Remove eval folder (Moved to bigscience/evaluation-results)

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xstory_cloze/ar/Answer_Given_options/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xstory_cloze",
-  "dataset_config_name": "ar",
-  "template_name": "Answer Given options",
-  "evaluation": {
-    "accuracy": 0.47650562541363334
-  },
-  "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/760mt0/bloomz-1b1', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xstory_cloze/ar/Choose_Story_Ending/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xstory_cloze",
-  "dataset_config_name": "ar",
-  "template_name": "Choose Story Ending",
-  "evaluation": {
-    "accuracy": 0.5208471211118465
-  },
-  "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/760mt0/bloomz-1b1', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xstory_cloze/ar/Generate_Ending/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xstory_cloze",
-  "dataset_config_name": "ar",
-  "template_name": "Generate Ending",
-  "evaluation": {
-    "accuracy": 0.5354070152217075
-  },
-  "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/760mt0/bloomz-1b1', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xstory_cloze/ar/Novel_Correct_Ending/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xstory_cloze",
-  "dataset_config_name": "ar",
-  "template_name": "Novel Correct Ending",
-  "evaluation": {
-    "accuracy": 0.5062872270019855
-  },
-  "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/760mt0/bloomz-1b1', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xstory_cloze/ar/Story_Continuation_and_Options/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xstory_cloze",
-  "dataset_config_name": "ar",
-  "template_name": "Story Continuation and Options",
-  "evaluation": {
-    "accuracy": 0.5228325612177366
-  },
-  "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/760mt0/bloomz-1b1', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xstory_cloze/es/Answer_Given_options/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xstory_cloze",
-  "dataset_config_name": "es",
-  "template_name": "Answer Given options",
-  "evaluation": {
-    "accuracy": 0.514228987425546
-  },
-  "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/760mt0/bloomz-1b1', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xstory_cloze/es/Choose_Story_Ending/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xstory_cloze",
-  "dataset_config_name": "es",
-  "template_name": "Choose Story Ending",
-  "evaluation": {
-    "accuracy": 0.5724685638649901
-  },
-  "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/760mt0/bloomz-1b1', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xstory_cloze/es/Generate_Ending/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xstory_cloze",
-  "dataset_config_name": "es",
-  "template_name": "Generate Ending",
-  "evaluation": {
-    "accuracy": 0.5804103242885507
-  },
-  "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/760mt0/bloomz-1b1', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xstory_cloze/es/Novel_Correct_Ending/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xstory_cloze",
-  "dataset_config_name": "es",
-  "template_name": "Novel Correct Ending",
-  "evaluation": {
-    "accuracy": 0.5539377895433488
-  },
-  "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/760mt0/bloomz-1b1', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xstory_cloze/es/Story_Continuation_and_Options/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xstory_cloze",
-  "dataset_config_name": "es",
-  "template_name": "Story Continuation and Options",
-  "evaluation": {
-    "accuracy": 0.5598941098610192
-  },
-  "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/760mt0/bloomz-1b1', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xstory_cloze/eu/Answer_Given_options/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xstory_cloze",
-  "dataset_config_name": "eu",
-  "template_name": "Answer Given options",
-  "evaluation": {
-    "accuracy": 0.44209133024487096
-  },
-  "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/760mt0/bloomz-1b1', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xstory_cloze/eu/Choose_Story_Ending/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xstory_cloze",
-  "dataset_config_name": "eu",
-  "template_name": "Choose Story Ending",
-  "evaluation": {
-    "accuracy": 0.47782925215089345
-  },
-  "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/760mt0/bloomz-1b1', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xstory_cloze/eu/Generate_Ending/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xstory_cloze",
-  "dataset_config_name": "eu",
-  "template_name": "Generate Ending",
-  "evaluation": {
-    "accuracy": 0.5221707478491066
-  },
-  "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/760mt0/bloomz-1b1', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xstory_cloze/eu/Novel_Correct_Ending/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xstory_cloze",
-  "dataset_config_name": "eu",
-  "template_name": "Novel Correct Ending",
-  "evaluation": {
-    "accuracy": 0.4632693580410324
-  },
-  "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/760mt0/bloomz-1b1', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xstory_cloze/eu/Story_Continuation_and_Options/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xstory_cloze",
-  "dataset_config_name": "eu",
-  "template_name": "Story Continuation and Options",
-  "evaluation": {
-    "accuracy": 0.4672402382528127
-  },
-  "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/760mt0/bloomz-1b1', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xstory_cloze/hi/Answer_Given_options/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xstory_cloze",
-  "dataset_config_name": "hi",
-  "template_name": "Answer Given options",
-  "evaluation": {
-    "accuracy": 0.49702183984116477
-  },
-  "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/760mt0/bloomz-1b1', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xstory_cloze/hi/Choose_Story_Ending/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xstory_cloze",
-  "dataset_config_name": "hi",
-  "template_name": "Choose Story Ending",
-  "evaluation": {
-    "accuracy": 0.5274652547981469
-  },
-  "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/760mt0/bloomz-1b1', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xstory_cloze/hi/Generate_Ending/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xstory_cloze",
-  "dataset_config_name": "hi",
-  "template_name": "Generate Ending",
-  "evaluation": {
-    "accuracy": 0.5519523494374586
-  },
-  "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/760mt0/bloomz-1b1', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xstory_cloze/hi/Novel_Correct_Ending/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xstory_cloze",
-  "dataset_config_name": "hi",
-  "template_name": "Novel Correct Ending",
-  "evaluation": {
-    "accuracy": 0.5016545334215751
-  },
-  "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/760mt0/bloomz-1b1', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xstory_cloze/hi/Story_Continuation_and_Options/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xstory_cloze",
-  "dataset_config_name": "hi",
-  "template_name": "Story Continuation and Options",
-  "evaluation": {
-    "accuracy": 0.5181998676373263
-  },
-  "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/760mt0/bloomz-1b1', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xstory_cloze/id/Answer_Given_options/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xstory_cloze",
-  "dataset_config_name": "id",
-  "template_name": "Answer Given options",
-  "evaluation": {
-    "accuracy": 0.4990072799470549
-  },
-  "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/760mt0/bloomz-1b1', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xstory_cloze/id/Choose_Story_Ending/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xstory_cloze",
-  "dataset_config_name": "id",
-  "template_name": "Choose Story Ending",
-  "evaluation": {
-    "accuracy": 0.5645268034414295
-  },
-  "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/760mt0/bloomz-1b1', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xstory_cloze/id/Generate_Ending/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xstory_cloze",
-  "dataset_config_name": "id",
-  "template_name": "Generate Ending",
-  "evaluation": {
-    "accuracy": 0.5797485109199206
-  },
-  "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/760mt0/bloomz-1b1', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xstory_cloze/id/Novel_Correct_Ending/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xstory_cloze",
-  "dataset_config_name": "id",
-  "template_name": "Novel Correct Ending",
-  "evaluation": {
-    "accuracy": 0.513567174056916
-  },
-  "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/760mt0/bloomz-1b1', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xstory_cloze/id/Story_Continuation_and_Options/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xstory_cloze",
-  "dataset_config_name": "id",
-  "template_name": "Story Continuation and Options",
-  "evaluation": {
-    "accuracy": 0.5579086697551291
-  },
-  "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/760mt0/bloomz-1b1', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xstory_cloze/zh/Answer_Given_options/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xstory_cloze",
-  "dataset_config_name": "zh",
-  "template_name": "Answer Given options",
-  "evaluation": {
-    "accuracy": 0.5367306419589676
-  },
-  "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/760mt0/bloomz-1b1', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xstory_cloze/zh/Choose_Story_Ending/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xstory_cloze",
-  "dataset_config_name": "zh",
-  "template_name": "Choose Story Ending",
-  "evaluation": {
-    "accuracy": 0.5817339510258107
-  },
-  "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/760mt0/bloomz-1b1', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xstory_cloze/zh/Generate_Ending/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xstory_cloze",
-  "dataset_config_name": "zh",
-  "template_name": "Generate Ending",
-  "evaluation": {
-    "accuracy": 0.5671740569159497
-  },
-  "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/760mt0/bloomz-1b1', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xstory_cloze/zh/Novel_Correct_Ending/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xstory_cloze",
-  "dataset_config_name": "zh",
-  "template_name": "Novel Correct Ending",
-  "evaluation": {
-    "accuracy": 0.57180675049636
-  },
-  "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/760mt0/bloomz-1b1', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xstory_cloze/zh/Story_Continuation_and_Options/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xstory_cloze",
-  "dataset_config_name": "zh",
-  "template_name": "Story Continuation and Options",
-  "evaluation": {
-    "accuracy": 0.5731303772336201
-  },
-  "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/760mt0/bloomz-1b1', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xwinograd/en/Replace/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xwinograd",
-  "dataset_config_name": "en",
-  "template_name": "Replace",
-  "evaluation": {
-    "accuracy": 0.5040860215053763
-  },
-  "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/760mt0/bloomz-1b1', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xwinograd/en/True_or_False/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xwinograd",
-  "dataset_config_name": "en",
-  "template_name": "True or False",
-  "evaluation": {
-    "accuracy": 0.5049462365591398
-  },
-  "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/760mt0/bloomz-1b1', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xwinograd/en/does_underscore_refer_to/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xwinograd",
-  "dataset_config_name": "en",
-  "template_name": "does underscore refer to",
-  "evaluation": {
-    "accuracy": 0.4997849462365591
-  },
-  "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/760mt0/bloomz-1b1', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xwinograd/en/stand_for/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xwinograd",
-  "dataset_config_name": "en",
-  "template_name": "stand for",
-  "evaluation": {
-    "accuracy": 0.5006451612903225
-  },
-  "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/760mt0/bloomz-1b1', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xwinograd/en/underscore_refer_to/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xwinograd",
-  "dataset_config_name": "en",
-  "template_name": "underscore refer to",
-  "evaluation": {
-    "accuracy": 0.501505376344086
-  },
-  "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/760mt0/bloomz-1b1', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xwinograd/fr/Replace/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xwinograd",
-  "dataset_config_name": "fr",
-  "template_name": "Replace",
-  "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/760mt0/bloomz-1b1', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xwinograd/fr/True_or_False/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xwinograd",
-  "dataset_config_name": "fr",
-  "template_name": "True or False",
-  "evaluation": {
-    "accuracy": 0.5662650602409639
-  },
-  "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/760mt0/bloomz-1b1', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xwinograd/fr/does_underscore_refer_to/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xwinograd",
-  "dataset_config_name": "fr",
-  "template_name": "does underscore refer to",
-  "evaluation": {
-    "accuracy": 0.5421686746987951
-  },
-  "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/760mt0/bloomz-1b1', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xwinograd/fr/stand_for/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xwinograd",
-  "dataset_config_name": "fr",
-  "template_name": "stand for",
-  "evaluation": {
-    "accuracy": 0.5180722891566265
-  },
-  "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/760mt0/bloomz-1b1', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xwinograd/fr/underscore_refer_to/results.json

@@ -1,9 +0,0 @@
-{
-  "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/760mt0/bloomz-1b1', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xwinograd/pt/Replace/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xwinograd",
-  "dataset_config_name": "pt",
-  "template_name": "Replace",
-  "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/760mt0/bloomz-1b1', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xwinograd/pt/True_or_False/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xwinograd",
-  "dataset_config_name": "pt",
-  "template_name": "True or False",
-  "evaluation": {
-    "accuracy": 0.4790874524714829
-  },
-  "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/760mt0/bloomz-1b1', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xwinograd/pt/does_underscore_refer_to/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xwinograd",
-  "dataset_config_name": "pt",
-  "template_name": "does underscore refer to",
-  "evaluation": {
-    "accuracy": 0.49049429657794674
-  },
-  "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/760mt0/bloomz-1b1', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xwinograd/pt/stand_for/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xwinograd",
-  "dataset_config_name": "pt",
-  "template_name": "stand for",
-  "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/760mt0/bloomz-1b1', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xwinograd/pt/underscore_refer_to/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xwinograd",
-  "dataset_config_name": "pt",
-  "template_name": "underscore refer to",
-  "evaluation": {
-    "accuracy": 0.5133079847908745
-  },
-  "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/760mt0/bloomz-1b1', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xwinograd/zh/Replace/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xwinograd",
-  "dataset_config_name": "zh",
-  "template_name": "Replace",
-  "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/760mt0/bloomz-1b1', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xwinograd/zh/True_or_False/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xwinograd",
-  "dataset_config_name": "zh",
-  "template_name": "True or False",
-  "evaluation": {
-    "accuracy": 0.5138888888888888
-  },
-  "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/760mt0/bloomz-1b1', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xwinograd/zh/does_underscore_refer_to/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xwinograd",
-  "dataset_config_name": "zh",
-  "template_name": "does underscore refer to",
-  "evaluation": {
-    "accuracy": 0.5396825396825397
-  },
-  "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/760mt0/bloomz-1b1', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xwinograd/zh/stand_for/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xwinograd",
-  "dataset_config_name": "zh",
-  "template_name": "stand for",
-  "evaluation": {
-    "accuracy": 0.49404761904761907
-  },
-  "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/760mt0/bloomz-1b1', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}

evaluation_bloomz-1b1/evaluation_l1/Muennighoff_xwinograd/zh/underscore_refer_to/results.json

@@ -1,9 +0,0 @@
-{
-  "dataset_name": "Muennighoff/xwinograd",
-  "dataset_config_name": "zh",
-  "template_name": "underscore refer to",
-  "evaluation": {
-    "accuracy": 0.5436507936507936
-  },
-  "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/760mt0/bloomz-1b1', nospace=False, output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/760mt0/bloomz-1b1/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)"
-}