rajatrc1705 commited on
Commit
1663fca
1 Parent(s): 6c65f0a

model at final check point

Browse files
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 384,
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
+ }
1_Pooling/config.json:Zone.Identifier ADDED
File without changes
README.md CHANGED
@@ -1 +1,750 @@
1
- hello
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: BAAI/bge-small-en
3
+ datasets:
4
+ - sentence-transformers/hotpotqa
5
+ language:
6
+ - en
7
+ library_name: sentence-transformers
8
+ license: apache-2.0
9
+ metrics:
10
+ - cosine_accuracy
11
+ - dot_accuracy
12
+ - manhattan_accuracy
13
+ - euclidean_accuracy
14
+ - max_accuracy
15
+ pipeline_tag: sentence-similarity
16
+ tags:
17
+ - sentence-transformers
18
+ - sentence-similarity
19
+ - feature-extraction
20
+ - generated_from_trainer
21
+ - dataset_size:76064
22
+ - loss:MatryoshkaLoss
23
+ - loss:TripletLoss
24
+ widget:
25
+ - source_sentence: When was the brewery founded by the family who resided in the Lemp
26
+ Mansion founded?
27
+ sentences:
28
+ - Latrobe Brewing Company Latrobe Brewing Company in Latrobe, Pennsylvania, founded
29
+ in 1839, was one of the largest breweries in the United States and the maker of
30
+ "Rolling Rock" beer (famous for its small green bottles). It was purchased by
31
+ Labatt Brewing Company in 1987, which in turn was purchased in 1995 by the Belgian
32
+ brewing conglomerate corporation Interbrew, which merged later into InBev in 2004.
33
+ - Lemp Mansion The Lemp Mansion (3322 DeMenil Place, St. Louis, Missouri) is a historical
34
+ house in Benton Park, St. Louis, Missouri. It is also the site of four suicides
35
+ by Lemp family members after the death of the son Frederick Lemp, whose William
36
+ J. Lemp Brewing Co. dominated the St. Louis beer market before Prohibition with
37
+ its Falstaff beer brand. The mansion is said to be haunted by members of the Lemp
38
+ family.
39
+ - 'Man of the House (song) "Man of the House" is a song co-written and recorded
40
+ by American country music artist Chuck Wicks. It was released in January 2009
41
+ as the third single from the album "Starting Now". The song reached #27 on the
42
+ "Billboard" Hot Country Songs chart. The song was written by Wicks and Michael
43
+ Mobley.'
44
+ - source_sentence: Who is the translator and researcher who served as a dean at Hartford
45
+ Junior College and translated her Belgian-French partner's 1968 work into English?
46
+ sentences:
47
+ - William L. Shirer William Lawrence Shirer (February 23, 1904 – December 28, 1993)
48
+ was an American journalist and war correspondent. He wrote "The Rise and Fall
49
+ of the Third Reich", a history of Nazi Germany that has been read by many and
50
+ cited in scholarly works for more than 50 years. Originally a foreign correspondent
51
+ for the "Chicago Tribune" and the International News Service, Shirer was the first
52
+ reporter hired by Edward R. Murrow for what would become a CBS radio team of journalists
53
+ known as "Murrow's Boys". He became known for his broadcasts from Berlin, from
54
+ the rise of the Nazi dictatorship through the first year of World War II (1940).
55
+ With Murrow, he organized the first broadcast world news roundup, a format still
56
+ followed by news broadcasts.
57
+ - 'The Abyss (Yourcenar novel) The Abyss (French: L''Œuvre au noir ) is a 1968 novel
58
+ by the Belgian-French writer Marguerite Yourcenar. Its narrative centers on the
59
+ life and death of Zeno, a physician, philosopher, scientist and alchemist born
60
+ in Bruges during the Renaissance era. The book was published in France in 1968
61
+ and was met with immediate popular interest as well as critical acclaim, obtaining
62
+ the Prix Femina with unanimous votes the year of its publication. The English
63
+ translation by Grace Frick has been published under the title "The Abyss" or alternatively
64
+ Zeno of Bruges. Belgian filmmaker André Delvaux adapted it into a film in 1988.'
65
+ - Pierre L. van den Berghe Pierre L. van den Berghe (born 1933) is professor emeritus
66
+ of sociology and anthropology at the University of Washington, where he has worked
67
+ since 1965. Born in the Belgian Congo to Belgian parents, and spending World War
68
+ II in occupied Belgium, he was an early witness to ethnic conflict and racism,
69
+ which eventually led him to become a leading authority on ethnic relations. He
70
+ has conducted field work in South Africa, Mexico, Guatemala, Iran, Lebanon, Nigeria,
71
+ Peru, and Israel. Early in his career, he lectured at the University of Natal
72
+ alongside Leo Kuper and Fatima Meer. A student of Talcott Parsons at Harvard (receiving
73
+ the Ph.D. in 1960), he nevertheless had little interest in structural functionalism
74
+ and was one of the first proponents of sociobiological approaches to social phenomena.
75
+ - source_sentence: Them Crooked Vultures and The Vines are both part of what music
76
+ genres?
77
+ sentences:
78
+ - Friendly Center Friendly Center is a large, open-air shopping center located in
79
+ northwestern Greensboro, North Carolina, near the intersection of Wendover Avenue
80
+ and Friendly Avenue. The shopping center opened in August 1957, and with its inward
81
+ orientation, Friendly Center could be classified as an outdoor lifestyle center.
82
+ Its anchor tenants include Belk, Macy's, and Sears. Other tenants include Barnes
83
+ & Noble, Old Navy, The Grande Theatre is a 16-screen multiplex cinema operated
84
+ by Regal Cinemas. It also contains Harris Teeter's flagship supermarket location
85
+ encompassing 72,000 square feet (6,700 m2) and Whole Foods Market. There are specialty
86
+ "foodie" stores tucked away in the back corner by Harris Teeter such as the Savory
87
+ Spice Shop and Midtown Olive Oil. It features a number of national retailers such
88
+ as Banana Republic, Victoria's Secret, The Limited, Bath & Body Works, Express,
89
+ The GAP, Eddie Bauer, Talbots, Birkenstock Feet First, Pier 1, and New York &
90
+ Company.
91
+ - Twin Wild Twin Wild is a British four-piece alternative rock band. Formed in 2012,
92
+ the band is made up of the collective creative energies of Richard Hutchison (vocals,
93
+ guitars), Imran Mair (drums), David Cuzner (guitars) and Edward Thomas (bass).
94
+ In 2014, the band self-released their track "Fears", which garnered over half
95
+ a million plays on Soundcloud and charted in Spotify’s Top 20 viral chart. Their
96
+ style of music has been compared to the likes of Foals, The Neighbourhood, and
97
+ Bastille. The band have been hailed by Edith Bowman as "The love child of Bastille
98
+ and Biffy Clyro".
99
+ - Them Crooked Vultures Them Crooked Vultures is a rock supergroup formed in Los
100
+ Angeles in 2009 by John Paul Jones (former member of Led Zeppelin) on bass and
101
+ keyboards, Dave Grohl (of Foo Fighters and formerly of Nirvana) on drums and backing
102
+ vocals, and Josh Homme (of Queens of the Stone Age, Eagles of Death Metal and
103
+ formerly of Kyuss) on guitar and vocals. The group also includes guitarist Alain
104
+ Johannes during live performances. The band began recording in February 2009,
105
+ and performed their first gig on August 9, 2009, in Chicago, followed by a European
106
+ debut on August 19. On October 1 the group embarked on a worldwide tour titled
107
+ "Deserve the Future" with dates going into 2010. The band's first single "New
108
+ Fang" was released in October 2009, followed by the group's self-titled debut
109
+ album the following month, debuting at number 12 on the "Billboard" 200. The group
110
+ won the 2011 Grammy Award for Best Hard Rock Performance for "New Fang".
111
+ - source_sentence: What type of collection does Nådens år and Agnetha Fältskog have
112
+ in common?
113
+ sentences:
114
+ - Gardiner Island (Nunavut) Gardiner Island is one of the many uninhabited Canadian
115
+ arctic islands in Qikiqtaaluk Region, Nunavut. It is a Baffin Island offshore
116
+ island located in Frobisher Bay south of the capital city of Iqaluit.
117
+ - Nådens år Nådens år (The Year of Grace) is the third studio album by the Swedish
118
+ rock artist Ulf Lundell. It was released in April 1978 on EMI and Parlophone.
119
+ It was recorded in EMI Studio, Stockholm, and produced by Kjell Andersson and
120
+ Lundell. It includes "Snön faller och vi med den" ("The snow is falling and we
121
+ are too"), one of Lundell's more famous songs. Agnetha Fältskog is involved in
122
+ the song. The cover picture shows Lundell sitting on a rock next to a dog and
123
+ was taken in Åre in 1977. "Nådens år" achieved Gold status in Sweden.
124
+ - Åsa Elzén Åsa Elzén is an artist whose work is informed by feminist theory, intersectionality
125
+ and post-colonialism. Elzén was born in Sweden in 1972 and currently lives and
126
+ works in Berlin.
127
+ - source_sentence: Red Velvet is a 2012 play by Lolita Chakrabarti, dealing with the
128
+ biography of a 19th century actor born in which year ?
129
+ sentences:
130
+ - Herbert Campbell Herbert Campbell (22 December 1844 – 19 July 1904) born Herbert
131
+ Edward Story was an English comedian and actor who appeared in music hall, Victorian
132
+ burlesques and musical comedies during the Victorian era. He was famous for starring,
133
+ for forty years, in the Theatre Royal, Drury Lane's annual Christmas pantomimes,
134
+ predominantly as a dame.
135
+ - Leptinella Leptinella is a genus of alpine flowering plant in the Asteraceae family,
136
+ comprising 33 species, distributed in New Guinea, Australia, New Zealand, South
137
+ Africa, and South America. Many of the species are endemic to New Zealand.
138
+ - Red Velvet (play) Red Velvet is a 2012 play by Lolita Chakrabarti, dealing with
139
+ the biography of the 19th century actor Ira Aldridge and his taking the role of
140
+ "Othello". It premiered at the Tricycle Theatre (directed by its new artistic
141
+ director Indhu Rubasingham) from 11 October to 24 November 2012, with Aldridge
142
+ played by Adrian Lester.
143
+ model-index:
144
+ - name: BGE-base-en-v1.5-Hotpotqa
145
+ results:
146
+ - task:
147
+ type: triplet
148
+ name: Triplet
149
+ dataset:
150
+ name: dim 384
151
+ type: dim_384
152
+ metrics:
153
+ - type: cosine_accuracy
154
+ value: 0.8698532891623284
155
+ name: Cosine Accuracy
156
+ - type: dot_accuracy
157
+ value: 0.13014671083767157
158
+ name: Dot Accuracy
159
+ - type: manhattan_accuracy
160
+ value: 0.8737576904874585
161
+ name: Manhattan Accuracy
162
+ - type: euclidean_accuracy
163
+ value: 0.8698532891623284
164
+ name: Euclidean Accuracy
165
+ - type: max_accuracy
166
+ value: 0.8737576904874585
167
+ name: Max Accuracy
168
+ - task:
169
+ type: triplet
170
+ name: Triplet
171
+ dataset:
172
+ name: dim 256
173
+ type: dim_256
174
+ metrics:
175
+ - type: cosine_accuracy
176
+ value: 0.86819687647894
177
+ name: Cosine Accuracy
178
+ - type: dot_accuracy
179
+ value: 0.1319214387127307
180
+ name: Dot Accuracy
181
+ - type: manhattan_accuracy
182
+ value: 0.8762423095125415
183
+ name: Manhattan Accuracy
184
+ - type: euclidean_accuracy
185
+ value: 0.8680785612872692
186
+ name: Euclidean Accuracy
187
+ - type: max_accuracy
188
+ value: 0.8762423095125415
189
+ name: Max Accuracy
190
+ - task:
191
+ type: triplet
192
+ name: Triplet
193
+ dataset:
194
+ name: dim 128
195
+ type: dim_128
196
+ metrics:
197
+ - type: cosine_accuracy
198
+ value: 0.8663038334122102
199
+ name: Cosine Accuracy
200
+ - type: dot_accuracy
201
+ value: 0.1386654046379555
202
+ name: Dot Accuracy
203
+ - type: manhattan_accuracy
204
+ value: 0.8742309512541411
205
+ name: Manhattan Accuracy
206
+ - type: euclidean_accuracy
207
+ value: 0.865712257453857
208
+ name: Euclidean Accuracy
209
+ - type: max_accuracy
210
+ value: 0.8742309512541411
211
+ name: Max Accuracy
212
+ - task:
213
+ type: triplet
214
+ name: Triplet
215
+ dataset:
216
+ name: dim 64
217
+ type: dim_64
218
+ metrics:
219
+ - type: cosine_accuracy
220
+ value: 0.8634642688121155
221
+ name: Cosine Accuracy
222
+ - type: dot_accuracy
223
+ value: 0.1508518693800284
224
+ name: Dot Accuracy
225
+ - type: manhattan_accuracy
226
+ value: 0.8728111689540937
227
+ name: Manhattan Accuracy
228
+ - type: euclidean_accuracy
229
+ value: 0.8637008991954567
230
+ name: Euclidean Accuracy
231
+ - type: max_accuracy
232
+ value: 0.8728111689540937
233
+ name: Max Accuracy
234
+ ---
235
+
236
+ # BGE-base-en-v1.5-Hotpotqa
237
+
238
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-small-en](https://huggingface.co/BAAI/bge-small-en) on the [sentence-transformers/hotpotqa](https://huggingface.co/datasets/sentence-transformers/hotpotqa) 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.
239
+
240
+ ## Model Details
241
+
242
+ ### Model Description
243
+ - **Model Type:** Sentence Transformer
244
+ - **Base model:** [BAAI/bge-small-en](https://huggingface.co/BAAI/bge-small-en) <!-- at revision 2275a7bdee235e9b4f01fa73aa60d3311983cfea -->
245
+ - **Maximum Sequence Length:** 512 tokens
246
+ - **Output Dimensionality:** 384 tokens
247
+ - **Similarity Function:** Cosine Similarity
248
+ - **Training Dataset:**
249
+ - [sentence-transformers/hotpotqa](https://huggingface.co/datasets/sentence-transformers/hotpotqa)
250
+ - **Language:** en
251
+ - **License:** apache-2.0
252
+
253
+ ### Model Sources
254
+
255
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
256
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
257
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
258
+
259
+ ### Full Model Architecture
260
+
261
+ ```
262
+ SentenceTransformer(
263
+ (0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel
264
+ (1): Pooling({'word_embedding_dimension': 384, '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})
265
+ (2): Normalize()
266
+ )
267
+ ```
268
+
269
+ ## Usage
270
+
271
+ ### Direct Usage (Sentence Transformers)
272
+
273
+ First install the Sentence Transformers library:
274
+
275
+ ```bash
276
+ pip install -U sentence-transformers
277
+ ```
278
+
279
+ Then you can load this model and run inference.
280
+ ```python
281
+ from sentence_transformers import SentenceTransformer
282
+
283
+ # Download from the 🤗 Hub
284
+ model = SentenceTransformer("sentence_transformers_model_id")
285
+ # Run inference
286
+ sentences = [
287
+ 'Red Velvet is a 2012 play by Lolita Chakrabarti, dealing with the biography of a 19th century actor born in which year ?',
288
+ 'Red Velvet (play) Red Velvet is a 2012 play by Lolita Chakrabarti, dealing with the biography of the 19th century actor Ira Aldridge and his taking the role of "Othello". It premiered at the Tricycle Theatre (directed by its new artistic director Indhu Rubasingham) from 11 October to 24 November 2012, with Aldridge played by Adrian Lester.',
289
+ "Herbert Campbell Herbert Campbell (22 December 1844 – 19 July 1904) born Herbert Edward Story was an English comedian and actor who appeared in music hall, Victorian burlesques and musical comedies during the Victorian era. He was famous for starring, for forty years, in the Theatre Royal, Drury Lane's annual Christmas pantomimes, predominantly as a dame.",
290
+ ]
291
+ embeddings = model.encode(sentences)
292
+ print(embeddings.shape)
293
+ # [3, 384]
294
+
295
+ # Get the similarity scores for the embeddings
296
+ similarities = model.similarity(embeddings, embeddings)
297
+ print(similarities.shape)
298
+ # [3, 3]
299
+ ```
300
+
301
+ <!--
302
+ ### Direct Usage (Transformers)
303
+
304
+ <details><summary>Click to see the direct usage in Transformers</summary>
305
+
306
+ </details>
307
+ -->
308
+
309
+ <!--
310
+ ### Downstream Usage (Sentence Transformers)
311
+
312
+ You can finetune this model on your own dataset.
