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/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)"
}