LeoChiuu commited on
Commit
a33e7dc
1 Parent(s): b06db9c

Add new SentenceTransformer model.

Browse files
Files changed (2) hide show
  1. README.md +531 -164
  2. model.safetensors +1 -1
README.md CHANGED
@@ -1,201 +1,568 @@
1
  ---
2
  base_model: sentence-transformers/all-MiniLM-L6-v2
3
- language: en
4
- license: apache-2.0
5
- model_name: LeoChiuu/all-MiniLM-L6-v2-arc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  ---
7
 
8
- # Model Card for LeoChiuu/all-MiniLM-L6-v2-arc
9
-
10
- <!-- Provide a quick summary of what the model is/does. -->
11
-
12
 
 
13
 
14
  ## Model Details
15
 
16
  ### Model Description
 
 
 
 
 
 
 
 
 
17
 
18
- <!-- Provide a longer summary of what this model is. -->
19
-
20
- Generates similarity embeddings
21
-
22
- - **Developed by:** [More Information Needed]
23
- - **Funded by [optional]:** [More Information Needed]
24
- - **Shared by [optional]:** [More Information Needed]
25
- - **Model type:** [More Information Needed]
26
- - **Language(s) (NLP):** en
27
- - **License:** apache-2.0
28
- - **Finetuned from model [optional]:** sentence-transformers/all-MiniLM-L6-v2
29
-
30
- ### Model Sources [optional]
31
-
32
- <!-- Provide the basic links for the model. -->
33
-
34
- - **Repository:** [More Information Needed]
35
- - **Paper [optional]:** [More Information Needed]
36
- - **Demo [optional]:** [More Information Needed]
37
-
38
- ## Uses
39
-
40
- <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
41
 
42
- ### Direct Use
 
 
43
 
44
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
45
 
46
- [More Information Needed]
 
 
 
 
 
 
47
 
48
- ### Downstream Use [optional]
49
 
50
- <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
51
 
52
- [More Information Needed]
53
 
54
- ### Out-of-Scope Use
55
-
56
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
57
-
58
- [More Information Needed]
59
 
60
- ## Bias, Risks, and Limitations
 
 
61
 
62
- <!-- This section is meant to convey both technical and sociotechnical limitations. -->
 
 
 
 
 
 
 
 
 
 
63
 
64
- [More Information Needed]
65
-
66
- ### Recommendations
 
 
67
 
68
- <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
 
69
 
70
- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
71
 
72
- ## How to Get Started with the Model
73
-
74
- Use the code below to get started with the model.
75
-
76
- [More Information Needed]
77
-
78
- ## Training Details
79
 
80
- ### Training Data
 
81
 
82
- <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
83
 
84
- [More Information Needed]
85
 
86
- ### Training Procedure
 
87
 
88
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
89
-
90
- #### Preprocessing [optional]
91
-
92
- [More Information Needed]
93
-
94
-
95
- #### Training Hyperparameters
96
-
97
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
98
-
99
- #### Speeds, Sizes, Times [optional]
100
-
101
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
102
 
103
- [More Information Needed]
 
