Add new SentenceTransformer model.
Browse files- 1_Pooling/config.json +10 -0
- README.md +446 -0
- config.json +26 -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 +66 -0
1_Pooling/config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"word_embedding_dimension": 1024,
|
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 |
+
}
|
README.md
ADDED
@@ -0,0 +1,446 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: sentence-transformers
|
3 |
+
metrics:
|
4 |
+
- cosine_accuracy
|
5 |
+
- dot_accuracy
|
6 |
+
- manhattan_accuracy
|
7 |
+
- euclidean_accuracy
|
8 |
+
- max_accuracy
|
9 |
+
pipeline_tag: sentence-similarity
|
10 |
+
tags:
|
11 |
+
- sentence-transformers
|
12 |
+
- sentence-similarity
|
13 |
+
- feature-extraction
|
14 |
+
- generated_from_trainer
|
15 |
+
- dataset_size:9504
|
16 |
+
- loss:TripletLoss
|
17 |
+
widget:
|
18 |
+
- source_sentence: cap product
|
19 |
+
sentences:
|
20 |
+
- method of adjoining a chain of degree p with a co-chain of degree q, where q is
|
21 |
+
less than or equal to p, to form a composite chain of degree p-q
|
22 |
+
- 'Ontology '
|
23 |
+
- hat commodity
|
24 |
+
- source_sentence: cognitivism
|
25 |
+
sentences:
|
26 |
+
- supporting cognitive science
|
27 |
+
- study of changes in organisms caused by modification of gene expression rather
|
28 |
+
than alteration of the genetic code
|
29 |
+
- 'the idea that mind works like an algorithmic symbol manipulation '
|
30 |
+
- source_sentence: doxastic voluntarism
|
31 |
+
sentences:
|
32 |
+
- Land surrounded by water
|
33 |
+
- belief one is free
|
34 |
+
- the ability to will beliefs
|
35 |
+
- source_sentence: conceptual role
|
36 |
+
sentences:
|
37 |
+
- concept
|
38 |
+
- inferential role
|
39 |
+
- 'Theory of knowledge '
|
40 |
+
- source_sentence: scientific revolutions
|
41 |
+
sentences:
|
42 |
+
- scientific realism
|
43 |
+
- Universal moral principles govern legal systems
|
44 |
+
- paradigm shifts
|
45 |
+
model-index:
|
46 |
+
- name: SentenceTransformer
|
47 |
+
results:
|
48 |
+
- task:
|
49 |
+
type: triplet
|
50 |
+
name: Triplet
|
51 |
+
dataset:
|
52 |
+
name: beatai dev
|
53 |
+
type: beatai-dev
|
54 |
+
metrics:
|
55 |
+
- type: cosine_accuracy
|
56 |
+
value: 0.8080808080808081
|
57 |
+
name: Cosine Accuracy
|
58 |
+
- type: dot_accuracy
|
59 |
+
value: 0.28114478114478114
|
60 |
+
name: Dot Accuracy
|
61 |
+
- type: manhattan_accuracy
|
62 |
+
value: 0.8316498316498316
|
63 |
+
name: Manhattan Accuracy
|
64 |
+
- type: euclidean_accuracy
|
65 |
+
value: 0.8249158249158249
|
66 |
+
name: Euclidean Accuracy
|
67 |
+
- type: max_accuracy
|
68 |
+
value: 0.8316498316498316
|
69 |
+
name: Max Accuracy
|
70 |
+
---
|
71 |
+
|
72 |
+
# SentenceTransformer
|
73 |
+
|
74 |
+
This is a [sentence-transformers](https://www.SBERT.net) model trained. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
|
75 |
+
|
76 |
+
## Model Details
|
77 |
+
|
78 |
+
### Model Description
|
79 |
+
- **Model Type:** Sentence Transformer
|
80 |
+
<!-- - **Base model:** [Unknown](https://huggingface.co/unknown) -->
|
81 |
+
- **Maximum Sequence Length:** 512 tokens
|
82 |
+
- **Output Dimensionality:** 1024 tokens
|
83 |
+
- **Similarity Function:** Cosine Similarity
|
84 |
+
<!-- - **Training Dataset:** Unknown -->
|
85 |
+
<!-- - **Language:** Unknown -->
|
86 |
+
<!-- - **License:** Unknown -->
|
87 |
+
|
88 |
+
### Model Sources
|
89 |
+
|
90 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
91 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
92 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
93 |
+
|
94 |
+
### Full Model Architecture
|
95 |
+
|
96 |
+
```
|
97 |
+
SentenceTransformer(
|
98 |
+
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
|
99 |
+
(1): Pooling({'word_embedding_dimension': 1024, '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})
|
100 |
+
)
|
101 |
+
```
|
102 |
+
|
103 |
+
## Usage
|
104 |
+
|
105 |
+
### Direct Usage (Sentence Transformers)
|
106 |
+
|
107 |
+
First install the Sentence Transformers library:
|
108 |
+
|
109 |
+
```bash
|
110 |
+
pip install -U sentence-transformers
|
111 |
+
```
|
112 |
+
|
113 |
+
Then you can load this model and run inference.
