Hugging Face's logo

lion-ai
/
arctic-l-medembed

Sentence Similarity
sentence-transformers
Safetensors
bert
feature-extraction
dense
Generated from Trainer
dataset_size:230357
loss:MultipleNegativesRankingLoss
Eval Results (legacy)
text-embeddings-inference
Model card Files
xet
 Community
AleksanderObuchowski commited on
Commit
a86881d
·
verified ·
1 Parent(s): d52d8e4

Add new SentenceTransformer model

Browse files
Files changed (11) hide show
  1. 1_Pooling/config.json +10 -0
  2. README.md +826 -0
  3. config.json +24 -0
  4. config_sentence_transformers.json +14 -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 +63 -0
  11. vocab.txt +0 -0
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 1024,
3
+ "pooling_mode_cls_token": true,
4
+ "pooling_mode_mean_tokens": false,
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 +1,826 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - sentence-transformers
4
+ - sentence-similarity
5
+ - feature-extraction
6
+ - dense
7
+ - generated_from_trainer
8
+ - dataset_size:230357
9
+ - loss:MultipleNegativesRankingLoss
10
+ base_model: Snowflake/snowflake-arctic-embed-l
11
+ widget:
12
+ - source_sentence: post-discharge oral hygiene follow-up plan
13
+ sentences:
14
+ - The patient is advised to continue regular oral hygiene measures and follow-up
15
+ with their primary care dentist.
16
+ - 'PLAN: Follow-up with the patient as clinically indicated.'
17
+ - The patient's last available report revealed significant improvement in kidney
18
+ function. No further information is currently available. The patient is advised
19
+ to follow up with his primary care physician for routine care.
20
+ - source_sentence: Genetic mutations associated with PKD
21
+ sentences:
22
+ - We identified an insertion of C at 650 bp of coding sequence (exon 2) leading
23
+ to frameshift mutation [p.R217Pfs*8] in the PKD patient, but not in the control
24
+ subject. In addition, we also identified a novel point mutation [c.244C > T;]
25
+ at exon 2 in the patient, but not in the control subject.
26
+ - Following the National Comprehensive Cancer Network guidelines, the patient will
27
+ be monitored with careful history and physical, blood pressure measurement, and
28
+ urine and plasma catecholamine assessment every three months through the first
29
+ year and every 6–12 months thereafter through 10 years.
30
+ - 'Genetic analysis showed two variants in NR2E3: a missense variation c.1118T>C,
31
+ which leads to substitution of leucine with proline in amino acid position 373,
32
+ and c.349+5G>C, which involves a gene sequence near a splicing site.'
33
+ - source_sentence: What was the patient's diagnosis based on the MRI results?
34
+ sentences:
35
+ - Magnetic resonance imaging of the orbit showed hyperintensity and increased thickness
36
+ of the preseptal orbital tissue, and optic nerve thickening in the right eye.
37
+ - 'Probands #1 and #2 presented with significant and consistent delays in cognitive
38
+ function, language and sensorimotor development.'
39
+ - An MRI was performed, which revealed the presence of a declivous purulent material
40
+ inside the lateral ventricles with a moderate dilatation of these structures and
41
+ semi-recent ischemic strokes.
42
+ - source_sentence: Post-operative complications of extended left hepatectomy
43
+ sentences:
44
+ - The patient was referred to the Oncology Department for further management and
45
+ treatment. A multidisciplinary team approach would be used to develop an optimal
46
+ treatment strategy.
47
+ - However, on postoperative day 15, the patient was readmitted with symptoms of
48
+ abdominal pain, fevers, elevated total bilirubin, and leukocytosis. A CT scan
49
+ revealed the formation of a collection in the hepatic fossa and a dilated right
50
+ posterior bile duct, which prompted the placement of a drain.
51
+ - Post-operatively, the patient recovered well, and was discharged on the 7th post-operative
52
+ day without any complications. Follow-up assessments did not report any issues,
53
+ and the patient was advised to maintain ample rest and a nutritious diet with
54
+ frequent walkthroughs to avoid stress on the abdomen.
55
+ - source_sentence: moderate level of depression diagnosis
56
+ sentences:
57
+ - The right upper limb was examined and revealed a morphological variant of the
58
+ coracobrachialis muscle (CBM) that corresponded to the classical description,
59
+ originating from the apex of the coracoid process together with the short head
60
+ of the biceps brachii.
61
+ - The patient's symptoms are suggestive of depression. The Beck Depression Inventory
62
+ score was 24, indicating a moderate level of depression.
63
+ - The patient was admitted due to symptoms of Major Depressive Disorder (MDD) which
64
+ included restlessness, sleep problems, depressed mood, decreased social function,
65
+ and suicidal thoughts as reported by the patient.
66
+ datasets:
67
+ - abhinand/MedEmbed-training-triplets-v1
68
+ pipeline_tag: sentence-similarity
69
+ library_name: sentence-transformers
70
+ metrics:
71
+ - cosine_accuracy
72
+ model-index:
73
+ - name: SentenceTransformer based on Snowflake/snowflake-arctic-embed-l
74
+ results:
75
+ - task:
76
+ type: triplet
77
+ name: Triplet
78
+ dataset:
79
+ name: medembed triplets dev 300
80
+ type: medembed-triplets-dev-300
81
+ metrics:
82
+ - type: cosine_accuracy
83
+ value: 0.9599999785423279
84
+ name: Cosine Accuracy
85
+ ---
86
+
87
+ # SentenceTransformer based on Snowflake/snowflake-arctic-embed-l
88
+
89
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Snowflake/snowflake-arctic-embed-l](https://huggingface.co/Snowflake/snowflake-arctic-embed-l) on the [med_embed-training-triplets-v1](https://huggingface.co/datasets/abhinand/MedEmbed-training-triplets-v1) dataset. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
90
+
91
+ ## Model Details
92
+
93
+ ### Model Description
94
+ - **Model Type:** Sentence Transformer
95
+ - **Base model:** [Snowflake/snowflake-arctic-embed-l](https://huggingface.co/Snowflake/snowflake-arctic-embed-l) <!-- at revision d8fb21ca8d905d2832ee8b96c894d3298964346b -->
96
+ - **Maximum Sequence Length:** 512 tokens
97
+ - **Output Dimensionality:** 1024 dimensions
98
+ - **Similarity Function:** Cosine Similarity
99
+ - **Training Dataset:**
100
+ - [med_embed-training-triplets-v1](https://huggingface.co/datasets/abhinand/MedEmbed-training-triplets-v1)
101
+ <!-- - **Language:** Unknown -->
102
+ <!-- - **License:** Unknown -->
103
+
104
+ ### Model Sources
105
+
106
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
107
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
108
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
109
+
110
+ ### Full Model Architecture
111
+
112
+ ```
113
+ SentenceTransformer(
114
+ (0): Transformer({'max_seq_length': 512, 'do_lower_case': False, 'architecture': 'BertModel'})
115
+ (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
116
+ (2): Normalize()
117
+ )
118
+ ```
119
+
120
+ ## Usage
121
+
122
+ ### Direct Usage (Sentence Transformers)
123
+
124
+ First install the Sentence Transformers library:
125
+
126
+ ```bash
127
+ pip install -U sentence-transformers
128
+ ```
129
+
130
+ Then you can load this model and run inference.
131
+ ```python
132
+ from sentence_transformers import SentenceTransformer
133
+
134
+ # Download from the 🤗 Hub
135
+ model = SentenceTransformer("lion-ai/arctic-l-medembed")
136
+ # Run inference
137
+ queries = [
138
+ "moderate level of depression diagnosis",
139
+ ]
140
+ documents = [
141
+ "The patient's symptoms are suggestive of depression. The Beck Depression Inventory score was 24, indicating a moderate level of depression.",
142
+ 'The patient was admitted due to symptoms of Major Depressive Disorder (MDD) which included restlessness, sleep problems, depressed mood, decreased social function, and suicidal thoughts as reported by the patient.',
143
+ 'The right upper limb was examined and revealed a morphological variant of the coracobrachialis muscle (CBM) that corresponded to the classical description, originating from the apex of the coracoid process together with the short head of the biceps brachii.',
144
+ ]
145
+ query_embeddings = model.encode_query(queries)
146
+ document_embeddings = model.encode_document(documents)
147
+ print(query_embeddings.shape, document_embeddings.shape)
148
+ # [1, 1024] [3, 1024]
149
+
150
+ # Get the similarity scores for the embeddings
151
+ similarities = model.similarity(query_embeddings, document_embeddings)
152
+ print(similarities)
153
+ # tensor([[0.5307, 0.3000, 0.0426]])
154
+ ```
155
+
156
+ <!--
157
+ ### Direct Usage (Transformers)
158
+
159
+ <details><summary>Click to see the direct usage in Transformers</summary>
160
+
161
+ </details>
162
+ -->
163
+
164
+ <!--
165
+ ### Downstream Usage (Sentence Transformers)
166
+
167
+ You can finetune this model on your own dataset.
168
+
169
+ <details><summary>Click to expand</summary>
170
+
171
+ </details>
172
+ -->
173
+
174
+ <!--
175
+ ### Out-of-Scope Use
176
+
177
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
178
+ -->
179
+
180
+ ## Evaluation
181
+
182
+ ### Metrics
183
+
184
+ #### Triplet
185
+
186
+ * Dataset: `medembed-triplets-dev-300`
187
+ * Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
188
+
189
+ | Metric | Value |
190
+ |:--------------------|:---------|
191
+ | **cosine_accuracy** | **0.96** |
192
+
193
+ <!--
194
+ ## Bias, Risks and Limitations
195
+
196
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
197
+ -->
198
+
199
+ <!--
200
+ ### Recommendations
201
+
202
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
203
+ -->
204
+
205
+ ## Training Details
206
+
207
+ ### Training Dataset
208
+
209
+ #### med_embed-training-triplets-v1
210
+
211
+ * Dataset: [med_embed-training-triplets-v1](https://huggingface.co/datasets/abhinand/MedEmbed-training-triplets-v1) at [0b344f0](https://huggingface.co/datasets/abhinand/MedEmbed-training-triplets-v1/tree/0b344f0f578f1cf3435338dbc53a2bf3449d5c88)
212
+ * Size: 230,357 training samples
213
+ * Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
214
+ * Approximate statistics based on the first 1000 samples:
215
+ | | anchor | positive | negative |
216
+ |:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
217
+ | type | string | string | string |
218
+ | details | <ul><li>min: 5 tokens</li><li>mean: 11.84 tokens</li><li>max: 28 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 39.33 tokens</li><li>max: 216 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 40.03 tokens</li><li>max: 171 tokens</li></ul> |
219
+ * Samples:
220
+ | anchor | positive | negative |
221
+ |:------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
222
+ | <code>MTHFR homozygous A223V mutation symptoms</code> | <code>The patient was admitted to our institution where MTHFR homozygous A223V mutation was identified. Folic acid intake was increased to 800 mcg/d, and no other coagulation tests were abnormal.</code> | <code>The patient had several symptoms of MM, including hypercalcemia, bone fractures, anemia, and renal insufficiency. A biopsy showed atypical clonal plasma cells with Cluster of Differentiation (CD)138 positive infiltration.</code> |
223
+ | <code>Causes of spindle cell malignancy in the duodenal wall</code> | <code>Histological analysis revealed a spindle cell malignancy that was positive for CD21, CD23, and vimentin, but negative for CD20, CD34, CD35, CD117, DOG 1, and smooth muscle actin.</code> | <code>Based on immunohistochemical analysis of the tumor cells, the primary buttock tumor was diagnosed as a skeletal muscle metastasis of the primary small intestine gastrointestinal stromal tumor (GIST).</code> |
224
+ | <code>What was the patient's main complaint during hospital admission?</code> | <code>This 27-year-old pregnant woman was admitted to the hospital at 36 weeks gestation with acute vision loss in her left eye and severe onset headache.</code> | <code>The patient was discharged the next day</code> |
225
+ * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
226
+ ```json
227
+ {
228
+ "scale": 20.0,
229
+ "similarity_fct": "cos_sim",
230
+ "gather_across_devices": false
231
+ }
232
+ ```
233
+
234
+ ### Evaluation Dataset
235
+
236
+ #### med_embed-training-triplets-v1
237
+
238
+ * Dataset: [med_embed-training-triplets-v1](https://huggingface.co/datasets/abhinand/MedEmbed-training-triplets-v1) at [0b344f0](https://huggingface.co/datasets/abhinand/MedEmbed-training-triplets-v1/tree/0b344f0f578f1cf3435338dbc53a2bf3449d5c88)
239
+ * Size: 300 evaluation samples
240
+ * Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
241
+ * Approximate statistics based on the first 300 samples:
242
+ | | anchor | positive | negative |
243
+ |:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
244
+ | type | string | string | string |
245
+ | details | <ul><li>min: 4 tokens</li><li>mean: 11.88 tokens</li><li>max: 32 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 38.67 tokens</li><li>max: 127 tokens</li></ul> | <ul><li>min: 8 tokens</li><li>mean: 40.55 tokens</li><li>max: 108 tokens</li></ul> |
246
+ * Samples:
247
+ | anchor | positive | negative |
248
+ |:---------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
249
+ | <code>What was the initial presentation of the patient?</code> | <code>The 45-year-old female patient presented to the department with an enlarging lesion in her upper abdomen.</code> | <code>The patient was transferred to this hospital for further evaluation.</code> |
250
+ | <code>giant omphalocele symptoms</code> | <code>The patient, a 9-year-old female, presented to the hospital with a large lump in the anterior abdominal wall extending from the xiphisternum to the level of iliac crest.</code> | <code>The patient presented with bilateral nasovestibular lumps which grew in size over several months, occluding nasal entrance and protruding outside the nose.</code> |
251
+ | <code>granulomatous lymphocytic interstitial lung disease treatment</code> | <code>The patient had clubbing and chronic lung findings, and thorax CT revealed extended and severe bronchiectasis with thickened bronchial walls, some granulomatous nodules and mosaic appearance, compatible with granulomatous lymphocytic interstitial lung disease (GLILD). Regular intravenous immunoglobulin (IVIG) replacement was started.</code> | <code>The patient was treated with methylprednisolone pulse therapy followed by oral prednisolone (PSL) and cyclophosphamide intravenously. After treatment, arthralgia, renal function, proteinuria, and skin manifestations improved.</code> |
252
+ * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
253
+ ```json
254
+ {
255
+ "scale": 20.0,
256
+ "similarity_fct": "cos_sim",
257
+ "gather_across_devices": false
258
+ }
259
+ ```
260
+
261
+ ### Training Hyperparameters
262
+ #### Non-Default Hyperparameters
263
+
264
+ - `eval_strategy`: steps
265
+ - `per_device_train_batch_size`: 16
266
+ - `per_device_eval_batch_size`: 16
267
+ - `gradient_accumulation_steps`: 8
268
+ - `learning_rate`: 1e-05
269
+ - `weight_decay`: 0.01
270
+ - `num_train_epochs`: 2
271
+ - `warmup_ratio`: 0.1
272
+ - `dataloader_num_workers`: 4
273
+ - `load_best_model_at_end`: True
274
+ - `ddp_find_unused_parameters`: False
275
+ - `batch_sampler`: no_duplicates
276
+
277
+ #### All Hyperparameters
278
+ <details><summary>Click to expand</summary>
279
+
280
+ - `overwrite_output_dir`: False
281
+ - `do_predict`: False
282
+ - `eval_strategy`: steps
283
+ - `prediction_loss_only`: True
284
+ - `per_device_train_batch_size`: 16
285
+ - `per_device_eval_batch_size`: 16
286
+ - `per_gpu_train_batch_size`: None
287
+ - `per_gpu_eval_batch_size`: None
288
+ - `gradient_accumulation_steps`: 8
289
+ - `eval_accumulation_steps`: None
290
+ - `torch_empty_cache_steps`: None
291
+ - `learning_rate`: 1e-05
292
+ - `weight_decay`: 0.01
293
+ - `adam_beta1`: 0.9
294
+ - `adam_beta2`: 0.999
295
+ - `adam_epsilon`: 1e-08
296
+ - `max_grad_norm`: 1.0
297
+ - `num_train_epochs`: 2
298
+ - `max_steps`: -1
299
+ - `lr_scheduler_type`: linear
300
+ - `lr_scheduler_kwargs`: {}
301
+ - `warmup_ratio`: 0.1
302
+ - `warmup_steps`: 0
303
+ - `log_level`: passive
304
+ - `log_level_replica`: warning
305
+ - `log_on_each_node`: True
306
+ - `logging_nan_inf_filter`: True
307
+ - `save_safetensors`: True
308
+ - `save_on_each_node`: False
309
+ - `save_only_model`: False
310
+ - `restore_callback_states_from_checkpoint`: False
311
+ - `no_cuda`: False
312
+ - `use_cpu`: False
313
+ - `use_mps_device`: False
314
+ - `seed`: 42
315
+ - `data_seed`: None
316
+ - `jit_mode_eval`: False
317
+ - `bf16`: False
318
+ - `fp16`: False
319
+ - `fp16_opt_level`: O1
320
+ - `half_precision_backend`: auto
321
+ - `bf16_full_eval`: False
322
+ - `fp16_full_eval`: False
323
+ - `tf32`: None
324
+ - `local_rank`: 0
325
+ - `ddp_backend`: None
326
+ - `tpu_num_cores`: None
327
+ - `tpu_metrics_debug`: False
328
+ - `debug`: []
329
+ - `dataloader_drop_last`: False
330
+ - `dataloader_num_workers`: 4
331
+ - `dataloader_prefetch_factor`: None
332
+ - `past_index`: -1
333
+ - `disable_tqdm`: False
334
+ - `remove_unused_columns`: True
335
+ - `label_names`: None
336
+ - `load_best_model_at_end`: True
337
+ - `ignore_data_skip`: False
338
+ - `fsdp`: []
339
+ - `fsdp_min_num_params`: 0
340
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
341
+ - `fsdp_transformer_layer_cls_to_wrap`: None
342
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
343
+ - `parallelism_config`: None
344
+ - `deepspeed`: None
345
+ - `label_smoothing_factor`: 0.0
346
+ - `optim`: adamw_torch_fused
347
+ - `optim_args`: None
348
+ - `adafactor`: False
349
+ - `group_by_length`: False
350
+ - `length_column_name`: length
351
+ - `project`: huggingface
352
+ - `trackio_space_id`: trackio
353
+ - `ddp_find_unused_parameters`: False
354
+ - `ddp_bucket_cap_mb`: None
355
+ - `ddp_broadcast_buffers`: False
356
+ - `dataloader_pin_memory`: True
357
+ - `dataloader_persistent_workers`: False
358
+ - `skip_memory_metrics`: True
359
+ - `use_legacy_prediction_loop`: False
360
+ - `push_to_hub`: False
361
+ - `resume_from_checkpoint`: None
362
+ - `hub_model_id`: None
363
+ - `hub_strategy`: every_save
364
+ - `hub_private_repo`: None
365
+ - `hub_always_push`: False
366
+ - `hub_revision`: None
367
+ - `gradient_checkpointing`: False
368
+ - `gradient_checkpointing_kwargs`: None
369
+ - `include_inputs_for_metrics`: False
370
+ - `include_for_metrics`: []
371
+ - `eval_do_concat_batches`: True
372
+ - `fp16_backend`: auto
373
+ - `push_to_hub_model_id`: None
374
+ - `push_to_hub_organization`: None
375
+ - `mp_parameters`:
376
+ - `auto_find_batch_size`: False
377
+ - `full_determinism`: False
378
+ - `torchdynamo`: None
379
+ - `ray_scope`: last
380
+ - `ddp_timeout`: 1800
381
+ - `torch_compile`: False
382
+ - `torch_compile_backend`: None
383
+ - `torch_compile_mode`: None
384
+ - `include_tokens_per_second`: False
385
+ - `include_num_input_tokens_seen`: no
386
+ - `neftune_noise_alpha`: None
387
+ - `optim_target_modules`: None
388
+ - `batch_eval_metrics`: False
389
+ - `eval_on_start`: False
390
+ - `use_liger_kernel`: False
391
+ - `liger_kernel_config`: None
392
+ - `eval_use_gather_object`: False
393
+ - `average_tokens_across_devices`: True
394
+ - `prompts`: None
395
+ - `batch_sampler`: no_duplicates
396
+ - `multi_dataset_batch_sampler`: proportional
397
+ - `router_mapping`: {}
398
+ - `learning_rate_mapping`: {}
399
+
400
+ </details>
401
+
402
+ ### Training Logs
403
+ <details><summary>Click to expand</summary>
404
+
405
+ | Epoch | Step | Training Loss | Validation Loss | medembed-triplets-dev-300_cosine_accuracy |
406
+ |:----------:|:--------:|:-------------:|:---------------:|:-----------------------------------------:|
407
+ | -1 | -1 | - | - | 0.5767 |
408
+ | 0.0056 | 10 | 2.6703 | - | - |
409
+ | 0.0111 | 20 | 2.5114 | - | - |
410
+ | 0.0167 | 30 | 2.3725 | - | - |
411
+ | 0.0222 | 40 | 2.2162 | - | - |
412
+ | 0.0278 | 50 | 2.0325 | - | - |
413
+ | 0.0333 | 60 | 1.8674 | - | - |
414
+ | 0.0389 | 70 | 1.7283 | - | - |
415
+ | 0.0445 | 80 | 1.5936 | - | - |
416
+ | 0.0500 | 90 | 1.5153 | - | - |
417
+ | 0.0556 | 100 | 1.421 | 1.3269 | 0.6367 |
418
+ | 0.0611 | 110 | 1.3861 | - | - |
419
+ | 0.0667 | 120 | 1.2706 | - | - |
420
+ | 0.0722 | 130 | 1.286 | - | - |
421
+ | 0.0778 | 140 | 1.2037 | - | - |
422
+ | 0.0833 | 150 | 1.1301 | - | - |
423
+ | 0.0889 | 160 | 1.1587 | - | - |
424
+ | 0.0945 | 170 | 1.1741 | - | - |
425
+ | 0.1000 | 180 | 1.0915 | - | - |
426
+ | 0.1056 | 190 | 1.0786 | - | - |
427
+ | 0.1111 | 200 | 1.0518 | 1.0083 | 0.7767 |
428
+ | 0.1167 | 210 | 1.0562 | - | - |
429
+ | 0.1222 | 220 | 1.042 | - | - |
430
+ | 0.1278 | 230 | 0.9928 | - | - |
431
+ | 0.1334 | 240 | 1.022 | - | - |
432
+ | 0.1389 | 250 | 1.044 | - | - |
433
+ | 0.1445 | 260 | 0.9621 | - | - |
434
+ | 0.1500 | 270 | 0.98 | - | - |
435
+ | 0.1556 | 280 | 1.0073 | - | - |
436
+ | 0.1611 | 290 | 0.9346 | - | - |
437
+ | 0.1667 | 300 | 0.995 | 0.8794 | 0.8100 |
438
+ | 0.1722 | 310 | 0.9057 | - | - |
439
+ | 0.1778 | 320 | 1.0023 | - | - |
440
+ | 0.1834 | 330 | 0.8486 | - | - |
441
+ | 0.1889 | 340 | 0.8888 | - | - |
442
+ | 0.1945 | 350 | 0.9358 | - | - |
443
+ | 0.2000 | 360 | 0.8503 | - | - |
444
+ | 0.2056 | 370 | 0.9181 | - | - |
445
+ | 0.2111 | 380 | 0.8965 | - | - |
446
+ | 0.2167 | 390 | 0.8807 | - | - |
447
+ | 0.2223 | 400 | 0.8833 | 0.8012 | 0.8267 |
448
+ | 0.2278 | 410 | 0.8564 | - | - |
449
+ | 0.2334 | 420 | 0.838 | - | - |
450
+ | 0.2389 | 430 | 0.8775 | - | - |
451
+ | 0.2445 | 440 | 0.7808 | - | - |
452
+ | 0.2500 | 450 | 0.7795 | - | - |
453
+ | 0.2556 | 460 | 0.8087 | - | - |
454
+ | 0.2611 | 470 | 0.7418 | - | - |
455
+ | 0.2667 | 480 | 0.7921 | - | - |
456
+ | 0.2723 | 490 | 0.7526 | - | - |
457
+ | 0.2778 | 500 | 0.6838 | 0.7306 | 0.8567 |
458
+ | 0.2834 | 510 | 0.7908 | - | - |
459
+ | 0.2889 | 520 | 0.8013 | - | - |
460
+ | 0.2945 | 530 | 0.7176 | - | - |
461
+ | 0.3000 | 540 | 0.7432 | - | - |
462
+ | 0.3056 | 550 | 0.7148 | - | - |
463
+ | 0.3112 | 560 | 0.7034 | - | - |
464
+ | 0.3167 | 570 | 0.7405 | - | - |
465
+ | 0.3223 | 580 | 0.7185 | - | - |
466
+ | 0.3278 | 590 | 0.6609 | - | - |
467
+ | 0.3334 | 600 | 0.6246 | 0.6693 | 0.8767 |
468
+ | 0.3389 | 610 | 0.6743 | - | - |
469
+ | 0.3445 | 620 | 0.6826 | - | - |
470
+ | 0.3500 | 630 | 0.7143 | - | - |
471
+ | 0.3556 | 640 | 0.706 | - | - |
472
+ | 0.3612 | 650 | 0.6787 | - | - |
473
+ | 0.3667 | 660 | 0.6784 | - | - |
474
+ | 0.3723 | 670 | 0.6938 | - | - |
475
+ | 0.3778 | 680 | 0.6647 | - | - |
476
+ | 0.3834 | 690 | 0.6732 | - | - |
477
+ | 0.3889 | 700 | 0.6409 | 0.6291 | 0.9033 |
478
+ | 0.3945 | 710 | 0.6773 | - | - |
479
+ | 0.4001 | 720 | 0.6767 | - | - |
480
+ | 0.4056 | 730 | 0.6656 | - | - |
481
+ | 0.4112 | 740 | 0.6423 | - | - |
482
+ | 0.4167 | 750 | 0.6341 | - | - |
483
+ | 0.4223 | 760 | 0.6369 | - | - |
484
+ | 0.4278 | 770 | 0.5883 | - | - |
485
+ | 0.4334 | 780 | 0.6497 | - | - |
486
+ | 0.4389 | 790 | 0.6106 | - | - |
487
+ | 0.4445 | 800 | 0.6423 | 0.5550 | 0.9067 |
488
+ | 0.4501 | 810 | 0.6054 | - | - |
489
+ | 0.4556 | 820 | 0.6238 | - | - |
490
+ | 0.4612 | 830 | 0.5986 | - | - |
491
+ | 0.4667 | 840 | 0.6196 | - | - |
492
+ | 0.4723 | 850 | 0.5767 | - | - |
493
+ | 0.4778 | 860 | 0.6286 | - | - |
494
+ | 0.4834 | 870 | 0.587 | - | - |
495
+ | 0.4890 | 880 | 0.5661 | - | - |
496
+ | 0.4945 | 890 | 0.51 | - | - |
497
+ | 0.5001 | 900 | 0.6048 | 0.5459 | 0.9167 |
498
+ | 0.5056 | 910 | 0.5621 | - | - |
499
+ | 0.5112 | 920 | 0.5954 | - | - |
500
+ | 0.5167 | 930 | 0.5542 | - | - |
501
+ | 0.5223 | 940 | 0.5846 | - | - |
502
+ | 0.5279 | 950 | 0.5864 | - | - |
503
+ | 0.5334 | 960 | 0.6152 | - | - |
504
+ | 0.5390 | 970 | 0.5696 | - | - |
505
+ | 0.5445 | 980 | 0.5639 | - | - |
506
+ | 0.5501 | 990 | 0.555 | - | - |
507
+ | 0.5556 | 1000 | 0.5465 | 0.4860 | 0.9200 |
508
+ | 0.5612 | 1010 | 0.5618 | - | - |
509
+ | 0.5667 | 1020 | 0.5228 | - | - |
510
+ | 0.5723 | 1030 | 0.5117 | - | - |
511
+ | 0.5779 | 1040 | 0.5305 | - | - |
512
+ | 0.5834 | 1050 | 0.5048 | - | - |
513
+ | 0.5890 | 1060 | 0.5261 | - | - |
514
+ | 0.5945 | 1070 | 0.4963 | - | - |
515
+ | 0.6001 | 1080 | 0.5034 | - | - |
516
+ | 0.6056 | 1090 | 0.4615 | - | - |
517
+ | 0.6112 | 1100 | 0.5192 | 0.4642 | 0.9267 |
518
+ | 0.6168 | 1110 | 0.5226 | - | - |
519
+ | 0.6223 | 1120 | 0.5417 | - | - |
520
+ | 0.6279 | 1130 | 0.5214 | - | - |
521
+ | 0.6334 | 1140 | 0.5256 | - | - |
522
+ | 0.6390 | 1150 | 0.5327 | - | - |
523
+ | 0.6445 | 1160 | 0.5413 | - | - |
524
+ | 0.6501 | 1170 | 0.5261 | - | - |
525
+ | 0.6556 | 1180 | 0.4876 | - | - |
526
+ | 0.6612 | 1190 | 0.4694 | - | - |
527
+ | 0.6668 | 1200 | 0.4795 | 0.4229 | 0.9500 |
528
+ | 0.6723 | 1210 | 0.4896 | - | - |
529
+ | 0.6779 | 1220 | 0.4796 | - | - |
530
+ | 0.6834 | 1230 | 0.4732 | - | - |
531
+ | 0.6890 | 1240 | 0.486 | - | - |
532
+ | 0.6945 | 1250 | 0.4942 | - | - |
533
+ | 0.7001 | 1260 | 0.4403 | - | - |
534
+ | 0.7057 | 1270 | 0.4581 | - | - |
535
+ | 0.7112 | 1280 | 0.4494 | - | - |
536
+ | 0.7168 | 1290 | 0.4676 | - | - |
537
+ | 0.7223 | 1300 | 0.4575 | 0.4201 | 0.9500 |
538
+ | 0.7279 | 1310 | 0.4395 | - | - |
539
+ | 0.7334 | 1320 | 0.4197 | - | - |
540
+ | 0.7390 | 1330 | 0.4471 | - | - |
541
+ | 0.7445 | 1340 | 0.4724 | - | - |
542
+ | 0.7501 | 1350 | 0.43 | - | - |
543
+ | 0.7557 | 1360 | 0.4691 | - | - |
544
+ | 0.7612 | 1370 | 0.425 | - | - |
545
+ | 0.7668 | 1380 | 0.4244 | - | - |
546
+ | 0.7723 | 1390 | 0.417 | - | - |
547
+ | 0.7779 | 1400 | 0.4398 | 0.3899 | 0.9467 |
548
+ | 0.7834 | 1410 | 0.452 | - | - |
549
+ | 0.7890 | 1420 | 0.476 | - | - |
550
+ | 0.7946 | 1430 | 0.4433 | - | - |
551
+ | 0.8001 | 1440 | 0.4021 | - | - |
552
+ | 0.8057 | 1450 | 0.461 | - | - |
553
+ | 0.8112 | 1460 | 0.4191 | - | - |
554
+ | 0.8168 | 1470 | 0.4068 | - | - |
555
+ | 0.8223 | 1480 | 0.4274 | - | - |
556
+ | 0.8279 | 1490 | 0.4238 | - | - |
557
+ | 0.8334 | 1500 | 0.4403 | 0.3585 | 0.9433 |
558
+ | 0.8390 | 1510 | 0.3875 | - | - |
559
+ | 0.8446 | 1520 | 0.4004 | - | - |
560
+ | 0.8501 | 1530 | 0.4194 | - | - |
561
+ | 0.8557 | 1540 | 0.3883 | - | - |
562
+ | 0.8612 | 1550 | 0.3861 | - | - |
563
+ | 0.8668 | 1560 | 0.4131 | - | - |
564
+ | 0.8723 | 1570 | 0.4006 | - | - |
565
+ | 0.8779 | 1580 | 0.4195 | - | - |
566
+ | 0.8835 | 1590 | 0.4144 | - | - |
567
+ | 0.8890 | 1600 | 0.4454 | 0.3131 | 0.9533 |
568
+ | 0.8946 | 1610 | 0.3751 | - | - |
569
+ | 0.9001 | 1620 | 0.3655 | - | - |
570
+ | 0.9057 | 1630 | 0.3875 | - | - |
571
+ | 0.9112 | 1640 | 0.3922 | - | - |
572
+ | 0.9168 | 1650 | 0.4043 | - | - |
573
+ | 0.9224 | 1660 | 0.3686 | - | - |
574
+ | 0.9279 | 1670 | 0.3745 | - | - |
575
+ | 0.9335 | 1680 | 0.3681 | - | - |
576
+ | 0.9390 | 1690 | 0.3858 | - | - |
577
+ | 0.9446 | 1700 | 0.3817 | 0.3126 | 0.9533 |
578
+ | 0.9501 | 1710 | 0.3787 | - | - |
579
+ | 0.9557 | 1720 | 0.3849 | - | - |
580
+ | 0.9612 | 1730 | 0.352 | - | - |
581
+ | 0.9668 | 1740 | 0.3549 | - | - |
582
+ | 0.9724 | 1750 | 0.3634 | - | - |
583
+ | 0.9779 | 1760 | 0.3548 | - | - |
584
+ | 0.9835 | 1770 | 0.3662 | - | - |
585
+ | 0.9890 | 1780 | 0.3915 | - | - |
586
+ | 0.9946 | 1790 | 0.3713 | - | - |
587
+ | 1.0 | 1800 | 0.3647 | 0.3077 | 0.9533 |
588
+ | 1.0056 | 1810 | 0.3365 | - | - |
589
+ | 1.0111 | 1820 | 0.3084 | - | - |
590
+ | 1.0167 | 1830 | 0.3261 | - | - |
591
+ | 1.0222 | 1840 | 0.3036 | - | - |
592
+ | 1.0278 | 1850 | 0.3054 | - | - |
593
+ | 1.0333 | 1860 | 0.3384 | - | - |
594
+ | 1.0389 | 1870 | 0.3129 | - | - |
595
+ | 1.0445 | 1880 | 0.3092 | - | - |
596
+ | 1.0500 | 1890 | 0.3043 | - | - |
597
+ | 1.0556 | 1900 | 0.2904 | 0.3005 | 0.9533 |
598
+ | 1.0611 | 1910 | 0.2917 | - | - |
599
+ | 1.0667 | 1920 | 0.3196 | - | - |
600
+ | 1.0722 | 1930 | 0.3401 | - | - |
601
+ | 1.0778 | 1940 | 0.312 | - | - |
602
+ | 1.0833 | 1950 | 0.321 | - | - |
603
+ | 1.0889 | 1960 | 0.3052 | - | - |
604
+ | 1.0945 | 1970 | 0.3136 | - | - |
605
+ | 1.1000 | 1980 | 0.3243 | - | - |
606
+ | 1.1056 | 1990 | 0.2843 | - | - |
607
+ | 1.1111 | 2000 | 0.2994 | 0.2905 | 0.9533 |
608
+ | 1.1167 | 2010 | 0.3144 | - | - |
609
+ | 1.1222 | 2020 | 0.3029 | - | - |
610
+ | 1.1278 | 2030 | 0.3085 | - | - |
611
+ | 1.1334 | 2040 | 0.3053 | - | - |
612
+ | 1.1389 | 2050 | 0.3009 | - | - |
613
+ | 1.1445 | 2060 | 0.3083 | - | - |
614
+ | 1.1500 | 2070 | 0.2993 | - | - |
615
+ | 1.1556 | 2080 | 0.2932 | - | - |
616
+ | 1.1611 | 2090 | 0.2994 | - | - |
617
+ | 1.1667 | 2100 | 0.2796 | 0.2704 | 0.9467 |
618
+ | 1.1722 | 2110 | 0.3033 | - | - |
619
+ | 1.1778 | 2120 | 0.3083 | - | - |
620
+ | 1.1834 | 2130 | 0.3118 | - | - |
621
+ | 1.1889 | 2140 | 0.2978 | - | - |
622
+ | 1.1945 | 2150 | 0.2697 | - | - |
623
+ | 1.2000 | 2160 | 0.2918 | - | - |
624
+ | 1.2056 | 2170 | 0.2814 | - | - |
625
+ | 1.2111 | 2180 | 0.2615 | - | - |
626
+ | 1.2167 | 2190 | 0.289 | - | - |
627
+ | 1.2223 | 2200 | 0.2819 | 0.2454 | 0.9533 |
628
+ | 1.2278 | 2210 | 0.2751 | - | - |
629
+ | 1.2334 | 2220 | 0.3228 | - | - |
630
+ | 1.2389 | 2230 | 0.2852 | - | - |
631
+ | 1.2445 | 2240 | 0.2909 | - | - |
632
+ | 1.2500 | 2250 | 0.285 | - | - |
633
+ | 1.2556 | 2260 | 0.2936 | - | - |
634
+ | 1.2611 | 2270 | 0.3052 | - | - |
635
+ | 1.2667 | 2280 | 0.2874 | - | - |
636
+ | 1.2723 | 2290 | 0.3008 | - | - |
637
+ | 1.2778 | 2300 | 0.3161 | 0.2529 | 0.9567 |
638
+ | 1.2834 | 2310 | 0.2764 | - | - |
639
+ | 1.2889 | 2320 | 0.2779 | - | - |
640
+ | 1.2945 | 2330 | 0.2547 | - | - |
641
+ | 1.3000 | 2340 | 0.2645 | - | - |
642
+ | 1.3056 | 2350 | 0.3015 | - | - |
643
+ | 1.3112 | 2360 | 0.2835 | - | - |
644
+ | 1.3167 | 2370 | 0.279 | - | - |
645
+ | 1.3223 | 2380 | 0.3158 | - | - |
646
+ | 1.3278 | 2390 | 0.2933 | - | - |
647
+ | 1.3334 | 2400 | 0.2791 | 0.2412 | 0.9567 |
648
+ | 1.3389 | 2410 | 0.2783 | - | - |
649
+ | 1.3445 | 2420 | 0.2533 | - | - |
650
+ | 1.3500 | 2430 | 0.2943 | - | - |
651
+ | 1.3556 | 2440 | 0.2808 | - | - |
652
+ | 1.3612 | 2450 | 0.2828 | - | - |
653
+ | 1.3667 | 2460 | 0.2789 | - | - |
654
+ | 1.3723 | 2470 | 0.2814 | - | - |
655
+ | 1.3778 | 2480 | 0.2675 | - | - |
656
+ | 1.3834 | 2490 | 0.2746 | - | - |
657
+ | 1.3889 | 2500 | 0.2907 | 0.2419 | 0.9567 |
658
+ | 1.3945 | 2510 | 0.278 | - | - |
659
+ | 1.4001 | 2520 | 0.2594 | - | - |
660
+ | 1.4056 | 2530 | 0.2659 | - | - |
661
+ | 1.4112 | 2540 | 0.2859 | - | - |
662
+ | 1.4167 | 2550 | 0.2755 | - | - |
663
+ | 1.4223 | 2560 | 0.2834 | - | - |
664
+ | 1.4278 | 2570 | 0.26 | - | - |
665
+ | 1.4334 | 2580 | 0.2693 | - | - |
666
+ | 1.4389 | 2590 | 0.2678 | - | - |
667
+ | **1.4445** | **2600** | **0.2624** | **0.2236** | **0.96** |
668
+ | 1.4501 | 2610 | 0.257 | - | - |
669
+ | 1.4556 | 2620 | 0.2876 | - | - |
670
+ | 1.4612 | 2630 | 0.2263 | - | - |
671
+ | 1.4667 | 2640 | 0.2508 | - | - |
672
+ | 1.4723 | 2650 | 0.2446 | - | - |
673
+ | 1.4778 | 2660 | 0.2532 | - | - |
674
+ | 1.4834 | 2670 | 0.2383 | - | - |
675
+ | 1.4890 | 2680 | 0.2441 | - | - |
676
+ | 1.4945 | 2690 | 0.241 | - | - |
677
+ | 1.5001 | 2700 | 0.2594 | 0.2242 | 0.9567 |
678
+ | 1.5056 | 2710 | 0.2463 | - | - |
679
+ | 1.5112 | 2720 | 0.2797 | - | - |
680
+ | 1.5167 | 2730 | 0.2419 | - | - |
681
+ | 1.5223 | 2740 | 0.2933 | - | - |
682
+ | 1.5279 | 2750 | 0.2724 | - | - |
683
+ | 1.5334 | 2760 | 0.2434 | - | - |
684
+ | 1.5390 | 2770 | 0.2635 | - | - |
685
+ | 1.5445 | 2780 | 0.2317 | - | - |
686
+ | 1.5501 | 2790 | 0.2698 | - | - |
687
+ | 1.5556 | 2800 | 0.2645 | 0.2309 | 0.9567 |
688
+ | 1.5612 | 2810 | 0.2585 | - | - |
689
+ | 1.5667 | 2820 | 0.2456 | - | - |
690
+ | 1.5723 | 2830 | 0.2211 | - | - |
691
+ | 1.5779 | 2840 | 0.2547 | - | - |
692
+ | 1.5834 | 2850 | 0.2673 | - | - |
693
+ | 1.5890 | 2860 | 0.2569 | - | - |
694
+ | 1.5945 | 2870 | 0.2477 | - | - |
695
+ | 1.6001 | 2880 | 0.2277 | - | - |
696
+ | 1.6056 | 2890 | 0.223 | - | - |
697
+ | 1.6112 | 2900 | 0.2415 | 0.2254 | 0.9600 |
698
+ | 1.6168 | 2910 | 0.2412 | - | - |
699
+ | 1.6223 | 2920 | 0.2564 | - | - |
700
+ | 1.6279 | 2930 | 0.2735 | - | - |
701
+ | 1.6334 | 2940 | 0.2589 | - | - |
702
+ | 1.6390 | 2950 | 0.2678 | - | - |
703
+ | 1.6445 | 2960 | 0.2549 | - | - |
704
+ | 1.6501 | 2970 | 0.227 | - | - |
705
+ | 1.6556 | 2980 | 0.2598 | - | - |
706
+ | 1.6612 | 2990 | 0.2593 | - | - |
707
+ | 1.6668 | 3000 | 0.2248 | 0.2247 | 0.9533 |
708
+ | 1.6723 | 3010 | 0.2432 | - | - |
709
+ | 1.6779 | 3020 | 0.2469 | - | - |
710
+ | 1.6834 | 3030 | 0.2394 | - | - |
711
+ | 1.6890 | 3040 | 0.2525 | - | - |
712
+ | 1.6945 | 3050 | 0.2436 | - | - |
713
+ | 1.7001 | 3060 | 0.2247 | - | - |
714
+ | 1.7057 | 3070 | 0.2564 | - | - |
715
+ | 1.7112 | 3080 | 0.2267 | - | - |
716
+ | 1.7168 | 3090 | 0.2667 | - | - |
717
+ | 1.7223 | 3100 | 0.2365 | 0.2198 | 0.9600 |
718
+ | 1.7279 | 3110 | 0.2354 | - | - |
719
+ | 1.7334 | 3120 | 0.2396 | - | - |
720
+ | 1.7390 | 3130 | 0.2357 | - | - |
721
+ | 1.7445 | 3140 | 0.2397 | - | - |
722
+ | 1.7501 | 3150 | 0.2371 | - | - |
723
+ | 1.7557 | 3160 | 0.2508 | - | - |
724
+ | 1.7612 | 3170 | 0.2247 | - | - |
725
+ | 1.7668 | 3180 | 0.2561 | - | - |
726
+ | 1.7723 | 3190 | 0.2309 | - | - |
727
+ | 1.7779 | 3200 | 0.2275 | 0.2126 | 0.9567 |
728
+ | 1.7834 | 3210 | 0.2234 | - | - |
729
+ | 1.7890 | 3220 | 0.2332 | - | - |
730
+ | 1.7946 | 3230 | 0.2611 | - | - |
731
+ | 1.8001 | 3240 | 0.2227 | - | - |
732
+ | 1.8057 | 3250 | 0.2582 | - | - |
733
+ | 1.8112 | 3260 | 0.2574 | - | - |
734
+ | 1.8168 | 3270 | 0.2144 | - | - |
735
+ | 1.8223 | 3280 | 0.2353 | - | - |
736
