Muennighoff
commited on
Commit
•
254560d
1
Parent(s):
5d98487
Add fiels
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +1 -0
- config.json +30 -0
- evaluation_l1/Muennighoff_xstory_cloze/ar/Answer_Given_options/results.json +9 -0
- evaluation_l1/Muennighoff_xstory_cloze/ar/Choose_Story_Ending/results.json +9 -0
- evaluation_l1/Muennighoff_xstory_cloze/ar/Generate_Ending/results.json +9 -0
- evaluation_l1/Muennighoff_xstory_cloze/ar/Novel_Correct_Ending/results.json +9 -0
- evaluation_l1/Muennighoff_xstory_cloze/ar/Story_Continuation_and_Options/results.json +9 -0
- evaluation_l1/Muennighoff_xstory_cloze/es/Answer_Given_options/results.json +9 -0
- evaluation_l1/Muennighoff_xstory_cloze/es/Choose_Story_Ending/results.json +9 -0
- evaluation_l1/Muennighoff_xstory_cloze/es/Generate_Ending/results.json +9 -0
- evaluation_l1/Muennighoff_xstory_cloze/es/Novel_Correct_Ending/results.json +9 -0
- evaluation_l1/Muennighoff_xstory_cloze/es/Story_Continuation_and_Options/results.json +9 -0
- evaluation_l1/Muennighoff_xstory_cloze/eu/Answer_Given_options/results.json +9 -0
- evaluation_l1/Muennighoff_xstory_cloze/eu/Choose_Story_Ending/results.json +9 -0
- evaluation_l1/Muennighoff_xstory_cloze/eu/Generate_Ending/results.json +9 -0
- evaluation_l1/Muennighoff_xstory_cloze/eu/Novel_Correct_Ending/results.json +9 -0
- evaluation_l1/Muennighoff_xstory_cloze/eu/Story_Continuation_and_Options/results.json +9 -0
- evaluation_l1/Muennighoff_xstory_cloze/hi/Answer_Given_options/results.json +9 -0
- evaluation_l1/Muennighoff_xstory_cloze/hi/Choose_Story_Ending/results.json +9 -0
- evaluation_l1/Muennighoff_xstory_cloze/hi/Generate_Ending/results.json +9 -0
- evaluation_l1/Muennighoff_xstory_cloze/hi/Novel_Correct_Ending/results.json +9 -0
- evaluation_l1/Muennighoff_xstory_cloze/hi/Story_Continuation_and_Options/results.json +9 -0
- evaluation_l1/Muennighoff_xstory_cloze/id/Answer_Given_options/results.json +9 -0
- evaluation_l1/Muennighoff_xstory_cloze/id/Choose_Story_Ending/results.json +9 -0
- evaluation_l1/Muennighoff_xstory_cloze/id/Generate_Ending/results.json +9 -0
- evaluation_l1/Muennighoff_xstory_cloze/id/Novel_Correct_Ending/results.json +9 -0
- evaluation_l1/Muennighoff_xstory_cloze/id/Story_Continuation_and_Options/results.json +9 -0
- evaluation_l1/Muennighoff_xstory_cloze/zh/Answer_Given_options/results.json +9 -0
- evaluation_l1/Muennighoff_xstory_cloze/zh/Choose_Story_Ending/results.json +9 -0
- evaluation_l1/Muennighoff_xstory_cloze/zh/Generate_Ending/results.json +9 -0
- evaluation_l1/Muennighoff_xstory_cloze/zh/Novel_Correct_Ending/results.json +9 -0
- evaluation_l1/Muennighoff_xstory_cloze/zh/Story_Continuation_and_Options/results.json +9 -0
- evaluation_l1/Muennighoff_xwinograd/en/Replace/results.json +9 -0
- evaluation_l1/Muennighoff_xwinograd/en/True_or_False/results.json +9 -0
- evaluation_l1/Muennighoff_xwinograd/en/does_underscore_refer_to/results.json +9 -0
- evaluation_l1/Muennighoff_xwinograd/en/stand_for/results.json +9 -0
- evaluation_l1/Muennighoff_xwinograd/en/underscore_refer_to/results.json +9 -0
- evaluation_l1/Muennighoff_xwinograd/fr/Replace/results.json +9 -0
- evaluation_l1/Muennighoff_xwinograd/fr/True_or_False/results.json +9 -0
- evaluation_l1/Muennighoff_xwinograd/fr/does_underscore_refer_to/results.json +9 -0
- evaluation_l1/Muennighoff_xwinograd/fr/stand_for/results.json +9 -0
- evaluation_l1/Muennighoff_xwinograd/fr/underscore_refer_to/results.json +9 -0
- evaluation_l1/Muennighoff_xwinograd/pt/Replace/results.json +9 -0
- evaluation_l1/Muennighoff_xwinograd/pt/True_or_False/results.json +9 -0
- evaluation_l1/Muennighoff_xwinograd/pt/does_underscore_refer_to/results.json +9 -0
- evaluation_l1/Muennighoff_xwinograd/pt/stand_for/results.json +9 -0
- evaluation_l1/Muennighoff_xwinograd/pt/underscore_refer_to/results.json +9 -0
- evaluation_l1/Muennighoff_xwinograd/zh/Replace/results.json +9 -0
- evaluation_l1/Muennighoff_xwinograd/zh/True_or_False/results.json +9 -0
- 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 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"apply_residual_connection_post_layernorm": false,
|
3 |
+
"attention_dropout": 0.0,
|
4 |
+
"attention_softmax_in_fp32": true,
|
5 |
+
"architectures": [
|
6 |
+
"BloomModel"
|
7 |
+
],
|
8 |
+
"bias_dropout_fusion": true,
|
9 |
+
"bos_token_id": 1,
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"pad_token_id": 3,
|
12 |
+
"unk_token_id": 0,
|
13 |
+
"hidden_dropout": 0.0,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"layer_norm_epsilon": 1e-05,
