Muennighoff commited on
Commit
44fd161
1 Parent(s): 0985003
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +1 -0
  2. config.json +25 -0
  3. evaluation_l1/Muennighoff_xstory_cloze/ar/Answer_Given_options/results.json +9 -0
  4. evaluation_l1/Muennighoff_xstory_cloze/ar/Choose_Story_Ending/results.json +9 -0
  5. evaluation_l1/Muennighoff_xstory_cloze/ar/Generate_Ending/results.json +9 -0
  6. evaluation_l1/Muennighoff_xstory_cloze/ar/Novel_Correct_Ending/results.json +9 -0
  7. evaluation_l1/Muennighoff_xstory_cloze/ar/Story_Continuation_and_Options/results.json +9 -0
  8. evaluation_l1/Muennighoff_xstory_cloze/es/Answer_Given_options/results.json +9 -0
  9. evaluation_l1/Muennighoff_xstory_cloze/es/Choose_Story_Ending/results.json +9 -0
  10. evaluation_l1/Muennighoff_xstory_cloze/es/Generate_Ending/results.json +9 -0
  11. evaluation_l1/Muennighoff_xstory_cloze/es/Novel_Correct_Ending/results.json +9 -0
  12. evaluation_l1/Muennighoff_xstory_cloze/es/Story_Continuation_and_Options/results.json +9 -0
  13. evaluation_l1/Muennighoff_xstory_cloze/eu/Answer_Given_options/results.json +9 -0
  14. evaluation_l1/Muennighoff_xstory_cloze/eu/Choose_Story_Ending/results.json +9 -0
  15. evaluation_l1/Muennighoff_xstory_cloze/eu/Generate_Ending/results.json +9 -0
  16. evaluation_l1/Muennighoff_xstory_cloze/eu/Novel_Correct_Ending/results.json +9 -0
  17. evaluation_l1/Muennighoff_xstory_cloze/eu/Story_Continuation_and_Options/results.json +9 -0
  18. evaluation_l1/Muennighoff_xstory_cloze/hi/Answer_Given_options/results.json +9 -0
  19. evaluation_l1/Muennighoff_xstory_cloze/hi/Choose_Story_Ending/results.json +9 -0
  20. evaluation_l1/Muennighoff_xstory_cloze/hi/Generate_Ending/results.json +9 -0
  21. evaluation_l1/Muennighoff_xstory_cloze/hi/Novel_Correct_Ending/results.json +9 -0
  22. evaluation_l1/Muennighoff_xstory_cloze/hi/Story_Continuation_and_Options/results.json +9 -0
  23. evaluation_l1/Muennighoff_xstory_cloze/id/Answer_Given_options/results.json +9 -0
  24. evaluation_l1/Muennighoff_xstory_cloze/id/Choose_Story_Ending/results.json +9 -0
  25. evaluation_l1/Muennighoff_xstory_cloze/id/Generate_Ending/results.json +9 -0
  26. evaluation_l1/Muennighoff_xstory_cloze/id/Novel_Correct_Ending/results.json +9 -0
  27. evaluation_l1/Muennighoff_xstory_cloze/id/Story_Continuation_and_Options/results.json +9 -0
  28. evaluation_l1/Muennighoff_xstory_cloze/zh/Answer_Given_options/results.json +9 -0
  29. evaluation_l1/Muennighoff_xstory_cloze/zh/Choose_Story_Ending/results.json +9 -0
  30. evaluation_l1/Muennighoff_xstory_cloze/zh/Generate_Ending/results.json +9 -0
  31. evaluation_l1/Muennighoff_xstory_cloze/zh/Novel_Correct_Ending/results.json +9 -0
  32. evaluation_l1/Muennighoff_xstory_cloze/zh/Story_Continuation_and_Options/results.json +9 -0
  33. evaluation_l1/Muennighoff_xwinograd/en/Replace/results.json +9 -0
  34. evaluation_l1/Muennighoff_xwinograd/en/True_or_False/results.json +9 -0
  35. evaluation_l1/Muennighoff_xwinograd/en/does_underscore_refer_to/results.json +9 -0
  36. evaluation_l1/Muennighoff_xwinograd/en/stand_for/results.json +9 -0
  37. evaluation_l1/Muennighoff_xwinograd/en/underscore_refer_to/results.json +9 -0
  38. evaluation_l1/Muennighoff_xwinograd/fr/Replace/results.json +9 -0
  39. evaluation_l1/Muennighoff_xwinograd/fr/True_or_False/results.json +9 -0
  40. evaluation_l1/Muennighoff_xwinograd/fr/does_underscore_refer_to/results.json +9 -0
  41. evaluation_l1/Muennighoff_xwinograd/fr/stand_for/results.json +9 -0
  42. evaluation_l1/Muennighoff_xwinograd/fr/underscore_refer_to/results.json +9 -0
  43. evaluation_l1/Muennighoff_xwinograd/pt/Replace/results.json +9 -0
  44. evaluation_l1/Muennighoff_xwinograd/pt/True_or_False/results.json +9 -0
  45. evaluation_l1/Muennighoff_xwinograd/pt/does_underscore_refer_to/results.json +9 -0
  46. evaluation_l1/Muennighoff_xwinograd/pt/stand_for/results.json +9 -0
  47. evaluation_l1/Muennighoff_xwinograd/pt/underscore_refer_to/results.json +9 -0
  48. evaluation_l1/Muennighoff_xwinograd/zh/Replace/results.json +9 -0
  49. evaluation_l1/Muennighoff_xwinograd/zh/True_or_False/results.json +9 -0
  50. evaluation_l1/Muennighoff_xwinograd/zh/does_underscore_refer_to/results.json +9 -0
.gitattributes CHANGED
@@ -30,3 +30,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
30
  *.zip filter=lfs diff=lfs merge=lfs -text
31
  *.zst filter=lfs diff=lfs merge=lfs -text
32
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
30
  *.zip filter=lfs diff=lfs merge=lfs -text
31
  *.zst filter=lfs diff=lfs merge=lfs -text
32
  *tfevents* filter=lfs diff=lfs merge=lfs -text
33
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "apply_residual_connection_post_layernorm": false,
3
+ "attention_dropout": 0.0,
4
+ "architectures": [
5
+ "BloomModel"
6
+ ],
7
+ "attention_softmax_in_fp32": true,
8
+ "pad_token_id": 3,
9
+ "bos_token_id": 1,
10
+ "eos_token_id": 2,
11
+ "hidden_dropout": 0.0,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "masked_softmax_fusion": true,
15
+ "model_type": "bloom",
16
+ "n_embed": 14336,
17
+ "n_layer": 70,
18
+ "num_attention_heads": 112,
19
+ "pretraining_tp": 4,
20
+ "slow_but_exact": false,
21
+ "transformers_version": "4.21.0",
22
+ "use_cache": true,
23
+ "vocab_size": 250880
24
+ }
25
+
evaluation_l1/Muennighoff_xstory_cloze/ar/Answer_Given_options/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xstory_cloze/ar/Choose_Story_Ending/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xstory_cloze/ar/Generate_Ending/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xstory_cloze/ar/Novel_Correct_Ending/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xstory_cloze/ar/Story_Continuation_and_Options/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xstory_cloze/es/Answer_Given_options/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xstory_cloze/es/Choose_Story_Ending/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xstory_cloze/es/Generate_Ending/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xstory_cloze/es/Novel_Correct_Ending/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xstory_cloze/es/Story_Continuation_and_Options/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xstory_cloze/eu/Answer_Given_options/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xstory_cloze/eu/Choose_Story_Ending/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xstory_cloze/eu/Generate_Ending/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xstory_cloze/eu/Novel_Correct_Ending/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xstory_cloze/eu/Story_Continuation_and_Options/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xstory_cloze/hi/Answer_Given_options/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xstory_cloze/hi/Choose_Story_Ending/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xstory_cloze/hi/Generate_Ending/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xstory_cloze/hi/Novel_Correct_Ending/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xstory_cloze/hi/Story_Continuation_and_Options/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xstory_cloze/id/Answer_Given_options/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xstory_cloze/id/Choose_Story_Ending/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xstory_cloze/id/Generate_Ending/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xstory_cloze/id/Novel_Correct_Ending/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xstory_cloze/id/Story_Continuation_and_Options/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xstory_cloze/zh/Answer_Given_options/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xstory_cloze/zh/Choose_Story_Ending/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xstory_cloze/zh/Generate_Ending/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xstory_cloze/zh/Novel_Correct_Ending/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xstory_cloze/zh/Story_Continuation_and_Options/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xwinograd/en/Replace/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xwinograd/en/True_or_False/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xwinograd/en/does_underscore_refer_to/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xwinograd/en/stand_for/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xwinograd/en/underscore_refer_to/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xwinograd/fr/Replace/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xwinograd/fr/True_or_False/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xwinograd/fr/does_underscore_refer_to/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xwinograd/fr/stand_for/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xwinograd/fr/underscore_refer_to/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xwinograd/pt/Replace/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xwinograd/pt/True_or_False/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xwinograd/pt/does_underscore_refer_to/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xwinograd/pt/stand_for/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xwinograd/pt/underscore_refer_to/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xwinograd/zh/Replace/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xwinograd/zh/True_or_False/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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_l1/Muennighoff_xwinograd/zh/does_underscore_refer_to/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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
+ }