diff --git a/evaluation_l1/Muennighoff_xstory_cloze/ar/Choose_Story_Ending/results.json b/evaluation_l1/Muennighoff_xstory_cloze/ar/Choose_Story_Ending/results.json new file mode 100644 index 0000000000000000000000000000000000000000..96a180bfedb69ca3e8350cede23b277f4343598f --- /dev/null +++ b/evaluation_l1/Muennighoff_xstory_cloze/ar/Choose_Story_Ending/results.json @@ -0,0 +1,9 @@ +{ + "dataset_name": "Muennighoff/xstory_cloze", + "dataset_config_name": "ar", + "template_name": "Choose Story Ending", + "evaluation": { + "accuracy": 0.8060886829913965 + }, + "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/2b5t0/bloomz-3b', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b/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)" +} \ No newline at end of file diff --git a/evaluation_l1/Muennighoff_xstory_cloze/ar/Generate_Ending/results.json b/evaluation_l1/Muennighoff_xstory_cloze/ar/Generate_Ending/results.json new file mode 100644 index 0000000000000000000000000000000000000000..298a8972d27fa22a145b40e397c24c1512e9854b --- /dev/null +++ b/evaluation_l1/Muennighoff_xstory_cloze/ar/Generate_Ending/results.json @@ -0,0 +1,9 @@ +{ + "dataset_name": "Muennighoff/xstory_cloze", + "dataset_config_name": "ar", + "template_name": "Generate Ending", + "evaluation": { + "accuracy": 0.5684976836532097 + }, + "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/2b5t0/bloomz-3b', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b/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)" +} \ No newline at end of file diff --git a/evaluation_l1/Muennighoff_xstory_cloze/es/Answer_Given_options/results.json b/evaluation_l1/Muennighoff_xstory_cloze/es/Answer_Given_options/results.json new file mode 100644 index 0000000000000000000000000000000000000000..e3c63b9122e58d2376f189281f21524b65e968cc --- /dev/null +++ b/evaluation_l1/Muennighoff_xstory_cloze/es/Answer_Given_options/results.json @@ -0,0 +1,9 @@ +{ + "dataset_name": "Muennighoff/xstory_cloze", + "dataset_config_name": "es", + "template_name": "Answer Given options", + "evaluation": { + "accuracy": 0.7498345466578424 + }, + "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/2b5t0/bloomz-3b', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b/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)" +} \ No newline at end of file diff --git a/evaluation_l1/Muennighoff_xstory_cloze/es/Choose_Story_Ending/results.json b/evaluation_l1/Muennighoff_xstory_cloze/es/Choose_Story_Ending/results.json new file mode 100644 index 0000000000000000000000000000000000000000..a720a12fe3a75c52416fec50567aad2811d88b6f --- /dev/null +++ b/evaluation_l1/Muennighoff_xstory_cloze/es/Choose_Story_Ending/results.json @@ -0,0 +1,9 @@ +{ + "dataset_name": "Muennighoff/xstory_cloze", + "dataset_config_name": "es", + "template_name": "Choose Story Ending", + "evaluation": { + "accuracy": 0.8590337524818001 + }, + "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/2b5t0/bloomz-3b', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b/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)" +} \ No newline at end of file diff --git a/evaluation_l1/Muennighoff_xstory_cloze/es/Generate_Ending/results.json b/evaluation_l1/Muennighoff_xstory_cloze/es/Generate_Ending/results.json new file mode 100644 index 0000000000000000000000000000000000000000..1297bcfa9f3d3985dd3577dc8d9ad535c7455cb6 --- /dev/null +++ b/evaluation_l1/Muennighoff_xstory_cloze/es/Generate_Ending/results.json @@ -0,0 +1,9 @@ +{ + "dataset_name": "Muennighoff/xstory_cloze", + "dataset_config_name": "es", + "template_name": "Generate Ending", + "evaluation": { + "accuracy": 0.6260754467240238 + }, + "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/2b5t0/bloomz-3b', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b/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)" +} \ No newline at end of file diff --git a/evaluation_l1/Muennighoff_xstory_cloze/es/Novel_Correct_Ending/results.json b/evaluation_l1/Muennighoff_xstory_cloze/es/Novel_Correct_Ending/results.json new file mode 100644 index 0000000000000000000000000000000000000000..a4706135974a71513adcfffa59077fdbf03caac9 --- /dev/null +++ b/evaluation_l1/Muennighoff_xstory_cloze/es/Novel_Correct_Ending/results.json @@ -0,0 +1,9 @@ +{ + "dataset_name": "Muennighoff/xstory_cloze", + "dataset_config_name": "es", + "template_name": "Novel Correct Ending", + "evaluation": { + "accuracy": 0.8166776968894772 + }, + "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/2b5t0/bloomz-3b', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b/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)" +} \ No newline at end of file diff --git a/evaluation_l1/Muennighoff_xstory_cloze/es/Story_Continuation_and_Options/results.json b/evaluation_l1/Muennighoff_xstory_cloze/es/Story_Continuation_and_Options/results.json new file mode 100644 index 0000000000000000000000000000000000000000..04ae4d293c1052a5ed5c450908fea29db1c803fa --- /dev/null +++ b/evaluation_l1/Muennighoff_xstory_cloze/es/Story_Continuation_and_Options/results.json @@ -0,0 +1,9 @@ +{ + "dataset_name": "Muennighoff/xstory_cloze", + "dataset_config_name": "es", + "template_name": "Story Continuation and Options", + "evaluation": { + "accuracy": 0.8352084712111185 + }, + "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/2b5t0/bloomz-3b', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b/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)" +} \ No newline at end of file diff --git a/evaluation_l1/Muennighoff_xstory_cloze/eu/Story_Continuation_and_Options/results.json b/evaluation_l1/Muennighoff_xstory_cloze/eu/Story_Continuation_and_Options/results.json new file mode 100644 index 0000000000000000000000000000000000000000..40b21d2df8deb0511232fbff9ba8e86f5f354450 --- /dev/null +++ b/evaluation_l1/Muennighoff_xstory_cloze/eu/Story_Continuation_and_Options/results.json @@ -0,0 +1,9 @@ +{ + "dataset_name": "Muennighoff/xstory_cloze", + "dataset_config_name": "eu", + "template_name": "Story Continuation and Options", + "evaluation": { + "accuracy": 0.7074784910655195 + }, + "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/2b5t0/bloomz-3b', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b/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)" +} \ No newline at end of file diff --git a/evaluation_l1/Muennighoff_xwinograd/fr/underscore_refer_to/results.json b/evaluation_l1/Muennighoff_xwinograd/fr/underscore_refer_to/results.json new file mode 100644 index 0000000000000000000000000000000000000000..a11aa2ad249d23c91dd79a5abc33b7a2afb877c3 --- /dev/null +++ b/evaluation_l1/Muennighoff_xwinograd/fr/underscore_refer_to/results.json @@ -0,0 +1,9 @@ +{ + "dataset_name": "Muennighoff/xwinograd", + "dataset_config_name": "fr", + "template_name": "underscore refer to", + "evaluation": { + "accuracy": 0.5301204819277109 + }, + "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/2b5t0/bloomz-3b', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b/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)" +} \ No newline at end of file diff --git a/evaluation_l1/Muennighoff_xwinograd/zh/True_or_False/results.json b/evaluation_l1/Muennighoff_xwinograd/zh/True_or_False/results.json new file mode 100644 index 0000000000000000000000000000000000000000..6fc263c6800c16b18c1c4fa5baeb8681f111acde --- /dev/null +++ b/evaluation_l1/Muennighoff_xwinograd/zh/True_or_False/results.json @@ -0,0 +1,9 @@ +{ + "dataset_name": "Muennighoff/xwinograd", + "dataset_config_name": "zh", + "template_name": "True or False", + "evaluation": { + "accuracy": 0.5515873015873016 + }, + "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/2b5t0/bloomz-3b', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b/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)" +} \ No newline at end of file diff --git a/evaluation_l1/Muennighoff_xwinograd/zh/does_underscore_refer_to/results.json b/evaluation_l1/Muennighoff_xwinograd/zh/does_underscore_refer_to/results.json new file mode 100644 index 0000000000000000000000000000000000000000..3f601fad695841efffa6c49527c4a726a060db63 --- /dev/null +++ b/evaluation_l1/Muennighoff_xwinograd/zh/does_underscore_refer_to/results.json @@ -0,0 +1,9 @@ +{ + "dataset_name": "Muennighoff/xwinograd", + "dataset_config_name": "zh", + "template_name": "does underscore refer to", + "evaluation": { + "accuracy": 0.5357142857142857 + }, + "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/2b5t0/bloomz-3b', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b/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)" +} \ No newline at end of file diff --git a/evaluation_l1/Muennighoff_xwinograd/zh/stand_for/results.json b/evaluation_l1/Muennighoff_xwinograd/zh/stand_for/results.json new file mode 100644 index 0000000000000000000000000000000000000000..b08dc3fec50e171d69434b4d3df061f599ba54ef --- /dev/null +++ b/evaluation_l1/Muennighoff_xwinograd/zh/stand_for/results.json @@ -0,0 +1,9 @@ +{ + "dataset_name": "Muennighoff/xwinograd", + "dataset_config_name": "zh", + "template_name": "stand for", + "evaluation": { + "accuracy": 0.5238095238095238 + }, + "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/2b5t0/bloomz-3b', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b/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)" +} \ No newline at end of file diff --git a/evaluation_l1/xnli/sw/can_we_infer/results.json b/evaluation_l1/xnli/sw/can_we_infer/results.json new file mode 100644 index 0000000000000000000000000000000000000000..f313a515fe8c47e1374e044f1ad90a558c75630d --- /dev/null +++ b/evaluation_l1/xnli/sw/can_we_infer/results.json @@ -0,0 +1,9 @@ +{ + "dataset_name": "xnli", + "dataset_config_name": "sw", + "template_name": "can we infer", + "evaluation": { + "accuracy": 0.41767068273092367 + }, + "arguments": "Namespace(config_name=None, dataset_config_name='sw', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b/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='can we infer', tokenizer_name=None, use_slow_tokenizer=False)" +} \ No newline at end of file diff --git a/evaluation_l1/xnli/ur/GPT-3_style/results.json b/evaluation_l1/xnli/ur/GPT-3_style/results.json new file mode 100644 index 0000000000000000000000000000000000000000..bcb04221302c0e5458c20688b5686b074d11cd63 --- /dev/null +++ b/evaluation_l1/xnli/ur/GPT-3_style/results.json @@ -0,0 +1,9 @@ +{ + "dataset_name": "xnli", + "dataset_config_name": "ur", + "template_name": "GPT-3 style", + "evaluation": { + "accuracy": 0.4903614457831325 + }, + "arguments": "Namespace(config_name=None, dataset_config_name='ur', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b/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='GPT-3 style', tokenizer_name=None, use_slow_tokenizer=False)" +} \ No newline at end of file diff --git a/evaluation_l1/xnli/ur/MNLI_crowdsource/results.json b/evaluation_l1/xnli/ur/MNLI_crowdsource/results.json new file mode 100644 index 0000000000000000000000000000000000000000..fc1721a806a978f22a4dc6461c889d935d2ca118 --- /dev/null +++ b/evaluation_l1/xnli/ur/MNLI_crowdsource/results.json @@ -0,0 +1,9 @@ +{ + "dataset_name": "xnli", + "dataset_config_name": "ur", + "template_name": "MNLI crowdsource", + "evaluation": { + "accuracy": 0.36666666666666664 + }, + "arguments": "Namespace(config_name=None, dataset_config_name='ur', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b/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='MNLI crowdsource', tokenizer_name=None, use_slow_tokenizer=False)" +} \ No newline at end of file diff --git a/evaluation_l1/xnli/ur/can_we_infer/results.json b/evaluation_l1/xnli/ur/can_we_infer/results.json new file mode 100644 index 0000000000000000000000000000000000000000..fa0d73440216816909c050de3a09c50514e28aab --- /dev/null +++ b/evaluation_l1/xnli/ur/can_we_infer/results.json @@ -0,0 +1,9 @@ +{ + "dataset_name": "xnli", + "dataset_config_name": "ur", + "template_name": "can we infer", + "evaluation": { + "accuracy": 0.43654618473895584 + }, + "arguments": "Namespace(config_name=None, dataset_config_name='ur', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b/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='can we infer', tokenizer_name=None, use_slow_tokenizer=False)" +} \ No newline at end of file diff --git a/evaluation_l1/xnli/ur/guaranteed_possible_impossible/results.json b/evaluation_l1/xnli/ur/guaranteed_possible_impossible/results.json new file mode 100644 index 0000000000000000000000000000000000000000..1c5db6041c202869fb13d329b94823b09364074b --- /dev/null +++ b/evaluation_l1/xnli/ur/guaranteed_possible_impossible/results.json @@ -0,0 +1,9 @@ +{ + "dataset_name": "xnli", + "dataset_config_name": "ur", + "template_name": "guaranteed/possible/impossible", + "evaluation": { + "accuracy": 0.3345381526104418 + }, + "arguments": "Namespace(config_name=None, dataset_config_name='ur', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b/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='guaranteed/possible/impossible', tokenizer_name=None, use_slow_tokenizer=False)" +} \ No newline at end of file diff --git a/evaluation_l1/xnli/ur/justified_in_saying/results.json b/evaluation_l1/xnli/ur/justified_in_saying/results.json new file mode 100644 index 0000000000000000000000000000000000000000..1ef6d518b3c9f3f0df148fe38bc7684c58a1475a --- /dev/null +++ b/evaluation_l1/xnli/ur/justified_in_saying/results.json @@ -0,0 +1,9 @@ +{ + "dataset_name": "xnli", + "dataset_config_name": "ur", + "template_name": "justified in saying", + "evaluation": { + "accuracy": 0.42891566265060244 + }, + "arguments": "Namespace(config_name=None, dataset_config_name='ur', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b/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='justified in saying', tokenizer_name=None, use_slow_tokenizer=False)" +} \ No newline at end of file diff --git a/evaluation_l2/Muennighoff_xwinograd/jp/underscore_refer_to/results.json b/evaluation_l2/Muennighoff_xwinograd/jp/underscore_refer_to/results.json new file mode 100644 index 0000000000000000000000000000000000000000..3e9e1ae38f6de323a731b991f21fd5d9078f3ae4 --- /dev/null +++ b/evaluation_l2/Muennighoff_xwinograd/jp/underscore_refer_to/results.json @@ -0,0 +1,9 @@ +{ + "dataset_name": "Muennighoff/xwinograd", + "dataset_config_name": "jp", + "template_name": "underscore refer to", + "evaluation": { + "accuracy": 0.4848800834202294 + }, + "arguments": "Namespace(config_name=None, dataset_config_name='jp', dataset_name='Muennighoff/xwinograd', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b/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)" +} \ No newline at end of file diff --git a/evaluation_l2/xnli/tr/can_we_infer/results.json b/evaluation_l2/xnli/tr/can_we_infer/results.json new file mode 100644 index 0000000000000000000000000000000000000000..f5c381357d88868e0fd90077302961a996a9f13d --- /dev/null +++ b/evaluation_l2/xnli/tr/can_we_infer/results.json @@ -0,0 +1,9 @@ +{ + "dataset_name": "xnli", + "dataset_config_name": "tr", + "template_name": "can we infer", + "evaluation": { + "accuracy": 0.3530120481927711 + }, + "arguments": "Namespace(config_name=None, dataset_config_name='tr', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b/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='can we infer', tokenizer_name=None, use_slow_tokenizer=False)" +} \ No newline at end of file diff --git a/evaluation_l2/xnli/tr/justified_in_saying/results.json b/evaluation_l2/xnli/tr/justified_in_saying/results.json new file mode 100644 index 0000000000000000000000000000000000000000..8faf35e6c679cc9e77bccdcaafa75516938d036e --- /dev/null +++ b/evaluation_l2/xnli/tr/justified_in_saying/results.json @@ -0,0 +1,9 @@ +{ + "dataset_name": "xnli", + "dataset_config_name": "tr", + "template_name": "justified in saying", + "evaluation": { + "accuracy": 0.36265060240963853 + }, + "arguments": "Namespace(config_name=None, dataset_config_name='tr', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b/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='justified in saying', tokenizer_name=None, use_slow_tokenizer=False)" +} \ No newline at end of file diff --git a/evaluation_xnlimtht/xnli/es/can_we_infer_esmt/results.json b/evaluation_xnlimtht/xnli/es/can_we_infer_esmt/results.json new file mode 100644 index 0000000000000000000000000000000000000000..03bc6d553b733ece0040bc737c4d587a66dee990 --- /dev/null +++ b/evaluation_xnlimtht/xnli/es/can_we_infer_esmt/results.json @@ -0,0 +1,9 @@ +{ + "dataset_name": "xnli", + "dataset_config_name": "es", + "template_name": "can we infer_esmt", + "evaluation": { + "accuracy": 0.3333333333333333 + }, + "arguments": "Namespace(config_name=None, dataset_config_name='es', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='es', template_name='can we infer_esmt', tokenizer_name=None, use_slow_tokenizer=False)" +} \ No newline at end of file diff --git a/evaluation_xnlimtht/xnli/fr/GPT-3_style_frht/results.json b/evaluation_xnlimtht/xnli/fr/GPT-3_style_frht/results.json new file mode 100644 index 0000000000000000000000000000000000000000..a9e24fa2abf5012918f458eb10abb8e7c639840d --- /dev/null +++ b/evaluation_xnlimtht/xnli/fr/GPT-3_style_frht/results.json @@ -0,0 +1,9 @@ +{ + "dataset_name": "xnli", + "dataset_config_name": "fr", + "template_name": "GPT-3 style_frht", + "evaluation": { + "accuracy": 0.3405622489959839 + }, + "arguments": "Namespace(config_name=None, dataset_config_name='fr', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='fr', template_name='GPT-3 style_frht', tokenizer_name=None, use_slow_tokenizer=False)" +} \ No newline at end of file diff --git a/evaluation_xnlimtht/xnli/fr/MNLI_crowdsource_frht/results.json b/evaluation_xnlimtht/xnli/fr/MNLI_crowdsource_frht/results.json new file mode 100644 index 0000000000000000000000000000000000000000..5ec19c60ec71756e32ea23ac12d2f23d93f7b907 --- /dev/null +++ b/evaluation_xnlimtht/xnli/fr/MNLI_crowdsource_frht/results.json @@ -0,0 +1,9 @@ +{ + "dataset_name": "xnli", + "dataset_config_name": "fr", + "template_name": "MNLI crowdsource_frht", + "evaluation": { + "accuracy": 0.344578313253012 + }, + "arguments": "Namespace(config_name=None, dataset_config_name='fr', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='fr', template_name='MNLI crowdsource_frht', tokenizer_name=None, use_slow_tokenizer=False)" +} \ No newline at end of file diff --git a/evaluation_xnlimtht/xnli/fr/MNLI_crowdsource_frmt/results.json b/evaluation_xnlimtht/xnli/fr/MNLI_crowdsource_frmt/results.json new file mode 100644 index 0000000000000000000000000000000000000000..52b147ce7c1dddb223991bd3591495e84fa5fe31 --- /dev/null +++ b/evaluation_xnlimtht/xnli/fr/MNLI_crowdsource_frmt/results.json @@ -0,0 +1,9 @@ +{ + "dataset_name": "xnli", + "dataset_config_name": "fr", + "template_name": "MNLI crowdsource_frmt", + "evaluation": { + "accuracy": 0.3333333333333333 + }, + "arguments": "Namespace(config_name=None, dataset_config_name='fr', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='fr', template_name='MNLI crowdsource_frmt', tokenizer_name=None, use_slow_tokenizer=False)" +} \ No newline at end of file diff --git a/evaluation_xnlimtht/xnli/fr/can_we_infer_frht/results.json b/evaluation_xnlimtht/xnli/fr/can_we_infer_frht/results.json new file mode 100644 index 0000000000000000000000000000000000000000..4b2df10e096f09510ea1f7a81e91dc1837e48da4 --- /dev/null +++ b/evaluation_xnlimtht/xnli/fr/can_we_infer_frht/results.json @@ -0,0 +1,9 @@ +{ + "dataset_name": "xnli", + "dataset_config_name": "fr", + "template_name": "can we infer_frht", + "evaluation": { + "accuracy": 0.5188755020080321 + }, + "arguments": "Namespace(config_name=None, dataset_config_name='fr', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='fr', template_name='can we infer_frht', tokenizer_name=None, use_slow_tokenizer=False)" +} \ No newline at end of file diff --git a/evaluation_xnlimtht/xnli/fr/guaranteed_possible_impossible_frht/results.json b/evaluation_xnlimtht/xnli/fr/guaranteed_possible_impossible_frht/results.json new file mode 100644 index 0000000000000000000000000000000000000000..246169d4b5b252645db0ef81f70f0579d48e9fd5 --- /dev/null +++ b/evaluation_xnlimtht/xnli/fr/guaranteed_possible_impossible_frht/results.json @@ -0,0 +1,9 @@ +{ + "dataset_name": "xnli", + "dataset_config_name": "fr", + "template_name": "guaranteed/possible/impossible_frht", + "evaluation": { + "accuracy": 0.3457831325301205 + }, + "arguments": "Namespace(config_name=None, dataset_config_name='fr', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='fr', template_name='guaranteed/possible/impossible_frht', tokenizer_name=None, use_slow_tokenizer=False)" +} \ No newline at end of file diff --git a/evaluation_xnlimtht/xnli/fr/justified_in_saying_frht/results.json b/evaluation_xnlimtht/xnli/fr/justified_in_saying_frht/results.json new file mode 100644 index 0000000000000000000000000000000000000000..19f9fef7425a75cee10a19b40bf0060536970a62 --- /dev/null +++ b/evaluation_xnlimtht/xnli/fr/justified_in_saying_frht/results.json @@ -0,0 +1,9 @@ +{ + "dataset_name": "xnli", + "dataset_config_name": "fr", + "template_name": "justified in saying_frht", + "evaluation": { + "accuracy": 0.4843373493975904 + }, + "arguments": "Namespace(config_name=None, dataset_config_name='fr', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='fr', template_name='justified in saying_frht', tokenizer_name=None, use_slow_tokenizer=False)" +} \ No newline at end of file diff --git a/evaluation_xnlimtht/xnli/zh/can_we_infer_zhmt/results.json b/evaluation_xnlimtht/xnli/zh/can_we_infer_zhmt/results.json new file mode 100644 index 0000000000000000000000000000000000000000..d265c2de5ebb8d11a3ae9ee586b6629c3958bc5d --- /dev/null +++ b/evaluation_xnlimtht/xnli/zh/can_we_infer_zhmt/results.json @@ -0,0 +1,9 @@ +{ + "dataset_name": "xnli", + "dataset_config_name": "zh", + "template_name": "can we infer_zhmt", + "evaluation": { + "accuracy": 0.3405622489959839 + }, + "arguments": "Namespace(config_name=None, dataset_config_name='zh', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='zh', template_name='can we infer_zhmt', tokenizer_name=None, use_slow_tokenizer=False)" +} \ No newline at end of file diff --git a/evaluation_xnlimtht/xnli/zh/justified_in_saying_zhmt/results.json b/evaluation_xnlimtht/xnli/zh/justified_in_saying_zhmt/results.json new file mode 100644 index 0000000000000000000000000000000000000000..484a88115292334b309922bd41fb2f11fd449a12 --- /dev/null +++ b/evaluation_xnlimtht/xnli/zh/justified_in_saying_zhmt/results.json @@ -0,0 +1,9 @@ +{ + "dataset_name": "xnli", + "dataset_config_name": "zh", + "template_name": "justified in saying_zhmt", + "evaluation": { + "accuracy": 0.334136546184739 + }, + "arguments": "Namespace(config_name=None, dataset_config_name='zh', dataset_name='xnli', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='zh', template_name='justified in saying_zhmt', tokenizer_name=None, use_slow_tokenizer=False)" +} \ No newline at end of file diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/ar/Answer_Given_options_armt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/ar/Answer_Given_options_armt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/ar/Answer_Given_options_armt/results.json rename to evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/ar/Answer_Given_options_armt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/ar/Choose_Story_Ending_armt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/ar/Choose_Story_Ending_armt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/ar/Choose_Story_Ending_armt/results.json rename to evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/ar/Choose_Story_Ending_armt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/ar/Generate_Ending_armt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/ar/Generate_Ending_armt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/ar/Generate_Ending_armt/results.json rename to evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/ar/Generate_Ending_armt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/ar/Novel_Correct_Ending_armt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/ar/Novel_Correct_Ending_armt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/ar/Novel_Correct_Ending_armt/results.json rename to evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/ar/Novel_Correct_Ending_armt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/ar/Story_Continuation_and_Options_armt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/ar/Story_Continuation_and_Options_armt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/ar/Story_Continuation_and_Options_armt/results.json rename to evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/ar/Story_Continuation_and_Options_armt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/es/Answer_Given_options_esmt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/es/Answer_Given_options_esmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/es/Answer_Given_options_esmt/results.json rename to evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/es/Answer_Given_options_esmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/es/Choose_Story_Ending_esmt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/es/Choose_Story_Ending_esmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/es/Choose_Story_Ending_esmt/results.json rename to evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/es/Choose_Story_Ending_esmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/es/Generate_Ending_esmt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/es/Generate_Ending_esmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/es/Generate_Ending_esmt/results.json rename to evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/es/Generate_Ending_esmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/es/Novel_Correct_Ending_esmt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/es/Novel_Correct_Ending_esmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/es/Novel_Correct_Ending_esmt/results.json rename to evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/es/Novel_Correct_Ending_esmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/es/Story_Continuation_and_Options_esmt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/es/Story_Continuation_and_Options_esmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/es/Story_Continuation_and_Options_esmt/results.json rename to evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/es/Story_Continuation_and_Options_esmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/eu/Answer_Given_options_eumt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/eu/Answer_Given_options_eumt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/eu/Answer_Given_options_eumt/results.json rename to evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/eu/Answer_Given_options_eumt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/eu/Choose_Story_Ending_eumt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/eu/Choose_Story_Ending_eumt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/eu/Choose_Story_Ending_eumt/results.json rename to evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/eu/Choose_Story_Ending_eumt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/eu/Generate_Ending_eumt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/eu/Generate_Ending_eumt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/eu/Generate_Ending_eumt/results.json rename to evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/eu/Generate_Ending_eumt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/eu/Novel_Correct_Ending_eumt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/eu/Novel_Correct_Ending_eumt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/eu/Novel_Correct_Ending_eumt/results.json rename to evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/eu/Novel_Correct_Ending_eumt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/eu/Story_Continuation_and_Options_eumt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/eu/Story_Continuation_and_Options_eumt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/eu/Story_Continuation_and_Options_eumt/results.json rename to evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/eu/Story_Continuation_and_Options_eumt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/hi/Answer_Given_options_himt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/hi/Answer_Given_options_himt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/hi/Answer_Given_options_himt/results.json rename to evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/hi/Answer_Given_options_himt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/hi/Choose_Story_Ending_himt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/hi/Choose_Story_Ending_himt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/hi/Choose_Story_Ending_himt/results.json rename to evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/hi/Choose_Story_Ending_himt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/hi/Generate_Ending_himt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/hi/Generate_Ending_himt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/hi/Generate_Ending_himt/results.json rename to evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/hi/Generate_Ending_himt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/hi/Novel_Correct_Ending_himt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/hi/Novel_Correct_Ending_himt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/hi/Novel_Correct_Ending_himt/results.json rename to evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/hi/Novel_Correct_Ending_himt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/hi/Story_Continuation_and_Options_himt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/hi/Story_Continuation_and_Options_himt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/hi/Story_Continuation_and_Options_himt/results.json rename to evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/hi/Story_Continuation_and_Options_himt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/id/Answer_Given_options_idmt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/id/Answer_Given_options_idmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/id/Answer_Given_options_idmt/results.json rename to evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/id/Answer_Given_options_idmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/id/Choose_Story_Ending_idmt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/id/Choose_Story_Ending_idmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/id/Choose_Story_Ending_idmt/results.json rename to evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/id/Choose_Story_Ending_idmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/id/Generate_Ending_idmt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/id/Generate_Ending_idmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/id/Generate_Ending_idmt/results.json rename to evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/id/Generate_Ending_idmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/id/Novel_Correct_Ending_idmt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/id/Novel_Correct_Ending_idmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/id/Novel_Correct_Ending_idmt/results.json rename to evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/id/Novel_Correct_Ending_idmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/id/Story_Continuation_and_Options_idmt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/id/Story_Continuation_and_Options_idmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/id/Story_Continuation_and_Options_idmt/results.json rename to evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/id/Story_Continuation_and_Options_idmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/zh/Answer_Given_options_zhmt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/zh/Answer_Given_options_zhmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/zh/Answer_Given_options_zhmt/results.json rename to evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/zh/Answer_Given_options_zhmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/zh/Choose_Story_Ending_zhmt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/zh/Choose_Story_Ending_zhmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/zh/Choose_Story_Ending_zhmt/results.json rename to evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/zh/Choose_Story_Ending_zhmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/zh/Generate_Ending_zhmt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/zh/Generate_Ending_zhmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/zh/Generate_Ending_zhmt/results.json rename to evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/zh/Generate_Ending_zhmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/zh/Novel_Correct_Ending_zhmt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/zh/Novel_Correct_Ending_zhmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/zh/Novel_Correct_Ending_zhmt/results.json rename to evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/zh/Novel_Correct_Ending_zhmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/zh/Story_Continuation_and_Options_zhmt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/zh/Story_Continuation_and_Options_zhmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xstory_cloze/zh/Story_Continuation_and_Options_zhmt/results.json rename to evaluation_xwinostorycopamt/Muennighoff_xstory_cloze/zh/Story_Continuation_and_Options_zhmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xwinograd/fr/Replace_frmt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xwinograd/fr/Replace_frmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xwinograd/fr/Replace_frmt/results.json rename to evaluation_xwinostorycopamt/Muennighoff_xwinograd/fr/Replace_frmt/results.json diff --git a/evaluation_xwinostorycopamt/Muennighoff_xwinograd/fr/True_or_False_frmt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xwinograd/fr/True_or_False_frmt/results.json new file mode 100644 index 0000000000000000000000000000000000000000..13bce784c795fd08c0ecb687dd654dd9d8a91347 --- /dev/null +++ b/evaluation_xwinostorycopamt/Muennighoff_xwinograd/fr/True_or_False_frmt/results.json @@ -0,0 +1,9 @@ +{ + "dataset_name": "Muennighoff/xwinograd", + "dataset_config_name": "fr", + "template_name": "True or False_frmt", + "evaluation": { + "accuracy": 0.4819277108433735 + }, + "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/2b5t0/bloomz-3b', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='test', target_max_length=256, template_config_name='fr', template_name='True or False_frmt', tokenizer_name=None, use_slow_tokenizer=False)" +} \ No newline at end of file diff --git a/evaluation_xwinostorycopamt/Muennighoff_xwinograd/fr/does_underscore_refer_to_frmt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xwinograd/fr/does_underscore_refer_to_frmt/results.json new file mode 100644 index 0000000000000000000000000000000000000000..17b392ab6093d19889e43cc0c324cc8bac39d3a1 --- /dev/null +++ b/evaluation_xwinostorycopamt/Muennighoff_xwinograd/fr/does_underscore_refer_to_frmt/results.json @@ -0,0 +1,9 @@ +{ + "dataset_name": "Muennighoff/xwinograd", + "dataset_config_name": "fr", + "template_name": "does underscore refer to_frmt", + "evaluation": { + "accuracy": 0.5060240963855421 + }, + "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/2b5t0/bloomz-3b', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='test', target_max_length=256, template_config_name='fr', template_name='does underscore refer to_frmt', tokenizer_name=None, use_slow_tokenizer=False)" +} \ No newline at end of file diff --git a/evaluation_xcopawinostorymt/Muennighoff_xwinograd/fr/stand_for_frmt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xwinograd/fr/stand_for_frmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xwinograd/fr/stand_for_frmt/results.json rename to evaluation_xwinostorycopamt/Muennighoff_xwinograd/fr/stand_for_frmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xwinograd/fr/underscore_refer_to_frmt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xwinograd/fr/underscore_refer_to_frmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xwinograd/fr/underscore_refer_to_frmt/results.json rename to evaluation_xwinostorycopamt/Muennighoff_xwinograd/fr/underscore_refer_to_frmt/results.json diff --git a/evaluation_xwinostorycopamt/Muennighoff_xwinograd/pt/Replace_ptmt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xwinograd/pt/Replace_ptmt/results.json new file mode 100644 index 0000000000000000000000000000000000000000..935941d1883764fd70eea04f87279378c3e7354b --- /dev/null +++ b/evaluation_xwinostorycopamt/Muennighoff_xwinograd/pt/Replace_ptmt/results.json @@ -0,0 +1,9 @@ +{ + "dataset_name": "Muennighoff/xwinograd", + "dataset_config_name": "pt", + "template_name": "Replace_ptmt", + "evaluation": { + "accuracy": 0.5247148288973384 + }, + "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/2b5t0/bloomz-3b', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='test', target_max_length=256, template_config_name='pt', template_name='Replace_ptmt', tokenizer_name=None, use_slow_tokenizer=False)" +} \ No newline at end of file diff --git a/evaluation_xwinostorycopamt/Muennighoff_xwinograd/pt/True_or_False_ptmt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xwinograd/pt/True_or_False_ptmt/results.json new file mode 100644 index 0000000000000000000000000000000000000000..b205b8334f9b6102bccaacea377e8c7051172fde --- /dev/null +++ b/evaluation_xwinostorycopamt/Muennighoff_xwinograd/pt/True_or_False_ptmt/results.json @@ -0,0 +1,9 @@ +{ + "dataset_name": "Muennighoff/xwinograd", + "dataset_config_name": "pt", + "template_name": "True or False_ptmt", + "evaluation": { + "accuracy": 0.44866920152091255 + }, + "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/2b5t0/bloomz-3b', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='test', target_max_length=256, template_config_name='pt', template_name='True or False_ptmt', tokenizer_name=None, use_slow_tokenizer=False)" +} \ No newline at end of file diff --git a/evaluation_xwinostorycopamt/Muennighoff_xwinograd/pt/does_underscore_refer_to_ptmt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xwinograd/pt/does_underscore_refer_to_ptmt/results.json new file mode 100644 index 0000000000000000000000000000000000000000..b72ae129c44693d0b79945f4eca525e8e89bdecf --- /dev/null +++ b/evaluation_xwinostorycopamt/Muennighoff_xwinograd/pt/does_underscore_refer_to_ptmt/results.json @@ -0,0 +1,9 @@ +{ + "dataset_name": "Muennighoff/xwinograd", + "dataset_config_name": "pt", + "template_name": "does underscore refer to_ptmt", + "evaluation": { + "accuracy": 0.5019011406844106 + }, + "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/2b5t0/bloomz-3b', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='test', target_max_length=256, template_config_name='pt', template_name='does underscore refer to_ptmt', tokenizer_name=None, use_slow_tokenizer=False)" +} \ No newline at end of file diff --git a/evaluation_xwinostorycopamt/Muennighoff_xwinograd/pt/stand_for_ptmt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xwinograd/pt/stand_for_ptmt/results.json new file mode 100644 index 0000000000000000000000000000000000000000..fc7081e46e2781a7350cec9776e8d15448525c9b --- /dev/null +++ b/evaluation_xwinostorycopamt/Muennighoff_xwinograd/pt/stand_for_ptmt/results.json @@ -0,0 +1,9 @@ +{ + "dataset_name": "Muennighoff/xwinograd", + "dataset_config_name": "pt", + "template_name": "stand for_ptmt", + "evaluation": { + "accuracy": 0.5095057034220533 + }, + "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/2b5t0/bloomz-3b', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='test', target_max_length=256, template_config_name='pt', template_name='stand for_ptmt', tokenizer_name=None, use_slow_tokenizer=False)" +} \ No newline at end of file diff --git a/evaluation_xwinostorycopamt/Muennighoff_xwinograd/pt/underscore_refer_to_ptmt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xwinograd/pt/underscore_refer_to_ptmt/results.json new file mode 100644 index 0000000000000000000000000000000000000000..99e8523ca945bf00677e8ee1e5f943c8d83387d2 --- /dev/null +++ b/evaluation_xwinostorycopamt/Muennighoff_xwinograd/pt/underscore_refer_to_ptmt/results.json @@ -0,0 +1,9 @@ +{ + "dataset_name": "Muennighoff/xwinograd", + "dataset_config_name": "pt", + "template_name": "underscore refer to_ptmt", + "evaluation": { + "accuracy": 0.4866920152091255 + }, + "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/2b5t0/bloomz-3b', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='test', target_max_length=256, template_config_name='pt', template_name='underscore refer to_ptmt', tokenizer_name=None, use_slow_tokenizer=False)" +} \ No newline at end of file diff --git a/evaluation_xcopawinostorymt/Muennighoff_xwinograd/zh/Replace_zhmt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xwinograd/zh/Replace_zhmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xwinograd/zh/Replace_zhmt/results.json rename to evaluation_xwinostorycopamt/Muennighoff_xwinograd/zh/Replace_zhmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xwinograd/zh/True_or_False_zhmt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xwinograd/zh/True_or_False_zhmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xwinograd/zh/True_or_False_zhmt/results.json rename to evaluation_xwinostorycopamt/Muennighoff_xwinograd/zh/True_or_False_zhmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xwinograd/zh/does_underscore_refer_to_zhmt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xwinograd/zh/does_underscore_refer_to_zhmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xwinograd/zh/does_underscore_refer_to_zhmt/results.json rename to evaluation_xwinostorycopamt/Muennighoff_xwinograd/zh/does_underscore_refer_to_zhmt/results.json diff --git a/evaluation_xcopawinostorymt/Muennighoff_xwinograd/zh/stand_for_zhmt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xwinograd/zh/stand_for_zhmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/Muennighoff_xwinograd/zh/stand_for_zhmt/results.json rename to evaluation_xwinostorycopamt/Muennighoff_xwinograd/zh/stand_for_zhmt/results.json diff --git a/evaluation_xwinostorycopamt/Muennighoff_xwinograd/zh/underscore_refer_to_zhmt/results.json b/evaluation_xwinostorycopamt/Muennighoff_xwinograd/zh/underscore_refer_to_zhmt/results.json new file mode 100644 index 0000000000000000000000000000000000000000..bbed06dc143ab80eb99d380c9bcf2b9c6317fa09 --- /dev/null +++ b/evaluation_xwinostorycopamt/Muennighoff_xwinograd/zh/underscore_refer_to_zhmt/results.json @@ -0,0 +1,9 @@ +{ + "dataset_name": "Muennighoff/xwinograd", + "dataset_config_name": "zh", + "template_name": "underscore refer to_zhmt", + "evaluation": { + "accuracy": 0.5297619047619048 + }, + "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/2b5t0/bloomz-3b', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/2b5t0/bloomz-3b/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='test', target_max_length=256, template_config_name='zh', template_name='underscore refer to_zhmt', tokenizer_name=None, use_slow_tokenizer=False)" +} \ No newline at end of file diff --git a/evaluation_xcopawinostorymt/xcopa/id/C1_or_C2?_premise_idmt/results.json b/evaluation_xwinostorycopamt/xcopa/id/C1_or_C2?_premise_idmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/id/C1_or_C2?_premise_idmt/results.json rename to evaluation_xwinostorycopamt/xcopa/id/C1_or_C2?_premise_idmt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/id/best_option_idmt/results.json b/evaluation_xwinostorycopamt/xcopa/id/best_option_idmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/id/best_option_idmt/results.json rename to evaluation_xwinostorycopamt/xcopa/id/best_option_idmt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/id/cause_effect_idmt/results.json b/evaluation_xwinostorycopamt/xcopa/id/cause_effect_idmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/id/cause_effect_idmt/results.json rename to evaluation_xwinostorycopamt/xcopa/id/cause_effect_idmt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/id/i_am_hesitating_idmt/results.json b/evaluation_xwinostorycopamt/xcopa/id/i_am_hesitating_idmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/id/i_am_hesitating_idmt/results.json rename to evaluation_xwinostorycopamt/xcopa/id/i_am_hesitating_idmt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/id/plausible_alternatives_idmt/results.json b/evaluation_xwinostorycopamt/xcopa/id/plausible_alternatives_idmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/id/plausible_alternatives_idmt/results.json rename to evaluation_xwinostorycopamt/xcopa/id/plausible_alternatives_idmt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/sw/C1_or_C2?_premise_swmt/results.json b/evaluation_xwinostorycopamt/xcopa/sw/C1_or_C2?_premise_swmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/sw/C1_or_C2?_premise_swmt/results.json rename to evaluation_xwinostorycopamt/xcopa/sw/C1_or_C2?_premise_swmt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/sw/best_option_swmt/results.json b/evaluation_xwinostorycopamt/xcopa/sw/best_option_swmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/sw/best_option_swmt/results.json rename to evaluation_xwinostorycopamt/xcopa/sw/best_option_swmt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/sw/cause_effect_swmt/results.json b/evaluation_xwinostorycopamt/xcopa/sw/cause_effect_swmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/sw/cause_effect_swmt/results.json rename to evaluation_xwinostorycopamt/xcopa/sw/cause_effect_swmt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/sw/i_am_hesitating_swmt/results.json b/evaluation_xwinostorycopamt/xcopa/sw/i_am_hesitating_swmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/sw/i_am_hesitating_swmt/results.json rename to evaluation_xwinostorycopamt/xcopa/sw/i_am_hesitating_swmt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/sw/plausible_alternatives_swmt/results.json b/evaluation_xwinostorycopamt/xcopa/sw/plausible_alternatives_swmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/sw/plausible_alternatives_swmt/results.json rename to evaluation_xwinostorycopamt/xcopa/sw/plausible_alternatives_swmt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/ta/C1_or_C2?_premise_tamt/results.json b/evaluation_xwinostorycopamt/xcopa/ta/C1_or_C2?_premise_tamt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/ta/C1_or_C2?_premise_tamt/results.json rename to evaluation_xwinostorycopamt/xcopa/ta/C1_or_C2?_premise_tamt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/ta/best_option_tamt/results.json b/evaluation_xwinostorycopamt/xcopa/ta/best_option_tamt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/ta/best_option_tamt/results.json rename to evaluation_xwinostorycopamt/xcopa/ta/best_option_tamt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/ta/cause_effect_tamt/results.json b/evaluation_xwinostorycopamt/xcopa/ta/cause_effect_tamt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/ta/cause_effect_tamt/results.json rename to evaluation_xwinostorycopamt/xcopa/ta/cause_effect_tamt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/ta/i_am_hesitating_tamt/results.json b/evaluation_xwinostorycopamt/xcopa/ta/i_am_hesitating_tamt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/ta/i_am_hesitating_tamt/results.json rename to evaluation_xwinostorycopamt/xcopa/ta/i_am_hesitating_tamt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/ta/plausible_alternatives_tamt/results.json b/evaluation_xwinostorycopamt/xcopa/ta/plausible_alternatives_tamt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/ta/plausible_alternatives_tamt/results.json rename to evaluation_xwinostorycopamt/xcopa/ta/plausible_alternatives_tamt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/vi/C1_or_C2?_premise_vimt/results.json b/evaluation_xwinostorycopamt/xcopa/vi/C1_or_C2?_premise_vimt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/vi/C1_or_C2?_premise_vimt/results.json rename to evaluation_xwinostorycopamt/xcopa/vi/C1_or_C2?_premise_vimt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/vi/best_option_vimt/results.json b/evaluation_xwinostorycopamt/xcopa/vi/best_option_vimt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/vi/best_option_vimt/results.json rename to evaluation_xwinostorycopamt/xcopa/vi/best_option_vimt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/vi/cause_effect_vimt/results.json b/evaluation_xwinostorycopamt/xcopa/vi/cause_effect_vimt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/vi/cause_effect_vimt/results.json rename to evaluation_xwinostorycopamt/xcopa/vi/cause_effect_vimt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/vi/i_am_hesitating_vimt/results.json b/evaluation_xwinostorycopamt/xcopa/vi/i_am_hesitating_vimt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/vi/i_am_hesitating_vimt/results.json rename to evaluation_xwinostorycopamt/xcopa/vi/i_am_hesitating_vimt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/vi/plausible_alternatives_vimt/results.json b/evaluation_xwinostorycopamt/xcopa/vi/plausible_alternatives_vimt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/vi/plausible_alternatives_vimt/results.json rename to evaluation_xwinostorycopamt/xcopa/vi/plausible_alternatives_vimt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/zh/C1_or_C2?_premise_zhmt/results.json b/evaluation_xwinostorycopamt/xcopa/zh/C1_or_C2?_premise_zhmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/zh/C1_or_C2?_premise_zhmt/results.json rename to evaluation_xwinostorycopamt/xcopa/zh/C1_or_C2?_premise_zhmt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/zh/best_option_zhmt/results.json b/evaluation_xwinostorycopamt/xcopa/zh/best_option_zhmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/zh/best_option_zhmt/results.json rename to evaluation_xwinostorycopamt/xcopa/zh/best_option_zhmt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/zh/cause_effect_zhmt/results.json b/evaluation_xwinostorycopamt/xcopa/zh/cause_effect_zhmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/zh/cause_effect_zhmt/results.json rename to evaluation_xwinostorycopamt/xcopa/zh/cause_effect_zhmt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/zh/i_am_hesitating_zhmt/results.json b/evaluation_xwinostorycopamt/xcopa/zh/i_am_hesitating_zhmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/zh/i_am_hesitating_zhmt/results.json rename to evaluation_xwinostorycopamt/xcopa/zh/i_am_hesitating_zhmt/results.json diff --git a/evaluation_xcopawinostorymt/xcopa/zh/plausible_alternatives_zhmt/results.json b/evaluation_xwinostorycopamt/xcopa/zh/plausible_alternatives_zhmt/results.json similarity index 100% rename from evaluation_xcopawinostorymt/xcopa/zh/plausible_alternatives_zhmt/results.json rename to evaluation_xwinostorycopamt/xcopa/zh/plausible_alternatives_zhmt/results.json