Hugging Face's logo

acayir64
/
arabic-embedding-model-pair-class2

Sentence Similarity
sentence-transformers
TensorBoard
Safetensors
xlm-roberta
feature-extraction
Trained with AutoTrain
text-embeddings-inference
Inference Endpoints
Model card Files Metrics Community
acayir64 commited on
Commit
1d9a89d
•
1 Parent(s): 5ffb8de

Upload folder using huggingface_hub

Browse files
Files changed (32) hide show
  1. .gitattributes +2 -0
  2. 1_Pooling/config.json +10 -0
  3. README.md +62 -0
  4. checkpoint-781/1_Pooling/config.json +10 -0
  5. checkpoint-781/README.md +388 -0
  6. checkpoint-781/config.json +29 -0
  7. checkpoint-781/config_sentence_transformers.json +10 -0
  8. checkpoint-781/model.safetensors +3 -0
  9. checkpoint-781/modules.json +14 -0
  10. checkpoint-781/optimizer.pt +3 -0
  11. checkpoint-781/rng_state.pth +3 -0
  12. checkpoint-781/scheduler.pt +3 -0
  13. checkpoint-781/sentence_bert_config.json +4 -0
  14. checkpoint-781/sentencepiece.bpe.model +3 -0
  15. checkpoint-781/special_tokens_map.json +51 -0
  16. checkpoint-781/tokenizer.json +3 -0
  17. checkpoint-781/tokenizer_config.json +61 -0
  18. checkpoint-781/trainer_state.json +267 -0
  19. checkpoint-781/training_args.bin +3 -0
  20. config.json +29 -0
  21. config_sentence_transformers.json +10 -0
  22. model.safetensors +3 -0
  23. modules.json +14 -0
  24. runs/Jun18_14-24-12_954fd82b1c9e/events.out.tfevents.1718720653.954fd82b1c9e.34702.0 +2 -2
  25. runs/Jun18_14-24-12_954fd82b1c9e/events.out.tfevents.1718721614.954fd82b1c9e.34702.1 +3 -0
  26. sentence_bert_config.json +4 -0
  27. sentencepiece.bpe.model +3 -0
  28. special_tokens_map.json +51 -0
  29. tokenizer.json +3 -0
  30. tokenizer_config.json +61 -0
  31. training_args.bin +3 -0
  32. training_params.json +33 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ 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
+ checkpoint-781/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
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 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ library_name: sentence-transformers
4
+ tags:
5
+ - sentence-transformers
6
+ - sentence-similarity
7
+ - feature-extraction
8
+ - autotrain
9
+ base_model: symanto/sn-xlm-roberta-base-snli-mnli-anli-xnli
10
+ widget:
11
+ - source_sentence: 'search_query: i love autotrain'
12
+ sentences:
13
+ - 'search_query: huggingface auto train'
14
+ - 'search_query: hugging face auto train'
15
+ - 'search_query: i love autotrain'
16
+ pipeline_tag: sentence-similarity
17
+ ---
18
+
19
+ # Model Trained Using AutoTrain
20
+
21
+ - Problem type: Sentence Transformers
22
+
23
+ ## Validation Metrics
24
+ loss: 1.1031256914138794
25
+
26
+ runtime: 10.5532
27
+
28
+ samples_per_second: 473.788
29
+
30
+ steps_per_second: 14.877
31
+
32
+ : 4.9968010236724245
33
+
34
+ ## Usage
35
+
36
+ ### Direct Usage (Sentence Transformers)
37
+
38
+ First install the Sentence Transformers library:
39
+
40
+ ```bash
41
+ pip install -U sentence-transformers
42
+ ```
43
+
44
+ Then you can load this model and run inference.
45
+ ```python
46
+ from sentence_transformers import SentenceTransformer
47
+
48
+ # Download from the Hugging Face Hub
49
+ model = SentenceTransformer("sentence_transformers_model_id")
50
+ # Run inference
51
+ sentences = [
52
+ 'search_query: autotrain',
53
+ 'search_query: auto train',
54
+ 'search_query: i love autotrain',
55
+ ]
56
+ embeddings = model.encode(sentences)
57
+ print(embeddings.shape)
58
+
59
+ # Get the similarity scores for the embeddings
60
+ similarities = model.similarity(embeddings, embeddings)
61
+ print(similarities.shape)
62
+ ```
checkpoint-781/1_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
+ }
checkpoint-781/README.md ADDED
@@ -0,0 +1,388 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: []
3
+ library_name: sentence-transformers
4
+ tags:
5
+ - sentence-transformers
6
+ - sentence-similarity
7
+ - feature-extraction
8
+ - dataset_size:10K<n<100K
9
+ - loss:SoftmaxLoss
10
+ base_model: symanto/sn-xlm-roberta-base-snli-mnli-anli-xnli
11
+ widget:
12
+ - source_sentence: كير في أمريكا
13
+ sentences:
14
+ - ترامب يؤثر على الثقافة الأمريكية
15
+ - لم يكن هناك أي صراع مع أي شخص.
