Hugging Face's logo

orhanxakarsu
/
sentence-distilbert-turkish

Sentence Similarity
sentence-transformers
Safetensors
Turkish
distilbert
feature-extraction
Generated from Trainer
dataset_size:814596
loss:MultipleNegativesRankingLoss
Eval Results
text-embeddings-inference
Inference Endpoints
Model card Files Community
orhanxakarsu commited on
Commit
628cfaa
·
verified ·
1 Parent(s): f4a4b5e

Add new SentenceTransformer model

Browse files
Files changed (11) hide show
  1. 1_Pooling/config.json +10 -0
  2. README.md +546 -0
  3. config.json +25 -0
  4. config_sentence_transformers.json +10 -0
  5. model.safetensors +3 -0
  6. modules.json +14 -0
  7. sentence_bert_config.json +4 -0
  8. special_tokens_map.json +37 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +65 -0
  11. 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 +1,546 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - tr
4
+ license: apache-2.0
5
+ tags:
6
+ - sentence-transformers
7
+ - sentence-similarity
8
+ - feature-extraction
9
+ - generated_from_trainer
10
+ - dataset_size:814596
11
+ - loss:MultipleNegativesRankingLoss
12
+ base_model: dbmdz/distilbert-base-turkish-cased
13
+ widget:
14
+ - source_sentence: Bir adam kitap okuyor.
15
+ sentences:
16
+ - Gözlüklü ve mavi gömlekli bir adam dizüstü bilgisayar ekranını okuyor.
17
+ - Suyun içinde olduğunun farkındasın.
18
+ - Plajda bir adam yüzüstü yatıp kitap okurken, puantiyeli bikinili bir kadın güneşleniyor.
19
+ - source_sentence: İki kişi parlak bir şekilde aydınlatılmış bir demiryolu geçidinin
20
+ yanında duruyor.
21
+ sentences:
22
+ - Balık kesen bir adam
23
+ - Uçakta bir hostes kahve servisi yapar.
24
+ - Demiryolu raylarının yanında iki kişi duruyor.
25
+ - source_sentence: Ağzında beyaz bir frizbi olan siyah beyaz köpek için frizbi fırlatan
26
+ beyaz gömlekli adam.
27
+ sentences:
28
+ - Hiçbir kardeşten bahsetmedi.
29
+ - Adam ve köpek su altında.
30
+ - Adam köpeğe frizbi atıyor
31
+ - source_sentence: Natüralist Sorgulamanın Mantığı.
32
+ sentences:
33
+ - İnsanlar otobüs bekliyor.
34
+ - Natüralist Sorgulamayı anlamak zordur.
35
+ - Natüralist Sorgulamanın anlaşılması kolaydır.
36
+ - source_sentence: İki kadın, Çin'deki bir markette bir ürüne bakıyor.
37
+ sentences:
38
+ - Kadınlar bir spor salonunda çalışıyorlar.
39
+ - Müzenin en büyüleyici parçaları arasında San Macro'daki Geçit Töreni yer alıyor.
40
+ - Alışveriş yapan iki kadın
41
+ pipeline_tag: sentence-similarity
42
+ library_name: sentence-transformers
43
+ metrics:
44
+ - cosine_accuracy
45
+ model-index:
46
+ - name: distilbert-base-turkish-case trained on AllNLI Turkish translate triplets
47
+ results:
48
+ - task:
49
+ type: triplet
50
+ name: Triplet
51
+ dataset:
52
+ name: all nli turkish dev
53
+ type: all-nli-turkish-dev
54
+ metrics:
55
+ - type: cosine_accuracy
56
+ value: 0.9801920038886863
57
+ name: Cosine Accuracy
58
+ ---
59
+
60
+ # distilbert-base-turkish-case trained on AllNLI Turkish translate triplets
61
+
62
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [dbmdz/distilbert-base-turkish-cased](https://huggingface.co/dbmdz/distilbert-base-turkish-cased). 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.
63
+
64
+ ## Model Details
65
+
66
+ ### Model Description
67
+ - **Model Type:** Sentence Transformer
68
+ - **Base model:** [dbmdz/distilbert-base-turkish-cased](https://huggingface.co/dbmdz/distilbert-base-turkish-cased) <!-- at revision 8ecd4d034c2612d4c5940795b4f2552a9f3543d6 -->
69
+ - **Maximum Sequence Length:** 512 tokens
70
+ - **Output Dimensionality:** 768 dimensions
71
+ - **Similarity Function:** Cosine Similarity
72
+ <!-- - **Training Dataset:** Unknown -->
73
+ - **Language:** tr
74
+ - **License:** apache-2.0
75
+
76
+ ### Model Sources
77
+
78
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
79
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
80
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
81
+
82
+ ### Full Model Architecture
83
+
84
+ ```
85
+ SentenceTransformer(
86
+ (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: DistilBertModel
87
+ (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})
88
+ )
89
+ ```
90
+
91
+ ## Usage
92
+
93
+ ### Direct Usage (Sentence Transformers)
94
+
95
+ First install the Sentence Transformers library:
96
+
97
+ ```bash
98
+ pip install -U sentence-transformers
99
+ ```
100
+
101
+ Then you can load this model and run inference.
102
+ ```python
103
+ from sentence_transformers import SentenceTransformer
104
+
105
+ # Download from the 🤗 Hub
106
+ model = SentenceTransformer("orhanxakarsu/sentence-distilbert-turkish")
107
+ # Run inference
108
+ sentences = [
109
+ "İki kadın, Çin'deki bir markette bir ürüne bakıyor.",
110
+ 'Alışveriş yapan iki kadın',
111
+ 'Kadınlar bir spor salonunda çalışıyorlar.',
112
+ ]
113
+ embeddings = model.encode(sentences)
114
+ print(embeddings.shape)
115
+ # [3, 768]
116
+
117
+ # Get the similarity scores for the embeddings
118
+ similarities = model.similarity(embeddings, embeddings)
119
+ print(similarities.shape)
120
+ # [3, 3]
121
+ ```
122
+
123
+ <!--
124
+ ### Direct Usage (Transformers)
125
+
126
+ <details><summary>Click to see the direct usage in Transformers</summary>
127
+
128
+ </details>
129
+ -->
130
+
131
+ <!--
132
+ ### Downstream Usage (Sentence Transformers)
133
+
134
+ You can finetune this model on your own dataset.
135
+
136
+ <details><summary>Click to expand</summary>
137
+
138
+ </details>
139
+ -->
140
+
141
+ <!--
142
+ ### Out-of-Scope Use
143
+
144
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
145
+ -->
146
+
147
+ ## Evaluation
148
+
149
+ ### Metrics
150
+
151
+ #### Triplet
152
+
153
+ * Dataset: `all-nli-turkish-dev`
154
+ * Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
155
+
156
+ | Metric | Value |
157
+ |:--------------------|:-----------|
158
+ | **cosine_accuracy** | **0.9802** |
159
+
160
+ <!--
161
+ ## Bias, Risks and Limitations
162
+
163
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
164
+ -->
165
+
166
+ <!--
167
+ ### Recommendations
168
+
169
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
170
+ -->
171
+
172
+ ## Training Details
173
+
174
+ ### Training Dataset
175
+
176
+ #### Unnamed Dataset
177
+
178
+
179
+ * Size: 814,596 training samples
180
+ * Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
181
+ * Approximate statistics based on the first 1000 samples:
182
+ | | anchor | positive | negative |
183
+ |:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
184
+ | type | string | string | string |
185
+ | details | <ul><li>min: 3 tokens</li><li>mean: 18.16 tokens</li><li>max: 91 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 10.54 tokens</li><li>max: 136 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 10.73 tokens</li><li>max: 29 tokens</li></ul> |
186
+ * Samples:
187
+ | anchor | positive | negative |
188
+ |:-----------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------|
189
+ | <code>Beyaz gömlekli ve güneş gözlüklü bir kadın, kucağında bir bebekle dışarıda bir sandalyede oturuyor.</code> | <code>Bebek yerden yukarıda oturuyor</code> | <code>Adam bir top atıyor</code> |
190
+ | <code>Mavi yakalı gömlek giyen ve kazaklı bir adam ve beyaz gömlek giyen hasır şapka takan bir kadın.</code> | <code>Yan yana bir erkek ve bir kadın var.</code> | <code>Evli bir çift akşam yemeği yiyor.</code> |
191
+ | <code>Adam içeride.</code> | <code>Siyah fötr şapkalı bir adam bir arenada boğaya biniyor.</code> | <code>Yeşil üniforma giyen beş subayla birlikte taş bir binanın önünde cep telefonuyla konuşan bir papaz; ikisi ayakta, diğerleri oturuyor.</code> |
192
+ * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
193
+ ```json
194
+ {
195
+ "scale": 20.0,
196
+ "similarity_fct": "cos_sim"
197
+ }
198
+ ```
199
+
200
+ ### Evaluation Dataset
201
+
202
+ #### Unnamed Dataset
203
+
204
+
205
+ * Size: 8,229 evaluation samples
206
+ * Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
207
+ * Approximate statistics based on the first 1000 samples:
208
+ | | anchor | positive | negative |
209
+ |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
210
+ | type | string | string | string |
211
+ | details | <ul><li>min: 4 tokens</li><li>mean: 17.91 tokens</li><li>max: 80 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 10.62 tokens</li><li>max: 35 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 11.01 tokens</li><li>max: 33 tokens</li></ul> |
212
+ * Samples:
213
+ | anchor | positive | negative |
214
+ |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------|:-----------------------------------------------------------------|
215
+ | <code>Patlamanın büyüklüğünün güçlü bir örneği, Haragosha Tapınağı'nda bulunur, burada tapınağın kemerinin üst crosebar'ını görebilirsiniz, geri kalanı sertleşmiş lav tarafından batırılmıştır.</code> | <code>Patlamanın büyüklüğünün sonucu Haragosha Tapınağı'nda görülüyor.</code> | <code>Haragosha Tapınağı bu güne kadar tamamen sağlamdır.</code> |
216
+ | <code>Arkeolojik kazı yapan iki kişi.</code> | <code>Kazı yapan insanlar var.</code> | <code>Kimse kazmıyor.</code> |
217
+ | <code>İşçiler, Martins'in ünlü Louisiana sosis satıcısı çadırının önünde sıraya giren müşterilere hizmet veriyor</code> | <code>Müşteriler bir satıcı çadırının önünde sıraya giriyor.</code> | <code>Pamuk şeker yiyen bir grup insan var.</code> |
218
+ * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
219
+ ```json
220
+ {
221
+ "scale": 20.0,
222
+ "similarity_fct": "cos_sim"
223
+ }
224
+ ```
225
+
226
+ ### Training Hyperparameters
227
+ #### Non-Default Hyperparameters
228
+
229
+ - `eval_strategy`: steps
230
+ - `per_device_train_batch_size`: 64
231
+ - `per_device_eval_batch_size`: 64
232
+ - `learning_rate`: 2e-05
233
+ - `num_train_epochs`: 10
234
+ - `warmup_ratio`: 0.1
235
+ - `fp16`: True
236
+ - `batch_sampler`: no_duplicates
237
+
238
+ #### All Hyperparameters
239
+ <details><summary>Click to expand</summary>
240
+
241
+ - `overwrite_output_dir`: False
242
+ - `do_predict`: False
243
+ - `eval_strategy`: steps
244
+ - `prediction_loss_only`: True
245
+ - `per_device_train_batch_size`: 64
246
+ - `per_device_eval_batch_size`: 64
247
+ - `per_gpu_train_batch_size`: None
248
+ - `per_gpu_eval_batch_size`: None
249
+ - `gradient_accumulation_steps`: 1
250
+ - `eval_accumulation_steps`: None
251
+ - `torch_empty_cache_steps`: None
252
+ - `learning_rate`: 2e-05
253
+ - `weight_decay`: 0.0
254
+ - `adam_beta1`: 0.9
255
+ - `adam_beta2`: 0.999
256
+ - `adam_epsilon`: 1e-08
257
+ - `max_grad_norm`: 1.0
258
+ - `num_train_epochs`: 10
259
+ - `max_steps`: -1
260
+ - `lr_scheduler_type`: linear
261
+ - `lr_scheduler_kwargs`: {}
262
+ - `warmup_ratio`: 0.1
263
+ - `warmup_steps`: 0
264
+ - `log_level`: passive
265
+ - `log_level_replica`: warning
266
+ - `log_on_each_node`: True
267
+ - `logging_nan_inf_filter`: True
268
+ - `save_safetensors`: True
269
+ - `save_on_each_node`: False
270
+ - `save_only_model`: False
271
+ - `restore_callback_states_from_checkpoint`: False
272
+ - `no_cuda`: False
273
+ - `use_cpu`: False
274
+ - `use_mps_device`: False
275
+ - `seed`: 42
276
+ - `data_seed`: None
277
+ - `jit_mode_eval`: False
278
+ - `use_ipex`: False
279
+ - `bf16`: False
280
+ - `fp16`: True
281
+ - `fp16_opt_level`: O1
282
+ - `half_precision_backend`: auto
283
+ - `bf16_full_eval`: False
284
+ - `fp16_full_eval`: False
285
+ - `tf32`: None
286
+ - `local_rank`: 0
287
+ - `ddp_backend`: None
288
+ - `tpu_num_cores`: None
289
+ - `tpu_metrics_debug`: False
290
+ - `debug`: []
291
+ - `dataloader_drop_last`: False
292
+ - `dataloader_num_workers`: 0
293
+ - `dataloader_prefetch_factor`: None
294
+ - `past_index`: -1
295
+ - `disable_tqdm`: False
296
+ - `remove_unused_columns`: True
297
+ - `label_names`: None
298
+ - `load_best_model_at_end`: False
299
+ - `ignore_data_skip`: False
300
+ - `fsdp`: []
301
+ - `fsdp_min_num_params`: 0
302
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
303
+ - `fsdp_transformer_layer_cls_to_wrap`: None
304
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
305
+ - `deepspeed`: None
306
+ - `label_smoothing_factor`: 0.0
307
+ - `optim`: adamw_torch
308
+ - `optim_args`: None
309
+ - `adafactor`: False
310
+ - `group_by_length`: False
311
+ - `length_column_name`: length
312
+ - `ddp_find_unused_parameters`: None
313
+ - `ddp_bucket_cap_mb`: None
314
+ - `ddp_broadcast_buffers`: False
315
+ - `dataloader_pin_memory`: True
316
+ - `dataloader_persistent_workers`: False
317
+ - `skip_memory_metrics`: True
318
+ - `use_legacy_prediction_loop`: False
319
+ - `push_to_hub`: False
320
+ - `resume_from_checkpoint`: None
321
+ - `hub_model_id`: None
322
+ - `hub_strategy`: every_save
323
+ - `hub_private_repo`: False
324
+ - `hub_always_push`: False
325
+ - `gradient_checkpointing`: False
326
+ - `gradient_checkpointing_kwargs`: None
327
+ - `include_inputs_for_metrics`: False
328
+ - `eval_do_concat_batches`: True
329
+ - `fp16_backend`: auto
330
+ - `push_to_hub_model_id`: None
331
+ - `push_to_hub_organization`: None
332
+ - `mp_parameters`:
333
+ - `auto_find_batch_size`: False
334
+ - `full_determinism`: False
335
+ - `torchdynamo`: None
336
+ - `ray_scope`: last
337
+ - `ddp_timeout`: 1800
338
+ - `torch_compile`: False
339
+ - `torch_compile_backend`: None
340
+ - `torch_compile_mode`: None
341
+ - `dispatch_batches`: None
342
+ - `split_batches`: None
343
+ - `include_tokens_per_second`: False
344
+ - `include_num_input_tokens_seen`: False
345
+ - `neftune_noise_alpha`: None
346
+ - `optim_target_modules`: None
347
+ - `batch_eval_metrics`: False
348
+ - `eval_on_start`: False
349
+ - `eval_use_gather_object`: False
350
+ - `prompts`: None
351
+ - `batch_sampler`: no_duplicates
352
+ - `multi_dataset_batch_sampler`: proportional
353
+
354
+ </details>
355
+
356
+ ### Training Logs
357
+ <details><summary>Click to expand</summary>
358
+
359
+ | Epoch | Step | Training Loss | Validation Loss | all-nli-turkish-dev_cosine_accuracy |
360
+ |:------:|:------:|:-------------:|:---------------:|:-----------------------------------:|
361
+ | 0 | 0 | - | - | 0.5808 |
362
+ | 0.0786 | 1000 | 3.5327 | 1.9481 | 0.7607 |
363
+ | 0.1571 | 2000 | 1.5833 | 1.2787 | 0.8260 |
364
+ | 0.2357 | 3000 | 1.2338 | 1.0960 | 0.8533 |
365
+ | 0.3142 | 4000 | 1.1031 | 0.9897 | 0.8695 |
366
+ | 0.3928 | 5000 | 0.998 | 0.9077 | 0.8793 |
367
+ | 0.4714 | 6000 | 0.9412 | 0.8434 | 0.8914 |
368
+ | 0.5499 | 7000 | 0.8703 | 0.7904 | 0.8982 |
369
+ | 0.6285 | 8000 | 0.8094 | 0.7311 | 0.9068 |
370
+ | 0.7070 | 9000 | 0.7653 | 0.6894 | 0.9086 |
371
+ | 0.7856 | 10000 | 0.7248 | 0.6509 | 0.9162 |
372
+ | 0.8642 | 11000 | 0.673 | 0.6145 | 0.9205 |
373
+ | 0.9427 | 12000 | 0.6514 | 0.5762 | 0.9273 |
374
+ | 1.0213 | 13000 | 0.6259 | 0.5463 | 0.9334 |
375
+ | 1.0999 | 14000 | 0.5874 | 0.5276 | 0.9332 |
376
+ | 1.1784 | 15000 | 0.5518 | 0.5053 | 0.9366 |
377
+ | 1.2570 | 16000 | 0.5277 | 0.4783 | 0.9391 |
378
+ | 1.3355 | 17000 | 0.5075 | 0.4571 | 0.9419 |
379
+ | 1.4141 | 18000 | 0.4906 | 0.4379 | 0.9454 |
380
+ | 1.4927 | 19000 | 0.475 | 0.4234 | 0.9465 |
381
+ | 1.5712 | 20000 | 0.447 | 0.4046 | 0.9499 |
382
+ | 1.6498 | 21000 | 0.4307 | 0.3908 | 0.9508 |
383
+ | 1.7283 | 22000 | 0.4126 | 0.3773 | 0.9548 |
384
+ | 1.8069 | 23000 | 0.3985 | 0.3654 | 0.9564 |
385
+ | 1.8855 | 24000 | 0.3748 | 0.3582 | 0.9560 |
386
+ | 1.9640 | 25000 | 0.3675 | 0.3449 | 0.9581 |
387
+ | 2.0426 | 26000 | 0.3545 | 0.3390 | 0.9586 |
388
+ | 2.1211 | 27000 | 0.3456 | 0.3335 | 0.9595 |
389
+ | 2.1997 | 28000 | 0.3295 | 0.3255 | 0.9626 |
390
+ | 2.2783 | 29000 | 0.3198 | 0.3146 | 0.9624 |
391
+ | 2.3568 | 30000 | 0.3107 | 0.3101 | 0.9642 |
392
+ | 2.4354 | 31000 | 0.3139 | 0.3014 | 0.9665 |
393
+ | 2.5139 | 32000 | 0.2982 | 0.3005 | 0.9659 |
394
+ | 2.5925 | 33000 | 0.2903 | 0.2891 | 0.9663 |
395
+ | 2.6711 | 34000 | 0.2778 | 0.2859 | 0.9662 |
396
+ | 2.7496 | 35000 | 0.2731 | 0.2812 | 0.9667 |
397
+ | 2.8282 | 36000 | 0.2613 | 0.2757 | 0.9677 |
398
+ | 2.9067 | 37000 | 0.2566 | 0.2680 | 0.9689 |
399
+ | 2.9853 | 38000 | 0.2488 | 0.2674 | 0.9699 |
400
+ | 3.0639 | 39000 | 0.2434 | 0.2594 | 0.9694 |
401
+ | 3.1424 | 40000 | 0.2375 | 0.2574 | 0.9705 |
402
+ | 3.2210 | 41000 | 0.2295 | 0.2553 | 0.9706 |
403
+ | 3.2996 | 42000 | 0.223 | 0.2501 | 0.9703 |
404
+ | 3.3781 | 43000 | 0.2209 | 0.2455 | 0.9719 |
405
+ | 3.4567 | 44000 | 0.2211 | 0.2409 | 0.9711 |
406
+ | 3.5352 | 45000 | 0.2097 | 0.2396 | 0.9728 |
407
+ | 3.6138 | 46000 | 0.2068 | 0.2345 | 0.9734 |
408
+ | 3.6924 | 47000 | 0.1994 | 0.2298 | 0.9731 |
409
+ | 3.7709 | 48000 | 0.1986 | 0.2299 | 0.9730 |
410
+ | 3.8495 | 49000 | 0.1878 | 0.2271 | 0.9728 |
411
+ | 3.9280 | 50000 | 0.1872 | 0.2244 | 0.9739 |
412
+ | 4.0066 | 51000 | 0.1821 | 0.2249 | 0.9734 |
413
+ | 4.0852 | 52000 | 0.1823 | 0.2188 | 0.9739 |
414
+ | 4.1637 | 53000 | 0.1736 | 0.2176 | 0.9748 |
415
+ | 4.2423 | 54000 | 0.1691 | 0.2152 | 0.9745 |
416
+ | 4.3208 | 55000 | 0.1665 | 0.2148 | 0.9753 |
417
+ | 4.3994 | 56000 | 0.1663 | 0.2133 | 0.9748 |
418
+ | 4.4780 | 57000 | 0.1666 | 0.2123 | 0.9755 |
419
+ | 4.5565 | 58000 | 0.1589 | 0.2082 | 0.9758 |
420
+ | 4.6351 | 59000 | 0.155 | 0.2053 | 0.9762 |
421
+ | 4.7136 | 60000 | 0.155 | 0.2037 | 0.9762 |
422
+ | 4.7922 | 61000 | 0.1536 | 0.2031 | 0.9764 |
423
+ | 4.8708 | 62000 | 0.1443 | 0.2020 | 0.9759 |
424
+ | 4.9493 | 63000 | 0.146 | 0.1999 | 0.9752 |
425
+ | 5.0279 | 64000 | 0.1417 | 0.1969 | 0.9764 |
426
+ | 5.1064 | 65000 | 0.1407 | 0.1966 | 0.9761 |
427
+ | 5.1850 | 66000 | 0.1342 | 0.1981 | 0.9757 |
428
+ | 5.2636 | 67000 | 0.1342 | 0.1933 | 0.9768 |
429
+ | 5.3421 | 68000 | 0.1312 | 0.1944 | 0.9758 |
430
+ | 5.4207 | 69000 | 0.1329 | 0.1932 | 0.9772 |
431
+ | 5.4993 | 70000 | 0.1304 | 0.1908 | 0.9768 |
432
+ | 5.5778 | 71000 | 0.1247 | 0.1880 | 0.9772 |
433
+ | 5.6564 | 72000 | 0.1221 | 0.1861 | 0.9779 |
434
+ | 5.7349 | 73000 | 0.1225 | 0.1831 | 0.9784 |
435
+ | 5.8135 | 74000 | 0.1205 | 0.1854 | 0.9790 |
436
+ | 5.8921 | 75000 | 0.1152 | 0.1815 | 0.9789 |
437
+ | 5.9706 | 76000 | 0.1161 | 0.1827 | 0.9782 |
438
+ | 6.0492 | 77000 | 0.1151 | 0.1819 | 0.9781 |
439
+ | 6.1277 | 78000 | 0.113 | 0.1818 | 0.9780 |
440
+ | 6.2063 | 79000 | 0.1102 | 0.1823 | 0.9784 |
441
+ | 6.2849 | 80000 | 0.1067 | 0.1798 | 0.9780 |
442
+ | 6.3634 | 81000 | 0.1067 | 0.1782 | 0.9790 |
443
+ | 6.4420 | 82000 | 0.1116 | 0.1779 | 0.9782 |
444
+ | 6.5205 | 83000 | 0.107 | 0.1752 | 0.9782 |
445
+ | 6.5991 | 84000 | 0.1039 | 0.1739 | 0.9792 |
446
+ | 6.6777 | 85000 | 0.1013 | 0.1728 | 0.9789 |
447
+ | 6.7562 | 86000 | 0.1029 | 0.1713 | 0.9786 |
448
+ | 6.8348 | 87000 | 0.0972 | 0.1721 | 0.9791 |
449
+ | 6.9133 | 88000 | 0.0991 | 0.1703 | 0.9790 |
450
+ | 6.9919 | 89000 | 0.0955 | 0.1708 | 0.9791 |
451
+ | 7.0705 | 90000 | 0.097 | 0.1715 | 0.9786 |
452
+ | 7.1490 | 91000 | 0.0941 | 0.1716 | 0.9793 |
453
+ | 7.2276 | 92000 | 0.0922 | 0.1712 | 0.9795 |
454
+ | 7.3062 | 93000 | 0.0921 | 0.1706 | 0.9789 |
455
+ | 7.3847 | 94000 | 0.091 | 0.1691 | 0.9793 |
456
+ | 7.4633 | 95000 | 0.0942 | 0.1689 | 0.9787 |
457
+ | 7.5418 | 96000 | 0.0905 | 0.1678 | 0.9790 |
458
+ | 7.6204 | 97000 | 0.0871 | 0.1664 | 0.9792 |
459
+ | 7.6990 | 98000 | 0.0859 | 0.1666 | 0.9793 |
460
+ | 7.7775 | 99000 | 0.0876 | 0.1656 | 0.9785 |
461
+ | 7.8561 | 100000 | 0.084 | 0.1643 | 0.9795 |
462
+ | 7.9346 | 101000 | 0.0853 | 0.1654 | 0.9795 |
463
+ | 8.0132 | 102000 | 0.083 | 0.1640 | 0.9789 |
464
+ | 8.0918 | 103000 | 0.0849 | 0.1637 | 0.9795 |
465
+ | 8.1703 | 104000 | 0.0816 | 0.1626 | 0.9797 |
466
+ | 8.2489 | 105000 | 0.0803 | 0.1627 | 0.9796 |
467
+ | 8.3274 | 106000 | 0.0802 | 0.1623 | 0.9796 |
468
+ | 8.4060 | 107000 | 0.0808 | 0.1622 | 0.9798 |
469
+ | 8.4846 | 108000 | 0.0836 | 0.1632 | 0.9792 |
470
+ | 8.5631 | 109000 | 0.0791 | 0.1612 | 0.9796 |
471
+ | 8.6417 | 110000 | 0.0761 | 0.1609 | 0.9798 |
472
+ | 8.7202 | 111000 | 0.0782 | 0.1604 | 0.9797 |
473
+ | 8.7988 | 112000 | 0.0784 | 0.1604 | 0.9803 |
474
+ | 8.8774 | 113000 | 0.0737 | 0.1600 | 0.9804 |
475
+ | 8.9559 | 114000 | 0.0762 | 0.1602 | 0.9799 |
476
+ | 9.0345 | 115000 | 0.0764 | 0.1597 | 0.9802 |
477
+ | 9.1130 | 116000 | 0.0761 | 0.1600 | 0.9799 |
478
+ | 9.1916 | 117000 | 0.0729 | 0.1592 | 0.9797 |
479
+ | 9.2702 | 118000 | 0.0728 | 0.1595 | 0.9803 |
480
+ | 9.3487 | 119000 | 0.0722 | 0.1590 | 0.9798 |
481
+ | 9.4273 | 120000 | 0.0745 | 0.1591 | 0.9797 |
482
+ | 9.5059 | 121000 | 0.0741 | 0.1591 | 0.9798 |
483
+ | 9.5844 | 122000 | 0.0715 | 0.1587 | 0.9797 |
484
+ | 9.6630 | 123000 | 0.0719 | 0.1581 | 0.9799 |
485
+ | 9.7415 | 124000 | 0.0716 | 0.1578 | 0.9799 |
486
+ | 9.8201 | 125000 | 0.0714 | 0.1582 | 0.9801 |
487
+ | 9.8987 | 126000 | 0.0712 | 0.1579 | 0.9803 |
488
+ | 9.9772 | 127000 | 0.0707 | 0.1581 | 0.9802 |
489
+
490
+ </details>
491
+
492
+ ### Framework Versions
493
+ - Python: 3.12.4
494
+ - Sentence Transformers: 3.3.1
495
+ - Transformers: 4.44.2
496
+ - PyTorch: 2.4.1+cu124
497
+ - Accelerate: 0.33.0
498
+ - Datasets: 3.1.0
499
+ - Tokenizers: 0.19.1
500
+
501
+ ## Citation
502
+
503
+ ### BibTeX
504
+
505
+ #### Sentence Transformers
506
+ ```bibtex
507
+ @inproceedings{reimers-2019-sentence-bert,
508
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
509
+ author = "Reimers, Nils and Gurevych, Iryna",
510
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
511
+ month = "11",
512
+ year = "2019",
513
+ publisher = "Association for Computational Linguistics",
514
+ url = "https://arxiv.org/abs/1908.10084",
515
+ }
516
+ ```
517
+
518
+ #### MultipleNegativesRankingLoss
519
+ ```bibtex
520
+ @misc{henderson2017efficient,
521
+ title={Efficient Natural Language Response Suggestion for Smart Reply},
522
+ 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},
523
+ year={2017},
524
+ eprint={1705.00652},
525
+ archivePrefix={arXiv},
526
+ primaryClass={cs.CL}
527
+ }
528
+ ```
529
+
530
+ <!--
531
+ ## Glossary
532
+
533
+ *Clearly define terms in order to be accessible across audiences.*
534
+ -->
535
+
536
+ <!--
537
+ ## Model Card Authors
538
+
539
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
540
+ -->
541
+
542
+ <!--
543
+ ## Model Card Contact
544
+
545
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
546
+ -->
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "models/dbmdz/distilbert-base-turkish-cased-all-nli-turkish-translate-triplet/final",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertModel"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "output_past": true,
17
+ "pad_token_id": 0,
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": true,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.44.2",
24
+ "vocab_size": 32000
25
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.3.1",
4
+ "transformers": "4.44.2",
5
+ "pytorch": "2.4.1+cu124"
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:be6e214abf9f46e9096ef497549a500cf9587c5755beb6173b7e8b0ec32c3dbe
3
+ size 270003032
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": 512,
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 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
48
+ "mask_token": "[MASK]",
49
+ "max_len": 512,
50
+ "max_length": 512,
51
+ "model_max_length": 512,
52
+ "never_split": null,
53
+ "pad_to_multiple_of": null,
54
+ "pad_token": "[PAD]",
55
+ "pad_token_type_id": 0,
56
+ "padding_side": "right",
57
+ "sep_token": "[SEP]",
58
+ "stride": 0,
59
+ "strip_accents": null,
60
+ "tokenize_chinese_chars": true,
61
+ "tokenizer_class": "DistilBertTokenizer",
62
+ "truncation_side": "right",
63
+ "truncation_strategy": "longest_first",
64
+ "unk_token": "[UNK]"
65
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff