Muennighoff commited on
Commit
29d50e7
1 Parent(s): 9c29398

Remove eval (Moved to bigscience/evaluation-results)

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xstory_cloze/ar/Answer_Given_options/results.json +0 -9
  2. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xstory_cloze/ar/Choose_Story_Ending/results.json +0 -9
  3. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xstory_cloze/ar/Generate_Ending/results.json +0 -9
  4. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xstory_cloze/ar/Novel_Correct_Ending/results.json +0 -9
  5. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xstory_cloze/ar/Story_Continuation_and_Options/results.json +0 -9
  6. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xstory_cloze/es/Answer_Given_options/results.json +0 -9
  7. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xstory_cloze/es/Choose_Story_Ending/results.json +0 -9
  8. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xstory_cloze/es/Generate_Ending/results.json +0 -9
  9. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xstory_cloze/es/Novel_Correct_Ending/results.json +0 -9
  10. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xstory_cloze/es/Story_Continuation_and_Options/results.json +0 -9
  11. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xstory_cloze/eu/Answer_Given_options/results.json +0 -9
  12. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xstory_cloze/eu/Choose_Story_Ending/results.json +0 -9
  13. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xstory_cloze/eu/Generate_Ending/results.json +0 -9
  14. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xstory_cloze/eu/Novel_Correct_Ending/results.json +0 -9
  15. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xstory_cloze/eu/Story_Continuation_and_Options/results.json +0 -9
  16. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xstory_cloze/hi/Answer_Given_options/results.json +0 -9
  17. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xstory_cloze/hi/Choose_Story_Ending/results.json +0 -9
  18. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xstory_cloze/hi/Generate_Ending/results.json +0 -9
  19. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xstory_cloze/hi/Novel_Correct_Ending/results.json +0 -9
  20. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xstory_cloze/hi/Story_Continuation_and_Options/results.json +0 -9
  21. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xstory_cloze/id/Answer_Given_options/results.json +0 -9
  22. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xstory_cloze/id/Choose_Story_Ending/results.json +0 -9
  23. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xstory_cloze/id/Generate_Ending/results.json +0 -9
  24. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xstory_cloze/id/Novel_Correct_Ending/results.json +0 -9
  25. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xstory_cloze/id/Story_Continuation_and_Options/results.json +0 -9
  26. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xstory_cloze/zh/Answer_Given_options/results.json +0 -9
  27. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xstory_cloze/zh/Choose_Story_Ending/results.json +0 -9
  28. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xstory_cloze/zh/Generate_Ending/results.json +0 -9
  29. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xstory_cloze/zh/Novel_Correct_Ending/results.json +0 -9
  30. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xstory_cloze/zh/Story_Continuation_and_Options/results.json +0 -9
  31. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xwinograd/en/Replace/results.json +0 -9
  32. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xwinograd/en/True_or_False/results.json +0 -9
  33. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xwinograd/en/does_underscore_refer_to/results.json +0 -9
  34. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xwinograd/en/stand_for/results.json +0 -9
  35. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xwinograd/en/underscore_refer_to/results.json +0 -9
  36. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xwinograd/fr/Replace/results.json +0 -9
  37. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xwinograd/fr/True_or_False/results.json +0 -9
  38. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xwinograd/fr/does_underscore_refer_to/results.json +0 -9
  39. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xwinograd/fr/stand_for/results.json +0 -9
  40. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xwinograd/fr/underscore_refer_to/results.json +0 -9
  41. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xwinograd/pt/Replace/results.json +0 -9
  42. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xwinograd/pt/True_or_False/results.json +0 -9
  43. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xwinograd/pt/does_underscore_refer_to/results.json +0 -9
  44. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xwinograd/pt/stand_for/results.json +0 -9
  45. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xwinograd/pt/underscore_refer_to/results.json +0 -9
  46. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xwinograd/zh/Replace/results.json +0 -9
  47. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xwinograd/zh/True_or_False/results.json +0 -9
  48. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xwinograd/zh/does_underscore_refer_to/results.json +0 -9
  49. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xwinograd/zh/stand_for/results.json +0 -9
  50. evaluation_bloomz-mt/evaluation_l1/Muennighoff_xwinograd/zh/underscore_refer_to/results.json +0 -9
evaluation_bloomz-mt/evaluation_l1/Muennighoff_xstory_cloze/ar/Answer_Given_options/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xstory_cloze",
3
- "dataset_config_name": "ar",
4
- "template_name": "Answer Given options",
5
- "evaluation": {
6
- "accuracy": 0.7835870284579749
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='ar', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/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-mt/evaluation_l1/Muennighoff_xstory_cloze/ar/Choose_Story_Ending/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xstory_cloze",
3
- "dataset_config_name": "ar",
4
- "template_name": "Choose Story Ending",
5
- "evaluation": {
6
- "accuracy": 0.9291859695565851
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='ar', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/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-mt/evaluation_l1/Muennighoff_xstory_cloze/ar/Generate_Ending/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xstory_cloze",
3
- "dataset_config_name": "ar",
4
- "template_name": "Generate Ending",
5
- "evaluation": {
6
- "accuracy": 0.6624751819986764
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='ar', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/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-mt/evaluation_l1/Muennighoff_xstory_cloze/ar/Novel_Correct_Ending/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xstory_cloze",
3
- "dataset_config_name": "ar",
4
- "template_name": "Novel Correct Ending",
5
- "evaluation": {
6
- "accuracy": 0.9252150893448048
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='ar', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/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-mt/evaluation_l1/Muennighoff_xstory_cloze/ar/Story_Continuation_and_Options/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xstory_cloze",
3
- "dataset_config_name": "ar",
4
- "template_name": "Story Continuation and Options",
5
- "evaluation": {
6
- "accuracy": 0.9159497021839841
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='ar', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/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-mt/evaluation_l1/Muennighoff_xstory_cloze/es/Answer_Given_options/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xstory_cloze",
3
- "dataset_config_name": "es",
4
- "template_name": "Answer Given options",
5
- "evaluation": {
6
- "accuracy": 0.870946393117141
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='es', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/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-mt/evaluation_l1/Muennighoff_xstory_cloze/es/Choose_Story_Ending/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xstory_cloze",
3
- "dataset_config_name": "es",
4
- "template_name": "Choose Story Ending",
5
- "evaluation": {
6
- "accuracy": 0.9523494374586366
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='es', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/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-mt/evaluation_l1/Muennighoff_xstory_cloze/es/Generate_Ending/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xstory_cloze",
3
- "dataset_config_name": "es",
4
- "template_name": "Generate Ending",
5
- "evaluation": {
6
- "accuracy": 0.7319655857048313
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='es', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/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-mt/evaluation_l1/Muennighoff_xstory_cloze/es/Novel_Correct_Ending/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xstory_cloze",
3
- "dataset_config_name": "es",
4
- "template_name": "Novel Correct Ending",
5
- "evaluation": {
6
- "accuracy": 0.9477167438782264
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='es', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/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-mt/evaluation_l1/Muennighoff_xstory_cloze/es/Story_Continuation_and_Options/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xstory_cloze",
3
- "dataset_config_name": "es",
4
- "template_name": "Story Continuation and Options",
5
- "evaluation": {
6
- "accuracy": 0.9516876240900066
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='es', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/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-mt/evaluation_l1/Muennighoff_xstory_cloze/eu/Answer_Given_options/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xstory_cloze",
3
- "dataset_config_name": "eu",
4
- "template_name": "Answer Given options",
5
- "evaluation": {
6
- "accuracy": 0.6982131039046989
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='eu', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/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-mt/evaluation_l1/Muennighoff_xstory_cloze/eu/Choose_Story_Ending/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xstory_cloze",
3
- "dataset_config_name": "eu",
4
- "template_name": "Choose Story Ending",
5
- "evaluation": {
6
- "accuracy": 0.85704831237591
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='eu', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/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-mt/evaluation_l1/Muennighoff_xstory_cloze/eu/Generate_Ending/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xstory_cloze",
3
- "dataset_config_name": "eu",
4
- "template_name": "Generate Ending",
5
- "evaluation": {
6
- "accuracy": 0.614162806088683
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='eu', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/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-mt/evaluation_l1/Muennighoff_xstory_cloze/eu/Novel_Correct_Ending/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xstory_cloze",
3
- "dataset_config_name": "eu",
4
- "template_name": "Novel Correct Ending",
5
- "evaluation": {
6
- "accuracy": 0.8590337524818001
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='eu', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/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-mt/evaluation_l1/Muennighoff_xstory_cloze/eu/Story_Continuation_and_Options/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xstory_cloze",
3
- "dataset_config_name": "eu",
4
- "template_name": "Story Continuation and Options",
5
- "evaluation": {
6
- "accuracy": 0.8504301786896096
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='eu', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/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-mt/evaluation_l1/Muennighoff_xstory_cloze/hi/Answer_Given_options/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xstory_cloze",
3
- "dataset_config_name": "hi",
4
- "template_name": "Answer Given options",
5
- "evaluation": {
6
- "accuracy": 0.7683653209794837
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='hi', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/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-mt/evaluation_l1/Muennighoff_xstory_cloze/hi/Choose_Story_Ending/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xstory_cloze",
3
- "dataset_config_name": "hi",
4
- "template_name": "Choose Story Ending",
5
- "evaluation": {
6
- "accuracy": 0.8742554599602912
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='hi', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/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-mt/evaluation_l1/Muennighoff_xstory_cloze/hi/Generate_Ending/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xstory_cloze",
3
- "dataset_config_name": "hi",
4
- "template_name": "Generate Ending",
5
- "evaluation": {
6
- "accuracy": 0.657180675049636
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='hi', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/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-mt/evaluation_l1/Muennighoff_xstory_cloze/hi/Novel_Correct_Ending/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xstory_cloze",
3
- "dataset_config_name": "hi",
4
- "template_name": "Novel Correct Ending",
5
- "evaluation": {
6
- "accuracy": 0.886829913964262
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='hi', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/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-mt/evaluation_l1/Muennighoff_xstory_cloze/hi/Story_Continuation_and_Options/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xstory_cloze",
3
- "dataset_config_name": "hi",
4
- "template_name": "Story Continuation and Options",
5
- "evaluation": {
6
- "accuracy": 0.8762409000661814
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='hi', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/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-mt/evaluation_l1/Muennighoff_xstory_cloze/id/Answer_Given_options/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xstory_cloze",
3
- "dataset_config_name": "id",
4
- "template_name": "Answer Given options",
5
- "evaluation": {
6
- "accuracy": 0.8332230311052283
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='id', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/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-mt/evaluation_l1/Muennighoff_xstory_cloze/id/Choose_Story_Ending/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xstory_cloze",
3
- "dataset_config_name": "id",
4
- "template_name": "Choose Story Ending",
5
- "evaluation": {
6
- "accuracy": 0.913964262078094
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='id', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/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-mt/evaluation_l1/Muennighoff_xstory_cloze/id/Generate_Ending/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xstory_cloze",
3
- "dataset_config_name": "id",
4
- "template_name": "Generate Ending",
5
- "evaluation": {
6
- "accuracy": 0.700198544010589
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='id', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/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-mt/evaluation_l1/Muennighoff_xstory_cloze/id/Novel_Correct_Ending/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xstory_cloze",
3
- "dataset_config_name": "id",
4
- "template_name": "Novel Correct Ending",
5
- "evaluation": {
6
- "accuracy": 0.9205823957643945
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='id', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/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-mt/evaluation_l1/Muennighoff_xstory_cloze/id/Story_Continuation_and_Options/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xstory_cloze",
3
- "dataset_config_name": "id",
4
- "template_name": "Story Continuation and Options",
5
- "evaluation": {
6
- "accuracy": 0.9086697551290536
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='id', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/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-mt/evaluation_l1/Muennighoff_xstory_cloze/zh/Answer_Given_options/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xstory_cloze",
3
- "dataset_config_name": "zh",
4
- "template_name": "Answer Given options",
5
- "evaluation": {
6
- "accuracy": 0.870946393117141
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='zh', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/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-mt/evaluation_l1/Muennighoff_xstory_cloze/zh/Choose_Story_Ending/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xstory_cloze",
3
- "dataset_config_name": "zh",
4
- "template_name": "Choose Story Ending",
5
- "evaluation": {
6
- "accuracy": 0.9265387160820648
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='zh', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/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-mt/evaluation_l1/Muennighoff_xstory_cloze/zh/Generate_Ending/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xstory_cloze",
3
- "dataset_config_name": "zh",
4
- "template_name": "Generate Ending",
5
- "evaluation": {
6
- "accuracy": 0.6823295830575777
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='zh', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/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-mt/evaluation_l1/Muennighoff_xstory_cloze/zh/Novel_Correct_Ending/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xstory_cloze",
3
- "dataset_config_name": "zh",
4
- "template_name": "Novel Correct Ending",
5
- "evaluation": {
6
- "accuracy": 0.928524156187955
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='zh', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/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-mt/evaluation_l1/Muennighoff_xstory_cloze/zh/Story_Continuation_and_Options/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xstory_cloze",
3
- "dataset_config_name": "zh",
4
- "template_name": "Story Continuation and Options",
5
- "evaluation": {
6
- "accuracy": 0.9232296492389146
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='zh', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/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-mt/evaluation_l1/Muennighoff_xwinograd/en/Replace/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xwinograd",
3
- "dataset_config_name": "en",
4
- "template_name": "Replace",
5
- "evaluation": {
6
- "accuracy": 0.6933333333333334
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='en', dataset_name='Muennighoff/xwinograd', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, 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-mt/evaluation_l1/Muennighoff_xwinograd/en/True_or_False/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xwinograd",
3
- "dataset_config_name": "en",
4
- "template_name": "True or False",
5
- "evaluation": {
6
- "accuracy": 0.5212903225806451
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='en', dataset_name='Muennighoff/xwinograd', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, 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-mt/evaluation_l1/Muennighoff_xwinograd/en/does_underscore_refer_to/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xwinograd",
3
- "dataset_config_name": "en",
4
- "template_name": "does underscore refer to",
5
- "evaluation": {
6
- "accuracy": 0.6563440860215054
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='en', dataset_name='Muennighoff/xwinograd', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, 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-mt/evaluation_l1/Muennighoff_xwinograd/en/stand_for/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xwinograd",
3
- "dataset_config_name": "en",
4
- "template_name": "stand for",
5
- "evaluation": {
6
- "accuracy": 0.5156989247311828
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='en', dataset_name='Muennighoff/xwinograd', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, 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-mt/evaluation_l1/Muennighoff_xwinograd/en/underscore_refer_to/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xwinograd",
3
- "dataset_config_name": "en",
4
- "template_name": "underscore refer to",
5
- "evaluation": {
6
- "accuracy": 0.6473118279569893
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='en', dataset_name='Muennighoff/xwinograd', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, 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-mt/evaluation_l1/Muennighoff_xwinograd/fr/Replace/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xwinograd",
3
- "dataset_config_name": "fr",
4
- "template_name": "Replace",
5
- "evaluation": {
6
- "accuracy": 0.6024096385542169
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='fr', dataset_name='Muennighoff/xwinograd', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, 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-mt/evaluation_l1/Muennighoff_xwinograd/fr/True_or_False/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xwinograd",
3
- "dataset_config_name": "fr",
4
- "template_name": "True or False",
5
- "evaluation": {
6
- "accuracy": 0.46987951807228917
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='fr', dataset_name='Muennighoff/xwinograd', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, 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-mt/evaluation_l1/Muennighoff_xwinograd/fr/does_underscore_refer_to/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xwinograd",
3
- "dataset_config_name": "fr",
4
- "template_name": "does underscore refer to",
5
- "evaluation": {
6
- "accuracy": 0.5903614457831325
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='fr', dataset_name='Muennighoff/xwinograd', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, 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-mt/evaluation_l1/Muennighoff_xwinograd/fr/stand_for/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xwinograd",
3
- "dataset_config_name": "fr",
4
- "template_name": "stand for",
5
- "evaluation": {
6
- "accuracy": 0.4939759036144578
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='fr', dataset_name='Muennighoff/xwinograd', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, 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-mt/evaluation_l1/Muennighoff_xwinograd/fr/underscore_refer_to/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xwinograd",
3
- "dataset_config_name": "fr",
4
- "template_name": "underscore refer to",
5
- "evaluation": {
6
- "accuracy": 0.6867469879518072
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='fr', dataset_name='Muennighoff/xwinograd', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, 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-mt/evaluation_l1/Muennighoff_xwinograd/pt/Replace/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xwinograd",
3
- "dataset_config_name": "pt",
4
- "template_name": "Replace",
5
- "evaluation": {
6
- "accuracy": 0.6463878326996197
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='pt', dataset_name='Muennighoff/xwinograd', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, 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-mt/evaluation_l1/Muennighoff_xwinograd/pt/True_or_False/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xwinograd",
3
- "dataset_config_name": "pt",
4
- "template_name": "True or False",
5
- "evaluation": {
6
- "accuracy": 0.5285171102661597
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='pt', dataset_name='Muennighoff/xwinograd', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, 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-mt/evaluation_l1/Muennighoff_xwinograd/pt/does_underscore_refer_to/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xwinograd",
3
- "dataset_config_name": "pt",
4
- "template_name": "does underscore refer to",
5
- "evaluation": {
6
- "accuracy": 0.6007604562737643
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='pt', dataset_name='Muennighoff/xwinograd', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, 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-mt/evaluation_l1/Muennighoff_xwinograd/pt/stand_for/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xwinograd",
3
- "dataset_config_name": "pt",
4
- "template_name": "stand for",
5
- "evaluation": {
6
- "accuracy": 0.49809885931558934
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='pt', dataset_name='Muennighoff/xwinograd', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, 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-mt/evaluation_l1/Muennighoff_xwinograd/pt/underscore_refer_to/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xwinograd",
3
- "dataset_config_name": "pt",
4
- "template_name": "underscore refer to",
5
- "evaluation": {
6
- "accuracy": 0.6083650190114068
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='pt', dataset_name='Muennighoff/xwinograd', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, 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-mt/evaluation_l1/Muennighoff_xwinograd/zh/Replace/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xwinograd",
3
- "dataset_config_name": "zh",
4
- "template_name": "Replace",
5
- "evaluation": {
6
- "accuracy": 0.7063492063492064
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='zh', dataset_name='Muennighoff/xwinograd', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, 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-mt/evaluation_l1/Muennighoff_xwinograd/zh/True_or_False/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xwinograd",
3
- "dataset_config_name": "zh",
4
- "template_name": "True or False",
5
- "evaluation": {
6
- "accuracy": 0.5515873015873016
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='zh', dataset_name='Muennighoff/xwinograd', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, 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-mt/evaluation_l1/Muennighoff_xwinograd/zh/does_underscore_refer_to/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xwinograd",
3
- "dataset_config_name": "zh",
4
- "template_name": "does underscore refer to",
5
- "evaluation": {
6
- "accuracy": 0.621031746031746
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='zh', dataset_name='Muennighoff/xwinograd', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, 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-mt/evaluation_l1/Muennighoff_xwinograd/zh/stand_for/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xwinograd",
3
- "dataset_config_name": "zh",
4
- "template_name": "stand for",
5
- "evaluation": {
6
- "accuracy": 0.5158730158730159
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='zh', dataset_name='Muennighoff/xwinograd', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, 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-mt/evaluation_l1/Muennighoff_xwinograd/zh/underscore_refer_to/results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "dataset_name": "Muennighoff/xwinograd",
3
- "dataset_config_name": "zh",
4
- "template_name": "underscore refer to",
5
- "evaluation": {
6
- "accuracy": 0.6765873015873016
7
- },
8
- "arguments": "Namespace(config_name=None, dataset_config_name='zh', dataset_name='Muennighoff/xwinograd', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/tr13-176b-ml-t0-lmtoks341b-t0toks4b-xp3mt/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, 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
- }