+ | 1.8279 | 3290 | 0.241 | - | - |
737
+ | 1.8334 | 3300 | 0.2406 | 0.2087 | 0.9567 |
738
+ | 1.8390 | 3310 | 0.2536 | - | - |
739
+ | 1.8446 | 3320 | 0.2579 | - | - |
740
+ | 1.8501 | 3330 | 0.2273 | - | - |
741
+ | 1.8557 | 3340 | 0.2662 | - | - |
742
+ | 1.8612 | 3350 | 0.2356 | - | - |
743
+ | 1.8668 | 3360 | 0.2177 | - | - |
744
+ | 1.8723 | 3370 | 0.2268 | - | - |
745
+ | 1.8779 | 3380 | 0.2337 | - | - |
746
+ | 1.8835 | 3390 | 0.2686 | - | - |
747
+ | 1.8890 | 3400 | 0.2239 | 0.2087 | 0.9567 |
748
+ | 1.8946 | 3410 | 0.2559 | - | - |
749
+ | 1.9001 | 3420 | 0.2135 | - | - |
750
+ | 1.9057 | 3430 | 0.2456 | - | - |
751
+ | 1.9112 | 3440 | 0.2461 | - | - |
752
+ | 1.9168 | 3450 | 0.2349 | - | - |
753
+ | 1.9224 | 3460 | 0.2227 | - | - |
754
+ | 1.9279 | 3470 | 0.2443 | - | - |
755
+ | 1.9335 | 3480 | 0.2425 | - | - |
756
+ | 1.9390 | 3490 | 0.2427 | - | - |
757
+ | 1.9446 | 3500 | 0.2469 | 0.2081 | 0.9600 |
758
+ | 1.9501 | 3510 | 0.2504 | - | - |
759
+ | 1.9557 | 3520 | 0.2518 | - | - |
760
+ | 1.9612 | 3530 | 0.2241 | - | - |
761
+ | 1.9668 | 3540 | 0.241 | - | - |
762
+ | 1.9724 | 3550 | 0.2204 | - | - |
763
+ | 1.9779 | 3560 | 0.2558 | - | - |
764
+ | 1.9835 | 3570 | 0.2109 | - | - |
765
+ | 1.9890 | 3580 | 0.2067 | - | - |
766
+ | 1.9946 | 3590 | 0.2556 | - | - |
767
+ | 2.0 | 3600 | 0.2603 | 0.2081 | 0.9600 |
768
+
769
+ * The bold row denotes the saved checkpoint.
770
+ </details>
771
+
772
+ ### Framework Versions
773
+ - Python: 3.12.7
774
+ - Sentence Transformers: 5.1.1
775
+ - Transformers: 4.57.1
776
+ - PyTorch: 2.9.0+cu128
777
+ - Accelerate: 1.10.1
778
+ - Datasets: 3.6.0
779
+ - Tokenizers: 0.22.1
780
+
781
+ ## Citation
782
+
783
+ ### BibTeX
784
+
785
+ #### Sentence Transformers
786
+ ```bibtex
787
+ @inproceedings{reimers-2019-sentence-bert,
788
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
789
+ author = "Reimers, Nils and Gurevych, Iryna",
790
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
791
+ month = "11",
792
+ year = "2019",
793
+ publisher = "Association for Computational Linguistics",
794
+ url = "https://arxiv.org/abs/1908.10084",
795
+ }
796
+ ```
797
+
798
+ #### MultipleNegativesRankingLoss
799
+ ```bibtex
800
+ @misc{henderson2017efficient,
801
+ title={Efficient Natural Language Response Suggestion for Smart Reply},
802
+ author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
803
+ year={2017},
804
+ eprint={1705.00652},
805
+ archivePrefix={arXiv},
806
+ primaryClass={cs.CL}
807
+ }
808
+ ```
809
+
810
+ <!--
811
+ ## Glossary
812
+
813
+ *Clearly define terms in order to be accessible across audiences.*
814
+ -->
815
+
816
+ <!--
817
+ ## Model Card Authors
818
+
819
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
820
+ -->
821
+
822
+ <!--
823
+ ## Model Card Contact
824
+
825
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
826
+ -->
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertModel"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 1024,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 4096,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 24,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "transformers_version": "4.57.1",
21
+ "type_vocab_size": 2,
22
+ "use_cache": true,
23
+ "vocab_size": 30522
24
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "5.1.1",
4
+ "transformers": "4.57.1",
5
+ "pytorch": "2.9.0+cu128"
6
+ },
7
+ "prompts": {
8
+ "query": "Represent this sentence for searching relevant passages: ",
9
+ "document": ""
10
+ },
11
+ "default_prompt_name": null,
12
+ "model_type": "SentenceTransformer",
13
+ "similarity_fn_name": "cosine"
14
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cff1ad617c3f89000b2732b7436282159a81fca6bff68775463cc919ba809c4c
3
+ size 1340612432
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": 512,
3
+ "do_lower_case": false
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "max_length": 512,
50
+ "model_max_length": 512,
51
+ "pad_to_multiple_of": null,
52
+ "pad_token": "[PAD]",
53
+ "pad_token_type_id": 0,
54
+ "padding_side": "right",
55
+ "sep_token": "[SEP]",
56
+ "stride": 0,
57
+ "strip_accents": null,
58
+ "tokenize_chinese_chars": true,
59
+ "tokenizer_class": "BertTokenizer",
60
+ "truncation_side": "right",
61
+ "truncation_strategy": "longest_first",
62
+ "unk_token": "[UNK]"
63
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff