Hugging Face's logo

yahyaabd
/
allstats-semantic-search-model-v1

Sentence Similarity
sentence-transformers
Safetensors
xlm-roberta
feature-extraction
Generated from Trainer
dataset_size:212917
loss:CosineSimilarityLoss
Eval Results
text-embeddings-inference
Model card Files Community
yahyaabd commited on
Commit
47821f3
·
verified ·
1 Parent(s): ea74d94

Add new SentenceTransformer model

Browse files
Files changed (11) hide show
  1. .gitattributes +1 -0
  2. 1_Pooling/config.json +10 -0
  3. README.md +533 -0
  4. config.json +29 -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 +62 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ 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
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 +1,533 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - sentence-transformers
4
+ - sentence-similarity
5
+ - feature-extraction
6
+ - generated_from_trainer
7
+ - dataset_size:212917
8
+ - loss:CosineSimilarityLoss
9
+ base_model: sentence-transformers/paraphrase-multilingual-mpnet-base-v2
10
+ widget:
11
+ - source_sentence: statistik neraca arus dana indonesia
12
+ sentences:
13
+ - Statistik Kelapa Sawit Indonesia 2012
14
+ - Distribusi Perdagangan Komoditas Kedelai Indonesia 2023
15
+ - Data Runtun Statistik Konstruksi 1990-2010
16
+ - source_sentence: Seberapa besar kenaikan produksi IBS pada Triwulan IV Tahun 2013
17
+ dibandingkan Triwulan IV Tahun Sebelumnya?
18
+ sentences:
19
+ - Pertumbuhan PDB 2013 Mencapai 5,78 Persen
20
+ - Statistik Komuter Gerbangkertosusila Hasil Survei Komuter Gerbangkertosusila 2017
21
+ - Statistik Penduduk Lanjut Usia Provinsi Jawa Timur 2010-Hasil Sensus Penduduk
22
+ 2010
23
+ - source_sentence: 'Penduduk Papua: migrasi 2015'
24
+ sentences:
25
+ - Rata-rata Upah/Gaji Bersih sebulan Buruh/Karyawan Pegawai Menurut Pendidikan Tertinggi
26
+ dan jenis pekerjaan utama, 2019
27
+ - Statistik Pemotongan Ternak 2010 dan 2011
28
+ - Statistik Harga Produsen Pertanian Sub Sektor Tanaman Pangan, Hortikultura dan
29
+ Perkebunan Rakyat 2010
30
+ - source_sentence: statistik konstruksi 2022
31
+ sentences:
32
+ - Studi Modal Sosial 2006
33
+ - BRS upah buruh agustus 2018
34
+ - Statistik Perdagangan Luar Negeri Indonesia Ekspor 2006 vol 1
35
+ - source_sentence: Statistik ekspor Indonesia Maret 2202
36
+ sentences:
37
+ - Produk Domestik Bruto Indonesia Triwulanan 2006-2010
38
+ - Indeks Perilaku Anti Korupsi (IPAK) Indonesia 2023 sebesar 3,92, menurun dibandingkan
39
+ IPAK 2022
40
+ - Buletin Statistik Perdagangan Luar Negeri Ekspor Menurut HS, Januari 2023
41
+ datasets:
42
+ - yahyaabd/allstats-semantic-search-synthetic-dataset-v1
43
+ pipeline_tag: sentence-similarity
44
+ library_name: sentence-transformers
45
+ metrics:
46
+ - pearson_cosine
47
+ - spearman_cosine
48
+ model-index:
49
+ - name: SentenceTransformer based on sentence-transformers/paraphrase-multilingual-mpnet-base-v2
50
+ results:
51
+ - task:
52
+ type: semantic-similarity
53
+ name: Semantic Similarity
54
+ dataset:
55
+ name: allstats semantic search v1 dev
56
+ type: allstats-semantic-search-v1-dev
57
+ metrics:
58
+ - type: pearson_cosine
59
+ value: 0.9894566758405579
60
+ name: Pearson Cosine
61
+ - type: spearman_cosine
62
+ value: 0.9072484378842124
63
+ name: Spearman Cosine
64
+ - task:
65
+ type: semantic-similarity
66
+ name: Semantic Similarity
67
+ dataset:
68
+ name: allstat semantic search v1 test
69
+ type: allstat-semantic-search-v1-test
70
+ metrics:
71
+ - type: pearson_cosine
72
+ value: 0.9895284407960067
73
+ name: Pearson Cosine
74
+ - type: spearman_cosine
75
+ value: 0.9074137706349162
76
+ name: Spearman Cosine
77
+ ---
78
+
79
+ # SentenceTransformer based on sentence-transformers/paraphrase-multilingual-mpnet-base-v2
80
+
81
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/paraphrase-multilingual-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2) on the [allstats-semantic-search-synthetic-dataset-v1](https://huggingface.co/datasets/yahyaabd/allstats-semantic-search-synthetic-dataset-v1) dataset. 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.
82
+
83
+ ## Model Details
84
+
85
+ ### Model Description
86
+ - **Model Type:** Sentence Transformer
87
+ - **Base model:** [sentence-transformers/paraphrase-multilingual-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2) <!-- at revision 75c57757a97f90ad739aca51fa8bfea0e485a7f2 -->
88
+ - **Maximum Sequence Length:** 128 tokens
89
+ - **Output Dimensionality:** 768 dimensions
90
+ - **Similarity Function:** Cosine Similarity
91
+ - **Training Dataset:**
92
+ - [allstats-semantic-search-synthetic-dataset-v1](https://huggingface.co/datasets/yahyaabd/allstats-semantic-search-synthetic-dataset-v1)
93
+ <!-- - **Language:** Unknown -->
94
+ <!-- - **License:** Unknown -->
95
+
96
+ ### Model Sources
97
+
98
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
99
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
100
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
101
+
102
+ ### Full Model Architecture
103
+
104
+ ```
105
+ SentenceTransformer(
106
+ (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: XLMRobertaModel
107
+ (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})
108
+ )
109
+ ```
110
+
111
+ ## Usage
112
+
113
+ ### Direct Usage (Sentence Transformers)
114
+
115
+ First install the Sentence Transformers library:
116
+
117
+ ```bash
118
+ pip install -U sentence-transformers
119
+ ```
120
+
121
+ Then you can load this model and run inference.
122
+ ```python
123
+ from sentence_transformers import SentenceTransformer
124
+
125
+ # Download from the 🤗 Hub
126
+ model = SentenceTransformer("yahyaabd/allstats-semantic-search-model-v1")
127
+ # Run inference
128
+ sentences = [
129
+ 'Statistik ekspor Indonesia Maret 2202',
130
+ 'Produk Domestik Bruto Indonesia Triwulanan 2006-2010',
131
+ 'Buletin Statistik Perdagangan Luar Negeri Ekspor Menurut HS, Januari 2023',
132
+ ]
133
+ embeddings = model.encode(sentences)
134
+ print(embeddings.shape)
135
+ # [3, 768]
136
+
137
+ # Get the similarity scores for the embeddings
138
+ similarities = model.similarity(embeddings, embeddings)
139
+ print(similarities.shape)
140
+ # [3, 3]
141
+ ```
142
+
143
+ <!--
144
+ ### Direct Usage (Transformers)
145
+
146
+ <details><summary>Click to see the direct usage in Transformers</summary>
147
+
148
+ </details>
149
+ -->
150
+
151
+ <!--
152
+ ### Downstream Usage (Sentence Transformers)
153
+
154
+ You can finetune this model on your own dataset.
