HelgeKn commited on
Commit
84394af
1 Parent(s): 42f4e53

Add SetFit model

Browse files
1_Pooling/config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false
7
+ }
README.md ADDED
@@ -0,0 +1,219 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: setfit
3
+ tags:
4
+ - setfit
5
+ - sentence-transformers
6
+ - text-classification
7
+ - generated_from_setfit_trainer
8
+ metrics:
9
+ - accuracy
10
+ widget:
11
+ - text: 'The Alavas worked themselves to the bone in the last period , and English
12
+ and San Emeterio ( 65-75 ) had already made it clear that they were not going
13
+ to let anyone take away what they had earned during the first thirty minutes . '
14
+ - text: 'To break the uncomfortable silence , Haney began to talk . '
15
+ - text: 'For the treatment of non-small cell lung cancer , the effects of Alimta were
16
+ compared with those of docetaxel ( another anticancer medicine ) in one study
17
+ involving 571 patients with locally advanced or metastatic disease who had received
18
+ chemotherapy in the past . '
19
+ - text: 'As we all know , a few minutes before the end of the game ( that their team
20
+ had already won ) , both players deliberately wasted time which made the referee
21
+ show the second yellow card to both of them . '
22
+ - text: 'In contrast , patients whose cancer was affecting squamous cells had shorter
23
+ survival times if they received Alimta . '
24
+ pipeline_tag: text-classification
25
+ inference: true
26
+ base_model: sentence-transformers/paraphrase-mpnet-base-v2
27
+ model-index:
28
+ - name: SetFit with sentence-transformers/paraphrase-mpnet-base-v2
29
+ results:
30
+ - task:
31
+ type: text-classification
32
+ name: Text Classification
33
+ dataset:
34
+ name: Unknown
35
+ type: unknown
36
+ split: test
37
+ metrics:
38
+ - type: accuracy
39
+ value: 0.17086092715231788
40
+ name: Accuracy
41
+ ---
42
+
43
+ # SetFit with sentence-transformers/paraphrase-mpnet-base-v2
44
+
45
+ This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2) as the Sentence Transformer embedding model. A [SetFitHead](huggingface.co/docs/setfit/reference/main#setfit.SetFitHead) instance is used for classification.
46
+
47
+ The model has been trained using an efficient few-shot learning technique that involves:
48
+
49
+ 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
50
+ 2. Training a classification head with features from the fine-tuned Sentence Transformer.
51
+
52
+ ## Model Details
53
+
54
+ ### Model Description
55
+ - **Model Type:** SetFit
56
+ - **Sentence Transformer body:** [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2)
57
+ - **Classification head:** a [SetFitHead](huggingface.co/docs/setfit/reference/main#setfit.SetFitHead) instance
58
+ - **Maximum Sequence Length:** 512 tokens
59
+ - **Number of Classes:** 7 classes
60
+ <!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
61
+ <!-- - **Language:** Unknown -->
62
+ <!-- - **License:** Unknown -->
63
+
64
+ ### Model Sources
65
+
66
+ - **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
67
+ - **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
68
+ - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
69
+
70
+ ### Model Labels
71
+ | Label | Examples |
72
+ |:------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
73
+ | 3 | <ul><li>'Saves the log with all results into an HTML file to be able to print or publish . '</li><li>'Alimta is used together with cisplatin ( another anticancer medicine ) when the cancer is unresectable ( cannot be removed by surgery alone ) and malignant ( has spread , or is likely to spread easily , to other parts of the body ) , in patients who have not received chemotherapy ( medicines for cancer ) before advanced or metastatic non-small cell lung cancer that is not affecting the squamous cells . '</li><li>"It was the most exercise we 'd had all morning and it was followed by our driving immediately to the nearest watering hole . "</li></ul> |
74
+ | 6 | <ul><li>'3 -RRB- Republican congressional representatives , because of their belief in a minimalist state , are less willing to engage in local benefit-seeking than are Democratic members of Congress . '</li><li>'Here , the experience of New York City is decisive . '</li><li>'The idea would be to administer to patients the growth-controlling proteins made by healthy versions of the damaged genes . '</li></ul> |
75
+ | 2 | <ul><li>'-- Students should move up the educational ladder as their academic potential allows . '</li><li>'The next day , Sunday , the hangover reminded Haney where he had been the night before . '</li><li>'It explains how the Committee for Medicinal Products for Veterinary Use ( CVMP ) assessed the studies performed , to reach their recommendations on how to use the medicine . '</li></ul> |
76
+ | 0 | <ul><li>'A minor contrast to Costa Rica , comparing the 22 players called by both countries for the friendly game today , at 3:05 pm at the National Stadium in San Jose . '</li><li>'Never in my life have I been so frightened . '</li><li>'Prior to 1932 , the pattern was nearly the opposite . '</li></ul> |
77
+ | 5 | <ul><li>'2 -RRB- Congressional representatives have two basic responsibilities while voting in office -- dealing with national issues -LRB- programmatic actions such as casting roll call votes on legislation that imposes costs and/or confers benefits on the population at large -RRB- and attending to local issues -LRB- constituency service and pork barrel -RRB- . '</li><li>'The scientists say that since breast cancer often strikes multiple members of certain families , the gene , when inherited in a damaged form , may predispose women to the cancer . '</li><li>"On the Right , the tone was set by Jacques Chirac , who declared in 1976 that `` 900,000 unemployed would not become a problem in a country with 2 million of foreign workers , '' and on the Left by Michel Rocard explaining in 1990 that France `` can not accommodate all the world 's misery . '' "</li></ul> |
78
+ | 4 | <ul><li>'Researchers say the inactivation of tumor-suppressor genes , alone or in combination , appears crucial to the development of such scourges as cancer of the brain , the skin , kidney , prostate , and cervix . '</li><li>'One writer , signing his letter as `` Red-blooded , balanced male , `` remarked on the `` frequency of women fainting in peals , `` and suggested that they `` settle back into their traditional role of making tea at meetings . `` '</li><li>'`` To ring for even one service at this tower , we have to scrape , `` says Mr. Hammond , a retired water-authority worker . `` '</li></ul> |
79
+ | 1 | <ul><li>"kalgebra 's console is useful as a calculator . "</li><li>'Mr. Neuberger realized that , although of Italian ancestry , Mr. Mariotta still could qualify as a minority person since he was born in Puerto Rico . '</li><li>"Biggest trouble was scared family who could n't get a phone line through , and spent a really horrible hour not knowing . "</li></ul> |
80
+
81
+ ## Evaluation
82
+
83
+ ### Metrics
84
+ | Label | Accuracy |
85
+ |:--------|:---------|
86
+ | **all** | 0.1709 |
87
+
88
+ ## Uses
89
+
90
+ ### Direct Use for Inference
91
+
92
+ First install the SetFit library:
93
+
94
+ ```bash
95
+ pip install setfit
96
+ ```
97
+
98
+ Then you can load this model and run inference.
99
+
100
+ ```python
101
+ from setfit import SetFitModel
102
+
103
+ # Download from the 🤗 Hub
104
+ model = SetFitModel.from_pretrained("HelgeKn/SemEval-multi-class-8")
105
+ # Run inference
106
+ preds = model("To break the uncomfortable silence , Haney began to talk . ")
107
+ ```
108
+
109
+ <!--
110
+ ### Downstream Use
111
+
112
+ *List how someone could finetune this model on their own dataset.*
113
+ -->
114
+
115
+ <!--
116
+ ### Out-of-Scope Use
117
+
118
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
119
+ -->
120
+
121
+ <!--
122
+ ## Bias, Risks and Limitations
123
+
124
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
125
+ -->
126
+
127
+ <!--
128
+ ### Recommendations
129
+
130
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
131
+ -->
132
+
133
+ ## Training Details
134
+
135
+ ### Training Set Metrics
136
+ | Training set | Min | Median | Max |
137
+ |:-------------|:----|:-------|:----|
138
+ | Word count | 4 | 27.0 | 74 |
139
+
140
+ | Label | Training Sample Count |
141
+ |:------|:----------------------|
142
+ | 0 | 8 |
143
+ | 1 | 8 |
144
+ | 2 | 8 |
145
+ | 3 | 8 |
146
+ | 4 | 8 |
147
+ | 5 | 8 |
148
+ | 6 | 8 |
149
+
150
+ ### Training Hyperparameters
151
+ - batch_size: (16, 16)
152
+ - num_epochs: (2, 2)
153
+ - max_steps: -1
154
+ - sampling_strategy: oversampling
155
+ - num_iterations: 20
156
+ - body_learning_rate: (2e-05, 2e-05)
157
+ - head_learning_rate: 2e-05
158
+ - loss: CosineSimilarityLoss
159
+ - distance_metric: cosine_distance
160
+ - margin: 0.25
161
+ - end_to_end: False
162
+ - use_amp: False
163
+ - warmup_proportion: 0.1
164
+ - seed: 42
165
+ - eval_max_steps: -1
166
+ - load_best_model_at_end: False
167
+
168
+ ### Training Results
169
+ | Epoch | Step | Training Loss | Validation Loss |
170
+ |:------:|:----:|:-------------:|:---------------:|
171
+ | 0.0071 | 1 | 0.2786 | - |
172
+ | 0.3571 | 50 | 0.1703 | - |
173
+ | 0.7143 | 100 | 0.0932 | - |
174
+ | 1.0714 | 150 | 0.0173 | - |
175
+ | 1.4286 | 200 | 0.0048 | - |
176
+ | 1.7857 | 250 | 0.0024 | - |
177
+
178
+ ### Framework Versions
179
+ - Python: 3.9.13
180
+ - SetFit: 1.0.1
181
+ - Sentence Transformers: 2.2.2
182
+ - Transformers: 4.36.0
183
+ - PyTorch: 2.1.1+cpu
184
+ - Datasets: 2.15.0
185
+ - Tokenizers: 0.15.0
186
+
187
+ ## Citation
188
+
189
+ ### BibTeX
190
+ ```bibtex
191
+ @article{https://doi.org/10.48550/arxiv.2209.11055,
192
+ doi = {10.48550/ARXIV.2209.11055},
193
+ url = {https://arxiv.org/abs/2209.11055},
194
+ author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
195
+ keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
196
+ title = {Efficient Few-Shot Learning Without Prompts},
197
+ publisher = {arXiv},
198
+ year = {2022},
199
+ copyright = {Creative Commons Attribution 4.0 International}
200
+ }
201
+ ```
202
+
203
+ <!--
204
+ ## Glossary
205
+
206
+ *Clearly define terms in order to be accessible across audiences.*
207
+ -->
208
+
209
+ <!--
210
+ ## Model Card Authors
211
+
212
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
213
+ -->
214
+
215
+ <!--
216
+ ## Model Card Contact
217
+
218
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
219
+ -->
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "C:\\Users\\Man_f/.cache\\torch\\sentence_transformers\\sentence-transformers_paraphrase-mpnet-base-v2\\",
3
+ "architectures": [
4
+ "MPNetModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "mpnet",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 1,
20
+ "relative_attention_num_buckets": 32,
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.36.0",
23
+ "vocab_size": 30527
24
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "2.0.0",
4
+ "transformers": "4.7.0",
5
+ "pytorch": "1.9.0+cu102"
6
+ }
7
+ }
config_setfit.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "labels": null,
3
+ "normalize_embeddings": false
4
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:097ca2f46f3d0d394109a452695ebd5766deaf93f079a14436f7dd20f922fea6
3
+ size 437967672
model_head.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8b3623ce1645ef4a097073a2d4e3795f519c0db15c4b097ac9bc782ed54ecd1
3
+ size 23052
modules.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ }
14
+ ]
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 512,
3
+ "do_lower_case": false
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "104": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "30526": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "do_basic_tokenize": true,
48
+ "do_lower_case": true,
49
+ "eos_token": "</s>",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 512,
52
+ "never_split": null,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "strip_accents": null,
56
+ "tokenize_chinese_chars": true,
57
+ "tokenizer_class": "MPNetTokenizer",
58
+ "unk_token": "[UNK]"
59
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff