ahmadreza123
commited on
Commit
•
35c4781
1
Parent(s):
ca94922
End of training
Browse files- 1_Pooling/config.json +10 -0
- README.md +421 -0
- config_sentence_transformers.json +10 -0
- modules.json +14 -0
- runs/Sep28_15-35-03_f410adec6ee3/events.out.tfevents.1727537724.f410adec6ee3.209.0 +2 -2
- 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": 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 +1,421 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: HooshvareLab/bert-base-parsbert-uncased
|
3 |
+
library_name: sentence-transformers
|
4 |
+
pipeline_tag: sentence-similarity
|
5 |
+
tags:
|
6 |
+
- sentence-transformers
|
7 |
+
- sentence-similarity
|
8 |
+
- feature-extraction
|
9 |
+
- generated_from_trainer
|
10 |
+
- dataset_size:941951
|
11 |
+
- loss:CoSENTLoss
|
12 |
+
widget:
|
13 |
+
- source_sentence: تماشاگران سینما نام او و جسارت افسانه ای او را می دانستند.
|
14 |
+
sentences:
|
15 |
+
- HCFA نظراتی را درخواست و ارزیابی کرد که بسیار بحث برانگیز بود.
|
16 |
+
- زنی در اسکله قدم می زند.
|
17 |
+
- او خجالتی و ترسو است و دوست ندارد ریسک کند.
|
18 |
+
- source_sentence: یک ماشین مسابقه آبی در پیست مسابقه با عدد 90 مشخص شده است.
|
19 |
+
sentences:
|
20 |
+
- من در گذاشتن خیلی خوب هستم.
|
21 |
+
- کارشناسان مافیا گیج شده اند.
|
22 |
+
- یک ماشین مسابقه دارای شماره 90 است.
|
23 |
+
- source_sentence: دوازده کودک در یک مکان گرمسیری در فضای باز جمع می شوند.
|
24 |
+
sentences:
|
25 |
+
- گل زرد در موهای زن است.
|
26 |
+
- گروهی از دانش آموزان در جزیره ای در حال تعطیلات هستند.
|
27 |
+
- تیم های لیگ کوچک مجبور نیستند بازیکنان خود را به تیم های لیگ برتر واگذار کنند.
|
28 |
+
- source_sentence: کارگرانی که در امتداد یک راه آهن شن می چینند.
|
29 |
+
sentences:
|
30 |
+
- آنها روی خط راه آهن کار می کردند.
|
31 |
+
- بسیاری از زنان در انبوهی از مالچ کشتی می گیرند.
|
32 |
+
- سربازان با لباس های جنگ جهانی دوم در حال رژه هستند و یک گروه موسیقی پشت سر آنها
|
33 |
+
رژه می روند.
|
34 |
+
- source_sentence: یک دختر جوان بلوند با پیراهن صورتی به آخوندکی بزرگ در حال نماز
|
35 |
+
روی بازوی خود نگاه می کند.
|
36 |
+
sentences:
|
37 |
+
- مربیان عالی بودند و حتی یکی دو چیز را به بچه ها یاد دادند.
|
38 |
+
- دختر جوانی یک آخوندک نمازگزار روی بازوی خود دارد.
|
39 |
+
- کاخ هنرهای زیبا آثار سوررئالیستی زیادی دارد.
|
40 |
+
---
|
41 |
+
|
42 |
+
# SentenceTransformer based on HooshvareLab/bert-base-parsbert-uncased
|
43 |
+
|
44 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [HooshvareLab/bert-base-parsbert-uncased](https://huggingface.co/HooshvareLab/bert-base-parsbert-uncased) on the csv dataset. 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.
|
45 |
+
|
46 |
+
## Model Details
|
47 |
+
|
48 |
+
### Model Description
|
49 |
+
- **Model Type:** Sentence Transformer
|
50 |
+
- **Base model:** [HooshvareLab/bert-base-parsbert-uncased](https://huggingface.co/HooshvareLab/bert-base-parsbert-uncased) <!-- at revision d73a0e2c7492c33bd5819bcdb23eba207404dd19 -->
|
51 |
+
- **Maximum Sequence Length:** 512 tokens
|
52 |
+
- **Output Dimensionality:** 768 tokens
|
53 |
+
- **Similarity Function:** Cosine Similarity
|
54 |
+
- **Training Dataset:**
|
55 |
+
- csv
|
56 |
+
<!-- - **Language:** Unknown -->
|
57 |
+
<!-- - **License:** Unknown -->
|
58 |
+
|
59 |
+
### Model Sources
|
60 |
+
|
61 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
62 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
63 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
64 |
+
|
65 |
+
### Full Model Architecture
|
66 |
+
|
67 |
+
```
|
68 |
+
SentenceTransformer(
|
69 |
+
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
|
70 |
+
(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})
|
71 |
+
)
|
72 |
+
```
|
73 |
+
|
74 |
+
## Usage
|
75 |
+
|
76 |
+
### Direct Usage (Sentence Transformers)
|
77 |
+
|
78 |
+
First install the Sentence Transformers library:
|
79 |
+
|
80 |
+
```bash
|
81 |
+
pip install -U sentence-transformers
|
82 |
+
```
|
83 |
+
|
84 |
+
Then you can load this model and run inference.
|
85 |
+
```python
|
86 |
+
from sentence_transformers import SentenceTransformer
|
87 |
+
|
88 |
+
# Download from the 🤗 Hub
|
89 |
+
model = SentenceTransformer("sentence_transformers_model_id")
|
90 |
+
# Run inference
|
91 |
+
sentences = [
|
92 |
+
'یک دختر جوان بلوند با پیراهن صورتی به آخوندکی بزرگ در حال نماز روی بازوی خود نگاه می کند.',
|
93 |
+
'دختر جوانی یک آخوندک نمازگزار روی بازوی خود دارد.',
|
94 |
+
'کاخ هنرهای زیبا آثار سوررئالیستی زیادی دارد.',
|
95 |
+
]
|
96 |
+
embeddings = model.encode(sentences)
|
97 |
+
print(embeddings.shape)
|
98 |
+
# [3, 768]
|
99 |
+
|
100 |
+
# Get the similarity scores for the embeddings
|
101 |
+
similarities = model.similarity(embeddings, embeddings)
|
102 |
+
print(similarities.shape)
|
103 |
+
# [3, 3]
|
104 |
+
```
|
105 |
+
|
106 |
+
<!--
|
107 |
+
### Direct Usage (Transformers)
|
108 |
+
|
109 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
110 |
+
|
111 |
+
</details>
|
112 |
+
-->
|
113 |
+
|
114 |
+
<!--
|
115 |
+
### Downstream Usage (Sentence Transformers)
|
116 |
+
|
117 |
+
You can finetune this model on your own dataset.
|
118 |
+
|
119 |
+
<details><summary>Click to expand</summary>
|
120 |
+
|
121 |
+
</details>
|
122 |
+
-->
|
123 |
+
|
124 |
+
<!--
|
125 |
+
### Out-of-Scope Use
|
126 |
+
|
127 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
128 |
+
-->
|
129 |
+
|
130 |
+
<!--
|
131 |
+
## Bias, Risks and Limitations
|
132 |
+
|
133 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
134 |
+
-->
|
135 |
+
|
136 |
+
<!--
|
137 |
+
### Recommendations
|
138 |
+
|
139 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
140 |
+
-->
|
141 |
+
|
142 |
+
## Training Details
|
143 |
+
|
144 |
+
### Training Dataset
|
145 |
+
|
146 |
+
#### csv
|
147 |
+
|
148 |
+
* Dataset: csv
|
149 |
+
* Size: 941,951 training samples
|
150 |
+
* Columns: <code>premise</code>, <code>hypothesis</code>, and <code>score</code>
|
151 |
+
* Approximate statistics based on the first 1000 samples:
|
152 |
+
| | premise | hypothesis | score |
|
153 |
+
|:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:--------------------------------------------------------------|
|
154 |
+
| type | string | string | float |
|
155 |
+
| details | <ul><li>min: 4 tokens</li><li>mean: 20.6 tokens</li><li>max: 125 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 12.1 tokens</li><li>max: 38 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.5</li><li>max: 1.0</li></ul> |
|
156 |
+
* Samples:
|
157 |
+
| premise | hypothesis | score |
|
158 |
+
|:--------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------|:-----------------|
|
159 |
+
| <code>موارد پیکربندی پس از استقرار رسمی</code> | <code>آیتم ها پس از ایجاد رسمی پیکربندی می شوند.</code> | <code>1.0</code> |
|
160 |
+
| <code>به همان خوبی که در دنیای من انجام شده است. سر پرث، موقتاً از خودش راضی بود، رفت و هانسون ایستاد و به مدل خیره شد.</code> | <code>هانسون از خیره شدن به مدل دست کشید و سر پرث را دنبال کرد.</code> | <code>0.0</code> |
|
161 |
+
| <code>به نظر می رسد شما قبلاً رفته اید.</code> | <code>انگار رفتی</code> | <code>1.0</code> |
|
162 |
+
* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
|
163 |
+
```json
|
164 |
+
{
|
165 |
+
"scale": 20.0,
|
166 |
+
"similarity_fct": "pairwise_cos_sim"
|
167 |
+
}
|
168 |
+
```
|
169 |
+
|
170 |
+
### Evaluation Dataset
|
171 |
+
|
172 |
+
#### csv
|
173 |
+
|
174 |
+
* Dataset: csv
|
175 |
+
* Size: 941,951 evaluation samples
|
176 |
+
* Columns: <code>premise</code>, <code>hypothesis</code>, and <code>score</code>
|
177 |
+
* Approximate statistics based on the first 1000 samples:
|
178 |
+
| | premise | hypothesis | score |
|
179 |
+
|:--------|:-----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:--------------------------------------------------------------|
|
180 |
+
| type | string | string | float |
|
181 |
+
| details | <ul><li>min: 4 tokens</li><li>mean: 21.56 tokens</li><li>max: 115 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 12.3 tokens</li><li>max: 42 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.5</li><li>max: 1.0</li></ul> |
|
182 |
+
* Samples:
|
183 |
+
| premise | hypothesis | score |
|
184 |
+
|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------|:-----------------|
|
185 |
+
| <code>آنها سوار بر همدیگر شده بودند و کتک خورده بودند تا اینکه اهمیتی ندادند.</code> | <code>مردم مجروح شده بودند.</code> | <code>1.0</code> |
|
186 |
+
| <code>در منطقه چمن نگه داشتن چمن در مناطق خاص به نوعی سخت است و من واقعاً هرگز به آن فکر نکرده بودم، اما ما تقریباً در بالای این تپه کوچک هستیم و تمام رواناب های حاصل از بتن، اوه خرید مرکز نزدیک ما و کوچه همه چیزهایی که به سمت همسایههای ما میرود، بنابراین این یک چیز کوچکی بود که من واقعاً هرگز به آن فکر نمیکردم و خوشبختانه به این ترتیب انجام شد.</code> | <code>ما روی تپه ای هستیم و آب در نزدیکی همسایه هایمان جمع می شود.</code> | <code>1.0</code> |
|
187 |
+
| <code>زنی با چتر در ایستگاهی نشسته و آگهی تبلیغاتی Aquos روی دیوار دارد.</code> | <code>زنی روی مبل اتاق نشیمنش نشسته است.</code> | <code>0.0</code> |
|
188 |
+
* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
|
189 |
+
```json
|
190 |
+
{
|
191 |
+
"scale": 20.0,
|
192 |
+
"similarity_fct": "pairwise_cos_sim"
|
193 |
+
}
|
194 |
+
```
|
195 |
+
|
196 |
+
### Training Hyperparameters
|
197 |
+
#### Non-Default Hyperparameters
|
198 |
+
|
199 |
+
- `eval_strategy`: steps
|
200 |
+
- `per_device_train_batch_size`: 48
|
201 |
+
- `per_device_eval_batch_size`: 32
|
202 |
+
- `learning_rate`: 2e-05
|
203 |
+
- `num_train_epochs`: 1
|
204 |
+
- `warmup_ratio`: 0.1
|
205 |
+
- `fp16`: True
|
206 |
+
- `push_to_hub`: True
|
207 |
+
- `hub_private_repo`: True
|
208 |
+
- `batch_sampler`: no_duplicates
|
209 |
+
|
210 |
+
#### All Hyperparameters
|
211 |
+
<details><summary>Click to expand</summary>
|
212 |
+
|
213 |
+
- `overwrite_output_dir`: False
|
214 |
+
- `do_predict`: False
|
215 |
+
- `eval_strategy`: steps
|
216 |
+
- `prediction_loss_only`: True
|
217 |
+
- `per_device_train_batch_size`: 48
|
218 |
+
- `per_device_eval_batch_size`: 32
|
219 |
+
- `per_gpu_train_batch_size`: None
|
220 |
+
- `per_gpu_eval_batch_size`: None
|
221 |
+
- `gradient_accumulation_steps`: 1
|
222 |
+
- `eval_accumulation_steps`: None
|
223 |
+
- `torch_empty_cache_steps`: None
|
224 |
+
- `learning_rate`: 2e-05
|
225 |
+
- `weight_decay`: 0.0
|
226 |
+
- `adam_beta1`: 0.9
|
227 |
+
- `adam_beta2`: 0.999
|
228 |
+
- `adam_epsilon`: 1e-08
|
229 |
+
- `max_grad_norm`: 1.0
|
230 |
+
- `num_train_epochs`: 1
|
231 |
+
- `max_steps`: -1
|
232 |
+
- `lr_scheduler_type`: linear
|
233 |
+
- `lr_scheduler_kwargs`: {}
|
234 |
+
- `warmup_ratio`: 0.1
|
235 |
+
- `warmup_steps`: 0
|
236 |
+
- `log_level`: passive
|
237 |
+
- `log_level_replica`: warning
|
238 |
+
- `log_on_each_node`: True
|
239 |
+
- `logging_nan_inf_filter`: True
|
240 |
+
- `save_safetensors`: True
|
241 |
+
- `save_on_each_node`: False
|
242 |
+
- `save_only_model`: False
|
243 |
+
- `restore_callback_states_from_checkpoint`: False
|
244 |
+
- `no_cuda`: False
|
245 |
+
- `use_cpu`: False
|
246 |
+
- `use_mps_device`: False
|
247 |
+
- `seed`: 42
|
248 |
+
- `data_seed`: None
|
249 |
+
- `jit_mode_eval`: False
|
250 |
+
- `use_ipex`: False
|
251 |
+
- `bf16`: False
|
252 |
+
- `fp16`: True
|
253 |
+
- `fp16_opt_level`: O1
|
254 |
+
- `half_precision_backend`: auto
|
255 |
+
- `bf16_full_eval`: False
|
256 |
+
- `fp16_full_eval`: False
|
257 |
+
- `tf32`: None
|
258 |
+
- `local_rank`: 0
|
259 |
+
- `ddp_backend`: None
|
260 |
+
- `tpu_num_cores`: None
|
261 |
+
- `tpu_metrics_debug`: False
|
262 |
+
- `debug`: []
|
263 |
+
- `dataloader_drop_last`: False
|
264 |
+
- `dataloader_num_workers`: 0
|
265 |
+
- `dataloader_prefetch_factor`: None
|
266 |
+
- `past_index`: -1
|
267 |
+
- `disable_tqdm`: False
|
268 |
+
- `remove_unused_columns`: True
|
269 |
+
- `label_names`: None
|
270 |
+
- `load_best_model_at_end`: False
|
271 |
+
- `ignore_data_skip`: False
|
272 |
+
- `fsdp`: []
|
273 |
+
- `fsdp_min_num_params`: 0
|
274 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
275 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
276 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
277 |
+
- `deepspeed`: None
|
278 |
+
- `label_smoothing_factor`: 0.0
|
279 |
+
- `optim`: adamw_torch
|
280 |
+
- `optim_args`: None
|
281 |
+
- `adafactor`: False
|
282 |
+
- `group_by_length`: False
|
283 |
+
- `length_column_name`: length
|
284 |
+
- `ddp_find_unused_parameters`: None
|
285 |
+
- `ddp_bucket_cap_mb`: None
|
286 |
+
- `ddp_broadcast_buffers`: False
|
287 |
+
- `dataloader_pin_memory`: True
|
288 |
+
- `dataloader_persistent_workers`: False
|
289 |
+
- `skip_memory_metrics`: True
|
290 |
+
- `use_legacy_prediction_loop`: False
|
291 |
+
- `push_to_hub`: True
|
292 |
+
- `resume_from_checkpoint`: None
|
293 |
+
- `hub_model_id`: None
|
294 |
+
- `hub_strategy`: every_save
|
295 |
+
- `hub_private_repo`: True
|
296 |
+
- `hub_always_push`: False
|
297 |
+
- `gradient_checkpointing`: False
|
298 |
+
- `gradient_checkpointing_kwargs`: None
|
299 |
+
- `include_inputs_for_metrics`: False
|
300 |
+
- `eval_do_concat_batches`: True
|
301 |
+
- `fp16_backend`: auto
|
302 |
+
- `push_to_hub_model_id`: None
|
303 |
+
- `push_to_hub_organization`: None
|
304 |
+
- `mp_parameters`:
|
305 |
+
- `auto_find_batch_size`: False
|
306 |
+
- `full_determinism`: False
|
307 |
+
- `torchdynamo`: None
|
308 |
+
- `ray_scope`: last
|
309 |
+
- `ddp_timeout`: 1800
|
310 |
+
- `torch_compile`: False
|
311 |
+
- `torch_compile_backend`: None
|
312 |
+
- `torch_compile_mode`: None
|
313 |
+
- `dispatch_batches`: None
|
314 |
+
- `split_batches`: None
|
315 |
+
- `include_tokens_per_second`: False
|
316 |
+
- `include_num_input_tokens_seen`: False
|
317 |
+
- `neftune_noise_alpha`: None
|
318 |
+
- `optim_target_modules`: None
|
319 |
+
- `batch_eval_metrics`: False
|
320 |
+
- `eval_on_start`: False
|
321 |
+
- `eval_use_gather_object`: False
|
322 |
+
- `batch_sampler`: no_duplicates
|
323 |
+
- `multi_dataset_batch_sampler`: proportional
|
324 |
+
|
325 |
+
</details>
|
326 |
+
|
327 |
+
### Training Logs
|
328 |
+
| Epoch | Step | Training Loss | loss |
|
329 |
+
|:------:|:-----:|:-------------:|:------:|
|
330 |
+
| 0.0271 | 500 | 7.0257 | - |
|
331 |
+
| 0.0542 | 1000 | 6.3955 | - |
|
332 |
+
| 0.0813 | 1500 | 6.3502 | - |
|
333 |
+
| 0.1084 | 2000 | 6.3209 | - |
|
334 |
+
| 0.1355 | 2500 | 6.292 | - |
|
335 |
+
| 0.1626 | 3000 | 6.2518 | 5.3943 |
|
336 |
+
| 0.1897 | 3500 | 6.2469 | - |
|
337 |
+
| 0.2168 | 4000 | 6.2352 | - |
|
338 |
+
| 0.2439 | 4500 | 6.2095 | - |
|
339 |
+
| 0.2710 | 5000 | 6.2006 | - |
|
340 |
+
| 0.2982 | 5500 | 6.1951 | - |
|
341 |
+
| 0.3253 | 6000 | 6.1945 | 5.2832 |
|
342 |
+
| 0.3524 | 6500 | 6.1681 | - |
|
343 |
+
| 0.3795 | 7000 | 6.167 | - |
|
344 |
+
| 0.4066 | 7500 | 6.1474 | - |
|
345 |
+
| 0.4337 | 8000 | 6.1506 | - |
|
346 |
+
| 0.4608 | 8500 | 6.1506 | - |
|
347 |
+
| 0.4879 | 9000 | 6.15 | 5.2294 |
|
348 |
+
| 0.5150 | 9500 | 6.1512 | - |
|
349 |
+
| 0.5421 | 10000 | 6.149 | - |
|
350 |
+
| 0.5692 | 10500 | 6.1218 | - |
|
351 |
+
| 0.5963 | 11000 | 6.1312 | - |
|
352 |
+
| 0.6234 | 11500 | 6.1233 | - |
|
353 |
+
| 0.6505 | 12000 | 6.1053 | 5.1807 |
|
354 |
+
| 0.6776 | 12500 | 6.1209 | - |
|
355 |
+
| 0.7047 | 13000 | 6.1088 | - |
|
356 |
+
| 0.7318 | 13500 | 6.0944 | - |
|
357 |
+
| 0.7589 | 14000 | 6.1089 | - |
|
358 |
+
| 0.7860 | 14500 | 6.1062 | - |
|
359 |
+
| 0.8131 | 15000 | 6.0975 | 5.1374 |
|
360 |
+
| 0.8402 | 15500 | 6.1009 | - |
|
361 |
+
| 0.8673 | 16000 | 6.086 | - |
|
362 |
+
| 0.8945 | 16500 | 6.0687 | - |
|
363 |
+
| 0.9216 | 17000 | 6.0804 | - |
|
364 |
+
| 0.9487 | 17500 | 6.0981 | - |
|
365 |
+
| 0.9758 | 18000 | 6.0895 | 5.1153 |
|
366 |
+
|
367 |
+
|
368 |
+
### Framework Versions
|
369 |
+
- Python: 3.10.12
|
370 |
+
- Sentence Transformers: 3.1.1
|
371 |
+
- Transformers: 4.44.2
|
372 |
+
- PyTorch: 2.4.1+cu121
|
373 |
+
- Accelerate: 0.34.2
|
374 |
+
- Datasets: 3.0.1
|
375 |
+
- Tokenizers: 0.19.1
|
376 |
+
|
377 |
+
## Citation
|
378 |
+
|
379 |
+
### BibTeX
|
380 |
+
|
381 |
+
#### Sentence Transformers
|
382 |
+
```bibtex
|
383 |
+
@inproceedings{reimers-2019-sentence-bert,
|
384 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
385 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
386 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
387 |
+
month = "11",
|
388 |
+
year = "2019",
|
389 |
+
publisher = "Association for Computational Linguistics",
|
390 |
+
url = "https://arxiv.org/abs/1908.10084",
|
391 |
+
}
|
392 |
+
```
|
393 |
+
|
394 |
+
#### CoSENTLoss
|
395 |
+
```bibtex
|
396 |
+
@online{kexuefm-8847,
|
397 |
+
title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
|
398 |
+
author={Su Jianlin},
|
399 |
+
year={2022},
|
400 |
+
month={Jan},
|
401 |
+
url={https://kexue.fm/archives/8847},
|
402 |
+
}
|
403 |
+
```
|
404 |
+
|
405 |
+
<!--
|
406 |
+
## Glossary
|
407 |
+
|
408 |
+
*Clearly define terms in order to be accessible across audiences.*
|
409 |
+
-->
|
410 |
+
|
411 |
+
<!--
|
412 |
+
## Model Card Authors
|
413 |
+
|
414 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
415 |
+
-->
|
416 |
+
|
417 |
+
<!--
|
418 |
+
## Model Card Contact
|
419 |
+
|
420 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
421 |
+
-->
|
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": "2.4.1+cu121"
|
6 |
+
},
|
7 |
+
"prompts": {},
|
8 |
+
"default_prompt_name": null,
|
9 |
+
"similarity_fn_name": null
|
10 |
+
}
|
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 |
+
]
|
runs/Sep28_15-35-03_f410adec6ee3/events.out.tfevents.1727537724.f410adec6ee3.209.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:efb6102b4d96e051b8f811eb03ac9b9c25640eb8a2f6364d58e05b305aabb442
|
3 |
+
size 13921
|
sentence_bert_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"max_seq_length": 512,
|
3 |
+
"do_lower_case": false
|
4 |
+
}
|