Muennighoff
commited on
Commit
•
ad49413
1
Parent(s):
8634ce5
Add res
Browse files- evaluation_bloomz-7b1-p3/evaluation_l2/Muennighoff_xwinograd/jp/Replace/results.json +9 -0
- evaluation_bloomz-7b1-p3/evaluation_l2/Muennighoff_xwinograd/jp/True_or_False/results.json +2 -2
- evaluation_bloomz-7b1-p3/evaluation_l2/Muennighoff_xwinograd/jp/does_underscore_refer_to/results.json +9 -0
- evaluation_bloomz-7b1-p3/evaluation_l2/Muennighoff_xwinograd/jp/stand_for/results.json +9 -0
- evaluation_bloomz-7b1-p3/evaluation_l2/Muennighoff_xwinograd/jp/underscore_refer_to/results.json +9 -0
- evaluation_bloomz-7b1-p3/evaluation_val/examples.limited=3000.model=p31lossseqglobal_step1000.task=wmt14_hi_en.templates=gpt3-en-hi-target.fewshot=0.batchsize=16.seed=1234.timestamp=2022-09-09T23:48:38.jsonl +0 -0
- evaluation_bloomz-7b1-p3/evaluation_val/examples.limited=3000.model=p31lossseqglobal_step1000.task=wmt14_hi_en.templates=gpt3-hi-en-target.fewshot=0.batchsize=16.seed=1234.timestamp=2022-09-09T23:48:40.jsonl +0 -0
evaluation_bloomz-7b1-p3/evaluation_l2/Muennighoff_xwinograd/jp/Replace/results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"dataset_name": "Muennighoff/xwinograd",
|
3 |
+
"dataset_config_name": "jp",
|
4 |
+
"template_name": "Replace",
|
5 |
+
"evaluation": {
|
6 |
+
"accuracy": 0.5130344108446299
|
7 |
+
},
|
8 |
+
"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
CHANGED
@@ -3,7 +3,7 @@
|
|
3 |
"dataset_config_name": "jp",
|
4 |
"template_name": "True or False",
|
5 |
"evaluation": {
|
6 |
-
"accuracy": 0.
|
7 |
},
|
8 |
-
"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=
|
9 |
}
|
|
|
3 |
"dataset_config_name": "jp",
|
4 |
"template_name": "True or False",
|
5 |
"evaluation": {
|
6 |
+
"accuracy": 0.5036496350364964
|
7 |
},
|
8 |
+
"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
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"dataset_name": "Muennighoff/xwinograd",
|
3 |
+
"dataset_config_name": "jp",
|
4 |
+
"template_name": "does underscore refer to",
|
5 |
+
"evaluation": {
|
6 |
+
"accuracy": 0.5192909280500522
|
7 |
+
},
|
8 |
+
"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
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"dataset_name": "Muennighoff/xwinograd",
|
3 |
+
"dataset_config_name": "jp",
|
4 |
+
"template_name": "stand for",
|
5 |
+
"evaluation": {
|
6 |
+
"accuracy": 0.49635036496350365
|
7 |
+
},
|
8 |
+
"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
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"dataset_name": "Muennighoff/xwinograd",
|
3 |
+
"dataset_config_name": "jp",
|
4 |
+
"template_name": "underscore refer to",
|
5 |
+
"evaluation": {
|
6 |
+
"accuracy": 0.4994786235662148
|
7 |
+
},
|
8 |
+
"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_val/examples.limited=3000.model=p31lossseqglobal_step1000.task=wmt14_hi_en.templates=gpt3-en-hi-target.fewshot=0.batchsize=16.seed=1234.timestamp=2022-09-09T23:48:38.jsonl
DELETED
File without changes
|
evaluation_bloomz-7b1-p3/evaluation_val/examples.limited=3000.model=p31lossseqglobal_step1000.task=wmt14_hi_en.templates=gpt3-hi-en-target.fewshot=0.batchsize=16.seed=1234.timestamp=2022-09-09T23:48:40.jsonl
DELETED
File without changes
|