Hugging Face's logo

codersan
/
FaMiniLm_Mizan3

Sentence Similarity
sentence-transformers
TensorBoard
Safetensors
bert
feature-extraction
Generated from Trainer
dataset_size:1021596
loss:MultipleNegativesRankingLoss
text-embeddings-inference
Model card Files
xet
Metrics Community
codersan commited on
Commit
376cb0c
·
verified ·
1 Parent(s): f0685bd

Add new SentenceTransformer model

Browse files
Files changed (5) hide show
  1. 1_Pooling/config.json +10 -0
  2. README.md +1013 -0
  3. config_sentence_transformers.json +10 -0
  4. modules.json +20 -0
  5. sentence_bert_config.json +4 -0
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 384,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
+ }
README.md ADDED
@@ -0,0 +1,1013 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - sentence-transformers
4
+ - sentence-similarity
5
+ - feature-extraction
6
+ - generated_from_trainer
7
+ - dataset_size:1021596
8
+ - loss:MultipleNegativesRankingLoss
9
+ base_model: codersan/FaMiniLM
10
+ widget:
11
+ - source_sentence: 'بیشتر زنان دلیل این کار را درک نمی‌کنند '
12
+ sentences:
13
+ - Most women can't understand why this happens.
14
+ - feeling with confusion and annoyance that what he could decide easily and clearly
15
+ by himself, he could not discuss before Princess Tverskaya, who to him stood for
16
+ the incarnation of that brute force which would inevitably control him in the
17
+ life he led in the eyes of the world, and hinder him from giving way to his feeling
18
+ of love and forgiveness.
19
+ - 'MR TALLBOYS: Happy days, happy days!'
20
+ - source_sentence: به ادارات دولتی و اداره پست و سپس نزد استاندار رفت.
21
+ sentences:
22
+ - It strengthens the disease
23
+ - to government offices, to the post office, and to the Governor's.
24
+ - but she was utterly beside herself, and moved hanging on her husband's arm as
25
+ though in a dream.
26
+ - source_sentence: در همین آن صدائی به گوشش رسید که بدون شک صدای بسته شدن ‌پنجره خانه
27
+ خانم سمپریل بود!
28
+ sentences:
29
+ - Even as she did so a sound checked her for an instant ' the unmistakable bang
30
+ of a window shutting, somewhere in Mrs Semprill's house.
31
+ - That was over the line.
32
+ - No one would be better able than she to shape the virtuous man who would restore
33
+ the prestige of the family
34
+ - source_sentence: معنی آن مهر این است که 3 خدا، امروز به دست من انجام شد.
35
+ sentences:
36
+ - 'It signifies God: done this day by my hand.'
37
+ - They all embraced one another
38
+ - that's the mark of a Dark wizard.
39
+ - source_sentence: اگر این کار مداومت می‌یافت، سنگر قادر به مقاومت نمی‌بود.
40
+ sentences:
41
+ - If this were continued, the barricade was no longer tenable.
42
+ - They rolled down on the ground.
43
+ - Well, for this moment she had a protector.
44
+ pipeline_tag: sentence-similarity
45
+ library_name: sentence-transformers
46
+ ---
47
+
48
+ # SentenceTransformer based on codersan/FaMiniLM
49
+
50
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [codersan/FaMiniLM](https://huggingface.co/codersan/FaMiniLM). It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
51
+
52
+ ## Model Details
53
+
54
+ ### Model Description
55
+ - **Model Type:** Sentence Transformer
56
+ - **Base model:** [codersan/FaMiniLM](https://huggingface.co/codersan/FaMiniLM) <!-- at revision 22713fef958dd574a0171739cb8f8804c8650527 -->
57
+ - **Maximum Sequence Length:** 256 tokens
58
+ - **Output Dimensionality:** 384 dimensions
59
+ - **Similarity Function:** Cosine Similarity
60
+ <!-- - **Training Dataset:** Unknown -->
61
+ <!-- - **Language:** Unknown -->
62
+ <!-- - **License:** Unknown -->
63
+
64
+ ### Model Sources
65
+
66
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
67
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
68
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
69
+
70
+ ### Full Model Architecture
71
+
72
+ ```
73
+ SentenceTransformer(
74
+ (0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: BertModel
75
+ (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
76
+ (2): Normalize()
77
+ )
78
+ ```
79
+
80
+ ## Usage
81
+
82
+ ### Direct Usage (Sentence Transformers)
83
+
84
+ First install the Sentence Transformers library:
85
+
86
+ ```bash
87
+ pip install -U sentence-transformers
88
+ ```
89
+
90
+ Then you can load this model and run inference.
91
+ ```python
92
+ from sentence_transformers import SentenceTransformer
93
+
94
+ # Download from the 🤗 Hub
95
+ model = SentenceTransformer("codersan/FaMiniLm_Mizan3")
96
+ # Run inference
97
+ sentences = [
98
+ 'اگر این کار مداومت می\u200cیافت، سنگر قادر به مقاومت نمی\u200cبود.',
99
+ 'If this were continued, the barricade was no longer tenable.',
100
+ 'Well, for this moment she had a protector.',
101
+ ]
102
+ embeddings = model.encode(sentences)
103
+ print(embeddings.shape)
104
+ # [3, 384]
105
+
106
+ # Get the similarity scores for the embeddings
107
+ similarities = model.similarity(embeddings, embeddings)
108
+ print(similarities.shape)
109
+ # [3, 3]
110
+ ```
111
+
112
+ <!--
113
+ ### Direct Usage (Transformers)
114
+
115
+ <details><summary>Click to see the direct usage in Transformers</summary>
116
+
117
+ </details>
118
+ -->
119
+
120
+ <!--
121
+ ### Downstream Usage (Sentence Transformers)
122
+
123
+ You can finetune this model on your own dataset.
