omarelsayeed
commited on
Commit
•
256b349
1
Parent(s):
c23473d
Upload folder using huggingface_hub
Browse files- 1_Pooling/config.json +10 -0
- README.md +373 -0
- config.json +43 -0
- config_sentence_transformers.json +10 -0
- model.safetensors +3 -0
- modules.json +14 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- vocab.txt +0 -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 +1,373 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language: []
|
3 |
+
library_name: sentence-transformers
|
4 |
+
tags:
|
5 |
+
- sentence-transformers
|
6 |
+
- sentence-similarity
|
7 |
+
- feature-extraction
|
8 |
+
- generated_from_trainer
|
9 |
+
- dataset_size:400000
|
10 |
+
- loss:LoggingBAS
|
11 |
+
base_model: Ammar-alhaj-ali/arabic-MARBERT-sentiment
|
12 |
+
datasets: []
|
13 |
+
widget:
|
14 |
+
- source_sentence: "السلام عليكم \nرجاءً تواصلو معي على الخاص ضروري"
|
15 |
+
sentences:
|
16 |
+
- ياليت والله أنا في المدينة لكن سعر الرحلات غالي 🥺
|
17 |
+
- متوفر ملزمه عامر قدره معرفيه
|
18 |
+
- الف مبرووك
|
19 |
+
- source_sentence: 'قسم بايات الله اسوء موظفين من يوم يشوف وجهي يقول لي تعال الاسبوع
|
20 |
+
الجاي ولي اسبوعين على ذا الحال واليوم اروح يقول لي الموظف مو موجود تعال بكرة
|
21 |
+
|
22 |
+
وانا كل شوي بخرج من الدوام على حساب مزاج الموظف وقت ما يبي يشتغل يخي وش الخدمة
|
23 |
+
ذي
|
24 |
+
|
25 |
+
هذا كله كمان علشان اخذ حقي الله يشغلكم في نفسكم بس'
|
26 |
+
sentences:
|
27 |
+
- امس شاركت بمسابقه وطلعت احتيال واخذوا اخر ١٠٠ بحسابي الله يعوضني العوض الجميل
|
28 |
+
المبارك فيه 🧡..
|
29 |
+
- اسوء وازبل بنك بالتاريخ وانا راح اغرد بالموضوع وادفع عليه فلوس نشر واخلي العالم
|
30 |
+
كلها تشوف التسيب والمصخره اللي انتم فيها
|
31 |
+
- متوفر عندكم معمول خاص بالدايت ( خالي من السكر ) ؟ 🌹
|
32 |
+
- source_sentence: 'أجر لك وأجر لي ساهم معي في التبرع لـ (عليه امر بالتنفيذ وحكم بالسجن
|
33 |
+
عمره 33 عاما متزوج لديه طفل متبقى عليه مبلغ 159342ريال) عبر #منصة_إحسان:'
|
34 |
+
sentences:
|
35 |
+
- تكفى ي يزيد انا في وجهك
|
36 |
+
- طلبت بطاقة سفر بلس قبل حوالي شهر والى الان ماوصلت مع العلم أنه عند إصدارها كان
|
37 |
+
الوقت المستغرق خمسة ايام من تاريخ الإصدار لمن هم خارج الرياض
|
38 |
+
- أسأل الله العلي العظيم ان يوفق الجميع بكل خير وان يارب ❤️❤️🇸🇦🇸🇦🇸🇦💚💚💚💙💙💙
|
39 |
+
- source_sentence: الله ياليت
|
40 |
+
sentences:
|
41 |
+
- 'الله يسعد ايامك
|
42 |
+
|
43 |
+
#حاضر_وموجود'
|
44 |
+
- "حجز عمره \nحجز الصلاة بالروضة\n ب اسعار مناسبه وسرعه بالانجاز\U0001F554⏳\nلتواصل\
|
45 |
+
\ \n 0531927254"
|
46 |
+
- "#يوم_السعادة_العالمي \n#حاضر_وموجود \n#الماجد_للعود \n\nهذا العطر يسعدني برائحته\
|
47 |
+
\ الزكية وتبقى ذكرياته الجميلة وعبقه الرائع في المكان.\nإنه عطر (برستيج روبي)\
|
48 |
+
\ \n(PRESTIGE RUBY )\nالعطر الأجمل والأفضل\nبين كل العطور ."
