Muennighoff commited on
Commit
7f49339
1 Parent(s): ad49413
evaluation_bloomz-7b1-p3/evaluation_l2/Muennighoff_xwinograd/ru/Replace/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_name": "Muennighoff/xwinograd",
3
+ "dataset_config_name": "ru",
4
+ "template_name": "Replace",
5
+ "evaluation": {
6
+ "accuracy": 0.49206349206349204
7
+ },
8
+ "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 ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_name": "Muennighoff/xwinograd",
3
+ "dataset_config_name": "ru",
4
+ "template_name": "True or False",
5
+ "evaluation": {
6
+ "accuracy": 0.4793650793650794
7
+ },
8
+ "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 ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_name": "Muennighoff/xwinograd",
3
+ "dataset_config_name": "ru",
4
+ "template_name": "does underscore refer to",
5
+ "evaluation": {
6
+ "accuracy": 0.4857142857142857
7
+ },
8
+ "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 ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_name": "Muennighoff/xwinograd",
3
+ "dataset_config_name": "ru",
4
+ "template_name": "stand for",
5
+ "evaluation": {
6
+ "accuracy": 0.4888888888888889
7
+ },
8
+ "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 ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_name": "Muennighoff/xwinograd",
3
+ "dataset_config_name": "ru",
4
+ "template_name": "underscore refer to",
5
+ "evaluation": {
6
+ "accuracy": 0.4857142857142857
7
+ },
8
+ "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
+ }