104
 
105
  ## Evaluation
106
 
107
- <!-- This section describes the evaluation protocols and provides the results. -->
108
-
109
- ### Testing Data, Factors & Metrics
110
-
111
- #### Testing Data
112
-
113
- <!-- This should link to a Dataset Card if possible. -->
114
-
115
- [More Information Needed]
116
-
117
- #### Factors
118
-
119
- <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
120
-
121
- [More Information Needed]
122
-
123
- #### Metrics
124
-
125
- <!-- These are the evaluation metrics being used, ideally with a description of why. -->
126
-
127
- [More Information Needed]
128
-
129
- ### Results
130
-
131
- [More Information Needed]
132
-
133
- #### Summary
134
-
135
-
136
-
137
- ## Model Examination [optional]
138
-
139
- <!-- Relevant interpretability work for the model goes here -->
140
-
141
- [More Information Needed]
142
-
143
- ## Environmental Impact
144
-
145
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
146
-
147
- Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
148
-
149
- - **Hardware Type:** [More Information Needed]
150
- - **Hours used:** [More Information Needed]
151
- - **Cloud Provider:** [More Information Needed]
152
- - **Compute Region:** [More Information Needed]
153
- - **Carbon Emitted:** [More Information Needed]
154
-
155
- ## Technical Specifications [optional]
156
-
157
- ### Model Architecture and Objective
158
-
159
- [More Information Needed]
160
-
161
- ### Compute Infrastructure
162
-
163
- [More Information Needed]
164
-
165
- #### Hardware
166
-
167
- [More Information Needed]
168
-
169
- #### Software
170
-
171
- [More Information Needed]
172
-
173
- ## Citation [optional]
174
-
175
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
176
-
177
- **BibTeX:**
178
-
179
- [More Information Needed]
180
-
181
- **APA:**
182
-
183
- [More Information Needed]
184
-
185
- ## Glossary [optional]
186
-
187
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
188
-
189
- [More Information Needed]
190
-
191
- ## More Information [optional]
192
-
193
- [More Information Needed]
194
 
195
- ## Model Card Authors [optional]
 
196
 
197
- [More Information Needed]
198
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
199
  ## Model Card Contact
200
 
201
- [More Information Needed]
 
 
1
  ---
2
  base_model: sentence-transformers/all-MiniLM-L6-v2
3
+ library_name: sentence-transformers
4
+ metrics:
5
+ - cosine_accuracy
6
+ - cosine_accuracy_threshold
7
+ - cosine_f1
8
+ - cosine_f1_threshold
9
+ - cosine_precision
10
+ - cosine_recall
11
+ - cosine_ap
12
+ - dot_accuracy
13
+ - dot_accuracy_threshold
14
+ - dot_f1
15
+ - dot_f1_threshold
16
+ - dot_precision
17
+ - dot_recall
18
+ - dot_ap
19
+ - manhattan_accuracy
20
+ - manhattan_accuracy_threshold
21
+ - manhattan_f1
22
+ - manhattan_f1_threshold
23
+ - manhattan_precision
24
+ - manhattan_recall
25
+ - manhattan_ap
26
+ - euclidean_accuracy
27
+ - euclidean_accuracy_threshold
28
+ - euclidean_f1
29
+ - euclidean_f1_threshold
30
+ - euclidean_precision
31
+ - euclidean_recall
32
+ - euclidean_ap
33
+ - max_accuracy
34
+ - max_accuracy_threshold
35
+ - max_f1
36
+ - max_f1_threshold
37
+ - max_precision
38
+ - max_recall
39
+ - max_ap
40
+ pipeline_tag: sentence-similarity
41
+ tags:
42
+ - sentence-transformers
43
+ - sentence-similarity
44
+ - feature-extraction
45
+ - generated_from_trainer
46
+ - dataset_size:965
47
+ - loss:OnlineContrastiveLoss
48
+ widget:
49
+ - source_sentence: Do it by yourself
50
+ sentences:
51
+ - What magic can he use?
52
+ - Let's go outside
53
+ - Why do I have to do that?
54
+ - source_sentence: What is that on the tree?
55
+ sentences:
56
+ - I have not
57
+ - Oblivion
58
+ - Is that a cloth on the tree?
59
+ - source_sentence: Which one?
60
+ sentences:
61
+ - Bed
62
+ - I found lillies.
63
+ - The plush is the flower
64
+ - source_sentence: Who are you?
65
+ sentences:
66
+ - You are beautiful
67
+ - What's analyze mode?
68
+ - Let's go outside
69
+ - source_sentence: 'Someone who uses magic that turns something into something. '
70
+ sentences:
71
+ - Where am I?
72
+ - 'Mage who can use magic to change the object. '
73
+ - what's the mystery?
74
+ model-index:
75
+ - name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
76
+ results:
77
+ - task:
78
+ type: binary-classification
79
+ name: Binary Classification
80
+ dataset:
81
+ name: custom arc semantics data en
82
+ type: custom-arc-semantics-data-en
83
+ metrics:
84
+ - type: cosine_accuracy
85
+ value: 0.8911917098445595
86
+ name: Cosine Accuracy
87
+ - type: cosine_accuracy_threshold
88
+ value: 0.8555419445037842
89
+ name: Cosine Accuracy Threshold
90
+ - type: cosine_f1
91
+ value: 0.9041095890410958
92
+ name: Cosine F1
93
+ - type: cosine_f1_threshold
94
+ value: 0.8399168252944946
95
+ name: Cosine F1 Threshold
96
+ - type: cosine_precision
97
+ value: 0.9252336448598131
98
+ name: Cosine Precision
99
+ - type: cosine_recall
100
+ value: 0.8839285714285714
101
+ name: Cosine Recall
102
+ - type: cosine_ap
103
+ value: 0.9448087103322457
104
+ name: Cosine Ap
105
+ - type: dot_accuracy
106
+ value: 0.8911917098445595
107
+ name: Dot Accuracy
108
+ - type: dot_accuracy_threshold
109
+ value: 0.8555418252944946
110
+ name: Dot Accuracy Threshold
111
+ - type: dot_f1
112
+ value: 0.9041095890410958
113
+ name: Dot F1
114
+ - type: dot_f1_threshold
115
+ value: 0.8399168252944946
116
+ name: Dot F1 Threshold
117
+ - type: dot_precision
118
+ value: 0.9252336448598131
119
+ name: Dot Precision
120
+ - type: dot_recall
121
+ value: 0.8839285714285714
122
+ name: Dot Recall
123
+ - type: dot_ap
124
+ value: 0.9448087103322457
125
+ name: Dot Ap
126
+ - type: manhattan_accuracy
127
+ value: 0.8911917098445595
128
+ name: Manhattan Accuracy
129
+ - type: manhattan_accuracy_threshold
130
+ value: 8.42230224609375
131
+ name: Manhattan Accuracy Threshold
132
+ - type: manhattan_f1
133
+ value: 0.9041095890410958
134
+ name: Manhattan F1
135
+ - type: manhattan_f1_threshold
136
+ value: 8.718589782714844
137
+ name: Manhattan F1 Threshold
138
+ - type: manhattan_precision
139
+ value: 0.9252336448598131
140
+ name: Manhattan Precision
141
+ - type: manhattan_recall
142
+ value: 0.8839285714285714
143
+ name: Manhattan Recall
144
+ - type: manhattan_ap
145
+ value: 0.9451459110925178
146
+ name: Manhattan Ap
147
+ - type: euclidean_accuracy
148
+ value: 0.8911917098445595
149
+ name: Euclidean Accuracy
150
+ - type: euclidean_accuracy_threshold
151
+ value: 0.5375091433525085
152
+ name: Euclidean Accuracy Threshold
153
+ - type: euclidean_f1
154
+ value: 0.9041095890410958
155
+ name: Euclidean F1
156
+ - type: euclidean_f1_threshold
157
+ value: 0.5658255219459534
158
+ name: Euclidean F1 Threshold
159
+ - type: euclidean_precision
160
+ value: 0.9252336448598131
161
+ name: Euclidean Precision
162
+ - type: euclidean_recall
163
+ value: 0.8839285714285714
164
+ name: Euclidean Recall
165
+ - type: euclidean_ap
166
+ value: 0.9448087103322457
167
+ name: Euclidean Ap
168
+ - type: max_accuracy
169
+ value: 0.8911917098445595
170
+ name: Max Accuracy
171
+ - type: max_accuracy_threshold
172
+ value: 8.42230224609375
173
+ name: Max Accuracy Threshold
174
+ - type: max_f1
175
+ value: 0.9041095890410958
176
+ name: Max F1
177
+ - type: max_f1_threshold
178
+ value: 8.718589782714844
179
+ name: Max F1 Threshold
180
+ - type: max_precision
181
+ value: 0.9252336448598131
182
+ name: Max Precision
183
+ - type: max_recall
184
+ value: 0.8839285714285714
185
+ name: Max Recall
186
+ - type: max_ap
187
+ value: 0.9451459110925178
188
+ name: Max Ap
189
  ---
190
 
191
+ # SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
 
 
 
192
 
193
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) on the csv dataset. It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
194
 
195
  ## Model Details
196
 
197
  ### Model Description
198
+ - **Model Type:** Sentence Transformer
199
+ - **Base model:** [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) <!-- at revision 8b3219a92973c328a8e22fadcfa821b5dc75636a -->
200
+ - **Maximum Sequence Length:** 256 tokens
201
+ - **Output Dimensionality:** 384 tokens
202
+ - **Similarity Function:** Cosine Similarity
203
+ - **Training Dataset:**
204
+ - csv
205
+ <!-- - **Language:** Unknown -->
206
+ <!-- - **License:** Unknown -->
207
 
208
+ ### Model Sources
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
209
 
210
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
211
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
212
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
213
 
214
+ ### Full Model Architecture
215
 
216
+ ```
217
+ SentenceTransformer(
218
+ (0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: BertModel
219
+ (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
220
+ (2): Normalize()
221
+ )
222
+ ```
223
 
224
+ ## Usage
225
 
226
+ ### Direct Usage (Sentence Transformers)
227
 
228
+ First install the Sentence Transformers library:
229
 
230
+ ```bash
231
+ pip install -U sentence-transformers
232
+ ```
 
 
233
 
234
+ Then you can load this model and run inference.
235
+ ```python
236
+ from sentence_transformers import SentenceTransformer
237
 
238
+ # Download from the 🤗 Hub
239
+ model = SentenceTransformer("LeoChiuu/all-MiniLM-L6-v2-arc")
240
+ # Run inference
241
+ sentences = [
242
+ 'Someone who uses magic that turns something into something. ',
243
+ 'Mage who can use magic to change the object. ',
244
+ "what's the mystery?",
245
+ ]
246
+ embeddings = model.encode(sentences)
247
+ print(embeddings.shape)
248
+ # [3, 384]
249
 
250
+ # Get the similarity scores for the embeddings
251
+ similarities = model.similarity(embeddings, embeddings)
252
+ print(similarities.shape)
253
+ # [3, 3]
254
+ ```
255
 
256
+ <!--
257
+ ### Direct Usage (Transformers)
258
 
259
+ <details><summary>Click to see the direct usage in Transformers</summary>
260
 
261
+ </details>
262
+ -->
 
 
 
 
 
263
 
264
+ <!--
265
+ ### Downstream Usage (Sentence Transformers)
266
 
267
+ You can finetune this model on your own dataset.
268
 
269
+ <details><summary>Click to expand</summary>
270
 
271
+ </details>
272
+ -->
273
 
274
+ <!--
275
+ ### Out-of-Scope Use
 
 
 
 
 
 
 
 
 
 
 
 
276
 
277
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
278
+ -->
279
 
280
  ## Evaluation
281
 
282
+ ### Metrics
283
+
284
+ #### Binary Classification
285
+ * Dataset: `custom-arc-semantics-data-en`
286
+ * Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
287
+
288
+ | Metric | Value |
289
+ |:-----------------------------|:-----------|
290
+ | cosine_accuracy | 0.8912 |
291
+ | cosine_accuracy_threshold | 0.8555 |
292
+ | cosine_f1 | 0.9041 |
293
+ | cosine_f1_threshold | 0.8399 |
294
+ | cosine_precision | 0.9252 |
295
+ | cosine_recall | 0.8839 |
296
+ | cosine_ap | 0.9448 |
297
+ | dot_accuracy | 0.8912 |
298
+ | dot_accuracy_threshold | 0.8555 |
299
+ | dot_f1 | 0.9041 |
300
+ | dot_f1_threshold | 0.8399 |
301
+ | dot_precision | 0.9252 |
302
+ | dot_recall | 0.8839 |
303
+ | dot_ap | 0.9448 |
304
+ | manhattan_accuracy | 0.8912 |
305
+ | manhattan_accuracy_threshold | 8.4223 |
306
+ | manhattan_f1 | 0.9041 |
307
+ | manhattan_f1_threshold | 8.7186 |
308
+ | manhattan_precision | 0.9252 |
309
+ | manhattan_recall | 0.8839 |
310
+ | manhattan_ap | 0.9451 |
311
+ | euclidean_accuracy | 0.8912 |
312
+ | euclidean_accuracy_threshold | 0.5375 |
313
+ | euclidean_f1 | 0.9041 |
314
+ | euclidean_f1_threshold | 0.5658 |
315
+ | euclidean_precision | 0.9252 |
316
+ | euclidean_recall | 0.8839 |
317
+ | euclidean_ap | 0.9448 |
318
+ | max_accuracy | 0.8912 |
319
+ | max_accuracy_threshold | 8.4223 |
320
+ | max_f1 | 0.9041 |
321
+ | max_f1_threshold | 8.7186 |
322
+ | max_precision | 0.9252 |
323
+ | max_recall | 0.8839 |
324
+ | **max_ap** | **0.9451** |
325
+
326
+ <!--
327
+ ## Bias, Risks and Limitations
328
+
329
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
330
+ -->
331
+
332
+ <!--
333
+ ### Recommendations
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
334
 