|
49 |
+
- source_sentence: دائماً موفقين 👍
|
50 |
+
sentences:
|
51 |
+
- العذر اقبح من ذنب مصرف فاشل
|
52 |
+
- "مصرف الانماء \nممكن اعرف ايش يعني هذا في كشف الحساب ومين الدائن ومين المدين ؟من\
|
53 |
+
\ امي اسال محد رد ؟!"
|
54 |
+
- "متجر سبونج يوفر لكم اشتراك رسمي وباسعار مناسبه للجميع ❤️\U0001F44C\U0001F3FB\
|
55 |
+
\ \nوموثقين في معروف وتقدر تشوف تقييماتنا بالموقع الخاص فينا \U0001FAE1"
|
56 |
+
pipeline_tag: sentence-similarity
|
57 |
+
---
|
58 |
+
|
59 |
+
# SentenceTransformer based on Ammar-alhaj-ali/arabic-MARBERT-sentiment
|
60 |
+
|
61 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Ammar-alhaj-ali/arabic-MARBERT-sentiment](https://huggingface.co/Ammar-alhaj-ali/arabic-MARBERT-sentiment). 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.
|
62 |
+
|
63 |
+
## Model Details
|
64 |
+
|
65 |
+
### Model Description
|
66 |
+
- **Model Type:** Sentence Transformer
|
67 |
+
- **Base model:** [Ammar-alhaj-ali/arabic-MARBERT-sentiment](https://huggingface.co/Ammar-alhaj-ali/arabic-MARBERT-sentiment) <!-- at revision db063587f876d5abcf6cdeed70648fc76a30349f -->
|
68 |
+
- **Maximum Sequence Length:** 35 tokens
|
69 |
+
- **Output Dimensionality:** 768 tokens
|
70 |
+
- **Similarity Function:** Cosine Similarity
|
71 |
+
<!-- - **Training Dataset:** Unknown -->
|
72 |
+
<!-- - **Language:** Unknown -->
|
73 |
+
<!-- - **License:** Unknown -->
|
74 |
+
|
75 |
+
### Model Sources
|
76 |
+
|
77 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
78 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
79 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
80 |
+
|
81 |
+
### Full Model Architecture
|
82 |
+
|
83 |
+
```
|
84 |
+
SentenceTransformer(
|
85 |
+
(0): Transformer({'max_seq_length': 35, 'do_lower_case': False}) with Transformer model: BertModel
|
86 |
+
(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})
|
87 |
+
)
|
88 |
+
```
|
89 |
+
|
90 |
+
## Usage
|
91 |
+
|
92 |
+
### Direct Usage (Sentence Transformers)
|
93 |
+
|
94 |
+
First install the Sentence Transformers library:
|
95 |
+
|
96 |
+
```bash
|
97 |
+
pip install -U sentence-transformers
|
98 |
+
```
|
99 |
+
|
100 |
+
Then you can load this model and run inference.
|
101 |
+
```python
|
102 |
+
from sentence_transformers import SentenceTransformer
|
103 |
+
|
104 |
+
# Download from the 🤗 Hub
|
105 |
+
model = SentenceTransformer("sentence_transformers_model_id")
|
106 |
+
# Run inference
|
107 |
+
sentences = [
|
108 |
+
'دائماً موفقين 👍',
|
109 |
+
'متجر سبونج يوفر لكم اشتراك رسمي وباسعار مناسبه للجميع ❤️👌🏻 \nوموثقين في معروف وتقدر تشوف تقييماتنا بالموقع الخاص فينا \U0001fae1',
|
110 |
+
'العذر اقبح من ذنب مصرف فاشل',
|
111 |
+
]
|
112 |
+
embeddings = model.encode(sentences)
|
113 |
+
print(embeddings.shape)
|
114 |
+
# [3, 768]
|
115 |
+
|
116 |
+
# Get the similarity scores for the embeddings
|
117 |
+
similarities = model.similarity(embeddings, embeddings)
|
118 |
+
print(similarities.shape)
|
119 |
+
# [3, 3]
|
120 |
+
```
|
121 |
+
|
122 |
+
<!--
|
123 |
+
### Direct Usage (Transformers)
|
124 |
+
|
125 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
126 |
+
|
127 |
+
</details>
|
128 |
+
-->
|
129 |
+
|
130 |
+
<!--
|
131 |
+
### Downstream Usage (Sentence Transformers)
|
132 |
+
|
133 |
+
You can finetune this model on your own dataset.
|
134 |
+
|
135 |
+
<details><summary>Click to expand</summary>
|
136 |
+
|
137 |
+
</details>
|
138 |
+
-->
|
139 |
+
|
140 |
+
<!--
|
141 |
+
### Out-of-Scope Use
|
142 |
+
|
143 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
144 |
+
-->
|
145 |
+
|
146 |
+
<!--
|
147 |
+
## Bias, Risks and Limitations
|
148 |
+
|
149 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
150 |
+
-->
|
151 |
+
|
152 |
+
<!--
|
153 |
+
### Recommendations
|
154 |
+
|
155 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
156 |
+
-->
|
157 |
+
|
158 |
+
## Training Details
|
159 |
+
|
160 |
+
### Training Dataset
|
161 |
+
|
162 |
+
#### Unnamed Dataset
|
163 |
+
|
164 |
+
|
165 |
+
* Size: 400,000 training samples
|
166 |
+
* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code>
|
167 |
+
* Approximate statistics based on the first 1000 samples:
|
168 |
+
| | sentence_0 | sentence_1 | label |
|
169 |
+
|:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------|
|
170 |
+
| type | string | string | float |
|
171 |
+
| details | <ul><li>min: 3 tokens</li><li>mean: 21.12 tokens</li><li>max: 35 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 19.25 tokens</li><li>max: 35 tokens</li></ul> | <ul><li>min: -1.0</li><li>mean: -0.3</li><li>max: 1.0</li></ul> |
|
172 |
+
* Samples:
|
173 |
+
| sentence_0 | sentence_1 | label |
|
174 |
+
|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------|
|
175 |
+
| <code>سددت مخالفات لسياره الوالد بمبلغ ١٥٠٠ ريال وبقيت معلقه وحاولت اسوي استرداد ولم يتم إرجاع المبلغ واضطريت اسوي سداد للمخالفات مره وراجعت احد فروع بنك الراجحي لارجاع المبلغ يدوياً ولم يتم إرجاع المبلغ وش الحل</code> | <code>ي اخي اسوء بنك كيف م اقدر اطلع مبلغ مسحوب في سنه ٢٠٢٢ ولازم اراجع البنك ع سبب تافه من المفترض اقدر اسويه وانا ف البيت انتم في اي عصر</code> | <code>1.0</code> |
|
176 |
+
| <code>ياليت بس اتمنى اشتري مقاضي العيد<br>ولكن حالتي لايسمح 😔💔💸<br>.<br>.<br>ولكن من أفضل الحسابات حاليا بوجهة نظري انتم ❤️✋️</code> | <code>انا شاري وحدة سكنية عام 1441 من البنك الاهلي والان يوجد اضرار وقدمت ع البنك وحولت معاملتي على التامين المتعاقد مع البنك ورفض معاملتي بحجة ان الشركة المتعاقدة الاولى مع البنك تقلت وهذي الشركة جديده والا تتدخل في الشركة الاولى افادوا ان اللي يعوض البنك . حسبي الله عليكم</code> | <code>-1.0</code> |
|
177 |
+
| <code>عندي مشكله بطاقتي انتهت وجاني وحده جديده مو قادره اضيفها ف الجوال لا يدوي ولا بالمسح ولا حتى بالموقع حقكم ايش الحل</code> | <code>السلام عليكم عندما احاول تسديد اي فاتورة لوزارة العدل والتنفيذ القضائي (للمعسرين) يظهر لي المبلغ المستحق صفر في حين اذا فتحت الفاتورة من بنك آخر يظهر المبلغ مازال موجود المشكلة في بنك الإنماء فقط عندي وعند كذا شخص من معارفي أرجو حلها في أسرع وقت</code> | <code>1.0</code> |
|
178 |
+
* Loss: <code>__main__.LoggingBAS</code> with these parameters:
|
179 |
+
```json
|
180 |
+
{
|
181 |
+
"scale": 20.0,
|
182 |
+
"similarity_fct": "cos_sim"
|
183 |
+
}
|
184 |
+
```
|
185 |
+
|
186 |
+
### Training Hyperparameters
|
187 |
+
#### Non-Default Hyperparameters
|
188 |
+
|
189 |
+
- `per_device_train_batch_size`: 256
|
190 |
+
- `per_device_eval_batch_size`: 256
|
191 |
+
- `num_train_epochs`: 2
|
192 |
+
- `multi_dataset_batch_sampler`: round_robin
|
193 |
+
|
194 |
+
#### All Hyperparameters
|
195 |
+
<details><summary>Click to expand</summary>
|
196 |
+
|
197 |
+
- `overwrite_output_dir`: False
|
198 |
+
- `do_predict`: False
|
199 |
+
- `eval_strategy`: no
|
200 |
+
- `prediction_loss_only`: True
|
201 |
+
- `per_device_train_batch_size`: 256
|
202 |
+
- `per_device_eval_batch_size`: 256
|
203 |
+
- `per_gpu_train_batch_size`: None
|
204 |
+
- `per_gpu_eval_batch_size`: None
|
205 |
+
- `gradient_accumulation_steps`: 1
|
206 |
+
- `eval_accumulation_steps`: None
|
207 |
+
- `learning_rate`: 5e-05
|
208 |
+
- `weight_decay`: 0.0
|
209 |
+
- `adam_beta1`: 0.9
|
210 |
+
- `adam_beta2`: 0.999
|
211 |
+
- `adam_epsilon`: 1e-08
|
212 |
+
- `max_grad_norm`: 1
|
213 |
+
- `num_train_epochs`: 2
|
214 |
+
- `max_steps`: -1
|
215 |
+
- `lr_scheduler_type`: linear
|
216 |
+
- `lr_scheduler_kwargs`: {}
|
217 |
+
- `warmup_ratio`: 0.0
|
218 |
+
- `warmup_steps`: 0
|
219 |
+
- `log_level`: passive
|
220 |
+
- `log_level_replica`: warning
|
221 |
+
- `log_on_each_node`: True
|
222 |
+
- `logging_nan_inf_filter`: True
|
223 |
+
- `save_safetensors`: True
|
224 |
+
- `save_on_each_node`: False
|
225 |
+
- `save_only_model`: False
|
226 |
+
- `restore_callback_states_from_checkpoint`: False
|
227 |
+
- `no_cuda`: False
|
228 |
+
- `use_cpu`: False
|
229 |
+
- `use_mps_device`: False
|
230 |
+
- `seed`: 42
|
231 |
+
- `data_seed`: None
|
232 |
+
- `jit_mode_eval`: False
|
233 |
+
- `use_ipex`: False
|
234 |
+
- `bf16`: False
|
235 |
+
- `fp16`: False
|
236 |
+
- `fp16_opt_level`: O1
|
237 |
+
- `half_precision_backend`: auto
|
238 |
+
- `bf16_full_eval`: False
|
239 |
+
- `fp16_full_eval`: False
|
240 |
+
- `tf32`: None
|
241 |
+
- `local_rank`: 0
|
242 |
+
- `ddp_backend`: None
|
243 |
+
- `tpu_num_cores`: None
|
244 |
+
- `tpu_metrics_debug`: False
|
245 |
+
- `debug`: []
|
246 |
+
- `dataloader_drop_last`: False
|
247 |
+
- `dataloader_num_workers`: 0
|
248 |
+
- `dataloader_prefetch_factor`: None
|
249 |
+
- `past_index`: -1
|
250 |
+
- `disable_tqdm`: False
|
251 |
+
- `remove_unused_columns`: True
|
252 |
+
- `label_names`: None
|
253 |
+
- `load_best_model_at_end`: False
|
254 |
+
- `ignore_data_skip`: False
|
255 |
+
- `fsdp`: []
|
256 |
+
- `fsdp_min_num_params`: 0
|
257 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
258 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
259 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
260 |
+
- `deepspeed`: None
|
261 |
+
- `label_smoothing_factor`: 0.0
|
262 |
+
- `optim`: adamw_torch
|
263 |
+
- `optim_args`: None
|
264 |
+
- `adafactor`: False
|
265 |
+
- `group_by_length`: False
|
266 |
+
- `length_column_name`: length
|
267 |
+
- `ddp_find_unused_parameters`: None
|
268 |
+
- `ddp_bucket_cap_mb`: None
|
269 |
+
- `ddp_broadcast_buffers`: False
|
270 |
+
- `dataloader_pin_memory`: True
|
271 |
+
- `dataloader_persistent_workers`: False
|
272 |
+
- `skip_memory_metrics`: True
|
273 |
+
- `use_legacy_prediction_loop`: False
|
274 |
+
- `push_to_hub`: False
|
275 |
+
- `resume_from_checkpoint`: None
|
276 |
+
- `hub_model_id`: None
|
277 |
+
- `hub_strategy`: every_save
|
278 |
+
- `hub_private_repo`: False
|
279 |
+
- `hub_always_push`: False
|
280 |
+
- `gradient_checkpointing`: False
|
281 |
+
- `gradient_checkpointing_kwargs`: None
|
282 |
+
- `include_inputs_for_metrics`: False
|
283 |
+
- `eval_do_concat_batches`: True
|
284 |
+
- `fp16_backend`: auto
|
285 |
+
- `push_to_hub_model_id`: None
|
286 |
+
- `push_to_hub_organization`: None
|
287 |
+
- `mp_parameters`:
|
288 |
+
- `auto_find_batch_size`: False
|
289 |
+
- `full_determinism`: False
|
290 |
+
- `torchdynamo`: None
|
291 |
+
- `ray_scope`: last
|
292 |
+
- `ddp_timeout`: 1800
|
293 |
+
- `torch_compile`: False
|
294 |
+
- `torch_compile_backend`: None
|
295 |
+
- `torch_compile_mode`: None
|
296 |
+
- `dispatch_batches`: None
|
297 |
+
- `split_batches`: None
|
298 |
+
- `include_tokens_per_second`: False
|
299 |
+
- `include_num_input_tokens_seen`: False
|
300 |
+
- `neftune_noise_alpha`: None
|
301 |
+
- `optim_target_modules`: None
|
302 |
+
- `batch_eval_metrics`: False
|
303 |
+
- `batch_sampler`: batch_sampler
|
304 |
+
- `multi_dataset_batch_sampler`: round_robin
|
305 |
+
|
306 |
+
</details>
|
307 |
+
|
308 |
+
### Training Logs
|
309 |
+
| Epoch | Step | Training Loss |
|
310 |
+
|:------:|:----:|:-------------:|
|
311 |
+
| 0.3199 | 500 | 5.7094 |
|
312 |
+
| 0.6398 | 1000 | 5.4777 |
|
313 |
+
| 0.9597 | 1500 | 5.438 |
|
314 |
+
| 1.2796 | 2000 | 5.4277 |
|
315 |
+
| 1.5995 | 2500 | 5.4283 |
|
316 |
+
| 1.9194 | 3000 | 5.4247 |
|
317 |
+
|
318 |
+
|
319 |
+
### Framework Versions
|
320 |
+
- Python: 3.10.13
|
321 |
+
- Sentence Transformers: 3.0.1
|
322 |
+
- Transformers: 4.41.2
|
323 |
+
- PyTorch: 2.1.2
|
324 |
+
- Accelerate: 0.32.1
|
325 |
+
- Datasets: 2.19.2
|
326 |
+
- Tokenizers: 0.19.1
|
327 |
+
|
328 |
+
## Citation
|
329 |
+
|
330 |
+
### BibTeX
|
331 |
+
|
332 |
+
#### Sentence Transformers
|
333 |
+
```bibtex
|
334 |
+
@inproceedings{reimers-2019-sentence-bert,
|
335 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
336 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
337 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
338 |
+
month = "11",
|
339 |
+
year = "2019",
|
340 |
+
publisher = "Association for Computational Linguistics",
|
341 |
+
url = "https://arxiv.org/abs/1908.10084",
|
342 |
+
}
|
343 |
+
```
|
344 |
+
|
345 |
+
#### LoggingBAS
|
346 |
+
```bibtex
|
347 |
+
@misc{henderson2017efficient,
|
348 |
+
title={Efficient Natural Language Response Suggestion for Smart Reply},
|
349 |
+
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},
|
350 |
+
year={2017},
|
351 |
+
eprint={1705.00652},
|
352 |
+
archivePrefix={arXiv},
|
353 |
+
primaryClass={cs.CL}
|
354 |
+
}
|
355 |
+
```
|
356 |
+
|
357 |
+
<!--
|
358 |
+
## Glossary
|
359 |
+
|
360 |
+
*Clearly define terms in order to be accessible across audiences.*
|
361 |
+
-->
|
362 |
+
|
363 |
+
<!--
|
364 |
+
## Model Card Authors
|
365 |
+
|
366 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
367 |
+
-->
|
368 |
+
|
369 |
+
<!--
|
370 |
+
## Model Card Contact
|
371 |
+
|
372 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
373 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Ammar-alhaj-ali/arabic-MARBERT-sentiment",
|
3 |
+
"architectures": [
|
4 |
+
"BertModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"directionality": "bidi",
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "neutral",
|
15 |
+
"1": "negative",
|
16 |
+
"2": "positive"
|
17 |
+
},
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 3072,
|
20 |
+
"label2id": {
|
21 |
+
"negative": 1,
|
22 |
+
"neutral": 0,
|
23 |
+
"positive": 2
|
24 |
+
},
|
25 |
+
"layer_norm_eps": 1e-12,
|
26 |
+
"max_position_embeddings": 512,
|
27 |
+
"model_type": "bert",
|
28 |
+
"num_attention_heads": 12,
|
29 |
+
"num_hidden_layers": 12,
|
30 |
+
"pad_token_id": 0,
|
31 |
+
"pooler_fc_size": 768,
|
32 |
+
"pooler_num_attention_heads": 12,
|
33 |
+
"pooler_num_fc_layers": 3,
|
34 |
+
"pooler_size_per_head": 128,
|
35 |
+
"pooler_type": "first_token_transform",
|
36 |
+
"position_embedding_type": "absolute",
|
37 |
+
"problem_type": "single_label_classification",
|
38 |
+
"torch_dtype": "float32",
|
39 |
+
"transformers_version": "4.41.2",
|
40 |
+
"type_vocab_size": 2,
|
41 |
+
"use_cache": true,
|
42 |
+
"vocab_size": 100000
|
43 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "3.0.1",
|
4 |
+
"transformers": "4.41.2",
|
5 |
+
"pytorch": "2.1.2"
|
6 |
+
},
|
7 |
+
"prompts": {},
|
8 |
+
"default_prompt_name": null,
|
9 |
+
"similarity_fn_name": null
|
10 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e8440afcb3c4e278f6b9d1083a372b1e7969d525ec209dea18fa320a2c5cbd9
|
3 |
+
size 651387752
|
modules.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[
|
2 |
+
{
|
3 |
+
"idx": 0,
|
4 |
+
"name": "0",
|
5 |
+
"path": "",
|
6 |
+
"type": "sentence_transformers.models.Transformer"
|
7 |
+
},
|
8 |
+
{
|
9 |
+
"idx": 1,
|
10 |
+
"name": "1",
|
11 |
+
"path": "1_Pooling",
|
12 |
+
"type": "sentence_transformers.models.Pooling"
|
13 |
+
}
|
14 |
+
]
|
sentence_bert_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"max_seq_length": 35,
|
3 |
+
"do_lower_case": false
|
4 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"4": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": true,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 1000000000000000019884624838656,
|
50 |
+
"never_split": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"strip_accents": null,
|
54 |
+
"tokenize_chinese_chars": true,
|
55 |
+
"tokenizer_class": "BertTokenizer",
|
56 |
+
"unk_token": "[UNK]"
|
57 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|