553 lines
23 KiB
JSON
553 lines
23 KiB
JSON
|
{
|
||
|
|
"results": {
|
||
|
|
"gat": {
|
||
|
|
"acc,none": 0.27994481374639407,
|
||
|
|
"acc_stderr,none": 0.003542796359675536,
|
||
|
|
"alias": "gat"
|
||
|
|
},
|
||
|
|
"gat_algebra": {
|
||
|
|
"alias": " - gat_algebra",
|
||
|
|
"acc,none": 0.2571428571428571,
|
||
|
|
"acc_stderr,none": 0.008420562208967575
|
||
|
|
},
|
||
|
|
"gat_analogy": {
|
||
|
|
"alias": " - gat_analogy",
|
||
|
|
"acc,none": 0.24553734061930782,
|
||
|
|
"acc_stderr,none": 0.008216476082874105
|
||
|
|
},
|
||
|
|
"gat_arithmetic": {
|
||
|
|
"alias": " - gat_arithmetic",
|
||
|
|
"acc,none": 0.26573426573426573,
|
||
|
|
"acc_stderr,none": 0.008475894211016492
|
||
|
|
},
|
||
|
|
"gat_association": {
|
||
|
|
"alias": " - gat_association",
|
||
|
|
"acc,none": 0.24019138755980862,
|
||
|
|
"acc_stderr,none": 0.013221495215360054
|
||
|
|
},
|
||
|
|
"gat_comparisons": {
|
||
|
|
"alias": " - gat_comparisons",
|
||
|
|
"acc,none": 0.319672131147541,
|
||
|
|
"acc_stderr,none": 0.013357022766710734
|
||
|
|
},
|
||
|
|
"gat_completion": {
|
||
|
|
"alias": " - gat_completion",
|
||
|
|
"acc,none": 0.27520661157024795,
|
||
|
|
"acc_stderr,none": 0.012844683062506254
|
||
|
|
},
|
||
|
|
"gat_contextual": {
|
||
|
|
"alias": " - gat_contextual",
|
||
|
|
"acc,none": 0.26993865030674846,
|
||
|
|
"acc_stderr,none": 0.01229815625441917
|
||
|
|
},
|
||
|
|
"gat_geometry": {
|
||
|
|
"alias": " - gat_geometry",
|
||
|
|
"acc,none": 0.2876712328767123,
|
||
|
|
"acc_stderr,none": 0.023726723391354485
|
||
|
|
},
|
||
|
|
"gat_reading": {
|
||
|
|
"alias": " - gat_reading",
|
||
|
|
"acc,none": 0.3568998109640832,
|
||
|
|
"acc_stderr,none": 0.009317121354774414
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"groups": {
|
||
|
|
"gat": {
|
||
|
|
"acc,none": 0.27994481374639407,
|
||
|
|
"acc_stderr,none": 0.003542796359675536,
|
||
|
|
"alias": "gat"
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"group_subtasks": {
|
||
|
|
"gat": [
|
||
|
|
"gat_analogy",
|
||
|
|
"gat_association",
|
||
|
|
"gat_completion",
|
||
|
|
"gat_reading",
|
||
|
|
"gat_algebra",
|
||
|
|
"gat_arithmetic",
|
||
|
|
"gat_comparisons",
|
||
|
|
"gat_contextual",
|
||
|
|
"gat_geometry"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
"configs": {
|
||
|
|
"gat_algebra": {
|
||
|
|
"task": "gat_algebra",
|
||
|
|
"dataset_path": "lm_eval/tasks/gat/gat_data/gat.py",
|
||
|
|
"dataset_name": "algebra",
|
||
|
|
"dataset_kwargs": {
|
||
|
|
"trust_remote_code": true
|
||
|
|
},
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "validation",
|
||
|
|
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n # def _process_doc(doc):\n \n # subject = doc['id'].split(\"-\")[0]\n # subject_ar = subtasks_ar[subtasks.index(subject)]\n # out_doc = {**doc, 'subject_ar': subject_ar}\n # print(subject_ar)\n # print(out_doc)\n # return out_doc\n\n return dataset\n",
|
||
|
|
"doc_to_text": "{{question}}\n\u0623. {{choices[0]}}\n\u0628. {{choices[1]}}\n\u062c. {{choices[2]}}\n\u062f. {{choices[3]}}\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:",
|
||
|
|
"doc_to_target": "{{label}}",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"\u0623",
|
||
|
|
"\u0628",
|
||
|
|
"\u062c",
|
||
|
|
"\u062f"
|
||
|
|
],
|
||
|
|
"description": "",
|
||
|
|
"target_delimiter": " ",
|
||
|
|
"fewshot_delimiter": "\n\n",
|
||
|
|
"num_fewshot": 0,
|
||
|
|
"metric_list": [
|
||
|
|
{
|
||
|
|
"metric": "acc",
|
||
|
|
"aggregation": "mean",
|
||
|
|
"higher_is_better": true
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"output_type": "multiple_choice",
|
||
|
|
"repeats": 1,
|
||
|
|
"should_decontaminate": false,
|
||
|
|
"metadata": {
|
||
|
|
"version": 0.0
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"gat_analogy": {
|
||
|
|
"task": "gat_analogy",
|
||
|
|
"dataset_path": "lm_eval/tasks/gat/gat_data/gat.py",
|
||
|
|
"dataset_name": "analogy",
|
||
|
|
"dataset_kwargs": {
|
||
|
|
"trust_remote_code": true
|
||
|
|
},
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "validation",
|
||
|
|
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n # def _process_doc(doc):\n \n # subject = doc['id'].split(\"-\")[0]\n # subject_ar = subtasks_ar[subtasks.index(subject)]\n # out_doc = {**doc, 'subject_ar': subject_ar}\n # print(subject_ar)\n # print(out_doc)\n # return out_doc\n\n return dataset\n",
|
||
|
|
"doc_to_text": "{{question}}\n\u0623. {{choices[0]}}\n\u0628. {{choices[1]}}\n\u062c. {{choices[2]}}\n\u062f. {{choices[3]}}\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:",
|
||
|
|
"doc_to_target": "{{label}}",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"\u0623",
|
||
|
|
"\u0628",
|
||
|
|
"\u062c",
|
||
|
|
"\u062f"
|
||
|
|
],
|
||
|
|
"description": "",
|
||
|
|
"target_delimiter": " ",
|
||
|
|
"fewshot_delimiter": "\n\n",
|
||
|
|
"num_fewshot": 0,
|
||
|
|
"metric_list": [
|
||
|
|
{
|
||
|
|
"metric": "acc",
|
||
|
|
"aggregation": "mean",
|
||
|
|
"higher_is_better": true
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"output_type": "multiple_choice",
|
||
|
|
"repeats": 1,
|
||
|
|
"should_decontaminate": false,
|
||
|
|
"metadata": {
|
||
|
|
"version": 0.0
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"gat_arithmetic": {
|
||
|
|
"task": "gat_arithmetic",
|
||
|
|
"dataset_path": "lm_eval/tasks/gat/gat_data/gat.py",
|
||
|
|
"dataset_name": "arithmetic",
|
||
|
|
"dataset_kwargs": {
|
||
|
|
"trust_remote_code": true
|
||
|
|
},
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "validation",
|
||
|
|
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n # def _process_doc(doc):\n \n # subject = doc['id'].split(\"-\")[0]\n # subject_ar = subtasks_ar[subtasks.index(subject)]\n # out_doc = {**doc, 'subject_ar': subject_ar}\n # print(subject_ar)\n # print(out_doc)\n # return out_doc\n\n return dataset\n",
|
||
|
|
"doc_to_text": "{{question}}\n\u0623. {{choices[0]}}\n\u0628. {{choices[1]}}\n\u062c. {{choices[2]}}\n\u062f. {{choices[3]}}\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:",
|
||
|
|
"doc_to_target": "{{label}}",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"\u0623",
|
||
|
|
"\u0628",
|
||
|
|
"\u062c",
|
||
|
|
"\u062f"
|
||
|
|
],
|
||
|
|
"description": "",
|
||
|
|
"target_delimiter": " ",
|
||
|
|
"fewshot_delimiter": "\n\n",
|
||
|
|
"num_fewshot": 0,
|
||
|
|
"metric_list": [
|
||
|
|
{
|
||
|
|
"metric": "acc",
|
||
|
|
"aggregation": "mean",
|
||
|
|
"higher_is_better": true
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"output_type": "multiple_choice",
|
||
|
|
"repeats": 1,
|
||
|
|
"should_decontaminate": false,
|
||
|
|
"metadata": {
|
||
|
|
"version": 0.0
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"gat_association": {
|
||
|
|
"task": "gat_association",
|
||
|
|
"dataset_path": "lm_eval/tasks/gat/gat_data/gat.py",
|
||
|
|
"dataset_name": "association",
|
||
|
|
"dataset_kwargs": {
|
||
|
|
"trust_remote_code": true
|
||
|
|
},
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "validation",
|
||
|
|
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n # def _process_doc(doc):\n \n # subject = doc['id'].split(\"-\")[0]\n # subject_ar = subtasks_ar[subtasks.index(subject)]\n # out_doc = {**doc, 'subject_ar': subject_ar}\n # print(subject_ar)\n # print(out_doc)\n # return out_doc\n\n return dataset\n",
|
||
|
|
"doc_to_text": "{{question}}\n\u0623. {{choices[0]}}\n\u0628. {{choices[1]}}\n\u062c. {{choices[2]}}\n\u062f. {{choices[3]}}\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:",
|
||
|
|
"doc_to_target": "{{label}}",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"\u0623",
|
||
|
|
"\u0628",
|
||
|
|
"\u062c",
|
||
|
|
"\u062f"
|
||
|
|
],
|
||
|
|
"description": "",
|
||
|
|
"target_delimiter": " ",
|
||
|
|
"fewshot_delimiter": "\n\n",
|
||
|
|
"num_fewshot": 0,
|
||
|
|
"metric_list": [
|
||
|
|
{
|
||
|
|
"metric": "acc",
|
||
|
|
"aggregation": "mean",
|
||
|
|
"higher_is_better": true
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"output_type": "multiple_choice",
|
||
|
|
"repeats": 1,
|
||
|
|
"should_decontaminate": false,
|
||
|
|
"metadata": {
|
||
|
|
"version": 0.0
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"gat_comparisons": {
|
||
|
|
"task": "gat_comparisons",
|
||
|
|
"dataset_path": "lm_eval/tasks/gat/gat_data/gat.py",
|
||
|
|
"dataset_name": "comparisons",
|
||
|
|
"dataset_kwargs": {
|
||
|
|
"trust_remote_code": true
|
||
|
|
},
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "validation",
|
||
|
|
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n # def _process_doc(doc):\n \n # subject = doc['id'].split(\"-\")[0]\n # subject_ar = subtasks_ar[subtasks.index(subject)]\n # out_doc = {**doc, 'subject_ar': subject_ar}\n # print(subject_ar)\n # print(out_doc)\n # return out_doc\n\n return dataset\n",
|
||
|
|
"doc_to_text": "{{question}}\n\u0623. {{choices[0]}}\n\u0628. {{choices[1]}}\n\u062c. {{choices[2]}}\n\u062f. {{choices[3]}}\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:",
|
||
|
|
"doc_to_target": "{{label}}",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"\u0623",
|
||
|
|
"\u0628",
|
||
|
|
"\u062c",
|
||
|
|
"\u062f"
|
||
|
|
],
|
||
|
|
"description": "",
|
||
|
|
"target_delimiter": " ",
|
||
|
|
"fewshot_delimiter": "\n\n",
|
||
|
|
"num_fewshot": 0,
|
||
|
|
"metric_list": [
|
||
|
|
{
|
||
|
|
"metric": "acc",
|
||
|
|
"aggregation": "mean",
|
||
|
|
"higher_is_better": true
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"output_type": "multiple_choice",
|
||
|
|
"repeats": 1,
|
||
|
|
"should_decontaminate": false,
|
||
|
|
"metadata": {
|
||
|
|
"version": 0.0
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"gat_completion": {
|
||
|
|
"task": "gat_completion",
|
||
|
|
"dataset_path": "lm_eval/tasks/gat/gat_data/gat.py",
|
||
|
|
"dataset_name": "completion",
|
||
|
|
"dataset_kwargs": {
|
||
|
|
"trust_remote_code": true
|
||
|
|
},
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "validation",
|
||
|
|
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n # def _process_doc(doc):\n \n # subject = doc['id'].split(\"-\")[0]\n # subject_ar = subtasks_ar[subtasks.index(subject)]\n # out_doc = {**doc, 'subject_ar': subject_ar}\n # print(subject_ar)\n # print(out_doc)\n # return out_doc\n\n return dataset\n",
|
||
|
|
"doc_to_text": "{{question}}\n\u0623. {{choices[0]}}\n\u0628. {{choices[1]}}\n\u062c. {{choices[2]}}\n\u062f. {{choices[3]}}\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:",
|
||
|
|
"doc_to_target": "{{label}}",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"\u0623",
|
||
|
|
"\u0628",
|
||
|
|
"\u062c",
|
||
|
|
"\u062f"
|
||
|
|
],
|
||
|
|
"description": "",
|
||
|
|
"target_delimiter": " ",
|
||
|
|
"fewshot_delimiter": "\n\n",
|
||
|
|
"num_fewshot": 0,
|
||
|
|
"metric_list": [
|
||
|
|
{
|
||
|
|
"metric": "acc",
|
||
|
|
"aggregation": "mean",
|
||
|
|
"higher_is_better": true
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"output_type": "multiple_choice",
|
||
|
|
"repeats": 1,
|
||
|
|
"should_decontaminate": false,
|
||
|
|
"metadata": {
|
||
|
|
"version": 0.0
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"gat_contextual": {
|
||
|
|
"task": "gat_contextual",
|
||
|
|
"dataset_path": "lm_eval/tasks/gat/gat_data/gat.py",
|
||
|
|
"dataset_name": "contextual",
|
||
|
|
"dataset_kwargs": {
|
||
|
|
"trust_remote_code": true
|
||
|
|
},
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "validation",
|
||
|
|
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n # def _process_doc(doc):\n \n # subject = doc['id'].split(\"-\")[0]\n # subject_ar = subtasks_ar[subtasks.index(subject)]\n # out_doc = {**doc, 'subject_ar': subject_ar}\n # print(subject_ar)\n # print(out_doc)\n # return out_doc\n\n return dataset\n",
|
||
|
|
"doc_to_text": "{{question}}\n\u0623. {{choices[0]}}\n\u0628. {{choices[1]}}\n\u062c. {{choices[2]}}\n\u062f. {{choices[3]}}\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:",
|
||
|
|
"doc_to_target": "{{label}}",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"\u0623",
|
||
|
|
"\u0628",
|
||
|
|
"\u062c",
|
||
|
|
"\u062f"
|
||
|
|
],
|
||
|
|
"description": "\u0627\u0648\u062c\u062f \u0627\u0644\u062e\u0637\u0623 \u0627\u0644\u0633\u064a\u0627\u0642\u064a \u0641\u064a \u0627\u0644\u0639\u0628\u0627\u0631\u0629 \u0627\u0644\u062a\u0627\u0644\u064a\u0629 \u0645\u0646 \u0628\u064a\u0646 \u0627\u0644\u062e\u064a\u0627\u0631\u0627\u062a:",
|
||
|
|
"target_delimiter": " ",
|
||
|
|
"fewshot_delimiter": "\n\n",
|
||
|
|
"num_fewshot": 0,
|
||
|
|
"metric_list": [
|
||
|
|
{
|
||
|
|
"metric": "acc",
|
||
|
|
"aggregation": "mean",
|
||
|
|
"higher_is_better": true
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"output_type": "multiple_choice",
|
||
|
|
"repeats": 1,
|
||
|
|
"should_decontaminate": false,
|
||
|
|
"metadata": {
|
||
|
|
"version": 0.0
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"gat_geometry": {
|
||
|
|
"task": "gat_geometry",
|
||
|
|
"dataset_path": "lm_eval/tasks/gat/gat_data/gat.py",
|
||
|
|
"dataset_name": "geometry",
|
||
|
|
"dataset_kwargs": {
|
||
|
|
"trust_remote_code": true
|
||
|
|
},
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "validation",
|
||
|
|
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n # def _process_doc(doc):\n \n # subject = doc['id'].split(\"-\")[0]\n # subject_ar = subtasks_ar[subtasks.index(subject)]\n # out_doc = {**doc, 'subject_ar': subject_ar}\n # print(subject_ar)\n # print(out_doc)\n # return out_doc\n\n return dataset\n",
|
||
|
|
"doc_to_text": "{{question}}\n\u0623. {{choices[0]}}\n\u0628. {{choices[1]}}\n\u062c. {{choices[2]}}\n\u062f. {{choices[3]}}\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:",
|
||
|
|
"doc_to_target": "{{label}}",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"\u0623",
|
||
|
|
"\u0628",
|
||
|
|
"\u062c",
|
||
|
|
"\u062f"
|
||
|
|
],
|
||
|
|
"description": "",
|
||
|
|
"target_delimiter": " ",
|
||
|
|
"fewshot_delimiter": "\n\n",
|
||
|
|
"num_fewshot": 0,
|
||
|
|
"metric_list": [
|
||
|
|
{
|
||
|
|
"metric": "acc",
|
||
|
|
"aggregation": "mean",
|
||
|
|
"higher_is_better": true
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"output_type": "multiple_choice",
|
||
|
|
"repeats": 1,
|
||
|
|
"should_decontaminate": false,
|
||
|
|
"metadata": {
|
||
|
|
"version": 0.0
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"gat_reading": {
|
||
|
|
"task": "gat_reading",
|
||
|
|
"dataset_path": "lm_eval/tasks/gat/gat_data/gat.py",
|
||
|
|
"dataset_name": "reading",
|
||
|
|
"dataset_kwargs": {
|
||
|
|
"trust_remote_code": true
|
||
|
|
},
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "validation",
|
||
|
|
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n # def _process_doc(doc):\n \n # subject = doc['id'].split(\"-\")[0]\n # subject_ar = subtasks_ar[subtasks.index(subject)]\n # out_doc = {**doc, 'subject_ar': subject_ar}\n # print(subject_ar)\n # print(out_doc)\n # return out_doc\n\n return dataset\n",
|
||
|
|
"doc_to_text": "{{question}}\n\u0623. {{choices[0]}}\n\u0628. {{choices[1]}}\n\u062c. {{choices[2]}}\n\u062f. {{choices[3]}}\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:",
|
||
|
|
"doc_to_target": "{{label}}",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"\u0623",
|
||
|
|
"\u0628",
|
||
|
|
"\u062c",
|
||
|
|
"\u062f"
|
||
|
|
],
|
||
|
|
"description": "",
|
||
|
|
"target_delimiter": " ",
|
||
|
|
"fewshot_delimiter": "\n\n",
|
||
|
|
"num_fewshot": 0,
|
||
|
|
"metric_list": [
|
||
|
|
{
|
||
|
|
"metric": "acc",
|
||
|
|
"aggregation": "mean",
|
||
|
|
"higher_is_better": true
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"output_type": "multiple_choice",
|
||
|
|
"repeats": 1,
|
||
|
|
"should_decontaminate": false,
|
||
|
|
"metadata": {
|
||
|
|
"version": 0.0
|
||
|
|
}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"versions": {
|
||
|
|
"gat": 0,
|
||
|
|
"gat_algebra": 0.0,
|
||
|
|
"gat_analogy": 0.0,
|
||
|
|
"gat_arithmetic": 0.0,
|
||
|
|
"gat_association": 0.0,
|
||
|
|
"gat_comparisons": 0.0,
|
||
|
|
"gat_completion": 0.0,
|
||
|
|
"gat_contextual": 0.0,
|
||
|
|
"gat_geometry": 0.0,
|
||
|
|
"gat_reading": 0.0
|
||
|
|
},
|
||
|
|
"n-shot": {
|
||
|
|
"gat_algebra": 0,
|
||
|
|
"gat_analogy": 0,
|
||
|
|
"gat_arithmetic": 0,
|
||
|
|
"gat_association": 0,
|
||
|
|
"gat_comparisons": 0,
|
||
|
|
"gat_completion": 0,
|
||
|
|
"gat_contextual": 0,
|
||
|
|
"gat_geometry": 0,
|
||
|
|
"gat_reading": 0
|
||
|
|
},
|
||
|
|
"higher_is_better": {
|
||
|
|
"gat": {
|
||
|
|
"acc": true
|
||
|
|
},
|
||
|
|
"gat_algebra": {
|
||
|
|
"acc": true
|
||
|
|
},
|
||
|
|
"gat_analogy": {
|
||
|
|
"acc": true
|
||
|
|
},
|
||
|
|
"gat_arithmetic": {
|
||
|
|
"acc": true
|
||
|
|
},
|
||
|
|
"gat_association": {
|
||
|
|
"acc": true
|
||
|
|
},
|
||
|
|
"gat_comparisons": {
|
||
|
|
"acc": true
|
||
|
|
},
|
||
|
|
"gat_completion": {
|
||
|
|
"acc": true
|
||
|
|
},
|
||
|
|
"gat_contextual": {
|
||
|
|
"acc": true
|
||
|
|
},
|
||
|
|
"gat_geometry": {
|
||
|
|
"acc": true
|
||
|
|
},
|
||
|
|
"gat_reading": {
|
||
|
|
"acc": true
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"n-samples": {
|
||
|
|
"gat_analogy": {
|
||
|
|
"original": 2745,
|
||
|
|
"effective": 2745
|
||
|
|
},
|
||
|
|
"gat_association": {
|
||
|
|
"original": 1045,
|
||
|
|
"effective": 1045
|
||
|
|
},
|
||
|
|
"gat_completion": {
|
||
|
|
"original": 1210,
|
||
|
|
"effective": 1210
|
||
|
|
},
|
||
|
|
"gat_reading": {
|
||
|
|
"original": 2645,
|
||
|
|
"effective": 2645
|
||
|
|
},
|
||
|
|
"gat_algebra": {
|
||
|
|
"original": 2695,
|
||
|
|
"effective": 2695
|
||
|
|
},
|
||
|
|
"gat_arithmetic": {
|
||
|
|
"original": 2717,
|
||
|
|
"effective": 2717
|
||
|
|
},
|
||
|
|
"gat_comparisons": {
|
||
|
|
"original": 1220,
|
||
|
|
"effective": 1220
|
||
|
|
},
|
||
|
|
"gat_contextual": {
|
||
|
|
"original": 1304,
|
||
|
|
"effective": 1304
|
||
|
|
},
|
||
|
|
"gat_geometry": {
|
||
|
|
"original": 365,
|
||
|
|
"effective": 365
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"config": {
|
||
|
|
"model": "hf",
|
||
|
|
"model_args": "pretrained=tiiuae/Falcon3-7B-Instruct,trust_remote_code=True,cache_dir=/tmp,parallelize=True",
|
||
|
|
"model_num_parameters": 7455550464,
|
||
|
|
"model_dtype": "torch.bfloat16",
|
||
|
|
"model_revision": "main",
|
||
|
|
"model_sha": "5563a370c1848366c7a095bde4bbff2cdb419cc6",
|
||
|
|
"batch_size": 1,
|
||
|
|
"batch_sizes": [],
|
||
|
|
"device": null,
|
||
|
|
"use_cache": null,
|
||
|
|
"limit": null,
|
||
|
|
"bootstrap_iters": 100000,
|
||
|
|
"gen_kwargs": null,
|
||
|
|
"random_seed": 0,
|
||
|
|
"numpy_seed": 1234,
|
||
|
|
"torch_seed": 1234,
|
||
|
|
"fewshot_seed": 1234
|
||
|
|
},
|
||
|
|
"git_hash": "5e10e017",
|
||
|
|
"date": 1736891004.0192773,
|
||
|
|
"pretty_env_info": "PyTorch version: 2.4.0+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 22.04.3 LTS (x86_64)\nGCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0\nClang version: Could not collect\nCMake version: version 3.27.1\nLibc version: glibc-2.35\n\nPython version: 3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0] (64-bit runtime)\nPython platform: Linux-5.15.0-1064-azure-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 12.2.128\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA A100-SXM4-80GB\nGPU 1: NVIDIA A100-SXM4-80GB\nGPU 2: NVIDIA A100-SXM4-80GB\nGPU 3: NVIDIA A100-SXM4-80GB\nGPU 4: NVIDIA A100-SXM4-80GB\nGPU 5: NVIDIA A100-SXM4-80GB\nGPU 6: NVIDIA A100-SXM4-80GB\nGPU 7: NVIDIA A100-SXM4-80GB\n\nNvidia driver version: 535.161.08\ncuDNN version: Probably one of the following:\n/usr/lib/x86_64-linux-gnu/libcudnn.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_train.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_train.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_train.so.8.9.4\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\n\nCPU:\nArchitecture: x86_64\nCPU op-mode(s): 32-bit, 64-bit\nAddress sizes: 48 bits physical, 48 bits virtual\nByte Order: Little Endian\nCPU(s): 96\nOn-line CPU(s) list: 0-95\nVendor ID: AuthenticAMD\nModel name: AMD EPYC 7V12 64-Core Processor\nCPU family: 23\nModel: 49\nThread(s) per core: 1\nCore(s) per socket: 48\nSocket(s): 2\nStepping: 0\nBogoMIPS: 4890.88\nFlags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl tsc_reliable nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext perfctr_core ssbd vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr rdpru arat umip rdpid\nHypervisor vendor: Microsoft\nVirtualization type: full\nL1d cache: 3 MiB (96 instances)\nL1i cache: 3 MiB (96 instances)\nL2 cache: 48 MiB (96 instances)\nL3 cache: 384 MiB (24 instances)\nNUMA node(s): 4\nNUMA node0 CPU(s): 0-23\nNUMA node1 CPU(s): 24-47\nNUMA node2 CPU(s): 48-71\nNUMA node3 CPU(s): 72-95\nVulnerability Gather data sampling: Not affected\nVulnerability Itlb multihit: Not affected\nVulnerability L1tf: Not affected\nVulnerability Mds: Not affected\nVulnerability Meltdown: Not affected\nVulnerability Mmio stale data: Not affected\nVulnerability Retbleed: Mitigation; untrained return thunk; SMT disabled\nVulnerability Spec rstack overflow: Mitigation; safe RET, no microcode\nVulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp\nVulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization\nVulnerability Spectre v2: Mitigation; Retpolines; STIBP disabled; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected\nVulnerability Srbds: Not affected\nVulnerability Tsx async abort:
|
||
|
|
"transformers_version": "4.48.0",
|
||
|
|
"upper_git_hash": "f64fe2f2a86055aaecced603b56097fd79201711",
|
||
|
|
"tokenizer_pad_token": [
|
||
|
|
"<|pad|>",
|
||
|
|
"2023"
|
||
|
|
],
|
||
|
|
"tokenizer_eos_token": [
|
||
|
|
"<|endoftext|>",
|
||
|
|
"11"
|
||
|
|
],
|
||
|
|
"tokenizer_bos_token": [
|
||
|
|
null,
|
||
|
|
"None"
|
||
|
|
],
|
||
|
|
"eot_token_id": 11,
|
||
|
|
"max_length": 32768,
|
||
|
|
"task_hashes": {
|
||
|
|
"gat_analogy": "04ac010c48ed039457058b512b7ac0586c7c76a628da7caaf9aeb8f3e99ae5e3",
|
||
|
|
"gat_association": "2cbd868d220125bfcc54ae738592ad902191e4b7f804ce1772ae29e2d3bb3bf6",
|
||
|
|
"gat_completion": "74cf159ef4a3455a6a0e984fed8e9e9a12f0dc21fde95c2058216c5a711a4d31",
|
||
|
|
"gat_reading": "6f21934e536e7dca65361d01e5cafc27f8070c4f0dccf5a88c1fe071194b78a4",
|
||
|
|
"gat_algebra": "20750c926608570eaf87d29981e5ab49b2b097bd52d7f749c44ab4e175d9fdd2",
|
||
|
|
"gat_arithmetic": "c4b0c73c269d9eb3e8482fbda42e69191c28b95e75e1517d5f9142c6ef410204",
|
||
|
|
"gat_comparisons": "88bc22db186a50cab28938ec1fc332366fa0bc886bc98edf810cc9ae938405db",
|
||
|
|
"gat_contextual": "b8e88ff29b62b54eb834dca696304ca0fe1ce55d5cf7d0a9f0204456e3955be6",
|
||
|
|
"gat_geometry": "229545188469d0512a3297737f4ec7afe88d8a30e7e04f87b4982548e83b1e56"
|
||
|
|
},
|
||
|
|
"model_source": "hf",
|
||
|
|
"model_name": "tiiuae/Falcon3-7B-Instruct",
|
||
|
|
"model_name_sanitized": "tiiuae__Falcon3-7B-Instruct",
|
||
|
|
"system_instruction": null,
|
||
|
|
"system_instruction_sha": null,
|
||
|
|
"fewshot_as_multiturn": false,
|
||
|
|
"chat_template": null,
|
||
|
|
"chat_template_sha": null,
|
||
|
|
"start_time": 601254.206185867,
|
||
|
|
"end_time": 601373.470204397,
|
||
|
|
"total_evaluation_time_seconds": "119.26401853002608"
|
||
|
|
}
|