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_xwinostorycopamt/xcopa/id/C1_or_C2?_premise_idmt/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "id",
"template_name": "C1 or C2? premise_idmt",
"evaluation": {
"accuracy": 0.51
},
"arguments": "Namespace(config_name=None, dataset_config_name='id', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='id', template_name='C1 or C2? premise_idmt', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_xwinostorycopamt/xcopa/id/best_option_idmt/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "id",
"template_name": "best_option_idmt",
"evaluation": {
"accuracy": 0.53
},
"arguments": "Namespace(config_name=None, dataset_config_name='id', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='id', template_name='best_option_idmt', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_xwinostorycopamt/xcopa/id/cause_effect_idmt/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "id",
"template_name": "cause_effect_idmt",
"evaluation": {
"accuracy": 0.69
},
"arguments": "Namespace(config_name=None, dataset_config_name='id', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='id', template_name='cause_effect_idmt', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_xwinostorycopamt/xcopa/id/i_am_hesitating_idmt/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "id",
"template_name": "i_am_hesitating_idmt",
"evaluation": {
"accuracy": 0.64
},
"arguments": "Namespace(config_name=None, dataset_config_name='id', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='id', template_name='i_am_hesitating_idmt', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_xwinostorycopamt/xcopa/id/plausible_alternatives_idmt/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "id",
"template_name": "plausible_alternatives_idmt",
"evaluation": {
"accuracy": 0.7
},
"arguments": "Namespace(config_name=None, dataset_config_name='id', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='id', template_name='plausible_alternatives_idmt', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_xwinostorycopamt/xcopa/sw/C1_or_C2?_premise_swmt/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "sw",
"template_name": "C1 or C2? premise_swmt",
"evaluation": {
"accuracy": 0.6
},
"arguments": "Namespace(config_name=None, dataset_config_name='sw', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='sw', template_name='C1 or C2? premise_swmt', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_xwinostorycopamt/xcopa/sw/best_option_swmt/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "sw",
"template_name": "best_option_swmt",
"evaluation": {
"accuracy": 0.62
},
"arguments": "Namespace(config_name=None, dataset_config_name='sw', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='sw', template_name='best_option_swmt', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_xwinostorycopamt/xcopa/sw/cause_effect_swmt/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "sw",
"template_name": "cause_effect_swmt",
"evaluation": {
"accuracy": 0.49
},
"arguments": "Namespace(config_name=None, dataset_config_name='sw', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='sw', template_name='cause_effect_swmt', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_xwinostorycopamt/xcopa/sw/i_am_hesitating_swmt/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "sw",
"template_name": "i_am_hesitating_swmt",
"evaluation": {
"accuracy": 0.56
},
"arguments": "Namespace(config_name=None, dataset_config_name='sw', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='sw', template_name='i_am_hesitating_swmt', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_xwinostorycopamt/xcopa/sw/plausible_alternatives_swmt/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "sw",
"template_name": "plausible_alternatives_swmt",
"evaluation": {
"accuracy": 0.54
},
"arguments": "Namespace(config_name=None, dataset_config_name='sw', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='sw', template_name='plausible_alternatives_swmt', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_xwinostorycopamt/xcopa/ta/C1_or_C2?_premise_tamt/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "ta",
"template_name": "C1 or C2? premise_tamt",
"evaluation": {
"accuracy": 0.52
},
"arguments": "Namespace(config_name=None, dataset_config_name='ta', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='ta', template_name='C1 or C2? premise_tamt', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_xwinostorycopamt/xcopa/ta/best_option_tamt/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "ta",
"template_name": "best_option_tamt",
"evaluation": {
"accuracy": 0.55
},
"arguments": "Namespace(config_name=None, dataset_config_name='ta', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='ta', template_name='best_option_tamt', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_xwinostorycopamt/xcopa/ta/cause_effect_tamt/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "ta",
"template_name": "cause_effect_tamt",
"evaluation": {
"accuracy": 0.63
},
"arguments": "Namespace(config_name=None, dataset_config_name='ta', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='ta', template_name='cause_effect_tamt', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_xwinostorycopamt/xcopa/ta/i_am_hesitating_tamt/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "ta",
"template_name": "i_am_hesitating_tamt",
"evaluation": {
"accuracy": 0.63
},
"arguments": "Namespace(config_name=None, dataset_config_name='ta', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='ta', template_name='i_am_hesitating_tamt', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_xwinostorycopamt/xcopa/ta/plausible_alternatives_tamt/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "ta",
"template_name": "plausible_alternatives_tamt",
"evaluation": {
"accuracy": 0.66
},
"arguments": "Namespace(config_name=None, dataset_config_name='ta', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='ta', template_name='plausible_alternatives_tamt', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_xwinostorycopamt/xcopa/vi/C1_or_C2?_premise_vimt/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "vi",
"template_name": "C1 or C2? premise_vimt",
"evaluation": {
"accuracy": 0.55
},
"arguments": "Namespace(config_name=None, dataset_config_name='vi', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='vi', template_name='C1 or C2? premise_vimt', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_xwinostorycopamt/xcopa/vi/best_option_vimt/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "vi",
"template_name": "best_option_vimt",
"evaluation": {
"accuracy": 0.61
},
"arguments": "Namespace(config_name=None, dataset_config_name='vi', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='vi', template_name='best_option_vimt', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_xwinostorycopamt/xcopa/vi/cause_effect_vimt/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "vi",
"template_name": "cause_effect_vimt",
"evaluation": {
"accuracy": 0.64
},
"arguments": "Namespace(config_name=None, dataset_config_name='vi', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='vi', template_name='cause_effect_vimt', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_xwinostorycopamt/xcopa/vi/i_am_hesitating_vimt/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "vi",
"template_name": "i_am_hesitating_vimt",
"evaluation": {
"accuracy": 0.6
},
"arguments": "Namespace(config_name=None, dataset_config_name='vi', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='vi', template_name='i_am_hesitating_vimt', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_xwinostorycopamt/xcopa/vi/plausible_alternatives_vimt/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "vi",
"template_name": "plausible_alternatives_vimt",
"evaluation": {
"accuracy": 0.64
},
"arguments": "Namespace(config_name=None, dataset_config_name='vi', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='vi', template_name='plausible_alternatives_vimt', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_xwinostorycopamt/xcopa/zh/C1_or_C2?_premise_zhmt/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "zh",
"template_name": "C1 or C2? premise_zhmt",
"evaluation": {
"accuracy": 0.52
},
"arguments": "Namespace(config_name=None, dataset_config_name='zh', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='zh', template_name='C1 or C2? premise_zhmt', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_xwinostorycopamt/xcopa/zh/best_option_zhmt/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "zh",
"template_name": "best_option_zhmt",
"evaluation": {
"accuracy": 0.61
},
"arguments": "Namespace(config_name=None, dataset_config_name='zh', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='zh', template_name='best_option_zhmt', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_xwinostorycopamt/xcopa/zh/cause_effect_zhmt/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "zh",
"template_name": "cause_effect_zhmt",
"evaluation": {
"accuracy": 0.75
},
"arguments": "Namespace(config_name=None, dataset_config_name='zh', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='zh', template_name='cause_effect_zhmt', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_xwinostorycopamt/xcopa/zh/i_am_hesitating_zhmt/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "zh",
"template_name": "i_am_hesitating_zhmt",
"evaluation": {
"accuracy": 0.72
},
"arguments": "Namespace(config_name=None, dataset_config_name='zh', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='zh', template_name='i_am_hesitating_zhmt', tokenizer_name=None, use_slow_tokenizer=False)"
}

9
evaluation_bloomz-7b1-p3/evaluation_xwinostorycopamt/xcopa/zh/plausible_alternatives_zhmt/results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"dataset_name": "xcopa",
"dataset_config_name": "zh",
"template_name": "plausible_alternatives_zhmt",
"evaluation": {
"accuracy": 0.76
},
"arguments": "Namespace(config_name=None, dataset_config_name='zh', dataset_name='xcopa', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/p31lossseqglobal_step1000/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='zh', template_name='plausible_alternatives_zhmt', tokenizer_name=None, use_slow_tokenizer=False)"
}