Add new SentenceTransformer model
Browse files- .gitattributes +1 -0
- 1_Pooling/config.json +10 -0
- README.md +775 -0
- config.json +26 -0
- config_sentence_transformers.json +10 -0
- model.safetensors +3 -0
- modules.json +20 -0
- sentence_bert_config.json +4 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +3 -0
- tokenizer_config.json +56 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
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 +1,775 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: intfloat/multilingual-e5-small
|
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 intfloat/multilingual-e5-small
|
46 |
+
|
47 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [intfloat/multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small). 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:** [intfloat/multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small) <!-- at revision c007d7ef6fd86656326059b28395a7a03a7c5846 -->
|
54 |
+
- **Maximum Sequence Length:** 512 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': 512, '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/eFuck")
|
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 آمار بهتر استفاده کنم؟',
|
97 |
+
'من به دنبال خر��د 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: 6 tokens</li><li>mean: 16.81 tokens</li><li>max: 97 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 16.59 tokens</li><li>max: 59 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 |
+
- `per_device_train_batch_size`: 32
|
177 |
+
- `learning_rate`: 2e-05
|
178 |
+
- `weight_decay`: 0.005
|
179 |
+
- `num_train_epochs`: 10
|
180 |
+
- `warmup_ratio`: 0.1
|
181 |
+
- `batch_sampler`: no_duplicates
|
182 |
+
|
183 |
+
#### All Hyperparameters
|
184 |
+
<details><summary>Click to expand</summary>
|
185 |
+
|
186 |
+
- `overwrite_output_dir`: False
|
187 |
+
- `do_predict`: False
|
188 |
+
- `eval_strategy`: no
|
189 |
+
- `prediction_loss_only`: True
|
190 |
+
- `per_device_train_batch_size`: 32
|
191 |
+
- `per_device_eval_batch_size`: 8
|
192 |
+
- `per_gpu_train_batch_size`: None
|
193 |
+
- `per_gpu_eval_batch_size`: None
|
194 |
+
- `gradient_accumulation_steps`: 1
|
195 |
+
- `eval_accumulation_steps`: None
|
196 |
+
- `torch_empty_cache_steps`: None
|
197 |
+
- `learning_rate`: 2e-05
|
198 |
+
- `weight_decay`: 0.005
|
199 |
+
- `adam_beta1`: 0.9
|
200 |
+
- `adam_beta2`: 0.999
|
201 |
+
- `adam_epsilon`: 1e-08
|
202 |
+
- `max_grad_norm`: 1
|
203 |
+
- `num_train_epochs`: 10
|
204 |
+
- `max_steps`: -1
|
205 |
+
- `lr_scheduler_type`: linear
|
206 |
+
- `lr_scheduler_kwargs`: {}
|
207 |
+
- `warmup_ratio`: 0.1
|
208 |
+
- `warmup_steps`: 0
|
209 |
+
- `log_level`: passive
|
210 |
+
- `log_level_replica`: warning
|
211 |
+
- `log_on_each_node`: True
|
212 |
+
- `logging_nan_inf_filter`: True
|
213 |
+
- `save_safetensors`: True
|
214 |
+
- `save_on_each_node`: False
|
215 |
+
- `save_only_model`: False
|
216 |
+
- `restore_callback_states_from_checkpoint`: False
|
217 |
+
- `no_cuda`: False
|
218 |
+
- `use_cpu`: False
|
219 |
+
- `use_mps_device`: False
|
220 |
+
- `seed`: 42
|
221 |
+
- `data_seed`: None
|
222 |
+
- `jit_mode_eval`: False
|
223 |
+
- `use_ipex`: False
|
224 |
+
- `bf16`: False
|
225 |
+
- `fp16`: False
|
226 |
+
- `fp16_opt_level`: O1
|
227 |
+
- `half_precision_backend`: auto
|
228 |
+
- `bf16_full_eval`: False
|
229 |
+
- `fp16_full_eval`: False
|
230 |
+
- `tf32`: None
|
231 |
+
- `local_rank`: 0
|
232 |
+
- `ddp_backend`: None
|
233 |
+
- `tpu_num_cores`: None
|
234 |
+
- `tpu_metrics_debug`: False
|
235 |
+
- `debug`: []
|
236 |
+
- `dataloader_drop_last`: False
|
237 |
+
- `dataloader_num_workers`: 0
|
238 |
+
- `dataloader_prefetch_factor`: None
|
239 |
+
- `past_index`: -1
|
240 |
+
- `disable_tqdm`: False
|
241 |
+
- `remove_unused_columns`: True
|
242 |
+
- `label_names`: None
|
243 |
+
- `load_best_model_at_end`: False
|
244 |
+
- `ignore_data_skip`: False
|
245 |
+
- `fsdp`: []
|
246 |
+
- `fsdp_min_num_params`: 0
|
247 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
248 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
249 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
250 |
+
- `deepspeed`: None
|
251 |
+
- `label_smoothing_factor`: 0.0
|
252 |
+
- `optim`: adamw_torch
|
253 |
+
- `optim_args`: None
|
254 |
+
- `adafactor`: False
|
255 |
+
- `group_by_length`: False
|
256 |
+
- `length_column_name`: length
|
257 |
+
- `ddp_find_unused_parameters`: None
|
258 |
+
- `ddp_bucket_cap_mb`: None
|
259 |
+
- `ddp_broadcast_buffers`: False
|
260 |
+
- `dataloader_pin_memory`: True
|
261 |
+
- `dataloader_persistent_workers`: False
|
262 |
+
- `skip_memory_metrics`: True
|
263 |
+
- `use_legacy_prediction_loop`: False
|
264 |
+
- `push_to_hub`: False
|
265 |
+
- `resume_from_checkpoint`: None
|
266 |
+
- `hub_model_id`: None
|
267 |
+
- `hub_strategy`: every_save
|
268 |
+
- `hub_private_repo`: None
|
269 |
+
- `hub_always_push`: False
|
270 |
+
- `gradient_checkpointing`: False
|
271 |
+
- `gradient_checkpointing_kwargs`: None
|
272 |
+
- `include_inputs_for_metrics`: False
|
273 |
+
- `include_for_metrics`: []
|
274 |
+
- `eval_do_concat_batches`: True
|
275 |
+
- `fp16_backend`: auto
|
276 |
+
- `push_to_hub_model_id`: None
|
277 |
+
- `push_to_hub_organization`: None
|
278 |
+
- `mp_parameters`:
|
279 |
+
- `auto_find_batch_size`: False
|
280 |
+
- `full_determinism`: False
|
281 |
+
- `torchdynamo`: None
|
282 |
+
- `ray_scope`: last
|
283 |
+
- `ddp_timeout`: 1800
|
284 |
+
- `torch_compile`: False
|
285 |
+
- `torch_compile_backend`: None
|
286 |
+
- `torch_compile_mode`: None
|
287 |
+
- `dispatch_batches`: None
|
288 |
+
- `split_batches`: None
|
289 |
+
- `include_tokens_per_second`: False
|
290 |
+
- `include_num_input_tokens_seen`: False
|
291 |
+
- `neftune_noise_alpha`: None
|
292 |
+
- `optim_target_modules`: None
|
293 |
+
- `batch_eval_metrics`: False
|
294 |
+
- `eval_on_start`: False
|
295 |
+
- `use_liger_kernel`: False
|
296 |
+
- `eval_use_gather_object`: False
|
297 |
+
- `average_tokens_across_devices`: False
|
298 |
+
- `prompts`: None
|
299 |
+
- `batch_sampler`: no_duplicates
|
300 |
+
- `multi_dataset_batch_sampler`: proportional
|
301 |
+
|
302 |
+
</details>
|
303 |
+
|
304 |
+
### Training Logs
|
305 |
+
<details><summary>Click to expand</summary>
|
306 |
+
|
307 |
+
| Epoch | Step | Training Loss |
|
308 |
+
|:------:|:-----:|:-------------:|
|
309 |
+
| 0.0244 | 100 | 1.3984 |
|
310 |
+
| 0.0488 | 200 | 0.8762 |
|
311 |
+
| 0.0732 | 300 | 0.2492 |
|
312 |
+
| 0.0976 | 400 | 0.0754 |
|
313 |
+
| 0.1220 | 500 | 0.0809 |
|
314 |
+
| 0.1464 | 600 | 0.0789 |
|
315 |
+
| 0.1708 | 700 | 0.076 |
|
316 |
+
| 0.1952 | 800 | 0.0642 |
|
317 |
+
| 0.2196 | 900 | 0.0743 |
|
318 |
+
| 0.2440 | 1000 | 0.0605 |
|
319 |
+
| 0.2684 | 1100 | 0.0705 |
|
320 |
+
| 0.2928 | 1200 | 0.0594 |
|
321 |
+
| 0.3172 | 1300 | 0.0565 |
|
322 |
+
| 0.3415 | 1400 | 0.071 |
|
323 |
+
| 0.3659 | 1500 | 0.0476 |
|
324 |
+
| 0.3903 | 1600 | 0.0514 |
|
325 |
+
| 0.4147 | 1700 | 0.0584 |
|
326 |
+
| 0.4391 | 1800 | 0.0649 |
|
327 |
+
| 0.4635 | 1900 | 0.0485 |
|
328 |
+
| 0.4879 | 2000 | 0.0556 |
|
329 |
+
| 0.5123 | 2100 | 0.0594 |
|
330 |
+
| 0.5367 | 2200 | 0.0556 |
|
331 |
+
| 0.5611 | 2300 | 0.0439 |
|
332 |
+
| 0.5855 | 2400 | 0.0619 |
|
333 |
+
| 0.6099 | 2500 | 0.0553 |
|
334 |
+
| 0.6343 | 2600 | 0.0393 |
|
335 |
+
| 0.6587 | 2700 | 0.0458 |
|
336 |
+
| 0.6831 | 2800 | 0.0476 |
|
337 |
+
| 0.7075 | 2900 | 0.0535 |
|
338 |
+
| 0.7319 | 3000 | 0.0439 |
|
339 |
+
| 0.7563 | 3100 | 0.0438 |
|
340 |
+
| 0.7807 | 3200 | 0.052 |
|
341 |
+
| 0.8051 | 3300 | 0.0514 |
|
342 |
+
| 0.8295 | 3400 | 0.0549 |
|
343 |
+
| 0.8539 | 3500 | 0.0439 |
|
344 |
+
| 0.8783 | 3600 | 0.0429 |
|
345 |
+
| 0.9027 | 3700 | 0.0442 |
|
346 |
+
| 0.9271 | 3800 | 0.0643 |
|
347 |
+
| 0.9515 | 3900 | 0.0408 |
|
348 |
+
| 0.9758 | 4000 | 0.0403 |
|
349 |
+
| 1.0002 | 4100 | 0.0446 |
|
350 |
+
| 1.0246 | 4200 | 0.0527 |
|
351 |
+
| 1.0490 | 4300 | 0.0545 |
|
352 |
+
| 1.0734 | 4400 | 0.0517 |
|
353 |
+
| 1.0978 | 4500 | 0.0299 |
|
354 |
+
| 1.1222 | 4600 | 0.0444 |
|
355 |
+
| 1.1466 | 4700 | 0.0475 |
|
356 |
+
| 1.1710 | 4800 | 0.0414 |
|
357 |
+
| 1.1954 | 4900 | 0.0386 |
|
358 |
+
| 1.2198 | 5000 | 0.0508 |
|
359 |
+
| 1.2442 | 5100 | 0.0384 |
|
360 |
+
| 1.2686 | 5200 | 0.0453 |
|
361 |
+
| 1.2930 | 5300 | 0.0401 |
|
362 |
+
| 1.3174 | 5400 | 0.0328 |
|
363 |
+
| 1.3418 | 5500 | 0.0456 |
|
364 |
+
| 1.3662 | 5600 | 0.0295 |
|
365 |
+
| 1.3906 | 5700 | 0.0366 |
|
366 |
+
| 1.4150 | 5800 | 0.0431 |
|
367 |
+
| 1.4394 | 5900 | 0.0442 |
|
368 |
+
| 1.4638 | 6000 | 0.0343 |
|
369 |
+
| 1.4882 | 6100 | 0.0405 |
|
370 |
+
| 1.5126 | 6200 | 0.0357 |
|
371 |
+
| 1.5370 | 6300 | 0.0423 |
|
372 |
+
| 1.5614 | 6400 | 0.0288 |
|
373 |
+
| 1.5858 | 6500 | 0.0393 |
|
374 |
+
| 1.6101 | 6600 | 0.0369 |
|
375 |
+
| 1.6345 | 6700 | 0.0245 |
|
376 |
+
| 1.6589 | 6800 | 0.0286 |
|
377 |
+
| 1.6833 | 6900 | 0.0325 |
|
378 |
+
| 1.7077 | 7000 | 0.0311 |
|
379 |
+
| 1.7321 | 7100 | 0.0272 |
|
380 |
+
| 1.7565 | 7200 | 0.0261 |
|
381 |
+
| 1.7809 | 7300 | 0.0296 |
|
382 |
+
| 1.8053 | 7400 | 0.0343 |
|
383 |
+
| 1.8297 | 7500 | 0.036 |
|
384 |
+
| 1.8541 | 7600 | 0.0225 |
|
385 |
+
| 1.8785 | 7700 | 0.0232 |
|
386 |
+
| 1.9029 | 7800 | 0.0275 |
|
387 |
+
| 1.9273 | 7900 | 0.0394 |
|
388 |
+
| 1.9517 | 8000 | 0.0297 |
|
389 |
+
| 1.9761 | 8100 | 0.0249 |
|
390 |
+
| 2.0005 | 8200 | 0.0268 |
|
391 |
+
| 2.0249 | 8300 | 0.0269 |
|
392 |
+
| 2.0493 | 8400 | 0.0296 |
|
393 |
+
| 2.0737 | 8500 | 0.0326 |
|
394 |
+
| 2.0981 | 8600 | 0.0183 |
|
395 |
+
| 2.1225 | 8700 | 0.024 |
|
396 |
+
| 2.1469 | 8800 | 0.0298 |
|
397 |
+
| 2.1713 | 8900 | 0.0273 |
|
398 |
+
| 2.1957 | 9000 | 0.0244 |
|
399 |
+
| 2.2201 | 9100 | 0.0308 |
|
400 |
+
| 2.2444 | 9200 | 0.0247 |
|
401 |
+
| 2.2688 | 9300 | 0.0299 |
|
402 |
+
| 2.2932 | 9400 | 0.0222 |
|
403 |
+
| 2.3176 | 9500 | 0.0213 |
|
404 |
+
| 2.3420 | 9600 | 0.0316 |
|
405 |
+
| 2.3664 | 9700 | 0.0157 |
|
406 |
+
| 2.3908 | 9800 | 0.0248 |
|
407 |
+
| 2.4152 | 9900 | 0.028 |
|
408 |
+
| 2.4396 | 10000 | 0.0269 |
|
409 |
+
| 2.4640 | 10100 | 0.0214 |
|
410 |
+
| 2.4884 | 10200 | 0.0242 |
|
411 |
+
| 2.5128 | 10300 | 0.0222 |
|
412 |
+
| 2.5372 | 10400 | 0.0253 |
|
413 |
+
| 2.5616 | 10500 | 0.0175 |
|
414 |
+
| 2.5860 | 10600 | 0.0269 |
|
415 |
+
| 2.6104 | 10700 | 0.0281 |
|
416 |
+
| 2.6348 | 10800 | 0.014 |
|
417 |
+
| 2.6592 | 10900 | 0.0187 |
|
418 |
+
| 2.6836 | 11000 | 0.0204 |
|
419 |
+
| 2.7080 | 11100 | 0.0228 |
|
420 |
+
| 2.7324 | 11200 | 0.0193 |
|
421 |
+
| 2.7568 | 11300 | 0.014 |
|
422 |
+
| 2.7812 | 11400 | 0.0171 |
|
423 |
+
| 2.8056 | 11500 | 0.0213 |
|
424 |
+
| 2.8300 | 11600 | 0.025 |
|
425 |
+
| 2.8544 | 11700 | 0.0138 |
|
426 |
+
| 2.8788 | 11800 | 0.0133 |
|
427 |
+
| 2.9031 | 11900 | 0.021 |
|
428 |
+
| 2.9275 | 12000 | 0.0256 |
|
429 |
+
| 2.9519 | 12100 | 0.019 |
|
430 |
+
| 2.9763 | 12200 | 0.0149 |
|
431 |
+
| 3.0007 | 12300 | 0.0192 |
|
432 |
+
| 3.0251 | 12400 | 0.0194 |
|
433 |
+
| 3.0495 | 12500 | 0.0179 |
|
434 |
+
| 3.0739 | 12600 | 0.0218 |
|
435 |
+
| 3.0983 | 12700 | 0.0126 |
|
436 |
+
| 3.1227 | 12800 | 0.018 |
|
437 |
+
| 3.1471 | 12900 | 0.0188 |
|
438 |
+
| 3.1715 | 13000 | 0.0181 |
|
439 |
+
| 3.1959 | 13100 | 0.0186 |
|
440 |
+
| 3.2203 | 13200 | 0.0235 |
|
441 |
+
| 3.2447 | 13300 | 0.0172 |
|
442 |
+
| 3.2691 | 13400 | 0.0183 |
|
443 |
+
| 3.2935 | 13500 | 0.0155 |
|
444 |
+
| 3.3179 | 13600 | 0.0135 |
|
445 |
+
| 3.3423 | 13700 | 0.0236 |
|
446 |
+
| 3.3667 | 13800 | 0.0115 |
|
447 |
+
| 3.3911 | 13900 | 0.0162 |
|
448 |
+
| 3.4155 | 14000 | 0.0207 |
|
449 |
+
| 3.4399 | 14100 | 0.0174 |
|
450 |
+
| 3.4643 | 14200 | 0.0128 |
|
451 |
+
| 3.4887 | 14300 | 0.0202 |
|
452 |
+
| 3.5131 | 14400 | 0.0165 |
|
453 |
+
| 3.5374 | 14500 | 0.0162 |
|
454 |
+
| 3.5618 | 14600 | 0.015 |
|
455 |
+
| 3.5862 | 14700 | 0.0203 |
|
456 |
+
| 3.6106 | 14800 | 0.0222 |
|
457 |
+
| 3.6350 | 14900 | 0.0105 |
|
458 |
+
| 3.6594 | 15000 | 0.014 |
|
459 |
+
| 3.6838 | 15100 | 0.0146 |
|
460 |
+
| 3.7082 | 15200 | 0.015 |
|
461 |
+
| 3.7326 | 15300 | 0.0153 |
|
462 |
+
| 3.7570 | 15400 | 0.0099 |
|
463 |
+
| 3.7814 | 15500 | 0.0105 |
|
464 |
+
| 3.8058 | 15600 | 0.0168 |
|
465 |
+
| 3.8302 | 15700 | 0.0185 |
|
466 |
+
| 3.8546 | 15800 | 0.0104 |
|
467 |
+
| 3.8790 | 15900 | 0.01 |
|
468 |
+
| 3.9034 | 16000 | 0.0142 |
|
469 |
+
| 3.9278 | 16100 | 0.0197 |
|
470 |
+
| 3.9522 | 16200 | 0.013 |
|
471 |
+
| 3.9766 | 16300 | 0.0137 |
|
472 |
+
| 4.0010 | 16400 | 0.0133 |
|
473 |
+
| 4.0254 | 16500 | 0.0132 |
|
474 |
+
| 4.0498 | 16600 | 0.0124 |
|
475 |
+
| 4.0742 | 16700 | 0.0141 |
|
476 |
+
| 4.0986 | 16800 | 0.0099 |
|
477 |
+
| 4.1230 | 16900 | 0.0113 |
|
478 |
+
| 4.1474 | 17000 | 0.0149 |
|
479 |
+
| 4.1717 | 17100 | 0.0145 |
|
480 |
+
| 4.1961 | 17200 | 0.0129 |
|
481 |
+
| 4.2205 | 17300 | 0.0185 |
|
482 |
+
| 4.2449 | 17400 | 0.0138 |
|
483 |
+
| 4.2693 | 17500 | 0.0133 |
|
484 |
+
| 4.2937 | 17600 | 0.0107 |
|
485 |
+
| 4.3181 | 17700 | 0.0092 |
|
486 |
+
| 4.3425 | 17800 | 0.0175 |
|
487 |
+
| 4.3669 | 17900 | 0.0097 |
|
488 |
+
| 4.3913 | 18000 | 0.0111 |
|
489 |
+
| 4.4157 | 18100 | 0.0136 |
|
490 |
+
| 4.4401 | 18200 | 0.0122 |
|
491 |
+
| 4.4645 | 18300 | 0.0095 |
|
492 |
+
| 4.4889 | 18400 | 0.0141 |
|
493 |
+
| 4.5133 | 18500 | 0.0094 |
|
494 |
+
| 4.5377 | 18600 | 0.0123 |
|
495 |
+
| 4.5621 | 18700 | 0.0108 |
|
496 |
+
| 4.5865 | 18800 | 0.0145 |
|
497 |
+
| 4.6109 | 18900 | 0.0195 |
|
498 |
+
| 4.6353 | 19000 | 0.0099 |
|
499 |
+
| 4.6597 | 19100 | 0.0107 |
|
500 |
+
| 4.6841 | 19200 | 0.0105 |
|
501 |
+
| 4.7085 | 19300 | 0.0124 |
|
502 |
+
| 4.7329 | 19400 | 0.012 |
|
503 |
+
| 4.7573 | 19500 | 0.0081 |
|
504 |
+
| 4.7817 | 19600 | 0.0081 |
|
505 |
+
| 4.8061 | 19700 | 0.0111 |
|
506 |
+
| 4.8304 | 19800 | 0.0141 |
|
507 |
+
| 4.8548 | 19900 | 0.0073 |
|
508 |
+
| 4.8792 | 20000 | 0.0094 |
|
509 |
+
| 4.9036 | 20100 | 0.011 |
|
510 |
+
| 4.9280 | 20200 | 0.0157 |
|
511 |
+
| 4.9524 | 20300 | 0.0086 |
|
512 |
+
| 4.9768 | 20400 | 0.0093 |
|
513 |
+
| 5.0012 | 20500 | 0.011 |
|
514 |
+
| 5.0256 | 20600 | 0.0107 |
|
515 |
+
| 5.0500 | 20700 | 0.0094 |
|
516 |
+
| 5.0744 | 20800 | 0.008 |
|
517 |
+
| 5.0988 | 20900 | 0.0076 |
|
518 |
+
| 5.1232 | 21000 | 0.0088 |
|
519 |
+
| 5.1476 | 21100 | 0.0119 |
|
520 |
+
| 5.1720 | 21200 | 0.0118 |
|
521 |
+
| 5.1964 | 21300 | 0.0105 |
|
522 |
+
| 5.2208 | 21400 | 0.0138 |
|
523 |
+
| 5.2452 | 21500 | 0.0109 |
|
524 |
+
| 5.2696 | 21600 | 0.0101 |
|
525 |
+
| 5.2940 | 21700 | 0.008 |
|
526 |
+
| 5.3184 | 21800 | 0.0068 |
|
527 |
+
| 5.3428 | 21900 | 0.0123 |
|
528 |
+
| 5.3672 | 22000 | 0.0086 |
|
529 |
+
| 5.3916 | 22100 | 0.0084 |
|
530 |
+
| 5.4160 | 22200 | 0.0113 |
|
531 |
+
| 5.4404 | 22300 | 0.0086 |
|
532 |
+
| 5.4647 | 22400 | 0.0076 |
|
533 |
+
| 5.4891 | 22500 | 0.0101 |
|
534 |
+
| 5.5135 | 22600 | 0.0083 |
|
535 |
+
| 5.5379 | 22700 | 0.0116 |
|
536 |
+
| 5.5623 | 22800 | 0.0083 |
|
537 |
+
| 5.5867 | 22900 | 0.0137 |
|
538 |
+
| 5.6111 | 23000 | 0.0144 |
|
539 |
+
| 5.6355 | 23100 | 0.0081 |
|
540 |
+
| 5.6599 | 23200 | 0.006 |
|
541 |
+
| 5.6843 | 23300 | 0.0096 |
|
542 |
+
| 5.7087 | 23400 | 0.0098 |
|
543 |
+
| 5.7331 | 23500 | 0.0096 |
|
544 |
+
| 5.7575 | 23600 | 0.0063 |
|
545 |
+
| 5.7819 | 23700 | 0.0052 |
|
546 |
+
| 5.8063 | 23800 | 0.008 |
|
547 |
+
| 5.8307 | 23900 | 0.0117 |
|
548 |
+
| 5.8551 | 24000 | 0.0053 |
|
549 |
+
| 5.8795 | 24100 | 0.0077 |
|
550 |
+
| 5.9039 | 24200 | 0.0086 |
|
551 |
+
| 5.9283 | 24300 | 0.0129 |
|
552 |
+
| 5.9527 | 24400 | 0.0085 |
|
553 |
+
| 5.9771 | 24500 | 0.0064 |
|
554 |
+
| 6.0015 | 24600 | 0.0092 |
|
555 |
+
| 6.0259 | 24700 | 0.0076 |
|
556 |
+
| 6.0503 | 24800 | 0.0078 |
|
557 |
+
| 6.0747 | 24900 | 0.0074 |
|
558 |
+
| 6.0990 | 25000 | 0.0064 |
|
559 |
+
| 6.1234 | 25100 | 0.0067 |
|
560 |
+
| 6.1478 | 25200 | 0.0091 |
|
561 |
+
| 6.1722 | 25300 | 0.0087 |
|
562 |
+
| 6.1966 | 25400 | 0.0076 |
|
563 |
+
| 6.2210 | 25500 | 0.0104 |
|
564 |
+
| 6.2454 | 25600 | 0.0077 |
|
565 |
+
| 6.2698 | 25700 | 0.0074 |
|
566 |
+
| 6.2942 | 25800 | 0.0055 |
|
567 |
+
| 6.3186 | 25900 | 0.0059 |
|
568 |
+
| 6.3430 | 26000 | 0.0092 |
|
569 |
+
| 6.3674 | 26100 | 0.0051 |
|
570 |
+
| 6.3918 | 26200 | 0.0075 |
|
571 |
+
| 6.4162 | 26300 | 0.0093 |
|
572 |
+
| 6.4406 | 26400 | 0.0073 |
|
573 |
+
| 6.4650 | 26500 | 0.0051 |
|
574 |
+
| 6.4894 | 26600 | 0.0093 |
|
575 |
+
| 6.5138 | 26700 | 0.0065 |
|
576 |
+
| 6.5382 | 26800 | 0.0072 |
|
577 |
+
| 6.5626 | 26900 | 0.0075 |
|
578 |
+
| 6.5870 | 27000 | 0.0111 |
|
579 |
+
| 6.6114 | 27100 | 0.0139 |
|
580 |
+
| 6.6358 | 27200 | 0.0066 |
|
581 |
+
| 6.6602 | 27300 | 0.0062 |
|
582 |
+
| 6.6846 | 27400 | 0.0078 |
|
583 |
+
| 6.7090 | 27500 | 0.0084 |
|
584 |
+
| 6.7333 | 27600 | 0.0077 |
|
585 |
+
| 6.7577 | 27700 | 0.0055 |
|
586 |
+
| 6.7821 | 27800 | 0.0039 |
|
587 |
+
| 6.8065 | 27900 | 0.0082 |
|
588 |
+
| 6.8309 | 28000 | 0.0101 |
|
589 |
+
| 6.8553 | 28100 | 0.0041 |
|
590 |
+
| 6.8797 | 28200 | 0.0058 |
|
591 |
+
| 6.9041 | 28300 | 0.0058 |
|
592 |
+
| 6.9285 | 28400 | 0.0109 |
|
593 |
+
| 6.9529 | 28500 | 0.0054 |
|
594 |
+
| 6.9773 | 28600 | 0.0061 |
|
595 |
+
| 7.0017 | 28700 | 0.0078 |
|
596 |
+
| 7.0261 | 28800 | 0.0065 |
|
597 |
+
| 7.0505 | 28900 | 0.0061 |
|
598 |
+
| 7.0749 | 29000 | 0.0049 |
|
599 |
+
| 7.0993 | 29100 | 0.0062 |
|
600 |
+
| 7.1237 | 29200 | 0.0052 |
|
601 |
+
| 7.1481 | 29300 | 0.0073 |
|
602 |
+
| 7.1725 | 29400 | 0.0072 |
|
603 |
+
| 7.1969 | 29500 | 0.0067 |
|
604 |
+
| 7.2213 | 29600 | 0.0093 |
|
605 |
+
| 7.2457 | 29700 | 0.008 |
|
606 |
+
| 7.2701 | 29800 | 0.0057 |
|
607 |
+
| 7.2945 | 29900 | 0.0051 |
|
608 |
+
| 7.3189 | 30000 | 0.0046 |
|
609 |
+
| 7.3433 | 30100 | 0.0078 |
|
610 |
+
| 7.3677 | 30200 | 0.0041 |
|
611 |
+
| 7.3920 | 30300 | 0.0054 |
|
612 |
+
| 7.4164 | 30400 | 0.008 |
|
613 |
+
| 7.4408 | 30500 | 0.0056 |
|
614 |
+
| 7.4652 | 30600 | 0.0037 |
|
615 |
+
| 7.4896 | 30700 | 0.0071 |
|
616 |
+
| 7.5140 | 30800 | 0.0058 |
|
617 |
+
| 7.5384 | 30900 | 0.0074 |
|
618 |
+
| 7.5628 | 31000 | 0.0059 |
|
619 |
+
| 7.5872 | 31100 | 0.0088 |
|
620 |
+
| 7.6116 | 31200 | 0.0102 |
|
621 |
+
| 7.6360 | 31300 | 0.0058 |
|
622 |
+
| 7.6604 | 31400 | 0.0044 |
|
623 |
+
| 7.6848 | 31500 | 0.0065 |
|
624 |
+
| 7.7092 | 31600 | 0.007 |
|
625 |
+
| 7.7336 | 31700 | 0.0078 |
|
626 |
+
| 7.7580 | 31800 | 0.0048 |
|
627 |
+
| 7.7824 | 31900 | 0.0033 |
|
628 |
+
| 7.8068 | 32000 | 0.0063 |
|
629 |
+
| 7.8312 | 32100 | 0.008 |
|
630 |
+
| 7.8556 | 32200 | 0.004 |
|
631 |
+
| 7.8800 | 32300 | 0.0057 |
|
632 |
+
| 7.9044 | 32400 | 0.005 |
|
633 |
+
| 7.9288 | 32500 | 0.0095 |
|
634 |
+
| 7.9532 | 32600 | 0.0042 |
|
635 |
+
| 7.9776 | 32700 | 0.0058 |
|
636 |
+
| 8.0020 | 32800 | 0.006 |
|
637 |
+
| 8.0263 | 32900 | 0.006 |
|
638 |
+
| 8.0507 | 33000 | 0.0054 |
|
639 |
+
| 8.0751 | 33100 | 0.0041 |
|
640 |
+
| 8.0995 | 33200 | 0.0045 |
|
641 |
+
| 8.1239 | 33300 | 0.0052 |
|
642 |
+
| 8.1483 | 33400 | 0.0067 |
|
643 |
+
| 8.1727 | 33500 | 0.008 |
|
644 |
+
| 8.1971 | 33600 | 0.0047 |
|
645 |
+
| 8.2215 | 33700 | 0.0079 |
|
646 |
+
| 8.2459 | 33800 | 0.0071 |
|
647 |
+
| 8.2703 | 33900 | 0.0043 |
|
648 |
+
| 8.2947 | 34000 | 0.0041 |
|
649 |
+
| 8.3191 | 34100 | 0.0035 |
|
650 |
+
| 8.3435 | 34200 | 0.0059 |
|
651 |
+
| 8.3679 | 34300 | 0.004 |
|
652 |
+
| 8.3923 | 34400 | 0.005 |
|
653 |
+
| 8.4167 | 34500 | 0.0067 |
|
654 |
+
| 8.4411 | 34600 | 0.0049 |
|
655 |
+
| 8.4655 | 34700 | 0.0034 |
|
656 |
+
| 8.4899 | 34800 | 0.0057 |
|
657 |
+
| 8.5143 | 34900 | 0.0052 |
|
658 |
+
| 8.5387 | 35000 | 0.005 |
|
659 |
+
| 8.5631 | 35100 | 0.0047 |
|
660 |
+
| 8.5875 | 35200 | 0.0089 |
|
661 |
+
| 8.6119 | 35300 | 0.0066 |
|
662 |
+
| 8.6363 | 35400 | 0.0044 |
|
663 |
+
| 8.6606 | 35500 | 0.0037 |
|
664 |
+
| 8.6850 | 35600 | 0.0059 |
|
665 |
+
| 8.7094 | 35700 | 0.0069 |
|
666 |
+
| 8.7338 | 35800 | 0.0069 |
|
667 |
+
| 8.7582 | 35900 | 0.0038 |
|
668 |
+
| 8.7826 | 36000 | 0.0028 |
|
669 |
+
| 8.8070 | 36100 | 0.0047 |
|
670 |
+
| 8.8314 | 36200 | 0.007 |
|
671 |
+
| 8.8558 | 36300 | 0.0036 |
|
672 |
+
| 8.8802 | 36400 | 0.0049 |
|
673 |
+
| 8.9046 | 36500 | 0.0041 |
|
674 |
+
| 8.9290 | 36600 | 0.0085 |
|
675 |
+
| 8.9534 | 36700 | 0.004 |
|
676 |
+
| 8.9778 | 36800 | 0.0044 |
|
677 |
+
| 9.0022 | 36900 | 0.0053 |
|
678 |
+
| 9.0266 | 37000 | 0.006 |
|
679 |
+
| 9.0510 | 37100 | 0.0051 |
|
680 |
+
| 9.0754 | 37200 | 0.0029 |
|
681 |
+
| 9.0998 | 37300 | 0.0041 |
|
682 |
+
| 9.1242 | 37400 | 0.0046 |
|
683 |
+
| 9.1486 | 37500 | 0.0057 |
|
684 |
+
| 9.1730 | 37600 | 0.0063 |
|
685 |
+
| 9.1974 | 37700 | 0.0048 |
|
686 |
+
| 9.2218 | 37800 | 0.0077 |
|
687 |
+
| 9.2462 | 37900 | 0.0056 |
|
688 |
+
| 9.2706 | 38000 | 0.0039 |
|
689 |
+
| 9.2949 | 38100 | 0.0036 |
|
690 |
+
| 9.3193 | 38200 | 0.0032 |
|
691 |
+
| 9.3437 | 38300 | 0.0055 |
|
692 |
+
| 9.3681 | 38400 | 0.0037 |
|
693 |
+
| 9.3925 | 38500 | 0.0045 |
|
694 |
+
| 9.4169 | 38600 | 0.0065 |
|
695 |
+
| 9.4413 | 38700 | 0.0047 |
|
696 |
+
| 9.4657 | 38800 | 0.0033 |
|
697 |
+
| 9.4901 | 38900 | 0.0052 |
|
698 |
+
| 9.5145 | 39000 | 0.0043 |
|
699 |
+
| 9.5389 | 39100 | 0.0043 |
|
700 |
+
| 9.5633 | 39200 | 0.0049 |
|
701 |
+
| 9.5877 | 39300 | 0.0074 |
|
702 |
+
| 9.6121 | 39400 | 0.0054 |
|
703 |
+
| 9.6365 | 39500 | 0.004 |
|
704 |
+
| 9.6609 | 39600 | 0.0031 |
|
705 |
+
| 9.6853 | 39700 | 0.0054 |
|
706 |
+
| 9.7097 | 39800 | 0.0061 |
|
707 |
+
| 9.7341 | 39900 | 0.0055 |
|
708 |
+
| 9.7585 | 40000 | 0.0033 |
|
709 |
+
| 9.7829 | 40100 | 0.0028 |
|
710 |
+
| 9.8073 | 40200 | 0.0046 |
|
711 |
+
| 9.8317 | 40300 | 0.0062 |
|
712 |
+
| 9.8561 | 40400 | 0.0033 |
|
713 |
+
| 9.8805 | 40500 | 0.0047 |
|
714 |
+
| 9.9049 | 40600 | 0.0045 |
|
715 |
+
| 9.9293 | 40700 | 0.0075 |
|
716 |
+
| 9.9536 | 40800 | 0.0035 |
|
717 |
+
| 9.9780 | 40900 | 0.0038 |
|
718 |
+
|
719 |
+
</details>
|
720 |
+
|
721 |
+
### Framework Versions
|
722 |
+
- Python: 3.10.12
|
723 |
+
- Sentence Transformers: 3.3.1
|
724 |
+
- Transformers: 4.47.0
|
725 |
+
- PyTorch: 2.5.1+cu121
|
726 |
+
- Accelerate: 1.2.1
|
727 |
+
- Datasets: 4.0.0
|
728 |
+
- Tokenizers: 0.21.0
|
729 |
+
|
730 |
+
## Citation
|
731 |
+
|
732 |
+
### BibTeX
|
733 |
+
|
734 |
+
#### Sentence Transformers
|
735 |
+
```bibtex
|
736 |
+
@inproceedings{reimers-2019-sentence-bert,
|
737 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
738 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
739 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
740 |
+
month = "11",
|
741 |
+
year = "2019",
|
742 |
+
publisher = "Association for Computational Linguistics",
|
743 |
+
url = "https://arxiv.org/abs/1908.10084",
|
744 |
+
}
|
745 |
+
```
|
746 |
+
|
747 |
+
#### MultipleNegativesRankingLoss
|
748 |
+
```bibtex
|
749 |
+
@misc{henderson2017efficient,
|
750 |
+
title={Efficient Natural Language Response Suggestion for Smart Reply},
|
751 |
+
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},
|
752 |
+
year={2017},
|
753 |
+
eprint={1705.00652},
|
754 |
+
archivePrefix={arXiv},
|
755 |
+
primaryClass={cs.CL}
|
756 |
+
}
|
757 |
+
```
|
758 |
+
|
759 |
+
<!--
|
760 |
+
## Glossary
|
761 |
+
|
762 |
+
*Clearly define terms in order to be accessible across audiences.*
|
763 |
+
-->
|
764 |
+
|
765 |
+
<!--
|
766 |
+
## Model Card Authors
|
767 |
+
|
768 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
769 |
+
-->
|
770 |
+
|
771 |
+
<!--
|
772 |
+
## Model Card Contact
|
773 |
+
|
774 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
775 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "intfloat/multilingual-e5-small",
|
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": 384,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 1536,
|
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": "XLMRobertaTokenizer",
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.47.0",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 250037
|
26 |
+
}
|
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 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c21a1606b9d53642bcb9f06f7cd6ab913e4d8bd59cf578c715cce7d13b851c7c
|
3 |
+
size 470637416
|
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": 512,
|
3 |
+
"do_lower_case": false
|
4 |
+
}
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
3 |
+
size 5069051
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef04f2b385d1514f500e779207ace0f53e30895ce37563179e29f4022d28ca38
|
3 |
+
size 17083053
|
tokenizer_config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"250001": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"bos_token": "<s>",
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "<s>",
|
47 |
+
"eos_token": "</s>",
|
48 |
+
"extra_special_tokens": {},
|
49 |
+
"mask_token": "<mask>",
|
50 |
+
"model_max_length": 512,
|
51 |
+
"pad_token": "<pad>",
|
52 |
+
"sep_token": "</s>",
|
53 |
+
"sp_model_kwargs": {},
|
54 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
55 |
+
"unk_token": "<unk>"
|
56 |
+
}
|