155
+
156
+ <details><summary>Click to expand</summary>
157
+
158
+ </details>
159
+ -->
160
+
161
+ <!--
162
+ ### Out-of-Scope Use
163
+
164
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
165
+ -->
166
+
167
+ ## Evaluation
168
+
169
+ ### Metrics
170
+
171
+ #### Semantic Similarity
172
+
173
+ * Datasets: `allstats-semantic-search-v1-dev` and `allstat-semantic-search-v1-test`
174
+ * Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
175
+
176
+ | Metric | allstats-semantic-search-v1-dev | allstat-semantic-search-v1-test |
177
+ |:--------------------|:--------------------------------|:--------------------------------|
178
+ | pearson_cosine | 0.9895 | 0.9895 |
179
+ | **spearman_cosine** | **0.9072** | **0.9074** |
180
+
181
+ <!--
182
+ ## Bias, Risks and Limitations
183
+
184
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
185
+ -->
186
+
187
+ <!--
188
+ ### Recommendations
189
+
190
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
191
+ -->
192
+
193
+ ## Training Details
194
+
195
+ ### Training Dataset
196
+
197
+ #### allstats-semantic-search-synthetic-dataset-v1
198
+
199
+ * Dataset: [allstats-semantic-search-synthetic-dataset-v1](https://huggingface.co/datasets/yahyaabd/allstats-semantic-search-synthetic-dataset-v1) at [06f849a](https://huggingface.co/datasets/yahyaabd/allstats-semantic-search-synthetic-dataset-v1/tree/06f849af5602fea6ce00e5ecdd9a99cd0cafc2de)
200
+ * Size: 212,917 training samples
201
+ * Columns: <code>query</code>, <code>doc</code>, and <code>label</code>
202
+ * Approximate statistics based on the first 1000 samples:
203
+ | | query | doc | label |
204
+ |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
205
+ | type | string | string | float |
206
+ | details | <ul><li>min: 5 tokens</li><li>mean: 11.48 tokens</li><li>max: 29 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 14.89 tokens</li><li>max: 53 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.52</li><li>max: 1.0</li></ul> |
207
+ * Samples:
208
+ | query | doc | label |
209
+ |:-------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------|:------------------|
210
+ | <code>ringkasan aktivitas badan pusat statistik tahun 2018</code> | <code>Statistik Harga Produsen sektor pertanian di indonesia 2008</code> | <code>0.1</code> |
211
+ | <code>indikator kesejahteraan petani rejang lebong 2015</code> | <code>Diagram Timbang Nilai Tukar Petani Kabupaten Rejang Lebong 2015</code> | <code>0.82</code> |
212
+ | <code>Berapa persen kenaikan kunjungan wisatawan mancanegara pada April 2024?</code> | <code>Indeks Perilaku Anti Korupsi (IPAK) Indonesia 2023 sebesar 3,92, menurun dibandingkan IPAK 2022</code> | <code>0.0</code> |
213
+ * Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
214
+ ```json
215
+ {
216
+ "loss_fct": "torch.nn.modules.loss.MSELoss"
217
+ }
218
+ ```
219
+
220
+ ### Evaluation Dataset
221
+
222
+ #### allstats-semantic-search-synthetic-dataset-v1
223
+
224
+ * Dataset: [allstats-semantic-search-synthetic-dataset-v1](https://huggingface.co/datasets/yahyaabd/allstats-semantic-search-synthetic-dataset-v1) at [06f849a](https://huggingface.co/datasets/yahyaabd/allstats-semantic-search-synthetic-dataset-v1/tree/06f849af5602fea6ce00e5ecdd9a99cd0cafc2de)
225
+ * Size: 26,614 evaluation samples
226
+ * Columns: <code>query</code>, <code>doc</code>, and <code>label</code>
227
+ * Approximate statistics based on the first 1000 samples:
228
+ | | query | doc | label |
229
+ |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:--------------------------------------------------------------|
230
+ | type | string | string | float |
231
+ | details | <ul><li>min: 5 tokens</li><li>mean: 11.21 tokens</li><li>max: 32 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 14.41 tokens</li><li>max: 54 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.5</li><li>max: 1.0</li></ul> |
232
+ * Samples:
233
+ | query | doc | label |
234
+ |:-----------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------|:------------------|
235
+ | <code>Laporan bulanan ekonomi Indonesia bulan November 201</code> | <code>Laporan Bulanan Data Sosial Ekonomi November 2021</code> | <code>0.92</code> |
236
+ | <code>pekerjaan layak di indonesia tahun 2022: data dan analisis</code> | <code>Statistik Penduduk Lanjut Usia Provinsi Papua Barat 2010-Hasil Sensus Penduduk 2010</code> | <code>0.09</code> |
237
+ | <code>Tabel pendapatan rata-rata pekerja lepas berdasarkan provinsi dan pendidikan tahun 2021</code> | <code>Nilai Impor Kendaraan Bermotor Menurut Negara Asal Utama (Nilai CIF:juta US$), 2018-2023</code> | <code>0.1</code> |
238
+ * Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
239
+ ```json
240
+ {
241
+ "loss_fct": "torch.nn.modules.loss.MSELoss"
242
+ }
243
+ ```
244
+
245
+ ### Training Hyperparameters
246
+ #### Non-Default Hyperparameters
247
+
248
+ - `eval_strategy`: steps
249
+ - `per_device_train_batch_size`: 32
250
+ - `per_device_eval_batch_size`: 32
251
+ - `num_train_epochs`: 4
252
+ - `warmup_ratio`: 0.1
253
+ - `fp16`: True
254
+
255
+ #### All Hyperparameters
256
+ <details><summary>Click to expand</summary>
257
+
258
+ - `overwrite_output_dir`: False
259
+ - `do_predict`: False
260
+ - `eval_strategy`: steps
261
+ - `prediction_loss_only`: True
262
+ - `per_device_train_batch_size`: 32
263
+ - `per_device_eval_batch_size`: 32
264
+ - `per_gpu_train_batch_size`: None
265
+ - `per_gpu_eval_batch_size`: None
266
+ - `gradient_accumulation_steps`: 1
267
+ - `eval_accumulation_steps`: None
268
+ - `torch_empty_cache_steps`: None
269
+ - `learning_rate`: 5e-05
270
+ - `weight_decay`: 0.0
271
+ - `adam_beta1`: 0.9
272
+ - `adam_beta2`: 0.999
273
+ - `adam_epsilon`: 1e-08
274
+ - `max_grad_norm`: 1.0
275
+ - `num_train_epochs`: 4
276
+ - `max_steps`: -1
277
+ - `lr_scheduler_type`: linear
278
+ - `lr_scheduler_kwargs`: {}
279
+ - `warmup_ratio`: 0.1
280
+ - `warmup_steps`: 0
281
+ - `log_level`: passive
282
+ - `log_level_replica`: warning
283
+ - `log_on_each_node`: True
284
+ - `logging_nan_inf_filter`: True
285
+ - `save_safetensors`: True
286
+ - `save_on_each_node`: False
287
+ - `save_only_model`: False
288
+ - `restore_callback_states_from_checkpoint`: False
289
+ - `no_cuda`: False
290
+ - `use_cpu`: False
291
+ - `use_mps_device`: False
292
+ - `seed`: 42
293
+ - `data_seed`: None
294
+ - `jit_mode_eval`: False
295
+ - `use_ipex`: False
296
+ - `bf16`: False
297
+ - `fp16`: True
298
+ - `fp16_opt_level`: O1
299
+ - `half_precision_backend`: auto
300
+ - `bf16_full_eval`: False
301
+ - `fp16_full_eval`: False
302
+ - `tf32`: None
303
+ - `local_rank`: 0
304
+ - `ddp_backend`: None
305
+ - `tpu_num_cores`: None
306
+ - `tpu_metrics_debug`: False
307
+ - `debug`: []
308
+ - `dataloader_drop_last`: False
309
+ - `dataloader_num_workers`: 0
310
+ - `dataloader_prefetch_factor`: None
311
+ - `past_index`: -1
312
+ - `disable_tqdm`: False
313
+ - `remove_unused_columns`: True
314
+ - `label_names`: None
315
+ - `load_best_model_at_end`: False
316
+ - `ignore_data_skip`: False
317
+ - `fsdp`: []
318
+ - `fsdp_min_num_params`: 0
319
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
320
+ - `fsdp_transformer_layer_cls_to_wrap`: None
321
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
322
+ - `deepspeed`: None
323
+ - `label_smoothing_factor`: 0.0
324
+ - `optim`: adamw_torch
325
+ - `optim_args`: None
326
+ - `adafactor`: False
327
+ - `group_by_length`: False
328
+ - `length_column_name`: length
329
+ - `ddp_find_unused_parameters`: None
330
+ - `ddp_bucket_cap_mb`: None
331
+ - `ddp_broadcast_buffers`: False
332
+ - `dataloader_pin_memory`: True
333
+ - `dataloader_persistent_workers`: False
334
+ - `skip_memory_metrics`: True
335
+ - `use_legacy_prediction_loop`: False
336
+ - `push_to_hub`: False
337
+ - `resume_from_checkpoint`: None
338
+ - `hub_model_id`: None
339
+ - `hub_strategy`: every_save
340
+ - `hub_private_repo`: None
341
+ - `hub_always_push`: False
342
+ - `gradient_checkpointing`: False
343
+ - `gradient_checkpointing_kwargs`: None
344
+ - `include_inputs_for_metrics`: False
345
+ - `include_for_metrics`: []
346
+ - `eval_do_concat_batches`: True
347
+ - `fp16_backend`: auto
348
+ - `push_to_hub_model_id`: None
349
+ - `push_to_hub_organization`: None
350
+ - `mp_parameters`:
351
+ - `auto_find_batch_size`: False
352
+ - `full_determinism`: False
353
+ - `torchdynamo`: None
354
+ - `ray_scope`: last
355
+ - `ddp_timeout`: 1800
356
+ - `torch_compile`: False
357
+ - `torch_compile_backend`: None
358
+ - `torch_compile_mode`: None
359
+ - `dispatch_batches`: None
360
+ - `split_batches`: None
361
+ - `include_tokens_per_second`: False
362
+ - `include_num_input_tokens_seen`: False
363
+ - `neftune_noise_alpha`: None
364
+ - `optim_target_modules`: None
365
+ - `batch_eval_metrics`: False
366
+ - `eval_on_start`: False
367
+ - `use_liger_kernel`: False
368
+ - `eval_use_gather_object`: False
369
+ - `average_tokens_across_devices`: False
370
+ - `prompts`: None
371
+ - `batch_sampler`: batch_sampler
372
+ - `multi_dataset_batch_sampler`: proportional
373
+
374
+ </details>
375
+
376
+ ### Training Logs
377
+ <details><summary>Click to expand</summary>
378
+
379
+ | Epoch | Step | Training Loss | Validation Loss | allstats-semantic-search-v1-dev_spearman_cosine | allstat-semantic-search-v1-test_spearman_cosine |
380
+ |:------:|:-----:|:-------------:|:---------------:|:-----------------------------------------------:|:-----------------------------------------------:|
381
+ | 0.0376 | 250 | 0.0683 | 0.0432 | 0.6955 | - |
382
+ | 0.0751 | 500 | 0.0393 | 0.0322 | 0.7230 | - |
383
+ | 0.1127 | 750 | 0.0321 | 0.0270 | 0.7476 | - |
384
+ | 0.1503 | 1000 | 0.0255 | 0.0226 | 0.7789 | - |
385
+ | 0.1879 | 1250 | 0.024 | 0.0213 | 0.7683 | - |
386
+ | 0.2254 | 1500 | 0.022 | 0.0199 | 0.7727 | - |
387
+ | 0.2630 | 1750 | 0.0219 | 0.0195 | 0.7853 | - |
388
+ | 0.3006 | 2000 | 0.0202 | 0.0188 | 0.7795 | - |
389
+ | 0.3381 | 2250 | 0.0191 | 0.0187 | 0.7943 | - |
390
+ | 0.3757 | 2500 | 0.0198 | 0.0178 | 0.7842 | - |
391
+ | 0.4133 | 2750 | 0.0179 | 0.0184 | 0.7974 | - |
392
+ | 0.4509 | 3000 | 0.0179 | 0.0194 | 0.7810 | - |
393
+ | 0.4884 | 3250 | 0.0182 | 0.0168 | 0.8080 | - |
394
+ | 0.5260 | 3500 | 0.0174 | 0.0164 | 0.8131 | - |
395
+ | 0.5636 | 3750 | 0.0174 | 0.0154 | 0.8113 | - |
396
+ | 0.6011 | 4000 | 0.0169 | 0.0157 | 0.7981 | - |
397
+ | 0.6387 | 4250 | 0.0152 | 0.0146 | 0.8099 | - |
398
+ | 0.6763 | 4500 | 0.0148 | 0.0147 | 0.8091 | - |
399
+ | 0.7139 | 4750 | 0.0145 | 0.0145 | 0.8178 | - |
400
+ | 0.7514 | 5000 | 0.014 | 0.0139 | 0.8184 | - |
401
+ | 0.7890 | 5250 | 0.0145 | 0.0130 | 0.8166 | - |
402
+ | 0.8266 | 5500 | 0.0134 | 0.0129 | 0.8306 | - |
403
+ | 0.8641 | 5750 | 0.013 | 0.0122 | 0.8251 | - |
404
+ | 0.9017 | 6000 | 0.0136 | 0.0130 | 0.8265 | - |
405
+ | 0.9393 | 6250 | 0.0123 | 0.0126 | 0.8224 | - |
406
+ | 0.9769 | 6500 | 0.0113 | 0.0120 | 0.8305 | - |
407
+ | 1.0144 | 6750 | 0.0129 | 0.0117 | 0.8204 | - |
408
+ | 1.0520 | 7000 | 0.0106 | 0.0116 | 0.8284 | - |
409
+ | 1.0896 | 7250 | 0.01 | 0.0116 | 0.8303 | - |
410
+ | 1.1271 | 7500 | 0.0096 | 0.0110 | 0.8303 | - |
411
+ | 1.1647 | 7750 | 0.01 | 0.0113 | 0.8305 | - |
412
+ | 1.2023 | 8000 | 0.0116 | 0.0108 | 0.8300 | - |
413
+ | 1.2399 | 8250 | 0.0095 | 0.0104 | 0.8432 | - |
414
+ | 1.2774 | 8500 | 0.009 | 0.0104 | 0.8370 | - |
415
+ | 1.3150 | 8750 | 0.0101 | 0.0102 | 0.8434 | - |
416
+ | 1.3526 | 9000 | 0.01 | 0.0097 | 0.8450 | - |
417
+ | 1.3901 | 9250 | 0.0097 | 0.0103 | 0.8286 | - |
418
+ | 1.4277 | 9500 | 0.0092 | 0.0096 | 0.8393 | - |
419
+ | 1.4653 | 9750 | 0.0093 | 0.0089 | 0.8480 | - |
420
+ | 1.5029 | 10000 | 0.0088 | 0.0090 | 0.8439 | - |
421
+ | 1.5404 | 10250 | 0.0087 | 0.0089 | 0.8569 | - |
422
+ | 1.5780 | 10500 | 0.0082 | 0.0088 | 0.8488 | - |
423
+ | 1.6156 | 10750 | 0.009 | 0.0089 | 0.8493 | - |
424
+ | 1.6531 | 11000 | 0.0086 | 0.0086 | 0.8499 | - |
425
+ | 1.6907 | 11250 | 0.0076 | 0.0083 | 0.8600 | - |
426
+ | 1.7283 | 11500 | 0.0076 | 0.0081 | 0.8621 | - |
427
+ | 1.7659 | 11750 | 0.0079 | 0.0081 | 0.8611 | - |
428
+ | 1.8034 | 12000 | 0.0082 | 0.0085 | 0.8540 | - |
429
+ | 1.8410 | 12250 | 0.0074 | 0.0081 | 0.8620 | - |
430
+ | 1.8786 | 12500 | 0.007 | 0.0080 | 0.8639 | - |
431
+ | 1.9161 | 12750 | 0.0071 | 0.0083 | 0.8450 | - |
432
+ | 1.9537 | 13000 | 0.007 | 0.0076 | 0.8585 | - |
433
+ | 1.9913 | 13250 | 0.0072 | 0.0074 | 0.8640 | - |
434
+ | 2.0289 | 13500 | 0.0055 | 0.0069 | 0.8699 | - |
435
+ | 2.0664 | 13750 | 0.0056 | 0.0068 | 0.8673 | - |
436
+ | 2.1040 | 14000 | 0.0052 | 0.0066 | 0.8723 | - |
437
+ | 2.1416 | 14250 | 0.0059 | 0.0069 | 0.8644 | - |
438
+ | 2.1791 | 14500 | 0.0055 | 0.0068 | 0.8670 | - |
439
+ | 2.2167 | 14750 | 0.005 | 0.0065 | 0.8723 | - |
440
+ | 2.2543 | 15000 | 0.0053 | 0.0066 | 0.8766 | - |
441
+ | 2.2919 | 15250 | 0.0057 | 0.0065 | 0.8782 | - |
442
+ | 2.3294 | 15500 | 0.0053 | 0.0064 | 0.8749 | - |
443
+ | 2.3670 | 15750 | 0.0056 | 0.0070 | 0.8708 | - |
444
+ | 2.4046 | 16000 | 0.0058 | 0.0065 | 0.8731 | - |
445
+ | 2.4421 | 16250 | 0.0047 | 0.0064 | 0.8793 | - |
446
+ | 2.4797 | 16500 | 0.0049 | 0.0063 | 0.8801 | - |
447
+ | 2.5173 | 16750 | 0.0051 | 0.0063 | 0.8782 | - |
448
+ | 2.5549 | 17000 | 0.0053 | 0.0060 | 0.8799 | - |
449
+ | 2.5924 | 17250 | 0.0051 | 0.0059 | 0.8825 | - |
450
+ | 2.6300 | 17500 | 0.0048 | 0.0060 | 0.8761 | - |
451
+ | 2.6676 | 17750 | 0.0055 | 0.0055 | 0.8773 | - |
452
+ | 2.7051 | 18000 | 0.0045 | 0.0053 | 0.8833 | - |
453
+ | 2.7427 | 18250 | 0.0041 | 0.0053 | 0.8868 | - |
454
+ | 2.7803 | 18500 | 0.0051 | 0.0054 | 0.8811 | - |
455
+ | 2.8179 | 18750 | 0.004 | 0.0052 | 0.8881 | - |
456
+ | 2.8554 | 19000 | 0.0043 | 0.0053 | 0.8764 | - |
457
+ | 2.8930 | 19250 | 0.0047 | 0.0051 | 0.8874 | - |
458
+ | 2.9306 | 19500 | 0.0038 | 0.0051 | 0.8922 | - |
459
+ | 2.9681 | 19750 | 0.0047 | 0.0050 | 0.8821 | - |
460
+ | 3.0057 | 20000 | 0.0037 | 0.0048 | 0.8911 | - |
461
+ | 3.0433 | 20250 | 0.0031 | 0.0048 | 0.8911 | - |
462
+ | 3.0809 | 20500 | 0.0032 | 0.0046 | 0.8934 | - |
463
+ | 3.1184 | 20750 | 0.0034 | 0.0046 | 0.8942 | - |
464
+ | 3.1560 | 21000 | 0.0028 | 0.0045 | 0.8976 | - |
465
+ | 3.1936 | 21250 | 0.0034 | 0.0045 | 0.8932 | - |
466
+ | 3.2311 | 21500 | 0.003 | 0.0044 | 0.8959 | - |
467
+ | 3.2687 | 21750 | 0.0033 | 0.0044 | 0.8961 | - |
468
+ | 3.3063 | 22000 | 0.0029 | 0.0043 | 0.8995 | - |
469
+ | 3.3439 | 22250 | 0.0029 | 0.0044 | 0.8978 | - |
470
+ | 3.3814 | 22500 | 0.0027 | 0.0043 | 0.8998 | - |
471
+ | 3.4190 | 22750 | 0.003 | 0.0043 | 0.9019 | - |
472
+ | 3.4566 | 23000 | 0.0027 | 0.0042 | 0.8982 | - |
473
+ | 3.4941 | 23250 | 0.0027 | 0.0042 | 0.9014 | - |
474
+ | 3.5317 | 23500 | 0.0034 | 0.0042 | 0.9025 | - |
475
+ | 3.5693 | 23750 | 0.003 | 0.0041 | 0.9027 | - |
476
+ | 3.6069 | 24000 | 0.0029 | 0.0041 | 0.9003 | - |
477
+ | 3.6444 | 24250 | 0.0027 | 0.0040 | 0.9023 | - |
478
+ | 3.6820 | 24500 | 0.0027 | 0.0040 | 0.9035 | - |
479
+ | 3.7196 | 24750 | 0.0033 | 0.0040 | 0.9042 | - |
480
+ | 3.7571 | 25000 | 0.0028 | 0.0039 | 0.9053 | - |
481
+ | 3.7947 | 25250 | 0.0027 | 0.0039 | 0.9049 | - |
482
+ | 3.8323 | 25500 | 0.0033 | 0.0039 | 0.9057 | - |
483
+ | 3.8699 | 25750 | 0.0025 | 0.0039 | 0.9075 | - |
484
+ | 3.9074 | 26000 | 0.003 | 0.0039 | 0.9068 | - |
485
+ | 3.9450 | 26250 | 0.0026 | 0.0039 | 0.9073 | - |
486
+ | 3.9826 | 26500 | 0.0023 | 0.0038 | 0.9072 | - |
487
+ | 4.0 | 26616 | - | - | - | 0.9074 |
488
+
489
+ </details>
490
+
491
+ ### Framework Versions
492
+ - Python: 3.10.12
493
+ - Sentence Transformers: 3.3.1
494
+ - Transformers: 4.47.1
495
+ - PyTorch: 2.2.2+cu121
496
+ - Accelerate: 1.2.1
497
+ - Datasets: 3.2.0
498
+ - Tokenizers: 0.21.0
499
+
500
+ ## Citation
501
+
502
+ ### BibTeX
503
+
504
+ #### Sentence Transformers
505
+ ```bibtex
506
+ @inproceedings{reimers-2019-sentence-bert,
507
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
508
+ author = "Reimers, Nils and Gurevych, Iryna",
509
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
510
+ month = "11",
511
+ year = "2019",
512
+ publisher = "Association for Computational Linguistics",
513
+ url = "https://arxiv.org/abs/1908.10084",
514
+ }
515
+ ```
516
+
517
+ <!--
518
+ ## Glossary
519
+
520
+ *Clearly define terms in order to be accessible across audiences.*
521
+ -->
522
+
523
+ <!--
524
+ ## Model Card Authors
525
+
526
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
527
+ -->
528
+
529
+ <!--
530
+ ## Model Card Contact
531
+
532
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
533
+ -->
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sentence-transformers/paraphrase-multilingual-mpnet-base-v2",
3
+ "architectures": [
4
+ "XLMRobertaModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 514,
18
+ "model_type": "xlm-roberta",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
+ "output_past": true,
22
+ "pad_token_id": 1,
23
+ "position_embedding_type": "absolute",
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.47.1",
26
+ "type_vocab_size": 1,
27
+ "use_cache": true,
28
+ "vocab_size": 250002
29
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.3.1",
4
+ "transformers": "4.47.1",
5
+ "pytorch": "2.2.2+cu121"
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 sha256:33d1ebf6638ce90842d5477df62360cf5ea1d3feda70786e492a40281512166c
3
+ size 1112197096
modules.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ }
14
+ ]
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 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "eos_token": "</s>",
48
+ "extra_special_tokens": {},
49
+ "mask_token": "<mask>",
50
+ "max_length": 128,
51
+ "model_max_length": 128,
52
+ "pad_to_multiple_of": null,
53
+ "pad_token": "<pad>",
54
+ "pad_token_type_id": 0,
55
+ "padding_side": "right",
56
+ "sep_token": "</s>",
57
+ "stride": 0,
58
+ "tokenizer_class": "XLMRobertaTokenizer",
59
+ "truncation_side": "right",
60
+ "truncation_strategy": "longest_first",
61
+ "unk_token": "<unk>"
62
+ }