124
+
125
+ <details><summary>Click to expand</summary>
126
+
127
+ </details>
128
+ -->
129
+
130
+ <!--
131
+ ### Out-of-Scope Use
132
+
133
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
134
+ -->
135
+
136
+ <!--
137
+ ## Bias, Risks and Limitations
138
+
139
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
140
+ -->
141
+
142
+ <!--
143
+ ### Recommendations
144
+
145
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
146
+ -->
147
+
148
+ ## Training Details
149
+
150
+ ### Training Dataset
151
+
152
+ #### Unnamed Dataset
153
+
154
+
155
+ * Size: 1,021,596 training samples
156
+ * Columns: <code>anchor</code> and <code>positive</code>
157
+ * Approximate statistics based on the first 1000 samples:
158
+ | | anchor | positive |
159
+ |:--------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
160
+ | type | string | string |
161
+ | details | <ul><li>min: 4 tokens</li><li>mean: 46.68 tokens</li><li>max: 212 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 16.07 tokens</li><li>max: 81 tokens</li></ul> |
162
+ * Samples:
163
+ | anchor | positive |
164
+ |:--------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------|
165
+ | <code>دختران برای اطاعت امر پدر از جا برخاستند.</code> | <code>They arose to obey.</code> |
166
+ | <code>همه چیز را بم وقع خواهی دانست.</code> | <code>You'll know it all in time</code> |
167
+ | <code>او هر لحظه گرفتار یک‌ وضع است، زارزار گریه می‌کند. می‌گوید به ما توهین کرده‌اند، حیثیتمان را لکه‌دار نمودند.</code> | <code>She is in hysterics up there, and moans and says that we have been 'shamed and disgraced.</code> |
168
+ * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
169
+ ```json
170
+ {
171
+ "scale": 20.0,
172
+ "similarity_fct": "cos_sim"
173
+ }
174
+ ```
175
+
176
+ ### Training Hyperparameters
177
+ #### Non-Default Hyperparameters
178
+
179
+ - `eval_strategy`: steps
180
+ - `per_device_train_batch_size`: 16
181
+ - `learning_rate`: 2e-05
182
+ - `num_train_epochs`: 1
183
+ - `warmup_ratio`: 0.1
184
+ - `load_best_model_at_end`: True
185
+ - `push_to_hub`: True
186
+ - `hub_model_id`: codersan/FaMiniLm_Mizan3
187
+ - `eval_on_start`: True
188
+ - `batch_sampler`: no_duplicates
189
+
190
+ #### All Hyperparameters
191
+ <details><summary>Click to expand</summary>
192
+
193
+ - `overwrite_output_dir`: False
194
+ - `do_predict`: False
195
+ - `eval_strategy`: steps
196
+ - `prediction_loss_only`: True
197
+ - `per_device_train_batch_size`: 16
198
+ - `per_device_eval_batch_size`: 8
199
+ - `per_gpu_train_batch_size`: None
200
+ - `per_gpu_eval_batch_size`: None
201
+ - `gradient_accumulation_steps`: 1
202
+ - `eval_accumulation_steps`: None
203
+ - `torch_empty_cache_steps`: None
204
+ - `learning_rate`: 2e-05
205
+ - `weight_decay`: 0
206
+ - `adam_beta1`: 0.9
207
+ - `adam_beta2`: 0.999
208
+ - `adam_epsilon`: 1e-08
209
+ - `max_grad_norm`: 1
210
+ - `num_train_epochs`: 1
211
+ - `max_steps`: -1
212
+ - `lr_scheduler_type`: linear
213
+ - `lr_scheduler_kwargs`: {}
214
+ - `warmup_ratio`: 0.1
215
+ - `warmup_steps`: 0
216
+ - `log_level`: passive
217
+ - `log_level_replica`: warning
218
+ - `log_on_each_node`: True
219
+ - `logging_nan_inf_filter`: True
220
+ - `save_safetensors`: True
221
+ - `save_on_each_node`: False
222
+ - `save_only_model`: False
223
+ - `restore_callback_states_from_checkpoint`: False
224
+ - `no_cuda`: False
225
+ - `use_cpu`: False
226
+ - `use_mps_device`: False
227
+ - `seed`: 42
228
+ - `data_seed`: None
229
+ - `jit_mode_eval`: False
230
+ - `use_ipex`: False
231
+ - `bf16`: False
232
+ - `fp16`: False
233
+ - `fp16_opt_level`: O1
234
+ - `half_precision_backend`: auto
235
+ - `bf16_full_eval`: False
236
+ - `fp16_full_eval`: False
237
+ - `tf32`: None
238
+ - `local_rank`: 0
239
+ - `ddp_backend`: None
240
+ - `tpu_num_cores`: None
241
+ - `tpu_metrics_debug`: False
242
+ - `debug`: []
243
+ - `dataloader_drop_last`: False
244
+ - `dataloader_num_workers`: 0
245
+ - `dataloader_prefetch_factor`: None
246
+ - `past_index`: -1
247
+ - `disable_tqdm`: False
248
+ - `remove_unused_columns`: True
249
+ - `label_names`: None
250
+ - `load_best_model_at_end`: True
251
+ - `ignore_data_skip`: False
252
+ - `fsdp`: []
253
+ - `fsdp_min_num_params`: 0
254
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
255
+ - `fsdp_transformer_layer_cls_to_wrap`: None
256
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
257
+ - `deepspeed`: None
258
+ - `label_smoothing_factor`: 0.0
259
+ - `optim`: adamw_torch
260
+ - `optim_args`: None
261
+ - `adafactor`: False
262
+ - `group_by_length`: False
263
+ - `length_column_name`: length
264
+ - `ddp_find_unused_parameters`: None
265
+ - `ddp_bucket_cap_mb`: None
266
+ - `ddp_broadcast_buffers`: False
267
+ - `dataloader_pin_memory`: True
268
+ - `dataloader_persistent_workers`: False
269
+ - `skip_memory_metrics`: True
270
+ - `use_legacy_prediction_loop`: False
271
+ - `push_to_hub`: True
272
+ - `resume_from_checkpoint`: None
273
+ - `hub_model_id`: codersan/FaMiniLm_Mizan3
274
+ - `hub_strategy`: every_save
275
+ - `hub_private_repo`: None
276
+ - `hub_always_push`: False
277
+ - `gradient_checkpointing`: False
278
+ - `gradient_checkpointing_kwargs`: None
279
+ - `include_inputs_for_metrics`: False
280
+ - `include_for_metrics`: []
281
+ - `eval_do_concat_batches`: True
282
+ - `fp16_backend`: auto
283
+ - `push_to_hub_model_id`: None
284
+ - `push_to_hub_organization`: None
285
+ - `mp_parameters`:
286
+ - `auto_find_batch_size`: False
287
+ - `full_determinism`: False
288
+ - `torchdynamo`: None
289
+ - `ray_scope`: last
290
+ - `ddp_timeout`: 1800
291
+ - `torch_compile`: False
292
+ - `torch_compile_backend`: None
293
+ - `torch_compile_mode`: None
294
+ - `dispatch_batches`: None
295
+ - `split_batches`: None
296
+ - `include_tokens_per_second`: False
297
+ - `include_num_input_tokens_seen`: False
298
+ - `neftune_noise_alpha`: None
299
+ - `optim_target_modules`: None
300
+ - `batch_eval_metrics`: False
301
+ - `eval_on_start`: True
302
+ - `use_liger_kernel`: False
303
+ - `eval_use_gather_object`: False
304
+ - `average_tokens_across_devices`: False
305
+ - `prompts`: None
306
+ - `batch_sampler`: no_duplicates
307
+ - `multi_dataset_batch_sampler`: proportional
308
+
309
+ </details>
310
+
311
+ ### Training Logs
312
+ <details><summary>Click to expand</summary>
313
+
314
+ | Epoch | Step | Training Loss |
315
+ |:----------:|:-------:|:-------------:|
316
+ | 0 | 0 | - |
317
+ | 0.0016 | 100 | 3.1518 |
318
+ | 0.0031 | 200 | 3.1015 |
319
+ | 0.0047 | 300 | 2.9207 |
320
+ | **0.0063** | **400** | **2.8322** |
321
+ | 0.0078 | 500 | 2.7199 |
322
+ | 0.0094 | 600 | 2.6413 |
323
+ | 0.0110 | 700 | 2.4895 |
324
+ | 0.0125 | 800 | 2.4221 |
325
+ | 0.0141 | 900 | 2.2712 |
326
+ | 0.0157 | 1000 | 2.1497 |
327
+ | 0.0172 | 1100 | 2.0346 |
328
+ | 0.0188 | 1200 | 1.9132 |
329
+ | 0.0204 | 1300 | 1.848 |
330
+ | 0.0219 | 1400 | 1.7412 |
331
+ | 0.0235 | 1500 | 1.6231 |
332
+ | 0.0251 | 1600 | 1.5678 |
333
+ | 0.0266 | 1700 | 1.4954 |
334
+ | 0.0282 | 1800 | 1.4429 |
335
+ | 0.0298 | 1900 | 1.4179 |
336
+ | 0.0313 | 2000 | 1.3837 |
337
+ | 0.0329 | 2100 | 1.3612 |
338
+ | 0.0345 | 2200 | 1.3025 |
339
+ | 0.0360 | 2300 | 1.2768 |
340
+ | 0.0376 | 2400 | 1.2126 |
341
+ | 0.0392 | 2500 | 1.1951 |
342
+ | 0.0407 | 2600 | 1.1558 |
343
+ | 0.0423 | 2700 | 1.1002 |
344
+ | 0.0439 | 2800 | 1.1269 |
345
+ | 0.0454 | 2900 | 1.0932 |
346
+ | 0.0470 | 3000 | 1.0697 |
347
+ | 0.0486 | 3100 | 1.0455 |
348
+ | 0.0501 | 3200 | 1.0405 |
349
+ | 0.0517 | 3300 | 0.9895 |
350
+ | 0.0532 | 3400 | 0.9983 |
351
+ | 0.0548 | 3500 | 0.9381 |
352
+ | 0.0564 | 3600 | 0.9618 |
353
+ | 0.0579 | 3700 | 0.9799 |
354
+ | 0.0595 | 3800 | 0.8866 |
355
+ | 0.0611 | 3900 | 0.9085 |
356
+ | 0.0626 | 4000 | 0.9123 |
357
+ | 0.0642 | 4100 | 0.9017 |
358
+ | 0.0658 | 4200 | 0.8789 |
359
+ | 0.0673 | 4300 | 0.8164 |
360
+ | 0.0689 | 4400 | 0.8131 |
361
+ | 0.0705 | 4500 | 0.7834 |
362
+ | 0.0720 | 4600 | 0.7814 |
363
+ | 0.0736 | 4700 | 0.7927 |
364
+ | 0.0752 | 4800 | 0.8416 |
365
+ | 0.0767 | 4900 | 0.73 |
366
+ | 0.0783 | 5000 | 0.753 |
367
+ | 0.0799 | 5100 | 0.7397 |
368
+ | 0.0814 | 5200 | 0.7242 |
369
+ | 0.0830 | 5300 | 0.734 |
370
+ | 0.0846 | 5400 | 0.7379 |
371
+ | 0.0861 | 5500 | 0.7255 |
372
+ | 0.0877 | 5600 | 0.7621 |
373
+ | 0.0893 | 5700 | 0.6825 |
374
+ | 0.0908 | 5800 | 0.7056 |
375
+ | 0.0924 | 5900 | 0.6877 |
376
+ | 0.0940 | 6000 | 0.6865 |
377
+ | 0.0955 | 6100 | 0.6652 |
378
+ | 0.0971 | 6200 | 0.6445 |
379
+ | 0.0987 | 6300 | 0.6548 |
380
+ | 0.1002 | 6400 | 0.6556 |
381
+ | 0.1018 | 6500 | 0.6544 |
382
+ | 0.1034 | 6600 | 0.6496 |
383
+ | 0.1049 | 6700 | 0.6158 |
384
+ | 0.1065 | 6800 | 0.6693 |
385
+ | 0.1081 | 6900 | 0.6179 |
386
+ | 0.1096 | 7000 | 0.5527 |
387
+ | 0.1112 | 7100 | 0.596 |
388
+ | 0.1128 | 7200 | 0.5625 |
389
+ | 0.1143 | 7300 | 0.592 |
390
+ | 0.1159 | 7400 | 0.6063 |
391
+ | 0.1175 | 7500 | 0.5163 |
392
+ | 0.1190 | 7600 | 0.5472 |
393
+ | 0.1206 | 7700 | 0.5849 |
394
+ | 0.1222 | 7800 | 0.5948 |
395
+ | 0.1237 | 7900 | 0.5245 |
396
+ | 0.1253 | 8000 | 0.5561 |
397
+ | 0.1269 | 8100 | 0.5175 |
398
+ | 0.1284 | 8200 | 0.4929 |
399
+ | 0.1300 | 8300 | 0.5158 |
400
+ | 0.1316 | 8400 | 0.5429 |
401
+ | 0.1331 | 8500 | 0.5324 |
402
+ | 0.1347 | 8600 | 0.511 |
403
+ | 0.1363 | 8700 | 0.5242 |
404
+ | 0.1378 | 8800 | 0.5202 |
405
+ | 0.1394 | 8900 | 0.4967 |
406
+ | 0.1410 | 9000 | 0.5466 |
407
+ | 0.1425 | 9100 | 0.4865 |
408
+ | 0.1441 | 9200 | 0.5172 |
409
+ | 0.1457 | 9300 | 0.51 |
410
+ | 0.1472 | 9400 | 0.5204 |
411
+ | 0.1488 | 9500 | 0.4851 |
412
+ | 0.1504 | 9600 | 0.4726 |
413
+ | 0.1519 | 9700 | 0.4608 |
414
+ | 0.1535 | 9800 | 0.453 |
415
+ | 0.1551 | 9900 | 0.4539 |
416
+ | 0.1566 | 10000 | 0.442 |
417
+ | 0.1582 | 10100 | 0.4632 |
418
+ | 0.1597 | 10200 | 0.4024 |
419
+ | 0.1613 | 10300 | 0.4516 |
420
+ | 0.1629 | 10400 | 0.4551 |
421
+ | 0.1644 | 10500 | 0.4598 |
422
+ | 0.1660 | 10600 | 0.4791 |
423
+ | 0.1676 | 10700 | 0.4295 |
424
+ | 0.1691 | 10800 | 0.4552 |
425
+ | 0.1707 | 10900 | 0.4548 |
426
+ | 0.1723 | 11000 | 0.4795 |
427
+ | 0.1738 | 11100 | 0.4694 |
428
+ | 0.1754 | 11200 | 0.4049 |
429
+ | 0.1770 | 11300 | 0.4473 |
430
+ | 0.1785 | 11400 | 0.4161 |
431
+ | 0.1801 | 11500 | 0.4106 |
432
+ | 0.1817 | 11600 | 0.4276 |
433
+ | 0.1832 | 11700 | 0.416 |
434
+ | 0.1848 | 11800 | 0.4184 |
435
+ | 0.1864 | 11900 | 0.4268 |
436
+ | 0.1879 | 12000 | 0.4169 |
437
+ | 0.1895 | 12100 | 0.4063 |
438
+ | 0.1911 | 12200 | 0.4257 |
439
+ | 0.1926 | 12300 | 0.4114 |
440
+ | 0.1942 | 12400 | 0.3921 |
441
+ | 0.1958 | 12500 | 0.4037 |
442
+ | 0.1973 | 12600 | 0.4642 |
443
+ | 0.1989 | 12700 | 0.3929 |
444
+ | 0.2005 | 12800 | 0.4059 |
445
+ | 0.2020 | 12900 | 0.4132 |
446
+ | 0.2036 | 13000 | 0.4101 |
447
+ | 0.2052 | 13100 | 0.4122 |
448
+ | 0.2067 | 13200 | 0.3954 |
449
+ | 0.2083 | 13300 | 0.3671 |
450
+ | 0.2099 | 13400 | 0.4257 |
451
+ | 0.2114 | 13500 | 0.3719 |
452
+ | 0.2130 | 13600 | 0.3603 |
453
+ | 0.2146 | 13700 | 0.3465 |
454
+ | 0.2161 | 13800 | 0.3726 |
455
+ | 0.2177 | 13900 | 0.4021 |
456
+ | 0.2193 | 14000 | 0.3706 |
457
+ | 0.2208 | 14100 | 0.3471 |
458
+ | 0.2224 | 14200 | 0.3848 |
459
+ | 0.2240 | 14300 | 0.3967 |
460
+ | 0.2255 | 14400 | 0.3985 |
461
+ | 0.2271 | 14500 | 0.3457 |
462
+ | 0.2287 | 14600 | 0.3438 |
463
+ | 0.2302 | 14700 | 0.3333 |
464
+ | 0.2318 | 14800 | 0.3525 |
465
+ | 0.2334 | 14900 | 0.3948 |
466
+ | 0.2349 | 15000 | 0.3657 |
467
+ | 0.2365 | 15100 | 0.3437 |
468
+ | 0.2381 | 15200 | 0.361 |
469
+ | 0.2396 | 15300 | 0.356 |
470
+ | 0.2412 | 15400 | 0.3572 |
471
+ | 0.2428 | 15500 | 0.3464 |
472
+ | 0.2443 | 15600 | 0.3885 |
473
+ | 0.2459 | 15700 | 0.3324 |
474
+ | 0.2475 | 15800 | 0.3553 |
475
+ | 0.2490 | 15900 | 0.3201 |
476
+ | 0.2506 | 16000 | 0.4078 |
477
+ | 0.2522 | 16100 | 0.3919 |
478
+ | 0.2537 | 16200 | 0.3505 |
479
+ | 0.2553 | 16300 | 0.3423 |
480
+ | 0.2569 | 16400 | 0.3018 |
481
+ | 0.2584 | 16500 | 0.3392 |
482
+ | 0.2600 | 16600 | 0.3128 |
483
+ | 0.2616 | 16700 | 0.3542 |
484
+ | 0.2631 | 16800 | 0.3639 |
485
+ | 0.2647 | 16900 | 0.3765 |
486
+ | 0.2662 | 17000 | 0.3405 |
487
+ | 0.2678 | 17100 | 0.326 |
488
+ | 0.2694 | 17200 | 0.3591 |
489
+ | 0.2709 | 17300 | 0.3087 |
490
+ | 0.2725 | 17400 | 0.3336 |
491
+ | 0.2741 | 17500 | 0.2889 |
492
+ | 0.2756 | 17600 | 0.3341 |
493
+ | 0.2772 | 17700 | 0.3468 |
494
+ | 0.2788 | 17800 | 0.3033 |
495
+ | 0.2803 | 17900 | 0.3482 |
496
+ | 0.2819 | 18000 | 0.3649 |
497
+ | 0.2835 | 18100 | 0.3134 |
498
+ | 0.2850 | 18200 | 0.3264 |
499
+ | 0.2866 | 18300 | 0.3127 |
500
+ | 0.2882 | 18400 | 0.3483 |
501
+ | 0.2897 | 18500 | 0.349 |
502
+ | 0.2913 | 18600 | 0.2957 |
503
+ | 0.2929 | 18700 | 0.3443 |
504
+ | 0.2944 | 18800 | 0.2884 |
505
+ | 0.2960 | 18900 | 0.34 |
506
+ | 0.2976 | 19000 | 0.2875 |
507
+ | 0.2991 | 19100 | 0.3322 |
508
+ | 0.3007 | 19200 | 0.3438 |
509
+ | 0.3023 | 19300 | 0.3188 |
510
+ | 0.3038 | 19400 | 0.3315 |
511
+ | 0.3054 | 19500 | 0.3018 |
512
+ | 0.3070 | 19600 | 0.331 |
513
+ | 0.3085 | 19700 | 0.34 |
514
+ | 0.3101 | 19800 | 0.2819 |
515
+ | 0.3117 | 19900 | 0.3218 |
516
+ | 0.3132 | 20000 | 0.3026 |
517
+ | 0.3148 | 20100 | 0.3341 |
518
+ | 0.3164 | 20200 | 0.285 |
519
+ | 0.3179 | 20300 | 0.3076 |
520
+ | 0.3195 | 20400 | 0.3262 |
521
+ | 0.3211 | 20500 | 0.3225 |
522
+ | 0.3226 | 20600 | 0.293 |
523
+ | 0.3242 | 20700 | 0.3187 |
524
+ | 0.3258 | 20800 | 0.3255 |
525
+ | 0.3273 | 20900 | 0.2978 |
526
+ | 0.3289 | 21000 | 0.2946 |
527
+ | 0.3305 | 21100 | 0.2887 |
528
+ | 0.3320 | 21200 | 0.3098 |
529
+ | 0.3336 | 21300 | 0.2942 |
530
+ | 0.3352 | 21400 | 0.3134 |
531
+ | 0.3367 | 21500 | 0.267 |
532
+ | 0.3383 | 21600 | 0.2907 |
533
+ | 0.3399 | 21700 | 0.2919 |
534
+ | 0.3414 | 21800 | 0.2985 |
535
+ | 0.3430 | 21900 | 0.2815 |
536
+ | 0.3446 | 22000 | 0.2785 |
537
+ | 0.3461 | 22100 | 0.2932 |
538
+ | 0.3477 | 22200 | 0.2599 |
539
+ | 0.3493 | 22300 | 0.2697 |
540
+ | 0.3508 | 22400 | 0.3206 |
541
+ | 0.3524 | 22500 | 0.2874 |
542
+ | 0.3540 | 22600 | 0.2947 |
543
+ | 0.3555 | 22700 | 0.2863 |
544
+ | 0.3571 | 22800 | 0.2906 |
545
+ | 0.3587 | 22900 | 0.3155 |
546
+ | 0.3602 | 23000 | 0.304 |
547
+ | 0.3618 | 23100 | 0.2769 |
548
+ | 0.3634 | 23200 | 0.3024 |
549
+ | 0.3649 | 23300 | 0.2877 |
550
+ | 0.3665 | 23400 | 0.2907 |
551
+ | 0.3681 | 23500 | 0.2813 |
552
+ | 0.3696 | 23600 | 0.3059 |
553
+ | 0.3712 | 23700 | 0.3004 |
554
+ | 0.3727 | 23800 | 0.261 |
555
+ | 0.3743 | 23900 | 0.2952 |
556
+ | 0.3759 | 24000 | 0.2687 |
557
+ | 0.3774 | 24100 | 0.2645 |
558
+ | 0.3790 | 24200 | 0.323 |
559
+ | 0.3806 | 24300 | 0.2982 |
560
+ | 0.3821 | 24400 | 0.2797 |
561
+ | 0.3837 | 24500 | 0.2661 |
562
+ | 0.3853 | 24600 | 0.251 |
563
+ | 0.3868 | 24700 | 0.2991 |
564
+ | 0.3884 | 24800 | 0.2634 |
565
+ | 0.3900 | 24900 | 0.2716 |
566
+ | 0.3915 | 25000 | 0.2902 |
567
+ | 0.3931 | 25100 | 0.276 |
568
+ | 0.3947 | 25200 | 0.2695 |
569
+ | 0.3962 | 25300 | 0.2415 |
570
+ | 0.3978 | 25400 | 0.2694 |
571
+ | 0.3994 | 25500 | 0.2604 |
572
+ | 0.4009 | 25600 | 0.2966 |
573
+ | 0.4025 | 25700 | 0.2798 |
574
+ | 0.4041 | 25800 | 0.2354 |
575
+ | 0.4056 | 25900 | 0.3068 |
576
+ | 0.4072 | 26000 | 0.2434 |
577
+ | 0.4088 | 26100 | 0.24 |
578
+ | 0.4103 | 26200 | 0.2888 |
579
+ | 0.4119 | 26300 | 0.2525 |
580
+ | 0.4135 | 26400 | 0.2632 |
581
+ | 0.4150 | 26500 | 0.2643 |
582
+ | 0.4166 | 26600 | 0.2585 |
583
+ | 0.4182 | 26700 | 0.236 |
584
+ | 0.4197 | 26800 | 0.2796 |
585
+ | 0.4213 | 26900 | 0.2658 |
586
+ | 0.4229 | 27000 | 0.241 |
587
+ | 0.4244 | 27100 | 0.2764 |
588
+ | 0.4260 | 27200 | 0.2534 |
589
+ | 0.4276 | 27300 | 0.2572 |
590
+ | 0.4291 | 27400 | 0.2513 |
591
+ | 0.4307 | 27500 | 0.2254 |
592
+ | 0.4323 | 27600 | 0.2734 |
593
+ | 0.4338 | 27700 | 0.2459 |
594
+ | 0.4354 | 27800 | 0.2202 |
595
+ | 0.4370 | 27900 | 0.2583 |
596
+ | 0.4385 | 28000 | 0.2741 |
597
+ | 0.4401 | 28100 | 0.2329 |
598
+ | 0.4417 | 28200 | 0.2262 |
599
+ | 0.4432 | 28300 | 0.2573 |
600
+ | 0.4448 | 28400 | 0.2559 |
601
+ | 0.4464 | 28500 | 0.3188 |
602
+ | 0.4479 | 28600 | 0.2431 |
603
+ | 0.4495 | 28700 | 0.275 |
604
+ | 0.4511 | 28800 | 0.25 |
605
+ | 0.4526 | 28900 | 0.2721 |
606
+ | 0.4542 | 29000 | 0.2401 |
607
+ | 0.4558 | 29100 | 0.2435 |
608
+ | 0.4573 | 29200 | 0.2703 |
609
+ | 0.4589 | 29300 | 0.2266 |
610
+ | 0.4605 | 29400 | 0.263 |
611
+ | 0.4620 | 29500 | 0.242 |
612
+ | 0.4636 | 29600 | 0.2844 |
613
+ | 0.4652 | 29700 | 0.2317 |
614
+ | 0.4667 | 29800 | 0.2768 |
615
+ | 0.4683 | 29900 | 0.2496 |
616
+ | 0.4699 | 30000 | 0.2377 |
617
+ | 0.4714 | 30100 | 0.2813 |
618
+ | 0.4730 | 30200 | 0.2175 |
619
+ | 0.4745 | 30300 | 0.2502 |
620
+ | 0.4761 | 30400 | 0.2591 |
621
+ | 0.4777 | 30500 | 0.2547 |
622
+ | 0.4792 | 30600 | 0.2521 |
623
+ | 0.4808 | 30700 | 0.263 |
624
+ | 0.4824 | 30800 | 0.1986 |
625
+ | 0.4839 | 30900 | 0.2437 |
626
+ | 0.4855 | 31000 | 0.2397 |
627
+ | 0.4871 | 31100 | 0.2424 |
628
+ | 0.4886 | 31200 | 0.2785 |
629
+ | 0.4902 | 31300 | 0.2517 |
630
+ | 0.4918 | 31400 | 0.2467 |
631
+ | 0.4933 | 31500 | 0.242 |
632
+ | 0.4949 | 31600 | 0.26 |
633
+ | 0.4965 | 31700 | 0.2345 |
634
+ | 0.4980 | 31800 | 0.2228 |
635
+ | 0.4996 | 31900 | 0.2455 |
636
+ | 0.5012 | 32000 | 0.2505 |
637
+ | 0.5027 | 32100 | 0.2352 |
638
+ | 0.5043 | 32200 | 0.2529 |
639
+ | 0.5059 | 32300 | 0.2537 |
640
+ | 0.5074 | 32400 | 0.2147 |
641
+ | 0.5090 | 32500 | 0.2085 |
642
+ | 0.5106 | 32600 | 0.2472 |
643
+ | 0.5121 | 32700 | 0.2487 |
644
+ | 0.5137 | 32800 | 0.2543 |
645
+ | 0.5153 | 32900 | 0.2519 |
646
+ | 0.5168 | 33000 | 0.2589 |
647
+ | 0.5184 | 33100 | 0.2232 |
648
+ | 0.5200 | 33200 | 0.2148 |
649
+ | 0.5215 | 33300 | 0.2377 |
650
+ | 0.5231 | 33400 | 0.2311 |
651
+ | 0.5247 | 33500 | 0.2153 |
652
+ | 0.5262 | 33600 | 0.2138 |
653
+ | 0.5278 | 33700 | 0.218 |
654
+ | 0.5294 | 33800 | 0.2298 |
655
+ | 0.5309 | 33900 | 0.2663 |
656
+ | 0.5325 | 34000 | 0.2489 |
657
+ | 0.5341 | 34100 | 0.2129 |
658
+ | 0.5356 | 34200 | 0.2298 |
659
+ | 0.5372 | 34300 | 0.2742 |
660
+ | 0.5388 | 34400 | 0.2389 |
661
+ | 0.5403 | 34500 | 0.2232 |
662
+ | 0.5419 | 34600 | 0.1931 |
663
+ | 0.5435 | 34700 | 0.2504 |
664
+ | 0.5450 | 34800 | 0.2349 |
665
+ | 0.5466 | 34900 | 0.22 |
666
+ | 0.5482 | 35000 | 0.249 |
667
+ | 0.5497 | 35100 | 0.2541 |
668
+ | 0.5513 | 35200 | 0.2406 |
669
+ | 0.5529 | 35300 | 0.2168 |
670
+ | 0.5544 | 35400 | 0.2481 |
671
+ | 0.5560 | 35500 | 0.2274 |
672
+ | 0.5576 | 35600 | 0.2168 |
673
+ | 0.5591 | 35700 | 0.2443 |
674
+ | 0.5607 | 35800 | 0.2378 |
675
+ | 0.5623 | 35900 | 0.2364 |
676
+ | 0.5638 | 36000 | 0.2232 |
677
+ | 0.5654 | 36100 | 0.2044 |
678
+ | 0.5670 | 36200 | 0.2153 |
679
+ | 0.5685 | 36300 | 0.2178 |
680
+ | 0.5701 | 36400 | 0.2314 |
681
+ | 0.5717 | 36500 | 0.2448 |
682
+ | 0.5732 | 36600 | 0.2652 |
683
+ | 0.5748 | 36700 | 0.2315 |
684
+ | 0.5764 | 36800 | 0.2071 |
685
+ | 0.5779 | 36900 | 0.2267 |
686
+ | 0.5795 | 37000 | 0.2797 |
687
+ | 0.5810 | 37100 | 0.2053 |
688
+ | 0.5826 | 37200 | 0.2331 |
689
+ | 0.5842 | 37300 | 0.2231 |
690
+ | 0.5857 | 37400 | 0.2135 |
691
+ | 0.5873 | 37500 | 0.2424 |
692
+ | 0.5889 | 37600 | 0.2345 |
693
+ | 0.5904 | 37700 | 0.2111 |
694
+ | 0.5920 | 37800 | 0.2553 |
695
+ | 0.5936 | 37900 | 0.2252 |
696
+ | 0.5951 | 38000 | 0.2033 |
697
+ | 0.5967 | 38100 | 0.2284 |
698
+ | 0.5983 | 38200 | 0.213 |
699
+ | 0.5998 | 38300 | 0.195 |
700
+ | 0.6014 | 38400 | 0.1886 |
701
+ | 0.6030 | 38500 | 0.2192 |
702
+ | 0.6045 | 38600 | 0.2569 |
703
+ | 0.6061 | 38700 | 0.1765 |
704
+ | 0.6077 | 38800 | 0.2127 |
705
+ | 0.6092 | 38900 | 0.2213 |
706
+ | 0.6108 | 39000 | 0.2217 |
707
+ | 0.6124 | 39100 | 0.2163 |
708
+ | 0.6139 | 39200 | 0.2141 |
709
+ | 0.6155 | 39300 | 0.2255 |
710
+ | 0.6171 | 39400 | 0.2326 |
711
+ | 0.6186 | 39500 | 0.2005 |
712
+ | 0.6202 | 39600 | 0.2043 |
713
+ | 0.6218 | 39700 | 0.2122 |
714
+ | 0.6233 | 39800 | 0.2212 |
715
+ | 0.6249 | 39900 | 0.2265 |
716
+ | 0.6265 | 40000 | 0.2259 |
717
+ | 0.6280 | 40100 | 0.2456 |
718
+ | 0.6296 | 40200 | 0.2037 |
719
+ | 0.6312 | 40300 | 0.2082 |
720
+ | 0.6327 | 40400 | 0.2284 |
721
+ | 0.6343 | 40500 | 0.2246 |
722
+ | 0.6359 | 40600 | 0.1884 |
723
+ | 0.6374 | 40700 | 0.1909 |
724
+ | 0.6390 | 40800 | 0.2038 |
725
+ | 0.6406 | 40900 | 0.2249 |
726
+ | 0.6421 | 41000 | 0.2211 |
727
+ | 0.6437 | 41100 | 0.2267 |
728
+ | 0.6453 | 41200 | 0.1926 |
729
+ | 0.6468 | 41300 | 0.1787 |
730
+ | 0.6484 | 41400 | 0.2209 |
731
+ | 0.6500 | 41500 | 0.2091 |
732
+ | 0.6515 | 41600 | 0.2064 |
733
+ | 0.6531 | 41700 | 0.2093 |
734
+ | 0.6547 | 41800 | 0.2413 |
735
+ | 0.6562 | 41900 | 0.2141 |
736
+ | 0.6578 | 42000 | 0.2293 |
737
+ | 0.6594 | 42100 | 0.2084 |
738
+ | 0.6609 | 42200 | 0.2095 |
739
+ | 0.6625 | 42300 | 0.2162 |
740
+ | 0.6641 | 42400 | 0.2188 |
741
+ | 0.6656 | 42500 | 0.1992 |
742
+ | 0.6672 | 42600 | 0.2216 |
743
+ | 0.6688 | 42700 | 0.2338 |
744
+ | 0.6703 | 42800 | 0.1941 |
745
+ | 0.6719 | 42900 | 0.2122 |
746
+ | 0.6735 | 43000 | 0.194 |
747
+ | 0.6750 | 43100 | 0.2413 |
748
+ | 0.6766 | 43200 | 0.232 |
749
+ | 0.6782 | 43300 | 0.2115 |
750
+ | 0.6797 | 43400 | 0.2172 |
751
+ | 0.6813 | 43500 | 0.2122 |
752
+ | 0.6829 | 43600 | 0.2059 |
753
+ | 0.6844 | 43700 | 0.2085 |
754
+ | 0.6860 | 43800 | 0.2045 |
755
+ | 0.6875 | 43900 | 0.1893 |
756
+ | 0.6891 | 44000 | 0.204 |
757
+ | 0.6907 | 44100 | 0.1991 |
758
+ | 0.6922 | 44200 | 0.2342 |
759
+ | 0.6938 | 44300 | 0.1834 |
760
+ | 0.6954 | 44400 | 0.1979 |
761
+ | 0.6969 | 44500 | 0.2302 |
762
+ | 0.6985 | 44600 | 0.2144 |
763
+ | 0.7001 | 44700 | 0.185 |
764
+ | 0.7016 | 44800 | 0.2014 |
765
+ | 0.7032 | 44900 | 0.1772 |
766
+ | 0.7048 | 45000 | 0.1967 |
767
+ | 0.7063 | 45100 | 0.1924 |
768
+ | 0.7079 | 45200 | 0.2114 |
769
+ | 0.7095 | 45300 | 0.2091 |
770
+ | 0.7110 | 45400 | 0.2044 |
771
+ | 0.7126 | 45500 | 0.2246 |
772
+ | 0.7142 | 45600 | 0.2109 |
773
+ | 0.7157 | 45700 | 0.1772 |
774
+ | 0.7173 | 45800 | 0.1988 |
775
+ | 0.7189 | 45900 | 0.2183 |
776
+ | 0.7204 | 46000 | 0.1918 |
777
+ | 0.7220 | 46100 | 0.2332 |
778
+ | 0.7236 | 46200 | 0.2097 |
779
+ | 0.7251 | 46300 | 0.2005 |
780
+ | 0.7267 | 46400 | 0.189 |
781
+ | 0.7283 | 46500 | 0.1993 |
782
+ | 0.7298 | 46600 | 0.2224 |
783
+ | 0.7314 | 46700 | 0.2 |
784
+ | 0.7330 | 46800 | 0.1949 |
785
+ | 0.7345 | 46900 | 0.2061 |
786
+ | 0.7361 | 47000 | 0.211 |
787
+ | 0.7377 | 47100 | 0.2393 |
788
+ | 0.7392 | 47200 | 0.2498 |
789
+ | 0.7408 | 47300 | 0.1811 |
790
+ | 0.7424 | 47400 | 0.1873 |
791
+ | 0.7439 | 47500 | 0.2238 |
792
+ | 0.7455 | 47600 | 0.1918 |
793
+ | 0.7471 | 47700 | 0.1805 |
794
+ | 0.7486 | 47800 | 0.2256 |
795
+ | 0.7502 | 47900 | 0.1901 |
796
+ | 0.7518 | 48000 | 0.2344 |
797
+ | 0.7533 | 48100 | 0.2212 |
798
+ | 0.7549 | 48200 | 0.2089 |
799
+ | 0.7565 | 48300 | 0.2169 |
800
+ | 0.7580 | 48400 | 0.2152 |
801
+ | 0.7596 | 48500 | 0.1831 |
802
+ | 0.7612 | 48600 | 0.1521 |
803
+ | 0.7627 | 48700 | 0.2177 |
804
+ | 0.7643 | 48800 | 0.2035 |
805
+ | 0.7659 | 48900 | 0.1713 |
806
+ | 0.7674 | 49000 | 0.2547 |
807
+ | 0.7690 | 49100 | 0.1802 |
808
+ | 0.7706 | 49200 | 0.1975 |
809
+ | 0.7721 | 49300 | 0.2107 |
810
+ | 0.7737 | 49400 | 0.2078 |
811
+ | 0.7753 | 49500 | 0.1917 |
812
+ | 0.7768 | 49600 | 0.1917 |
813
+ | 0.7784 | 49700 | 0.1948 |
814
+ | 0.7800 | 49800 | 0.1881 |
815
+ | 0.7815 | 49900 | 0.1799 |
816
+ | 0.7831 | 50000 | 0.2184 |
817
+ | 0.7847 | 50100 | 0.2323 |
818
+ | 0.7862 | 50200 | 0.1949 |
819
+ | 0.7878 | 50300 | 0.1908 |
820
+ | 0.7894 | 50400 | 0.182 |
821
+ | 0.7909 | 50500 | 0.1783 |
822
+ | 0.7925 | 50600 | 0.2187 |
823
+ | 0.7940 | 50700 | 0.1711 |
824
+ | 0.7956 | 50800 | 0.2127 |
825
+ | 0.7972 | 50900 | 0.1886 |
826
+ | 0.7987 | 51000 | 0.1825 |
827
+ | 0.8003 | 51100 | 0.206 |
828
+ | 0.8019 | 51200 | 0.2058 |
829
+ | 0.8034 | 51300 | 0.2065 |
830
+ | 0.8050 | 51400 | 0.1857 |
831
+ | 0.8066 | 51500 | 0.1853 |
832
+ | 0.8081 | 51600 | 0.2035 |
833
+ | 0.8097 | 51700 | 0.194 |
834
+ | 0.8113 | 51800 | 0.2157 |
835
+ | 0.8128 | 51900 | 0.1965 |
836
+ | 0.8144 | 52000 | 0.1924 |
837
+ | 0.8160 | 52100 | 0.1995 |
838
+ | 0.8175 | 52200 | 0.2166 |
839
+ | 0.8191 | 52300 | 0.15 |
840
+ | 0.8207 | 52400 | 0.1507 |
841
+ | 0.8222 | 52500 | 0.2096 |
842
+ | 0.8238 | 52600 | 0.205 |
843
+ | 0.8254 | 52700 | 0.207 |
844
+ | 0.8269 | 52800 | 0.1735 |
845
+ | 0.8285 | 52900 | 0.1748 |
846
+ | 0.8301 | 53000 | 0.2401 |
847
+ | 0.8316 | 53100 | 0.1749 |
848
+ | 0.8332 | 53200 | 0.1996 |
849
+ | 0.8348 | 53300 | 0.194 |
850
+ | 0.8363 | 53400 | 0.1856 |
851
+ | 0.8379 | 53500 | 0.1926 |
852
+ | 0.8395 | 53600 | 0.1914 |
853
+ | 0.8410 | 53700 | 0.1988 |
854
+ | 0.8426 | 53800 | 0.1778 |
855
+ | 0.8442 | 53900 | 0.1884 |
856
+ | 0.8457 | 54000 | 0.1965 |
857
+ | 0.8473 | 54100 | 0.2086 |
858
+ | 0.8489 | 54200 | 0.1934 |
859
+ | 0.8504 | 54300 | 0.1789 |
860
+ | 0.8520 | 54400 | 0.1947 |
861
+ | 0.8536 | 54500 | 0.1768 |
862
+ | 0.8551 | 54600 | 0.2194 |
863
+ | 0.8567 | 54700 | 0.1944 |
864
+ | 0.8583 | 54800 | 0.1946 |
865
+ | 0.8598 | 54900 | 0.1998 |
866
+ | 0.8614 | 55000 | 0.1716 |
867
+ | 0.8630 | 55100 | 0.202 |
868
+ | 0.8645 | 55200 | 0.2069 |
869
+ | 0.8661 | 55300 | 0.2221 |
870
+ | 0.8677 | 55400 | 0.1859 |
871
+ | 0.8692 | 55500 | 0.1817 |
872
+ | 0.8708 | 55600 | 0.2091 |
873
+ | 0.8724 | 55700 | 0.1756 |
874
+ | 0.8739 | 55800 | 0.1982 |
875
+ | 0.8755 | 55900 | 0.1947 |
876
+ | 0.8771 | 56000 | 0.1745 |
877
+ | 0.8786 | 56100 | 0.1914 |
878
+ | 0.8802 | 56200 | 0.1867 |
879
+ | 0.8818 | 56300 | 0.1935 |
880
+ | 0.8833 | 56400 | 0.1844 |
881
+ | 0.8849 | 56500 | 0.1704 |
882
+ | 0.8865 | 56600 | 0.2127 |
883
+ | 0.8880 | 56700 | 0.224 |
884
+ | 0.8896 | 56800 | 0.2092 |
885
+ | 0.8912 | 56900 | 0.2042 |
886
+ | 0.8927 | 57000 | 0.1898 |
887
+ | 0.8943 | 57100 | 0.1515 |
888
+ | 0.8958 | 57200 | 0.1952 |
889
+ | 0.8974 | 57300 | 0.17 |
890
+ | 0.8990 | 57400 | 0.1843 |
891
+ | 0.9005 | 57500 | 0.2019 |
892
+ | 0.9021 | 57600 | 0.1724 |
893
+ | 0.9037 | 57700 | 0.1912 |
894
+ | 0.9052 | 57800 | 0.1979 |
895
+ | 0.9068 | 57900 | 0.2014 |
896
+ | 0.9084 | 58000 | 0.2063 |
897
+ | 0.9099 | 58100 | 0.1794 |
898
+ | 0.9115 | 58200 | 0.1972 |
899
+ | 0.9131 | 58300 | 0.1501 |
900
+ | 0.9146 | 58400 | 0.2001 |
901
+ | 0.9162 | 58500 | 0.2082 |
902
+ | 0.9178 | 58600 | 0.2076 |
903
+ | 0.9193 | 58700 | 0.1722 |
904
+ | 0.9209 | 58800 | 0.1954 |
905
+ | 0.9225 | 58900 | 0.1604 |
906
+ | 0.9240 | 59000 | 0.1816 |
907
+ | 0.9256 | 59100 | 0.1809 |
908
+ | 0.9272 | 59200 | 0.1762 |
909
+ | 0.9287 | 59300 | 0.215 |
910
+ | 0.9303 | 59400 | 0.1953 |
911
+ | 0.9319 | 59500 | 0.1865 |
912
+ | 0.9334 | 59600 | 0.208 |
913
+ | 0.9350 | 59700 | 0.2035 |
914
+ | 0.9366 | 59800 | 0.1966 |
915
+ | 0.9381 | 59900 | 0.1777 |
916
+ | 0.9397 | 60000 | 0.2044 |
917
+ | 0.9413 | 60100 | 0.1773 |
918
+ | 0.9428 | 60200 | 0.1843 |
919
+ | 0.9444 | 60300 | 0.1786 |
920
+ | 0.9460 | 60400 | 0.1958 |
921
+ | 0.9475 | 60500 | 0.1959 |
922
+ | 0.9491 | 60600 | 0.2047 |
923
+ | 0.9507 | 60700 | 0.2 |
924
+ | 0.9522 | 60800 | 0.1843 |
925
+ | 0.9538 | 60900 | 0.1946 |
926
+ | 0.9554 | 61000 | 0.1752 |
927
+ | 0.9569 | 61100 | 0.1724 |
928
+ | 0.9585 | 61200 | 0.1701 |
929
+ | 0.9601 | 61300 | 0.1791 |
930
+ | 0.9616 | 61400 | 0.1731 |
931
+ | 0.9632 | 61500 | 0.203 |
932
+ | 0.9648 | 61600 | 0.1985 |
933
+ | 0.9663 | 61700 | 0.1968 |
934
+ | 0.9679 | 61800 | 0.1719 |
935
+ | 0.9695 | 61900 | 0.1608 |
936
+ | 0.9710 | 62000 | 0.1691 |
937
+ | 0.9726 | 62100 | 0.1761 |
938
+ | 0.9742 | 62200 | 0.1805 |
939
+ | 0.9757 | 62300 | 0.1732 |
940
+ | 0.9773 | 62400 | 0.1657 |
941
+ | 0.9789 | 62500 | 0.1757 |
942
+ | 0.9804 | 62600 | 0.157 |
943
+ | 0.9820 | 62700 | 0.1995 |
944
+ | 0.9836 | 62800 | 0.1937 |
945
+ | 0.9851 | 62900 | 0.1839 |
946
+ | 0.9867 | 63000 | 0.194 |
947
+ | 0.9883 | 63100 | 0.1755 |
948
+ | 0.9898 | 63200 | 0.1819 |
949
+ | 0.9914 | 63300 | 0.1918 |
950
+ | 0.9930 | 63400 | 0.1636 |
951
+ | 0.9945 | 63500 | 0.1731 |
952
+ | 0.9961 | 63600 | 0.1671 |
953
+ | 0.9977 | 63700 | 0.1704 |
954
+ | 0.9992 | 63800 | 0.2089 |
955
+
956
+ * The bold row denotes the saved checkpoint.
957
+ </details>
958
+
959
+ ### Framework Versions
960
+ - Python: 3.10.12
961
+ - Sentence Transformers: 3.3.1
962
+ - Transformers: 4.47.0
963
+ - PyTorch: 2.5.1+cu121
964
+ - Accelerate: 1.2.1
965
+ - Datasets: 3.2.0
966
+ - Tokenizers: 0.21.0
967
+
968
+ ## Citation
969
+
970
+ ### BibTeX
971
+
972
+ #### Sentence Transformers
973
+ ```bibtex
974
+ @inproceedings{reimers-2019-sentence-bert,
975
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
976
+ author = "Reimers, Nils and Gurevych, Iryna",
977
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
978
+ month = "11",
979
+ year = "2019",
980
+ publisher = "Association for Computational Linguistics",
981
+ url = "https://arxiv.org/abs/1908.10084",
982
+ }
983
+ ```
984
+
985
+ #### MultipleNegativesRankingLoss
986
+ ```bibtex
987
+ @misc{henderson2017efficient,
988
+ title={Efficient Natural Language Response Suggestion for Smart Reply},
989
+ 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},
990
+ year={2017},
991
+ eprint={1705.00652},
992
+ archivePrefix={arXiv},
993
+ primaryClass={cs.CL}
994
+ }
995
+ ```
996
+
997
+ <!--
998
+ ## Glossary
999
+
1000
+ *Clearly define terms in order to be accessible across audiences.*
1001
+ -->
1002
+
1003
+ <!--
1004
+ ## Model Card Authors
1005
+
1006
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
1007
+ -->
1008
+
1009
+ <!--
1010
+ ## Model Card Contact
1011
+
1012
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
1013
+ -->
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.3.1",
4
+ "transformers": "4.47.0",
5
+ "pytorch": "2.5.1+cu121"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null,
9
+ "similarity_fn_name": "cosine"
10
+ }
modules.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ },
14
+ {
15
+ "idx": 2,
16
+ "name": "2",
17
+ "path": "2_Normalize",
18
+ "type": "sentence_transformers.models.Normalize"
19
+ }
20
+ ]
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 256,
3
+ "do_lower_case": false
4
+ }