|
16 |
+
"masked_softmax_fusion": true,
|
17 |
+
"model_type": "bloom",
|
18 |
+
"n_embed": 2048,
|
19 |
+
"n_inner": null,
|
20 |
+
"n_layer": 24,
|
21 |
+
"num_attention_heads": 16,
|
22 |
+
"offset_alibi": 100,
|
23 |
+
"pretraining_tp": 2,
|
24 |
+
"seq_length": 4096,
|
25 |
+
"skip_bias_add": true,
|
26 |
+
"skip_bias_add_qkv": false,
|
27 |
+
"transformers_version": "4.20.0",
|
28 |
+
"use_cache": true,
|
29 |
+
"vocab_size": 250880
|
30 |
+
}
|
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": 0.5559232296492389
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.7332892124420913
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.5473196558570483
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.6949040370615487
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.7074784910655195
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.5956320317670417
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.7796161482461945
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.6022501654533422
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.6955658504301787
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.7551290536068829
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.49040370615486434
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.6048974189278623
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.5109199205823958
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.5704831237590999
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.5949702183984117
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.5671740569159497
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.728656518861681
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.5671740569159497
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.6803441429516877
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.7220383851753805
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.5691594970218399
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.7491727332892124
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.5830575777630708
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.6399735274652548
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.7432164129715421
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.5771012574454004
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.786896095301125
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.5823957643944407
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.7703507610853739
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.7683653209794837
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.5634408602150538
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.5208602150537635
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.5053763440860215
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.4997849462365591
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.5303225806451612
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.5301204819277109
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.5542168674698795
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.4819277108433735
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.5180722891566265
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.5180722891566265
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.532319391634981
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.5133079847908745
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.5095057034220533
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.4866920152091255
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.49429657794676807
|
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/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.5615079365079365
|
7 |
+
},
|
8 |
+
"arguments": "Namespace(config_name=None, dataset_config_name='zh', dataset_name='Muennighoff/xwinograd', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.5297619047619048
|
7 |
+
},
|
8 |
+
"arguments": "Namespace(config_name=None, dataset_config_name='zh', dataset_name='Muennighoff/xwinograd', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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": 0.49206349206349204
|
7 |
+
},
|
8 |
+
"arguments": "Namespace(config_name=None, dataset_config_name='zh', dataset_name='Muennighoff/xwinograd', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/1b3t0/bloomz-1b7/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 |
+
}
|