335
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
336
+ -->
337
 
338
+ ## Training Details
339
 
340
+ ### Training Dataset
341
+
342
+ #### csv
343
+
344
+ * Dataset: csv
345
+ * Size: 965 training samples
346
+ * Columns: <code>text1</code>, <code>text2</code>, and <code>label</code>
347
+ * Approximate statistics based on the first 965 samples:
348
+ | | text1 | text2 | label |
349
+ |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:------------------------------------------------|
350
+ | type | string | string | int |
351
+ | details | <ul><li>min: 3 tokens</li><li>mean: 7.23 tokens</li><li>max: 18 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 7.08 tokens</li><li>max: 18 tokens</li></ul> | <ul><li>0: ~42.88%</li><li>1: ~57.12%</li></ul> |
352
+ * Samples:
353
+ | text1 | text2 | label |
354
+ |:----------------------------------------|:---------------------------------------|:---------------|
355
+ | <code>This storybook is related.</code> | <code>Do you know this book?</code> | <code>1</code> |
356
+ | <code>Who gave it to you?</code> | <code>Is it the one I gave you?</code> | <code>1</code> |
357
+ | <code>Why rosemary?</code> | <code>Thank you!</code> | <code>0</code> |
358
+ * Loss: [<code>OnlineContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#onlinecontrastiveloss)
359
+
360
+ ### Evaluation Dataset
361
+
362
+ #### csv
363
+
364
+ * Dataset: csv
365
+ * Size: 965 evaluation samples
366
+ * Columns: <code>text1</code>, <code>text2</code>, and <code>label</code>
367
+ * Approximate statistics based on the first 965 samples:
368
+ | | text1 | text2 | label |
369
+ |:--------|:--------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:------------------------------------------------|
370
+ | type | string | string | int |
371
+ | details | <ul><li>min: 3 tokens</li><li>mean: 7.4 tokens</li><li>max: 16 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 7.34 tokens</li><li>max: 18 tokens</li></ul> | <ul><li>0: ~41.97%</li><li>1: ~58.03%</li></ul> |
372
+ * Samples:
373
+ | text1 | text2 | label |
374
+ |:---------------------------------------|:---------------------------------------|:---------------|
375
+ | <code>Where?</code> | <code>Which one should I chose?</code> | <code>1</code> |
376
+ | <code>Was the window left open?</code> | <code>Did you open the window?</code> | <code>0</code> |
377
+ | <code>I don't need any</code> | <code>Inside</code> | <code>0</code> |
378
+ * Loss: [<code>OnlineContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#onlinecontrastiveloss)
379
+
380
+ ### Training Hyperparameters
381
+ #### Non-Default Hyperparameters
382
+
383
+ - `eval_strategy`: epoch
384
+ - `learning_rate`: 2e-05
385
+ - `num_train_epochs`: 13
386
+ - `warmup_ratio`: 0.1
387
+ - `fp16`: True
388
+ - `batch_sampler`: no_duplicates
389
+
390
+ #### All Hyperparameters
391
+ <details><summary>Click to expand</summary>
392
+
393
+ - `overwrite_output_dir`: False
394
+ - `do_predict`: False
395
+ - `eval_strategy`: epoch
396
+ - `prediction_loss_only`: True
397
+ - `per_device_train_batch_size`: 8
398
+ - `per_device_eval_batch_size`: 8
399
+ - `per_gpu_train_batch_size`: None
400
+ - `per_gpu_eval_batch_size`: None
401
+ - `gradient_accumulation_steps`: 1
402
+ - `eval_accumulation_steps`: None
403
+ - `torch_empty_cache_steps`: None
404
+ - `learning_rate`: 2e-05
405
+ - `weight_decay`: 0.0
406
+ - `adam_beta1`: 0.9
407
+ - `adam_beta2`: 0.999
408
+ - `adam_epsilon`: 1e-08
409
+ - `max_grad_norm`: 1.0
410
+ - `num_train_epochs`: 13
411
+ - `max_steps`: -1
412
+ - `lr_scheduler_type`: linear
413
+ - `lr_scheduler_kwargs`: {}
414
+ - `warmup_ratio`: 0.1
415
+ - `warmup_steps`: 0
416
+ - `log_level`: passive
417
+ - `log_level_replica`: warning
418
+ - `log_on_each_node`: True
419
+ - `logging_nan_inf_filter`: True
420
+ - `save_safetensors`: True
421
+ - `save_on_each_node`: False
422
+ - `save_only_model`: False
423
+ - `restore_callback_states_from_checkpoint`: False
424
+ - `no_cuda`: False
425
+ - `use_cpu`: False
426
+ - `use_mps_device`: False
427
+ - `seed`: 42
428
+ - `data_seed`: None
429
+ - `jit_mode_eval`: False
430
+ - `use_ipex`: False
431
+ - `bf16`: False
432
+ - `fp16`: True
433
+ - `fp16_opt_level`: O1
434
+ - `half_precision_backend`: auto
435
+ - `bf16_full_eval`: False
436
+ - `fp16_full_eval`: False
437
+ - `tf32`: None
438
+ - `local_rank`: 0
439
+ - `ddp_backend`: None
440
+ - `tpu_num_cores`: None
441
+ - `tpu_metrics_debug`: False
442
+ - `debug`: []
443
+ - `dataloader_drop_last`: False
444
+ - `dataloader_num_workers`: 0
445
+ - `dataloader_prefetch_factor`: None
446
+ - `past_index`: -1
447
+ - `disable_tqdm`: False
448
+ - `remove_unused_columns`: True
449
+ - `label_names`: None
450
+ - `load_best_model_at_end`: False
451
+ - `ignore_data_skip`: False
452
+ - `fsdp`: []
453
+ - `fsdp_min_num_params`: 0
454
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
455
+ - `fsdp_transformer_layer_cls_to_wrap`: None
456
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
457
+ - `deepspeed`: None
458
+ - `label_smoothing_factor`: 0.0
459
+ - `optim`: adamw_torch
460
+ - `optim_args`: None
461
+ - `adafactor`: False
462
+ - `group_by_length`: False
463
+ - `length_column_name`: length
464
+ - `ddp_find_unused_parameters`: None
465
+ - `ddp_bucket_cap_mb`: None
466
+ - `ddp_broadcast_buffers`: False
467
+ - `dataloader_pin_memory`: True
468
+ - `dataloader_persistent_workers`: False
469
+ - `skip_memory_metrics`: True
470
+ - `use_legacy_prediction_loop`: False
471
+ - `push_to_hub`: False
472
+ - `resume_from_checkpoint`: None
473
+ - `hub_model_id`: None
474
+ - `hub_strategy`: every_save
475
+ - `hub_private_repo`: False
476
+ - `hub_always_push`: False
477
+ - `gradient_checkpointing`: False
478
+ - `gradient_checkpointing_kwargs`: None
479
+ - `include_inputs_for_metrics`: False
480
+ - `eval_do_concat_batches`: True
481
+ - `fp16_backend`: auto
482
+ - `push_to_hub_model_id`: None
