-7b_0_PL.json index d621f76c801ec1cf9de0d0d7de2d8213b1768a2d..433136d11aa7e75af354ec87bf5564002610ef38 100644 --- a/e3c_llm_results/epfl-llm/meditron-7b_0_PL.json +++ b/e3c_llm_results/epfl-llm/meditron-7b_0_PL.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 11.979474000000002 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/epfl-llm/meditron-7b_0_SK.json b/e3c_llm_results/epfl-llm/meditron-7b_0_SK.json index 86b454df6aa8be6d9fdf83599932ab839a4b3da4..c1088a80244410d5643344fd84cb21aef85cbccd 100644 --- a/e3c_llm_results/epfl-llm/meditron-7b_0_SK.json +++ b/e3c_llm_results/epfl-llm/meditron-7b_0_SK.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 8.656096 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/epfl-llm/meditron-7b_0_SL.json b/e3c_llm_results/epfl-llm/meditron-7b_0_SL.json index 00247b291ae9201b1e8121580372b79ab0658fa0..e14c8cd313fd6f7b95ea2e1c72a4de13c6fa791a 100644 --- a/e3c_llm_results/epfl-llm/meditron-7b_0_SL.json +++ b/e3c_llm_results/epfl-llm/meditron-7b_0_SL.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 11.675937000000001 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/epfl-llm/meditron-7b_10_EN.json b/e3c_llm_results/epfl-llm/meditron-7b_10_EN.json index 96677630ce61b99e58ea81b8e93cd5a76128dc4a..434a5329b12aece570f1653c203c6d90d132951b 100644 --- a/e3c_llm_results/epfl-llm/meditron-7b_10_EN.json +++ b/e3c_llm_results/epfl-llm/meditron-7b_10_EN.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 14.444407000000002 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/epfl-llm/meditron-7b_10_GR.json b/e3c_llm_results/epfl-llm/meditron-7b_10_GR.json index e4d86751d45f813987e29672710c1f53186a0dcc..6baca6a43c7ffb81f47740fc6aab100082d5b1e2 100644 --- a/e3c_llm_results/epfl-llm/meditron-7b_10_GR.json +++ b/e3c_llm_results/epfl-llm/meditron-7b_10_GR.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 0.0 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/epfl-llm/meditron-7b_10_IT.json b/e3c_llm_results/epfl-llm/meditron-7b_10_IT.json index 059144e00a5496a1ccf7640177e1e0063bd39b2c..7031881141abb2a27198e9213d39c3dfd04074cb 100644 --- a/e3c_llm_results/epfl-llm/meditron-7b_10_IT.json +++ b/e3c_llm_results/epfl-llm/meditron-7b_10_IT.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 34.651362666666664 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/epfl-llm/meditron-7b_10_PL.json b/e3c_llm_results/epfl-llm/meditron-7b_10_PL.json index 0f954175b73d882e48dd8a76b6bb7d771971cdcd..6d10f8a603bb645cb8f7878e792ae3f4f5f3b330 100644 --- a/e3c_llm_results/epfl-llm/meditron-7b_10_PL.json +++ b/e3c_llm_results/epfl-llm/meditron-7b_10_PL.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 32.721626 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/epfl-llm/meditron-7b_10_SK.json b/e3c_llm_results/epfl-llm/meditron-7b_10_SK.json index ee8e0981aa2d878b6166738df9c83b7b2e7a07df..f863ae30b498c369fe5313b55c180baed455017a 100644 --- a/e3c_llm_results/epfl-llm/meditron-7b_10_SK.json +++ b/e3c_llm_results/epfl-llm/meditron-7b_10_SK.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 30.005954666666668 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/epfl-llm/meditron-7b_10_SL.json b/e3c_llm_results/epfl-llm/meditron-7b_10_SL.json index b1d0c6247efcb7da38104f3b91a5aad8a2b8a629..cb031f581ed64e83aa508b1434f11d9477dfec7a 100644 --- a/e3c_llm_results/epfl-llm/meditron-7b_10_SL.json +++ b/e3c_llm_results/epfl-llm/meditron-7b_10_SL.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 30.978947666666667 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/gemma-2-9b-it_0_EN.json b/e3c_llm_results/google/gemma-2-9b-it_0_EN.json index bf45d6b410264a81d53d1e0689390e8a1cbd6d8b..7b5ea61ddf5254922257c58258b8a74bd284a13c 100644 --- a/e3c_llm_results/google/gemma-2-9b-it_0_EN.json +++ b/e3c_llm_results/google/gemma-2-9b-it_0_EN.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p3", "CPS": 49.584790000000005 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/gemma-2-9b-it_0_GR.json b/e3c_llm_results/google/gemma-2-9b-it_0_GR.json index eb3cad84202f239566048211c3ab20d87c812cb0..a3a49bcb2c37c253e9218a06801bd3fc58c37542 100644 --- a/e3c_llm_results/google/gemma-2-9b-it_0_GR.json +++ b/e3c_llm_results/google/gemma-2-9b-it_0_GR.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 54.06205733333333 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/gemma-2-9b-it_0_IT.json b/e3c_llm_results/google/gemma-2-9b-it_0_IT.json index 338e0244dedd57856946c40010229327fc27e344..64c3f144a8ebc59f5bc551b43992496a059f44b6 100644 --- a/e3c_llm_results/google/gemma-2-9b-it_0_IT.json +++ b/e3c_llm_results/google/gemma-2-9b-it_0_IT.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 62.85004133333333 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/gemma-2-9b-it_0_PL.json b/e3c_llm_results/google/gemma-2-9b-it_0_PL.json index b0688f7b2df1b4ad1b2e8098f9feaa75a2c2dd81..8c574103fa989c0e877cfe8ae56e3e9f973279ac 100644 --- a/e3c_llm_results/google/gemma-2-9b-it_0_PL.json +++ b/e3c_llm_results/google/gemma-2-9b-it_0_PL.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 41.28685 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/gemma-2-9b-it_0_SK.json b/e3c_llm_results/google/gemma-2-9b-it_0_SK.json index aa861a173d7daaf73ab92a101e58293814c6026d..68c81ec7fbe90d9da66b5c7b8e8e4e5d670c9b68 100644 --- a/e3c_llm_results/google/gemma-2-9b-it_0_SK.json +++ b/e3c_llm_results/google/gemma-2-9b-it_0_SK.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 48.2625 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/gemma-2-9b-it_0_SL.json b/e3c_llm_results/google/gemma-2-9b-it_0_SL.json index a62fbfa62d7292d0fad7e189a09e02b6239819c1..293853a75701a2b24ce483ca57b4b063fe2a7b39 100644 --- a/e3c_llm_results/google/gemma-2-9b-it_0_SL.json +++ b/e3c_llm_results/google/gemma-2-9b-it_0_SL.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 46.032891 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/gemma-2-9b-it_10_EN.json b/e3c_llm_results/google/gemma-2-9b-it_10_EN.json index 2a1c47e896bc69b1abe3c369899c40a0199913b2..cc2ad75233b19512ad0e9566419d36068a722532 100644 --- a/e3c_llm_results/google/gemma-2-9b-it_10_EN.json +++ b/e3c_llm_results/google/gemma-2-9b-it_10_EN.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 60.257799999999996 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/gemma-2-9b-it_10_GR.json b/e3c_llm_results/google/gemma-2-9b-it_10_GR.json index d72281ce42496d5e93ba1fa1bfdea23bae73581c..0bba7406aa35200f7ea3dc465af5fde82f3e4925 100644 --- a/e3c_llm_results/google/gemma-2-9b-it_10_GR.json +++ b/e3c_llm_results/google/gemma-2-9b-it_10_GR.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 59.978379999999994 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/gemma-2-9b-it_10_IT.json b/e3c_llm_results/google/gemma-2-9b-it_10_IT.json index 61a38ce67f438143898a12d83df180d28a3912b9..5a0cdb8b6d62f4718c31f660903e246d14effa82 100644 --- a/e3c_llm_results/google/gemma-2-9b-it_10_IT.json +++ b/e3c_llm_results/google/gemma-2-9b-it_10_IT.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 67.69957333333333 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/gemma-2-9b-it_10_PL.json b/e3c_llm_results/google/gemma-2-9b-it_10_PL.json index e9f069f5bcc8f192dc889af8b7c2c2f45a4fbca7..bf494b9a6cb7e1aa37d080b22c9228d6192d8a6e 100644 --- a/e3c_llm_results/google/gemma-2-9b-it_10_PL.json +++ b/e3c_llm_results/google/gemma-2-9b-it_10_PL.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 58.98941066666667 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/gemma-2-9b-it_10_SK.json b/e3c_llm_results/google/gemma-2-9b-it_10_SK.json index 2fbe3145867d01e281bb2b66559db9eff2af319e..aa0fae50b3fef12bdfedd530ed4b7fcaf9e8fbb6 100644 --- a/e3c_llm_results/google/gemma-2-9b-it_10_SK.json +++ b/e3c_llm_results/google/gemma-2-9b-it_10_SK.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 61.371106999999995 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/gemma-2-9b-it_10_SL.json b/e3c_llm_results/google/gemma-2-9b-it_10_SL.json index 57eb906afa46c50d46f49f42ab3b6fe949d1d954..a3f3562b3e48f6decc3ba27495b4e0ca19f77d6e 100644 --- a/e3c_llm_results/google/gemma-2-9b-it_10_SL.json +++ b/e3c_llm_results/google/gemma-2-9b-it_10_SL.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 62.31759333333333 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/gemma-3-27b-it_0_EN.json b/e3c_llm_results/google/gemma-3-27b-it_0_EN.json index d64ce0e5f4b1a3a1c7a110fc652dbb3067648ba4..af7286d3941ae9d09182310991fcf45796a7a2ab 100644 --- a/e3c_llm_results/google/gemma-3-27b-it_0_EN.json +++ b/e3c_llm_results/google/gemma-3-27b-it_0_EN.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 56.3178 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/gemma-3-27b-it_0_GR.json b/e3c_llm_results/google/gemma-3-27b-it_0_GR.json index c7608c89b95a9b573aa92dfcb6b71a711794db0a..57f5fce3e48473d1150218b62964e4d9a27b9c69 100644 --- a/e3c_llm_results/google/gemma-3-27b-it_0_GR.json +++ b/e3c_llm_results/google/gemma-3-27b-it_0_GR.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 53.94903000000001 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/gemma-3-27b-it_0_IT.json b/e3c_llm_results/google/gemma-3-27b-it_0_IT.json index a1c986af3a03e9510c0d853057a23bbc21b3ad5f..dd110f42cc6d62942b3a0db4684a57a2bb96e159 100644 --- a/e3c_llm_results/google/gemma-3-27b-it_0_IT.json +++ b/e3c_llm_results/google/gemma-3-27b-it_0_IT.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 62.73526366666667 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/gemma-3-27b-it_0_PL.json b/e3c_llm_results/google/gemma-3-27b-it_0_PL.json index d40e27aa90d3d6c757f72ebdb7bcccec5282dbdb..7b0569f8e12ef06b8b2a03c6a3320f0624580425 100644 --- a/e3c_llm_results/google/gemma-3-27b-it_0_PL.json +++ b/e3c_llm_results/google/gemma-3-27b-it_0_PL.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 45.09496333333333 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/gemma-3-27b-it_0_SK.json b/e3c_llm_results/google/gemma-3-27b-it_0_SK.json index d47ed61406c00ff429886925305611ba87a9eeeb..e06cfef6bc90db6e038c33f31af47a8a8b26853b 100644 --- a/e3c_llm_results/google/gemma-3-27b-it_0_SK.json +++ b/e3c_llm_results/google/gemma-3-27b-it_0_SK.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 30.741414000000002 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/gemma-3-27b-it_0_SL.json b/e3c_llm_results/google/gemma-3-27b-it_0_SL.json index 6bd284fccd9162348b3657f15ec506ff69fda58e..9d3ffdae1b80b261b72c163b99fa145ed7818d28 100644 --- a/e3c_llm_results/google/gemma-3-27b-it_0_SL.json +++ b/e3c_llm_results/google/gemma-3-27b-it_0_SL.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 46.513080666666674 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/gemma-3-27b-it_10_EN.json b/e3c_llm_results/google/gemma-3-27b-it_10_EN.json index 8a68c7d453d7a914032504b668104de36291df97..39851139187b27808e4d7f952fb8d85d50a5e5c7 100644 --- a/e3c_llm_results/google/gemma-3-27b-it_10_EN.json +++ b/e3c_llm_results/google/gemma-3-27b-it_10_EN.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 62.318834666666675 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/gemma-3-27b-it_10_GR.json b/e3c_llm_results/google/gemma-3-27b-it_10_GR.json index fb65103d364a4feae35a872c0677bd4d92da6f4b..a6109ef1b3e6581047d1257034f65ac2c9c1866f 100644 --- a/e3c_llm_results/google/gemma-3-27b-it_10_GR.json +++ b/e3c_llm_results/google/gemma-3-27b-it_10_GR.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 65.828896 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/gemma-3-27b-it_10_IT.json b/e3c_llm_results/google/gemma-3-27b-it_10_IT.json index dc6f89824afe7665fc4d1adf165cd4a2c8de28f7..72bd21009a82814bac749f05afecd68b1a1ce129 100644 --- a/e3c_llm_results/google/gemma-3-27b-it_10_IT.json +++ b/e3c_llm_results/google/gemma-3-27b-it_10_IT.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p3", "CPS": 71.42284 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/gemma-3-27b-it_10_PL.json b/e3c_llm_results/google/gemma-3-27b-it_10_PL.json index bead1cad147ec714c27d9740da60d6e809aa882b..9a90d98c694bde491a52c642376e96ffc7b4aa27 100644 --- a/e3c_llm_results/google/gemma-3-27b-it_10_PL.json +++ b/e3c_llm_results/google/gemma-3-27b-it_10_PL.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 66.35971199999999 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/gemma-3-27b-it_10_SK.json b/e3c_llm_results/google/gemma-3-27b-it_10_SK.json index 1c04043b51947a6fd1f3e318d625de621a85f219..49c3469167d1730e3a4b64251d858dbb86bac7f2 100644 --- a/e3c_llm_results/google/gemma-3-27b-it_10_SK.json +++ b/e3c_llm_results/google/gemma-3-27b-it_10_SK.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 68.17067999999999 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/gemma-3-27b-it_10_SL.json b/e3c_llm_results/google/gemma-3-27b-it_10_SL.json index 6d2ace6f7eb48518649c7907ae57aec4a4469b8d..1a4bf277bd953b6dbafae6009a4de844f3c955ae 100644 --- a/e3c_llm_results/google/gemma-3-27b-it_10_SL.json +++ b/e3c_llm_results/google/gemma-3-27b-it_10_SL.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 68.405184 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/medgemma-27b-text-it_0_EN.json b/e3c_llm_results/google/medgemma-27b-text-it_0_EN.json index 3f4cd952f4fda1e9ce50f89d395a8d60bf6957ac..ff6e165be2cc649edeaf18aa977f6b6696c1b862 100644 --- a/e3c_llm_results/google/medgemma-27b-text-it_0_EN.json +++ b/e3c_llm_results/google/medgemma-27b-text-it_0_EN.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 54.170159999999996 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/medgemma-27b-text-it_0_GR.json b/e3c_llm_results/google/medgemma-27b-text-it_0_GR.json index f13143d9ac5e2e7eb7aa339f7117855e133da2cf..6d2c404a27a9347989f54f4ac0833bdebd120aee 100644 --- a/e3c_llm_results/google/medgemma-27b-text-it_0_GR.json +++ b/e3c_llm_results/google/medgemma-27b-text-it_0_GR.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 57.943792 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/medgemma-27b-text-it_0_IT.json b/e3c_llm_results/google/medgemma-27b-text-it_0_IT.json index 85d4c2b955d9109dac24600175bc519b95b330a9..ba2d095e7a6e810b9ca77a6a77ddd42bff04b9ad 100644 --- a/e3c_llm_results/google/medgemma-27b-text-it_0_IT.json +++ b/e3c_llm_results/google/medgemma-27b-text-it_0_IT.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 56.77560933333334 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/medgemma-27b-text-it_0_PL.json b/e3c_llm_results/google/medgemma-27b-text-it_0_PL.json index 1594c071a37c857b3035ebd0c555f749048d7d30..1f30f15180aaafee89b21659d43aaad0a2f00407 100644 --- a/e3c_llm_results/google/medgemma-27b-text-it_0_PL.json +++ b/e3c_llm_results/google/medgemma-27b-text-it_0_PL.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 42.780426 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/medgemma-27b-text-it_0_SK.json b/e3c_llm_results/google/medgemma-27b-text-it_0_SK.json index 33d47a87d2b164424187aced2cd531d8aadf1aaf..da892b37ce4b87a7741604689fae122e3e7802d3 100644 --- a/e3c_llm_results/google/medgemma-27b-text-it_0_SK.json +++ b/e3c_llm_results/google/medgemma-27b-text-it_0_SK.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 27.823414999999997 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/medgemma-27b-text-it_0_SL.json b/e3c_llm_results/google/medgemma-27b-text-it_0_SL.json index 0f7f99959d4458ce3cb4757738c2f10f8ff54739..15a0929f20159962ee110f91f9dcfcff66cae370 100644 --- a/e3c_llm_results/google/medgemma-27b-text-it_0_SL.json +++ b/e3c_llm_results/google/medgemma-27b-text-it_0_SL.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 50.414004 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/medgemma-27b-text-it_10_EN.json b/e3c_llm_results/google/medgemma-27b-text-it_10_EN.json index f2aa5f156979a7fe28ac6861596dce98dfdaa1c3..8f37ddd9d98878decba3c075bd569bdddd6e8706 100644 --- a/e3c_llm_results/google/medgemma-27b-text-it_10_EN.json +++ b/e3c_llm_results/google/medgemma-27b-text-it_10_EN.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p3", "CPS": 63.70224333333332 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/medgemma-27b-text-it_10_GR.json b/e3c_llm_results/google/medgemma-27b-text-it_10_GR.json index d38f87e279e73c26d67480863631bda50390dc06..15883f234d5b4039d2c458f7d80870b1e6583e8f 100644 --- a/e3c_llm_results/google/medgemma-27b-text-it_10_GR.json +++ b/e3c_llm_results/google/medgemma-27b-text-it_10_GR.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 68.41436 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/medgemma-27b-text-it_10_IT.json b/e3c_llm_results/google/medgemma-27b-text-it_10_IT.json index 76310e0c5141b518b3e17ed4f9473cc823df72a9..b93101faf21531e6fd73ddbbefa27657ffb533b4 100644 --- a/e3c_llm_results/google/medgemma-27b-text-it_10_IT.json +++ b/e3c_llm_results/google/medgemma-27b-text-it_10_IT.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -33,7 +33,7 @@ "prompt_id": "p1", "CPS": 71.686833 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/medgemma-27b-text-it_10_PL.json b/e3c_llm_results/google/medgemma-27b-text-it_10_PL.json index 531f67b03eb325cc8de1b028a7f10c2956a3d5c4..484f18476901461347c20029d764b523f15639d4 100644 --- a/e3c_llm_results/google/medgemma-27b-text-it_10_PL.json +++ b/e3c_llm_results/google/medgemma-27b-text-it_10_PL.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 68.030498 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/medgemma-27b-text-it_10_SK.json b/e3c_llm_results/google/medgemma-27b-text-it_10_SK.json index 1cb35f7ef94b0af9408747636209ed338ac3ebcc..6ff6020bc8239293936c81c1ceedeffb517bb34e 100644 --- a/e3c_llm_results/google/medgemma-27b-text-it_10_SK.json +++ b/e3c_llm_results/google/medgemma-27b-text-it_10_SK.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 71.391904 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/medgemma-27b-text-it_10_SL.json b/e3c_llm_results/google/medgemma-27b-text-it_10_SL.json index 03feb9fefb01b93cb04084e4f3b5355eeb571be5..532f06d770ab15eb3fab5a51e5b8da8028ef5876 100644 --- a/e3c_llm_results/google/medgemma-27b-text-it_10_SL.json +++ b/e3c_llm_results/google/medgemma-27b-text-it_10_SL.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 69.04854866666666 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/medgemma-4b-it_0_EN.json b/e3c_llm_results/google/medgemma-4b-it_0_EN.json index 18fd4074023cd571b288201cd24ff20e9302a517..df88f5c4b07c29143e6dbdefaee00b4d2bf91a77 100644 --- a/e3c_llm_results/google/medgemma-4b-it_0_EN.json +++ b/e3c_llm_results/google/medgemma-4b-it_0_EN.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p3", "CPS": 27.063456000000002 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/medgemma-4b-it_0_GR.json b/e3c_llm_results/google/medgemma-4b-it_0_GR.json index 3835892ab50cf74c6c4a63372320d1bb4f8f4b9e..ca6fd8573b8fc354c557b566854465ce92dcbf07 100644 --- a/e3c_llm_results/google/medgemma-4b-it_0_GR.json +++ b/e3c_llm_results/google/medgemma-4b-it_0_GR.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 27.004015 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/medgemma-4b-it_0_IT.json b/e3c_llm_results/google/medgemma-4b-it_0_IT.json index cb98f8f02ae025b72d36db009ebab6d0520533f4..514ce069415cac763ca4a1d6328758c6359ad305 100644 --- a/e3c_llm_results/google/medgemma-4b-it_0_IT.json +++ b/e3c_llm_results/google/medgemma-4b-it_0_IT.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 30.851256333333332 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/medgemma-4b-it_0_PL.json b/e3c_llm_results/google/medgemma-4b-it_0_PL.json index 14c1f5f02728860f4c00666b348cc06d819c4ed8..c4fccc04fc74bd7bc0eb9feea16aea685c9ce998 100644 --- a/e3c_llm_results/google/medgemma-4b-it_0_PL.json +++ b/e3c_llm_results/google/medgemma-4b-it_0_PL.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 22.495880000000003 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/medgemma-4b-it_0_SK.json b/e3c_llm_results/google/medgemma-4b-it_0_SK.json index 39e39c7e167f3fef988796f8ae4a6742f23cf037..e23534e4628922671b0f0b4dd211d9434739834f 100644 --- a/e3c_llm_results/google/medgemma-4b-it_0_SK.json +++ b/e3c_llm_results/google/medgemma-4b-it_0_SK.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 24.421059999999997 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/medgemma-4b-it_0_SL.json b/e3c_llm_results/google/medgemma-4b-it_0_SL.json index b25cdd8ddf43458f8d01a054d249972089a89a2d..7a3493c014bbb6fa2a33185ee23da96e1baf2e9c 100644 --- a/e3c_llm_results/google/medgemma-4b-it_0_SL.json +++ b/e3c_llm_results/google/medgemma-4b-it_0_SL.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 25.726272 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/medgemma-4b-it_10_EN.json b/e3c_llm_results/google/medgemma-4b-it_10_EN.json index 20e519982838ed46b8a34855977c7aa03b943a3c..807748196ed95b23ef9beb177def349cf1649619 100644 --- a/e3c_llm_results/google/medgemma-4b-it_10_EN.json +++ b/e3c_llm_results/google/medgemma-4b-it_10_EN.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 49.672956666666664 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/medgemma-4b-it_10_GR.json b/e3c_llm_results/google/medgemma-4b-it_10_GR.json index 88d7b983e916403ee1eb80b67fd097622abb2126..9eb3f40ba2685801aeb92716d13041033aa52942 100644 --- a/e3c_llm_results/google/medgemma-4b-it_10_GR.json +++ b/e3c_llm_results/google/medgemma-4b-it_10_GR.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 49.956646000000006 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/medgemma-4b-it_10_IT.json b/e3c_llm_results/google/medgemma-4b-it_10_IT.json index 412d9f1fca6b3e81531909a695eea1ce45efcb6e..10aaf80dc8c2c39a4049e39b28ed20897231ba03 100644 --- a/e3c_llm_results/google/medgemma-4b-it_10_IT.json +++ b/e3c_llm_results/google/medgemma-4b-it_10_IT.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 55.321693 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/medgemma-4b-it_10_PL.json b/e3c_llm_results/google/medgemma-4b-it_10_PL.json index 7fed991c7499ee2c17181d350e82c36106bd427b..36cef39e6ce98b8e2408629ead032012867984b6 100644 --- a/e3c_llm_results/google/medgemma-4b-it_10_PL.json +++ b/e3c_llm_results/google/medgemma-4b-it_10_PL.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 51.99058666666666 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/medgemma-4b-it_10_SK.json b/e3c_llm_results/google/medgemma-4b-it_10_SK.json index 2d69fa0e9c70a53e2ea4427554f8ac2718000b67..b34fccb0376282fa798c99e03b66b0b227e575a0 100644 --- a/e3c_llm_results/google/medgemma-4b-it_10_SK.json +++ b/e3c_llm_results/google/medgemma-4b-it_10_SK.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 47.07330266666667 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/google/medgemma-4b-it_10_SL.json b/e3c_llm_results/google/medgemma-4b-it_10_SL.json index 5ce12945def960eefdd10aac3a6b5ea9c1864a4e..5e0d57a9c19ecdd26c6dd5e21eafd1bb53e91109 100644 --- a/e3c_llm_results/google/medgemma-4b-it_10_SL.json +++ b/e3c_llm_results/google/medgemma-4b-it_10_SL.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 50.893682 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/microsoft/MediPhi-Clinical_0_EN.json b/e3c_llm_results/microsoft/MediPhi-Clinical_0_EN.json index c0ae4e930c79065b67d63cfcc6fc4af41c70fba6..98a6e0f785d0df9fdabc0ce2b7dba10c86eb6341 100644 --- a/e3c_llm_results/microsoft/MediPhi-Clinical_0_EN.json +++ b/e3c_llm_results/microsoft/MediPhi-Clinical_0_EN.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 29.955062666666667 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/microsoft/MediPhi-Clinical_0_GR.json b/e3c_llm_results/microsoft/MediPhi-Clinical_0_GR.json index 93d5f8222bb73eac2bb5b7aff34d71b25f65ef97..6a6a11334dacdc148c4c44e3bfc69cd5bda481c9 100644 --- a/e3c_llm_results/microsoft/MediPhi-Clinical_0_GR.json +++ b/e3c_llm_results/microsoft/MediPhi-Clinical_0_GR.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 18.405912 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/microsoft/MediPhi-Clinical_0_IT.json b/e3c_llm_results/microsoft/MediPhi-Clinical_0_IT.json index 2c837b3b6b372cf0b28ffd264f9ff25d7c83b0f6..bed90daaef3864044a73374247b7f6459e17dbac 100644 --- a/e3c_llm_results/microsoft/MediPhi-Clinical_0_IT.json +++ b/e3c_llm_results/microsoft/MediPhi-Clinical_0_IT.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 33.666534666666664 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/microsoft/MediPhi-Clinical_0_PL.json b/e3c_llm_results/microsoft/MediPhi-Clinical_0_PL.json index 2d11b207b3cc06efca3e6c395a7f3e01897a8f76..2f93e127070f8a5949bf8a835c9f160364e26db9 100644 --- a/e3c_llm_results/microsoft/MediPhi-Clinical_0_PL.json +++ b/e3c_llm_results/microsoft/MediPhi-Clinical_0_PL.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 28.522262666666666 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/microsoft/MediPhi-Clinical_0_SK.json b/e3c_llm_results/microsoft/MediPhi-Clinical_0_SK.json index 899fc55a71ca57694da1af13bc8df3e64e248beb..c3d496d955f633bf0be15550f6669da7fb35d1ab 100644 --- a/e3c_llm_results/microsoft/MediPhi-Clinical_0_SK.json +++ b/e3c_llm_results/microsoft/MediPhi-Clinical_0_SK.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 29.041605333333333 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/microsoft/MediPhi-Clinical_0_SL.json b/e3c_llm_results/microsoft/MediPhi-Clinical_0_SL.json index c3a032699b93f22c4d898f1796521a8f166678a9..5c499e998d83a98fe29b6a690c7b6a139a8c41dd 100644 --- a/e3c_llm_results/microsoft/MediPhi-Clinical_0_SL.json +++ b/e3c_llm_results/microsoft/MediPhi-Clinical_0_SL.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 29.662212000000004 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/microsoft/MediPhi-Clinical_10_EN.json b/e3c_llm_results/microsoft/MediPhi-Clinical_10_EN.json index 0df51052f3cd02a20cdbf74ca118988824ed9f34..f344c5490e953ef567e6c28ca7c40b9f4771653c 100644 --- a/e3c_llm_results/microsoft/MediPhi-Clinical_10_EN.json +++ b/e3c_llm_results/microsoft/MediPhi-Clinical_10_EN.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p3", "CPS": 50.282991 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/microsoft/MediPhi-Clinical_10_GR.json b/e3c_llm_results/microsoft/MediPhi-Clinical_10_GR.json index e9f1b1dcb36bd8f0494116bc079fcbbd61eddbdb..5b87eebc7064e75682cca17d008cdafbb96e0343 100644 --- a/e3c_llm_results/microsoft/MediPhi-Clinical_10_GR.json +++ b/e3c_llm_results/microsoft/MediPhi-Clinical_10_GR.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 33.96647733333334 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/microsoft/MediPhi-Clinical_10_IT.json b/e3c_llm_results/microsoft/MediPhi-Clinical_10_IT.json index 9630d4c74c728514fd0ad286528e3704713b91cb..e5cde9d20753a875bd2ceea41c35bb0ed36c6927 100644 --- a/e3c_llm_results/microsoft/MediPhi-Clinical_10_IT.json +++ b/e3c_llm_results/microsoft/MediPhi-Clinical_10_IT.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 52.776756 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/microsoft/MediPhi-Clinical_10_PL.json b/e3c_llm_results/microsoft/MediPhi-Clinical_10_PL.json index dc4149a99351c4d8531026cfbd0d6cf649ed13c8..1f4ddef202d128bacc0fb89d6ac6c5ac8b19d406 100644 --- a/e3c_llm_results/microsoft/MediPhi-Clinical_10_PL.json +++ b/e3c_llm_results/microsoft/MediPhi-Clinical_10_PL.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 40.716727999999996 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/microsoft/MediPhi-Clinical_10_SK.json b/e3c_llm_results/microsoft/MediPhi-Clinical_10_SK.json index c240b904d5cb159530bb49ce9fe4804042ec5d78..a476b0b5b1655bcf1a1d266712f05f09d32a56f7 100644 --- a/e3c_llm_results/microsoft/MediPhi-Clinical_10_SK.json +++ b/e3c_llm_results/microsoft/MediPhi-Clinical_10_SK.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 40.72467666666667 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/microsoft/MediPhi-Clinical_10_SL.json b/e3c_llm_results/microsoft/MediPhi-Clinical_10_SL.json index 9c9595d905cc296e4b02233827f82fbded3a00d7..3fd457471a1622134fdbbcf9dcf3640eb3f5b25b 100644 --- a/e3c_llm_results/microsoft/MediPhi-Clinical_10_SL.json +++ b/e3c_llm_results/microsoft/MediPhi-Clinical_10_SL.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 40.29811466666667 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/microsoft/MediPhi-Instruct_0_EN.json b/e3c_llm_results/microsoft/MediPhi-Instruct_0_EN.json index 6c0779796fa82060b849295643c06df44b0114ef..22ce1987e27b47151de0819e610f8b7a1847b14b 100644 --- a/e3c_llm_results/microsoft/MediPhi-Instruct_0_EN.json +++ b/e3c_llm_results/microsoft/MediPhi-Instruct_0_EN.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 22.144686666666665 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/microsoft/MediPhi-Instruct_0_GR.json b/e3c_llm_results/microsoft/MediPhi-Instruct_0_GR.json index 71d26338cfb4ed5c7793df881f3f0d103a47c271..da244d4097b0eb2f428c05b2766afa2abe199a9e 100644 --- a/e3c_llm_results/microsoft/MediPhi-Instruct_0_GR.json +++ b/e3c_llm_results/microsoft/MediPhi-Instruct_0_GR.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 12.765741333333333 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/microsoft/MediPhi-Instruct_0_IT.json b/e3c_llm_results/microsoft/MediPhi-Instruct_0_IT.json index 292d372190765f390ac4a0824e6ca24e69f82c92..0841f839a64bc0b9b922147ccea62cf26e0a601b 100644 --- a/e3c_llm_results/microsoft/MediPhi-Instruct_0_IT.json +++ b/e3c_llm_results/microsoft/MediPhi-Instruct_0_IT.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p3", "CPS": 25.283496333333332 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/microsoft/MediPhi-Instruct_0_PL.json b/e3c_llm_results/microsoft/MediPhi-Instruct_0_PL.json index 1202eb41e6f940041bb4dd7c92806e504221502e..d310296a6cfd872d87b0ac069ca9720091362f13 100644 --- a/e3c_llm_results/microsoft/MediPhi-Instruct_0_PL.json +++ b/e3c_llm_results/microsoft/MediPhi-Instruct_0_PL.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 16.6096 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/microsoft/MediPhi-Instruct_0_SK.json b/e3c_llm_results/microsoft/MediPhi-Instruct_0_SK.json index 7283b7adc881ac280deb3682387213262b6dca55..e04423fa8fe8a13c7aa56753c7194c337a73e6ea 100644 --- a/e3c_llm_results/microsoft/MediPhi-Instruct_0_SK.json +++ b/e3c_llm_results/microsoft/MediPhi-Instruct_0_SK.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 20.199573333333337 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/microsoft/MediPhi-Instruct_0_SL.json b/e3c_llm_results/microsoft/MediPhi-Instruct_0_SL.json index 3ebdade3147e2a00171743d8bc718167b054e66b..c39fa4962d9c73f16202f4c7c0784db69d3aeb89 100644 --- a/e3c_llm_results/microsoft/MediPhi-Instruct_0_SL.json +++ b/e3c_llm_results/microsoft/MediPhi-Instruct_0_SL.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 18.47352 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/microsoft/MediPhi-Instruct_10_EN.json b/e3c_llm_results/microsoft/MediPhi-Instruct_10_EN.json index a7650bd6ea580b99e5880ff3c71f8844ae1f0c2e..cb974e94763965f9431ddda2a910ecf491835ed0 100644 --- a/e3c_llm_results/microsoft/MediPhi-Instruct_10_EN.json +++ b/e3c_llm_results/microsoft/MediPhi-Instruct_10_EN.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 52.81287733333333 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/microsoft/MediPhi-Instruct_10_GR.json b/e3c_llm_results/microsoft/MediPhi-Instruct_10_GR.json index 09121be062b47a9d9fa8f95b95dae8679fef4653..149452159a6757c747d997062330a34cc2d7812d 100644 --- a/e3c_llm_results/microsoft/MediPhi-Instruct_10_GR.json +++ b/e3c_llm_results/microsoft/MediPhi-Instruct_10_GR.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 29.636117999999996 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/microsoft/MediPhi-Instruct_10_IT.json b/e3c_llm_results/microsoft/MediPhi-Instruct_10_IT.json index 5725a716e2cdc34e293f9fcaf8fe800989401764..24442aca65d8939081dc0f4f5b56077f2ff2a346 100644 --- a/e3c_llm_results/microsoft/MediPhi-Instruct_10_IT.json +++ b/e3c_llm_results/microsoft/MediPhi-Instruct_10_IT.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p3", "CPS": 57.467679999999994 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/microsoft/MediPhi-Instruct_10_PL.json b/e3c_llm_results/microsoft/MediPhi-Instruct_10_PL.json index 163aa7524ca797372574ed3c5c67fa525c589fa2..ac551a4ccca8c6a3595810d2b8eeb92e3c63c894 100644 --- a/e3c_llm_results/microsoft/MediPhi-Instruct_10_PL.json +++ b/e3c_llm_results/microsoft/MediPhi-Instruct_10_PL.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 44.792644 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/microsoft/MediPhi-Instruct_10_SK.json b/e3c_llm_results/microsoft/MediPhi-Instruct_10_SK.json index bd12cc62797182a384cfd307e705454eb5fac735..1e5bb73452f7a115703b74777cc6aa212671bae2 100644 --- a/e3c_llm_results/microsoft/MediPhi-Instruct_10_SK.json +++ b/e3c_llm_results/microsoft/MediPhi-Instruct_10_SK.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 42.831530666666666 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/microsoft/MediPhi-Instruct_10_SL.json b/e3c_llm_results/microsoft/MediPhi-Instruct_10_SL.json index a935ec1eddd79dd152a2cc0e8ace87b73512c462..9c94f5e10660da5c8297852f6617cee1bc56e3b4 100644 --- a/e3c_llm_results/microsoft/MediPhi-Instruct_10_SL.json +++ b/e3c_llm_results/microsoft/MediPhi-Instruct_10_SL.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 39.188347666666665 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_0_EN.json b/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_0_EN.json index 74e5096fed16055fcb6688f2815227b2426bf9d0..09b48d5503371b1651be316f6dbb21ba9fce6c34 100644 --- a/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_0_EN.json +++ b/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_0_EN.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 24.656064 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_0_GR.json b/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_0_GR.json index 6719657cdb412c1a590eecc02936bf8490c96d00..c0ccb63ae51aedbdaaf0f22e88c8d9b6264517f2 100644 --- a/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_0_GR.json +++ b/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_0_GR.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 18.700564 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_0_IT.json b/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_0_IT.json index 6e72b69246cb0cb14bdd742a15d4e5bd0a749f2f..9998fd4cd3f71845aff867c97000e62c1662f5fb 100644 --- a/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_0_IT.json +++ b/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_0_IT.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 26.89026 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_0_PL.json b/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_0_PL.json index ed2764b1f6aa0d0040e55ea28a9166546136c9e4..770eab4c5a5168471cfeb8615bdb4865175d5457 100644 --- a/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_0_PL.json +++ b/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_0_PL.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 30.025296 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_0_SK.json b/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_0_SK.json index 9c30a1c774cfb1ee338ab94043d096ea4d55ba70..fa66c644a134754eac14f412cc230e113ec12ad9 100644 --- a/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_0_SK.json +++ b/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_0_SK.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 21.455708 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_0_SL.json b/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_0_SL.json index fb51bf4f973a10498c0092ba08780e0682e5fe39..cbcfa790d9fef4dd5fa4f1df4c3812eb1511dfbe 100644 --- a/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_0_SL.json +++ b/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_0_SL.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 19.235062000000003 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_10_EN.json b/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_10_EN.json index 331516e5509ecb6d70a8c113a6d4a67d17970c95..b4d5c267aa9fdedd0c8300bdec145f28a6cddb3b 100644 --- a/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_10_EN.json +++ b/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_10_EN.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p3", "CPS": 47.801741666666665 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_10_GR.json b/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_10_GR.json index 0e61eac9dba0617e85484c36930f38adcaf4ff21..1d8702b1dea6caa05a6f0095e103342e26caa583 100644 --- a/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_10_GR.json +++ b/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_10_GR.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 36.1152 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_10_IT.json b/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_10_IT.json index 90e813c542eeb50e89264e9a7bbc1d77d5eb3b0e..f294ab11c5ff34468871a1d005672671f8abd5f2 100644 --- a/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_10_IT.json +++ b/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_10_IT.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 52.027007999999995 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_10_PL.json b/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_10_PL.json index a57782b79c6e9f4213222458c344219974e4c69d..f02babaae462403cb8fb4c5c3844604d6e868c2f 100644 --- a/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_10_PL.json +++ b/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_10_PL.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 50.005860000000006 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_10_SK.json b/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_10_SK.json index 50c353afb467295e60134901013669f36f0ddebd..26c3ccc0f04ecebef572fed9d721e222ecf46582 100644 --- a/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_10_SK.json +++ b/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_10_SK.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 39.974395 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_10_SL.json b/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_10_SL.json index 169954f3903532996acb053dcdc1c21c41c9e80d..06ad9bf9476245acfbc22e97399b4d4521eb42c0 100644 --- a/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_10_SL.json +++ b/e3c_llm_results/mistralai/Mistral-7B-Instruct-v0.2_10_SL.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 41.99796 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_0_EN.json b/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_0_EN.json index 52ede58d4b7e91ba34218b9be8dfa1edc4c1c45f..10e5f5fcc524655d6416f6c912e97e8c9dc3f984 100644 --- a/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_0_EN.json +++ b/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_0_EN.json @@ -13,7 +13,7 @@ "language": "en_fr_de_es_it_pt_ru_zh_ja" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 26.298490333333337 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_0_GR.json b/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_0_GR.json index 450b326d419591181d6f4d3a5569b18fa3bf9e20..96f5e2cf137d493e100323cf6eae12f5103bc8ec 100644 --- a/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_0_GR.json +++ b/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_0_GR.json @@ -13,7 +13,7 @@ "language": "en_fr_de_es_it_pt_ru_zh_ja" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 7.30902 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_0_IT.json b/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_0_IT.json index 77fa35820f9d5c29b775b0a552876c44e6bf6e31..91b0a3a567b60f79a3aca8cb9c914da759c7da05 100644 --- a/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_0_IT.json +++ b/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_0_IT.json @@ -13,7 +13,7 @@ "language": "en_fr_de_es_it_pt_ru_zh_ja" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 25.597056 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_0_PL.json b/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_0_PL.json index 8ace4330841e419b7656d4dc037041e081372b5b..d9583de11950a2782b559d1116c723eff4a969a9 100644 --- a/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_0_PL.json +++ b/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_0_PL.json @@ -13,7 +13,7 @@ "language": "en_fr_de_es_it_pt_ru_zh_ja" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 4.822916 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_0_SK.json b/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_0_SK.json index 66a263277c38d6ee3968141d54319ccd52f50d0d..8a39855286f44c49cdbc166b823a8bd7da6b6400 100644 --- a/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_0_SK.json +++ b/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_0_SK.json @@ -13,7 +13,7 @@ "language": "en_fr_de_es_it_pt_ru_zh_ja" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 8.350536 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_0_SL.json b/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_0_SL.json index a53b24df5563a56c9c9e66d930010cfa94f5240c..990d4a209e6d2c60c4106696857ed0db633b4e2b 100644 --- a/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_0_SL.json +++ b/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_0_SL.json @@ -13,7 +13,7 @@ "language": "en_fr_de_es_it_pt_ru_zh_ja" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 8.593928 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_10_EN.json b/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_10_EN.json index a9ca30e36d1c9ba1200906eb04a3c5ee7dc947b8..040b0ac7667da1f2f949a6ea3df406276253933d 100644 --- a/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_10_EN.json +++ b/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_10_EN.json @@ -13,7 +13,7 @@ "language": "en_fr_de_es_it_pt_ru_zh_ja" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 57.948561 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_10_GR.json b/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_10_GR.json index 30ae9f124005ce43a9410b480b4fc21fe3693645..cc4ef5b88c658086e726d65bb822ff7ee1f2ab9d 100644 --- a/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_10_GR.json +++ b/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_10_GR.json @@ -13,7 +13,7 @@ "language": "en_fr_de_es_it_pt_ru_zh_ja" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 50.652489 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_10_IT.json b/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_10_IT.json index ffeaed0aa24500189694adb019a652ddb50890d4..dfefd924d7c5cf422a1f35cded759cac49d4c45a 100644 --- a/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_10_IT.json +++ b/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_10_IT.json @@ -13,7 +13,7 @@ "language": "en_fr_de_es_it_pt_ru_zh_ja" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p3", "CPS": 64.46884033333333 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_10_PL.json b/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_10_PL.json index 3079ee525824488df6c027190e8557f78d768ea1..4206fa687f230ece8058b8c1b4ae59d4f1167b0c 100644 --- a/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_10_PL.json +++ b/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_10_PL.json @@ -13,7 +13,7 @@ "language": "en_fr_de_es_it_pt_ru_zh_ja" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 53.960634 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_10_SK.json b/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_10_SK.json index f508f2cf049802baf4d56e0a4d146ea9590e3f40..8c45c7dce219c11c5835177a0fef0e3ce5e7fd57 100644 --- a/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_10_SK.json +++ b/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_10_SK.json @@ -13,7 +13,7 @@ "language": "en_fr_de_es_it_pt_ru_zh_ja" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 50.349599999999995 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_10_SL.json b/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_10_SL.json index 8058a5dff8de98a7efe1ce8f45ad024a463ca569..f87c68055b57f56199312bffa491c2af51c48c57 100644 --- a/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_10_SL.json +++ b/e3c_llm_results/mistralai/Mistral-Nemo-Instruct-2407_10_SL.json @@ -13,7 +13,7 @@ "language": "en_fr_de_es_it_pt_ru_zh_ja" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 53.30732 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_0_EN.json b/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_0_EN.json index d7fa5577a054e4c4d05d08e14f8ad47a129e0a2f..2413d2b84467652dbe116bf4931dd1e893652048 100644 --- a/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_0_EN.json +++ b/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_0_EN.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p3", "CPS": 28.948350666666666 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_0_GR.json b/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_0_GR.json index 1cf988506780753209f92d40621e68cbff6f6bca..a4b66d245149e88cc2acb30299099d44d3eda5e5 100644 --- a/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_0_GR.json +++ b/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_0_GR.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 20.13915 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_0_IT.json b/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_0_IT.json index 486acfd28b741977f1049f5415ac79b2550bb88b..02b723a4ef36250504e231fbf43a4a1568f4627c 100644 --- a/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_0_IT.json +++ b/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_0_IT.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p3", "CPS": 23.380933333333335 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_0_PL.json b/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_0_PL.json index 1e782f919c922f0c0eec0ea68327fd937e493722..efc38268895e80d78afe735347e4cec25a212cf0 100644 --- a/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_0_PL.json +++ b/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_0_PL.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 24.426824 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_0_SK.json b/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_0_SK.json index c750e1e3efa704f41a04658a66df1c01fe84f803..80f14bb3307e33e3a63e248e58608f69d5bd07f7 100644 --- a/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_0_SK.json +++ b/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_0_SK.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 30.803294666666666 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_0_SL.json b/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_0_SL.json index de5e2ef6ac90f60b1dce06ad24bb425c268247a6..fc0d9538afb21063d53669859ec1ca6d971c25ed 100644 --- a/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_0_SL.json +++ b/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_0_SL.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 24.630782 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_10_EN.json b/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_10_EN.json index b5e7b6262bac82ece4c4bbb2cd1cdc97089b24aa..747bcb29604ec0e57014eebaa167529d276d4cb3 100644 --- a/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_10_EN.json +++ b/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_10_EN.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p3", "CPS": 58.104279999999996 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_10_GR.json b/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_10_GR.json index d4377d8728ba5a5ae908b22c1af752d7a49704d6..e3fb23fceb939e2d23d052f58cb289fc04356f7d 100644 --- a/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_10_GR.json +++ b/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_10_GR.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 35.79463333333333 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_10_IT.json b/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_10_IT.json index 645b2d6b480189c228afb4c0be89cd567cb864e6..5bdf27224c5e6d54413ebd78381dab3272d8a4d7 100644 --- a/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_10_IT.json +++ b/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_10_IT.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 57.069084 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_10_PL.json b/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_10_PL.json index 91954f0c6a2f324b52b9097bb0303fc5211754cd..6a8fd7dcc417e06e14b79cdf6dd14de9c3745219 100644 --- a/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_10_PL.json +++ b/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_10_PL.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 42.78032533333333 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_10_SK.json b/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_10_SK.json index a459171da36ed4654f83074129d6a78adb9f3393..6dbca7b6d5cf492013ee7048f39596c99d55f411 100644 --- a/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_10_SK.json +++ b/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_10_SK.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 44.800065000000004 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_10_SL.json b/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_10_SL.json index e25214684f52f09b3d42a5e9c1c6ec948dd96485..cd737fe4a1c1052ceecbdd7fb274d4327e6b42ad 100644 --- a/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_10_SL.json +++ b/e3c_llm_results/tiiuae/Falcon3-10B-Instruct_10_SL.json @@ -13,7 +13,7 @@ "language": "" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 40.918782666666665 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/unsloth/.ipynb_checkpoints/phi-4_10_SL-checkpoint.json b/e3c_llm_results/unsloth/.ipynb_checkpoints/phi-4_10_SL-checkpoint.json deleted file mode 100644 index ab7e893b84d037203dcfcba7c1a6c2fef7f044f7..0000000000000000000000000000000000000000 --- a/e3c_llm_results/unsloth/.ipynb_checkpoints/phi-4_10_SL-checkpoint.json +++ /dev/null @@ -1,63 +0,0 @@ -{ - "average_CPS": 53.913512000000004, - "config": { - "model_name": "unsloth/phi-4", - "num_fewshot": "10", - "batch_size": 1, - "LANG": "SL", - "model": "unsloth/phi-4", - "base_model": "LlamaForCausalLM", - "revision": "c6220bde10fff762dbd72c3331894aa4cade249d", - "submitted_time": "2025-01-08 21:56:16+00:00", - "num_params_billion": 14.6595072, - "language": "en" - }, - "tasks": { - "ner": { - "prompts": [ - { - "prompt": "p1", - "metric": "f1", - "value": 55.86, - "stderr": 0.0 - }, - { - "prompt": "p2", - "metric": "f1", - "value": 55.58, - "stderr": 0.0 - }, - { - "prompt": "p3", - "metric": "f1", - "value": 55.86, - "stderr": 0.0 - } - ], - "average_accuracy": 55.76666666666667, - "best_prompt": 55.86, - "prompt_id": "p1", - "CPS": 55.807864 - }, - "re": { - "prompts": [ - { - "prompt": "p1", - "metric": "f1", - "value": 51.17, - "stderr": 0.0 - }, - { - "prompt": "p2", - "metric": "f1", - "value": 52.32, - "stderr": 0.0 - } - ], - "average_accuracy": 51.745000000000005, - "best_prompt": 52.32, - "prompt_id": "p2", - "CPS": 52.01916000000001 - } - } -} \ No newline at end of file diff --git a/e3c_llm_results/unsloth/phi-4_0_EN.json b/e3c_llm_results/unsloth/phi-4_0_EN.json index 92f33f44529c6c1a4e1cd0b895f6c7d3b2a942ac..13f50870e15d60be47bcbe3372c8f160253be831 100644 --- a/e3c_llm_results/unsloth/phi-4_0_EN.json +++ b/e3c_llm_results/unsloth/phi-4_0_EN.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p3", "CPS": 5.549925333333333 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/unsloth/phi-4_0_GR.json b/e3c_llm_results/unsloth/phi-4_0_GR.json index 05d89337bff36f6b158e2f634552675b418a00a0..28b5b848a74b32573aa16eeec5cd9fbc8d9560f1 100644 --- a/e3c_llm_results/unsloth/phi-4_0_GR.json +++ b/e3c_llm_results/unsloth/phi-4_0_GR.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 0.0 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/unsloth/phi-4_0_IT.json b/e3c_llm_results/unsloth/phi-4_0_IT.json index 6e26ae3093925c32149d6e2f3bf7f17d6433f196..34827aa451f82d0a0a881b3dfcdad74347c8e88d 100644 --- a/e3c_llm_results/unsloth/phi-4_0_IT.json +++ b/e3c_llm_results/unsloth/phi-4_0_IT.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p3", "CPS": 28.415834666666665 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/unsloth/phi-4_0_PL.json b/e3c_llm_results/unsloth/phi-4_0_PL.json index aa90d501bcb8fd46119784ae5142abae8480fb81..a87b57aa990def590e05dd8044d0f0c302d89bb9 100644 --- a/e3c_llm_results/unsloth/phi-4_0_PL.json +++ b/e3c_llm_results/unsloth/phi-4_0_PL.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 3.62828 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/unsloth/phi-4_0_SK.json b/e3c_llm_results/unsloth/phi-4_0_SK.json index e019448e08233966028e131fc182396d832c926f..a50726599101df7722e364fe1065962a8e836a80 100644 --- a/e3c_llm_results/unsloth/phi-4_0_SK.json +++ b/e3c_llm_results/unsloth/phi-4_0_SK.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p2", "CPS": 10.162146666666667 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/unsloth/phi-4_0_SL.json b/e3c_llm_results/unsloth/phi-4_0_SL.json index e4f1d858f492b5afc6f070c32200b284266cd874..683c18670b665b52f01bd0d957a2f5d06ae32fe3 100644 --- a/e3c_llm_results/unsloth/phi-4_0_SL.json +++ b/e3c_llm_results/unsloth/phi-4_0_SL.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 26.892856666666667 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/unsloth/phi-4_10_EN.json b/e3c_llm_results/unsloth/phi-4_10_EN.json index 6fadb2859e48671f3d04006c3740f2243bf1be09..eb0adde58a2ebdd3f982acfc747b7b4141139e11 100644 --- a/e3c_llm_results/unsloth/phi-4_10_EN.json +++ b/e3c_llm_results/unsloth/phi-4_10_EN.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p3", "CPS": 60.441769 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/unsloth/phi-4_10_GR.json b/e3c_llm_results/unsloth/phi-4_10_GR.json index 1e8e520d343ada009bd322e341e8633e009a92e4..b5f9c45022f9b3c80b616f9bcd5699076c1b67ce 100644 --- a/e3c_llm_results/unsloth/phi-4_10_GR.json +++ b/e3c_llm_results/unsloth/phi-4_10_GR.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 56.96799933333334 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/unsloth/phi-4_10_IT.json b/e3c_llm_results/unsloth/phi-4_10_IT.json index fa0c532f79c35d1e6eba7397536cf25ae1c276d5..c283cbddc646329830c9e162df8c39c84b103619 100644 --- a/e3c_llm_results/unsloth/phi-4_10_IT.json +++ b/e3c_llm_results/unsloth/phi-4_10_IT.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p3", "CPS": 68.01591499999999 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/unsloth/phi-4_10_PL.json b/e3c_llm_results/unsloth/phi-4_10_PL.json index 900d801d6a7a0752b34896e5e05ce1991e8f738f..3176e3d74c97d71f538a74afc95dc050bb323baa 100644 --- a/e3c_llm_results/unsloth/phi-4_10_PL.json +++ b/e3c_llm_results/unsloth/phi-4_10_PL.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 55.07382499999999 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/unsloth/phi-4_10_SK.json b/e3c_llm_results/unsloth/phi-4_10_SK.json index 5ae34425e6b791d353340c516375b3e919140c1b..daddc042c466749fdbab28df910892ba9607541b 100644 --- a/e3c_llm_results/unsloth/phi-4_10_SK.json +++ b/e3c_llm_results/unsloth/phi-4_10_SK.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 55.40238933333334 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", diff --git a/e3c_llm_results/unsloth/phi-4_10_SL.json b/e3c_llm_results/unsloth/phi-4_10_SL.json index d17aef5dc7249a04394291aa477508a45aa826a1..1b84e88b895fcc0115b87c4d3644b7bc0ac09151 100644 --- a/e3c_llm_results/unsloth/phi-4_10_SL.json +++ b/e3c_llm_results/unsloth/phi-4_10_SL.json @@ -13,7 +13,7 @@ "language": "en" }, "tasks": { - "ner": { + "NER": { "prompts": [ { "prompt": "p1", @@ -39,7 +39,7 @@ "prompt_id": "p1", "CPS": 55.807864 }, - "re": { + "RE": { "prompts": [ { "prompt": "p1", @@ -52,12 +52,6 @@ "metric": "f1", "value": 52.32, "stderr": 0.0 - }, - { - "prompt": "p3", - "metric": "f1", - "value": 52.32, - "stderr": 0.0 } ], "average_accuracy": 51.745000000000005, diff --git a/src/leaderboard/read_evals.py b/src/leaderboard/read_evals.py index 7afaa23edce75f0bc8e20819a4d7f49bafbb649d..f476262efdac83d9c67fd5ef66fd952d9cedd701 100644 --- a/src/leaderboard/read_evals.py +++ b/src/leaderboard/read_evals.py @@ -54,7 +54,7 @@ class EvalResult: fewshot = config.get("num_fewshot", False) Lang=config.get("LANG", "EN") try: - if fewshot == "5": + if fewshot == "10": is_5fewshot = True else: is_5fewshot = False