Muennighoff commited on
Commit
5491b69
·
1 Parent(s): ffcf2c0
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 +31 -0
  3. evaluation/Muennighoff_xstory_cloze/ar/Answer_Given_options/results.json +9 -0
  4. evaluation/Muennighoff_xstory_cloze/ar/Choose_Story_Ending/results.json +9 -0
  5. evaluation/Muennighoff_xstory_cloze/ar/Generate_Ending/results.json +9 -0
  6. evaluation/Muennighoff_xstory_cloze/ar/Novel_Correct_Ending/results.json +9 -0
  7. evaluation/Muennighoff_xstory_cloze/ar/Story_Continuation_and_Options/results.json +9 -0
  8. evaluation/Muennighoff_xstory_cloze/es/Answer_Given_options/results.json +9 -0
  9. evaluation/Muennighoff_xstory_cloze/es/Choose_Story_Ending/results.json +9 -0
  10. evaluation/Muennighoff_xstory_cloze/es/Generate_Ending/results.json +9 -0
  11. evaluation/Muennighoff_xstory_cloze/es/Novel_Correct_Ending/results.json +9 -0
  12. evaluation/Muennighoff_xstory_cloze/es/Story_Continuation_and_Options/results.json +9 -0
  13. evaluation/Muennighoff_xstory_cloze/eu/Answer_Given_options/results.json +9 -0
  14. evaluation/Muennighoff_xstory_cloze/eu/Choose_Story_Ending/results.json +9 -0
  15. evaluation/Muennighoff_xstory_cloze/eu/Generate_Ending/results.json +9 -0
  16. evaluation/Muennighoff_xstory_cloze/eu/Novel_Correct_Ending/results.json +9 -0
  17. evaluation/Muennighoff_xstory_cloze/eu/Story_Continuation_and_Options/results.json +9 -0
  18. evaluation/Muennighoff_xstory_cloze/hi/Answer_Given_options/results.json +9 -0
  19. evaluation/Muennighoff_xstory_cloze/hi/Choose_Story_Ending/results.json +9 -0
  20. evaluation/Muennighoff_xstory_cloze/hi/Generate_Ending/results.json +9 -0
  21. evaluation/Muennighoff_xstory_cloze/hi/Story_Continuation_and_Options/results.json +9 -0
  22. evaluation/Muennighoff_xstory_cloze/id/Answer_Given_options/results.json +9 -0
  23. evaluation/Muennighoff_xstory_cloze/id/Generate_Ending/results.json +9 -0
  24. evaluation/Muennighoff_xstory_cloze/id/Novel_Correct_Ending/results.json +9 -0
  25. evaluation/Muennighoff_xstory_cloze/sw/Answer_Given_options/results.json +9 -0
  26. evaluation/Muennighoff_xstory_cloze/sw/Choose_Story_Ending/results.json +9 -0
  27. evaluation/Muennighoff_xstory_cloze/sw/Generate_Ending/results.json +9 -0
  28. evaluation/Muennighoff_xstory_cloze/sw/Novel_Correct_Ending/results.json +9 -0
  29. evaluation/Muennighoff_xstory_cloze/sw/Story_Continuation_and_Options/results.json +9 -0
  30. evaluation/Muennighoff_xstory_cloze/te/Answer_Given_options/results.json +9 -0
  31. evaluation/Muennighoff_xstory_cloze/te/Choose_Story_Ending/results.json +9 -0
  32. evaluation/Muennighoff_xstory_cloze/te/Generate_Ending/results.json +9 -0
  33. evaluation/Muennighoff_xstory_cloze/te/Novel_Correct_Ending/results.json +9 -0
  34. evaluation/Muennighoff_xstory_cloze/zh/Answer_Given_options/results.json +9 -0
  35. evaluation/Muennighoff_xstory_cloze/zh/Choose_Story_Ending/results.json +9 -0
  36. evaluation/Muennighoff_xstory_cloze/zh/Generate_Ending/results.json +9 -0
  37. evaluation/Muennighoff_xstory_cloze/zh/Novel_Correct_Ending/results.json +9 -0
  38. evaluation/Muennighoff_xstory_cloze/zh/Story_Continuation_and_Options/results.json +9 -0
  39. evaluation/Muennighoff_xwinograd/en/Replace/results.json +9 -0
  40. evaluation/Muennighoff_xwinograd/en/True_or_False/results.json +9 -0
  41. evaluation/Muennighoff_xwinograd/en/does_underscore_refer_to/results.json +9 -0
  42. evaluation/Muennighoff_xwinograd/en/stand_for/results.json +9 -0
  43. evaluation/Muennighoff_xwinograd/en/underscore_refer_to/results.json +9 -0
  44. evaluation/Muennighoff_xwinograd/fr/Replace/results.json +9 -0
  45. evaluation/Muennighoff_xwinograd/fr/True_or_False/results.json +9 -0
  46. evaluation/Muennighoff_xwinograd/fr/does_underscore_refer_to/results.json +9 -0
  47. evaluation/Muennighoff_xwinograd/fr/stand_for/results.json +9 -0
  48. evaluation/Muennighoff_xwinograd/fr/underscore_refer_to/results.json +9 -0
  49. evaluation/Muennighoff_xwinograd/pt/Replace/results.json +9 -0
  50. evaluation/Muennighoff_xwinograd/pt/True_or_False/results.json +9 -0
.gitattributes CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "apply_residual_connection_post_layernorm": false,
3
+ "architectures": [
4
+ "BloomModel"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "attention_softmax_in_fp32": true,
8
+ "bias_dropout_fusion": true,
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": 4096,
17
+ "n_inner": null,
18
+ "n_layer": 30,
19
+ "num_attention_heads": 32,
20
+ "offset_alibi": 100,
21
+ "pad_token_id": 3,
22
+ "pretraining_tp": 4,
23
+ "seq_length": 2048,
24
+ "skip_bias_add": true,
25
+ "skip_bias_add_qkv": false,
26
+ "slow_but_exact": false,
27
+ "transformers_version": "4.21.0.dev0",
28
+ "unk_token_id": 0,
29
+ "use_cache": true,
30
+ "vocab_size": 250880
31
+ }
evaluation/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": 0.5360688285903376
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='ar', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/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": 0.5188616810059563
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='ar', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/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": 0.5916611515552614
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='ar', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/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": 0.528788881535407
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='ar', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/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": 0.5109199205823958
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='ar', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/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": 0.5023163467902052
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='es', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/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": 0.5274652547981469
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='es', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/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": 0.6644606221045665
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='es', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/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": 0.5095962938451357
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='es', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/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": 0.5115817339510258
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='es', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/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": 0.49172733289212445
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='eu', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/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": 0.4672402382528127
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='eu', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/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": 0.5737921906022502
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='eu', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/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": 0.4784910655195235
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='eu', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/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": 0.4685638649900728
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='eu', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/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": 0.4923891462607545
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='hi', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/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": 0.5181998676373263
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='hi', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/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": 0.5936465916611515