|
114 |
+
```python
|
115 |
+
from sentence_transformers import SentenceTransformer
|
116 |
+
|
117 |
+
# Download from the 🤗 Hub
|
118 |
+
model = SentenceTransformer("dbourget/pb-small-10e-tsdae6e-philsim-cosine-6e-beatai-20e")
|
119 |
+
# Run inference
|
120 |
+
sentences = [
|
121 |
+
'scientific revolutions',
|
122 |
+
'paradigm shifts',
|
123 |
+
'scientific realism',
|
124 |
+
]
|
125 |
+
embeddings = model.encode(sentences)
|
126 |
+
print(embeddings.shape)
|
127 |
+
# [3, 1024]
|
128 |
+
|
129 |
+
# Get the similarity scores for the embeddings
|
130 |
+
similarities = model.similarity(embeddings, embeddings)
|
131 |
+
print(similarities.shape)
|
132 |
+
# [3, 3]
|
133 |
+
```
|
134 |
+
|
135 |
+
<!--
|
136 |
+
### Direct Usage (Transformers)
|
137 |
+
|
138 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
139 |
+
|
140 |
+
</details>
|
141 |
+
-->
|
142 |
+
|
143 |
+
<!--
|
144 |
+
### Downstream Usage (Sentence Transformers)
|
145 |
+
|
146 |
+
You can finetune this model on your own dataset.
|
147 |
+
|
148 |
+
<details><summary>Click to expand</summary>
|
149 |
+
|
150 |
+
</details>
|
151 |
+
-->
|
152 |
+
|
153 |
+
<!--
|
154 |
+
### Out-of-Scope Use
|
155 |
+
|
156 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
157 |
+
-->
|
158 |
+
|
159 |
+
## Evaluation
|
160 |
+
|
161 |
+
### Metrics
|
162 |
+
|
163 |
+
#### Triplet
|
164 |
+
* Dataset: `beatai-dev`
|
165 |
+
* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
|
166 |
+
|
167 |
+
| Metric | Value |
|
168 |
+
|:-------------------|:-----------|
|
169 |
+
| cosine_accuracy | 0.8081 |
|
170 |
+
| dot_accuracy | 0.2811 |
|
171 |
+
| manhattan_accuracy | 0.8316 |
|
172 |
+
| euclidean_accuracy | 0.8249 |
|
173 |
+
| **max_accuracy** | **0.8316** |
|
174 |
+
|
175 |
+
<!--
|
176 |
+
## Bias, Risks and Limitations
|
177 |
+
|
178 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
179 |
+
-->
|
180 |
+
|
181 |
+
<!--
|
182 |
+
### Recommendations
|
183 |
+
|
184 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
185 |
+
-->
|
186 |
+
|
187 |
+
## Training Details
|
188 |
+
|
189 |
+
### Training Hyperparameters
|
190 |
+
#### Non-Default Hyperparameters
|
191 |
+
|
192 |
+
- `eval_strategy`: steps
|
193 |
+
- `per_device_train_batch_size`: 138
|
194 |
+
- `per_device_eval_batch_size`: 138
|
195 |
+
- `learning_rate`: 2e-06
|
196 |
+
- `num_train_epochs`: 10
|
197 |
+
- `lr_scheduler_type`: constant
|
198 |
+
- `bf16`: True
|
199 |
+
- `dataloader_drop_last`: True
|
200 |
+
|
201 |
+
#### All Hyperparameters
|
202 |
+
<details><summary>Click to expand</summary>
|
203 |
+
|
204 |
+
- `overwrite_output_dir`: False
|
205 |
+
- `do_predict`: False
|
206 |
+
- `eval_strategy`: steps
|
207 |
+
- `prediction_loss_only`: True
|
208 |
+
- `per_device_train_batch_size`: 138
|
209 |
+
- `per_device_eval_batch_size`: 138
|
210 |
+
- `per_gpu_train_batch_size`: None
|
211 |
+
- `per_gpu_eval_batch_size`: None
|
212 |
+
- `gradient_accumulation_steps`: 1
|
213 |
+
- `eval_accumulation_steps`: None
|
214 |
+
- `torch_empty_cache_steps`: None
|
215 |
+
- `learning_rate`: 2e-06
|
216 |
+
- `weight_decay`: 0
|
217 |
+
- `adam_beta1`: 0.9
|
218 |
+
- `adam_beta2`: 0.999
|
219 |
+
- `adam_epsilon`: 1e-08
|
220 |
+
- `max_grad_norm`: 1.0
|
221 |
+
- `num_train_epochs`: 10
|
222 |
+
- `max_steps`: -1
|
223 |
+
- `lr_scheduler_type`: constant
|
224 |
+
- `lr_scheduler_kwargs`: {}
|
225 |
+
- `warmup_ratio`: 0
|
226 |
+
- `warmup_steps`: 0
|
227 |
+
- `log_level`: passive
|
228 |
+
- `log_level_replica`: warning
|
229 |
+
- `log_on_each_node`: True
|
230 |
+
- `logging_nan_inf_filter`: True
|
231 |
+
- `save_safetensors`: True
|
232 |
+
- `save_on_each_node`: False
|
233 |
+
- `save_only_model`: False
|
234 |
+
- `restore_callback_states_from_checkpoint`: False
|
235 |
+
- `no_cuda`: False
|
236 |
+
- `use_cpu`: False
|
237 |
+
- `use_mps_device`: False
|
238 |
+
- `seed`: 42
|
239 |
+
- `data_seed`: None
|
240 |
+
- `jit_mode_eval`: False
|
241 |
+
- `use_ipex`: False
|
242 |
+
- `bf16`: True
|
243 |
+
- `fp16`: False
|
244 |
+
- `fp16_opt_level`: O1
|
245 |
+
- `half_precision_backend`: auto
|
246 |
+
- `bf16_full_eval`: False
|
247 |
+
- `fp16_full_eval`: False
|
248 |
+
- `tf32`: None
|
249 |
+
- `local_rank`: 0
|
250 |
+
- `ddp_backend`: None
|
251 |
+
- `tpu_num_cores`: None
|
252 |
+
- `tpu_metrics_debug`: False
|
253 |
+
- `debug`: []
|
254 |
+
- `dataloader_drop_last`: True
|
255 |
+
- `dataloader_num_workers`: 0
|
256 |
+
- `dataloader_prefetch_factor`: 2
|
257 |
+
- `past_index`: -1
|
258 |
+
- `disable_tqdm`: False
|
259 |
+
- `remove_unused_columns`: True
|
260 |
+
- `label_names`: None
|
261 |
+
- `load_best_model_at_end`: False
|
262 |
+
- `ignore_data_skip`: False
|
263 |
+
- `fsdp`: []
|
264 |
+
- `fsdp_min_num_params`: 0
|
265 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
266 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
267 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
268 |
+
- `deepspeed`: None
|
269 |
+
- `label_smoothing_factor`: 0.0
|
270 |
+
- `optim`: adamw_torch
|
271 |
+
- `optim_args`: None
|
272 |
+
- `adafactor`: False
|
273 |
+
- `group_by_length`: False
|
274 |
+
- `length_column_name`: length
|
275 |
+
- `ddp_find_unused_parameters`: None
|
276 |
+
- `ddp_bucket_cap_mb`: None
|
277 |
+
- `ddp_broadcast_buffers`: False
|
278 |
+
- `dataloader_pin_memory`: True
|
279 |
+
- `dataloader_persistent_workers`: False
|
280 |
+
- `skip_memory_metrics`: True
|
281 |
+
- `use_legacy_prediction_loop`: False
|
282 |
+
- `push_to_hub`: False
|
283 |
+
- `resume_from_checkpoint`: None
|
284 |
+
- `hub_model_id`: None
|
285 |
+
- `hub_strategy`: every_save
|
286 |
+
- `hub_private_repo`: False
|
287 |
+
- `hub_always_push`: False
|
288 |
+
- `gradient_checkpointing`: False
|
289 |
+
- `gradient_checkpointing_kwargs`: None
|
290 |
+
- `include_inputs_for_metrics`: False
|
291 |
+
- `eval_do_concat_batches`: True
|
292 |
+
- `fp16_backend`: auto
|
293 |
+
- `push_to_hub_model_id`: None
|
294 |
+
- `push_to_hub_organization`: None
|
295 |
+
- `mp_parameters`:
|
296 |
+
- `auto_find_batch_size`: False
|
297 |
+
- `full_determinism`: False
|
298 |
+
- `torchdynamo`: None
|
299 |
+
- `ray_scope`: last
|
300 |
+
- `ddp_timeout`: 1800
|
301 |
+
- `torch_compile`: False
|
302 |
+
- `torch_compile_backend`: None
|
303 |
+
- `torch_compile_mode`: None
|
304 |
+
- `dispatch_batches`: None
|
305 |
+
- `split_batches`: None
|
306 |
+
- `include_tokens_per_second`: False
|
307 |
+
- `include_num_input_tokens_seen`: False
|
308 |
+
- `neftune_noise_alpha`: None
|
309 |
+
- `optim_target_modules`: None
|
310 |
+
- `batch_eval_metrics`: False
|
311 |
+
- `eval_on_start`: False
|
312 |
+
- `eval_use_gather_object`: False
|
313 |
+
- `batch_sampler`: batch_sampler
|
314 |
+
- `multi_dataset_batch_sampler`: proportional
|
315 |
+
|
316 |
+
</details>
|
317 |
+
|
318 |
+
### Training Logs
|
319 |
+
| Epoch | Step | Training Loss | loss | beatai-dev_max_accuracy |
|
320 |
+
|:------:|:----:|:-------------:|:------:|:-----------------------:|
|
321 |
+
| 0 | 0 | - | - | 0.8072 |
|
322 |
+
| 0.1471 | 10 | 1.8573 | - | - |
|
323 |
+
| 0.2941 | 20 | 1.8196 | - | - |
|
324 |
+
| 0.4412 | 30 | 1.8594 | - | - |
|
325 |
+
| 0.5882 | 40 | 1.8581 | - | - |
|
326 |
+
| 0.7353 | 50 | 1.8766 | 2.3603 | 0.8047 |
|
327 |
+
| 0.8824 | 60 | 1.8596 | - | - |
|
328 |
+
| 1.0294 | 70 | 1.6816 | - | - |
|
329 |
+
| 1.1765 | 80 | 1.7564 | - | - |
|
330 |
+
| 1.3235 | 90 | 1.7191 | - | - |
|
331 |
+
| 1.4706 | 100 | 1.6521 | 2.3296 | 0.8064 |
|
332 |
+
| 1.6176 | 110 | 1.7054 | - | - |
|
333 |
+
| 1.7647 | 120 | 1.6895 | - | - |
|
334 |
+
| 1.9118 | 130 | 1.6724 | - | - |
|
335 |
+
| 2.0588 | 140 | 1.6369 | - | - |
|
336 |
+
| 2.2059 | 150 | 1.705 | 2.2941 | 0.8123 |
|
337 |
+
| 2.3529 | 160 | 1.8329 | - | - |
|
338 |
+
| 2.5 | 170 | 1.6071 | - | - |
|
339 |
+
| 2.6471 | 180 | 1.5157 | - | - |
|
340 |
+
| 2.7941 | 190 | 1.624 | - | - |
|
341 |
+
| 2.9412 | 200 | 1.6185 | 2.2668 | 0.8140 |
|
342 |
+
| 3.0882 | 210 | 1.6259 | - | - |
|
343 |
+
| 3.2353 | 220 | 1.5749 | - | - |
|
344 |
+
| 3.3824 | 230 | 1.5426 | - | - |
|
345 |
+
| 3.5294 | 240 | 1.5522 | - | - |
|
346 |
+
| 3.6765 | 250 | 1.5141 | 2.2498 | 0.8157 |
|
347 |
+
| 3.8235 | 260 | 1.5215 | - | - |
|
348 |
+
| 3.9706 | 270 | 1.4983 | - | - |
|
349 |
+
| 4.1176 | 280 | 1.4819 | - | - |
|
350 |
+
| 4.2647 | 290 | 1.4552 | - | - |
|
351 |
+
| 4.4118 | 300 | 1.5597 | 2.2226 | 0.8199 |
|
352 |
+
| 4.5588 | 310 | 1.3983 | - | - |
|
353 |
+
| 4.7059 | 320 | 1.5386 | - | - |
|
354 |
+
| 4.8529 | 330 | 1.4541 | - | - |
|
355 |
+
| 5.0 | 340 | 1.4097 | - | - |
|
356 |
+
| 5.1471 | 350 | 1.3741 | 2.2129 | 0.8207 |
|
357 |
+
| 5.2941 | 360 | 1.3909 | - | - |
|
358 |
+
| 5.4412 | 370 | 1.4116 | - | - |
|
359 |
+
| 5.5882 | 380 | 1.52 | - | - |
|
360 |
+
| 5.7353 | 390 | 1.3644 | - | - |
|
361 |
+
| 5.8824 | 400 | 1.3016 | 2.1699 | 0.8266 |
|
362 |
+
| 6.0294 | 410 | 1.4435 | - | - |
|
363 |
+
| 6.1765 | 420 | 1.3112 | - | - |
|
364 |
+
| 6.3235 | 430 | 1.4056 | - | - |
|
365 |
+
| 6.4706 | 440 | 1.4541 | - | - |
|
366 |
+
| 6.6176 | 450 | 1.3312 | 2.1486 | 0.8224 |
|
367 |
+
| 6.7647 | 460 | 1.2879 | - | - |
|
368 |
+
| 6.9118 | 470 | 1.227 | - | - |
|
369 |
+
| 7.0588 | 480 | 1.3834 | - | - |
|
370 |
+
| 7.2059 | 490 | 1.3242 | - | - |
|
371 |
+
| 7.3529 | 500 | 1.3756 | 2.1507 | 0.8274 |
|
372 |
+
| 7.5 | 510 | 1.2872 | - | - |
|
373 |
+
| 7.6471 | 520 | 1.3288 | - | - |
|
374 |
+
| 7.7941 | 530 | 1.2689 | - | - |
|
375 |
+
| 7.9412 | 540 | 1.3102 | - | - |
|
376 |
+
| 8.0882 | 550 | 1.2929 | 2.1355 | 0.8207 |
|
377 |
+
| 8.2353 | 560 | 1.2511 | - | - |
|
378 |
+
| 8.3824 | 570 | 1.1849 | - | - |
|
379 |
+
| 8.5294 | 580 | 1.2774 | - | - |
|
380 |
+
| 8.6765 | 590 | 1.1923 | - | - |
|
381 |
+
| 8.8235 | 600 | 1.1927 | 2.1111 | 0.8283 |
|
382 |
+
| 8.9706 | 610 | 1.2556 | - | - |
|
383 |
+
| 9.1176 | 620 | 1.2767 | - | - |
|
384 |
+
| 9.2647 | 630 | 1.1082 | - | - |
|
385 |
+
| 9.4118 | 640 | 1.3077 | - | - |
|
386 |
+
| 9.5588 | 650 | 1.1435 | 2.0922 | 0.8316 |
|
387 |
+
| 9.7059 | 660 | 1.1888 | - | - |
|
388 |
+
| 9.8529 | 670 | 1.2123 | - | - |
|
389 |
+
| 10.0 | 680 | 1.2554 | - | - |
|
390 |
+
|
391 |
+
|
392 |
+
### Framework Versions
|
393 |
+
- Python: 3.8.18
|
394 |
+
- Sentence Transformers: 3.1.1
|
395 |
+
- Transformers: 4.44.2
|
396 |
+
- PyTorch: 1.13.1+cu117
|
397 |
+
- Accelerate: 0.34.2
|
398 |
+
- Datasets: 3.0.0
|
399 |
+
- Tokenizers: 0.19.1
|
400 |
+
|
401 |
+
## Citation
|
402 |
+
|
403 |
+
### BibTeX
|
404 |
+
|
405 |
+
#### Sentence Transformers
|
406 |
+
```bibtex
|
407 |
+
@inproceedings{reimers-2019-sentence-bert,
|
408 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