16
+ - فأخذ زوجان ضد إرادتهما بسبب صراحتهما.
17
+ - source_sentence: الفضائح ممتعة
18
+ sentences:
19
+ - الناس يحبون السماء الزرقاء.
20
+ - قد يعتبر آخرون أنفسهم اشتراكيين.
21
+ - سبرينغر ليست شعبية.
22
+ - source_sentence: الجميع جائعون
23
+ sentences:
24
+ - كان الجميع يكذبون.
25
+ - تم سؤال الخدمة عن الرئيس الميت.
26
+ - ستار) قاوم الربط)
27
+ - source_sentence: لونها طبيعي.
28
+ sentences:
29
+ - يبقيه غبي بسيط وسوف تبدو جيدة.
30
+ - لا أحد يحمل براءة اختراع أبداً.
31
+ - لم تكن محامية جيدة
32
+ - source_sentence: لام هو محافظ.
33
+ sentences:
34
+ - هذا الرجل محافظ
35
+ - على الأرجح أنها ستلتصق بحشواته
36
+ - كانت كلماتها واضحة وموجزة.
37
+ pipeline_tag: sentence-similarity
38
+ ---
39
+
40
+ # SentenceTransformer based on symanto/sn-xlm-roberta-base-snli-mnli-anli-xnli
41
+
42
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [symanto/sn-xlm-roberta-base-snli-mnli-anli-xnli](https://huggingface.co/symanto/sn-xlm-roberta-base-snli-mnli-anli-xnli). 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.
43
+
44
+ ## Model Details
45
+
46
+ ### Model Description
47
+ - **Model Type:** Sentence Transformer
48
+ - **Base model:** [symanto/sn-xlm-roberta-base-snli-mnli-anli-xnli](https://huggingface.co/symanto/sn-xlm-roberta-base-snli-mnli-anli-xnli) <!-- at revision 068f854a8bdff365072583e5fbba7a9c69bd8606 -->
49
+ - **Maximum Sequence Length:** 128 tokens
50
+ - **Output Dimensionality:** 768 tokens
51
+ - **Similarity Function:** Cosine Similarity
52
+ <!-- - **Training Dataset:** Unknown -->
53
+ <!-- - **Language:** Unknown -->
54
+ <!-- - **License:** Unknown -->
55
+
56
+ ### Model Sources
57
+
58
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
59
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
60
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
61
+
62
+ ### Full Model Architecture
63
+
64
+ ```
65
+ SentenceTransformer(
66
+ (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: XLMRobertaModel
67
+ (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})
68
+ )
69
+ ```
70
+
71
+ ## Usage
72
+
73
+ ### Direct Usage (Sentence Transformers)
74
+
75
+ First install the Sentence Transformers library:
76
+
77
+ ```bash
78
+ pip install -U sentence-transformers
79
+ ```
80
+
81
+ Then you can load this model and run inference.
82
+ ```python
83
+ from sentence_transformers import SentenceTransformer
84
+
85
+ # Download from the 🤗 Hub
86
+ model = SentenceTransformer("sentence_transformers_model_id")
87
+ # Run inference
88
+ sentences = [
89
+ 'لام هو محافظ.',
90
+ 'هذا الرجل محافظ',
91
+ 'على الأرجح أنها ستلتصق بحشواته',
92
+ ]
93
+ embeddings = model.encode(sentences)
94
+ print(embeddings.shape)
95
+ # [3, 768]
96
+
97
+ # Get the similarity scores for the embeddings
98
+ similarities = model.similarity(embeddings, embeddings)
99
+ print(similarities.shape)
100
+ # [3, 3]
101
+ ```
102
+
103
+ <!--
104
+ ### Direct Usage (Transformers)
105
+
106
+ <details><summary>Click to see the direct usage in Transformers</summary>
107
+
108
+ </details>
109
+ -->
110
+
111
+ <!--
112
+ ### Downstream Usage (Sentence Transformers)
113
+
114
+ You can finetune this model on your own dataset.
