Add new SentenceTransformer model
Browse files- 1_Pooling/config.json +10 -0
- 2_Dense/config.json +1 -0
- 2_Dense/model.safetensors +3 -0
- README.md +481 -0
- config_sentence_transformers.json +10 -0
- modules.json +26 -0
- sentence_bert_config.json +4 -0
1_Pooling/config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"word_embedding_dimension": 768,
|
3 |
+
"pooling_mode_cls_token": true,
|
4 |
+
"pooling_mode_mean_tokens": false,
|
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 |
+
}
|
2_Dense/config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"in_features": 768, "out_features": 768, "bias": true, "activation_function": "torch.nn.modules.activation.Tanh"}
|
2_Dense/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5bcb5d1eea5908bf875da44f0b651a84185d1fc087a5e0c4db9d986b016e65f2
|
3 |
+
size 2362528
|
README.md
ADDED
@@ -0,0 +1,481 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- sentence-transformers
|
4 |
+
- sentence-similarity
|
5 |
+
- feature-extraction
|
6 |
+
- generated_from_trainer
|
7 |
+
- dataset_size:131157
|
8 |
+
- loss:MultipleNegativesRankingLoss
|
9 |
+
base_model: sentence-transformers/LaBSE
|
10 |
+
widget:
|
11 |
+
- source_sentence: عواقب ممنوعیت یادداشت های 500 روپیه و 1000 روپیه در مورد اقتصاد
|
12 |
+
هند چیست؟
|
13 |
+
sentences:
|
14 |
+
- آیا باید در فیزیک و علوم کامپیوتر دو برابر کنم؟
|
15 |
+
- چگونه اقتصاد هند پس از ممنوعیت 500 1000 یادداشت تحت تأثیر قرار گرفت؟
|
16 |
+
- آیا آلمان در اجازه پناهندگان سوری به کشور خود اشتباه کرد؟
|
17 |
+
- source_sentence: بهترین شماره پشتیبانی فنی QuickBooks در نیویورک ، ایالات متحده
|
18 |
+
کدام است؟
|
19 |
+
sentences:
|
20 |
+
- فناوری هایی که اکثر مردم از آنها نمی دانند چیست؟
|
21 |
+
- بهترین شماره پشتیبانی QuickBooks در آرکانزاس چیست؟
|
22 |
+
- چرا در مقایسه با طرف نزدیک ، دهانه های زیادی در قسمت دور ماه وجود دارد؟
|
23 |
+
- source_sentence: اقدامات احتیاطی ایمنی در مورد استفاده از اسلحه های پیشنهادی NRA
|
24 |
+
در میشیگان چیست؟
|
25 |
+
sentences:
|
26 |
+
- پیروزی ترامپ چگونه بر کانادا تأثیر خواهد گذاشت؟
|
27 |
+
- اقدامات احتیاطی ایمنی در مورد استفاده از اسلحه های پیشنهادی NRA در آیداهو چیست؟
|
28 |
+
- مزایای خرید بیمه عمر چیست؟
|
29 |
+
- source_sentence: چرا این همه افراد ناراضی هستند؟
|
30 |
+
sentences:
|
31 |
+
- چرا آب نبات تافی آب شور در مغولستان وارد می شود؟
|
32 |
+
- برای یک رابطه موفق از راه دور چه چیزی طول می کشد؟
|
33 |
+
- چرا مردم ناراضی هستند؟
|
34 |
+
- source_sentence: برای تبدیل شدن به نویسنده برتر Quora ، چند بازدید و پاسخ لازم است؟
|
35 |
+
sentences:
|
36 |
+
- چگونه می توانم نویسنده برتر Quora شوم ، از صعود بیشتر و آمار بهتر استفاده کنم؟
|
37 |
+
- چرا بسیاری از افرادی که سؤالاتی را در Quora ارسال می کنند ، ابتدا Google را بررسی
|
38 |
+
می کنند؟
|
39 |
+
- من به دنبال خرید دوچرخه جدید هستم.Suzuki Gixxer 155 یا Honda Hornet 160r.کدام
|
40 |
+
یک را بخرید؟
|
41 |
+
pipeline_tag: sentence-similarity
|
42 |
+
library_name: sentence-transformers
|
43 |
+
---
|
44 |
+
|
45 |
+
# SentenceTransformer based on sentence-transformers/LaBSE
|
46 |
+
|
47 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/LaBSE](https://huggingface.co/sentence-transformers/LaBSE). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
|
48 |
+
|
49 |
+
## Model Details
|
50 |
+
|
51 |
+
### Model Description
|
52 |
+
- **Model Type:** Sentence Transformer
|
53 |
+
- **Base model:** [sentence-transformers/LaBSE](https://huggingface.co/sentence-transformers/LaBSE) <!-- at revision 836121a0533e5664b21c7aacc5d22951f2b8b25b -->
|
54 |
+
- **Maximum Sequence Length:** 256 tokens
|
55 |
+
- **Output Dimensionality:** 768 dimensions
|
56 |
+
- **Similarity Function:** Cosine Similarity
|
57 |
+
<!-- - **Training Dataset:** Unknown -->
|
58 |
+
<!-- - **Language:** Unknown -->
|
59 |
+
<!-- - **License:** Unknown -->
|
60 |
+
|
61 |
+
### Model Sources
|
62 |
+
|
63 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
64 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
65 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
66 |
+
|
67 |
+
### Full Model Architecture
|
68 |
+
|
69 |
+
```
|
70 |
+
SentenceTransformer(
|
71 |
+
(0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: BertModel
|
72 |
+
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
|
73 |
+
(2): Dense({'in_features': 768, 'out_features': 768, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
|
74 |
+
(3): Normalize()
|
75 |
+
)
|
76 |
+
```
|
77 |
+
|
78 |
+
## Usage
|
79 |
+
|
80 |
+
### Direct Usage (Sentence Transformers)
|
81 |
+
|
82 |
+
First install the Sentence Transformers library:
|
83 |
+
|
84 |
+
```bash
|
85 |
+
pip install -U sentence-transformers
|
86 |
+
```
|
87 |
+
|
88 |
+
Then you can load this model and run inference.
|
89 |
+
```python
|
90 |
+
from sentence_transformers import SentenceTransformer
|
91 |
+
|
92 |
+
# Download from the 🤗 Hub
|
93 |
+
model = SentenceTransformer("codersan/validadted_falabse_onV9f")
|
94 |
+
# Run inference
|
95 |
+
sentences = [
|
96 |
+
'برای تبدیل شدن به نویسنده برتر Quora ، چند بازدید و پاسخ لازم است؟',
|
97 |
+
'چگونه می توانم نویسند�� برتر Quora شوم ، از صعود بیشتر و آمار بهتر استفاده کنم؟',
|
98 |
+
'من به دنبال خرید دوچرخه جدید هستم.Suzuki Gixxer 155 یا Honda Hornet 160r.کدام یک را بخرید؟',
|
99 |
+
]
|
100 |
+
embeddings = model.encode(sentences)
|
101 |
+
print(embeddings.shape)
|
102 |
+
# [3, 768]
|
103 |
+
|
104 |
+
# Get the similarity scores for the embeddings
|
105 |
+
similarities = model.similarity(embeddings, embeddings)
|
106 |
+
print(similarities.shape)
|
107 |
+
# [3, 3]
|
108 |
+
```
|
109 |
+
|
110 |
+
<!--
|
111 |
+
### Direct Usage (Transformers)
|
112 |
+
|
113 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
114 |
+
|
115 |
+
</details>
|
116 |
+
-->
|
117 |
+
|
118 |
+
<!--
|
119 |
+
### Downstream Usage (Sentence Transformers)
|
120 |
+
|
121 |
+
You can finetune this model on your own dataset.
|
122 |
+
|
123 |
+
<details><summary>Click to expand</summary>
|
124 |
+
|
125 |
+
</details>
|
126 |
+
-->
|
127 |
+
|
128 |
+
<!--
|
129 |
+
### Out-of-Scope Use
|
130 |
+
|
131 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
132 |
+
-->
|
133 |
+
|
134 |
+
<!--
|
135 |
+
## Bias, Risks and Limitations
|
136 |
+
|
137 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
138 |
+
-->
|
139 |
+
|
140 |
+
<!--
|
141 |
+
### Recommendations
|
142 |
+
|
143 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
144 |
+
-->
|
145 |
+
|
146 |
+
## Training Details
|
147 |
+
|
148 |
+
### Training Dataset
|
149 |
+
|
150 |
+
#### Unnamed Dataset
|
151 |
+
|
152 |
+
|
153 |
+
* Size: 131,157 training samples
|
154 |
+
* Columns: <code>anchor</code> and <code>positive</code>
|
155 |
+
* Approximate statistics based on the first 1000 samples:
|
156 |
+
| | anchor | positive |
|
157 |
+
|:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
|
158 |
+
| type | string | string |
|
159 |
+
| details | <ul><li>min: 6 tokens</li><li>mean: 15.78 tokens</li><li>max: 86 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 15.52 tokens</li><li>max: 57 tokens</li></ul> |
|
160 |
+
* Samples:
|
161 |
+
| anchor | positive |
|
162 |
+
|:----------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------|
|
163 |
+
| <code>وقتی سوال من به عنوان "این سوال ممکن است به ویرایش نیاز داشته باشد" چه کاری باید انجام دهم ، اما نمی توانم دلیل آن را پیدا کنم؟</code> | <code>چرا سوال من به عنوان نیاز به پیشرفت مشخص شده است؟</code> |
|
164 |
+
| <code>چگونه می توانید یک فایل رمزگذاری شده را با دانستن اینکه این یک فایل تصویری است بدون دانستن گسترش پرونده یا کلید ، رمزگشایی کنید؟</code> | <code>چگونه می توانید یک فایل رمزگذاری شده را رمزگشایی کنید و بدانید که این یک فایل تصویری است بدون اینکه از پسوند پرونده اطلاع داشته باشید؟</code> |
|
165 |
+
| <code>احساس می کنم خودکشی می کنم ، چگونه باید با آن برخورد کنم؟</code> | <code>احساس می کنم خودکشی می کنم.چه کاری باید انجام دهم؟</code> |
|
166 |
+
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
|
167 |
+
```json
|
168 |
+
{
|
169 |
+
"scale": 20.0,
|
170 |
+
"similarity_fct": "cos_sim"
|
171 |
+
}
|
172 |
+
```
|
173 |
+
|
174 |
+
### Training Hyperparameters
|
175 |
+
#### Non-Default Hyperparameters
|
176 |
+
|
177 |
+
- `eval_strategy`: steps
|
178 |
+
- `per_device_train_batch_size`: 12
|
179 |
+
- `learning_rate`: 5e-06
|
180 |
+
- `weight_decay`: 0.01
|
181 |
+
- `num_train_epochs`: 1
|
182 |
+
- `warmup_ratio`: 0.1
|
183 |
+
- `push_to_hub`: True
|
184 |
+
- `hub_model_id`: codersan/validadted_falabse_onV9f
|
185 |
+
- `eval_on_start`: True
|
186 |
+
- `batch_sampler`: no_duplicates
|
187 |
+
|
188 |
+
#### All Hyperparameters
|
189 |
+
<details><summary>Click to expand</summary>
|
190 |
+
|
191 |
+
- `overwrite_output_dir`: False
|
192 |
+
- `do_predict`: False
|
193 |
+
- `eval_strategy`: steps
|
194 |
+
- `prediction_loss_only`: True
|
195 |
+
- `per_device_train_batch_size`: 12
|
196 |
+
- `per_device_eval_batch_size`: 8
|
197 |
+
- `per_gpu_train_batch_size`: None
|
198 |
+
- `per_gpu_eval_batch_size`: None
|
199 |
+
- `gradient_accumulation_steps`: 1
|
200 |
+
- `eval_accumulation_steps`: None
|
201 |
+
- `torch_empty_cache_steps`: None
|
202 |
+
- `learning_rate`: 5e-06
|
203 |
+
- `weight_decay`: 0.01
|
204 |
+
- `adam_beta1`: 0.9
|
205 |
+
- `adam_beta2`: 0.999
|
206 |
+
- `adam_epsilon`: 1e-08
|
207 |
+
- `max_grad_norm`: 1
|
208 |
+
- `num_train_epochs`: 1
|
209 |
+
- `max_steps`: -1
|
210 |
+
- `lr_scheduler_type`: linear
|
211 |
+
- `lr_scheduler_kwargs`: {}
|
212 |
+
- `warmup_ratio`: 0.1
|
213 |
+
- `warmup_steps`: 0
|
214 |
+
- `log_level`: passive
|
215 |
+
- `log_level_replica`: warning
|
216 |
+
- `log_on_each_node`: True
|
217 |
+
- `logging_nan_inf_filter`: True
|
218 |
+
- `save_safetensors`: True
|
219 |
+
- `save_on_each_node`: False
|
220 |
+
- `save_only_model`: False
|
221 |
+
- `restore_callback_states_from_checkpoint`: False
|
222 |
+
- `no_cuda`: False
|
223 |
+
- `use_cpu`: False
|
224 |
+
- `use_mps_device`: False
|
225 |
+
- `seed`: 42
|
226 |
+
- `data_seed`: None
|
227 |
+
- `jit_mode_eval`: False
|
228 |
+
- `use_ipex`: False
|
229 |
+
- `bf16`: False
|
230 |
+
- `fp16`: False
|
231 |
+
- `fp16_opt_level`: O1
|
232 |
+
- `half_precision_backend`: auto
|
233 |
+
- `bf16_full_eval`: False
|
234 |
+
- `fp16_full_eval`: False
|
235 |
+
- `tf32`: None
|
236 |
+
- `local_rank`: 0
|
237 |
+
- `ddp_backend`: None
|
238 |
+
- `tpu_num_cores`: None
|
239 |
+
- `tpu_metrics_debug`: False
|
240 |
+
- `debug`: []
|
241 |
+
- `dataloader_drop_last`: False
|
242 |
+
- `dataloader_num_workers`: 0
|
243 |
+
- `dataloader_prefetch_factor`: None
|
244 |
+
- `past_index`: -1
|
245 |
+
- `disable_tqdm`: False
|
246 |
+
- `remove_unused_columns`: True
|
247 |
+
- `label_names`: None
|
248 |
+
- `load_best_model_at_end`: False
|
249 |
+
- `ignore_data_skip`: False
|
250 |
+
- `fsdp`: []
|
251 |
+
- `fsdp_min_num_params`: 0
|
252 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
253 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
254 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
255 |
+
- `deepspeed`: None
|
256 |
+
- `label_smoothing_factor`: 0.0
|
257 |
+
- `optim`: adamw_torch
|
258 |
+
- `optim_args`: None
|
259 |
+
- `adafactor`: False
|
260 |
+
- `group_by_length`: False
|
261 |
+
- `length_column_name`: length
|
262 |
+
- `ddp_find_unused_parameters`: None
|
263 |
+
- `ddp_bucket_cap_mb`: None
|
264 |
+
- `ddp_broadcast_buffers`: False
|
265 |
+
- `dataloader_pin_memory`: True
|
266 |
+
- `dataloader_persistent_workers`: False
|
267 |
+
- `skip_memory_metrics`: True
|
268 |
+
- `use_legacy_prediction_loop`: False
|
269 |
+
- `push_to_hub`: True
|
270 |
+
- `resume_from_checkpoint`: None
|
271 |
+
- `hub_model_id`: codersan/validadted_falabse_onV9f
|
272 |
+
- `hub_strategy`: every_save
|
273 |
+
- `hub_private_repo`: None
|
274 |
+
- `hub_always_push`: False
|
275 |
+
- `gradient_checkpointing`: False
|
276 |
+
- `gradient_checkpointing_kwargs`: None
|
277 |
+
- `include_inputs_for_metrics`: False
|
278 |
+
- `include_for_metrics`: []
|
279 |
+
- `eval_do_concat_batches`: True
|
280 |
+
- `fp16_backend`: auto
|
281 |
+
- `push_to_hub_model_id`: None
|
282 |
+
- `push_to_hub_organization`: None
|
283 |
+
- `mp_parameters`:
|
284 |
+
- `auto_find_batch_size`: False
|
285 |
+
- `full_determinism`: False
|
286 |
+
- `torchdynamo`: None
|
287 |
+
- `ray_scope`: last
|
288 |
+
- `ddp_timeout`: 1800
|
289 |
+
- `torch_compile`: False
|
290 |
+
- `torch_compile_backend`: None
|
291 |
+
- `torch_compile_mode`: None
|
292 |
+
- `dispatch_batches`: None
|
293 |
+
- `split_batches`: None
|
294 |
+
- `include_tokens_per_second`: False
|
295 |
+
- `include_num_input_tokens_seen`: False
|
296 |
+
- `neftune_noise_alpha`: None
|
297 |
+
- `optim_target_modules`: None
|
298 |
+
- `batch_eval_metrics`: False
|
299 |
+
- `eval_on_start`: True
|
300 |
+
- `use_liger_kernel`: False
|
301 |
+
- `eval_use_gather_object`: False
|
302 |
+
- `average_tokens_across_devices`: False
|
303 |
+
- `prompts`: None
|
304 |
+
- `batch_sampler`: no_duplicates
|
305 |
+
- `multi_dataset_batch_sampler`: proportional
|
306 |
+
|
307 |
+
</details>
|
308 |
+
|
309 |
+
### Training Logs
|
310 |
+
<details><summary>Click to expand</summary>
|
311 |
+
|
312 |
+
| Epoch | Step | Training Loss |
|
313 |
+
|:------:|:-----:|:-------------:|
|
314 |
+
| 0 | 0 | - |
|
315 |
+
| 0.0091 | 100 | 0.1214 |
|
316 |
+
| 0.0183 | 200 | 0.0776 |
|
317 |
+
| 0.0274 | 300 | 0.0555 |
|
318 |
+
| 0.0366 | 400 | 0.0507 |
|
319 |
+
| 0.0457 | 500 | 0.0423 |
|
320 |
+
| 0.0549 | 600 | 0.0328 |
|
321 |
+
| 0.0640 | 700 | 0.0391 |
|
322 |
+
| 0.0732 | 800 | 0.0164 |
|
323 |
+
| 0.0823 | 900 | 0.0155 |
|
324 |
+
| 0.0915 | 1000 | 0.0138 |
|
325 |
+
| 0.1006 | 1100 | 0.0219 |
|
326 |
+
| 0.1098 | 1200 | 0.0267 |
|
327 |
+
| 0.1189 | 1300 | 0.0251 |
|
328 |
+
| 0.1281 | 1400 | 0.033 |
|
329 |
+
| 0.1372 | 1500 | 0.0151 |
|
330 |
+
| 0.1464 | 1600 | 0.0129 |
|
331 |
+
| 0.1555 | 1700 | 0.023 |
|
332 |
+
| 0.1647 | 1800 | 0.026 |
|
333 |
+
| 0.1738 | 1900 | 0.0264 |
|
334 |
+
| 0.1830 | 2000 | 0.0105 |
|
335 |
+
| 0.1921 | 2100 | 0.0262 |
|
336 |
+
| 0.2013 | 2200 | 0.0118 |
|
337 |
+
| 0.2104 | 2300 | 0.0223 |
|
338 |
+
| 0.2196 | 2400 | 0.043 |
|
339 |
+
| 0.2287 | 2500 | 0.0187 |
|
340 |
+
| 0.2379 | 2600 | 0.0135 |
|
341 |
+
| 0.2470 | 2700 | 0.0165 |
|
342 |
+
| 0.2562 | 2800 | 0.0191 |
|
343 |
+
| 0.2653 | 2900 | 0.0247 |
|
344 |
+
| 0.2745 | 3000 | 0.0207 |
|
345 |
+
| 0.2836 | 3100 | 0.0213 |
|
346 |
+
| 0.2928 | 3200 | 0.0193 |
|
347 |
+
| 0.3019 | 3300 | 0.0137 |
|
348 |
+
| 0.3111 | 3400 | 0.0208 |
|
349 |
+
| 0.3202 | 3500 | 0.0228 |
|
350 |
+
| 0.3294 | 3600 | 0.0213 |
|
351 |
+
| 0.3385 | 3700 | 0.0184 |
|
352 |
+
| 0.3477 | 3800 | 0.016 |
|
353 |
+
| 0.3568 | 3900 | 0.0131 |
|
354 |
+
| 0.3660 | 4000 | 0.0133 |
|
355 |
+
| 0.3751 | 4100 | 0.0117 |
|
356 |
+
| 0.3843 | 4200 | 0.0201 |
|
357 |
+
| 0.3934 | 4300 | 0.0121 |
|
358 |
+
| 0.4026 | 4400 | 0.0309 |
|
359 |
+
| 0.4117 | 4500 | 0.0177 |
|
360 |
+
| 0.4209 | 4600 | 0.02 |
|
361 |
+
| 0.4300 | 4700 | 0.035 |
|
362 |
+
| 0.4392 | 4800 | 0.0167 |
|
363 |
+
| 0.4483 | 4900 | 0.0108 |
|
364 |
+
| 0.4575 | 5000 | 0.016 |
|
365 |
+
| 0.4666 | 5100 | 0.0158 |
|
366 |
+
| 0.4758 | 5200 | 0.0102 |
|
367 |
+
| 0.4849 | 5300 | 0.0167 |
|
368 |
+
| 0.4941 | 5400 | 0.0252 |
|
369 |
+
| 0.5032 | 5500 | 0.015 |
|
370 |
+
| 0.5124 | 5600 | 0.0321 |
|
371 |
+
| 0.5215 | 5700 | 0.0144 |
|
372 |
+
| 0.5306 | 5800 | 0.0228 |
|
373 |
+
| 0.5398 | 5900 | 0.0222 |
|
374 |
+
| 0.5489 | 6000 | 0.0234 |
|
375 |
+
| 0.5581 | 6100 | 0.0111 |
|
376 |
+
| 0.5672 | 6200 | 0.0265 |
|
377 |
+
| 0.5764 | 6300 | 0.0224 |
|
378 |
+
| 0.5855 | 6400 | 0.0237 |
|
379 |
+
| 0.5947 | 6500 | 0.0289 |
|
380 |
+
| 0.6038 | 6600 | 0.016 |
|
381 |
+
| 0.6130 | 6700 | 0.01 |
|
382 |
+
| 0.6221 | 6800 | 0.0129 |
|
383 |
+
| 0.6313 | 6900 | 0.0201 |
|
384 |
+
| 0.6404 | 7000 | 0.01 |
|
385 |
+
| 0.6496 | 7100 | 0.0126 |
|
386 |
+
| 0.6587 | 7200 | 0.0194 |
|
387 |
+
| 0.6679 | 7300 | 0.0204 |
|
388 |
+
| 0.6770 | 7400 | 0.0203 |
|
389 |
+
| 0.6862 | 7500 | 0.0141 |
|
390 |
+
| 0.6953 | 7600 | 0.015 |
|
391 |
+
| 0.7045 | 7700 | 0.0221 |
|
392 |
+
| 0.7136 | 7800 | 0.0155 |
|
393 |
+
| 0.7228 | 7900 | 0.0142 |
|
394 |
+
| 0.7319 | 8000 | 0.0112 |
|
395 |
+
| 0.7411 | 8100 | 0.0142 |
|
396 |
+
| 0.7502 | 8200 | 0.0141 |
|
397 |
+
| 0.7594 | 8300 | 0.0136 |
|
398 |
+
| 0.7685 | 8400 | 0.0328 |
|
399 |
+
| 0.7777 | 8500 | 0.0103 |
|
400 |
+
| 0.7868 | 8600 | 0.0156 |
|
401 |
+
| 0.7960 | 8700 | 0.0208 |
|
402 |
+
| 0.8051 | 8800 | 0.0262 |
|
403 |
+
| 0.8143 | 8900 | 0.0234 |
|
404 |
+
| 0.8234 | 9000 | 0.0128 |
|
405 |
+
| 0.8326 | 9100 | 0.0125 |
|
406 |
+
| 0.8417 | 9200 | 0.0309 |
|
407 |
+
| 0.8509 | 9300 | 0.012 |
|
408 |
+
| 0.8600 | 9400 | 0.0127 |
|
409 |
+
| 0.8692 | 9500 | 0.0119 |
|
410 |
+
| 0.8783 | 9600 | 0.0297 |
|
411 |
+
| 0.8875 | 9700 | 0.0208 |
|
412 |
+
| 0.8966 | 9800 | 0.0178 |
|
413 |
+
| 0.9058 | 9900 | 0.0216 |
|
414 |
+
| 0.9149 | 10000 | 0.0272 |
|
415 |
+
| 0.9241 | 10100 | 0.021 |
|
416 |
+
| 0.9332 | 10200 | 0.019 |
|
417 |
+
| 0.9424 | 10300 | 0.0104 |
|
418 |
+
| 0.9515 | 10400 | 0.0229 |
|
419 |
+
| 0.9607 | 10500 | 0.0161 |
|
420 |
+
| 0.9698 | 10600 | 0.0161 |
|
421 |
+
| 0.9790 | 10700 | 0.0243 |
|
422 |
+
| 0.9881 | 10800 | 0.0263 |
|
423 |
+
| 0.9973 | 10900 | 0.0112 |
|
424 |
+
|
425 |
+
</details>
|
426 |
+
|
427 |
+
### Framework Versions
|
428 |
+
- Python: 3.10.12
|
429 |
+
- Sentence Transformers: 3.3.1
|
430 |
+
- Transformers: 4.47.0
|
431 |
+
- PyTorch: 2.5.1+cu121
|
432 |
+
- Accelerate: 1.2.1
|
433 |
+
- Datasets: 3.2.0
|
434 |
+
- Tokenizers: 0.21.0
|
435 |
+
|
436 |
+
## Citation
|
437 |
+
|
438 |
+
### BibTeX
|
439 |
+
|
440 |
+
#### Sentence Transformers
|
441 |
+
```bibtex
|
442 |
+
@inproceedings{reimers-2019-sentence-bert,
|
443 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
444 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
445 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
446 |
+
month = "11",
|
447 |
+
year = "2019",
|
448 |
+
publisher = "Association for Computational Linguistics",
|
449 |
+
url = "https://arxiv.org/abs/1908.10084",
|
450 |
+
}
|
451 |
+
```
|
452 |
+
|
453 |
+
#### MultipleNegativesRankingLoss
|
454 |
+
```bibtex
|
455 |
+
@misc{henderson2017efficient,
|
456 |
+
title={Efficient Natural Language Response Suggestion for Smart Reply},
|
457 |
+
author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
|
458 |
+
year={2017},
|
459 |
+
eprint={1705.00652},
|
460 |
+
archivePrefix={arXiv},
|
461 |
+
primaryClass={cs.CL}
|
462 |
+
}
|
463 |
+
```
|
464 |
+
|
465 |
+
<!--
|
466 |
+
## Glossary
|
467 |
+
|
468 |
+
*Clearly define terms in order to be accessible across audiences.*
|
469 |
+
-->
|
470 |
+
|
471 |
+
<!--
|
472 |
+
## Model Card Authors
|
473 |
+
|
474 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
475 |
+
-->
|
476 |
+
|
477 |
+
<!--
|
478 |
+
## Model Card Contact
|
479 |
+
|
480 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
481 |
+
-->
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "3.3.1",
|
4 |
+
"transformers": "4.47.0",
|
5 |
+
"pytorch": "2.5.1+cu121"
|
6 |
+
},
|
7 |
+
"prompts": {},
|
8 |
+
"default_prompt_name": null,
|
9 |
+
"similarity_fn_name": "cosine"
|
10 |
+
}
|
modules.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
{
|
15 |
+
"idx": 2,
|
16 |
+
"name": "2",
|
17 |
+
"path": "2_Dense",
|
18 |
+
"type": "sentence_transformers.models.Dense"
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"idx": 3,
|
22 |
+
"name": "3",
|
23 |
+
"path": "3_Normalize",
|
24 |
+
"type": "sentence_transformers.models.Normalize"
|
25 |
+
}
|
26 |
+
]
|
sentence_bert_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"max_seq_length": 256,
|
3 |
+
"do_lower_case": false
|
4 |
+
}
|