409 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
410 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
411 |
+
month = "11",
|
412 |
+
year = "2019",
|
413 |
+
publisher = "Association for Computational Linguistics",
|
414 |
+
url = "https://arxiv.org/abs/1908.10084",
|
415 |
+
}
|
416 |
+
```
|
417 |
+
|
418 |
+
#### TripletLoss
|
419 |
+
```bibtex
|
420 |
+
@misc{hermans2017defense,
|
421 |
+
title={In Defense of the Triplet Loss for Person Re-Identification},
|
422 |
+
author={Alexander Hermans and Lucas Beyer and Bastian Leibe},
|
423 |
+
year={2017},
|
424 |
+
eprint={1703.07737},
|
425 |
+
archivePrefix={arXiv},
|
426 |
+
primaryClass={cs.CV}
|
427 |
+
}
|
428 |
+
```
|
429 |
+
|
430 |
+
<!--
|
431 |
+
## Glossary
|
432 |
+
|
433 |
+
*Clearly define terms in order to be accessible across audiences.*
|
434 |
+
-->
|
435 |
+
|
436 |
+
<!--
|
437 |
+
## Model Card Authors
|
438 |
+
|
439 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
440 |
+
-->
|
441 |
+
|
442 |
+
<!--
|
443 |
+
## Model Card Contact
|
444 |
+
|
445 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
446 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "../models/pb-small-10e-tsdae6e-philsim-cosine-6e-beatai-10e",
|
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": 768,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 3072,
|
13 |
+
"layer_norm_eps": 1e-12,
|
14 |
+
"max_position_embeddings": 512,
|
15 |
+
"model_type": "bert",
|
16 |
+
"num_attention_heads": 12,
|
17 |
+
"num_hidden_layers": 12,
|
18 |
+
"pad_token_id": 0,
|
19 |
+
"position_embedding_type": "absolute",
|
20 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.44.2",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 30522
|
26 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "3.1.1",
|
4 |
+
"transformers": "4.44.2",
|
5 |
+
"pytorch": "1.13.1+cu117"
|
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 sha256:46744ec43fabf3a3be9d3d4f33812a707b236c0a82b52d62396cd27f1d280120
|
3 |
+
size 437951328
|
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 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"1": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"4": {
|
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 |
+
"mask_token": "[MASK]",
|
54 |
+
"max_length": 512,
|
55 |
+
"model_max_length": 512,
|
56 |
+
"pad_to_multiple_of": null,
|
57 |
+
"pad_token": "[PAD]",
|
58 |
+
"pad_token_type_id": 0,
|
59 |
+
"padding_side": "right",
|
60 |
+
"sep_token": "[SEP]",
|
61 |
+
"stride": 0,
|
62 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
63 |
+
"truncation_side": "right",
|
64 |
+
"truncation_strategy": "longest_first",
|
65 |
+
"unk_token": "[UNK]"
|
66 |
+
}
|