115
+
116
+ <details><summary>Click to expand</summary>
117
+
118
+ </details>
119
+ -->
120
+
121
+ <!--
122
+ ### Out-of-Scope Use
123
+
124
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
125
+ -->
126
+
127
+ <!--
128
+ ## Bias, Risks and Limitations
129
+
130
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
131
+ -->
132
+
133
+ <!--
134
+ ### Recommendations
135
+
136
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
137
+ -->
138
+
139
+ ## Training Details
140
+
141
+ ### Training Dataset
142
+
143
+ #### Unnamed Dataset
144
+
145
+
146
+ * Size: 25,000 training samples
147
+ * Columns: <code>premise</code>, <code>hypothesis</code>, and <code>label</code>
148
+ * Approximate statistics based on the first 1000 samples:
149
+ | | premise | hypothesis | label |
150
+ |:--------|:------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:-------------------------------------------------------------------|
151
+ | type | string | string | int |
152
+ | details | <ul><li>min: 26 tokens</li><li>mean: 85.71 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.85 tokens</li><li>max: 98 tokens</li></ul> | <ul><li>0: ~24.10%</li><li>1: ~32.80%</li><li>2: ~43.10%</li></ul> |
153
+ * Samples:
154
+ | premise | hypothesis | label |
155
+ |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------|
156
+ | <code>Doom (منمنمة مثل DOOM) هي سلسلة من ألعاب الفيديو مطلق النار من منظور الشخص الأول التي طورتها id Software. تركز السلسلة على مآثر بحرية فضائية لم يكشف عن اسمها تعمل تحت رعاية شركة Union Aerospace Corporation (UAC) ، التي تحارب جحافل الشياطين والأجداد من أجل البقاء على قيد الحياة.</code> | <code>Doom هي أفضل لعبة مطلق النار الشخص الأول التي تم إنشاؤها</code> | <code>2</code> |
157
+ | <code>قال مسؤولون أمريكيون إن المسؤولين العسكريين والاستخباراتيين الأمريكيين على خلاف حول اتجاه الحرب في أفغانستان ، مما يخلق مصدرًا جديدًا للاحتكاك حيث يسعى الرئيس ترامب وفريق الأمن القومي التابع له إلى إيجاد طريقة لإنهاء الصراع المستمر منذ 17 عامًا. لدى مسؤولي الاستخبارات وجهة نظر متشائمة للصراع ، وفقًا لأشخاص مطلعين على تقييم سري مستمر ، بينما يتحدى القادة العسكريون هذا الاستنتاج بحجة أن استراتيجية السيد ترامب في جنوب آسيا تعمل....</code> | <code>مسؤولون عسكريون واستخباراتيون أمريكيون يتفقون على الحرب في أفغانستان</code> | <code>0</code> |
158
+ | <code>The Stranger Left No Card (1952) هو فيلم بريطاني قصير من إخراج ويندي توي. فاز الفيلم بجائزة أفضل خيال في مهرجان كان السينمائي 1953 ، حيث وصفه جان كوكتو بأنه "تحفة فنية". كان أول ظهور سينمائي للممثل آلان بادل.</code> | <code>ويندي توي تخرج من فيلم The Stranger Left No Card</code> | <code>2</code> |
159
+ * Loss: [<code>SoftmaxLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#softmaxloss)
160
+
161
+ ### Evaluation Dataset
162
+
163
+ #### Unnamed Dataset
164
+
165
+
166
+ * Size: 5,000 evaluation samples
167
+ * Columns: <code>premise</code>, <code>hypothesis</code>, and <code>label</code>
168
+ * Approximate statistics based on the first 1000 samples:
169
+ | | premise | hypothesis | label |
170
+ |:--------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:-------------------------------------------------------------------|
171
+ | type | string | string | int |
172
+ | details | <ul><li>min: 4 tokens</li><li>mean: 32.77 tokens</li><li>max: 117 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 16.72 tokens</li><li>max: 53 tokens</li></ul> | <ul><li>0: ~34.90%</li><li>1: ~32.80%</li><li>2: ~32.30%</li></ul> |
173
+ * Samples:
174
+ | premise | hypothesis | label |
175
+ |:-----------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------|:---------------|
176
+ | <code>هل المشكلة الآن أكثر حدة؟</code> | <code>وقد تم بالفعل حل هذه المسألة.</code> | <code>0</code> |
177
+ | <code>إن الخريطة التي تحتوي على ثقوب فيها هي تذكار لمعاهدة الاحترار العالمي وثغراتها التي يفترض أنها صارخة.</code> | <code>الثغرات في المعاهدة في معظمها لا يساء استخدامها.</code> | <code>2</code> |
178
+ | <code>يغطي The Star اعتقال جورج مايكل لتعريض نفسه في غرفة رجال في حديقة ويل روجرز التذكارية في لوس أنجلوس كما لو كان يكتب مراجعة.</code> | <code>السيد (مايكل) سيحاكم</code> | <code>2</code> |
179
+ * Loss: [<code>SoftmaxLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#softmaxloss)
180
+
181
+ ### Training Hyperparameters
182
+ #### Non-Default Hyperparameters
183
+
184
+ - `eval_strategy`: epoch
185
+ - `per_device_train_batch_size`: 16
186
+ - `per_device_eval_batch_size`: 32
187
+ - `gradient_accumulation_steps`: 2
188
+ - `learning_rate`: 2e-06
189
+ - `num_train_epochs`: 5
190
+ - `warmup_ratio`: 0.1
191
+ - `fp16`: True
192
+ - `load_best_model_at_end`: True
193
+ - `ddp_find_unused_parameters`: False
194
+
195
+ #### All Hyperparameters
196
+ <details><summary>Click to expand</summary>
197
+
198
+ - `overwrite_output_dir`: False
199
+ - `do_predict`: False
200
+ - `eval_strategy`: epoch
201
+ - `prediction_loss_only`: True
202
+ - `per_device_train_batch_size`: 16
203
+ - `per_device_eval_batch_size`: 32
204
+ - `per_gpu_train_batch_size`: None
205
+ - `per_gpu_eval_batch_size`: None
206
+ - `gradient_accumulation_steps`: 2
207
+ - `eval_accumulation_steps`: None
208
+ - `learning_rate`: 2e-06
209
+ - `weight_decay`: 0.0
210
+ - `adam_beta1`: 0.9
211
+ - `adam_beta2`: 0.999
212
+ - `adam_epsilon`: 1e-08
213
+ - `max_grad_norm`: 1.0
214
+ - `num_train_epochs`: 5
215
+ - `max_steps`: -1
216
+ - `lr_scheduler_type`: linear
217
+ - `lr_scheduler_kwargs`: {}
218
+ - `warmup_ratio`: 0.1
219
+ - `warmup_steps`: 0
220
+ - `log_level`: passive
221
+ - `log_level_replica`: warning
222
+ - `log_on_each_node`: True
223
+ - `logging_nan_inf_filter`: True
224
+ - `save_safetensors`: True
225
+ - `save_on_each_node`: False
226
+ - `save_only_model`: False
227
+ - `restore_callback_states_from_checkpoint`: False
228
+ - `no_cuda`: False
229
+ - `use_cpu`: False
230
+ - `use_mps_device`: False
231
+ - `seed`: 42
232
+ - `data_seed`: None
233
+ - `jit_mode_eval`: False
234
+ - `use_ipex`: False
235
+ - `bf16`: False
236
+ - `fp16`: True
237
+ - `fp16_opt_level`: O1
238
+ - `half_precision_backend`: auto
239
+ - `bf16_full_eval`: False
240
+ - `fp16_full_eval`: False
241
+ - `tf32`: None
242
+ - `local_rank`: 0
243
+ - `ddp_backend`: None
244
+ - `tpu_num_cores`: None
245
+ - `tpu_metrics_debug`: False
246
+ - `debug`: []
247
+ - `dataloader_drop_last`: False
248
+ - `dataloader_num_workers`: 0
249
+ - `dataloader_prefetch_factor`: None
250
+ - `past_index`: -1
251
+ - `disable_tqdm`: False
252
+ - `remove_unused_columns`: True
253
+ - `label_names`: None
254
+ - `load_best_model_at_end`: True
255
+ - `ignore_data_skip`: False
256
+ - `fsdp`: []
257
+ - `fsdp_min_num_params`: 0
258
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
259
+ - `fsdp_transformer_layer_cls_to_wrap`: None
260
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
261
+ - `deepspeed`: None
262
+ - `label_smoothing_factor`: 0.0
263
+ - `optim`: adamw_torch
264
+ - `optim_args`: None
265
+ - `adafactor`: False
266
+ - `group_by_length`: False
267
+ - `length_column_name`: length
268
+ - `ddp_find_unused_parameters`: False
269
+ - `ddp_bucket_cap_mb`: None
270
+ - `ddp_broadcast_buffers`: False
271
+ - `dataloader_pin_memory`: True
272
+ - `dataloader_persistent_workers`: False
273
+ - `skip_memory_metrics`: True
274
+ - `use_legacy_prediction_loop`: False
275
+ - `push_to_hub`: False
276
+ - `resume_from_checkpoint`: None
277
+ - `hub_model_id`: None
278
+ - `hub_strategy`: every_save
279
+ - `hub_private_repo`: False
280
+ - `hub_always_push`: False
281
+ - `gradient_checkpointing`: False
282
+ - `gradient_checkpointing_kwargs`: None
283
+ - `include_inputs_for_metrics`: False
284
+ - `eval_do_concat_batches`: True
285
+ - `fp16_backend`: auto
286
+ - `push_to_hub_model_id`: None
287
+ - `push_to_hub_organization`: None
288
+ - `mp_parameters`:
289
+ - `auto_find_batch_size`: False
290
