Hugging Face's logo

yahyaabd
/
allstats-semantic-search-mini-model-v2

Sentence Similarity
sentence-transformers
Safetensors
bert
feature-extraction
Generated from Trainer
dataset_size:244856
loss:CosineSimilarityLoss
Eval Results (legacy)
text-embeddings-inference
Model card Files
xet
 Community
yahyaabd commited on
Commit
9be9cdc
·
verified ·
1 Parent(s): 41fbb06

Add new SentenceTransformer model

Browse files
Files changed (12) hide show
  1. .gitattributes +2 -0
  2. 1_Pooling/config.json +10 -0
  3. README.md +483 -0
  4. config.json +26 -0
  5. config_sentence_transformers.json +10 -0
  6. model.safetensors +3 -0
  7. modules.json +14 -0
  8. sentence_bert_config.json +4 -0
  9. special_tokens_map.json +51 -0
  10. tokenizer.json +3 -0
  11. tokenizer_config.json +65 -0
  12. unigram.json +3 -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
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ unigram.json filter=lfs diff=lfs merge=lfs -text
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 384,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
+ }
README.md ADDED
@@ -0,0 +1,483 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - sentence-transformers
4
+ - sentence-similarity
5
+ - feature-extraction
6
+ - generated_from_trainer
7
+ - dataset_size:244856
8
+ - loss:CosineSimilarityLoss
9
+ base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
10
+ widget:
11
+ - source_sentence: Bulan apa inflasi sebesar 0,63 persen terjadi pada tahun 2013?
12
+ sentences:
13
+ - Pada bulan Mei 2013 terjadi inflasi sebesar 0,2 persen
14
+ - Nilai Tukar Petani (NTP) April 2024 sebesar 116,79 atau turun 2,18 persen.
15
+ - Posisi Kredit Perbankan<sup>1</sup>dalam Rupiah dan Valuta Asing Menurut Sektor
16
+ Ekonomi (miliar rupiah), 2016-2018
17
+ - source_sentence: Berapa persen penurunan Nilai Tukar Petani NTP Februari 2017
18
+ sentences:
19
+ - Produksi Tanaman Pangan Angka Ramalan II Tahun 2015
20
+ - Nilai Tukar Petani (NTP) Februari 2017 Sebesar 100,33 Atau Turun 0,58 Persen
21
+ - Buletin Statistik Perdagangan Luar Negeri Ekspor Menurut HS, Juni 2024
22
+ - source_sentence: analisis industri pariwisata indonesia tahun 2013
23
+ sentences:
24
+ - Ringkasan Neraca Arus Dana, Triwulan IV, 2012), (Miliar Rupiah)
25
+ - Pengeluaran Untuk Konsumsi Penduduk Indonesia September 2014
26
+ - Buletin Statistik Perdagangan Luar Negeri Ekspor Menurut Kelompok Komoditi dan
27
+ Negara, Desember 2020
28
+ - source_sentence: Sosial ekonomi Indonesia bulan November 2020
29
+ sentences:
30
+ - Pos Kesehatan Desa
31
+ - Jumlah Wisman Pada Januari 2011 Naik 11,14 Persen dan Penumpang Angkutan Udara
32
+ Domestik Pada Januari 2011 Turun 6,88 Persen
33
+ - Laporan Bulanan Data Sosial Ekonomi September 2017
34
+ - source_sentence: Tahun berapa Rupiah terdepresiasi 0,23 persen terhadap Dolar Amerika?
35
+ sentences:
36
+ - 'Nilai Impor Menurut Negara Asal Utama (Nilai CIF: juta US$), 2000-2023'
37
+ - Ringkasan Neraca Arus Dana Triwulan Pertama, 2002, (Miliar Rupiah)
38
+ - Depresiasi Rupiah terhadap Dolar Amerika pada tahun 2016 sebesar 0,5 persen.
39
+ datasets:
40
+ - yahyaabd/allstats-semantic-search-synthetic-dataset-v2
41
+ pipeline_tag: sentence-similarity
42
+ library_name: sentence-transformers
43
+ metrics:
44
+ - pearson_cosine
45
+ - spearman_cosine
46
+ model-index:
47
+ - name: SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
48
+ results:
49
+ - task:
50
+ type: semantic-similarity
51
+ name: Semantic Similarity
52
+ dataset:
53
+ name: allstats semantic search mini v2 eval
54
+ type: allstats-semantic-search-mini-v2-eval
55
+ metrics:
56
+ - type: pearson_cosine
57
+ value: 0.9838643974678674
58
+ name: Pearson Cosine
59
+ - type: spearman_cosine
60
+ value: 0.8951406685580494
61
+ name: Spearman Cosine
62
+ - task:
63
+ type: semantic-similarity
64
+ name: Semantic Similarity
65
+ dataset:
66
+ name: allstat semantic search mini v2 test
67
+ type: allstat-semantic-search-mini-v2-test
68
+ metrics:
69
+ - type: pearson_cosine
70
+ value: 0.98307083670705
71
+ name: Pearson Cosine
72
+ - type: spearman_cosine
73
+ value: 0.8922084062478435
74
+ name: Spearman Cosine
75
+ ---
76
+
77
+ # SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
78
+
79
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) on the [allstats-semantic-search-synthetic-dataset-v2](https://huggingface.co/datasets/yahyaabd/allstats-semantic-search-synthetic-dataset-v2) dataset. 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.
80
+
81
+ ## Model Details
82
+
83
+ ### Model Description
84
+ - **Model Type:** Sentence Transformer
85
+ - **Base model:** [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) <!-- at revision 8d6b950845285729817bf8e1af1861502c2fed0c -->
86
+ - **Maximum Sequence Length:** 128 tokens
87
+ - **Output Dimensionality:** 384 dimensions
88
+ - **Similarity Function:** Cosine Similarity
89
+ - **Training Dataset:**
90
+ - [allstats-semantic-search-synthetic-dataset-v2](https://huggingface.co/datasets/yahyaabd/allstats-semantic-search-synthetic-dataset-v2)
91
+ <!-- - **Language:** Unknown -->
92
+ <!-- - **License:** Unknown -->
93
+
94
+ ### Model Sources
95
+
96
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
97
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
98
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
99
+
100
+ ### Full Model Architecture
101
+
102
+ ```
103
+ SentenceTransformer(
104
+ (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel
105
+ (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})
106
+ )
107
+ ```
108
+
109
+ ## Usage
110
+
111
+ ### Direct Usage (Sentence Transformers)
112
+
113
+ First install the Sentence Transformers library:
114
+
115
+ ```bash
116
+ pip install -U sentence-transformers
117
+ ```
118
+
119
+ Then you can load this model and run inference.
120
+ ```python
121
+ from sentence_transformers import SentenceTransformer
122
+
123
+ # Download from the 🤗 Hub
124
+ model = SentenceTransformer("yahyaabd/allstats-semantic-search-mini-model-v2")
125
+ # Run inference
126
+ sentences = [
127
+ 'Tahun berapa Rupiah terdepresiasi 0,23 persen terhadap Dolar Amerika?',
128
+ 'Depresiasi Rupiah terhadap Dolar Amerika pada tahun 2016 sebesar 0,5 persen.',
129
+ 'Ringkasan Neraca Arus Dana Triwulan Pertama, 2002, (Miliar Rupiah)',
130
+ ]
131
+ embeddings = model.encode(sentences)
132
+ print(embeddings.shape)
133
+ # [3, 384]
134
+
135
+ # Get the similarity scores for the embeddings
136
+ similarities = model.similarity(embeddings, embeddings)
137
+ print(similarities.shape)
138
+ # [3, 3]
139
+ ```
140
+
141
+ <!--
142
+ ### Direct Usage (Transformers)
143
+
144
+ <details><summary>Click to see the direct usage in Transformers</summary>
145
+
146
+ </details>
147
+ -->
148
+
149
+ <!--
150
+ ### Downstream Usage (Sentence Transformers)
151
+
152
+ You can finetune this model on your own dataset.
153
+
154
+ <details><summary>Click to expand</summary>
155
+
156
+ </details>
157
+ -->
158
+
159
+ <!--
160
+ ### Out-of-Scope Use
161
+
162
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
163
+ -->
164
+
165
+ ## Evaluation
166
+
167
+ ### Metrics
168
+
169
+ #### Semantic Similarity
170
+
171
+ * Datasets: `allstats-semantic-search-mini-v2-eval` and `allstat-semantic-search-mini-v2-test`
172
+ * Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
173
+
174
+ | Metric | allstats-semantic-search-mini-v2-eval | allstat-semantic-search-mini-v2-test |
175
+ |:--------------------|:--------------------------------------|:-------------------------------------|
176
+ | pearson_cosine | 0.9839 | 0.9831 |
177
+ | **spearman_cosine** | **0.8951** | **0.8922** |
178
+
179
+ <!--
180
+ ## Bias, Risks and Limitations
181
+
182
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
183
+ -->
184
+
185
+ <!--
186
+ ### Recommendations
187
+
188
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
189
+ -->
190
+
191
+ ## Training Details
192
+
193
+ ### Training Dataset
194
+
195
+ #### allstats-semantic-search-synthetic-dataset-v2
196
+
197
+ * Dataset: [allstats-semantic-search-synthetic-dataset-v2](https://huggingface.co/datasets/yahyaabd/allstats-semantic-search-synthetic-dataset-v2) at [c76f31a](https://huggingface.co/datasets/yahyaabd/allstats-semantic-search-synthetic-dataset-v2/tree/c76f31abb3f2d3a2edd9895b9f5e896bf7c84f34)
198
+ * Size: 244,856 training samples
199
+ * Columns: <code>query</code>, <code>doc</code>, and <code>label</code>
200
+ * Approximate statistics based on the first 1000 samples:
201
+ | | query | doc | label |
202
+ |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
203
+ | type | string | string | float |
204
+ | details | <ul><li>min: 3 tokens</li><li>mean: 12.75 tokens</li><li>max: 45 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 14.81 tokens</li><li>max: 56 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.54</li><li>max: 1.0</li></ul> |
205
+ * Samples:
206
+ | query | doc | label |
207
+ |:------------------------------------------------------------------------|:--------------------------------------------------------------------------------|:------------------|
208
+ | <code>Dtaa harg konsymen edesaan (non-makann) 201</code> | <code>Statistik Harga Konsumen Perdesaan Kelompok Nonmakanan (Data 2013)</code> | <code>0.95</code> |
209
+ | <code>Bagaimna konidsi keuamgan rymah atngga Indonsia 2020-2022?</code> | <code>Statistik Perusahaan Perikanan 2007</code> | <code>0.1</code> |
210
+ | <code>Tingkat hunian kamar hotel tahun 2023</code> | <code>Tingkat Penghunian Kamar Hotel 2023</code> | <code>0.99</code> |
211
+ * Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
212
+ ```json
213
+ {
214
+ "loss_fct": "torch.nn.modules.loss.MSELoss"
215
+ }
216
+ ```
217
+
218
+ ### Evaluation Dataset
219
+
220
+ #### allstats-semantic-search-synthetic-dataset-v2
221
+
222
+ * Dataset: [allstats-semantic-search-synthetic-dataset-v2](https://huggingface.co/datasets/yahyaabd/allstats-semantic-search-synthetic-dataset-v2) at [c76f31a](https://huggingface.co/datasets/yahyaabd/allstats-semantic-search-synthetic-dataset-v2/tree/c76f31abb3f2d3a2edd9895b9f5e896bf7c84f34)
223
+ * Size: 52,469 evaluation samples
224
+ * Columns: <code>query</code>, <code>doc</code>, and <code>label</code>
225
+ * Approximate statistics based on the first 1000 samples:
226
+ | | query | doc | label |
227
+ |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
228
+ | type | string | string | float |
229
+ | details | <ul><li>min: 3 tokens</li><li>mean: 13.04 tokens</li><li>max: 43 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 15.01 tokens</li><li>max: 54 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.52</li><li>max: 1.0</li></ul> |
230
+ * Samples:
231
+ | query | doc | label |
232
+ |:---------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------|:------------------|
233
+ | <code>Bulan apa NTP mengalami kenaikan 0,25 persen?</code> | <code>Jumlah Wisatawan Mancanegara Bulan Agustus 2009 Turun 4,49 Persen Dibandingkan Bulan Sebelumnya.</code> | <code>0.0</code> |
234
+ | <code>Sebutksn keempa komositi tang disebutkn besert persentae mrajin persagangannya.</code> | <code>Marjin Perdagangan Minyak Goreng 3,86 Persen, Terigu 5,92 Persen, Garam 23,74 Persen, Dan Susu Bubuk 13,02 Persen</code> | <code>1.0</code> |
235
+ | <code>Data kemiskinan per kabupaten/kota tahun 2007</code> | <code>Data dan Informasi Kemiskinan 2007 Buku 2: Kabupaten/Kota</code> | <code>0.87</code> |
236
+ * Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
237
+ ```json
238
+ {
239
+ "loss_fct": "torch.nn.modules.loss.MSELoss"
240
+ }
241
+ ```
242
+
243
+ ### Training Hyperparameters
244
+ #### Non-Default Hyperparameters
245
+
246
+ - `eval_strategy`: steps
247
+ - `per_device_train_batch_size`: 64
248
+ - `per_device_eval_batch_size`: 64
249
+ - `num_train_epochs`: 8
250
+ - `warmup_ratio`: 0.1
251
+ - `fp16`: True
252
+
253
+ #### All Hyperparameters
254
+ <details><summary>Click to expand</summary>
255
+
256
+ - `overwrite_output_dir`: False
257
+ - `do_predict`: False
258
+ - `eval_strategy`: steps
259
+ - `prediction_loss_only`: True
260
+ - `per_device_train_batch_size`: 64
261
+ - `per_device_eval_batch_size`: 64
262
+ - `per_gpu_train_batch_size`: None
263
+ - `per_gpu_eval_batch_size`: None
264
+ - `gradient_accumulation_steps`: 1
265
+ - `eval_accumulation_steps`: None
266
+ - `torch_empty_cache_steps`: None
267
+ - `learning_rate`: 5e-05
268
+ - `weight_decay`: 0.0
269
+ - `adam_beta1`: 0.9
270
+ - `adam_beta2`: 0.999
271
+ - `adam_epsilon`: 1e-08
272
+ - `max_grad_norm`: 1.0
273
+ - `num_train_epochs`: 8
274
+ - `max_steps`: -1
275
+ - `lr_scheduler_type`: linear
276
+ - `lr_scheduler_kwargs`: {}
277
+ - `warmup_ratio`: 0.1
278
+ - `warmup_steps`: 0
279
+ - `log_level`: passive
280
+ - `log_level_replica`: warning
281
+ - `log_on_each_node`: True
282
+ - `logging_nan_inf_filter`: True
283
+ - `save_safetensors`: True
284
+ - `save_on_each_node`: False
285
+ - `save_only_model`: False
286
+ - `restore_callback_states_from_checkpoint`: False
287
+ - `no_cuda`: False
288
+ - `use_cpu`: False
289
+ - `use_mps_device`: False
290
+ - `seed`: 42
291
+ - `data_seed`: None
292
+ - `jit_mode_eval`: False
293
+ - `use_ipex`: False
294
+ - `bf16`: False
295
+ - `fp16`: True
296
+ - `fp16_opt_level`: O1
297
+ - `half_precision_backend`: auto
298
+ - `bf16_full_eval`: False
299
+ - `fp16_full_eval`: False
300
+ - `tf32`: None
301
+ - `local_rank`: 0
302
+ - `ddp_backend`: None
303
+ - `tpu_num_cores`: None
304
+ - `tpu_metrics_debug`: False
305
+ - `debug`: []
306
+ - `dataloader_drop_last`: False
307
+ - `dataloader_num_workers`: 0
308
+ - `dataloader_prefetch_factor`: None
309
+ - `past_index`: -1
310
+ - `disable_tqdm`: False
311
+ - `remove_unused_columns`: True
312
+ - `label_names`: None
313
+ - `load_best_model_at_end`: False
314
+ - `ignore_data_skip`: False
315
+ - `fsdp`: []
316
+ - `fsdp_min_num_params`: 0
317
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
318
+ - `fsdp_transformer_layer_cls_to_wrap`: None
319
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
320
+ - `deepspeed`: None
321
+ - `label_smoothing_factor`: 0.0
322
+ - `optim`: adamw_torch
323
+ - `optim_args`: None
324
+ - `adafactor`: False
325
+ - `group_by_length`: False
326
+ - `length_column_name`: length
327
+ - `ddp_find_unused_parameters`: None
328
+ - `ddp_bucket_cap_mb`: None
329
+ - `ddp_broadcast_buffers`: False
330
+ - `dataloader_pin_memory`: True
331
+ - `dataloader_persistent_workers`: False
332
+ - `skip_memory_metrics`: True
333
+ - `use_legacy_prediction_loop`: False
334
+ - `push_to_hub`: False
335
+ - `resume_from_checkpoint`: None
336
+ - `hub_model_id`: None
337
+ - `hub_strategy`: every_save
338
+ - `hub_private_repo`: None
339
+ - `hub_always_push`: False
340
+ - `gradient_checkpointing`: False
341
+ - `gradient_checkpointing_kwargs`: None
342
+ - `include_inputs_for_metrics`: False
343
+ - `include_for_metrics`: []
344
+ - `eval_do_concat_batches`: True
345
+ - `fp16_backend`: auto
346
+ - `push_to_hub_model_id`: None
347
+ - `push_to_hub_organization`: None
348
+ - `mp_parameters`:
349
+ - `auto_find_batch_size`: False
350
+ - `full_determinism`: False
351
+ - `torchdynamo`: None
352
+ - `ray_scope`: last
353
+ - `ddp_timeout`: 1800
354
+ - `torch_compile`: False
355
+ - `torch_compile_backend`: None
356
+ - `torch_compile_mode`: None
357
+ - `dispatch_batches`: None
358
+ - `split_batches`: None
359
+ - `include_tokens_per_second`: False
360
+ - `include_num_input_tokens_seen`: False
361
+ - `neftune_noise_alpha`: None
362
+ - `optim_target_modules`: None
363
+ - `batch_eval_metrics`: False
364
+ - `eval_on_start`: False
365
+ - `use_liger_kernel`: False
366
+ - `eval_use_gather_object`: False
367
+ - `average_tokens_across_devices`: False
368
+ - `prompts`: None
369
+ - `batch_sampler`: batch_sampler
370
+ - `multi_dataset_batch_sampler`: proportional
371
+
372
+ </details>
373
+
374
+ ### Training Logs
375
+ | Epoch | Step | Training Loss | Validation Loss | allstats-semantic-search-mini-v2-eval_spearman_cosine | allstat-semantic-search-mini-v2-test_spearman_cosine |
376
+ |:------:|:-----:|:-------------:|:---------------:|:-----------------------------------------------------:|:----------------------------------------------------:|
377
+ | 0.1307 | 500 | 0.0963 | 0.0657 | 0.6836 | - |
378
+ | 0.2614 | 1000 | 0.0558 | 0.0428 | 0.7480 | - |
379
+ | 0.3921 | 1500 | 0.0403 | 0.0335 | 0.7665 | - |
380
+ | 0.5227 | 2000 | 0.0324 | 0.0285 | 0.7744 | - |
381
+ | 0.6534 | 2500 | 0.0284 | 0.0255 | 0.7987 | - |
382
+ | 0.7841 | 3000 | 0.0246 | 0.0225 | 0.7883 | - |
383
+ | 0.9148 | 3500 | 0.0217 | 0.0217 | 0.7964 | - |
384
+ | 1.0455 | 4000 | 0.0193 | 0.0187 | 0.8111 | - |
385
+ | 1.1762 | 4500 | 0.017 | 0.0174 | 0.8086 | - |
386
+ | 1.3068 | 5000 | 0.0163 | 0.0170 | 0.8157 | - |
387
+ | 1.4375 | 5500 | 0.0157 | 0.0161 | 0.8000 | - |
388
+ | 1.5682 | 6000 | 0.015 | 0.0156 | 0.8133 | - |
389
+ | 1.6989 | 6500 | 0.0146 | 0.0146 | 0.8194 | - |
390
+ | 1.8296 | 7000 | 0.014 | 0.0140 | 0.8103 | - |
391
+ | 1.9603 | 7500 | 0.013 | 0.0132 | 0.8205 | - |
392
+ | 2.0910 | 8000 | 0.0111 | 0.0126 | 0.8353 | - |
393
+ | 2.2216 | 8500 | 0.0102 | 0.0123 | 0.8407 | - |
394
+ | 2.3523 | 9000 | 0.0101 | 0.0118 | 0.8389 | - |
395
+ | 2.4830 | 9500 | 0.01 | 0.0115 | 0.8444 | - |
396
+ | 2.6137 | 10000 | 0.0097 | 0.0111 | 0.8456 | - |
397
+ | 2.7444 | 10500 | 0.0097 | 0.0105 | 0.8524 | - |
398
+ | 2.8751 | 11000 | 0.0091 | 0.0102 | 0.8526 | - |
399
+ | 3.0058 | 11500 | 0.0088 | 0.0100 | 0.8561 | - |
400
+ | 3.1364 | 12000 | 0.0069 | 0.0095 | 0.8619 | - |
401
+ | 3.2671 | 12500 | 0.0071 | 0.0094 | 0.8534 | - |
402
+ | 3.3978 | 13000 | 0.0068 | 0.0092 | 0.8648 | - |
403
+ | 3.5285 | 13500 | 0.0069 | 0.0093 | 0.8638 | - |
404
+ | 3.6592 | 14000 | 0.0071 | 0.0091 | 0.8548 | - |
405
+ | 3.7899 | 14500 | 0.0065 | 0.0085 | 0.8711 | - |
406
+ | 3.9205 | 15000 | 0.0064 | 0.0084 | 0.8622 | - |
407
+ | 4.0512 | 15500 | 0.0061 | 0.0080 | 0.8675 | - |
408
+ | 4.1819 | 16000 | 0.0051 | 0.0082 | 0.8673 | - |
409
+ | 4.3126 | 16500 | 0.0052 | 0.0080 | 0.8659 | - |
410
+ | 4.4433 | 17000 | 0.0053 | 0.0078 | 0.8669 | - |
411
+ | 4.5740 | 17500 | 0.0053 | 0.0077 | 0.8690 | - |
412
+ | 4.7047 | 18000 | 0.005 | 0.0076 | 0.8758 | - |
413
+ | 4.8353 | 18500 | 0.0048 | 0.0074 | 0.8700 | - |
414
+ | 4.9660 | 19000 | 0.0049 | 0.0072 | 0.8785 | - |
415
+ | 5.0967 | 19500 | 0.0041 | 0.0070 | 0.8795 | - |
416
+ | 5.2274 | 20000 | 0.0039 | 0.0071 | 0.8803 | - |
417
+ | 5.3581 | 20500 | 0.0039 | 0.0071 | 0.8843 | - |
418
+ | 5.4888 | 21000 | 0.0041 | 0.0070 | 0.8818 | - |
419
+ | 5.6194 | 21500 | 0.0039 | 0.0069 | 0.8812 | - |
420
+ | 5.7501 | 22000 | 0.0038 | 0.0068 | 0.8868 | - |
421
+ | 5.8808 | 22500 | 0.0038 | 0.0067 | 0.8831 | - |
422
+ | 6.0115 | 23000 | 0.0037 | 0.0066 | 0.8869 | - |
423
+ | 6.1422 | 23500 | 0.003 | 0.0065 | 0.8888 | - |
424
+ | 6.2729 | 24000 | 0.0031 | 0.0064 | 0.8879 | - |
425
+ | 6.4036 | 24500 | 0.0032 | 0.0064 | 0.8881 | - |
426
+ | 6.5342 | 25000 | 0.003 | 0.0062 | 0.8919 | - |
427
+ | 6.6649 | 25500 | 0.0031 | 0.0062 | 0.8919 | - |
428
+ | 6.7956 | 26000 | 0.0031 | 0.0061 | 0.8910 | - |
429
+ | 6.9263 | 26500 | 0.003 | 0.0061 | 0.8911 | - |
430
+ | 7.0570 | 27000 | 0.0028 | 0.0061 | 0.8925 | - |
431
+ | 7.1877 | 27500 | 0.0025 | 0.0061 | 0.8922 | - |
432
+ | 7.3183 | 28000 | 0.0026 | 0.0060 | 0.8944 | - |
433
+ | 7.4490 | 28500 | 0.0026 | 0.0061 | 0.8953 | - |
434
+ | 7.5797 | 29000 | 0.0026 | 0.0060 | 0.8948 | - |
435
+ | 7.7104 | 29500 | 0.0025 | 0.0060 | 0.8941 | - |
436
+ | 7.8411 | 30000 | 0.0025 | 0.0059 | 0.8950 | - |
437
+ | 7.9718 | 30500 | 0.0025 | 0.0059 | 0.8951 | - |
438
+ | 8.0 | 30608 | - | - | - | 0.8922 |
439
+
440
+
441
+ ### Framework Versions
442
+ - Python: 3.10.12
443
+ - Sentence Transformers: 3.3.1
444
+ - Transformers: 4.47.1
445
+ - PyTorch: 2.5.1+cu124
446
+ - Accelerate: 1.2.1
447
+ - Datasets: 3.2.0
448
+ - Tokenizers: 0.21.0
449
+
450
+ ## Citation
451
+
452
+ ### BibTeX
453
+
454
+ #### Sentence Transformers
455
+ ```bibtex
456
+ @inproceedings{reimers-2019-sentence-bert,
457
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
458
+ author = "Reimers, Nils and Gurevych, Iryna",
459
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
460
+ month = "11",
461
+ year = "2019",
462
+ publisher = "Association for Computational Linguistics",
463
+ url = "https://arxiv.org/abs/1908.10084",
464
+ }
465
+ ```
466
+
467
+ <!--
468
+ ## Glossary
469
+
470
+ *Clearly define terms in order to be accessible across audiences.*
471
+ -->
472
+
473
+ <!--
474
+ ## Model Card Authors
475
+
476
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
477
+ -->
478
+
479
+ <!--
480
+ ## Model Card Contact
481
+
482
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
483
+ -->
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
3
+ "architectures": [
4
+ "BertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 384,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 1536,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.47.1",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 250037
26
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.3.1",
4
+ "transformers": "4.47.1",
5
+ "pytorch": "2.5.1+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:cc122a507a7a719a8698605f72c5c32d8607d137320d0bc20b5a725bcc243135
3
+ size 470637416
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": 128,
3
+ "do_lower_case": false
4
+ }
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 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
46
+ "cls_token": "<s>",
47
+ "do_lower_case": true,
48
+ "eos_token": "</s>",
49
+ "extra_special_tokens": {},
50
+ "mask_token": "<mask>",
51
+ "max_length": 128,
52
+ "model_max_length": 128,
53
+ "pad_to_multiple_of": null,
54
+ "pad_token": "<pad>",
55
+ "pad_token_type_id": 0,
56
+ "padding_side": "right",
57
+ "sep_token": "</s>",
58
+ "stride": 0,
59
+ "strip_accents": null,
60
+ "tokenize_chinese_chars": true,
61
+ "tokenizer_class": "BertTokenizer",
62
+ "truncation_side": "right",
63
+ "truncation_strategy": "longest_first",
64
+ "unk_token": "<unk>"
65
+ }
unigram.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da145b5e7700ae40f16691ec32a0b1fdc1ee3298db22a31ea55f57a966c4a65d
3
+ size 14763260