bigscience/bloomz-7b1-p3
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: bigscience/bloomz-7b1-p3
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-15 07:40:14 +08:00
commit 78a6661ff1
634 changed files with 7477 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
evaluation_bloomz-7b1-p3/evaluation_l2/Muennighoff_xstory_cloze/my/Answer_Given_options/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "Muennighoff/xstory_cloze",
"dataset_config_name": "my",
"template_name": "Answer Given options",
"evaluation": {
"accuracy": 0.5056254136333554
},
"arguments": "Namespace(config_name=None, dataset_config_name='my', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='Answer Given options', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/Muennighoff_xstory_cloze/my/Choose_Story_Ending/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "Muennighoff/xstory_cloze",
"dataset_config_name": "my",
"template_name": "Choose Story Ending",
"evaluation": {
"accuracy": 0.5069490403706155
},
"arguments": "Namespace(config_name=None, dataset_config_name='my', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='Choose Story Ending', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/Muennighoff_xstory_cloze/my/Generate_Ending/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "Muennighoff/xstory_cloze",
"dataset_config_name": "my",
"template_name": "Generate Ending",
"evaluation": {
"accuracy": 0.4784910655195235
},
"arguments": "Namespace(config_name=None, dataset_config_name='my', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='Generate Ending', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/Muennighoff_xstory_cloze/my/Novel_Correct_Ending/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "Muennighoff/xstory_cloze",
"dataset_config_name": "my",
"template_name": "Novel Correct Ending",
"evaluation": {
"accuracy": 0.5102581072137657
},
"arguments": "Namespace(config_name=None, dataset_config_name='my', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='Novel Correct Ending', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/Muennighoff_xstory_cloze/my/Story_Continuation_and_Options/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "Muennighoff/xstory_cloze",
"dataset_config_name": "my",
"template_name": "Story Continuation and Options",
"evaluation": {
"accuracy": 0.5062872270019855
},
"arguments": "Namespace(config_name=None, dataset_config_name='my', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='Story Continuation and Options', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/Muennighoff_xstory_cloze/ru/Answer_Given_options/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "Muennighoff/xstory_cloze",
"dataset_config_name": "ru",
"template_name": "Answer Given options",
"evaluation": {
"accuracy": 0.6406353408338848
},
"arguments": "Namespace(config_name=None, dataset_config_name='ru', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='Answer Given options', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/Muennighoff_xstory_cloze/ru/Choose_Story_Ending/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "Muennighoff/xstory_cloze",
"dataset_config_name": "ru",
"template_name": "Choose Story Ending",
"evaluation": {
"accuracy": 0.6644606221045665
},
"arguments": "Namespace(config_name=None, dataset_config_name='ru', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='Choose Story Ending', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/Muennighoff_xstory_cloze/ru/Generate_Ending/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "Muennighoff/xstory_cloze",
"dataset_config_name": "ru",
"template_name": "Generate Ending",
"evaluation": {
"accuracy": 0.514890800794176
},
"arguments": "Namespace(config_name=None, dataset_config_name='ru', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='Generate Ending', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/Muennighoff_xstory_cloze/ru/Novel_Correct_Ending/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "Muennighoff/xstory_cloze",
"dataset_config_name": "ru",
"template_name": "Novel Correct Ending",
"evaluation": {
"accuracy": 0.6393117140966248
},
"arguments": "Namespace(config_name=None, dataset_config_name='ru', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='Novel Correct Ending', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/Muennighoff_xstory_cloze/ru/Story_Continuation_and_Options/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "Muennighoff/xstory_cloze",
"dataset_config_name": "ru",
"template_name": "Story Continuation and Options",
"evaluation": {
"accuracy": 0.6545334215751158
},
"arguments": "Namespace(config_name=None, dataset_config_name='ru', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='Story Continuation and Options', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/Muennighoff_xwinograd/jp/Replace/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "Muennighoff/xwinograd",
"dataset_config_name": "jp",
"template_name": "Replace",
"evaluation": {
"accuracy": 0.5130344108446299
},
"arguments": "Namespace(config_name=None, dataset_config_name='jp', dataset_name='Muennighoff/xwinograd', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=4, prefixlm=False, split='test', target_max_length=256, template_config_name='en', template_name='Replace', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/Muennighoff_xwinograd/jp/True_or_False/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "Muennighoff/xwinograd",
"dataset_config_name": "jp",
"template_name": "True or False",
"evaluation": {
"accuracy": 0.5036496350364964
},
"arguments": "Namespace(config_name=None, dataset_config_name='jp', dataset_name='Muennighoff/xwinograd', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=4, prefixlm=False, split='test', target_max_length=256, template_config_name='en', template_name='True or False', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/Muennighoff_xwinograd/jp/does_underscore_refer_to/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "Muennighoff/xwinograd",
"dataset_config_name": "jp",
"template_name": "does underscore refer to",
"evaluation": {
"accuracy": 0.5192909280500522
},
"arguments": "Namespace(config_name=None, dataset_config_name='jp', dataset_name='Muennighoff/xwinograd', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=4, prefixlm=False, split='test', target_max_length=256, template_config_name='en', template_name='does underscore refer to', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/Muennighoff_xwinograd/jp/stand_for/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "Muennighoff/xwinograd",
"dataset_config_name": "jp",
"template_name": "stand for",
"evaluation": {
"accuracy": 0.49635036496350365
},
"arguments": "Namespace(config_name=None, dataset_config_name='jp', dataset_name='Muennighoff/xwinograd', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=4, prefixlm=False, split='test', target_max_length=256, template_config_name='en', template_name='stand for', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/Muennighoff_xwinograd/jp/underscore_refer_to/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "Muennighoff/xwinograd",
"dataset_config_name": "jp",
"template_name": "underscore refer to",
"evaluation": {
"accuracy": 0.4994786235662148
},
"arguments": "Namespace(config_name=None, dataset_config_name='jp', dataset_name='Muennighoff/xwinograd', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=4, prefixlm=False, split='test', target_max_length=256, template_config_name='en', template_name='underscore refer to', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/Muennighoff_xwinograd/ru/Replace/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "Muennighoff/xwinograd",
"dataset_config_name": "ru",
"template_name": "Replace",
"evaluation": {
"accuracy": 0.49206349206349204
},
"arguments": "Namespace(config_name=None, dataset_config_name='ru', dataset_name='Muennighoff/xwinograd', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=4, prefixlm=False, split='test', target_max_length=256, template_config_name='en', template_name='Replace', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/Muennighoff_xwinograd/ru/True_or_False/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "Muennighoff/xwinograd",
"dataset_config_name": "ru",
"template_name": "True or False",
"evaluation": {
"accuracy": 0.4793650793650794
},
"arguments": "Namespace(config_name=None, dataset_config_name='ru', dataset_name='Muennighoff/xwinograd', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=4, prefixlm=False, split='test', target_max_length=256, template_config_name='en', template_name='True or False', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/Muennighoff_xwinograd/ru/does_underscore_refer_to/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "Muennighoff/xwinograd",
"dataset_config_name": "ru",
"template_name": "does underscore refer to",
"evaluation": {
"accuracy": 0.4857142857142857
},
"arguments": "Namespace(config_name=None, dataset_config_name='ru', dataset_name='Muennighoff/xwinograd', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=4, prefixlm=False, split='test', target_max_length=256, template_config_name='en', template_name='does underscore refer to', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/Muennighoff_xwinograd/ru/stand_for/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "Muennighoff/xwinograd",
"dataset_config_name": "ru",
"template_name": "stand for",
"evaluation": {
"accuracy": 0.4888888888888889
},
"arguments": "Namespace(config_name=None, dataset_config_name='ru', dataset_name='Muennighoff/xwinograd', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=4, prefixlm=False, split='test', target_max_length=256, template_config_name='en', template_name='stand for', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/Muennighoff_xwinograd/ru/underscore_refer_to/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "Muennighoff/xwinograd",
"dataset_config_name": "ru",
"template_name": "underscore refer to",
"evaluation": {
"accuracy": 0.4857142857142857
},
"arguments": "Namespace(config_name=None, dataset_config_name='ru', dataset_name='Muennighoff/xwinograd', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=4, prefixlm=False, split='test', target_max_length=256, template_config_name='en', template_name='underscore refer to', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xcopa/et/C1_or_C2?_premise/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "et",
"template_name": "C1 or C2? premise, so/because\u2026",
"evaluation": {
"accuracy": 0.47
},
"arguments": "Namespace(config_name=None, dataset_config_name='et', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='so/because\u2026,validation', target_max_length=256, template_config_name='en', template_name='C1 or C2? premise', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xcopa/et/best_option/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "et",
"template_name": "best_option",
"evaluation": {
"accuracy": 0.52
},
"arguments": "Namespace(config_name=None, dataset_config_name='et', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='best_option', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xcopa/et/cause_effect/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "et",
"template_name": "cause_effect",
"evaluation": {
"accuracy": 0.49
},
"arguments": "Namespace(config_name=None, dataset_config_name='et', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='cause_effect', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xcopa/et/i_am_hesitating/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "et",
"template_name": "i_am_hesitating",
"evaluation": {
"accuracy": 0.57
},
"arguments": "Namespace(config_name=None, dataset_config_name='et', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='i_am_hesitating', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xcopa/et/plausible_alternatives/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "et",
"template_name": "plausible_alternatives",
"evaluation": {
"accuracy": 0.55
},
"arguments": "Namespace(config_name=None, dataset_config_name='et', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='plausible_alternatives', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xcopa/ht/C1_or_C2?_premise/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "ht",
"template_name": "C1 or C2? premise, so/because\u2026",
"evaluation": {
"accuracy": 0.51
},
"arguments": "Namespace(config_name=None, dataset_config_name='ht', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='so/because\u2026,validation', target_max_length=256, template_config_name='en', template_name='C1 or C2? premise', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xcopa/ht/best_option/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "ht",
"template_name": "best_option",
"evaluation": {
"accuracy": 0.47
},
"arguments": "Namespace(config_name=None, dataset_config_name='ht', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='best_option', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xcopa/ht/cause_effect/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "ht",
"template_name": "cause_effect",
"evaluation": {
"accuracy": 0.55
},
"arguments": "Namespace(config_name=None, dataset_config_name='ht', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='cause_effect', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xcopa/ht/i_am_hesitating/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "ht",
"template_name": "i_am_hesitating",
"evaluation": {
"accuracy": 0.51
},
"arguments": "Namespace(config_name=None, dataset_config_name='ht', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='i_am_hesitating', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xcopa/ht/plausible_alternatives/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "ht",
"template_name": "plausible_alternatives",
"evaluation": {
"accuracy": 0.52
},
"arguments": "Namespace(config_name=None, dataset_config_name='ht', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='plausible_alternatives', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xcopa/it/C1_or_C2?_premise/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "it",
"template_name": "C1 or C2? premise, so/because\u2026",
"evaluation": {
"accuracy": 0.57
},
"arguments": "Namespace(config_name=None, dataset_config_name='it', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='so/because\u2026,validation', target_max_length=256, template_config_name='en', template_name='C1 or C2? premise', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xcopa/it/best_option/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "it",
"template_name": "best_option",
"evaluation": {
"accuracy": 0.52
},
"arguments": "Namespace(config_name=None, dataset_config_name='it', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='best_option', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xcopa/it/cause_effect/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "it",
"template_name": "cause_effect",
"evaluation": {
"accuracy": 0.54
},
"arguments": "Namespace(config_name=None, dataset_config_name='it', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='cause_effect', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xcopa/it/i_am_hesitating/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "it",
"template_name": "i_am_hesitating",
"evaluation": {
"accuracy": 0.57
},
"arguments": "Namespace(config_name=None, dataset_config_name='it', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='i_am_hesitating', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xcopa/it/plausible_alternatives/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "it",
"template_name": "plausible_alternatives",
"evaluation": {
"accuracy": 0.6
},
"arguments": "Namespace(config_name=None, dataset_config_name='it', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='plausible_alternatives', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xcopa/qu/C1_or_C2?_premise/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "qu",
"template_name": "C1 or C2? premise, so/because\u2026",
"evaluation": {
"accuracy": 0.47
},
"arguments": "Namespace(config_name=None, dataset_config_name='qu', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='so/because\u2026,validation', target_max_length=256, template_config_name='en', template_name='C1 or C2? premise', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xcopa/qu/best_option/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "qu",
"template_name": "best_option",
"evaluation": {
"accuracy": 0.52
},
"arguments": "Namespace(config_name=None, dataset_config_name='qu', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='best_option', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xcopa/qu/cause_effect/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "qu",
"template_name": "cause_effect",
"evaluation": {
"accuracy": 0.5
},
"arguments": "Namespace(config_name=None, dataset_config_name='qu', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='cause_effect', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xcopa/qu/i_am_hesitating/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "qu",
"template_name": "i_am_hesitating",
"evaluation": {
"accuracy": 0.48
},
"arguments": "Namespace(config_name=None, dataset_config_name='qu', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='i_am_hesitating', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xcopa/qu/plausible_alternatives/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "qu",
"template_name": "plausible_alternatives",
"evaluation": {
"accuracy": 0.54
},
"arguments": "Namespace(config_name=None, dataset_config_name='qu', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='plausible_alternatives', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xcopa/tr/C1_or_C2?_premise/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "tr",
"template_name": "C1 or C2? premise, so/because\u2026",
"evaluation": {
"accuracy": 0.55
},
"arguments": "Namespace(config_name=None, dataset_config_name='tr', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='so/because\u2026,validation', target_max_length=256, template_config_name='en', template_name='C1 or C2? premise', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xcopa/tr/best_option/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "tr",
"template_name": "best_option",
"evaluation": {
"accuracy": 0.48
},
"arguments": "Namespace(config_name=None, dataset_config_name='tr', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='best_option', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xcopa/tr/cause_effect/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "tr",
"template_name": "cause_effect",
"evaluation": {
"accuracy": 0.53
},
"arguments": "Namespace(config_name=None, dataset_config_name='tr', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='cause_effect', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xcopa/tr/i_am_hesitating/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "tr",
"template_name": "i_am_hesitating",
"evaluation": {
"accuracy": 0.54
},
"arguments": "Namespace(config_name=None, dataset_config_name='tr', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='i_am_hesitating', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xcopa/tr/plausible_alternatives/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "tr",
"template_name": "plausible_alternatives",
"evaluation": {
"accuracy": 0.52
},
"arguments": "Namespace(config_name=None, dataset_config_name='tr', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='plausible_alternatives', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xnli/bg/GPT-3_style/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xnli",
"dataset_config_name": "bg",
"template_name": "GPT-3 style",
"evaluation": {
"accuracy": 0.43775100401606426
},
"arguments": "Namespace(config_name=None, dataset_config_name='bg', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='GPT-3 style', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xnli/bg/MNLI_crowdsource/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xnli",
"dataset_config_name": "bg",
"template_name": "MNLI crowdsource",
"evaluation": {
"accuracy": 0.36666666666666664
},
"arguments": "Namespace(config_name=None, dataset_config_name='bg', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='MNLI crowdsource', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xnli/bg/can_we_infer/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xnli",
"dataset_config_name": "bg",
"template_name": "can we infer",
"evaluation": {
"accuracy": 0.4397590361445783
},
"arguments": "Namespace(config_name=None, dataset_config_name='bg', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='can we infer', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xnli/bg/guaranteed_possible_impossible/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xnli",
"dataset_config_name": "bg",
"template_name": "guaranteed/possible/impossible",
"evaluation": {
"accuracy": 0.41646586345381525
},
"arguments": "Namespace(config_name=None, dataset_config_name='bg', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='guaranteed/possible/impossible', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xnli/bg/justified_in_saying/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xnli",
"dataset_config_name": "bg",
"template_name": "justified in saying",
"evaluation": {
"accuracy": 0.4108433734939759
},
"arguments": "Namespace(config_name=None, dataset_config_name='bg', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='justified in saying', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xnli/de/GPT-3_style/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xnli",
"dataset_config_name": "de",
"template_name": "GPT-3 style",
"evaluation": {
"accuracy": 0.470281124497992
},
"arguments": "Namespace(config_name=None, dataset_config_name='de', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='GPT-3 style', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xnli/de/MNLI_crowdsource/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xnli",
"dataset_config_name": "de",
"template_name": "MNLI crowdsource",
"evaluation": {
"accuracy": 0.3586345381526104
},
"arguments": "Namespace(config_name=None, dataset_config_name='de', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='MNLI crowdsource', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xnli/de/can_we_infer/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xnli",
"dataset_config_name": "de",
"template_name": "can we infer",
"evaluation": {
"accuracy": 0.44016064257028115
},
"arguments": "Namespace(config_name=None, dataset_config_name='de', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='can we infer', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xnli/de/guaranteed_possible_impossible/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xnli",
"dataset_config_name": "de",
"template_name": "guaranteed/possible/impossible",
"evaluation": {
"accuracy": 0.3538152610441767
},
"arguments": "Namespace(config_name=None, dataset_config_name='de', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='guaranteed/possible/impossible', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xnli/de/justified_in_saying/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xnli",
"dataset_config_name": "de",
"template_name": "justified in saying",
"evaluation": {
"accuracy": 0.41847389558232934
},
"arguments": "Namespace(config_name=None, dataset_config_name='de', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='justified in saying', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xnli/el/GPT-3_style/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xnli",
"dataset_config_name": "el",
"template_name": "GPT-3 style",
"evaluation": {
"accuracy": 0.41887550200803214
},
"arguments": "Namespace(config_name=None, dataset_config_name='el', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='GPT-3 style', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xnli/el/MNLI_crowdsource/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xnli",
"dataset_config_name": "el",
"template_name": "MNLI crowdsource",
"evaluation": {
"accuracy": 0.3598393574297189
},
"arguments": "Namespace(config_name=None, dataset_config_name='el', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='MNLI crowdsource', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xnli/el/can_we_infer/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xnli",
"dataset_config_name": "el",
"template_name": "can we infer",
"evaluation": {
"accuracy": 0.4108433734939759
},
"arguments": "Namespace(config_name=None, dataset_config_name='el', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='can we infer', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xnli/el/guaranteed_possible_impossible/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xnli",
"dataset_config_name": "el",
"template_name": "guaranteed/possible/impossible",
"evaluation": {
"accuracy": 0.40682730923694777
},
"arguments": "Namespace(config_name=None, dataset_config_name='el', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='guaranteed/possible/impossible', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xnli/el/justified_in_saying/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xnli",
"dataset_config_name": "el",
"template_name": "justified in saying",
"evaluation": {
"accuracy": 0.3823293172690763
},
"arguments": "Namespace(config_name=None, dataset_config_name='el', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='justified in saying', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xnli/ru/GPT-3_style/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xnli",
"dataset_config_name": "ru",
"template_name": "GPT-3 style",
"evaluation": {
"accuracy": 0.46546184738955826
},
"arguments": "Namespace(config_name=None, dataset_config_name='ru', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='GPT-3 style', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xnli/ru/MNLI_crowdsource/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xnli",
"dataset_config_name": "ru",
"template_name": "MNLI crowdsource",
"evaluation": {
"accuracy": 0.3819277108433735
},
"arguments": "Namespace(config_name=None, dataset_config_name='ru', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='MNLI crowdsource', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xnli/ru/can_we_infer/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xnli",
"dataset_config_name": "ru",
"template_name": "can we infer",
"evaluation": {
"accuracy": 0.4614457831325301
},
"arguments": "Namespace(config_name=None, dataset_config_name='ru', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='can we infer', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xnli/ru/guaranteed_possible_impossible/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xnli",
"dataset_config_name": "ru",
"template_name": "guaranteed/possible/impossible",
"evaluation": {
"accuracy": 0.42208835341365464
},
"arguments": "Namespace(config_name=None, dataset_config_name='ru', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='guaranteed/possible/impossible', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xnli/ru/justified_in_saying/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xnli",
"dataset_config_name": "ru",
"template_name": "justified in saying",
"evaluation": {
"accuracy": 0.4389558232931727
},
"arguments": "Namespace(config_name=None, dataset_config_name='ru', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='justified in saying', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xnli/th/GPT-3_style/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xnli",
"dataset_config_name": "th",
"template_name": "GPT-3 style",
"evaluation": {
"accuracy": 0.41646586345381525
},
"arguments": "Namespace(config_name=None, dataset_config_name='th', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='GPT-3 style', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xnli/th/MNLI_crowdsource/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xnli",
"dataset_config_name": "th",
"template_name": "MNLI crowdsource",
"evaluation": {
"accuracy": 0.3224899598393574
},
"arguments": "Namespace(config_name=None, dataset_config_name='th', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='MNLI crowdsource', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xnli/th/can_we_infer/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xnli",
"dataset_config_name": "th",
"template_name": "can we infer",
"evaluation": {
"accuracy": 0.43172690763052207
},
"arguments": "Namespace(config_name=None, dataset_config_name='th', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='can we infer', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xnli/th/guaranteed_possible_impossible/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xnli",
"dataset_config_name": "th",
"template_name": "guaranteed/possible/impossible",
"evaluation": {
"accuracy": 0.42730923694779116
},
"arguments": "Namespace(config_name=None, dataset_config_name='th', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='guaranteed/possible/impossible', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xnli/th/justified_in_saying/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xnli",
"dataset_config_name": "th",
"template_name": "justified in saying",
"evaluation": {
"accuracy": 0.40401606425702813
},
"arguments": "Namespace(config_name=None, dataset_config_name='th', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='justified in saying', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xnli/tr/GPT-3_style/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xnli",
"dataset_config_name": "tr",
"template_name": "GPT-3 style",
"evaluation": {
"accuracy": 0.40240963855421685
},
"arguments": "Namespace(config_name=None, dataset_config_name='tr', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='GPT-3 style', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xnli/tr/MNLI_crowdsource/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xnli",
"dataset_config_name": "tr",
"template_name": "MNLI crowdsource",
"evaluation": {
"accuracy": 0.351004016064257
},
"arguments": "Namespace(config_name=None, dataset_config_name='tr', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='MNLI crowdsource', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xnli/tr/can_we_infer/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xnli",
"dataset_config_name": "tr",
"template_name": "can we infer",
"evaluation": {
"accuracy": 0.40441767068273093
},
"arguments": "Namespace(config_name=None, dataset_config_name='tr', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='can we infer', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xnli/tr/guaranteed_possible_impossible/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xnli",
"dataset_config_name": "tr",
"template_name": "guaranteed/possible/impossible",
"evaluation": {
"accuracy": 0.3678714859437751
},
"arguments": "Namespace(config_name=None, dataset_config_name='tr', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='guaranteed/possible/impossible', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_l2/xnli/tr/justified_in_saying/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xnli",
"dataset_config_name": "tr",
"template_name": "justified in saying",
"evaluation": {
"accuracy": 0.38313253012048193
},
"arguments": "Namespace(config_name=None, dataset_config_name='tr', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/bloomz-7b1-p3/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='en', template_name='justified in saying', tokenizer_name=None, use_slow_tokenizer=False)"
}