Add new SentenceTransformer model
Browse files- 1_Pooling/config.json +10 -0
- README.md +697 -0
- config_sentence_transformers.json +10 -0
- modules.json +20 -0
- sentence_bert_config.json +4 -0
1_Pooling/config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"word_embedding_dimension": 384,
|
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 +1,697 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- sentence-transformers
|
4 |
+
- sentence-similarity
|
5 |
+
- feature-extraction
|
6 |
+
- generated_from_trainer
|
7 |
+
- dataset_size:131157
|
8 |
+
- loss:MultipleNegativesRankingLoss
|
9 |
+
base_model: sentence-transformers/all-MiniLM-L6-v2
|
10 |
+
widget:
|
11 |
+
- source_sentence: عواقب ممنوعیت یادداشت های 500 روپیه و 1000 روپیه در مورد اقتصاد
|
12 |
+
هند چیست؟
|
13 |
+
sentences:
|
14 |
+
- آیا باید در فیزیک و علوم کامپیوتر دو برابر کنم؟
|
15 |
+
- چگونه اقتصاد هند پس از ممنوعیت 500 1000 یادداشت تحت تأثیر قرار گرفت؟
|
16 |
+
- آیا آلمان در اجازه پناهندگان سوری به کشور خود اشتباه کرد؟
|
17 |
+
- source_sentence: بهترین شماره پشتیبانی فنی QuickBooks در نیویورک ، ایالات متحده
|
18 |
+
کدام است؟
|
19 |
+
sentences:
|
20 |
+
- فناوری هایی که اکثر مردم از آنها نمی دانند چیست؟
|
21 |
+
- بهترین شماره پشتیبانی QuickBooks در آرکانزاس چیست؟
|
22 |
+
- چرا در مقایسه با طرف نزدیک ، دهانه های زیادی در قسمت دور ماه وجود دارد؟
|
23 |
+
- source_sentence: اقدامات احتیاطی ایمنی در مورد استفاده از اسلحه های پیشنهادی NRA
|
24 |
+
در میشیگان چیست؟
|
25 |
+
sentences:
|
26 |
+
- پیروزی ترامپ چگونه بر کانادا تأثیر خواهد گذاشت؟
|
27 |
+
- اقدامات احتیاطی ایمنی در مورد استفاده از اسلحه های پیشنهادی NRA در آیداهو چیست؟
|
28 |
+
- مزایای خرید بیمه عمر چیست؟
|
29 |
+
- source_sentence: چرا این همه افراد ناراضی هستند؟
|
30 |
+
sentences:
|
31 |
+
- چرا آب نبات تافی آب شور در مغولستان وارد می شود؟
|
32 |
+
- برای یک رابطه موفق از راه دور چه چیزی طول می کشد؟
|
33 |
+
- چرا مردم ناراضی هستند؟
|
34 |
+
- source_sentence: برای تبدیل شدن به نویسنده برتر Quora ، چند بازدید و پاسخ لازم است؟
|
35 |
+
sentences:
|
36 |
+
- چگونه می توانم نویسنده برتر Quora شوم ، از صعود بیشتر و آمار بهتر استفاده کنم؟
|
37 |
+
- چرا بسیاری از افرادی که سؤالاتی را در Quora ارسال می کنند ، ابتدا Google را بررسی
|
38 |
+
می کنند؟
|
39 |
+
- من به دنبال خرید دوچرخه جدید هستم.Suzuki Gixxer 155 یا Honda Hornet 160r.کدام
|
40 |
+
یک را بخرید؟
|
41 |
+
pipeline_tag: sentence-similarity
|
42 |
+
library_name: sentence-transformers
|
43 |
+
---
|
44 |
+
|
45 |
+
# SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
|
46 |
+
|
47 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2). It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
|
48 |
+
|
49 |
+
## Model Details
|
50 |
+
|
51 |
+
### Model Description
|
52 |
+
- **Model Type:** Sentence Transformer
|
53 |
+
- **Base model:** [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) <!-- at revision c9745ed1d9f207416be6d2e6f8de32d1f16199bf -->
|
54 |
+
- **Maximum Sequence Length:** 256 tokens
|
55 |
+
- **Output Dimensionality:** 384 dimensions
|
56 |
+
- **Similarity Function:** Cosine Similarity
|
57 |
+
<!-- - **Training Dataset:** Unknown -->
|
58 |
+
<!-- - **Language:** Unknown -->
|
59 |
+
<!-- - **License:** Unknown -->
|
60 |
+
|
61 |
+
### Model Sources
|
62 |
+
|
63 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
64 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
65 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
66 |
+
|
67 |
+
### Full Model Architecture
|
68 |
+
|
69 |
+
```
|
70 |
+
SentenceTransformer(
|
71 |
+
(0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: BertModel
|
72 |
+
(1): Pooling({'word_embedding_dimension': 384, '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})
|
73 |
+
(2): Normalize()
|
74 |
+
)
|
75 |
+
```
|
76 |
+
|
77 |
+
## Usage
|
78 |
+
|
79 |
+
### Direct Usage (Sentence Transformers)
|
80 |
+
|
81 |
+
First install the Sentence Transformers library:
|
82 |
+
|
83 |
+
```bash
|
84 |
+
pip install -U sentence-transformers
|
85 |
+
```
|
86 |
+
|
87 |
+
Then you can load this model and run inference.
|
88 |
+
```python
|
89 |
+
from sentence_transformers import SentenceTransformer
|
90 |
+
|
91 |
+
# Download from the 🤗 Hub
|
92 |
+
model = SentenceTransformer("codersan/validadted_allMiniLM_onV9f")
|
93 |
+
# Run inference
|
94 |
+
sentences = [
|
95 |
+
'برای تبدیل شدن به نویسنده برتر Quora ، چند بازدید و پاسخ لازم است؟',
|
96 |
+
'چگونه می توانم نویسنده برتر Quora شوم ، از صعود بیشتر و آما�� بهتر استفاده کنم؟',
|
97 |
+
'من به دنبال خرید دوچرخه جدید هستم.Suzuki Gixxer 155 یا Honda Hornet 160r.کدام یک را بخرید؟',
|
98 |
+
]
|
99 |
+
embeddings = model.encode(sentences)
|
100 |
+
print(embeddings.shape)
|
101 |
+
# [3, 384]
|
102 |
+
|
103 |
+
# Get the similarity scores for the embeddings
|
104 |
+
similarities = model.similarity(embeddings, embeddings)
|
105 |
+
print(similarities.shape)
|
106 |
+
# [3, 3]
|
107 |
+
```
|
108 |
+
|
109 |
+
<!--
|
110 |
+
### Direct Usage (Transformers)
|
111 |
+
|
112 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
113 |
+
|
114 |
+
</details>
|
115 |
+
-->
|
116 |
+
|
117 |
+
<!--
|
118 |
+
### Downstream Usage (Sentence Transformers)
|
119 |
+
|
120 |
+
You can finetune this model on your own dataset.
|
121 |
+
|
122 |
+
<details><summary>Click to expand</summary>
|
123 |
+
|
124 |
+
</details>
|
125 |
+
-->
|
126 |
+
|
127 |
+
<!--
|
128 |
+
### Out-of-Scope Use
|
129 |
+
|
130 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
131 |
+
-->
|
132 |
+
|
133 |
+
<!--
|
134 |
+
## Bias, Risks and Limitations
|
135 |
+
|
136 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
137 |
+
-->
|
138 |
+
|
139 |
+
<!--
|
140 |
+
### Recommendations
|
141 |
+
|
142 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
143 |
+
-->
|
144 |
+
|
145 |
+
## Training Details
|
146 |
+
|
147 |
+
### Training Dataset
|
148 |
+
|
149 |
+
#### Unnamed Dataset
|
150 |
+
|
151 |
+
|
152 |
+
* Size: 131,157 training samples
|
153 |
+
* Columns: <code>anchor</code> and <code>positive</code>
|
154 |
+
* Approximate statistics based on the first 1000 samples:
|
155 |
+
| | anchor | positive |
|
156 |
+
|:--------|:------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
|
157 |
+
| type | string | string |
|
158 |
+
| details | <ul><li>min: 11 tokens</li><li>mean: 44.91 tokens</li><li>max: 256 tokens</li></ul> | <ul><li>min: 11 tokens</li><li>mean: 44.6 tokens</li><li>max: 154 tokens</li></ul> |
|
159 |
+
* Samples:
|
160 |
+
| anchor | positive |
|
161 |
+
|:----------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------|
|
162 |
+
| <code>وقتی سوال من به عنوان "این سوال ممکن است به ویرایش نیاز داشته باشد" چه کاری باید انجام دهم ، اما نمی توانم دلیل آن را پیدا کنم؟</code> | <code>چرا سوال من به عنوان نیاز به پیشرفت مشخص شده است؟</code> |
|
163 |
+
| <code>چگونه می توانید یک فایل رمزگذاری شده را با دانستن اینکه این یک فایل تصویری است بدون دانستن گسترش پرونده یا کلید ، رمزگشایی کنید؟</code> | <code>چگونه می توانید یک فایل رمزگذاری شده را رمزگشایی کنید و بدانید که این یک فایل تصویری است بدون اینکه از پسوند پرونده اطلاع داشته باشید؟</code> |
|
164 |
+
| <code>احساس می کنم خودکشی می کنم ، چگونه باید با آن برخورد کنم؟</code> | <code>احساس می کنم خودکشی می کنم.چه کاری باید انجام دهم؟</code> |
|
165 |
+
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
|
166 |
+
```json
|
167 |
+
{
|
168 |
+
"scale": 20.0,
|
169 |
+
"similarity_fct": "cos_sim"
|
170 |
+
}
|
171 |
+
```
|
172 |
+
|
173 |
+
### Training Hyperparameters
|
174 |
+
#### Non-Default Hyperparameters
|
175 |
+
|
176 |
+
- `eval_strategy`: steps
|
177 |
+
- `per_device_train_batch_size`: 12
|
178 |
+
- `learning_rate`: 5e-06
|
179 |
+
- `weight_decay`: 0.01
|
180 |
+
- `warmup_ratio`: 0.1
|
181 |
+
- `push_to_hub`: True
|
182 |
+
- `hub_model_id`: codersan/validadted_allMiniLM_onV9f
|
183 |
+
- `eval_on_start`: True
|
184 |
+
- `batch_sampler`: no_duplicates
|
185 |
+
|
186 |
+
#### All Hyperparameters
|
187 |
+
<details><summary>Click to expand</summary>
|
188 |
+
|
189 |
+
- `overwrite_output_dir`: False
|
190 |
+
- `do_predict`: False
|
191 |
+
- `eval_strategy`: steps
|
192 |
+
- `prediction_loss_only`: True
|
193 |
+
- `per_device_train_batch_size`: 12
|
194 |
+
- `per_device_eval_batch_size`: 8
|
195 |
+
- `per_gpu_train_batch_size`: None
|
196 |
+
- `per_gpu_eval_batch_size`: None
|
197 |
+
- `gradient_accumulation_steps`: 1
|
198 |
+
- `eval_accumulation_steps`: None
|
199 |
+
- `torch_empty_cache_steps`: None
|
200 |
+
- `learning_rate`: 5e-06
|
201 |
+
- `weight_decay`: 0.01
|
202 |
+
- `adam_beta1`: 0.9
|
203 |
+
- `adam_beta2`: 0.999
|
204 |
+
- `adam_epsilon`: 1e-08
|
205 |
+
- `max_grad_norm`: 1
|
206 |
+
- `num_train_epochs`: 3
|
207 |
+
- `max_steps`: -1
|
208 |
+
- `lr_scheduler_type`: linear
|
209 |
+
- `lr_scheduler_kwargs`: {}
|
210 |
+
- `warmup_ratio`: 0.1
|
211 |
+
- `warmup_steps`: 0
|
212 |
+
- `log_level`: passive
|
213 |
+
- `log_level_replica`: warning
|
214 |
+
- `log_on_each_node`: True
|
215 |
+
- `logging_nan_inf_filter`: True
|
216 |
+
- `save_safetensors`: True
|
217 |
+
- `save_on_each_node`: False
|
218 |
+
- `save_only_model`: False
|
219 |
+
- `restore_callback_states_from_checkpoint`: False
|
220 |
+
- `no_cuda`: False
|
221 |
+
- `use_cpu`: False
|
222 |
+
- `use_mps_device`: False
|
223 |
+
- `seed`: 42
|
224 |
+
- `data_seed`: None
|
225 |
+
- `jit_mode_eval`: False
|
226 |
+
- `use_ipex`: False
|
227 |
+
- `bf16`: False
|
228 |
+
- `fp16`: False
|
229 |
+
- `fp16_opt_level`: O1
|
230 |
+
- `half_precision_backend`: auto
|
231 |
+
- `bf16_full_eval`: False
|
232 |
+
- `fp16_full_eval`: False
|
233 |
+
- `tf32`: None
|
234 |
+
- `local_rank`: 0
|
235 |
+
- `ddp_backend`: None
|
236 |
+
- `tpu_num_cores`: None
|
237 |
+
- `tpu_metrics_debug`: False
|
238 |
+
- `debug`: []
|
239 |
+
- `dataloader_drop_last`: False
|
240 |
+
- `dataloader_num_workers`: 0
|
241 |
+
- `dataloader_prefetch_factor`: None
|
242 |
+
- `past_index`: -1
|
243 |
+
- `disable_tqdm`: False
|
244 |
+
- `remove_unused_columns`: True
|
245 |
+
- `label_names`: None
|
246 |
+
- `load_best_model_at_end`: False
|
247 |
+
- `ignore_data_skip`: False
|
248 |
+
- `fsdp`: []
|
249 |
+
- `fsdp_min_num_params`: 0
|
250 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
251 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
252 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
253 |
+
- `deepspeed`: None
|
254 |
+
- `label_smoothing_factor`: 0.0
|
255 |
+
- `optim`: adamw_torch
|
256 |
+
- `optim_args`: None
|
257 |
+
- `adafactor`: False
|
258 |
+
- `group_by_length`: False
|
259 |
+
- `length_column_name`: length
|
260 |
+
- `ddp_find_unused_parameters`: None
|
261 |
+
- `ddp_bucket_cap_mb`: None
|
262 |
+
- `ddp_broadcast_buffers`: False
|
263 |
+
- `dataloader_pin_memory`: True
|
264 |
+
- `dataloader_persistent_workers`: False
|
265 |
+
- `skip_memory_metrics`: True
|
266 |
+
- `use_legacy_prediction_loop`: False
|
267 |
+
- `push_to_hub`: True
|
268 |
+
- `resume_from_checkpoint`: None
|
269 |
+
- `hub_model_id`: codersan/validadted_allMiniLM_onV9f
|
270 |
+
- `hub_strategy`: every_save
|
271 |
+
- `hub_private_repo`: None
|
272 |
+
- `hub_always_push`: False
|
273 |
+
- `gradient_checkpointing`: False
|
274 |
+
- `gradient_checkpointing_kwargs`: None
|
275 |
+
- `include_inputs_for_metrics`: False
|
276 |
+
- `include_for_metrics`: []
|
277 |
+
- `eval_do_concat_batches`: True
|
278 |
+
- `fp16_backend`: auto
|
279 |
+
- `push_to_hub_model_id`: None
|
280 |
+
- `push_to_hub_organization`: None
|
281 |
+
- `mp_parameters`:
|
282 |
+
- `auto_find_batch_size`: False
|
283 |
+
- `full_determinism`: False
|
284 |
+
- `torchdynamo`: None
|
285 |
+
- `ray_scope`: last
|
286 |
+
- `ddp_timeout`: 1800
|
287 |
+
- `torch_compile`: False
|
288 |
+
- `torch_compile_backend`: None
|
289 |
+
- `torch_compile_mode`: None
|
290 |
+
- `dispatch_batches`: None
|
291 |
+
- `split_batches`: None
|
292 |
+
- `include_tokens_per_second`: False
|
293 |
+
- `include_num_input_tokens_seen`: False
|
294 |
+
- `neftune_noise_alpha`: None
|
295 |
+
- `optim_target_modules`: None
|
296 |
+
- `batch_eval_metrics`: False
|
297 |
+
- `eval_on_start`: True
|
298 |
+
- `use_liger_kernel`: False
|
299 |
+
- `eval_use_gather_object`: False
|
300 |
+
- `average_tokens_across_devices`: False
|
301 |
+
- `prompts`: None
|
302 |
+
- `batch_sampler`: no_duplicates
|
303 |
+
- `multi_dataset_batch_sampler`: proportional
|
304 |
+
|
305 |
+
</details>
|
306 |
+
|
307 |
+
### Training Logs
|
308 |
+
<details><summary>Click to expand</summary>
|
309 |
+
|
310 |
+
| Epoch | Step | Training Loss |
|
311 |
+
|:------:|:-----:|:-------------:|
|
312 |
+
| 0 | 0 | - |
|
313 |
+
| 0.0091 | 100 | 1.4865 |
|
314 |
+
| 0.0183 | 200 | 1.4429 |
|
315 |
+
| 0.0274 | 300 | 1.2725 |
|
316 |
+
| 0.0366 | 400 | 1.1602 |
|
317 |
+
| 0.0457 | 500 | 0.9429 |
|
318 |
+
| 0.0549 | 600 | 0.829 |
|
319 |
+
| 0.0640 | 700 | 0.7771 |
|
320 |
+
| 0.0732 | 800 | 0.6597 |
|
321 |
+
| 0.0823 | 900 | 0.5981 |
|
322 |
+
| 0.0915 | 1000 | 0.5826 |
|
323 |
+
| 0.1006 | 1100 | 0.5956 |
|
324 |
+
| 0.1098 | 1200 | 0.5254 |
|
325 |
+
| 0.1189 | 1300 | 0.5434 |
|
326 |
+
| 0.1281 | 1400 | 0.5495 |
|
327 |
+
| 0.1372 | 1500 | 0.4934 |
|
328 |
+
| 0.1464 | 1600 | 0.4684 |
|
329 |
+
| 0.1555 | 1700 | 0.4489 |
|
330 |
+
| 0.1647 | 1800 | 0.4401 |
|
331 |
+
| 0.1738 | 1900 | 0.4712 |
|
332 |
+
| 0.1830 | 2000 | 0.4407 |
|
333 |
+
| 0.1921 | 2100 | 0.4082 |
|
334 |
+
| 0.2013 | 2200 | 0.4384 |
|
335 |
+
| 0.2104 | 2300 | 0.3621 |
|
336 |
+
| 0.2196 | 2400 | 0.4423 |
|
337 |
+
| 0.2287 | 2500 | 0.4163 |
|
338 |
+
| 0.2379 | 2600 | 0.3769 |
|
339 |
+
| 0.2470 | 2700 | 0.3967 |
|
340 |
+
| 0.2562 | 2800 | 0.3812 |
|
341 |
+
| 0.2653 | 2900 | 0.3813 |
|
342 |
+
| 0.2745 | 3000 | 0.359 |
|
343 |
+
| 0.2836 | 3100 | 0.3454 |
|
344 |
+
| 0.2928 | 3200 | 0.3518 |
|
345 |
+
| 0.3019 | 3300 | 0.3306 |
|
346 |
+
| 0.3111 | 3400 | 0.3138 |
|
347 |
+
| 0.3202 | 3500 | 0.3416 |
|
348 |
+
| 0.3294 | 3600 | 0.3474 |
|
349 |
+
| 0.3385 | 3700 | 0.3153 |
|
350 |
+
| 0.3477 | 3800 | 0.2896 |
|
351 |
+
| 0.3568 | 3900 | 0.2737 |
|
352 |
+
| 0.3660 | 4000 | 0.3004 |
|
353 |
+
| 0.3751 | 4100 | 0.3109 |
|
354 |
+
| 0.3843 | 4200 | 0.2829 |
|
355 |
+
| 0.3934 | 4300 | 0.2729 |
|
356 |
+
| 0.4026 | 4400 | 0.2714 |
|
357 |
+
| 0.4117 | 4500 | 0.3014 |
|
358 |
+
| 0.4209 | 4600 | 0.27 |
|
359 |
+
| 0.4300 | 4700 | 0.3632 |
|
360 |
+
| 0.4392 | 4800 | 0.2571 |
|
361 |
+
| 0.4483 | 4900 | 0.2464 |
|
362 |
+
| 0.4575 | 5000 | 0.2681 |
|
363 |
+
| 0.4666 | 5100 | 0.2579 |
|
364 |
+
| 0.4758 | 5200 | 0.2377 |
|
365 |
+
| 0.4849 | 5300 | 0.2471 |
|
366 |
+
| 0.4941 | 5400 | 0.2625 |
|
367 |
+
| 0.5032 | 5500 | 0.2336 |
|
368 |
+
| 0.5124 | 5600 | 0.2553 |
|
369 |
+
| 0.5215 | 5700 | 0.2549 |
|
370 |
+
| 0.5306 | 5800 | 0.22 |
|
371 |
+
| 0.5398 | 5900 | 0.2682 |
|
372 |
+
| 0.5489 | 6000 | 0.2329 |
|
373 |
+
| 0.5581 | 6100 | 0.2244 |
|
374 |
+
| 0.5672 | 6200 | 0.2458 |
|
375 |
+
| 0.5764 | 6300 | 0.1881 |
|
376 |
+
| 0.5855 | 6400 | 0.209 |
|
377 |
+
| 0.5947 | 6500 | 0.2103 |
|
378 |
+
| 0.6038 | 6600 | 0.1982 |
|
379 |
+
| 0.6130 | 6700 | 0.2023 |
|
380 |
+
| 0.6221 | 6800 | 0.2244 |
|
381 |
+
| 0.6313 | 6900 | 0.2051 |
|
382 |
+
| 0.6404 | 7000 | 0.224 |
|
383 |
+
| 0.6496 | 7100 | 0.2113 |
|
384 |
+
| 0.6587 | 7200 | 0.2386 |
|
385 |
+
| 0.6679 | 7300 | 0.1685 |
|
386 |
+
| 0.6770 | 7400 | 0.2092 |
|
387 |
+
| 0.6862 | 7500 | 0.1832 |
|
388 |
+
| 0.6953 | 7600 | 0.1957 |
|
389 |
+
| 0.7045 | 7700 | 0.2082 |
|
390 |
+
| 0.7136 | 7800 | 0.2213 |
|
391 |
+
| 0.7228 | 7900 | 0.177 |
|
392 |
+
| 0.7319 | 8000 | 0.196 |
|
393 |
+
| 0.7411 | 8100 | 0.2034 |
|
394 |
+
| 0.7502 | 8200 | 0.2017 |
|
395 |
+
| 0.7594 | 8300 | 0.1741 |
|
396 |
+
| 0.7685 | 8400 | 0.2092 |
|
397 |
+
| 0.7777 | 8500 | 0.1684 |
|
398 |
+
| 0.7868 | 8600 | 0.1874 |
|
399 |
+
| 0.7960 | 8700 | 0.1866 |
|
400 |
+
| 0.8051 | 8800 | 0.2291 |
|
401 |
+
| 0.8143 | 8900 | 0.1796 |
|
402 |
+
| 0.8234 | 9000 | 0.2036 |
|
403 |
+
| 0.8326 | 9100 | 0.2173 |
|
404 |
+
| 0.8417 | 9200 | 0.2074 |
|
405 |
+
| 0.8509 | 9300 | 0.1914 |
|
406 |
+
| 0.8600 | 9400 | 0.1639 |
|
407 |
+
| 0.8692 | 9500 | 0.1798 |
|
408 |
+
| 0.8783 | 9600 | 0.1926 |
|
409 |
+
| 0.8875 | 9700 | 0.1672 |
|
410 |
+
| 0.8966 | 9800 | 0.1727 |
|
411 |
+
| 0.9058 | 9900 | 0.189 |
|
412 |
+
| 0.9149 | 10000 | 0.2055 |
|
413 |
+
| 0.9241 | 10100 | 0.2043 |
|
414 |
+
| 0.9332 | 10200 | 0.1515 |
|
415 |
+
| 0.9424 | 10300 | 0.1675 |
|
416 |
+
| 0.9515 | 10400 | 0.1764 |
|
417 |
+
| 0.9607 | 10500 | 0.1709 |
|
418 |
+
| 0.9698 | 10600 | 0.1861 |
|
419 |
+
| 0.9790 | 10700 | 0.1928 |
|
420 |
+
| 0.9881 | 10800 | 0.1756 |
|
421 |
+
| 0.9973 | 10900 | 0.1611 |
|
422 |
+
| 1.0064 | 11000 | 0.1371 |
|
423 |
+
| 1.0156 | 11100 | 0.1499 |
|
424 |
+
| 1.0247 | 11200 | 0.2001 |
|
425 |
+
| 1.0339 | 11300 | 0.197 |
|
426 |
+
| 1.0430 | 11400 | 0.2035 |
|
427 |
+
| 1.0522 | 11500 | 0.1524 |
|
428 |
+
| 1.0613 | 11600 | 0.1988 |
|
429 |
+
| 1.0704 | 11700 | 0.1643 |
|
430 |
+
| 1.0796 | 11800 | 0.1488 |
|
431 |
+
| 1.0887 | 11900 | 0.1402 |
|
432 |
+
| 1.0979 | 12000 | 0.1501 |
|
433 |
+
| 1.1070 | 12100 | 0.1476 |
|
434 |
+
| 1.1162 | 12200 | 0.1703 |
|
435 |
+
| 1.1253 | 12300 | 0.1437 |
|
436 |
+
| 1.1345 | 12400 | 0.1684 |
|
437 |
+
| 1.1436 | 12500 | 0.1583 |
|
438 |
+
| 1.1528 | 12600 | 0.1554 |
|
439 |
+
| 1.1619 | 12700 | 0.1453 |
|
440 |
+
| 1.1711 | 12800 | 0.1592 |
|
441 |
+
| 1.1802 | 12900 | 0.1508 |
|
442 |
+
| 1.1894 | 13000 | 0.1585 |
|
443 |
+
| 1.1985 | 13100 | 0.1381 |
|
444 |
+
| 1.2077 | 13200 | 0.1442 |
|
445 |
+
| 1.2168 | 13300 | 0.183 |
|
446 |
+
| 1.2260 | 13400 | 0.1704 |
|
447 |
+
| 1.2351 | 13500 | 0.152 |
|
448 |
+
| 1.2443 | 13600 | 0.136 |
|
449 |
+
| 1.2534 | 13700 | 0.1596 |
|
450 |
+
| 1.2626 | 13800 | 0.151 |
|
451 |
+
| 1.2717 | 13900 | 0.1597 |
|
452 |
+
| 1.2809 | 14000 | 0.1547 |
|
453 |
+
| 1.2900 | 14100 | 0.1717 |
|
454 |
+
| 1.2992 | 14200 | 0.1037 |
|
455 |
+
| 1.3083 | 14300 | 0.1452 |
|
456 |
+
| 1.3175 | 14400 | 0.155 |
|
457 |
+
| 1.3266 | 14500 | 0.189 |
|
458 |
+
| 1.3358 | 14600 | 0.1384 |
|
459 |
+
| 1.3449 | 14700 | 0.1711 |
|
460 |
+
| 1.3541 | 14800 | 0.1255 |
|
461 |
+
| 1.3632 | 14900 | 0.1439 |
|
462 |
+
| 1.3724 | 15000 | 0.1583 |
|
463 |
+
| 1.3815 | 15100 | 0.1586 |
|
464 |
+
| 1.3907 | 15200 | 0.1502 |
|
465 |
+
| 1.3998 | 15300 | 0.1199 |
|
466 |
+
| 1.4090 | 15400 | 0.1362 |
|
467 |
+
| 1.4181 | 15500 | 0.1502 |
|
468 |
+
| 1.4273 | 15600 | 0.191 |
|
469 |
+
| 1.4364 | 15700 | 0.1495 |
|
470 |
+
| 1.4456 | 15800 | 0.1313 |
|
471 |
+
| 1.4547 | 15900 | 0.1429 |
|
472 |
+
| 1.4639 | 16000 | 0.1004 |
|
473 |
+
| 1.4730 | 16100 | 0.1267 |
|
474 |
+
| 1.4822 | 16200 | 0.1382 |
|
475 |
+
| 1.4913 | 16300 | 0.1535 |
|
476 |
+
| 1.5005 | 16400 | 0.1328 |
|
477 |
+
| 1.5096 | 16500 | 0.1268 |
|
478 |
+
| 1.5188 | 16600 | 0.1819 |
|
479 |
+
| 1.5279 | 16700 | 0.133 |
|
480 |
+
| 1.5371 | 16800 | 0.1503 |
|
481 |
+
| 1.5462 | 16900 | 0.1217 |
|
482 |
+
| 1.5554 | 17000 | 0.1414 |
|
483 |
+
| 1.5645 | 17100 | 0.1413 |
|
484 |
+
| 1.5737 | 17200 | 0.124 |
|
485 |
+
| 1.5828 | 17300 | 0.1111 |
|
486 |
+
| 1.5919 | 17400 | 0.1641 |
|
487 |
+
| 1.6011 | 17500 | 0.1217 |
|
488 |
+
| 1.6102 | 17600 | 0.1148 |
|
489 |
+
| 1.6194 | 17700 | 0.1452 |
|
490 |
+
| 1.6285 | 17800 | 0.1245 |
|
491 |
+
| 1.6377 | 17900 | 0.1184 |
|
492 |
+
| 1.6468 | 18000 | 0.1333 |
|
493 |
+
| 1.6560 | 18100 | 0.1421 |
|
494 |
+
| 1.6651 | 18200 | 0.1243 |
|
495 |
+
| 1.6743 | 18300 | 0.1173 |
|
496 |
+
| 1.6834 | 18400 | 0.117 |
|
497 |
+
| 1.6926 | 18500 | 0.1145 |
|
498 |
+
| 1.7017 | 18600 | 0.1365 |
|
499 |
+
| 1.7109 | 18700 | 0.1404 |
|
500 |
+
| 1.7200 | 18800 | 0.1254 |
|
501 |
+
| 1.7292 | 18900 | 0.1131 |
|
502 |
+
| 1.7383 | 19000 | 0.1503 |
|
503 |
+
| 1.7475 | 19100 | 0.1429 |
|
504 |
+
| 1.7566 | 19200 | 0.1057 |
|
505 |
+
| 1.7658 | 19300 | 0.1221 |
|
506 |
+
| 1.7749 | 19400 | 0.1034 |
|
507 |
+
| 1.7841 | 19500 | 0.1154 |
|
508 |
+
| 1.7932 | 19600 | 0.1106 |
|
509 |
+
| 1.8024 | 19700 | 0.1568 |
|
510 |
+
| 1.8115 | 19800 | 0.1332 |
|
511 |
+
| 1.8207 | 19900 | 0.1238 |
|
512 |
+
| 1.8298 | 20000 | 0.1321 |
|
513 |
+
| 1.8390 | 20100 | 0.1629 |
|
514 |
+
| 1.8481 | 20200 | 0.135 |
|
515 |
+
| 1.8573 | 20300 | 0.1097 |
|
516 |
+
| 1.8664 | 20400 | 0.1233 |
|
517 |
+
| 1.8756 | 20500 | 0.1198 |
|
518 |
+
| 1.8847 | 20600 | 0.1151 |
|
519 |
+
| 1.8939 | 20700 | 0.1206 |
|
520 |
+
| 1.9030 | 20800 | 0.1295 |
|
521 |
+
| 1.9122 | 20900 | 0.126 |
|
522 |
+
| 1.9213 | 21000 | 0.147 |
|
523 |
+
| 1.9305 | 21100 | 0.1316 |
|
524 |
+
| 1.9396 | 21200 | 0.1019 |
|
525 |
+
| 1.9488 | 21300 | 0.1328 |
|
526 |
+
| 1.9579 | 21400 | 0.1127 |
|
527 |
+
| 1.9671 | 21500 | 0.1416 |
|
528 |
+
| 1.9762 | 21600 | 0.1428 |
|
529 |
+
| 1.9854 | 21700 | 0.1481 |
|
530 |
+
| 1.9945 | 21800 | 0.1169 |
|
531 |
+
| 2.0037 | 21900 | 0.1005 |
|
532 |
+
| 2.0128 | 22000 | 0.1114 |
|
533 |
+
| 2.0220 | 22100 | 0.1301 |
|
534 |
+
| 2.0311 | 22200 | 0.1554 |
|
535 |
+
| 2.0403 | 22300 | 0.1623 |
|
536 |
+
| 2.0494 | 22400 | 0.1153 |
|
537 |
+
| 2.0586 | 22500 | 0.1152 |
|
538 |
+
| 2.0677 | 22600 | 0.1406 |
|
539 |
+
| 2.0769 | 22700 | 0.1196 |
|
540 |
+
| 2.0860 | 22800 | 0.1172 |
|
541 |
+
| 2.0952 | 22900 | 0.1153 |
|
542 |
+
| 2.1043 | 23000 | 0.1126 |
|
543 |
+
| 2.1134 | 23100 | 0.1157 |
|
544 |
+
| 2.1226 | 23200 | 0.1102 |
|
545 |
+
| 2.1317 | 23300 | 0.1102 |
|
546 |
+
| 2.1409 | 23400 | 0.1198 |
|
547 |
+
| 2.1500 | 23500 | 0.1241 |
|
548 |
+
| 2.1592 | 23600 | 0.1124 |
|
549 |
+
| 2.1683 | 23700 | 0.1172 |
|
550 |
+
| 2.1775 | 23800 | 0.1161 |
|
551 |
+
| 2.1866 | 23900 | 0.1162 |
|
552 |
+
| 2.1958 | 24000 | 0.1209 |
|
553 |
+
| 2.2049 | 24100 | 0.1039 |
|
554 |
+
| 2.2141 | 24200 | 0.1183 |
|
555 |
+
| 2.2232 | 24300 | 0.1155 |
|
556 |
+
| 2.2324 | 24400 | 0.1168 |
|
557 |
+
| 2.2415 | 24500 | 0.1116 |
|
558 |
+
| 2.2507 | 24600 | 0.1173 |
|
559 |
+
| 2.2598 | 24700 | 0.1321 |
|
560 |
+
| 2.2690 | 24800 | 0.1217 |
|
561 |
+
| 2.2781 | 24900 | 0.1153 |
|
562 |
+
| 2.2873 | 25000 | 0.1464 |
|
563 |
+
| 2.2964 | 25100 | 0.101 |
|
564 |
+
| 2.3056 | 25200 | 0.1042 |
|
565 |
+
| 2.3147 | 25300 | 0.1382 |
|
566 |
+
| 2.3239 | 25400 | 0.1489 |
|
567 |
+
| 2.3330 | 25500 | 0.1187 |
|
568 |
+
| 2.3422 | 25600 | 0.1184 |
|
569 |
+
| 2.3513 | 25700 | 0.0971 |
|
570 |
+
| 2.3605 | 25800 | 0.0986 |
|
571 |
+
| 2.3696 | 25900 | 0.1114 |
|
572 |
+
| 2.3788 | 26000 | 0.1175 |
|
573 |
+
| 2.3879 | 26100 | 0.1136 |
|
574 |
+
| 2.3971 | 26200 | 0.1251 |
|
575 |
+
| 2.4062 | 26300 | 0.1097 |
|
576 |
+
| 2.4154 | 26400 | 0.1123 |
|
577 |
+
| 2.4245 | 26500 | 0.1446 |
|
578 |
+
| 2.4337 | 26600 | 0.1282 |
|
579 |
+
| 2.4428 | 26700 | 0.0988 |
|
580 |
+
| 2.4520 | 26800 | 0.1172 |
|
581 |
+
| 2.4611 | 26900 | 0.0903 |
|
582 |
+
| 2.4703 | 27000 | 0.1049 |
|
583 |
+
| 2.4794 | 27100 | 0.1043 |
|
584 |
+
| 2.4886 | 27200 | 0.1081 |
|
585 |
+
| 2.4977 | 27300 | 0.1265 |
|
586 |
+
| 2.5069 | 27400 | 0.1131 |
|
587 |
+
| 2.5160 | 27500 | 0.1403 |
|
588 |
+
| 2.5252 | 27600 | 0.1033 |
|
589 |
+
| 2.5343 | 27700 | 0.1175 |
|
590 |
+
| 2.5435 | 27800 | 0.1247 |
|
591 |
+
| 2.5526 | 27900 | 0.1115 |
|
592 |
+
| 2.5618 | 28000 | 0.1173 |
|
593 |
+
| 2.5709 | 28100 | 0.1209 |
|
594 |
+
| 2.5801 | 28200 | 0.0894 |
|
595 |
+
| 2.5892 | 28300 | 0.1238 |
|
596 |
+
| 2.5984 | 28400 | 0.1011 |
|
597 |
+
| 2.6075 | 28500 | 0.0976 |
|
598 |
+
| 2.6167 | 28600 | 0.0968 |
|
599 |
+
| 2.6258 | 28700 | 0.1065 |
|
600 |
+
| 2.6349 | 28800 | 0.1011 |
|
601 |
+
| 2.6441 | 28900 | 0.0975 |
|
602 |
+
| 2.6532 | 29000 | 0.1291 |
|
603 |
+
| 2.6624 | 29100 | 0.1118 |
|
604 |
+
| 2.6715 | 29200 | 0.0983 |
|
605 |
+
| 2.6807 | 29300 | 0.1119 |
|
606 |
+
| 2.6898 | 29400 | 0.0728 |
|
607 |
+
| 2.6990 | 29500 | 0.1241 |
|
608 |
+
| 2.7081 | 29600 | 0.1045 |
|
609 |
+
| 2.7173 | 29700 | 0.1186 |
|
610 |
+
| 2.7264 | 29800 | 0.1037 |
|
611 |
+
| 2.7356 | 29900 | 0.129 |
|
612 |
+
| 2.7447 | 30000 | 0.0921 |
|
613 |
+
| 2.7539 | 30100 | 0.1006 |
|
614 |
+
| 2.7630 | 30200 | 0.1068 |
|
615 |
+
| 2.7722 | 30300 | 0.099 |
|
616 |
+
| 2.7813 | 30400 | 0.0949 |
|
617 |
+
| 2.7905 | 30500 | 0.1066 |
|
618 |
+
| 2.7996 | 30600 | 0.1025 |
|
619 |
+
| 2.8088 | 30700 | 0.1148 |
|
620 |
+
| 2.8179 | 30800 | 0.1164 |
|
621 |
+
| 2.8271 | 30900 | 0.1147 |
|
622 |
+
| 2.8362 | 31000 | 0.1298 |
|
623 |
+
| 2.8454 | 31100 | 0.1245 |
|
624 |
+
| 2.8545 | 31200 | 0.087 |
|
625 |
+
| 2.8637 | 31300 | 0.1115 |
|
626 |
+
| 2.8728 | 31400 | 0.1129 |
|
627 |
+
| 2.8820 | 31500 | 0.1121 |
|
628 |
+
| 2.8911 | 31600 | 0.0985 |
|
629 |
+
| 2.9003 | 31700 | 0.1094 |
|
630 |
+
| 2.9094 | 31800 | 0.1296 |
|
631 |
+
| 2.9186 | 31900 | 0.1149 |
|
632 |
+
| 2.9277 | 32000 | 0.1146 |
|
633 |
+
| 2.9369 | 32100 | 0.1147 |
|
634 |
+
| 2.9460 | 32200 | 0.1045 |
|
635 |
+
| 2.9552 | 32300 | 0.0962 |
|
636 |
+
| 2.9643 | 32400 | 0.1065 |
|
637 |
+
| 2.9735 | 32500 | 0.1169 |
|
638 |
+
| 2.9826 | 32600 | 0.1162 |
|
639 |
+
| 2.9918 | 32700 | 0.1134 |
|
640 |
+
|
641 |
+
</details>
|
642 |
+
|
643 |
+
### Framework Versions
|
644 |
+
- Python: 3.10.12
|
645 |
+
- Sentence Transformers: 3.3.1
|
646 |
+
- Transformers: 4.47.0
|
647 |
+
- PyTorch: 2.5.1+cu121
|
648 |
+
- Accelerate: 1.2.1
|
649 |
+
- Datasets: 3.2.0
|
650 |
+
- Tokenizers: 0.21.0
|
651 |
+
|
652 |
+
## Citation
|
653 |
+
|
654 |
+
### BibTeX
|
655 |
+
|
656 |
+
#### Sentence Transformers
|
657 |
+
```bibtex
|
658 |
+
@inproceedings{reimers-2019-sentence-bert,
|
659 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
660 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
661 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
662 |
+
month = "11",
|
663 |
+
year = "2019",
|
664 |
+
publisher = "Association for Computational Linguistics",
|
665 |
+
url = "https://arxiv.org/abs/1908.10084",
|
666 |
+
}
|
667 |
+
```
|
668 |
+
|
669 |
+
#### MultipleNegativesRankingLoss
|
670 |
+
```bibtex
|
671 |
+
@misc{henderson2017efficient,
|
672 |
+
title={Efficient Natural Language Response Suggestion for Smart Reply},
|
673 |
+
author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
|
674 |
+
year={2017},
|
675 |
+
eprint={1705.00652},
|
676 |
+
archivePrefix={arXiv},
|
677 |
+
primaryClass={cs.CL}
|
678 |
+
}
|
679 |
+
```
|
680 |
+
|
681 |
+
<!--
|
682 |
+
## Glossary
|
683 |
+
|
684 |
+
*Clearly define terms in order to be accessible across audiences.*
|
685 |
+
-->
|
686 |
+
|
687 |
+
<!--
|
688 |
+
## Model Card Authors
|
689 |
+
|
690 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
691 |
+
-->
|
692 |
+
|
693 |
+
<!--
|
694 |
+
## Model Card Contact
|
695 |
+
|
696 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
697 |
+
-->
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "3.3.1",
|
4 |
+
"transformers": "4.47.0",
|
5 |
+
"pytorch": "2.5.1+cu121"
|
6 |
+
},
|
7 |
+
"prompts": {},
|
8 |
+
"default_prompt_name": null,
|
9 |
+
"similarity_fn_name": "cosine"
|
10 |
+
}
|
modules.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[
|
2 |
+
{
|
3 |
+
"idx": 0,
|
4 |
+
"name": "0",
|
5 |
+
"path": "",
|
6 |
+
"type": "sentence_transformers.models.Transformer"
|
7 |
+
},
|
8 |
+
{
|
9 |
+
"idx": 1,
|
10 |
+
"name": "1",
|
11 |
+
"path": "1_Pooling",
|
12 |
+
"type": "sentence_transformers.models.Pooling"
|
13 |
+
},
|
14 |
+
{
|
15 |
+
"idx": 2,
|
16 |
+
"name": "2",
|
17 |
+
"path": "2_Normalize",
|
18 |
+
"type": "sentence_transformers.models.Normalize"
|
19 |
+
}
|
20 |
+
]
|
sentence_bert_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"max_seq_length": 256,
|
3 |
+
"do_lower_case": false
|
4 |
+
}
|