+ - `full_determinism`: False
291
+ - `torchdynamo`: None
292
+ - `ray_scope`: last
293
+ - `ddp_timeout`: 1800
294
+ - `torch_compile`: False
295
+ - `torch_compile_backend`: None
296
+ - `torch_compile_mode`: None
297
+ - `dispatch_batches`: None
298
+ - `split_batches`: None
299
+ - `include_tokens_per_second`: False
300
+ - `include_num_input_tokens_seen`: False
301
+ - `neftune_noise_alpha`: None
302
+ - `optim_target_modules`: None
303
+ - `batch_eval_metrics`: False
304
+ - `batch_sampler`: batch_sampler
305
+ - `multi_dataset_batch_sampler`: proportional
306
+
307
+ </details>
308
+
309
+ ### Training Logs
310
+ | Epoch | Step | Training Loss | loss |
311
+ |:------:|:----:|:-------------:|:------:|
312
+ | 0.0320 | 25 | 1.172 | - |
313
+ | 0.0640 | 50 | 1.1839 | - |
314
+ | 0.0960 | 75 | 1.1595 | - |
315
+ | 0.1280 | 100 | 1.1516 | - |
316
+ | 0.1599 | 125 | 1.1312 | - |
317
+ | 0.1919 | 150 | 1.1458 | - |
318
+ | 0.2239 | 175 | 1.1202 | - |
319
+ | 0.2559 | 200 | 1.1113 | - |
320
+ | 0.2879 | 225 | 1.0973 | - |
321
+ | 0.3199 | 250 | 1.1004 | - |
322
+ | 0.3519 | 275 | 1.0892 | - |
323
+ | 0.3839 | 300 | 1.0708 | - |
324
+ | 0.4159 | 325 | 1.0937 | - |
325
+ | 0.4479 | 350 | 1.0698 | - |
326
+ | 0.4798 | 375 | 1.0893 | - |
327
+ | 0.5118 | 400 | 1.0597 | - |
328
+ | 0.5438 | 425 | 1.0638 | - |
329
+ | 0.5758 | 450 | 1.0524 | - |
330
+ | 0.6078 | 475 | 1.0673 | - |
331
+ | 0.6398 | 500 | 1.0619 | - |
332
+ | 0.6718 | 525 | 1.0254 | - |
333
+ | 0.7038 | 550 | 1.0423 | - |
334
+ | 0.7358 | 575 | 1.0175 | - |
335
+ | 0.7678 | 600 | 1.0365 | - |
336
+ | 0.7997 | 625 | 1.0412 | - |
337
+ | 0.8317 | 650 | 1.0411 | - |
338
+ | 0.8637 | 675 | 1.0287 | - |
339
+ | 0.8957 | 700 | 1.0318 | - |
340
+ | 0.9277 | 725 | 1.0486 | - |
341
+ | 0.9597 | 750 | 1.0237 | - |
342
+ | 0.9917 | 775 | 1.0199 | - |
343
+ | 0.9994 | 781 | - | 1.1031 |
344
+
345
+
346
+ ### Framework Versions
347
+ - Python: 3.10.12
348
+ - Sentence Transformers: 3.0.0
349
+ - Transformers: 4.41.2
350
+ - PyTorch: 2.3.0+cu121
351
+ - Accelerate: 0.31.0
352
+ - Datasets: 2.19.1
353
+ - Tokenizers: 0.19.1
354
+
355
+ ## Citation
356
+
357
+ ### BibTeX
358
+
359
+ #### Sentence Transformers and SoftmaxLoss
360
+ ```bibtex
361
+ @inproceedings{reimers-2019-sentence-bert,
362
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
363
+ author = "Reimers, Nils and Gurevych, Iryna",
364
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
365
+ month = "11",
366
+ year = "2019",
367
+ publisher = "Association for Computational Linguistics",
368
+ url = "https://arxiv.org/abs/1908.10084",
369
+ }
370
+ ```
371
+
372
+ <!--
373
+ ## Glossary
374
+
375
+ *Clearly define terms in order to be accessible across audiences.*
376
+ -->
377
+
378
+ <!--
379
+ ## Model Card Authors
380
+
381
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
382
+ -->
383
+
384
+ <!--
385
+ ## Model Card Contact
386
+
387
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
388
+ -->
checkpoint-781/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "symanto/sn-xlm-roberta-base-snli-mnli-anli-xnli",
3
+ "architectures": [
4
+ "XLMRobertaModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 514,
18
+ "model_type": "xlm-roberta",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
+ "output_past": true,
22
+ "pad_token_id": 1,
23
+ "position_embedding_type": "absolute",
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.41.2",
26
+ "type_vocab_size": 1,
27
+ "use_cache": true,
28
+ "vocab_size": 250002
29
+ }
checkpoint-781/config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "2.0.0",
4
+ "transformers": "4.6.0",
5
+ "pytorch": "1.7.0"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null,
9
+ "similarity_fn_name": null
10
+ }
checkpoint-781/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6353cc162bcb12228a1183a5dcb5e7a78fd0a1c683133610bf600036381d29ec
3
+ size 1112197096
checkpoint-781/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
+ ]
checkpoint-781/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a559b4f6641b2985f29e98fb4995b43581bdadd799bdbc21772c40428b930d54
3
+ size 2219789306
checkpoint-781/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84e03069ced653912e5fb1ce8a08b4d48879e369102d5053fe4494f83f69241b
3
+ size 14244
checkpoint-781/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f62ff97dc8b9b23e020f43ae970bae607badd1d1dc41eca6260ef04f4982920
3
+ size 1064
checkpoint-781/sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 128,
3
+ "do_lower_case": false
4
+ }
checkpoint-781/sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
checkpoint-781/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": true,
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
+ }
checkpoint-781/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cad551d5600a84242d0973327029452a1e3672ba6313c2a3c3d69c4310e12719
3
+ size 17082987
checkpoint-781/tokenizer_config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
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
+ "mask_token": "<mask>",
49
+ "max_length": 128,
50
+ "model_max_length": 128,
51
+ "pad_to_multiple_of": null,
52
+ "pad_token": "<pad>",
53
+ "pad_token_type_id": 0,
54
+ "padding_side": "right",
55
+ "sep_token": "</s>",
56
+ "stride": 0,
57
+ "tokenizer_class": "XLMRobertaTokenizer",
58
+ "truncation_side": "right",
59
+ "truncation_strategy": "longest_first",
60
+ "unk_token": "<unk>"
61
+ }
checkpoint-781/trainer_state.json ADDED
@@ -0,0 +1,267 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.1031256914138794,
3
+ "best_model_checkpoint": "arabic-embedding-model-pair-class2/checkpoint-781",
4
+ "epoch": 0.999360204734485,
5
+ "eval_steps": 500,
6
+ "global_step": 781,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03198976327575176,
13
+ "grad_norm": 4.865348815917969,
14
+ "learning_rate": 1.2787723785166242e-07,
15
+ "loss": 1.172,
16
+ "step": 25
17
+ },
18
+ {
19
+ "epoch": 0.06397952655150352,
20
+ "grad_norm": 4.501841068267822,
21
+ "learning_rate": 2.5575447570332484e-07,
22
+ "loss": 1.1839,
23
+ "step": 50
24
+ },
25
+ {
26
+ "epoch": 0.09596928982725528,
27
+ "grad_norm": 4.760345458984375,
28
+ "learning_rate": 3.836317135549872e-07,
29
+ "loss": 1.1595,
30
+ "step": 75
31
+ },
32
+ {
33
+ "epoch": 0.12795905310300704,
34
+ "grad_norm": 4.2426605224609375,
35
+ "learning_rate": 5.115089514066497e-07,
36
+ "loss": 1.1516,
37
+ "step": 100
38
+ },
39
+ {
40
+ "epoch": 0.1599488163787588,
41
+ "grad_norm": 4.42633581161499,
42
+ "learning_rate": 6.39386189258312e-07,
43
+ "loss": 1.1312,
44
+ "step": 125
45
+ },
46
+ {
47
+ "epoch": 0.19193857965451055,
48
+ "grad_norm": 4.73534631729126,
49
+ "learning_rate": 7.672634271099744e-07,
50
+ "loss": 1.1458,
51
+ "step": 150
52
+ },
53
+ {
54
+ "epoch": 0.22392834293026231,
55
+ "grad_norm": 4.202542781829834,
56
+ "learning_rate": 8.951406649616368e-07,
57
+ "loss": 1.1202,
58
+ "step": 175
59
+ },
60
+ {
61
+ "epoch": 0.2559181062060141,
62
+ "grad_norm": 4.2955827713012695,
63
+ "learning_rate": 1.0230179028132994e-06,
64
+ "loss": 1.1113,
65
+ "step": 200
66
+ },
67
+ {
68
+ "epoch": 0.28790786948176583,
69
+ "grad_norm": 4.325717926025391,
70
+ "learning_rate": 1.1508951406649615e-06,
71
+ "loss": 1.0973,
72
+ "step": 225
73
+ },
74
+ {
75
+ "epoch": 0.3198976327575176,
76
+ "grad_norm": 4.795027256011963,
77
+ "learning_rate": 1.278772378516624e-06,
78
+ "loss": 1.1004,
79
+ "step": 250
80
+ },
81
+ {
82
+ "epoch": 0.35188739603326935,
83
+ "grad_norm": 4.470003128051758,
84
+ "learning_rate": 1.4066496163682863e-06,
85
+ "loss": 1.0892,
86
+ "step": 275
87
+ },
88
+ {
89
+ "epoch": 0.3838771593090211,
90
+ "grad_norm": 4.943461894989014,
91
+ "learning_rate": 1.5345268542199487e-06,
92
+ "loss": 1.0708,
93
+ "step": 300
94
+ },
95
+ {
96
+ "epoch": 0.41586692258477287,
97
+ "grad_norm": 4.593530654907227,
98
+ "learning_rate": 1.6624040920716111e-06,
99
+ "loss": 1.0937,
100
+ "step": 325
101
+ },
102
+ {
103
+ "epoch": 0.44785668586052463,
104
+ "grad_norm": 4.122324466705322,
105
+ "learning_rate": 1.7902813299232735e-06,
106
+ "loss": 1.0698,
107
+ "step": 350
108
+ },
109
+ {
110
+ "epoch": 0.4798464491362764,
111
+ "grad_norm": 4.206705093383789,
112
+ "learning_rate": 1.918158567774936e-06,
113
+ "loss": 1.0893,
114
+ "step": 375
115
+ },
116
+ {
117
+ "epoch": 0.5118362124120281,
118
+ "grad_norm": 5.153020858764648,
119
+ "learning_rate": 1.9948776323278313e-06,
120
+ "loss": 1.0597,
121
+ "step": 400
122
+ },
123
+ {
124
+ "epoch": 0.5438259756877799,
125
+ "grad_norm": 4.710206985473633,
126
+ "learning_rate": 1.9806488332384747e-06,
127
+ "loss": 1.0638,
128
+ "step": 425
129
+ },
130
+ {
131
+ "epoch": 0.5758157389635317,
132
+ "grad_norm": 4.139469146728516,
133
+ "learning_rate": 1.9664200341491176e-06,
134
+ "loss": 1.0524,
135
+ "step": 450
136
+ },
137
+ {
138
+ "epoch": 0.6078055022392834,
139
+ "grad_norm": 4.873435974121094,
140
+ "learning_rate": 1.952191235059761e-06,
141
+ "loss": 1.0673,
142
+ "step": 475
143
+ },
144
+ {
145
+ "epoch": 0.6397952655150352,
146
+ "grad_norm": 4.9657063484191895,
147
+ "learning_rate": 1.9379624359704043e-06,
148
+ "loss": 1.0619,
149
+ "step": 500
150
+ },
151
+ {
152
+ "epoch": 0.6717850287907869,
153
+ "grad_norm": 4.697886943817139,
154
+ "learning_rate": 1.923733636881047e-06,
155
+ "loss": 1.0254,
156
+ "step": 525
157
+ },
158
+ {
159
+ "epoch": 0.7037747920665387,
160
+ "grad_norm": 5.463695526123047,
161
+ "learning_rate": 1.90950483779169e-06,
162
+ "loss": 1.0423,
163
+ "step": 550
164
+ },
165
+ {
166
+ "epoch": 0.7357645553422905,
167
+ "grad_norm": 4.888927459716797,
168
+ "learning_rate": 1.8952760387023335e-06,
169
+ "loss": 1.0175,
170
+ "step": 575
171
+ },
172
+ {
173
+ "epoch": 0.7677543186180422,
174
+ "grad_norm": 5.26019287109375,
175
+ "learning_rate": 1.8810472396129766e-06,
176
+ "loss": 1.0365,
177
+ "step": 600
178
+ },
179
+ {
180
+ "epoch": 0.799744081893794,
181
+ "grad_norm": 4.753886699676514,
182
+ "learning_rate": 1.8668184405236197e-06,
183
+ "loss": 1.0412,
184
+ "step": 625
185
+ },
186
+ {
187
+ "epoch": 0.8317338451695457,
188
+ "grad_norm": 4.420036315917969,
189
+ "learning_rate": 1.8525896414342628e-06,
190
+ "loss": 1.0411,
191
+ "step": 650
192
+ },
193
+ {
194
+ "epoch": 0.8637236084452975,
195
+ "grad_norm": 5.005071640014648,
196
+ "learning_rate": 1.838360842344906e-06,
197
+ "loss": 1.0287,
198
+ "step": 675
199
+ },
200
+ {
201
+ "epoch": 0.8957133717210493,
202
+ "grad_norm": 5.211964130401611,
203
+ "learning_rate": 1.8241320432555491e-06,
204
+ "loss": 1.0318,
205
+ "step": 700
206
+ },
207
+ {
208
+ "epoch": 0.927703134996801,
209
+ "grad_norm": 5.416666030883789,
210
+ "learning_rate": 1.8099032441661922e-06,
211
+ "loss": 1.0486,
212
+ "step": 725
213
+ },
214
+ {
215
+ "epoch": 0.9596928982725528,
216
+ "grad_norm": 4.680449962615967,
217
+ "learning_rate": 1.7956744450768356e-06,
218
+ "loss": 1.0237,
219
+ "step": 750
220
+ },
221
+ {
222
+ "epoch": 0.9916826615483045,
223
+ "grad_norm": 4.465170860290527,
224
+ "learning_rate": 1.7814456459874785e-06,
225
+ "loss": 1.0199,
226
+ "step": 775
227
+ },
228
+ {
229
+ "epoch": 0.999360204734485,
230
+ "eval_loss": 1.1031256914138794,
231
+ "eval_runtime": 10.1366,
232
+ "eval_samples_per_second": 493.263,
233
+ "eval_steps_per_second": 15.488,
234
+ "step": 781
235
+ }
236
+ ],
237
+ "logging_steps": 25,
238
+ "max_steps": 3905,
239
+ "num_input_tokens_seen": 0,
240
+ "num_train_epochs": 5,
241
+ "save_steps": 500,
242
+ "stateful_callbacks": {
243
+ "EarlyStoppingCallback": {
244
+ "args": {
245
+ "early_stopping_patience": 5,
246
+ "early_stopping_threshold": 0.01
247
+ },
248
+ "attributes": {
249
+ "early_stopping_patience_counter": 0
250
+ }
251
+ },
252
+ "TrainerControl": {
253
+ "args": {
254
+ "should_epoch_stop": false,
255
+ "should_evaluate": false,
256
+ "should_log": false,
257
+ "should_save": true,
258
+ "should_training_stop": false
259
+ },
260
+ "attributes": {}
261
+ }
262
+ },
263
+ "total_flos": 0.0,
264
+ "train_batch_size": 16,
265
+ "trial_name": null,
266
+ "trial_params": null
267
+ }
checkpoint-781/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:553c503eadd8dae5938be03b28f349b6c164dc2ff69b88d724b6845f6a3def0f
3
+ size 5368
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "symanto/sn-xlm-roberta-base-snli-mnli-anli-xnli",
3
+ "architectures": [
4
+ "XLMRobertaModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 514,
18
+ "model_type": "xlm-roberta",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
+ "output_past": true,
22
+ "pad_token_id": 1,
23
+ "position_embedding_type": "absolute",
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.41.2",
26
+ "type_vocab_size": 1,
27
+ "use_cache": true,
28
+ "vocab_size": 250002
29
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "2.0.0",
4
+ "transformers": "4.6.0",
5
+ "pytorch": "1.7.0"
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 sha256:6353cc162bcb12228a1183a5dcb5e7a78fd0a1c683133610bf600036381d29ec
3
+ size 1112197096
modules.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ }
14
+ ]
runs/Jun18_14-24-12_954fd82b1c9e/events.out.tfevents.1718720653.954fd82b1c9e.34702.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac1a82721a70628f1634fd3837873a1d83c12ba073200c672a349d4e639c68cb
3
- size 26113
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86ed46a50128809ec8f286af206c396da600fb9e803cebf2109512d9e7f77508
3
+ size 38825
runs/Jun18_14-24-12_954fd82b1c9e/events.out.tfevents.1718721614.954fd82b1c9e.34702.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:617d76cb7fd53934abe25a20c80071fcf9b33b0a9e867cb856bc4eecb9ee98a9
3
+ size 359
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 128,
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": true,
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:cad551d5600a84242d0973327029452a1e3672ba6313c2a3c3d69c4310e12719
3
+ size 17082987
tokenizer_config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
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
+ "mask_token": "<mask>",
49
+ "max_length": 128,
50
+ "model_max_length": 128,
51
+ "pad_to_multiple_of": null,
52
+ "pad_token": "<pad>",
53
+ "pad_token_type_id": 0,
54
+ "padding_side": "right",
55
+ "sep_token": "</s>",
56
+ "stride": 0,
57
+ "tokenizer_class": "XLMRobertaTokenizer",
58
+ "truncation_side": "right",
59
+ "truncation_strategy": "longest_first",
60
+ "unk_token": "<unk>"
61
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:553c503eadd8dae5938be03b28f349b6c164dc2ff69b88d724b6845f6a3def0f
3
+ size 5368
training_params.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data_path": "arabic-embedding-model-pair-class2/autotrain-data",
3
+ "model": "symanto/sn-xlm-roberta-base-snli-mnli-anli-xnli",
4
+ "lr": 2e-06,
5
+ "epochs": 5,
6
+ "max_seq_length": 512,
7
+ "batch_size": 16,
8
+ "warmup_ratio": 0.1,
9
+ "gradient_accumulation": 2,
10
+ "optimizer": "adamw_torch",
11
+ "scheduler": "linear",
12
+ "weight_decay": 0.0,
13
+ "max_grad_norm": 1.0,
14
+ "seed": 42,
15
+ "train_split": "train",
16
+ "valid_split": "validation",
17
+ "logging_steps": -1,
18
+ "project_name": "arabic-embedding-model-pair-class2",
19
+ "auto_find_batch_size": false,
20
+ "mixed_precision": "fp16",
21
+ "save_total_limit": 1,
22
+ "push_to_hub": true,
23
+ "evaluation_strategy": "epoch",
24
+ "username": "acayir64",
25
+ "log": "tensorboard",
26
+ "early_stopping_patience": 5,
27
+ "early_stopping_threshold": 0.01,
28
+ "trainer": "pair_class",
29
+ "sentence1_column": "autotrain_sentence1",
30
+ "sentence2_column": "autotrain_sentence2",
31
+ "sentence3_column": "autotrain_sentence3",
32
+ "target_column": "autotrain_target"
33
+ }