Upload 11 files
Browse files- 1_Pooling/config.json +10 -0
- README.md +492 -3
- config.json +25 -0
- config_sentence_transformers.json +10 -0
- model.safetensors +3 -0
- modules.json +14 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +44 -0
- tokenizer.json +0 -0
- tokenizer_config.json +71 -0
- vocab.txt +0 -0
1_Pooling/config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"word_embedding_dimension": 384,
|
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 |
+
"pooling_mode_weightedmean_tokens": false,
|
8 |
+
"pooling_mode_lasttoken": false,
|
9 |
+
"include_prompt": true
|
10 |
+
}
|
README.md
CHANGED
@@ -1,3 +1,492 @@
|
|
1 |
-
---
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: Mihaiii/Venusaur
|
3 |
+
datasets:
|
4 |
+
- Mihaiii/qa-assistant-2
|
5 |
+
language:
|
6 |
+
- en
|
7 |
+
library_name: sentence-transformers
|
8 |
+
metrics:
|
9 |
+
- pearson_cosine
|
10 |
+
- spearman_cosine
|
11 |
+
- pearson_manhattan
|
12 |
+
- spearman_manhattan
|
13 |
+
- pearson_euclidean
|
14 |
+
- spearman_euclidean
|
15 |
+
- pearson_dot
|
16 |
+
- spearman_dot
|
17 |
+
- pearson_max
|
18 |
+
- spearman_max
|
19 |
+
pipeline_tag: sentence-similarity
|
20 |
+
tags:
|
21 |
+
- sentence-transformers
|
22 |
+
- sentence-similarity
|
23 |
+
- feature-extraction
|
24 |
+
- generated_from_trainer
|
25 |
+
- dataset_size:16011
|
26 |
+
- loss:CosineSimilarityLoss
|
27 |
+
widget:
|
28 |
+
- source_sentence: What impact does high-speed rail have on connectivity between cities?
|
29 |
+
sentences:
|
30 |
+
- Art supplies can be quite expensive, especially high-quality paints and brushes.
|
31 |
+
- High-speed rail can be a more comfortable and convenient mode of travel compared
|
32 |
+
to buses or cars.
|
33 |
+
- Engineers use a variety of methods to test the safety of autonomous vehicles,
|
34 |
+
including controlled track testing and public road trials.
|
35 |
+
- source_sentence: What is the best soil type for growing tomatoes?
|
36 |
+
sentences:
|
37 |
+
- Sandy loam soil is often considered ideal for growing tomatoes due to its good
|
38 |
+
drainage and nutrient-holding capacity.
|
39 |
+
- Socialist political systems are often contrasted with capitalist systems, which
|
40 |
+
prioritize private ownership and market-driven economies.
|
41 |
+
- The core principles of Sikhism include the belief in one God, the importance of
|
42 |
+
honest living, and the practice of selfless service.
|
43 |
+
- source_sentence: What are the three main types of rocks?
|
44 |
+
sentences:
|
45 |
+
- Mount Everest is the highest mountain in the world, located in the Himalayas.
|
46 |
+
- Archaeologists sometimes face challenges such as funding and access to advanced
|
47 |
+
technology, which can impact their ability to preserve findings.
|
48 |
+
- Some people are concerned about the ethical implications of genetic modification
|
49 |
+
in food production.
|
50 |
+
- source_sentence: How do vaccines help prevent diseases?
|
51 |
+
sentences:
|
52 |
+
- The theory also posits that during periods of economic downturn, increased government
|
53 |
+
spending can help stimulate demand and pull the economy out of recession.
|
54 |
+
- The Gurdwara is a place where Sikhs can participate in religious rituals and ceremonies,
|
55 |
+
such as weddings and naming ceremonies.
|
56 |
+
- The development of vaccines involves rigorous testing to ensure their safety and
|
57 |
+
efficacy before they are approved for public use.
|
58 |
+
- source_sentence: What are the social structures of ants?
|
59 |
+
sentences:
|
60 |
+
- The social hierarchy of ants is a complex system that ensures the survival and
|
61 |
+
efficiency of the colony.
|
62 |
+
- In a parliamentary system, the executive branch derives its legitimacy from and
|
63 |
+
is accountable to the legislature; the executive and legislative branches are
|
64 |
+
thus interconnected.
|
65 |
+
- Proper waste management and recycling can contribute to a more sustainable farming
|
66 |
+
operation.
|
67 |
+
model-index:
|
68 |
+
- name: SentenceTransformer based on Mihaiii/Venusaur
|
69 |
+
results:
|
70 |
+
- task:
|
71 |
+
type: semantic-similarity
|
72 |
+
name: Semantic Similarity
|
73 |
+
dataset:
|
74 |
+
name: sts dev
|
75 |
+
type: sts-dev
|
76 |
+
metrics:
|
77 |
+
- type: pearson_cosine
|
78 |
+
value: 0.826101669872389
|
79 |
+
name: Pearson Cosine
|
80 |
+
- type: spearman_cosine
|
81 |
+
value: 0.8277251878978443
|
82 |
+
name: Spearman Cosine
|
83 |
+
- type: pearson_manhattan
|
84 |
+
value: 0.8199515763304537
|
85 |
+
name: Pearson Manhattan
|
86 |
+
- type: spearman_manhattan
|
87 |
+
value: 0.8225731321378551
|
88 |
+
name: Spearman Manhattan
|
89 |
+
- type: pearson_euclidean
|
90 |
+
value: 0.8214525375708358
|
91 |
+
name: Pearson Euclidean
|
92 |
+
- type: spearman_euclidean
|
93 |
+
value: 0.8236879484111633
|
94 |
+
name: Spearman Euclidean
|
95 |
+
- type: pearson_dot
|
96 |
+
value: 0.8037304918463798
|
97 |
+
name: Pearson Dot
|
98 |
+
- type: spearman_dot
|
99 |
+
value: 0.8082305683494836
|
100 |
+
name: Spearman Dot
|
101 |
+
- type: pearson_max
|
102 |
+
value: 0.826101669872389
|
103 |
+
name: Pearson Max
|
104 |
+
- type: spearman_max
|
105 |
+
value: 0.8277251878978443
|
106 |
+
name: Spearman Max
|
107 |
+
---
|
108 |
+
|
109 |
+
# SentenceTransformer based on Mihaiii/Venusaur
|
110 |
+
|
111 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Mihaiii/Venusaur](https://huggingface.co/Mihaiii/Venusaur) on the [Mihaiii/qa-assistant-2](https://huggingface.co/datasets/Mihaiii/qa-assistant-2) 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.
|
112 |
+
|
113 |
+
## Model Details
|
114 |
+
|
115 |
+
### Model Description
|
116 |
+
- **Model Type:** Sentence Transformer
|
117 |
+
- **Base model:** [Mihaiii/Venusaur](https://huggingface.co/Mihaiii/Venusaur) <!-- at revision 0dc817f0addbb7bab8feeeeaded538f9ffeb3419 -->
|
118 |
+
- **Maximum Sequence Length:** 512 tokens
|
119 |
+
- **Output Dimensionality:** 384 tokens
|
120 |
+
- **Similarity Function:** Cosine Similarity
|
121 |
+
- **Training Dataset:**
|
122 |
+
- [Mihaiii/qa-assistant-2](https://huggingface.co/datasets/Mihaiii/qa-assistant-2)
|
123 |
+
- **Language:** en
|
124 |
+
<!-- - **License:** Unknown -->
|
125 |
+
|
126 |
+
### Model Sources
|
127 |
+
|
128 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
129 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
130 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
131 |
+
|
132 |
+
### Full Model Architecture
|
133 |
+
|
134 |
+
```
|
135 |
+
SentenceTransformer(
|
136 |
+
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
|
137 |
+
(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})
|
138 |
+
)
|
139 |
+
```
|
140 |
+
|
141 |
+
## Usage
|
142 |
+
|
143 |
+
### Direct Usage (Sentence Transformers)
|
144 |
+
|
145 |
+
First install the Sentence Transformers library:
|
146 |
+
|
147 |
+
```bash
|
148 |
+
pip install -U sentence-transformers
|
149 |
+
```
|
150 |
+
|
151 |
+
Then you can load this model and run inference.
|
152 |
+
```python
|
153 |
+
from sentence_transformers import SentenceTransformer
|
154 |
+
|
155 |
+
# Download from the 🤗 Hub
|
156 |
+
model = SentenceTransformer("sentence_transformers_model_id")
|
157 |
+
# Run inference
|
158 |
+
sentences = [
|
159 |
+
'What are the social structures of ants?',
|
160 |
+
'The social hierarchy of ants is a complex system that ensures the survival and efficiency of the colony.',
|
161 |
+
'In a parliamentary system, the executive branch derives its legitimacy from and is accountable to the legislature; the executive and legislative branches are thus interconnected.',
|
162 |
+
]
|
163 |
+
embeddings = model.encode(sentences)
|
164 |
+
print(embeddings.shape)
|
165 |
+
# [3, 384]
|
166 |
+
|
167 |
+
# Get the similarity scores for the embeddings
|
168 |
+
similarities = model.similarity(embeddings, embeddings)
|
169 |
+
print(similarities.shape)
|
170 |
+
# [3, 3]
|
171 |
+
```
|
172 |
+
|
173 |
+
<!--
|
174 |
+
### Direct Usage (Transformers)
|
175 |
+
|
176 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
177 |
+
|
178 |
+
</details>
|
179 |
+
-->
|
180 |
+
|
181 |
+
<!--
|
182 |
+
### Downstream Usage (Sentence Transformers)
|
183 |
+
|
184 |
+
You can finetune this model on your own dataset.
|
185 |
+
|
186 |
+
<details><summary>Click to expand</summary>
|
187 |
+
|
188 |
+
</details>
|
189 |
+
-->
|
190 |
+
|
191 |
+
<!--
|
192 |
+
### Out-of-Scope Use
|
193 |
+
|
194 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
195 |
+
-->
|
196 |
+
|
197 |
+
## Evaluation
|
198 |
+
|
199 |
+
### Metrics
|
200 |
+
|
201 |
+
#### Semantic Similarity
|
202 |
+
* Dataset: `sts-dev`
|
203 |
+
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
|
204 |
+
|
205 |
+
| Metric | Value |
|
206 |
+
|:--------------------|:-----------|
|
207 |
+
| pearson_cosine | 0.8261 |
|
208 |
+
| **spearman_cosine** | **0.8277** |
|
209 |
+
| pearson_manhattan | 0.82 |
|
210 |
+
| spearman_manhattan | 0.8226 |
|
211 |
+
| pearson_euclidean | 0.8215 |
|
212 |
+
| spearman_euclidean | 0.8237 |
|
213 |
+
| pearson_dot | 0.8037 |
|
214 |
+
| spearman_dot | 0.8082 |
|
215 |
+
| pearson_max | 0.8261 |
|
216 |
+
| spearman_max | 0.8277 |
|
217 |
+
|
218 |
+
<!--
|
219 |
+
## Bias, Risks and Limitations
|
220 |
+
|
221 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
222 |
+
-->
|
223 |
+
|
224 |
+
<!--
|
225 |
+
### Recommendations
|
226 |
+
|
227 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
228 |
+
-->
|
229 |
+
|
230 |
+
## Training Details
|
231 |
+
|
232 |
+
### Training Dataset
|
233 |
+
|
234 |
+
#### Mihaiii/qa-assistant-2
|
235 |
+
|
236 |
+
* Dataset: [Mihaiii/qa-assistant-2](https://huggingface.co/datasets/Mihaiii/qa-assistant-2) at [9650e69](https://huggingface.co/datasets/Mihaiii/qa-assistant-2/tree/9650e69ae0a030fa74a8706a20a168a613c43241)
|
237 |
+
* Size: 16,011 training samples
|
238 |
+
* Columns: <code>question</code>, <code>answer</code>, and <code>score</code>
|
239 |
+
* Approximate statistics based on the first 1000 samples:
|
240 |
+
| | question | answer | score |
|
241 |
+
|:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------|
|
242 |
+
| type | string | string | float |
|
243 |
+
| details | <ul><li>min: 6 tokens</li><li>mean: 12.73 tokens</li><li>max: 27 tokens</li></ul> | <ul><li>min: 10 tokens</li><li>mean: 22.42 tokens</li><li>max: 65 tokens</li></ul> | <ul><li>min: 0.02</li><li>mean: 0.53</li><li>max: 1.0</li></ul> |
|
244 |
+
* Samples:
|
245 |
+
| question | answer | score |
|
246 |
+
|:-----------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------|
|
247 |
+
| <code>Can you describe the process of robot path planning?</code> | <code>Robots can be programmed to perform a variety of tasks, from simple repetitive actions to complex decision-making processes.</code> | <code>0.27999999999999997</code> |
|
248 |
+
| <code>Can humans live on Mars?</code> | <code>Mars is the fourth planet from the Sun and is often called the Red Planet due to its reddish appearance.</code> | <code>0.16</code> |
|
249 |
+
| <code>What are the key elements of composition in abstract art?</code> | <code>The history of abstract art dates back to the early 20th century, with pioneers like Wassily Kandinsky and Piet Mondrian.</code> | <code>0.36</code> |
|
250 |
+
* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
|
251 |
+
```json
|
252 |
+
{
|
253 |
+
"loss_fct": "torch.nn.modules.loss.MSELoss"
|
254 |
+
}
|
255 |
+
```
|
256 |
+
|
257 |
+
### Evaluation Dataset
|
258 |
+
|
259 |
+
#### Mihaiii/qa-assistant-2
|
260 |
+
|
261 |
+
* Dataset: [Mihaiii/qa-assistant-2](https://huggingface.co/datasets/Mihaiii/qa-assistant-2) at [9650e69](https://huggingface.co/datasets/Mihaiii/qa-assistant-2/tree/9650e69ae0a030fa74a8706a20a168a613c43241)
|
262 |
+
* Size: 3,879 evaluation samples
|
263 |
+
* Columns: <code>question</code>, <code>answer</code>, and <code>score</code>
|
264 |
+
* Approximate statistics based on the first 1000 samples:
|
265 |
+
| | question | answer | score |
|
266 |
+
|:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------|
|
267 |
+
| type | string | string | float |
|
268 |
+
| details | <ul><li>min: 7 tokens</li><li>mean: 12.71 tokens</li><li>max: 31 tokens</li></ul> | <ul><li>min: 10 tokens</li><li>mean: 22.63 tokens</li><li>max: 51 tokens</li></ul> | <ul><li>min: 0.02</li><li>mean: 0.53</li><li>max: 1.0</li></ul> |
|
269 |
+
* Samples:
|
270 |
+
| question | answer | score |
|
271 |
+
|:-------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------|
|
272 |
+
| <code>What is the concept of social stratification?</code> | <code>The study of social stratification involves examining the inequalities and divisions within a society.</code> | <code>0.6799999999999999</code> |
|
273 |
+
| <code>How does J.K. Rowling develop the character of Hermione Granger throughout the 'Harry Potter' series?</code> | <code>The 'Harry Potter' series consists of seven books, starting with 'Harry Potter and the Philosopher's Stone' and ending with 'Harry Potter and the Deathly Hallows'.</code> | <code>0.22000000000000003</code> |
|
274 |
+
| <code>What is the parliamentary system and how does it function?</code> | <code>In a parliamentary system, the government can be dissolved by a vote of no confidence, which can lead to new elections.</code> | <code>0.6799999999999999</code> |
|
275 |
+
* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
|
276 |
+
```json
|
277 |
+
{
|
278 |
+
"loss_fct": "torch.nn.modules.loss.MSELoss"
|
279 |
+
}
|
280 |
+
```
|
281 |
+
|
282 |
+
### Training Hyperparameters
|
283 |
+
#### Non-Default Hyperparameters
|
284 |
+
|
285 |
+
- `eval_strategy`: steps
|
286 |
+
- `per_device_train_batch_size`: 16
|
287 |
+
- `per_device_eval_batch_size`: 16
|
288 |
+
- `num_train_epochs`: 4
|
289 |
+
- `warmup_ratio`: 0.1
|
290 |
+
|
291 |
+
#### All Hyperparameters
|
292 |
+
<details><summary>Click to expand</summary>
|
293 |
+
|
294 |
+
- `overwrite_output_dir`: False
|
295 |
+
- `do_predict`: False
|
296 |
+
- `eval_strategy`: steps
|
297 |
+
- `prediction_loss_only`: True
|
298 |
+
- `per_device_train_batch_size`: 16
|
299 |
+
- `per_device_eval_batch_size`: 16
|
300 |
+
- `per_gpu_train_batch_size`: None
|
301 |
+
- `per_gpu_eval_batch_size`: None
|
302 |
+
- `gradient_accumulation_steps`: 1
|
303 |
+
- `eval_accumulation_steps`: None
|
304 |
+
- `learning_rate`: 5e-05
|
305 |
+
- `weight_decay`: 0.0
|
306 |
+
- `adam_beta1`: 0.9
|
307 |
+
- `adam_beta2`: 0.999
|
308 |
+
- `adam_epsilon`: 1e-08
|
309 |
+
- `max_grad_norm`: 1.0
|
310 |
+
- `num_train_epochs`: 4
|
311 |
+
- `max_steps`: -1
|
312 |
+
- `lr_scheduler_type`: linear
|
313 |
+
- `lr_scheduler_kwargs`: {}
|
314 |
+
- `warmup_ratio`: 0.1
|
315 |
+
- `warmup_steps`: 0
|
316 |
+
- `log_level`: passive
|
317 |
+
- `log_level_replica`: warning
|
318 |
+
- `log_on_each_node`: True
|
319 |
+
- `logging_nan_inf_filter`: True
|
320 |
+
- `save_safetensors`: True
|
321 |
+
- `save_on_each_node`: False
|
322 |
+
- `save_only_model`: False
|
323 |
+
- `restore_callback_states_from_checkpoint`: False
|
324 |
+
- `no_cuda`: False
|
325 |
+
- `use_cpu`: False
|
326 |
+
- `use_mps_device`: False
|
327 |
+
- `seed`: 42
|
328 |
+
- `data_seed`: None
|
329 |
+
- `jit_mode_eval`: False
|
330 |
+
- `use_ipex`: False
|
331 |
+
- `bf16`: False
|
332 |
+
- `fp16`: False
|
333 |
+
- `fp16_opt_level`: O1
|
334 |
+
- `half_precision_backend`: auto
|
335 |
+
- `bf16_full_eval`: False
|
336 |
+
- `fp16_full_eval`: False
|
337 |
+
- `tf32`: None
|
338 |
+
- `local_rank`: 0
|
339 |
+
- `ddp_backend`: None
|
340 |
+
- `tpu_num_cores`: None
|
341 |
+
- `tpu_metrics_debug`: False
|
342 |
+
- `debug`: []
|
343 |
+
- `dataloader_drop_last`: False
|
344 |
+
- `dataloader_num_workers`: 0
|
345 |
+
- `dataloader_prefetch_factor`: None
|
346 |
+
- `past_index`: -1
|
347 |
+
- `disable_tqdm`: False
|
348 |
+
- `remove_unused_columns`: True
|
349 |
+
- `label_names`: None
|
350 |
+
- `load_best_model_at_end`: False
|
351 |
+
- `ignore_data_skip`: False
|
352 |
+
- `fsdp`: []
|
353 |
+
- `fsdp_min_num_params`: 0
|
354 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
355 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
356 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
357 |
+
- `deepspeed`: None
|
358 |
+
- `label_smoothing_factor`: 0.0
|
359 |
+
- `optim`: adamw_torch
|
360 |
+
- `optim_args`: None
|
361 |
+
- `adafactor`: False
|
362 |
+
- `group_by_length`: False
|
363 |
+
- `length_column_name`: length
|
364 |
+
- `ddp_find_unused_parameters`: None
|
365 |
+
- `ddp_bucket_cap_mb`: None
|
366 |
+
- `ddp_broadcast_buffers`: False
|
367 |
+
- `dataloader_pin_memory`: True
|
368 |
+
- `dataloader_persistent_workers`: False
|
369 |
+
- `skip_memory_metrics`: True
|
370 |
+
- `use_legacy_prediction_loop`: False
|
371 |
+
- `push_to_hub`: False
|
372 |
+
- `resume_from_checkpoint`: None
|
373 |
+
- `hub_model_id`: None
|
374 |
+
- `hub_strategy`: every_save
|
375 |
+
- `hub_private_repo`: False
|
376 |
+
- `hub_always_push`: False
|
377 |
+
- `gradient_checkpointing`: False
|
378 |
+
- `gradient_checkpointing_kwargs`: None
|
379 |
+
- `include_inputs_for_metrics`: False
|
380 |
+
- `eval_do_concat_batches`: True
|
381 |
+
- `fp16_backend`: auto
|
382 |
+
- `push_to_hub_model_id`: None
|
383 |
+
- `push_to_hub_organization`: None
|
384 |
+
- `mp_parameters`:
|
385 |
+
- `auto_find_batch_size`: False
|
386 |
+
- `full_determinism`: False
|
387 |
+
- `torchdynamo`: None
|
388 |
+
- `ray_scope`: last
|
389 |
+
- `ddp_timeout`: 1800
|
390 |
+
- `torch_compile`: False
|
391 |
+
- `torch_compile_backend`: None
|
392 |
+
- `torch_compile_mode`: None
|
393 |
+
- `dispatch_batches`: None
|
394 |
+
- `split_batches`: None
|
395 |
+
- `include_tokens_per_second`: False
|
396 |
+
- `include_num_input_tokens_seen`: False
|
397 |
+
- `neftune_noise_alpha`: None
|
398 |
+
- `optim_target_modules`: None
|
399 |
+
- `batch_eval_metrics`: False
|
400 |
+
- `batch_sampler`: batch_sampler
|
401 |
+
- `multi_dataset_batch_sampler`: proportional
|
402 |
+
|
403 |
+
</details>
|
404 |
+
|
405 |
+
### Training Logs
|
406 |
+
| Epoch | Step | Training Loss | loss | sts-dev_spearman_cosine |
|
407 |
+
|:------:|:----:|:-------------:|:------:|:-----------------------:|
|
408 |
+
| 0.0999 | 100 | 0.0593 | 0.0540 | 0.5848 |
|
409 |
+
| 0.1998 | 200 | 0.05 | 0.0463 | 0.6618 |
|
410 |
+
| 0.2997 | 300 | 0.044 | 0.0418 | 0.7102 |
|
411 |
+
| 0.3996 | 400 | 0.0413 | 0.0385 | 0.7390 |
|
412 |
+
| 0.4995 | 500 | 0.0377 | 0.0349 | 0.7707 |
|
413 |
+
| 0.5994 | 600 | 0.034 | 0.0333 | 0.7770 |
|
414 |
+
| 0.6993 | 700 | 0.0344 | 0.0321 | 0.7879 |
|
415 |
+
| 0.7992 | 800 | 0.0324 | 0.0311 | 0.7927 |
|
416 |
+
| 0.8991 | 900 | 0.0334 | 0.0302 | 0.8005 |
|
417 |
+
| 0.9990 | 1000 | 0.0304 | 0.0305 | 0.8023 |
|
418 |
+
| 1.0989 | 1100 | 0.0261 | 0.0306 | 0.8072 |
|
419 |
+
| 1.1988 | 1200 | 0.0267 | 0.0292 | 0.8104 |
|
420 |
+
| 1.2987 | 1300 | 0.0244 | 0.0287 | 0.8110 |
|
421 |
+
| 1.3986 | 1400 | 0.0272 | 0.0294 | 0.8098 |
|
422 |
+
| 1.4985 | 1500 | 0.0241 | 0.0281 | 0.8135 |
|
423 |
+
| 1.5984 | 1600 | 0.0253 | 0.0282 | 0.8143 |
|
424 |
+
| 1.6983 | 1700 | 0.0245 | 0.0276 | 0.8169 |
|
425 |
+
| 1.7982 | 1800 | 0.025 | 0.0274 | 0.8182 |
|
426 |
+
| 1.8981 | 1900 | 0.0236 | 0.0273 | 0.8193 |
|
427 |
+
| 1.9980 | 2000 | 0.0236 | 0.0269 | 0.8218 |
|
428 |
+
| 2.0979 | 2100 | 0.0215 | 0.0278 | 0.8213 |
|
429 |
+
| 2.1978 | 2200 | 0.0216 | 0.0269 | 0.8226 |
|
430 |
+
| 2.2977 | 2300 | 0.0205 | 0.0276 | 0.8207 |
|
431 |
+
| 2.3976 | 2400 | 0.0181 | 0.0273 | 0.8202 |
|
432 |
+
| 2.4975 | 2500 | 0.0197 | 0.0267 | 0.8228 |
|
433 |
+
| 2.5974 | 2600 | 0.02 | 0.0267 | 0.8238 |
|
434 |
+
| 2.6973 | 2700 | 0.0203 | 0.0263 | 0.8258 |
|
435 |
+
| 2.7972 | 2800 | 0.0184 | 0.0263 | 0.8264 |
|
436 |
+
| 2.8971 | 2900 | 0.0201 | 0.0269 | 0.8243 |
|
437 |
+
| 2.9970 | 3000 | 0.0196 | 0.0263 | 0.8251 |
|
438 |
+
| 3.0969 | 3100 | 0.0168 | 0.0264 | 0.8250 |
|
439 |
+
| 3.1968 | 3200 | 0.0176 | 0.0263 | 0.8267 |
|
440 |
+
| 3.2967 | 3300 | 0.0168 | 0.0263 | 0.8270 |
|
441 |
+
| 3.3966 | 3400 | 0.017 | 0.0260 | 0.8277 |
|
442 |
+
| 3.4965 | 3500 | 0.0164 | 0.0261 | 0.8273 |
|
443 |
+
| 3.5964 | 3600 | 0.0172 | 0.0259 | 0.8280 |
|
444 |
+
| 3.6963 | 3700 | 0.0168 | 0.0260 | 0.8274 |
|
445 |
+
| 3.7962 | 3800 | 0.0176 | 0.0262 | 0.8279 |
|
446 |
+
| 3.8961 | 3900 | 0.0182 | 0.0261 | 0.8278 |
|
447 |
+
| 3.9960 | 4000 | 0.0174 | 0.0260 | 0.8277 |
|
448 |
+
|
449 |
+
|
450 |
+
### Framework Versions
|
451 |
+
- Python: 3.10.12
|
452 |
+
- Sentence Transformers: 3.0.1
|
453 |
+
- Transformers: 4.41.2
|
454 |
+
- PyTorch: 2.0.1+cu118
|
455 |
+
- Accelerate: 0.31.0
|
456 |
+
- Datasets: 2.20.0
|
457 |
+
- Tokenizers: 0.19.1
|
458 |
+
|
459 |
+
## Citation
|
460 |
+
|
461 |
+
### BibTeX
|
462 |
+
|
463 |
+
#### Sentence Transformers
|
464 |
+
```bibtex
|
465 |
+
@inproceedings{reimers-2019-sentence-bert,
|
466 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
467 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
468 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
469 |
+
month = "11",
|
470 |
+
year = "2019",
|
471 |
+
publisher = "Association for Computational Linguistics",
|
472 |
+
url = "https://arxiv.org/abs/1908.10084",
|
473 |
+
}
|
474 |
+
```
|
475 |
+
|
476 |
+
<!--
|
477 |
+
## Glossary
|
478 |
+
|
479 |
+
*Clearly define terms in order to be accessible across audiences.*
|
480 |
+
-->
|
481 |
+
|
482 |
+
<!--
|
483 |
+
## Model Card Authors
|
484 |
+
|
485 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
486 |
+
-->
|
487 |
+
|
488 |
+
<!--
|
489 |
+
## Model Card Contact
|
490 |
+
|
491 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
492 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Mihaiii/Venusaur",
|
3 |
+
"architectures": [
|
4 |
+
"BertModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 384,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 1536,
|
13 |
+
"layer_norm_eps": 1e-12,
|
14 |
+
"max_position_embeddings": 512,
|
15 |
+
"model_type": "bert",
|
16 |
+
"num_attention_heads": 12,
|
17 |
+
"num_hidden_layers": 2,
|
18 |
+
"pad_token_id": 0,
|
19 |
+
"position_embedding_type": "absolute",
|
20 |
+
"torch_dtype": "float32",
|
21 |
+
"transformers_version": "4.41.2",
|
22 |
+
"type_vocab_size": 2,
|
23 |
+
"use_cache": true,
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "3.0.1",
|
4 |
+
"transformers": "4.41.2",
|
5 |
+
"pytorch": "2.0.1+cu118"
|
6 |
+
},
|
7 |
+
"prompts": {},
|
8 |
+
"default_prompt_name": null,
|
9 |
+
"similarity_fn_name": null
|
10 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b7fba5907abae73be1381971d33455a4d60264dedc2143d95301cd1733d75dc
|
3 |
+
size 62465680
|
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 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"[PAD]",
|
4 |
+
"[UNK]",
|
5 |
+
"[CLS]",
|
6 |
+
"[SEP]",
|
7 |
+
"[MASK]"
|
8 |
+
],
|
9 |
+
"cls_token": {
|
10 |
+
"content": "[CLS]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"mask_token": {
|
17 |
+
"content": "[MASK]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"pad_token": {
|
24 |
+
"content": "[PAD]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"sep_token": {
|
31 |
+
"content": "[SEP]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"unk_token": {
|
38 |
+
"content": "[UNK]",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
}
|
44 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"additional_special_tokens": [
|
45 |
+
"[PAD]",
|
46 |
+
"[UNK]",
|
47 |
+
"[CLS]",
|
48 |
+
"[SEP]",
|
49 |
+
"[MASK]"
|
50 |
+
],
|
51 |
+
"clean_up_tokenization_spaces": true,
|
52 |
+
"cls_token": "[CLS]",
|
53 |
+
"do_basic_tokenize": true,
|
54 |
+
"do_lower_case": true,
|
55 |
+
"mask_token": "[MASK]",
|
56 |
+
"max_length": 128,
|
57 |
+
"model_max_length": 512,
|
58 |
+
"never_split": null,
|
59 |
+
"pad_to_multiple_of": null,
|
60 |
+
"pad_token": "[PAD]",
|
61 |
+
"pad_token_type_id": 0,
|
62 |
+
"padding_side": "right",
|
63 |
+
"sep_token": "[SEP]",
|
64 |
+
"stride": 0,
|
65 |
+
"strip_accents": null,
|
66 |
+
"tokenize_chinese_chars": true,
|
67 |
+
"tokenizer_class": "BertTokenizer",
|
68 |
+
"truncation_side": "right",
|
69 |
+
"truncation_strategy": "longest_first",
|
70 |
+
"unk_token": "[UNK]"
|
71 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|