Hugging Face's logo

yyzheng00
/
snomed_triplet_1M

Sentence Similarity
sentence-transformers
Safetensors
bert
feature-extraction
Generated from Trainer
dataset_size:1000000
loss:TripletLoss
Eval Results
text-embeddings-inference
Model card Files Community
yyzheng00 commited on
Commit
5cd7b03
·
verified ·
1 Parent(s): b2ba45a

Add new SentenceTransformer model

Browse files
Files changed (11) hide show
  1. 1_Pooling/config.json +10 -0
  2. README.md +815 -0
  3. config.json +26 -0
  4. config_sentence_transformers.json +10 -0
  5. model.safetensors +3 -0
  6. modules.json +20 -0
  7. sentence_bert_config.json +4 -0
  8. special_tokens_map.json +37 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +65 -0
  11. vocab.txt +0 -0
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 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 +1,815 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - sentence-transformers
4
+ - sentence-similarity
5
+ - feature-extraction
6
+ - generated_from_trainer
7
+ - dataset_size:1000000
8
+ - loss:TripletLoss
9
+ base_model: sentence-transformers/all-MiniLM-L6-v2
10
+ widget:
11
+ - source_sentence: '|Evaluation procedure (procedure)| : { |Method (attribute)| =
12
+ |Evaluation - action (qualifier value)|, |Has specimen (attribute)| = |Urine specimen
13
+ (specimen)| }'
14
+ sentences:
15
+ - Evaluation of urine specimen (procedure)
16
+ - Tacrolimus-containing product in oral dose form (medicinal product form)
17
+ - '|Measurement of substance in specimen (procedure)| + |Organic acids measurement
18
+ (procedure)| : { |Method (attribute)| = |Measurement - action (qualifier value)|,
19
+ |Component (attribute)| = |Organic acid (substance)|, |Has specimen (attribute)|
20
+ = |Fluid specimen (specimen)| }'
21
+ - source_sentence: Allergy to meclozine (finding)
22
+ sentences:
23
+ - Meclizine allergy (finding)
24
+ - Allergy to quinidine (finding)
25
+ - Disorder of ovary (disorder)
26
+ - source_sentence: '|Specimen observable (observable entity)|'
27
+ sentences:
28
+ - Carbamide peroxide (product)
29
+ - Neoplasm of uncertain behavior of dome of urinary bladder (disorder)
30
+ - Microscopic specimen observable (observable entity)
31
+ - source_sentence: '|Dilation of esophagus (procedure)| : { |Method (attribute)| =
32
+ |Dilation - action (qualifier value)|, |Procedure site - Direct (attribute)| =
33
+ |Esophageal structure (body structure)|, |Direct morphology (attribute)| = |Stricture
34
+ (morphologic abnormality)| }'
35
+ sentences:
36
+ - Fissure for ligamentum teres of liver (body structure)
37
+ - Dilatation of esophageal stricture (procedure)
38
+ - Dilation and insertion of tube into esophagus (procedure)
39
+ - source_sentence: '|Estradiol and/or estradiol derivative (substance)| + |Steroid
40
+ hormone (substance)| + |Substance with estrogen receptor agonist mechanism of
41
+ action (substance)| : |Has disposition (attribute)| = |Estrogen receptor agonist
42
+ (disposition)|, '
43
+ sentences:
44
+ - Oral form dioctahedral smectite (medicinal product form)
45
+ - 17-Beta oestradiol (substance)
46
+ - Rupture of Descemet's membrane of right eye (disorder)
47
+ pipeline_tag: sentence-similarity
48
+ library_name: sentence-transformers
49
+ metrics:
50
+ - cosine_accuracy
51
+ model-index:
52
+ - name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
53
+ results:
54
+ - task:
55
+ type: triplet
56
+ name: Triplet
57
+ dataset:
58
+ name: snomed triplet 1M 3 4 3 dev
59
+ type: snomed_triplet_1M_3_4_3-dev
60
+ metrics:
61
+ - type: cosine_accuracy
62
+ value: 0.979325
63
+ name: Cosine Accuracy
64
+ - type: cosine_accuracy
65
+ value: 0.9780125
66
+ name: Cosine Accuracy
67
+ ---
68
+
69
+ # SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
70
+
71
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) on the parquet 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.
72
+
73
+ ## Model Details
74
+
75
+ ### Model Description
76
+ - **Model Type:** Sentence Transformer
77
+ - **Base model:** [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) <!-- at revision c9745ed1d9f207416be6d2e6f8de32d1f16199bf -->
78
+ - **Maximum Sequence Length:** 256 tokens
79
+ - **Output Dimensionality:** 384 dimensions
80
+ - **Similarity Function:** Cosine Similarity
81
+ - **Training Dataset:**
82
+ - parquet
83
+ <!-- - **Language:** Unknown -->
84
+ <!-- - **License:** Unknown -->
85
+
86
+ ### Model Sources
87
+
88
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
89
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
90
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
91
+
92
+ ### Full Model Architecture
93
+
94
+ ```
95
+ SentenceTransformer(
96
+ (0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: BertModel
97
+ (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})
98
+ (2): Normalize()
99
+ )
100
+ ```
101
+
102
+ ## Usage
103
+
104
+ ### Direct Usage (Sentence Transformers)
105
+
106
+ First install the Sentence Transformers library:
107
+
108
+ ```bash
109
+ pip install -U sentence-transformers
110
+ ```
111
+
112
+ Then you can load this model and run inference.
113
+ ```python
114
+ from sentence_transformers import SentenceTransformer
115
+
116
+ # Download from the 🤗 Hub
117
+ model = SentenceTransformer("yyzheng00/snomed_triplet_1M")
118
+ # Run inference
119
+ sentences = [
120
+ '|Estradiol and/or estradiol derivative (substance)| + |Steroid hormone (substance)| + |Substance with estrogen receptor agonist mechanism of action (substance)| : |Has disposition (attribute)| = |Estrogen receptor agonist (disposition)|, ',
121
+ '17-Beta oestradiol (substance)',
122
+ "Rupture of Descemet's membrane of right eye (disorder)",
123
+ ]
124
+ embeddings = model.encode(sentences)
125
+ print(embeddings.shape)
126
+ # [3, 384]
127
+
128
+ # Get the similarity scores for the embeddings
129
+ similarities = model.similarity(embeddings, embeddings)
130
+ print(similarities.shape)
131
+ # [3, 3]
132
+ ```
133
+
134
+ <!--
135
+ ### Direct Usage (Transformers)
136
+
137
+ <details><summary>Click to see the direct usage in Transformers</summary>
138
+
139
+ </details>
140
+ -->
141
+
142
+ <!--
143
+ ### Downstream Usage (Sentence Transformers)
144
+
145
+ You can finetune this model on your own dataset.
146
+
147
+ <details><summary>Click to expand</summary>
148
+
149
+ </details>
150
+ -->
151
+
152
+ <!--
153
+ ### Out-of-Scope Use
154
+
155
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
156
+ -->
157
+
158
+ ## Evaluation
159
+
160
+ ### Metrics
161
+
162
+ #### Triplet
163
+
164
+ * Dataset: `snomed_triplet_1M_3_4_3-dev`
165
+ * Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
166
+
167
+ | Metric | Value |
168
+ |:--------------------|:-----------|
169
+ | **cosine_accuracy** | **0.9793** |
170
+
171
+ #### Triplet
172
+
173
+ * Dataset: `snomed_triplet_1M_3_4_3-dev`
174
+ * Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
175
+
176
+ | Metric | Value |
177
+ |:--------------------|:----------|
178
+ | **cosine_accuracy** | **0.978** |
179
+
180
+ <!--
181
+ ## Bias, Risks and Limitations
182
+
183
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
184
+ -->
185
+
186
+ <!--
187
+ ### Recommendations
188
+
189
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
190
+ -->
191
+
192
+ ## Training Details
193
+
194
+ ### Training Dataset
195
+
196
+ #### parquet
197
+
198
+ * Dataset: parquet
199
+ * Size: 1,000,000 training samples
200
+ * Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
201
+ * Approximate statistics based on the first 1000 samples:
202
+ | | anchor | positive | negative |
203
+ |:--------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
204
+ | type | string | string | string |
205
+ | details | <ul><li>min: 7 tokens</li><li>mean: 50.47 tokens</li><li>max: 256 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 14.36 tokens</li><li>max: 42 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 22.41 tokens</li><li>max: 256 tokens</li></ul> |
206
+ * Samples:
207
+ | anchor | positive | negative |
208
+ |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
209
+ | <code>Anas versicolor (organism)</code> | <code>Silver teal (organism)</code> | <code>Cryotherapy of gastric lesion (procedure)</code> |
210
+ | <code>|Vitamin B2 and/or vitamin B2 derivative (substance)| : |Is modification of (attribute)| = |Riboflavin (substance)|, </code> | <code>Riboflavin sodium phosphate (substance)</code> | <code>Nicotinic acid (substance)</code> |
211
+ | <code>|Aplasia of distal phalanx of fifth toe (disorder)| + |Disorder of epiphysis (disorder)| : { |Occurrence (attribute)| = |Congenital (qualifier value)|, |Finding site (attribute)| = |Entire epiphysis of distal phalanx of fifth toe (body structure)|, |Associated morphology (attribute)| = |Agenesis (morphologic abnormality)|, |Pathological process (attribute)| = |Pathological developmental process (qualifier value)| }</code> | <code>Agenesis of epiphysis of distal phalanx of fifth toe (disorder)</code> | <code>Product containing mianserin in oral dose form (medicinal product form)</code> |
212
+ * Loss: [<code>TripletLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#tripletloss) with these parameters:
213
+ ```json
214
+ {
215
+ "distance_metric": "TripletDistanceMetric.COSINE",
216
+ "triplet_margin": 0.2
217
+ }
218
+ ```
219
+
220
+ ### Evaluation Dataset
221
+
222
+ #### parquet
223
+
224
+ * Dataset: parquet
225
+ * Size: 1,000,000 evaluation samples
226
+ * Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
227
+ * Approximate statistics based on the first 1000 samples:
228
+ | | anchor | positive | negative |
229
+ |:--------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
230
+ | type | string | string | string |
231
+ | details | <ul><li>min: 6 tokens</li><li>mean: 48.58 tokens</li><li>max: 256 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 14.51 tokens</li><li>max: 45 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 20.96 tokens</li><li>max: 256 tokens</li></ul> |
232
+ * Samples:
233
+ | anchor | positive | negative |
234
+ |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------|
235
+ | <code>|Genus Roseateles (organism)|</code> | <code>Pelomonas saccharophila (organism)</code> | <code>|Mycology culture (procedure)|:{|Component (attribute)|=|Pichia manshurica (organism)|}{|Has specimen (attribute)|=|Fluid specimen (specimen)|}</code> |
236
+ | <code>|Partial urinary cystectomy (procedure)| + |Procedure on neck of urinary bladder (procedure)| + |Surgical procedure on outlet of urinary bladder (procedure)| + |Transurethral excision of urinary bladder (procedure)| : { |Surgical approach (attribute)| = |Transurethral approach (qualifier value)|, |Method (attribute)| = |Excision - action (qualifier value)|, |Procedure site - Direct (attribute)| = |Structure of neck of urinary bladder (body structure)| }</code> | <code>Transurethral excision of neck of urinary bladder (procedure)</code> | <code>Paracentesis of urinary bladder (procedure)</code> |
237
+ | <code>|Product containing integrase strand transfer inhibitor (product)| + |Product containing nitrogen and/or nitrogen compound (product)| : { |Has active ingredient (attribute)| = |Dolutegravir (substance)| }</code> | <code>Dolutegravir (product)</code> | <code>Product containing ammonium bicarbonate (medicinal product)</code> |
238
+ * Loss: [<code>TripletLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#tripletloss) with these parameters:
239
+ ```json
240
+ {
241
+ "distance_metric": "TripletDistanceMetric.COSINE",
242
+ "triplet_margin": 0.2
243
+ }
244
+ ```
245
+
246
+ ### Training Hyperparameters
247
+ #### Non-Default Hyperparameters
248
+
249
+ - `eval_strategy`: steps
250
+ - `per_device_train_batch_size`: 16
251
+ - `per_device_eval_batch_size`: 16
252
+ - `num_train_epochs`: 1
253
+ - `warmup_ratio`: 0.1
254
+ - `fp16`: True
255
+ - `batch_sampler`: no_duplicates
256
+
257
+ #### All Hyperparameters
258
+ <details><summary>Click to expand</summary>
259
+
260
+ - `overwrite_output_dir`: False
261
+ - `do_predict`: False
262
+ - `eval_strategy`: steps
263
+ - `prediction_loss_only`: True
264
+ - `per_device_train_batch_size`: 16
265
+ - `per_device_eval_batch_size`: 16
266
+ - `per_gpu_train_batch_size`: None
267
+ - `per_gpu_eval_batch_size`: None
268
+ - `gradient_accumulation_steps`: 1
269
+ - `eval_accumulation_steps`: None
270
+ - `torch_empty_cache_steps`: None
271
+ - `learning_rate`: 5e-05
272
+ - `weight_decay`: 0.0
273
+ - `adam_beta1`: 0.9
274
+ - `adam_beta2`: 0.999
275
+ - `adam_epsilon`: 1e-08
276
+ - `max_grad_norm`: 1.0
277
+ - `num_train_epochs`: 1
278
+ - `max_steps`: -1
279
+ - `lr_scheduler_type`: linear
280
+ - `lr_scheduler_kwargs`: {}
281
+ - `warmup_ratio`: 0.1
282
+ - `warmup_steps`: 0
283
+ - `log_level`: passive
284
+ - `log_level_replica`: warning
285
+ - `log_on_each_node`: True
286
+ - `logging_nan_inf_filter`: True
287
+ - `save_safetensors`: True
288
+ - `save_on_each_node`: False
289
+ - `save_only_model`: False
290
+ - `restore_callback_states_from_checkpoint`: False
291
+ - `no_cuda`: False
292
+ - `use_cpu`: False
293
+ - `use_mps_device`: False
294
+ - `seed`: 42
295
+ - `data_seed`: None
296
+ - `jit_mode_eval`: False
297
+ - `use_ipex`: False
298
+ - `bf16`: False
299
+ - `fp16`: True
300
+ - `fp16_opt_level`: O1
301
+ - `half_precision_backend`: auto
302
+ - `bf16_full_eval`: False
303
+ - `fp16_full_eval`: False
304
+ - `tf32`: None
305
+ - `local_rank`: 0
306
+ - `ddp_backend`: None
307
+ - `tpu_num_cores`: None
308
+ - `tpu_metrics_debug`: False
309
+ - `debug`: []
310
+ - `dataloader_drop_last`: False
311
+ - `dataloader_num_workers`: 0
312
+ - `dataloader_prefetch_factor`: None
313
+ - `past_index`: -1
314
+ - `disable_tqdm`: False
315
+ - `remove_unused_columns`: True
316
+ - `label_names`: None
317
+ - `load_best_model_at_end`: False
318
+ - `ignore_data_skip`: False
319
+ - `fsdp`: []
320
+ - `fsdp_min_num_params`: 0
321
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
322
+ - `fsdp_transformer_layer_cls_to_wrap`: None
323
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
324
+ - `deepspeed`: None
325
+ - `label_smoothing_factor`: 0.0
326
+ - `optim`: adamw_torch
327
+ - `optim_args`: None
328
+ - `adafactor`: False
329
+ - `group_by_length`: False
330
+ - `length_column_name`: length
331
+ - `ddp_find_unused_parameters`: None
332
+ - `ddp_bucket_cap_mb`: None
333
+ - `ddp_broadcast_buffers`: False
334
+ - `dataloader_pin_memory`: True
335
+ - `dataloader_persistent_workers`: False
336
+ - `skip_memory_metrics`: True
337
+ - `use_legacy_prediction_loop`: False
338
+ - `push_to_hub`: False
339
+ - `resume_from_checkpoint`: None
340
+ - `hub_model_id`: None
341
+ - `hub_strategy`: every_save
342
+ - `hub_private_repo`: None
343
+ - `hub_always_push`: False
344
+ - `gradient_checkpointing`: False
345
+ - `gradient_checkpointing_kwargs`: None
346
+ - `include_inputs_for_metrics`: False
347
+ - `include_for_metrics`: []
348
+ - `eval_do_concat_batches`: True
349
+ - `fp16_backend`: auto
350
+ - `push_to_hub_model_id`: None
351
+ - `push_to_hub_organization`: None
352
+ - `mp_parameters`:
353
+ - `auto_find_batch_size`: False
354
+ - `full_determinism`: False
355
+ - `torchdynamo`: None
356
+ - `ray_scope`: last
357
+ - `ddp_timeout`: 1800
358
+ - `torch_compile`: False
359
+ - `torch_compile_backend`: None
360
+ - `torch_compile_mode`: None
361
+ - `dispatch_batches`: None
362
+ - `split_batches`: None
363
+ - `include_tokens_per_second`: False
364
+ - `include_num_input_tokens_seen`: False
365
+ - `neftune_noise_alpha`: None
366
+ - `optim_target_modules`: None
367
+ - `batch_eval_metrics`: False
368
+ - `eval_on_start`: False
369
+ - `use_liger_kernel`: False
370
+ - `eval_use_gather_object`: False
371
+ - `average_tokens_across_devices`: False
372
+ - `prompts`: None
373
+ - `batch_sampler`: no_duplicates
374
+ - `multi_dataset_batch_sampler`: proportional
375
+
376
+ </details>
377
+
378
+ ### Training Logs
379
+ <details><summary>Click to expand</summary>
380
+
381
+ | Epoch | Step | Training Loss | Validation Loss | snomed_triplet_1M_3_4_3-dev_cosine_accuracy |
382
+ |:------:|:-----:|:-------------:|:---------------:|:-------------------------------------------:|
383
+ | 0.0027 | 100 | 0.0553 | 0.0405 | 0.9199 |
384
+ | 0.0053 | 200 | 0.0412 | 0.0316 | 0.9369 |
385
+ | 0.008 | 300 | 0.0277 | 0.0296 | 0.9405 |
386
+ | 0.0107 | 400 | 0.0303 | 0.0282 | 0.9433 |
387
+ | 0.0133 | 500 | 0.0262 | 0.0275 | 0.9450 |
388
+ | 0.016 | 600 | 0.0293 | 0.0266 | 0.9466 |
389
+ | 0.0187 | 700 | 0.0301 | 0.0257 | 0.9480 |
390
+ | 0.0213 | 800 | 0.0262 | 0.0249 | 0.9506 |
391
+ | 0.024 | 900 | 0.0258 | 0.0240 | 0.9527 |
392
+ | 0.0267 | 1000 | 0.0286 | 0.0235 | 0.9537 |
393
+ | 0.0293 | 1100 | 0.0239 | 0.0229 | 0.9547 |
394
+ | 0.032 | 1200 | 0.0211 | 0.0231 | 0.9548 |
395
+ | 0.0347 | 1300 | 0.0235 | 0.0228 | 0.9555 |
396
+ | 0.0373 | 1400 | 0.0257 | 0.0225 | 0.9559 |
397
+ | 0.04 | 1500 | 0.025 | 0.0217 | 0.9572 |
398
+ | 0.0427 | 1600 | 0.0216 | 0.0214 | 0.9581 |
399
+ | 0.0453 | 1700 | 0.0247 | 0.0214 | 0.9580 |
400
+ | 0.048 | 1800 | 0.0229 | 0.0212 | 0.9588 |
401
+ | 0.0507 | 1900 | 0.0207 | 0.0211 | 0.9585 |
402
+ | 0.0533 | 2000 | 0.0224 | 0.0214 | 0.9585 |
403
+ | 0.056 | 2100 | 0.0237 | 0.0209 | 0.9587 |
404
+ | 0.0587 | 2200 | 0.0205 | 0.0205 | 0.9591 |
405
+ | 0.0613 | 2300 | 0.0218 | 0.0208 | 0.9590 |
406
+ | 0.064 | 2400 | 0.0209 | 0.0204 | 0.9601 |
407
+ | 0.0667 | 2500 | 0.0225 | 0.0207 | 0.9591 |
408
+ | 0.0693 | 2600 | 0.021 | 0.0206 | 0.9604 |
409
+ | 0.072 | 2700 | 0.0222 | 0.0197 | 0.9622 |
410
+ | 0.0747 | 2800 | 0.0214 | 0.0198 | 0.9615 |
411
+ | 0.0773 | 2900 | 0.0204 | 0.0200 | 0.9611 |
412
+ | 0.08 | 3000 | 0.026 | 0.0197 | 0.9622 |
413
+ | 0.0827 | 3100 | 0.0181 | 0.0197 | 0.9617 |
414
+ | 0.0853 | 3200 | 0.023 | 0.0195 | 0.9612 |
415
+ | 0.088 | 3300 | 0.0198 | 0.0195 | 0.9620 |
416
+ | 0.0907 | 3400 | 0.0205 | 0.0198 | 0.9611 |
417
+ | 0.0933 | 3500 | 0.0208 | 0.0194 | 0.9622 |
418
+ | 0.096 | 3600 | 0.0205 | 0.0205 | 0.9592 |
419
+ | 0.0987 | 3700 | 0.0242 | 0.0196 | 0.9619 |
420
+ | 0.1013 | 3800 | 0.0178 | 0.0191 | 0.9634 |
421
+ | 0.104 | 3900 | 0.0189 | 0.0189 | 0.9629 |
422
+ | 0.1067 | 4000 | 0.0249 | 0.0188 | 0.9637 |
423
+ | 0.1093 | 4100 | 0.0201 | 0.0186 | 0.9634 |
424
+ | 0.112 | 4200 | 0.0198 | 0.0185 | 0.9636 |
425
+ | 0.1147 | 4300 | 0.0208 | 0.0186 | 0.9639 |
426
+ | 0.1173 | 4400 | 0.019 | 0.0185 | 0.9639 |
427
+ | 0.12 | 4500 | 0.0203 | 0.0188 | 0.9638 |
428
+ | 0.1227 | 4600 | 0.0205 | 0.0191 | 0.9633 |
429
+ | 0.1253 | 4700 | 0.0183 | 0.0194 | 0.9623 |
430
+ | 0.128 | 4800 | 0.022 | 0.0183 | 0.9643 |
431
+ | 0.1307 | 4900 | 0.0193 | 0.0182 | 0.9649 |
432
+ | 0.1333 | 5000 | 0.0192 | 0.0178 | 0.9659 |
433
+ | 0.136 | 5100 | 0.0212 | 0.0185 | 0.9650 |
434
+ | 0.1387 | 5200 | 0.0181 | 0.0183 | 0.9639 |
435
+ | 0.1413 | 5300 | 0.0189 | 0.0177 | 0.9656 |
436
+ | 0.144 | 5400 | 0.0209 | 0.0179 | 0.9658 |
437
+ | 0.1467 | 5500 | 0.0216 | 0.0175 | 0.9665 |
438
+ | 0.1493 | 5600 | 0.0178 | 0.0176 | 0.9665 |
439
+ | 0.152 | 5700 | 0.019 | 0.0178 | 0.9658 |
440
+ | 0.1547 | 5800 | 0.0215 | 0.0180 | 0.9655 |
441
+ | 0.1573 | 5900 | 0.0194 | 0.0176 | 0.9663 |
442
+ | 0.16 | 6000 | 0.0182 | 0.0181 | 0.9651 |
443
+ | 0.1627 | 6100 | 0.0186 | 0.0185 | 0.9640 |
444
+ | 0.1653 | 6200 | 0.019 | 0.0178 | 0.9650 |
445
+ | 0.168 | 6300 | 0.019 | 0.0172 | 0.9667 |
446
+ | 0.1707 | 6400 | 0.0186 | 0.0178 | 0.9654 |
447
+ | 0.1733 | 6500 | 0.0192 | 0.0172 | 0.9669 |
448
+ | 0.176 | 6600 | 0.0185 | 0.0171 | 0.9670 |
449
+ | 0.1787 | 6700 | 0.019 | 0.0169 | 0.9674 |
450
+ | 0.1813 | 6800 | 0.0183 | 0.0170 | 0.9671 |
451
+ | 0.184 | 6900 | 0.0199 | 0.0168 | 0.9675 |
452
+ | 0.1867 | 7000 | 0.0186 | 0.0169 | 0.9673 |
453
+ | 0.1893 | 7100 | 0.016 | 0.0169 | 0.9676 |
454
+ | 0.192 | 7200 | 0.0158 | 0.0174 | 0.9663 |
455
+ | 0.1947 | 7300 | 0.0205 | 0.0169 | 0.9681 |
456
+ | 0.1973 | 7400 | 0.0189 | 0.0169 | 0.9669 |
457
+ | 0.2 | 7500 | 0.0188 | 0.0170 | 0.9672 |
458
+ | 0.2027 | 7600 | 0.0193 | 0.0168 | 0.9674 |
459
+ | 0.2053 | 7700 | 0.0202 | 0.0168 | 0.9673 |
460
+ | 0.208 | 7800 | 0.0184 | 0.0165 | 0.9676 |
461
+ | 0.2107 | 7900 | 0.0196 | 0.0162 | 0.9687 |
462
+ | 0.2133 | 8000 | 0.0186 | 0.0161 | 0.9688 |
463
+ | 0.216 | 8100 | 0.0174 | 0.0166 | 0.9670 |
464
+ | 0.2187 | 8200 | 0.0178 | 0.0166 | 0.9676 |
465
+ | 0.2213 | 8300 | 0.0187 | 0.0172 | 0.9664 |
466
+ | 0.224 | 8400 | 0.0175 | 0.0162 | 0.9685 |
467
+ | 0.2267 | 8500 | 0.0165 | 0.0163 | 0.9674 |
468
+ | 0.2293 | 8600 | 0.018 | 0.0164 | 0.9678 |
469
+ | 0.232 | 8700 | 0.0192 | 0.0165 | 0.9680 |
470
+ | 0.2347 | 8800 | 0.0182 | 0.0164 | 0.9680 |
471
+ | 0.2373 | 8900 | 0.0191 | 0.0162 | 0.9689 |
472
+ | 0.24 | 9000 | 0.0173 | 0.0161 | 0.9683 |
473
+ | 0.2427 | 9100 | 0.022 | 0.0159 | 0.9685 |
474
+ | 0.2453 | 9200 | 0.0182 | 0.0161 | 0.9685 |
475
+ | 0.248 | 9300 | 0.0174 | 0.0165 | 0.9684 |
476
+ | 0.2507 | 9400 | 0.0181 | 0.0168 | 0.9667 |
477
+ | 0.2533 | 9500 | 0.0159 | 0.0163 | 0.9684 |
478
+ | 0.256 | 9600 | 0.0176 | 0.0162 | 0.9685 |
479
+ | 0.2587 | 9700 | 0.0155 | 0.0170 | 0.9668 |
480
+ | 0.2613 | 9800 | 0.0183 | 0.0162 | 0.9679 |
481
+ | 0.264 | 9900 | 0.0183 | 0.0156 | 0.9693 |
482
+ | 0.2667 | 10000 | 0.019 | 0.0156 | 0.9695 |
483
+ | 0.2693 | 10100 | 0.0167 | 0.0162 | 0.9683 |
484
+ | 0.272 | 10200 | 0.0202 | 0.0156 | 0.9695 |
485
+ | 0.2747 | 10300 | 0.0174 | 0.0157 | 0.9694 |
486
+ | 0.2773 | 10400 | 0.0165 | 0.0155 | 0.9694 |
487
+ | 0.28 | 10500 | 0.0176 | 0.0155 | 0.9700 |
488
+ | 0.2827 | 10600 | 0.0181 | 0.0153 | 0.9699 |
489
+ | 0.2853 | 10700 | 0.0184 | 0.0154 | 0.9697 |
490
+ | 0.288 | 10800 | 0.0172 | 0.0155 | 0.9692 |
491
+ | 0.2907 | 10900 | 0.0153 | 0.0156 | 0.9694 |
492
+ | 0.2933 | 11000 | 0.0169 | 0.0154 | 0.9700 |
493
+ | 0.296 | 11100 | 0.0181 | 0.0153 | 0.9698 |
494
+ | 0.2987 | 11200 | 0.0164 | 0.0154 | 0.9700 |
495
+ | 0.3013 | 11300 | 0.0177 | 0.0158 | 0.9691 |
496
+ | 0.304 | 11400 | 0.0154 | 0.0153 | 0.9700 |
497
+ | 0.3067 | 11500 | 0.0159 | 0.0153 | 0.9700 |
498
+ | 0.3093 | 11600 | 0.0162 | 0.0152 | 0.9699 |
499
+ | 0.312 | 11700 | 0.0172 | 0.0150 | 0.9710 |
500
+ | 0.3147 | 11800 | 0.0151 | 0.0153 | 0.9696 |
501
+ | 0.3173 | 11900 | 0.0157 | 0.0153 | 0.9697 |
502
+ | 0.32 | 12000 | 0.0145 | 0.0150 | 0.9705 |
503
+ | 0.3227 | 12100 | 0.0184 | 0.0153 | 0.9701 |
504
+ | 0.3253 | 12200 | 0.0173 | 0.0151 | 0.9706 |
505
+ | 0.328 | 12300 | 0.0158 | 0.0151 | 0.971 |
506
+ | 0.3307 | 12400 | 0.0154 | 0.0154 | 0.9697 |
507
+ | 0.3333 | 12500 | 0.0126 | 0.0153 | 0.9697 |
508
+ | 0.336 | 12600 | 0.0151 | 0.0150 | 0.9704 |
509
+ | 0.3387 | 12700 | 0.0152 | 0.0152 | 0.9698 |
510
+ | 0.3413 | 12800 | 0.0176 | 0.0150 | 0.9707 |
511
+ | 0.344 | 12900 | 0.0172 | 0.0149 | 0.9705 |
512
+ | 0.3467 | 13000 | 0.0149 | 0.0151 | 0.9704 |
513
+ | 0.3493 | 13100 | 0.0154 | 0.0151 | 0.9701 |
514
+ | 0.352 | 13200 | 0.0138 | 0.0148 | 0.9705 |
515
+ | 0.3547 | 13300 | 0.0195 | 0.0149 | 0.9705 |
516
+ | 0.3573 | 13400 | 0.0162 | 0.0151 | 0.9707 |
517
+ | 0.36 | 13500 | 0.0137 | 0.0150 | 0.9708 |
518
+ | 0.3627 | 13600 | 0.0153 | 0.0151 | 0.9704 |
519
+ | 0.3653 | 13700 | 0.0143 | 0.0150 | 0.9705 |
520
+ | 0.368 | 13800 | 0.0161 | 0.0149 | 0.9709 |
521
+ | 0.3707 | 13900 | 0.0136 | 0.0149 | 0.9712 |
522
+ | 0.3733 | 14000 | 0.0161 | 0.0150 | 0.9709 |
523
+ | 0.376 | 14100 | 0.0171 | 0.0148 | 0.9718 |
524
+ | 0.3787 | 14200 | 0.0168 | 0.0147 | 0.9717 |
525
+ | 0.3813 | 14300 | 0.0159 | 0.0147 | 0.9718 |
526
+ | 0.384 | 14400 | 0.0167 | 0.0145 | 0.9721 |
527
+ | 0.3867 | 14500 | 0.0158 | 0.0147 | 0.9715 |
528
+ | 0.3893 | 14600 | 0.0153 | 0.0146 | 0.9713 |
529
+ | 0.392 | 14700 | 0.0131 | 0.0145 | 0.9717 |
530
+ | 0.3947 | 14800 | 0.0166 | 0.0144 | 0.9722 |
531
+ | 0.3973 | 14900 | 0.0164 | 0.0142 | 0.9720 |
532
+ | 0.4 | 15000 | 0.0166 | 0.0143 | 0.9720 |
533
+ | 0.4027 | 15100 | 0.0168 | 0.0143 | 0.9726 |
534
+ | 0.4053 | 15200 | 0.0145 | 0.0143 | 0.9723 |
535
+ | 0.408 | 15300 | 0.0149 | 0.0144 | 0.9717 |
536
+ | 0.4107 | 15400 | 0.0152 | 0.0141 | 0.9729 |
537
+ | 0.4133 | 15500 | 0.0147 | 0.0140 | 0.9734 |
538
+ | 0.416 | 15600 | 0.0141 | 0.0140 | 0.9731 |
539
+ | 0.4187 | 15700 | 0.0147 | 0.0140 | 0.9731 |
540
+ | 0.4213 | 15800 | 0.0158 | 0.0139 | 0.9734 |
541
+ | 0.424 | 15900 | 0.0177 | 0.0141 | 0.9728 |
542
+ | 0.4267 | 16000 | 0.0151 | 0.0137 | 0.9734 |
543
+ | 0.4293 | 16100 | 0.0148 | 0.0145 | 0.9724 |
544
+ | 0.432 | 16200 | 0.0135 | 0.0144 | 0.9721 |
545
+ | 0.4347 | 16300 | 0.0167 | 0.0138 | 0.9736 |
546
+ | 0.4373 | 16400 | 0.0153 | 0.0138 | 0.9739 |
547
+ | 0.44 | 16500 | 0.014 | 0.0139 | 0.9731 |
548
+ | 0.4427 | 16600 | 0.0168 | 0.0139 | 0.9734 |
549
+ | 0.4453 | 16700 | 0.0125 | 0.0139 | 0.9734 |
550
+ | 0.448 | 16800 | 0.0163 | 0.0139 | 0.9733 |
551
+ | 0.4507 | 16900 | 0.0179 | 0.0137 | 0.9742 |
552
+ | 0.4533 | 17000 | 0.0162 | 0.0136 | 0.9738 |
553
+ | 0.456 | 17100 | 0.0148 | 0.0137 | 0.9734 |
554
+ | 0.4587 | 17200 | 0.0154 | 0.0137 | 0.9737 |
555
+ | 0.4613 | 17300 | 0.0178 | 0.0139 | 0.9732 |
556
+ | 0.464 | 17400 | 0.0176 | 0.0138 | 0.9731 |
557
+ | 0.4667 | 17500 | 0.012 | 0.0135 | 0.9738 |
558
+ | 0.4693 | 17600 | 0.0136 | 0.0137 | 0.9731 |
559
+ | 0.472 | 17700 | 0.0156 | 0.0133 | 0.9740 |
560
+ | 0.4747 | 17800 | 0.0151 | 0.0136 | 0.9738 |
561
+ | 0.4773 | 17900 | 0.0145 | 0.0135 | 0.9741 |
562
+ | 0.48 | 18000 | 0.0176 | 0.0136 | 0.9735 |
563
+ | 0.4827 | 18100 | 0.0143 | 0.0133 | 0.9744 |
564
+ | 0.4853 | 18200 | 0.0144 | 0.0133 | 0.9742 |
565
+ | 0.488 | 18300 | 0.0139 | 0.0135 | 0.9738 |
566
+ | 0.4907 | 18400 | 0.0134 | 0.0134 | 0.9740 |
567
+ | 0.4933 | 18500 | 0.0135 | 0.0134 | 0.9738 |
568
+ | 0.496 | 18600 | 0.0144 | 0.0134 | 0.9738 |
569
+ | 0.4987 | 18700 | 0.0143 | 0.0135 | 0.9744 |
570
+ | 0.5013 | 18800 | 0.0165 | 0.0133 | 0.9748 |
571
+ | 0.504 | 18900 | 0.0147 | 0.0133 | 0.9742 |
572
+ | 0.5067 | 19000 | 0.0159 | 0.0133 | 0.9743 |
573
+ | 0.5093 | 19100 | 0.013 | 0.0132 | 0.9746 |
574
+ | 0.512 | 19200 | 0.0145 | 0.0133 | 0.9744 |
575
+ | 0.5147 | 19300 | 0.0147 | 0.0134 | 0.9743 |
576
+ | 0.5173 | 19400 | 0.0151 | 0.0131 | 0.9748 |
577
+ | 0.52 | 19500 | 0.0134 | 0.0132 | 0.9742 |
578
+ | 0.5227 | 19600 | 0.0148 | 0.0135 | 0.9740 |
579
+ | 0.5253 | 19700 | 0.0142 | 0.0134 | 0.9744 |
580
+ | 0.528 | 19800 | 0.0158 | 0.0132 | 0.9746 |
581
+ | 0.5307 | 19900 | 0.015 | 0.0134 | 0.9748 |
582
+ | 0.5333 | 20000 | 0.0146 | 0.0132 | 0.9745 |
583
+ | 0.536 | 20100 | 0.0136 | 0.0130 | 0.9752 |
584
+ | 0.5387 | 20200 | 0.0142 | 0.0131 | 0.9750 |
585
+ | 0.5413 | 20300 | 0.0137 | 0.0130 | 0.9749 |
586
+ | 0.544 | 20400 | 0.0118 | 0.0132 | 0.9741 |
587
+ | 0.5467 | 20500 | 0.0129 | 0.0131 | 0.9750 |
588
+ | 0.5493 | 20600 | 0.015 | 0.0131 | 0.9749 |
589
+ | 0.552 | 20700 | 0.0154 | 0.0132 | 0.9743 |
590
+ | 0.5547 | 20800 | 0.0165 | 0.0132 | 0.9747 |
591
+ | 0.5573 | 20900 | 0.0158 | 0.0131 | 0.9751 |
592
+ | 0.56 | 21000 | 0.014 | 0.0130 | 0.9746 |
593
+ | 0.5627 | 21100 | 0.0157 | 0.0129 | 0.9755 |
594
+ | 0.5653 | 21200 | 0.014 | 0.0129 | 0.9754 |
595
+ | 0.568 | 21300 | 0.0149 | 0.0129 | 0.9751 |
596
+ | 0.5707 | 21400 | 0.0114 | 0.0129 | 0.9754 |
597
+ | 0.5733 | 21500 | 0.0116 | 0.0128 | 0.9755 |
598
+ | 0.576 | 21600 | 0.0114 | 0.0132 | 0.9743 |
599
+ | 0.5787 | 21700 | 0.0164 | 0.0127 | 0.9759 |
600
+ | 0.5813 | 21800 | 0.0137 | 0.0127 | 0.9754 |
601
+ | 0.584 | 21900 | 0.0118 | 0.0129 | 0.9745 |
602
+ | 0.5867 | 22000 | 0.0126 | 0.0129 | 0.9752 |
603
+ | 0.5893 | 22100 | 0.0153 | 0.0126 | 0.9758 |
604
+ | 0.592 | 22200 | 0.0128 | 0.0126 | 0.9759 |
605
+ | 0.5947 | 22300 | 0.0161 | 0.0128 | 0.9755 |
606
+ | 0.5973 | 22400 | 0.0121 | 0.0128 | 0.9754 |
607
+ | 0.6 | 22500 | 0.0144 | 0.0126 | 0.9758 |
608
+ | 0.6027 | 22600 | 0.0138 | 0.0127 | 0.9754 |
609
+ | 0.6053 | 22700 | 0.0114 | 0.0125 | 0.9757 |
610
+ | 0.608 | 22800 | 0.0163 | 0.0126 | 0.9755 |
611
+ | 0.6107 | 22900 | 0.0127 | 0.0125 | 0.9757 |
612
+ | 0.6133 | 23000 | 0.0139 | 0.0126 | 0.9752 |
613
+ | 0.616 | 23100 | 0.015 | 0.0126 | 0.9754 |
614
+ | 0.6187 | 23200 | 0.0128 | 0.0124 | 0.9759 |
615
+ | 0.6213 | 23300 | 0.0127 | 0.0126 | 0.9758 |
616
+ | 0.624 | 23400 | 0.0137 | 0.0126 | 0.9755 |
617
+ | 0.6267 | 23500 | 0.0171 | 0.0125 | 0.9760 |
618
+ | 0.6293 | 23600 | 0.0154 | 0.0123 | 0.9761 |
619
+ | 0.632 | 23700 | 0.0133 | 0.0125 | 0.9757 |
620
+ | 0.6347 | 23800 | 0.0147 | 0.0122 | 0.9762 |
621
+ | 0.6373 | 23900 | 0.012 | 0.0123 | 0.9759 |
622
+ | 0.64 | 24000 | 0.0121 | 0.0124 | 0.9762 |
623
+ | 0.6427 | 24100 | 0.0156 | 0.0122 | 0.9768 |
624
+ | 0.6453 | 24200 | 0.0135 | 0.0122 | 0.9763 |
625
+ | 0.648 | 24300 | 0.0111 | 0.0123 | 0.9762 |
626
+ | 0.6507 | 24400 | 0.0131 | 0.0121 | 0.9766 |
627
+ | 0.6533 | 24500 | 0.0166 | 0.0120 | 0.9766 |
628
+ | 0.656 | 24600 | 0.0145 | 0.0121 | 0.9764 |
629
+ | 0.6587 | 24700 | 0.0138 | 0.0122 | 0.9763 |
630
+ | 0.6613 | 24800 | 0.0127 | 0.0120 | 0.9766 |
631
+ | 0.664 | 24900 | 0.0142 | 0.0120 | 0.9767 |
632
+ | 0.6667 | 25000 | 0.0119 | 0.0122 | 0.9764 |
633
+ | 0.6693 | 25100 | 0.0157 | 0.0120 | 0.9768 |
634
+ | 0.672 | 25200 | 0.0126 | 0.0119 | 0.9769 |
635
+ | 0.6747 | 25300 | 0.0113 | 0.0119 | 0.9772 |
636
+ | 0.6773 | 25400 | 0.0138 | 0.0121 | 0.9767 |
637
+ | 0.68 | 25500 | 0.0135 | 0.0124 | 0.9759 |
638
+ | 0.6827 | 25600 | 0.0147 | 0.0120 | 0.9765 |
639
+ | 0.6853 | 25700 | 0.0119 | 0.0120 | 0.9764 |
640
+ | 0.688 | 25800 | 0.0167 | 0.0120 | 0.9765 |
641
+ | 0.6907 | 25900 | 0.0132 | 0.0120 | 0.9767 |
642
+ | 0.6933 | 26000 | 0.0144 | 0.0118 | 0.9768 |
643
+ | 0.696 | 26100 | 0.0135 | 0.0118 | 0.9771 |
644
+ | 0.6987 | 26200 | 0.0156 | 0.0119 | 0.9769 |
645
+ | 0.7013 | 26300 | 0.0132 | 0.0119 | 0.9769 |
646
+ | 0.704 | 26400 | 0.0139 | 0.0120 | 0.9769 |
647
+ | 0.7067 | 26500 | 0.014 | 0.0118 | 0.9771 |
648
+ | 0.7093 | 26600 | 0.0133 | 0.0118 | 0.9770 |
649
+ | 0.712 | 26700 | 0.0142 | 0.0118 | 0.9773 |
650
+ | 0.7147 | 26800 | 0.0113 | 0.0117 | 0.977 |
651
+ | 0.7173 | 26900 | 0.0142 | 0.0117 | 0.977 |
652
+ | 0.72 | 27000 | 0.0112 | 0.0117 | 0.9771 |
653
+ | 0.7227 | 27100 | 0.012 | 0.0118 | 0.9768 |
654
+ | 0.7253 | 27200 | 0.0135 | 0.0117 | 0.9768 |
655
+ | 0.728 | 27300 | 0.0126 | 0.0116 | 0.9769 |
656
+ | 0.7307 | 27400 | 0.0136 | 0.0117 | 0.9767 |
657
+ | 0.7333 | 27500 | 0.013 | 0.0116 | 0.9770 |
658
+ | 0.736 | 27600 | 0.0131 | 0.0117 | 0.9767 |
659
+ | 0.7387 | 27700 | 0.0127 | 0.0116 | 0.9772 |
660
+ | 0.7413 | 27800 | 0.0124 | 0.0116 | 0.9770 |
661
+ | 0.744 | 27900 | 0.011 | 0.0116 | 0.9771 |
662
+ | 0.7467 | 28000 | 0.0159 | 0.0116 | 0.9770 |
663
+ | 0.7493 | 28100 | 0.0118 | 0.0116 | 0.9770 |
664
+ | 0.752 | 28200 | 0.0146 | 0.0115 | 0.9773 |
665
+ | 0.7547 | 28300 | 0.0112 | 0.0116 | 0.9772 |
666
+ | 0.7573 | 28400 | 0.0116 | 0.0115 | 0.9776 |
667
+ | 0.76 | 28500 | 0.0115 | 0.0115 | 0.9775 |
668
+ | 0.7627 | 28600 | 0.0137 | 0.0115 | 0.9779 |
669
+ | 0.7653 | 28700 | 0.0106 | 0.0115 | 0.9777 |
670
+ | 0.768 | 28800 | 0.011 | 0.0116 | 0.9774 |
671
+ | 0.7707 | 28900 | 0.0132 | 0.0115 | 0.9774 |
672
+ | 0.7733 | 29000 | 0.0119 | 0.0114 | 0.9776 |
673
+ | 0.776 | 29100 | 0.0121 | 0.0114 | 0.9779 |
674
+ | 0.7787 | 29200 | 0.0136 | 0.0113 | 0.9780 |
675
+ | 0.7813 | 29300 | 0.0114 | 0.0114 | 0.9779 |
676
+ | 0.784 | 29400 | 0.0122 | 0.0115 | 0.9778 |
677
+ | 0.7867 | 29500 | 0.0117 | 0.0114 | 0.9780 |
678
+ | 0.7893 | 29600 | 0.0119 | 0.0114 | 0.9778 |
679
+ | 0.792 | 29700 | 0.0145 | 0.0114 | 0.9778 |
680
+ | 0.7947 | 29800 | 0.0098 | 0.0113 | 0.9779 |
681
+ | 0.7973 | 29900 | 0.015 | 0.0114 | 0.9777 |
682
+ | 0.8 | 30000 | 0.0123 | 0.0113 | 0.9779 |
683
+ | 0.8027 | 30100 | 0.0111 | 0.0115 | 0.9774 |
684
+ | 0.8053 | 30200 | 0.0126 | 0.0114 | 0.9778 |
685
+ | 0.808 | 30300 | 0.0131 | 0.0113 | 0.9783 |
686
+ | 0.8107 | 30400 | 0.0131 | 0.0113 | 0.9784 |
687
+ | 0.8133 | 30500 | 0.0113 | 0.0113 | 0.9783 |
688
+ | 0.816 | 30600 | 0.0131 | 0.0113 | 0.9783 |
689
+ | 0.8187 | 30700 | 0.0137 | 0.0113 | 0.9782 |
690
+ | 0.8213 | 30800 | 0.0119 | 0.0112 | 0.9784 |
691
+ | 0.824 | 30900 | 0.0127 | 0.0113 | 0.9782 |
692
+ | 0.8267 | 31000 | 0.0114 | 0.0112 | 0.9787 |
693
+ | 0.8293 | 31100 | 0.0116 | 0.0111 | 0.9784 |
694
+ | 0.832 | 31200 | 0.0117 | 0.0112 | 0.9784 |
695
+ | 0.8347 | 31300 | 0.0128 | 0.0112 | 0.9782 |
696
+ | 0.8373 | 31400 | 0.0125 | 0.0112 | 0.9782 |
697
+ | 0.84 | 31500 | 0.0136 | 0.0111 | 0.9787 |
698
+ | 0.8427 | 31600 | 0.0121 | 0.0111 | 0.9785 |
699
+ | 0.8453 | 31700 | 0.0137 | 0.0112 | 0.9785 |
700
+ | 0.848 | 31800 | 0.0115 | 0.0111 | 0.9786 |
701
+ | 0.8507 | 31900 | 0.0111 | 0.0111 | 0.9784 |
702
+ | 0.8533 | 32000 | 0.012 | 0.0111 | 0.9786 |
703
+ | 0.856 | 32100 | 0.0115 | 0.0111 | 0.9787 |
704
+ | 0.8587 | 32200 | 0.0125 | 0.0111 | 0.9785 |
705
+ | 0.8613 | 32300 | 0.0111 | 0.0111 | 0.9788 |
706
+ | 0.864 | 32400 | 0.0127 | 0.0111 | 0.9788 |
707
+ | 0.8667 | 32500 | 0.0126 | 0.0110 | 0.9788 |
708
+ | 0.8693 | 32600 | 0.012 | 0.0111 | 0.9788 |
709
+ | 0.872 | 32700 | 0.0117 | 0.0111 | 0.9787 |
710
+ | 0.8747 | 32800 | 0.0136 | 0.0110 | 0.9787 |
711
+ | 0.8773 | 32900 | 0.0118 | 0.0110 | 0.9788 |
712
+ | 0.88 | 33000 | 0.015 | 0.0110 | 0.9789 |
713
+ | 0.8827 | 33100 | 0.0105 | 0.0110 | 0.9788 |
714
+ | 0.8853 | 33200 | 0.0135 | 0.0110 | 0.9786 |
715
+ | 0.888 | 33300 | 0.0099 | 0.0110 | 0.9790 |
716
+ | 0.8907 | 33400 | 0.013 | 0.0109 | 0.9787 |
717
+ | 0.8933 | 33500 | 0.0149 | 0.0109 | 0.9788 |
718
+ | 0.896 | 33600 | 0.012 | 0.0109 | 0.9789 |
719
+ | 0.8987 | 33700 | 0.01 | 0.0110 | 0.9788 |
720
+ | 0.9013 | 33800 | 0.0132 | 0.0110 | 0.9788 |
721
+ | 0.904 | 33900 | 0.0138 | 0.0109 | 0.9791 |
722
+ | 0.9067 | 34000 | 0.0107 | 0.0109 | 0.9789 |
723
+ | 0.9093 | 34100 | 0.0133 | 0.0109 | 0.9789 |
724
+ | 0.912 | 34200 | 0.0124 | 0.0109 | 0.9788 |
725
+ | 0.9147 | 34300 | 0.0119 | 0.0109 | 0.9788 |
726
+ | 0.9173 | 34400 | 0.0101 | 0.0109 | 0.9787 |
727
+ | 0.92 | 34500 | 0.0135 | 0.0109 | 0.9790 |
728
+ | 0.9227 | 34600 | 0.0116 | 0.0109 | 0.9789 |
729
+ | 0.9253 | 34700 | 0.0116 | 0.0109 | 0.9791 |
730
+ | 0.928 | 34800 | 0.0082 | 0.0108 | 0.9791 |
731
+ | 0.9307 | 34900 | 0.0129 | 0.0108 | 0.9791 |
732
+ | 0.9333 | 35000 | 0.0129 | 0.0108 | 0.9792 |
733
+ | 0.936 | 35100 | 0.0147 | 0.0108 | 0.9791 |
734
+ | 0.9387 | 35200 | 0.0112 | 0.0108 | 0.9790 |
735
+ | 0.9413 | 35300 | 0.0108 | 0.0108 | 0.9790 |
736
+ | 0.944 | 35400 | 0.0114 | 0.0108 | 0.9791 |
737
+ | 0.9467 | 35500 | 0.0096 | 0.0108 | 0.9792 |
738
+ | 0.9493 | 35600 | 0.0111 | 0.0108 | 0.9790 |
739
+ | 0.952 | 35700 | 0.0131 | 0.0108 | 0.9790 |
740
+ | 0.9547 | 35800 | 0.0147 | 0.0108 | 0.9792 |
741
+ | 0.9573 | 35900 | 0.0121 | 0.0108 | 0.9792 |
742
+ | 0.96 | 36000 | 0.0105 | 0.0108 | 0.9791 |
743
+ | 0.9627 | 36100 | 0.0081 | 0.0108 | 0.9791 |
744
+ | 0.9653 | 36200 | 0.013 | 0.0108 | 0.9791 |
745
+ | 0.968 | 36300 | 0.0121 | 0.0108 | 0.9792 |
746
+ | 0.9707 | 36400 | 0.0122 | 0.0108 | 0.9792 |
747
+ | 0.9733 | 36500 | 0.0121 | 0.0108 | 0.9792 |
748
+ | 0.976 | 36600 | 0.011 | 0.0108 | 0.9792 |
749
+ | 0.9787 | 36700 | 0.0109 | 0.0107 | 0.9792 |
750
+ | 0.9813 | 36800 | 0.0114 | 0.0107 | 0.9792 |
751
+ | 0.984 | 36900 | 0.0113 | 0.0107 | 0.9793 |
752
+ | 0.9867 | 37000 | 0.0111 | 0.0107 | 0.9794 |
753
+ | 0.9893 | 37100 | 0.0097 | 0.0107 | 0.9793 |
754
+ | 0.992 | 37200 | 0.0127 | 0.0107 | 0.9793 |
755
+ | 0.9947 | 37300 | 0.0143 | 0.0107 | 0.9794 |
756
+ | 0.9973 | 37400 | 0.0103 | 0.0107 | 0.9794 |
757
+ | 1.0 | 37500 | 0.014 | 0.0107 | 0.9780 |
758
+
759
+ </details>
760
+
761
+ ### Framework Versions
762
+ - Python: 3.11.1
763
+ - Sentence Transformers: 3.3.1
764
+ - Transformers: 4.47.0
765
+ - PyTorch: 2.1.1+cu121
766
+ - Accelerate: 1.2.0
767
+ - Datasets: 2.18.0
768
+ - Tokenizers: 0.21.0
769
+
770
+ ## Citation
771
+
772
+ ### BibTeX
773
+
774
+ #### Sentence Transformers
775
+ ```bibtex
776
+ @inproceedings{reimers-2019-sentence-bert,
777
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
778
+ author = "Reimers, Nils and Gurevych, Iryna",
779
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
780
+ month = "11",
781
+ year = "2019",
782
+ publisher = "Association for Computational Linguistics",
783
+ url = "https://arxiv.org/abs/1908.10084",
784
+ }
785
+ ```
786
+
787
+ #### TripletLoss
788
+ ```bibtex
789
+ @misc{hermans2017defense,
790
+ title={In Defense of the Triplet Loss for Person Re-Identification},
791
+ author={Alexander Hermans and Lucas Beyer and Bastian Leibe},
792
+ year={2017},
793
+ eprint={1703.07737},
794
+ archivePrefix={arXiv},
795
+ primaryClass={cs.CV}
796
+ }
797
+ ```
798
+
799
+ <!--
800
+ ## Glossary
801
+
802
+ *Clearly define terms in order to be accessible across audiences.*
803
+ -->
804
+
805
+ <!--
806
+ ## Model Card Authors
807
+
808
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
809
+ -->
810
+
811
+ <!--
812
+ ## Model Card Contact
813
+
814
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
815
+ -->
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sentence-transformers/all-MiniLM-L6-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": 6,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.47.0",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
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": "2.1.1+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 sha256:21045b2a7ccb732dcf1d1c37c91661f854549404a8f10d09a9ab143e6b91a1d5
3
+ size 90864192
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
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": false,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "max_length": 128,
51
+ "model_max_length": 256,
52
+ "never_split": null,
53
+ "pad_to_multiple_of": null,
54
+ "pad_token": "[PAD]",
55
+ "pad_token_type_id": 0,
56
+ "padding_side": "right",
57
+ "sep_token": "[SEP]",
58
+ "stride": 0,
59
+ "strip_accents": null,
60
+ "tokenize_chinese_chars": true,
61
+ "tokenizer_class": "BertTokenizer",
62
+ "truncation_side": "right",
63
+ "truncation_strategy": "longest_first",
64
+ "unk_token": "[UNK]"
65
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff