Add new SentenceTransformer model.
Browse files- 1_Pooling/config.json +10 -0
- README.md +589 -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 +1,589 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: dbourget/pb-small-10e-tsdae6e-philsim-cosine-6e-beatai-cosine-50e
|
3 |
+
library_name: sentence-transformers
|
4 |
+
metrics:
|
5 |
+
- cosine_accuracy
|
6 |
+
- dot_accuracy
|
7 |
+
- manhattan_accuracy
|
8 |
+
- euclidean_accuracy
|
9 |
+
- max_accuracy
|
10 |
+
pipeline_tag: sentence-similarity
|
11 |
+
tags:
|
12 |
+
- sentence-transformers
|
13 |
+
- sentence-similarity
|
14 |
+
- feature-extraction
|
15 |
+
- generated_from_trainer
|
16 |
+
- dataset_size:9504
|
17 |
+
- loss:TripletLoss
|
18 |
+
widget:
|
19 |
+
- source_sentence: cap product
|
20 |
+
sentences:
|
21 |
+
- method of adjoining a chain of degree p with a co-chain of degree q, where q is
|
22 |
+
less than or equal to p, to form a composite chain of degree p-q
|
23 |
+
- 'Ontology '
|
24 |
+
- hat commodity
|
25 |
+
- source_sentence: cognitivism
|
26 |
+
sentences:
|
27 |
+
- supporting cognitive science
|
28 |
+
- study of changes in organisms caused by modification of gene expression rather
|
29 |
+
than alteration of the genetic code
|
30 |
+
- 'the idea that mind works like an algorithmic symbol manipulation '
|
31 |
+
- source_sentence: doxastic voluntarism
|
32 |
+
sentences:
|
33 |
+
- Land surrounded by water
|
34 |
+
- belief one is free
|
35 |
+
- the ability to will beliefs
|
36 |
+
- source_sentence: conceptual role
|
37 |
+
sentences:
|
38 |
+
- concept
|
39 |
+
- inferential role
|
40 |
+
- 'Theory of knowledge '
|
41 |
+
- source_sentence: scientific revolutions
|
42 |
+
sentences:
|
43 |
+
- scientific realism
|
44 |
+
- Universal moral principles govern legal systems
|
45 |
+
- paradigm shifts
|
46 |
+
model-index:
|
47 |
+
- name: SentenceTransformer based on dbourget/pb-small-10e-tsdae6e-philsim-cosine-6e-beatai-cosine-50e
|
48 |
+
results:
|
49 |
+
- task:
|
50 |
+
type: triplet
|
51 |
+
name: Triplet
|
52 |
+
dataset:
|
53 |
+
name: beatai dev
|
54 |
+
type: beatai-dev
|
55 |
+
metrics:
|
56 |
+
- type: cosine_accuracy
|
57 |
+
value: 0.813973063973064
|
58 |
+
name: Cosine Accuracy
|
59 |
+
- type: dot_accuracy
|
60 |
+
value: 0.22727272727272727
|
61 |
+
name: Dot Accuracy
|
62 |
+
- type: manhattan_accuracy
|
63 |
+
value: 0.8198653198653199
|
64 |
+
name: Manhattan Accuracy
|
65 |
+
- type: euclidean_accuracy
|
66 |
+
value: 0.8156565656565656
|
67 |
+
name: Euclidean Accuracy
|
68 |
+
- type: max_accuracy
|
69 |
+
value: 0.8198653198653199
|
70 |
+
name: Max Accuracy
|
71 |
+
---
|
72 |
+
|
73 |
+
# SentenceTransformer based on dbourget/pb-small-10e-tsdae6e-philsim-cosine-6e-beatai-cosine-50e
|
74 |
+
|
75 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [dbourget/pb-small-10e-tsdae6e-philsim-cosine-6e-beatai-cosine-50e](https://huggingface.co/dbourget/pb-small-10e-tsdae6e-philsim-cosine-6e-beatai-cosine-50e). 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.
|
76 |
+
|
77 |
+
## Model Details
|
78 |
+
|
79 |
+
### Model Description
|
80 |
+
- **Model Type:** Sentence Transformer
|
81 |
+
- **Base model:** [dbourget/pb-small-10e-tsdae6e-philsim-cosine-6e-beatai-cosine-50e](https://huggingface.co/dbourget/pb-small-10e-tsdae6e-philsim-cosine-6e-beatai-cosine-50e) <!-- at revision 86e3b91181f7c10aa5a92184184dc50f0f25aa57 -->
|
82 |
+
- **Maximum Sequence Length:** 512 tokens
|
83 |
+
- **Output Dimensionality:** 1024 tokens
|
84 |
+
- **Similarity Function:** Cosine Similarity
|
85 |
+
<!-- - **Training Dataset:** Unknown -->
|
86 |
+
<!-- - **Language:** Unknown -->
|
87 |
+
<!-- - **License:** Unknown -->
|
88 |
+
|
89 |
+
### Model Sources
|
90 |
+
|
91 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
92 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
93 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
94 |
+
|
95 |
+
### Full Model Architecture
|
96 |
+
|
97 |
+
```
|
98 |
+
SentenceTransformer(
|
99 |
+
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
|
100 |
+
(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})
|
101 |
+
)
|
102 |
+
```
|
103 |
+
|
104 |
+
## Usage
|
105 |
+
|
106 |
+
### Direct Usage (Sentence Transformers)
|
107 |
+
|
108 |
+
First install the Sentence Transformers library:
|
109 |
+
|
110 |
+
```bash
|
111 |
+
pip install -U sentence-transformers
|
112 |
+
```
|
113 |
+
|
114 |
+
Then you can load this model and run inference.
|
115 |
+
```python
|
116 |
+
from sentence_transformers import SentenceTransformer
|
117 |
+
|
118 |
+
# Download from the 🤗 Hub
|
119 |
+
model = SentenceTransformer("dbourget/pb-small-10e-tsdae6e-philsim-cosine-6e-beatai-cosine-80e")
|
120 |
+
# Run inference
|
121 |
+
sentences = [
|
122 |
+
'scientific revolutions',
|
123 |
+
'paradigm shifts',
|
124 |
+
'scientific realism',
|
125 |
+
]
|
126 |
+
embeddings = model.encode(sentences)
|
127 |
+
print(embeddings.shape)
|
128 |
+
# [3, 1024]
|
129 |
+
|
130 |
+
# Get the similarity scores for the embeddings
|
131 |
+
similarities = model.similarity(embeddings, embeddings)
|
132 |
+
print(similarities.shape)
|
133 |
+
# [3, 3]
|
134 |
+
```
|
135 |
+
|
136 |
+
<!--
|
137 |
+
### Direct Usage (Transformers)
|
138 |
+
|
139 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
140 |
+
|
141 |
+
</details>
|
142 |
+
-->
|
143 |
+
|
144 |
+
<!--
|
145 |
+
### Downstream Usage (Sentence Transformers)
|
146 |
+
|
147 |
+
You can finetune this model on your own dataset.
|
148 |
+
|
149 |
+
<details><summary>Click to expand</summary>
|
150 |
+
|
151 |
+
</details>
|
152 |
+
-->
|
153 |
+
|
154 |
+
<!--
|
155 |
+
### Out-of-Scope Use
|
156 |
+
|
157 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
158 |
+
-->
|
159 |
+
|
160 |
+
## Evaluation
|
161 |
+
|
162 |
+
### Metrics
|
163 |
+
|
164 |
+
#### Triplet
|
165 |
+
* Dataset: `beatai-dev`
|
166 |
+
* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
|
167 |
+
|
168 |
+
| Metric | Value |
|
169 |
+
|:--------------------|:----------|
|
170 |
+
| **cosine_accuracy** | **0.814** |
|
171 |
+
| dot_accuracy | 0.2273 |
|
172 |
+
| manhattan_accuracy | 0.8199 |
|
173 |
+
| euclidean_accuracy | 0.8157 |
|
174 |
+
| max_accuracy | 0.8199 |
|
175 |
+
|
176 |
+
<!--
|
177 |
+
## Bias, Risks and Limitations
|
178 |
+
|
179 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
180 |
+
-->
|
181 |
+
|
182 |
+
<!--
|
183 |
+
### Recommendations
|
184 |
+
|
185 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
186 |
+
-->
|
187 |
+
|
188 |
+
## Training Details
|
189 |
+
|
190 |
+
### Training Hyperparameters
|
191 |
+
#### Non-Default Hyperparameters
|
192 |
+
|
193 |
+
- `eval_strategy`: steps
|
194 |
+
- `per_device_train_batch_size`: 138
|
195 |
+
- `per_device_eval_batch_size`: 138
|
196 |
+
- `learning_rate`: 5e-07
|
197 |
+
- `weight_decay`: 0.01
|
198 |
+
- `num_train_epochs`: 30
|
199 |
+
- `lr_scheduler_type`: constant
|
200 |
+
- `bf16`: True
|
201 |
+
- `dataloader_drop_last`: True
|
202 |
+
- `resume_from_checkpoint`: True
|
203 |
+
|
204 |
+
#### All Hyperparameters
|
205 |
+
<details><summary>Click to expand</summary>
|
206 |
+
|
207 |
+
- `overwrite_output_dir`: False
|
208 |
+
- `do_predict`: False
|
209 |
+
- `eval_strategy`: steps
|
210 |
+
- `prediction_loss_only`: True
|
211 |
+
- `per_device_train_batch_size`: 138
|
212 |
+
- `per_device_eval_batch_size`: 138
|
213 |
+
- `per_gpu_train_batch_size`: None
|
214 |
+
- `per_gpu_eval_batch_size`: None
|
215 |
+
- `gradient_accumulation_steps`: 1
|
216 |
+
- `eval_accumulation_steps`: None
|
217 |
+
- `torch_empty_cache_steps`: None
|
218 |
+
- `learning_rate`: 5e-07
|
219 |
+
- `weight_decay`: 0.01
|
220 |
+
- `adam_beta1`: 0.9
|
221 |
+
- `adam_beta2`: 0.999
|
222 |
+
- `adam_epsilon`: 1e-08
|
223 |
+
- `max_grad_norm`: 1.0
|
224 |
+
- `num_train_epochs`: 30
|
225 |
+
- `max_steps`: -1
|
226 |
+
- `lr_scheduler_type`: constant
|
227 |
+
- `lr_scheduler_kwargs`: {}
|
228 |
+
- `warmup_ratio`: 0
|
229 |
+
- `warmup_steps`: 0
|
230 |
+
- `log_level`: passive
|
231 |
+
- `log_level_replica`: warning
|
232 |
+
- `log_on_each_node`: True
|
233 |
+
- `logging_nan_inf_filter`: True
|
234 |
+
- `save_safetensors`: True
|
235 |
+
- `save_on_each_node`: False
|
236 |
+
- `save_only_model`: False
|
237 |
+
- `restore_callback_states_from_checkpoint`: False
|
238 |
+
- `no_cuda`: False
|
239 |
+
- `use_cpu`: False
|
240 |
+
- `use_mps_device`: False
|
241 |
+
- `seed`: 42
|
242 |
+
- `data_seed`: None
|
243 |
+
- `jit_mode_eval`: False
|
244 |
+
- `use_ipex`: False
|
245 |
+
- `bf16`: True
|
246 |
+
- `fp16`: False
|
247 |
+
- `fp16_opt_level`: O1
|
248 |
+
- `half_precision_backend`: auto
|
249 |
+
- `bf16_full_eval`: False
|
250 |
+
- `fp16_full_eval`: False
|
251 |
+
- `tf32`: None
|
252 |
+
- `local_rank`: 0
|
253 |
+
- `ddp_backend`: None
|
254 |
+
- `tpu_num_cores`: None
|
255 |
+
- `tpu_metrics_debug`: False
|
256 |
+
- `debug`: []
|
257 |
+
- `dataloader_drop_last`: True
|
258 |
+
- `dataloader_num_workers`: 0
|
259 |
+
- `dataloader_prefetch_factor`: 2
|
260 |
+
- `past_index`: -1
|
261 |
+
- `disable_tqdm`: False
|
262 |
+
- `remove_unused_columns`: True
|
263 |
+
- `label_names`: None
|
264 |
+
- `load_best_model_at_end`: False
|
265 |
+
- `ignore_data_skip`: False
|
266 |
+
- `fsdp`: []
|
267 |
+
- `fsdp_min_num_params`: 0
|
268 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
269 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
270 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
271 |
+
- `deepspeed`: None
|
272 |
+
- `label_smoothing_factor`: 0.0
|
273 |
+
- `optim`: adamw_torch
|
274 |
+
- `optim_args`: None
|
275 |
+
- `adafactor`: False
|
276 |
+
- `group_by_length`: False
|
277 |
+
- `length_column_name`: length
|
278 |
+
- `ddp_find_unused_parameters`: None
|
279 |
+
- `ddp_bucket_cap_mb`: None
|
280 |
+
- `ddp_broadcast_buffers`: False
|
281 |
+
- `dataloader_pin_memory`: True
|
282 |
+
- `dataloader_persistent_workers`: False
|
283 |
+
- `skip_memory_metrics`: True
|
284 |
+
- `use_legacy_prediction_loop`: False
|
285 |
+
- `push_to_hub`: False
|
286 |
+
- `resume_from_checkpoint`: True
|
287 |
+
- `hub_model_id`: None
|
288 |
+
- `hub_strategy`: every_save
|
289 |
+
- `hub_private_repo`: False
|
290 |
+
- `hub_always_push`: False
|
291 |
+
- `gradient_checkpointing`: False
|
292 |
+
- `gradient_checkpointing_kwargs`: None
|
293 |
+
- `include_inputs_for_metrics`: False
|
294 |
+
- `eval_do_concat_batches`: True
|
295 |
+
- `fp16_backend`: auto
|
296 |
+
- `push_to_hub_model_id`: None
|
297 |
+
- `push_to_hub_organization`: None
|
298 |
+
- `mp_parameters`:
|
299 |
+
- `auto_find_batch_size`: False
|
300 |
+
- `full_determinism`: False
|
301 |
+
- `torchdynamo`: None
|
302 |
+
- `ray_scope`: last
|
303 |
+
- `ddp_timeout`: 1800
|
304 |
+
- `torch_compile`: False
|
305 |
+
- `torch_compile_backend`: None
|
306 |
+
- `torch_compile_mode`: None
|
307 |
+
- `dispatch_batches`: None
|
308 |
+
- `split_batches`: None
|
309 |
+
- `include_tokens_per_second`: False
|
310 |
+
- `include_num_input_tokens_seen`: False
|
311 |
+
- `neftune_noise_alpha`: None
|
312 |
+
- `optim_target_modules`: None
|
313 |
+
- `batch_eval_metrics`: False
|
314 |
+
- `eval_on_start`: False
|
315 |
+
- `use_liger_kernel`: False
|
316 |
+
- `eval_use_gather_object`: False
|
317 |
+
- `batch_sampler`: batch_sampler
|
318 |
+
- `multi_dataset_batch_sampler`: proportional
|
319 |
+
|
320 |
+
</details>
|
321 |
+
|
322 |
+
### Training Logs
|
323 |
+
<details><summary>Click to expand</summary>
|
324 |
+
|
325 |
+
| Epoch | Step | Training Loss | loss | beatai-dev_cosine_accuracy |
|
326 |
+
|:-------:|:----:|:-------------:|:------:|:--------------------------:|
|
327 |
+
| 0 | 0 | - | - | 0.7904 |
|
328 |
+
| 0.1471 | 10 | 0.0721 | - | - |
|
329 |
+
| 0.2941 | 20 | 0.0708 | - | - |
|
330 |
+
| 0.4412 | 30 | 0.0736 | - | - |
|
331 |
+
| 0.5882 | 40 | 0.0704 | - | - |
|
332 |
+
| 0.7353 | 50 | 0.0732 | 0.0971 | 0.7929 |
|
333 |
+
| 0.8824 | 60 | 0.0716 | - | - |
|
334 |
+
| 1.0294 | 70 | 0.0665 | - | - |
|
335 |
+
| 1.1765 | 80 | 0.0698 | - | - |
|
336 |
+
| 1.3235 | 90 | 0.0699 | - | - |
|
337 |
+
| 1.4706 | 100 | 0.0691 | 0.0968 | 0.7912 |
|
338 |
+
| 1.6176 | 110 | 0.0687 | - | - |
|
339 |
+
| 1.7647 | 120 | 0.0701 | - | - |
|
340 |
+
| 1.9118 | 130 | 0.0689 | - | - |
|
341 |
+
| 2.0588 | 140 | 0.0696 | - | - |
|
342 |
+
| 2.2059 | 150 | 0.071 | 0.0966 | 0.7929 |
|
343 |
+
| 2.3529 | 160 | 0.078 | - | - |
|
344 |
+
| 2.5 | 170 | 0.0675 | - | - |
|
345 |
+
| 2.6471 | 180 | 0.065 | - | - |
|
346 |
+
| 2.7941 | 190 | 0.0684 | - | - |
|
347 |
+
| 2.9412 | 200 | 0.0689 | 0.0963 | 0.7938 |
|
348 |
+
| 3.0882 | 210 | 0.0736 | - | - |
|
349 |
+
| 3.2353 | 220 | 0.0684 | - | - |
|
350 |
+
| 3.3824 | 230 | 0.0669 | - | - |
|
351 |
+
| 3.5294 | 240 | 0.0688 | - | - |
|
352 |
+
| 3.6765 | 250 | 0.0678 | 0.0959 | 0.7963 |
|
353 |
+
| 3.8235 | 260 | 0.0682 | - | - |
|
354 |
+
| 3.9706 | 270 | 0.0678 | - | - |
|
355 |
+
| 4.1176 | 280 | 0.0686 | - | - |
|
356 |
+
| 4.2647 | 290 | 0.0664 | - | - |
|
357 |
+
| 4.4118 | 300 | 0.0703 | 0.0957 | 0.7980 |
|
358 |
+
| 4.5588 | 310 | 0.065 | - | - |
|
359 |
+
| 4.7059 | 320 | 0.0719 | - | - |
|
360 |
+
| 4.8529 | 330 | 0.0685 | - | - |
|
361 |
+
| 5.0 | 340 | 0.0639 | - | - |
|
362 |
+
| 5.1471 | 350 | 0.0667 | 0.0957 | 0.7971 |
|
363 |
+
| 5.2941 | 360 | 0.0661 | - | - |
|
364 |
+
| 5.4412 | 370 | 0.0678 | - | - |
|
365 |
+
| 5.5882 | 380 | 0.0725 | - | - |
|
366 |
+
| 5.7353 | 390 | 0.0655 | - | - |
|
367 |
+
| 5.8824 | 400 | 0.0649 | 0.0953 | 0.7980 |
|
368 |
+
| 6.0294 | 410 | 0.0661 | - | - |
|
369 |
+
| 6.1765 | 420 | 0.0662 | - | - |
|
370 |
+
| 6.3235 | 430 | 0.0671 | - | - |
|
371 |
+
| 6.4706 | 440 | 0.0698 | - | - |
|
372 |
+
| 6.6176 | 450 | 0.0636 | 0.0951 | 0.7980 |
|
373 |
+
| 6.7647 | 460 | 0.0644 | - | - |
|
374 |
+
| 6.9118 | 470 | 0.0633 | - | - |
|
375 |
+
| 7.0588 | 480 | 0.0679 | - | - |
|
376 |
+
| 7.2059 | 490 | 0.067 | - | - |
|
377 |
+
| 7.3529 | 500 | 0.0713 | 0.0948 | 0.7963 |
|
378 |
+
| 7.5 | 510 | 0.0677 | - | - |
|
379 |
+
| 7.6471 | 520 | 0.0666 | - | - |
|
380 |
+
| 7.7941 | 530 | 0.065 | - | - |
|
381 |
+
| 7.9412 | 540 | 0.0665 | - | - |
|
382 |
+
| 8.0882 | 550 | 0.0656 | 0.0946 | 0.7963 |
|
383 |
+
| 8.2353 | 560 | 0.0649 | - | - |
|
384 |
+
| 8.3824 | 570 | 0.0649 | - | - |
|
385 |
+
| 8.5294 | 580 | 0.0653 | - | - |
|
386 |
+
| 8.6765 | 590 | 0.0648 | - | - |
|
387 |
+
| 8.8235 | 600 | 0.0622 | 0.0944 | 0.7946 |
|
388 |
+
| 8.9706 | 610 | 0.0689 | - | - |
|
389 |
+
| 9.1176 | 620 | 0.0711 | - | - |
|
390 |
+
| 9.2647 | 630 | 0.0611 | - | - |
|
391 |
+
| 9.4118 | 640 | 0.0697 | - | - |
|
392 |
+
| 9.5588 | 650 | 0.0645 | 0.0942 | 0.7963 |
|
393 |
+
| 9.7059 | 660 | 0.0639 | - | - |
|
394 |
+
| 9.8529 | 670 | 0.0643 | - | - |
|
395 |
+
| 10.0 | 680 | 0.0644 | - | - |
|
396 |
+
| 10.1471 | 690 | 0.0599 | - | - |
|
397 |
+
| 10.2941 | 700 | 0.0723 | 0.0940 | 0.7955 |
|
398 |
+
| 10.4412 | 710 | 0.0652 | - | - |
|
399 |
+
| 10.5882 | 720 | 0.0646 | - | - |
|
400 |
+
| 10.7353 | 730 | 0.0602 | - | - |
|
401 |
+
| 10.8824 | 740 | 0.0644 | - | - |
|
402 |
+
| 11.0294 | 750 | 0.066 | 0.0938 | 0.7971 |
|
403 |
+
| 11.1765 | 760 | 0.0624 | - | - |
|
404 |
+
| 11.3235 | 770 | 0.0652 | - | - |
|
405 |
+
| 11.4706 | 780 | 0.0649 | - | - |
|
406 |
+
| 11.6176 | 790 | 0.0624 | - | - |
|
407 |
+
| 11.7647 | 800 | 0.0626 | 0.0937 | 0.7988 |
|
408 |
+
| 11.9118 | 810 | 0.0635 | - | - |
|
409 |
+
| 12.0588 | 820 | 0.0643 | - | - |
|
410 |
+
| 12.2059 | 830 | 0.0663 | - | - |
|
411 |
+
| 12.3529 | 840 | 0.0641 | - | - |
|
412 |
+
| 12.5 | 850 | 0.0614 | 0.0933 | 0.8005 |
|
413 |
+
| 12.6471 | 860 | 0.0613 | - | - |
|
414 |
+
| 12.7941 | 870 | 0.0648 | - | - |
|
415 |
+
| 12.9412 | 880 | 0.065 | - | - |
|
416 |
+
| 13.0882 | 890 | 0.0589 | - | - |
|
417 |
+
| 13.2353 | 900 | 0.0632 | 0.0931 | 0.7997 |
|
418 |
+
| 13.3824 | 910 | 0.0649 | - | - |
|
419 |
+
| 13.5294 | 920 | 0.0612 | - | - |
|
420 |
+
| 13.6765 | 930 | 0.0634 | - | - |
|
421 |
+
| 13.8235 | 940 | 0.0637 | - | - |
|
422 |
+
| 13.9706 | 950 | 0.0626 | 0.0930 | 0.7997 |
|
423 |
+
| 14.1176 | 960 | 0.0593 | - | - |
|
424 |
+
| 14.2647 | 970 | 0.0662 | - | - |
|
425 |
+
| 14.4118 | 980 | 0.0644 | - | - |
|
426 |
+
| 14.5588 | 990 | 0.0582 | - | - |
|
427 |
+
| 14.7059 | 1000 | 0.0626 | 0.0927 | 0.8013 |
|
428 |
+
| 14.8529 | 1010 | 0.0605 | - | - |
|
429 |
+
| 15.0 | 1020 | 0.0615 | - | - |
|
430 |
+
| 15.1471 | 1030 | 0.0676 | - | - |
|
431 |
+
| 15.2941 | 1040 | 0.0633 | - | - |
|
432 |
+
| 15.4412 | 1050 | 0.06 | 0.0927 | 0.8047 |
|
433 |
+
| 15.5882 | 1060 | 0.0572 | - | - |
|
434 |
+
| 15.7353 | 1070 | 0.0579 | - | - |
|
435 |
+
| 15.8824 | 1080 | 0.0594 | - | - |
|
436 |
+
| 16.0294 | 1090 | 0.063 | - | - |
|
437 |
+
| 16.1765 | 1100 | 0.0581 | 0.0927 | 0.8030 |
|
438 |
+
| 16.3235 | 1110 | 0.0564 | - | - |
|
439 |
+
| 16.4706 | 1120 | 0.0632 | - | - |
|
440 |
+
| 16.6176 | 1130 | 0.065 | - | - |
|
441 |
+
| 16.7647 | 1140 | 0.0602 | - | - |
|
442 |
+
| 16.9118 | 1150 | 0.0581 | 0.0926 | 0.8039 |
|
443 |
+
| 17.0588 | 1160 | 0.0623 | - | - |
|
444 |
+
| 17.2059 | 1170 | 0.06 | - | - |
|
445 |
+
| 17.3529 | 1180 | 0.0562 | - | - |
|
446 |
+
| 17.5 | 1190 | 0.0627 | - | - |
|
447 |
+
| 17.6471 | 1200 | 0.056 | 0.0924 | 0.8013 |
|
448 |
+
| 17.7941 | 1210 | 0.0586 | - | - |
|
449 |
+
| 17.9412 | 1220 | 0.0576 | - | - |
|
450 |
+
| 18.0882 | 1230 | 0.056 | - | - |
|
451 |
+
| 18.2353 | 1240 | 0.0611 | - | - |
|
452 |
+
| 18.3824 | 1250 | 0.0551 | 0.0922 | 0.8047 |
|
453 |
+
| 18.5294 | 1260 | 0.058 | - | - |
|
454 |
+
| 18.6765 | 1270 | 0.0571 | - | - |
|
455 |
+
| 18.8235 | 1280 | 0.0616 | - | - |
|
456 |
+
| 18.9706 | 1290 | 0.0599 | - | - |
|
457 |
+
| 19.1176 | 1300 | 0.0604 | 0.0920 | 0.8081 |
|
458 |
+
| 19.2647 | 1310 | 0.0633 | - | - |
|
459 |
+
| 19.4118 | 1320 | 0.0573 | - | - |
|
460 |
+
| 19.5588 | 1330 | 0.0549 | - | - |
|
461 |
+
| 19.7059 | 1340 | 0.0591 | - | - |
|
462 |
+
| 19.8529 | 1350 | 0.0585 | 0.0918 | 0.8089 |
|
463 |
+
| 20.0 | 1360 | 0.057 | - | - |
|
464 |
+
| 20.1471 | 1370 | 0.057 | - | - |
|
465 |
+
| 20.2941 | 1380 | 0.0625 | - | - |
|
466 |
+
| 20.4412 | 1390 | 0.0589 | - | - |
|
467 |
+
| 20.5882 | 1400 | 0.0577 | 0.0918 | 0.8098 |
|
468 |
+
| 20.7353 | 1410 | 0.0583 | - | - |
|
469 |
+
| 20.8824 | 1420 | 0.0567 | - | - |
|
470 |
+
| 21.0294 | 1430 | 0.0619 | - | - |
|
471 |
+
| 21.1765 | 1440 | 0.0572 | - | - |
|
472 |
+
| 21.3235 | 1450 | 0.0594 | 0.0917 | 0.8123 |
|
473 |
+
| 21.4706 | 1460 | 0.0567 | - | - |
|
474 |
+
| 21.6176 | 1470 | 0.0611 | - | - |
|
475 |
+
| 21.7647 | 1480 | 0.0533 | - | - |
|
476 |
+
| 21.9118 | 1490 | 0.0595 | - | - |
|
477 |
+
| 22.0588 | 1500 | 0.0521 | 0.0913 | 0.8114 |
|
478 |
+
| 22.2059 | 1510 | 0.0586 | - | - |
|
479 |
+
| 22.3529 | 1520 | 0.0603 | - | - |
|
480 |
+
| 22.5 | 1530 | 0.0601 | - | - |
|
481 |
+
| 22.6471 | 1540 | 0.0567 | - | - |
|
482 |
+
| 22.7941 | 1550 | 0.0551 | 0.0911 | 0.8114 |
|
483 |
+
| 22.9412 | 1560 | 0.0542 | - | - |
|
484 |
+
| 23.0882 | 1570 | 0.057 | - | - |
|
485 |
+
| 23.2353 | 1580 | 0.0541 | - | - |
|
486 |
+
| 23.3824 | 1590 | 0.0586 | - | - |
|
487 |
+
| 23.5294 | 1600 | 0.0573 | 0.0912 | 0.8106 |
|
488 |
+
| 23.6765 | 1610 | 0.0543 | - | - |
|
489 |
+
| 23.8235 | 1620 | 0.0578 | - | - |
|
490 |
+
| 23.9706 | 1630 | 0.0563 | - | - |
|
491 |
+
| 24.1176 | 1640 | 0.0549 | - | - |
|
492 |
+
| 24.2647 | 1650 | 0.0549 | 0.0909 | 0.8140 |
|
493 |
+
| 24.4118 | 1660 | 0.056 | - | - |
|
494 |
+
| 24.5588 | 1670 | 0.0599 | - | - |
|
495 |
+
| 24.7059 | 1680 | 0.0543 | - | - |
|
496 |
+
| 24.8529 | 1690 | 0.0547 | - | - |
|
497 |
+
| 25.0 | 1700 | 0.0575 | 0.0906 | 0.8114 |
|
498 |
+
| 25.1471 | 1710 | 0.0544 | - | - |
|
499 |
+
| 25.2941 | 1720 | 0.0574 | - | - |
|
500 |
+
| 25.4412 | 1730 | 0.0565 | - | - |
|
501 |
+
| 25.5882 | 1740 | 0.0587 | - | - |
|
502 |
+
| 25.7353 | 1750 | 0.0559 | 0.0905 | 0.8157 |
|
503 |
+
| 25.8824 | 1760 | 0.0551 | - | - |
|
504 |
+
| 26.0294 | 1770 | 0.0569 | - | - |
|
505 |
+
| 26.1765 | 1780 | 0.0516 | - | - |
|
506 |
+
| 26.3235 | 1790 | 0.0561 | - | - |
|
507 |
+
| 26.4706 | 1800 | 0.0567 | 0.0906 | 0.8165 |
|
508 |
+
| 26.6176 | 1810 | 0.0599 | - | - |
|
509 |
+
| 26.7647 | 1820 | 0.0577 | - | - |
|
510 |
+
| 26.9118 | 1830 | 0.0532 | - | - |
|
511 |
+
| 27.0588 | 1840 | 0.0554 | - | - |
|
512 |
+
| 27.2059 | 1850 | 0.0579 | 0.0906 | 0.8123 |
|
513 |
+
| 27.3529 | 1860 | 0.0532 | - | - |
|
514 |
+
| 27.5 | 1870 | 0.0493 | - | - |
|
515 |
+
| 27.6471 | 1880 | 0.0552 | - | - |
|
516 |
+
| 27.7941 | 1890 | 0.0532 | - | - |
|
517 |
+
| 27.9412 | 1900 | 0.0569 | 0.0904 | 0.8089 |
|
518 |
+
| 28.0882 | 1910 | 0.0568 | - | - |
|
519 |
+
| 28.2353 | 1920 | 0.052 | - | - |
|
520 |
+
| 28.3824 | 1930 | 0.0555 | - | - |
|
521 |
+
| 28.5294 | 1940 | 0.0563 | - | - |
|
522 |
+
| 28.6765 | 1950 | 0.0555 | 0.0903 | 0.8140 |
|
523 |
+
| 28.8235 | 1960 | 0.0535 | - | - |
|
524 |
+
| 28.9706 | 1970 | 0.0525 | - | - |
|
525 |
+
| 29.1176 | 1980 | 0.0566 | - | - |
|
526 |
+
| 29.2647 | 1990 | 0.0562 | - | - |
|
527 |
+
| 29.4118 | 2000 | 0.0547 | 0.0902 | 0.8140 |
|
528 |
+
| 29.5588 | 2010 | 0.0495 | - | - |
|
529 |
+
| 29.7059 | 2020 | 0.0532 | - | - |
|
530 |
+
| 29.8529 | 2030 | 0.0553 | - | - |
|
531 |
+
| 30.0 | 2040 | 0.0544 | - | - |
|
532 |
+
|
533 |
+
</details>
|
534 |
+
|
535 |
+
### Framework Versions
|
536 |
+
- Python: 3.8.18
|
537 |
+
- Sentence Transformers: 3.1.1
|
538 |
+
- Transformers: 4.45.1
|
539 |
+
- PyTorch: 1.13.1+cu117
|
540 |
+
- Accelerate: 0.34.2
|
541 |
+
- Datasets: 3.0.0
|
542 |
+
- Tokenizers: 0.20.0
|
543 |
+
|
544 |
+
## Citation
|
545 |
+
|
546 |
+
### BibTeX
|
547 |
+
|
548 |
+
#### Sentence Transformers
|
549 |
+
```bibtex
|
550 |
+
@inproceedings{reimers-2019-sentence-bert,
|
551 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
552 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
553 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
554 |
+
month = "11",
|
555 |
+
year = "2019",
|
556 |
+
publisher = "Association for Computational Linguistics",
|
557 |
+
url = "https://arxiv.org/abs/1908.10084",
|
558 |
+
}
|
559 |
+
```
|
560 |
+
|
561 |
+
#### TripletLoss
|
562 |
+
```bibtex
|
563 |
+
@misc{hermans2017defense,
|
564 |
+
title={In Defense of the Triplet Loss for Person Re-Identification},
|
565 |
+
author={Alexander Hermans and Lucas Beyer and Bastian Leibe},
|
566 |
+
year={2017},
|
567 |
+
eprint={1703.07737},
|
568 |
+
archivePrefix={arXiv},
|
569 |
+
primaryClass={cs.CV}
|
570 |
+
}
|
571 |
+
```
|
572 |
+
|
573 |
+
<!--
|
574 |
+
## Glossary
|
575 |
+
|
576 |
+
*Clearly define terms in order to be accessible across audiences.*
|
577 |
+
-->
|
578 |
+
|
579 |
+
<!--
|
580 |
+
## Model Card Authors
|
581 |
+
|
582 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
583 |
+
-->
|
584 |
+
|
585 |
+
<!--
|
586 |
+
## Model Card Contact
|
587 |
+
|
588 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
589 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dbourget/pb-small-10e-tsdae6e-philsim-cosine-6e-beatai-cosine-50e",
|
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": "4.45.1",
|
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": "4.45.1",
|
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:a8484d101ae363b9be14f2fbaa7e43630f5222d0528ea4c7a561491b6086bceb
|
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 |
+
}
|