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='hi', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/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": 0.5102581072137657
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='hi', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/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": 0.5082726671078756
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='id', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/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": 0.6267372600926538
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='id', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/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": 0.5043017868960953
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='id', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/Muennighoff_xstory_cloze/sw/Answer_Given_options/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_name": "Muennighoff/xstory_cloze",
3
+ "dataset_config_name": "sw",
4
+ "template_name": "Answer Given options",
5
+ "evaluation": {
6
+ "accuracy": 0.5062872270019855
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='sw', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/Muennighoff_xstory_cloze/sw/Choose_Story_Ending/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_name": "Muennighoff/xstory_cloze",
3
+ "dataset_config_name": "sw",
4
+ "template_name": "Choose Story Ending",
5
+ "evaluation": {
6
+ "accuracy": 0.5069490403706155
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='sw', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/Muennighoff_xstory_cloze/sw/Generate_Ending/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_name": "Muennighoff/xstory_cloze",
3
+ "dataset_config_name": "sw",
4
+ "template_name": "Generate Ending",
5
+ "evaluation": {
6
+ "accuracy": 0.5446724023825281
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='sw', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/Muennighoff_xstory_cloze/sw/Novel_Correct_Ending/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_name": "Muennighoff/xstory_cloze",
3
+ "dataset_config_name": "sw",
4
+ "template_name": "Novel Correct Ending",
5
+ "evaluation": {
6
+ "accuracy": 0.5029781601588352
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='sw', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/Muennighoff_xstory_cloze/sw/Story_Continuation_and_Options/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_name": "Muennighoff/xstory_cloze",
3
+ "dataset_config_name": "sw",
4
+ "template_name": "Story Continuation and Options",
5
+ "evaluation": {
6
+ "accuracy": 0.5102581072137657
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='sw', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/Muennighoff_xstory_cloze/te/Answer_Given_options/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_name": "Muennighoff/xstory_cloze",
3
+ "dataset_config_name": "te",
4
+ "template_name": "Answer Given options",
5
+ "evaluation": {
6
+ "accuracy": 0.48643282594308407
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='te', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/Muennighoff_xstory_cloze/te/Choose_Story_Ending/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_name": "Muennighoff/xstory_cloze",
3
+ "dataset_config_name": "te",
4
+ "template_name": "Choose Story Ending",
5
+ "evaluation": {
6
+ "accuracy": 0.5274652547981469
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='te', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/Muennighoff_xstory_cloze/te/Generate_Ending/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_name": "Muennighoff/xstory_cloze",
3
+ "dataset_config_name": "te",
4
+ "template_name": "Generate Ending",
5
+ "evaluation": {
6
+ "accuracy": 0.585704831237591
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='te', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/Muennighoff_xstory_cloze/te/Novel_Correct_Ending/results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_name": "Muennighoff/xstory_cloze",
3
+ "dataset_config_name": "te",
4
+ "template_name": "Novel Correct Ending",
5
+ "evaluation": {
6
+ "accuracy": 0.49172733289212445
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='te', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/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": 0.5122435473196558
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='zh', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/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": 0.5095962938451357
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='zh', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/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": 0.6254136333553938
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='zh', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/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": 0.5215089344804765
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='zh', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/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": 0.5162144275314361
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='zh', dataset_name='Muennighoff/xstory_cloze', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/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": 0.5075268817204301
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='en', dataset_name='Muennighoff/xwinograd', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/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": 0.5156989247311828
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='en', dataset_name='Muennighoff/xwinograd', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/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": 0.5010752688172043
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='en', dataset_name='Muennighoff/xwinograd', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/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": 0.5023655913978494
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='en', dataset_name='Muennighoff/xwinograd', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/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": 0.5083870967741936
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='en', dataset_name='Muennighoff/xwinograd', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/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": 0.46987951807228917
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='fr', dataset_name='Muennighoff/xwinograd', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/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='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/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": 0.5542168674698795
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='fr', dataset_name='Muennighoff/xwinograd', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/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": 0.4457831325301205
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='fr', dataset_name='Muennighoff/xwinograd', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/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": 0.5421686746987951
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='fr', dataset_name='Muennighoff/xwinograd', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/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": 0.5057034220532319
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='pt', dataset_name='Muennighoff/xwinograd', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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/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": 0.5475285171102662
7
+ },
8
+ "arguments": "Namespace(config_name=None, dataset_config_name='pt', dataset_name='Muennighoff/xwinograd', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000', nospace=False, output_dir='/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3t0/tasky_global_step1000/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
+ }