Add new SentenceTransformer model.
Browse files- 1_Pooling/config.json +10 -0
- README.md +540 -0
- config.json +24 -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 +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- vocab.txt +0 -0
1_Pooling/config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"pooling_mode_weightedmean_tokens": false,
|
8 |
+
"pooling_mode_lasttoken": false,
|
9 |
+
"include_prompt": true
|
10 |
+
}
|
README.md
ADDED
@@ -0,0 +1,540 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language: []
|
3 |
+
library_name: sentence-transformers
|
4 |
+
tags:
|
5 |
+
- sentence-transformers
|
6 |
+
- sentence-similarity
|
7 |
+
- feature-extraction
|
8 |
+
- dataset_size:10K<n<100K
|
9 |
+
- loss:MultipleNegativesSymmetricRankingLoss
|
10 |
+
base_model: distilbert/distilbert-base-uncased
|
11 |
+
metrics:
|
12 |
+
- pearson_cosine
|
13 |
+
- spearman_cosine
|
14 |
+
- pearson_manhattan
|
15 |
+
- spearman_manhattan
|
16 |
+
- pearson_euclidean
|
17 |
+
- spearman_euclidean
|
18 |
+
- pearson_dot
|
19 |
+
- spearman_dot
|
20 |
+
- pearson_max
|
21 |
+
- spearman_max
|
22 |
+
widget:
|
23 |
+
- source_sentence: what is GOGO
|
24 |
+
sentences:
|
25 |
+
- What is Viasat
|
26 |
+
- are we flying into Tel Aviv
|
27 |
+
- how do i correct a name in term
|
28 |
+
- source_sentence: What is EU 261
|
29 |
+
sentences:
|
30 |
+
- is puj a EU compensation country
|
31 |
+
- can i take my bicycle on af
|
32 |
+
- flight delays over 6 hours
|
33 |
+
- source_sentence: Can i get wifi
|
34 |
+
sentences:
|
35 |
+
- which aircrafts do not have wifi
|
36 |
+
- military traveling with pet
|
37 |
+
- baggage delay to carousel
|
38 |
+
- source_sentence: austin airport
|
39 |
+
sentences:
|
40 |
+
- What time is IAH open
|
41 |
+
- amex card free checked bag
|
42 |
+
- what is upgrade companion
|
43 |
+
- source_sentence: pets in cargo
|
44 |
+
sentences:
|
45 |
+
- can a pet travel in cargo
|
46 |
+
- baggage exceptions for Amex
|
47 |
+
- how do I get sky priority
|
48 |
+
pipeline_tag: sentence-similarity
|
49 |
+
model-index:
|
50 |
+
- name: SentenceTransformer based on distilbert/distilbert-base-uncased
|
51 |
+
results:
|
52 |
+
- task:
|
53 |
+
type: semantic-similarity
|
54 |
+
name: Semantic Similarity
|
55 |
+
dataset:
|
56 |
+
name: eval examples
|
57 |
+
type: eval_examples
|
58 |
+
metrics:
|
59 |
+
- type: pearson_cosine
|
60 |
+
value: .nan
|
61 |
+
name: Pearson Cosine
|
62 |
+
- type: spearman_cosine
|
63 |
+
value: .nan
|
64 |
+
name: Spearman Cosine
|
65 |
+
- type: pearson_manhattan
|
66 |
+
value: .nan
|
67 |
+
name: Pearson Manhattan
|
68 |
+
- type: spearman_manhattan
|
69 |
+
value: .nan
|
70 |
+
name: Spearman Manhattan
|
71 |
+
- type: pearson_euclidean
|
72 |
+
value: .nan
|
73 |
+
name: Pearson Euclidean
|
74 |
+
- type: spearman_euclidean
|
75 |
+
value: .nan
|
76 |
+
name: Spearman Euclidean
|
77 |
+
- type: pearson_dot
|
78 |
+
value: .nan
|
79 |
+
name: Pearson Dot
|
80 |
+
- type: spearman_dot
|
81 |
+
value: .nan
|
82 |
+
name: Spearman Dot
|
83 |
+
- type: pearson_max
|
84 |
+
value: .nan
|
85 |
+
name: Pearson Max
|
86 |
+
- type: spearman_max
|
87 |
+
value: .nan
|
88 |
+
name: Spearman Max
|
89 |
+
---
|
90 |
+
|
91 |
+
# SentenceTransformer based on distilbert/distilbert-base-uncased
|
92 |
+
|
93 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased). 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.
|
94 |
+
|
95 |
+
## Model Details
|
96 |
+
|
97 |
+
### Model Description
|
98 |
+
- **Model Type:** Sentence Transformer
|
99 |
+
- **Base model:** [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) <!-- at revision 12040accade4e8a0f71eabdb258fecc2e7e948be -->
|
100 |
+
- **Maximum Sequence Length:** 512 tokens
|
101 |
+
- **Output Dimensionality:** 768 tokens
|
102 |
+
- **Similarity Function:** Cosine Similarity
|
103 |
+
<!-- - **Training Dataset:** Unknown -->
|
104 |
+
<!-- - **Language:** Unknown -->
|
105 |
+
<!-- - **License:** Unknown -->
|
106 |
+
|
107 |
+
### Model Sources
|
108 |
+
|
109 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
110 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
111 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
112 |
+
|
113 |
+
### Full Model Architecture
|
114 |
+
|
115 |
+
```
|
116 |
+
SentenceTransformer(
|
117 |
+
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: DistilBertModel
|
118 |
+
(1): Pooling({'word_embedding_dimension': 768, '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})
|
119 |
+
)
|
120 |
+
```
|
121 |
+
|
122 |
+
## Usage
|
123 |
+
|
124 |
+
### Direct Usage (Sentence Transformers)
|
125 |
+
|
126 |
+
First install the Sentence Transformers library:
|
127 |
+
|
128 |
+
```bash
|
129 |
+
pip install -U sentence-transformers
|
130 |
+
```
|
131 |
+
|
132 |
+
Then you can load this model and run inference.
|
133 |
+
```python
|
134 |
+
from sentence_transformers import SentenceTransformer
|
135 |
+
|
136 |
+
# Download from the 🤗 Hub
|
137 |
+
model = SentenceTransformer("pjbhaumik/biencoder-finetune-model-v9")
|
138 |
+
# Run inference
|
139 |
+
sentences = [
|
140 |
+
'pets in cargo',
|
141 |
+
'can a pet travel in cargo',
|
142 |
+
'baggage exceptions for Amex',
|
143 |
+
]
|
144 |
+
embeddings = model.encode(sentences)
|
145 |
+
print(embeddings.shape)
|
146 |
+
# [3, 768]
|
147 |
+
|
148 |
+
# Get the similarity scores for the embeddings
|
149 |
+
similarities = model.similarity(embeddings, embeddings)
|
150 |
+
print(similarities.shape)
|
151 |
+
# [3, 3]
|
152 |
+
```
|
153 |
+
|
154 |
+
<!--
|
155 |
+
### Direct Usage (Transformers)
|
156 |
+
|
157 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
158 |
+
|
159 |
+
</details>
|
160 |
+
-->
|
161 |
+
|
162 |
+
<!--
|
163 |
+
### Downstream Usage (Sentence Transformers)
|
164 |
+
|
165 |
+
You can finetune this model on your own dataset.
|
166 |
+
|
167 |
+
<details><summary>Click to expand</summary>
|
168 |
+
|
169 |
+
</details>
|
170 |
+
-->
|
171 |
+
|
172 |
+
<!--
|
173 |
+
### Out-of-Scope Use
|
174 |
+
|
175 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
176 |
+
-->
|
177 |
+
|
178 |
+
## Evaluation
|
179 |
+
|
180 |
+
### Metrics
|
181 |
+
|
182 |
+
#### Semantic Similarity
|
183 |
+
* Dataset: `eval_examples`
|
184 |
+
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
|
185 |
+
|
186 |
+
| Metric | Value |
|
187 |
+
|:-------------------|:--------|
|
188 |
+
| pearson_cosine | nan |
|
189 |
+
| spearman_cosine | nan |
|
190 |
+
| pearson_manhattan | nan |
|
191 |
+
| spearman_manhattan | nan |
|
192 |
+
| pearson_euclidean | nan |
|
193 |
+
| spearman_euclidean | nan |
|
194 |
+
| pearson_dot | nan |
|
195 |
+
| spearman_dot | nan |
|
196 |
+
| pearson_max | nan |
|
197 |
+
| **spearman_max** | **nan** |
|
198 |
+
|
199 |
+
<!--
|
200 |
+
## Bias, Risks and Limitations
|
201 |
+
|
202 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
203 |
+
-->
|
204 |
+
|
205 |
+
<!--
|
206 |
+
### Recommendations
|
207 |
+
|
208 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
209 |
+
-->
|
210 |
+
|
211 |
+
## Training Details
|
212 |
+
|
213 |
+
### Training Dataset
|
214 |
+
|
215 |
+
#### Unnamed Dataset
|
216 |
+
|
217 |
+
|
218 |
+
* Size: 15,488 training samples
|
219 |
+
* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code>
|
220 |
+
* Approximate statistics based on the first 1000 samples:
|
221 |
+
| | sentence_0 | sentence_1 | label |
|
222 |
+
|:--------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:-----------------------------|
|
223 |
+
| type | string | string | int |
|
224 |
+
| details | <ul><li>min: 4 tokens</li><li>mean: 10.4 tokens</li><li>max: 47 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 10.14 tokens</li><li>max: 37 tokens</li></ul> | <ul><li>1: 100.00%</li></ul> |
|
225 |
+
* Samples:
|
226 |
+
| sentence_0 | sentence_1 | label |
|
227 |
+
|:-----------------------------------------------------------------|:-------------------------------------------------------------------------------------|:---------------|
|
228 |
+
| <code>how to use a companion certificate on delta.com</code> | <code>SHOPPING ON DELTA.COM FOR AMEX CERT</code> | <code>1</code> |
|
229 |
+
| <code>is jamaica can be booked with companion certificate</code> | <code>what areas can the American Express companion certificate be applied to</code> | <code>1</code> |
|
230 |
+
| <code>how do i book award travel on klm</code> | <code>can you book an air france ticket with miles</code> | <code>1</code> |
|
231 |
+
* Loss: [<code>MultipleNegativesSymmetricRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativessymmetricrankingloss) with these parameters:
|
232 |
+
```json
|
233 |
+
{
|
234 |
+
"scale": 20.0,
|
235 |
+
"similarity_fct": "cos_sim"
|
236 |
+
}
|
237 |
+
```
|
238 |
+
|
239 |
+
### Training Hyperparameters
|
240 |
+
#### Non-Default Hyperparameters
|
241 |
+
|
242 |
+
- `eval_strategy`: steps
|
243 |
+
- `per_device_train_batch_size`: 16
|
244 |
+
- `per_device_eval_batch_size`: 16
|
245 |
+
- `num_train_epochs`: 12
|
246 |
+
- `multi_dataset_batch_sampler`: round_robin
|
247 |
+
|
248 |
+
#### All Hyperparameters
|
249 |
+
<details><summary>Click to expand</summary>
|
250 |
+
|
251 |
+
- `overwrite_output_dir`: False
|
252 |
+
- `do_predict`: False
|
253 |
+
- `eval_strategy`: steps
|
254 |
+
- `prediction_loss_only`: True
|
255 |
+
- `per_device_train_batch_size`: 16
|
256 |
+
- `per_device_eval_batch_size`: 16
|
257 |
+
- `per_gpu_train_batch_size`: None
|
258 |
+
- `per_gpu_eval_batch_size`: None
|
259 |
+
- `gradient_accumulation_steps`: 1
|
260 |
+
- `eval_accumulation_steps`: None
|
261 |
+
- `learning_rate`: 5e-05
|
262 |
+
- `weight_decay`: 0.0
|
263 |
+
- `adam_beta1`: 0.9
|
264 |
+
- `adam_beta2`: 0.999
|
265 |
+
- `adam_epsilon`: 1e-08
|
266 |
+
- `max_grad_norm`: 1
|
267 |
+
- `num_train_epochs`: 12
|
268 |
+
- `max_steps`: -1
|
269 |
+
- `lr_scheduler_type`: linear
|
270 |
+
- `lr_scheduler_kwargs`: {}
|
271 |
+
- `warmup_ratio`: 0.0
|
272 |
+
- `warmup_steps`: 0
|
273 |
+
- `log_level`: passive
|
274 |
+
- `log_level_replica`: warning
|
275 |
+
- `log_on_each_node`: True
|
276 |
+
- `logging_nan_inf_filter`: True
|
277 |
+
- `save_safetensors`: True
|
278 |
+
- `save_on_each_node`: False
|
279 |
+
- `save_only_model`: False
|
280 |
+
- `restore_callback_states_from_checkpoint`: False
|
281 |
+
- `no_cuda`: False
|
282 |
+
- `use_cpu`: False
|
283 |
+
- `use_mps_device`: False
|
284 |
+
- `seed`: 42
|
285 |
+
- `data_seed`: None
|
286 |
+
- `jit_mode_eval`: False
|
287 |
+
- `use_ipex`: False
|
288 |
+
- `bf16`: False
|
289 |
+
- `fp16`: False
|
290 |
+
- `fp16_opt_level`: O1
|
291 |
+
- `half_precision_backend`: auto
|
292 |
+
- `bf16_full_eval`: False
|
293 |
+
- `fp16_full_eval`: False
|
294 |
+
- `tf32`: None
|
295 |
+
- `local_rank`: 0
|
296 |
+
- `ddp_backend`: None
|
297 |
+
- `tpu_num_cores`: None
|
298 |
+
- `tpu_metrics_debug`: False
|
299 |
+
- `debug`: []
|
300 |
+
- `dataloader_drop_last`: False
|
301 |
+
- `dataloader_num_workers`: 0
|
302 |
+
- `dataloader_prefetch_factor`: None
|
303 |
+
- `past_index`: -1
|
304 |
+
- `disable_tqdm`: False
|
305 |
+
- `remove_unused_columns`: True
|
306 |
+
- `label_names`: None
|
307 |
+
- `load_best_model_at_end`: False
|
308 |
+
- `ignore_data_skip`: False
|
309 |
+
- `fsdp`: []
|
310 |
+
- `fsdp_min_num_params`: 0
|
311 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
312 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
313 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
314 |
+
- `deepspeed`: None
|
315 |
+
- `label_smoothing_factor`: 0.0
|
316 |
+
- `optim`: adamw_torch
|
317 |
+
- `optim_args`: None
|
318 |
+
- `adafactor`: False
|
319 |
+
- `group_by_length`: False
|
320 |
+
- `length_column_name`: length
|
321 |
+
- `ddp_find_unused_parameters`: None
|
322 |
+
- `ddp_bucket_cap_mb`: None
|
323 |
+
- `ddp_broadcast_buffers`: False
|
324 |
+
- `dataloader_pin_memory`: True
|
325 |
+
- `dataloader_persistent_workers`: False
|
326 |
+
- `skip_memory_metrics`: True
|
327 |
+
- `use_legacy_prediction_loop`: False
|
328 |
+
- `push_to_hub`: False
|
329 |
+
- `resume_from_checkpoint`: None
|
330 |
+
- `hub_model_id`: None
|
331 |
+
- `hub_strategy`: every_save
|
332 |
+
- `hub_private_repo`: False
|
333 |
+
- `hub_always_push`: False
|
334 |
+
- `gradient_checkpointing`: False
|
335 |
+
- `gradient_checkpointing_kwargs`: None
|
336 |
+
- `include_inputs_for_metrics`: False
|
337 |
+
- `eval_do_concat_batches`: True
|
338 |
+
- `fp16_backend`: auto
|
339 |
+
- `push_to_hub_model_id`: None
|
340 |
+
- `push_to_hub_organization`: None
|
341 |
+
- `mp_parameters`:
|
342 |
+
- `auto_find_batch_size`: False
|
343 |
+
- `full_determinism`: False
|
344 |
+
- `torchdynamo`: None
|
345 |
+
- `ray_scope`: last
|
346 |
+
- `ddp_timeout`: 1800
|
347 |
+
- `torch_compile`: False
|
348 |
+
- `torch_compile_backend`: None
|
349 |
+
- `torch_compile_mode`: None
|
350 |
+
- `dispatch_batches`: None
|
351 |
+
- `split_batches`: None
|
352 |
+
- `include_tokens_per_second`: False
|
353 |
+
- `include_num_input_tokens_seen`: False
|
354 |
+
- `neftune_noise_alpha`: None
|
355 |
+
- `optim_target_modules`: None
|
356 |
+
- `batch_eval_metrics`: False
|
357 |
+
- `batch_sampler`: batch_sampler
|
358 |
+
- `multi_dataset_batch_sampler`: round_robin
|
359 |
+
|
360 |
+
</details>
|
361 |
+
|
362 |
+
### Training Logs
|
363 |
+
<details><summary>Click to expand</summary>
|
364 |
+
|
365 |
+
| Epoch | Step | Training Loss | eval_examples_spearman_max |
|
366 |
+
|:-------:|:-----:|:-------------:|:--------------------------:|
|
367 |
+
| 0.1033 | 100 | - | nan |
|
368 |
+
| 0.2066 | 200 | - | nan |
|
369 |
+
| 0.3099 | 300 | - | nan |
|
370 |
+
| 0.4132 | 400 | - | nan |
|
371 |
+
| 0.5165 | 500 | 0.7655 | nan |
|
372 |
+
| 0.6198 | 600 | - | nan |
|
373 |
+
| 0.7231 | 700 | - | nan |
|
374 |
+
| 0.8264 | 800 | - | nan |
|
375 |
+
| 0.9298 | 900 | - | nan |
|
376 |
+
| 1.0 | 968 | - | nan |
|
377 |
+
| 1.0331 | 1000 | 0.3727 | nan |
|
378 |
+
| 1.1364 | 1100 | - | nan |
|
379 |
+
| 1.2397 | 1200 | - | nan |
|
380 |
+
| 1.3430 | 1300 | - | nan |
|
381 |
+
| 1.4463 | 1400 | - | nan |
|
382 |
+
| 1.5496 | 1500 | 0.2686 | nan |
|
383 |
+
| 1.6529 | 1600 | - | nan |
|
384 |
+
| 1.7562 | 1700 | - | nan |
|
385 |
+
| 1.8595 | 1800 | - | nan |
|
386 |
+
| 1.9628 | 1900 | - | nan |
|
387 |
+
| 2.0 | 1936 | - | nan |
|
388 |
+
| 2.0661 | 2000 | 0.2709 | nan |
|
389 |
+
| 2.1694 | 2100 | - | nan |
|
390 |
+
| 2.2727 | 2200 | - | nan |
|
391 |
+
| 2.3760 | 2300 | - | nan |
|
392 |
+
| 2.4793 | 2400 | - | nan |
|
393 |
+
| 2.5826 | 2500 | 0.231 | nan |
|
394 |
+
| 2.6860 | 2600 | - | nan |
|
395 |
+
| 2.7893 | 2700 | - | nan |
|
396 |
+
| 2.8926 | 2800 | - | nan |
|
397 |
+
| 2.9959 | 2900 | - | nan |
|
398 |
+
| 3.0 | 2904 | - | nan |
|
399 |
+
| 3.0992 | 3000 | 0.2461 | nan |
|
400 |
+
| 3.2025 | 3100 | - | nan |
|
401 |
+
| 3.3058 | 3200 | - | nan |
|
402 |
+
| 3.4091 | 3300 | - | nan |
|
403 |
+
| 3.5124 | 3400 | - | nan |
|
404 |
+
| 3.6157 | 3500 | 0.2181 | nan |
|
405 |
+
| 3.7190 | 3600 | - | nan |
|
406 |
+
| 3.8223 | 3700 | - | nan |
|
407 |
+
| 3.9256 | 3800 | - | nan |
|
408 |
+
| 4.0 | 3872 | - | nan |
|
409 |
+
| 4.0289 | 3900 | - | nan |
|
410 |
+
| 4.1322 | 4000 | 0.2288 | nan |
|
411 |
+
| 4.2355 | 4100 | - | nan |
|
412 |
+
| 4.3388 | 4200 | - | nan |
|
413 |
+
| 4.4421 | 4300 | - | nan |
|
414 |
+
| 4.5455 | 4400 | - | nan |
|
415 |
+
| 4.6488 | 4500 | 0.2123 | nan |
|
416 |
+
| 4.7521 | 4600 | - | nan |
|
417 |
+
| 4.8554 | 4700 | - | nan |
|
418 |
+
| 4.9587 | 4800 | - | nan |
|
419 |
+
| 5.0 | 4840 | - | nan |
|
420 |
+
| 5.0620 | 4900 | - | nan |
|
421 |
+
| 5.1653 | 5000 | 0.2254 | nan |
|
422 |
+
| 5.2686 | 5100 | - | nan |
|
423 |
+
| 5.3719 | 5200 | - | nan |
|
424 |
+
| 5.4752 | 5300 | - | nan |
|
425 |
+
| 5.5785 | 5400 | - | nan |
|
426 |
+
| 5.6818 | 5500 | 0.2077 | nan |
|
427 |
+
| 5.7851 | 5600 | - | nan |
|
428 |
+
| 5.8884 | 5700 | - | nan |
|
429 |
+
| 5.9917 | 5800 | - | nan |
|
430 |
+
| 6.0 | 5808 | - | nan |
|
431 |
+
| 6.0950 | 5900 | - | nan |
|
432 |
+
| 6.1983 | 6000 | 0.218 | nan |
|
433 |
+
| 6.3017 | 6100 | - | nan |
|
434 |
+
| 6.4050 | 6200 | - | nan |
|
435 |
+
| 6.5083 | 6300 | - | nan |
|
436 |
+
| 6.6116 | 6400 | - | nan |
|
437 |
+
| 6.7149 | 6500 | 0.206 | nan |
|
438 |
+
| 6.8182 | 6600 | - | nan |
|
439 |
+
| 6.9215 | 6700 | - | nan |
|
440 |
+
| 7.0 | 6776 | - | nan |
|
441 |
+
| 7.0248 | 6800 | - | nan |
|
442 |
+
| 7.1281 | 6900 | - | nan |
|
443 |
+
| 7.2314 | 7000 | 0.2126 | nan |
|
444 |
+
| 7.3347 | 7100 | - | nan |
|
445 |
+
| 7.4380 | 7200 | - | nan |
|
446 |
+
| 7.5413 | 7300 | - | nan |
|
447 |
+
| 7.6446 | 7400 | - | nan |
|
448 |
+
| 7.7479 | 7500 | 0.2065 | nan |
|
449 |
+
| 7.8512 | 7600 | - | nan |
|
450 |
+
| 7.9545 | 7700 | - | nan |
|
451 |
+
| 8.0 | 7744 | - | nan |
|
452 |
+
| 8.0579 | 7800 | - | nan |
|
453 |
+
| 8.1612 | 7900 | - | nan |
|
454 |
+
| 8.2645 | 8000 | 0.2068 | nan |
|
455 |
+
| 8.3678 | 8100 | - | nan |
|
456 |
+
| 8.4711 | 8200 | - | nan |
|
457 |
+
| 8.5744 | 8300 | - | nan |
|
458 |
+
| 8.6777 | 8400 | - | nan |
|
459 |
+
| 8.7810 | 8500 | 0.2014 | nan |
|
460 |
+
| 8.8843 | 8600 | - | nan |
|
461 |
+
| 8.9876 | 8700 | - | nan |
|
462 |
+
| 9.0 | 8712 | - | nan |
|
463 |
+
| 9.0909 | 8800 | - | nan |
|
464 |
+
| 9.1942 | 8900 | - | nan |
|
465 |
+
| 9.2975 | 9000 | 0.2057 | nan |
|
466 |
+
| 9.4008 | 9100 | - | nan |
|
467 |
+
| 9.5041 | 9200 | - | nan |
|
468 |
+
| 9.6074 | 9300 | - | nan |
|
469 |
+
| 9.7107 | 9400 | - | nan |
|
470 |
+
| 9.8140 | 9500 | 0.1969 | nan |
|
471 |
+
| 9.9174 | 9600 | - | nan |
|
472 |
+
| 10.0 | 9680 | - | nan |
|
473 |
+
| 10.0207 | 9700 | - | nan |
|
474 |
+
| 10.1240 | 9800 | - | nan |
|
475 |
+
| 10.2273 | 9900 | - | nan |
|
476 |
+
| 10.3306 | 10000 | 0.2023 | nan |
|
477 |
+
| 10.4339 | 10100 | - | nan |
|
478 |
+
| 10.5372 | 10200 | - | nan |
|
479 |
+
| 10.6405 | 10300 | - | nan |
|
480 |
+
| 10.7438 | 10400 | - | nan |
|
481 |
+
| 10.8471 | 10500 | 0.1946 | nan |
|
482 |
+
| 10.9504 | 10600 | - | nan |
|
483 |
+
| 11.0 | 10648 | - | nan |
|
484 |
+
| 11.0537 | 10700 | - | nan |
|
485 |
+
| 11.1570 | 10800 | - | nan |
|
486 |
+
| 11.2603 | 10900 | - | nan |
|
487 |
+
| 11.3636 | 11000 | 0.1982 | nan |
|
488 |
+
| 11.4669 | 11100 | - | nan |
|
489 |
+
| 11.5702 | 11200 | - | nan |
|
490 |
+
| 11.6736 | 11300 | - | nan |
|
491 |
+
| 11.7769 | 11400 | - | nan |
|
492 |
+
| 11.8802 | 11500 | 0.1919 | nan |
|
493 |
+
| 11.9835 | 11600 | - | nan |
|
494 |
+
| 12.0 | 11616 | - | nan |
|
495 |
+
|
496 |
+
</details>
|
497 |
+
|
498 |
+
### Framework Versions
|
499 |
+
- Python: 3.10.14
|
500 |
+
- Sentence Transformers: 3.0.0
|
501 |
+
- Transformers: 4.41.2
|
502 |
+
- PyTorch: 2.1.0
|
503 |
+
- Accelerate: 0.30.1
|
504 |
+
- Datasets: 2.19.1
|
505 |
+
- Tokenizers: 0.19.1
|
506 |
+
|
507 |
+
## Citation
|
508 |
+
|
509 |
+
### BibTeX
|
510 |
+
|
511 |
+
#### Sentence Transformers
|
512 |
+
```bibtex
|
513 |
+
@inproceedings{reimers-2019-sentence-bert,
|
514 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
515 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
516 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
517 |
+
month = "11",
|
518 |
+
year = "2019",
|
519 |
+
publisher = "Association for Computational Linguistics",
|
520 |
+
url = "https://arxiv.org/abs/1908.10084",
|
521 |
+
}
|
522 |
+
```
|
523 |
+
|
524 |
+
<!--
|
525 |
+
## Glossary
|
526 |
+
|
527 |
+
*Clearly define terms in order to be accessible across audiences.*
|
528 |
+
-->
|
529 |
+
|
530 |
+
<!--
|
531 |
+
## Model Card Authors
|
532 |
+
|
533 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
534 |
+
-->
|
535 |
+
|
536 |
+
<!--
|
537 |
+
## Model Card Contact
|
538 |
+
|
539 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
540 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertModel"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"max_position_embeddings": 512,
|
13 |
+
"model_type": "distilbert",
|
14 |
+
"n_heads": 12,
|
15 |
+
"n_layers": 6,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"qa_dropout": 0.1,
|
18 |
+
"seq_classif_dropout": 0.2,
|
19 |
+
"sinusoidal_pos_embds": false,
|
20 |
+
"tie_weights_": true,
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.41.2",
|
23 |
+
"vocab_size": 30522
|
24 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "3.0.0",
|
4 |
+
"transformers": "4.41.2",
|
5 |
+
"pytorch": "2.1.0"
|
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:e77cbf4e242b56ab29454849ed5c7c5baca410c5952c9a264f36faab52277c69
|
3 |
+
size 265462608
|
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 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|