483
+ - `push_to_hub_organization`: None
484
+ - `mp_parameters`:
485
+ - `auto_find_batch_size`: False
486
+ - `full_determinism`: False
487
+ - `torchdynamo`: None
488
+ - `ray_scope`: last
489
+ - `ddp_timeout`: 1800
490
+ - `torch_compile`: False
491
+ - `torch_compile_backend`: None
492
+ - `torch_compile_mode`: None
493
+ - `dispatch_batches`: None
494
+ - `split_batches`: None
495
+ - `include_tokens_per_second`: False
496
+ - `include_num_input_tokens_seen`: False
497
+ - `neftune_noise_alpha`: None
498
+ - `optim_target_modules`: None
499
+ - `batch_eval_metrics`: False
500
+ - `eval_on_start`: False
501
+ - `eval_use_gather_object`: False
502
+ - `batch_sampler`: no_duplicates
503
+ - `multi_dataset_batch_sampler`: proportional
504
+
505
+ </details>
506
+
507
+ ### Training Logs
508
+ | Epoch | Step | Training Loss | loss | custom-arc-semantics-data-en_max_ap |
509
+ |:-----:|:----:|:-------------:|:------:|:-----------------------------------:|
510
+ | None | 0 | - | - | 0.9204 |
511
+ | 1.0 | 97 | 0.4216 | 0.1880 | 0.9318 |
512
+ | 2.0 | 194 | 0.1234 | 0.1109 | 0.9388 |
513
+ | 3.0 | 291 | 0.0588 | 0.1065 | 0.9360 |
514
+ | 4.0 | 388 | 0.041 | 0.0964 | 0.9472 |
515
+ | 5.0 | 485 | 0.031 | 0.0962 | 0.9471 |
516
+ | 6.0 | 582 | 0.0202 | 0.1032 | 0.9444 |
517
+ | 7.0 | 679 | 0.0214 | 0.0922 | 0.9452 |
518
+ | 8.0 | 776 | 0.0232 | 0.0857 | 0.9454 |
519
+ | 9.0 | 873 | 0.0135 | 0.0873 | 0.9474 |
520
+ | 10.0 | 970 | 0.0136 | 0.0870 | 0.9444 |
521
+ | 11.0 | 1067 | 0.0131 | 0.0903 | 0.9452 |
522
+ | 12.0 | 1164 | 0.0135 | 0.0903 | 0.9450 |
523
+ | 13.0 | 1261 | 0.0082 | 0.0902 | 0.9451 |
524
+
525
+
526
+ ### Framework Versions
527
+ - Python: 3.10.14
528
+ - Sentence Transformers: 3.1.0
529
+ - Transformers: 4.44.2
530
+ - PyTorch: 2.4.1+cu121
531
+ - Accelerate: 0.34.2
532
+ - Datasets: 2.20.0
533
+ - Tokenizers: 0.19.1
534
+
535
+ ## Citation
536
+
537
+ ### BibTeX
538
+
539
+ #### Sentence Transformers
540
+ ```bibtex
541
+ @inproceedings{reimers-2019-sentence-bert,
542
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
543
+ author = "Reimers, Nils and Gurevych, Iryna",
544
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
545
+ month = "11",
546
+ year = "2019",
547
+ publisher = "Association for Computational Linguistics",
548
+ url = "https://arxiv.org/abs/1908.10084",
549
+ }
550
+ ```
551
+
552
+ <!--
553
+ ## Glossary
554
+
555
+ *Clearly define terms in order to be accessible across audiences.*
556
+ -->
557
+
558
+ <!--
559
+ ## Model Card Authors
560
+
561
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
562
+ -->
563
+
564
+ <!--
565
  ## Model Card Contact
566
 
567
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
568
+ -->
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d69507d61c4dad8a4b2276b36338d6e9e97f7dbc11623f392dc2d0f64f31a75
3
  size 90864192
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7fefe0ef583c2760d11ac99d99c8344222316fea40286e6ca9556955ab311af
3
  size 90864192