313
+
314
+ <details><summary>Click to expand</summary>
315
+
316
+ </details>
317
+ -->
318
+
319
+ <!--
320
+ ### Out-of-Scope Use
321
+
322
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
323
+ -->
324
+
325
+ ## Evaluation
326
+
327
+ ### Metrics
328
+
329
+ #### Triplet
330
+ * Dataset: `dim_384`
331
+ * Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
332
+
333
+ | Metric | Value |
334
+ |:--------------------|:-----------|
335
+ | **cosine_accuracy** | **0.8699** |
336
+ | dot_accuracy | 0.1301 |
337
+ | manhattan_accuracy | 0.8738 |
338
+ | euclidean_accuracy | 0.8699 |
339
+ | max_accuracy | 0.8738 |
340
+
341
+ #### Triplet
342
+ * Dataset: `dim_256`
343
+ * Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
344
+
345
+ | Metric | Value |
346
+ |:--------------------|:-----------|
347
+ | **cosine_accuracy** | **0.8682** |
348
+ | dot_accuracy | 0.1319 |
349
+ | manhattan_accuracy | 0.8762 |
350
+ | euclidean_accuracy | 0.8681 |
351
+ | max_accuracy | 0.8762 |
352
+
353
+ #### Triplet
354
+ * Dataset: `dim_128`
355
+ * Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
356
+
357
+ | Metric | Value |
358
+ |:--------------------|:-----------|
359
+ | **cosine_accuracy** | **0.8663** |
360
+ | dot_accuracy | 0.1387 |
361
+ | manhattan_accuracy | 0.8742 |
362
+ | euclidean_accuracy | 0.8657 |
363
+ | max_accuracy | 0.8742 |
364
+
365
+ #### Triplet
366
+ * Dataset: `dim_64`
367
+ * Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
368
+
369
+ | Metric | Value |
370
+ |:--------------------|:-----------|
371
+ | **cosine_accuracy** | **0.8635** |
372
+ | dot_accuracy | 0.1509 |
373
+ | manhattan_accuracy | 0.8728 |
374
+ | euclidean_accuracy | 0.8637 |
375
+ | max_accuracy | 0.8728 |
376
+
377
+ <!--
378
+ ## Bias, Risks and Limitations
379
+
380
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
381
+ -->
382
+
383
+ <!--
384
+ ### Recommendations
385
+
386
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
387
+ -->
388
+
389
+ ## Training Details
390
+
391
+ ### Training Dataset
392
+
393
+ #### sentence-transformers/hotpotqa
394
+
395
+ * Dataset: [sentence-transformers/hotpotqa](https://huggingface.co/datasets/sentence-transformers/hotpotqa) at [f07d3cd](https://huggingface.co/datasets/sentence-transformers/hotpotqa/tree/f07d3cd2d290ea2e83ed35e33d67d6a4658b8786)
396
+ * Size: 76,064 training samples
397
+ * Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
398
+ * Approximate statistics based on the first 1000 samples:
399
+ | | anchor | positive | negative |
400
+ |:--------|:----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
401
+ | type | string | string | string |
402
+ | details | <ul><li>min: 8 tokens</li><li>mean: 24.08 tokens</li><li>max: 95 tokens</li></ul> | <ul><li>min: 23 tokens</li><li>mean: 100.12 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 15 tokens</li><li>mean: 88.02 tokens</li><li>max: 512 tokens</li></ul> |
403
+ * Samples:
404
+ | anchor | positive | negative |
405
+ |:-------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
406
+ | <code>What nationality was the player named MVP in 2017 World Baseball Classic – Pool C ?</code> | <code>2017 World Baseball Classic – Pool C Pool C of the First Round of the 2017 World Baseball Classic was held at Marlins Park, Miami, Florida, United States, from March 9 to 12, 2017, between Canada, Colombia, the Dominican Republic, and the United States. Pool C was a round-robin tournament. Each team played the other three teams once, with the top two teams – the Dominican Republic and the United States – advancing to Pool F, one of two second-round pools. Manny Machado of the Dominican Republic was named MVP for the first-round Pool C bracket of the WBC, after batting .357.</code> | <code>2017 World Baseball Classic – Qualifier 2 Qualifier 2 of the Qualifying Round of the 2017 World Baseball Classic was held at Estadio B'Air, Mexicali, Mexico from March 17 to 20, 2016.</code> |
407
+ | <code>Karl Kraepelin specialized in the study of what predatory arachnids?</code> | <code>Karl Kraepelin Karl Matthias Friedrich Magnus Kraepelin (14 December 1848 Neustrelitz – 28 June 1915 Hamburg), was a German naturalist who specialised in the study of scorpions, centipedes, spiders and solfugids, and was noted for his monograph ""Scorpiones und Pedipalpi"" (Berlin) in 1899, which was an exhaustive survey of the taxonomy of the Order Scorpiones. From 1889–1914 he was Director of the "Naturhistorisches Museum Hamburg ", which was destroyed during World War II, and worked on myriapods from 1901–1916.</code> | <code>Teuthology Teuthology (from Greek "τεῦθος" , "cuttlefish, squid", and -λογία , "-logia") is the study of cephalopods.</code> |
408
+ | <code>Who directed the 1990 American crime film in which Vito Pick me played a bit part?</code> | <code>Vito Picone Vito Picone (born March 20, 1941) is the lead singer of The Elegants, and along with Jimmy Mochella is a remaining original member. He has also played bit parts in "Goodfellas", "Analyze This", and "The Sopranos".</code> | <code>The Rookie (1990 film) The Rookie is a 1990 American buddy cop film directed by Clint Eastwood and produced by Howard G. Kazanjian, Steven Siebert and David Valdes. It was written from a screenplay conceived by Boaz Yakin and Scott Spiegel. The film stars Charlie Sheen, Clint Eastwood, Raúl Juliá, Sônia Braga, Lara Flynn Boyle, and Tom Skerritt. Eastwood plays a veteran police officer teamed up with a younger detective played by Sheen ("the rookie"), whose intent is to take down a German crime lord in downtown Los Angeles following months of investigation into an exotic car theft ring.</code> |
409
+ * Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
410
+ ```json
411
+ {
412
+ "loss": "TripletLoss",
413
+ "matryoshka_dims": [
414
+ 384,
415
+ 256,
416
+ 128,
417
+ 64
418
+ ],
419
+ "matryoshka_weights": [
420
+ 1,
421
+ 1,
422
+ 1,
423
+ 1
424
+ ],
425
+ "n_dims_per_step": -1
426
+ }
427
+ ```
428
+
429
+ ### Evaluation Dataset
430
+
431
+ #### sentence-transformers/hotpotqa
432
+
433
+ * Dataset: [sentence-transformers/hotpotqa](https://huggingface.co/datasets/sentence-transformers/hotpotqa) at [f07d3cd](https://huggingface.co/datasets/sentence-transformers/hotpotqa/tree/f07d3cd2d290ea2e83ed35e33d67d6a4658b8786)
434
+ * Size: 8,452 evaluation samples
435
+ * Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
436
+ * Approximate statistics based on the first 1000 samples:
437
+ | | anchor | positive | negative |
438
+ |:--------|:------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
439
+ | type | string | string | string |
440
+ | details | <ul><li>min: 10 tokens</li><li>mean: 24.53 tokens</li><li>max: 114 tokens</li></ul> | <ul><li>min: 19 tokens</li><li>mean: 103.87 tokens</li><li>max: 407 tokens</li></ul> | <ul><li>min: 17 tokens</li><li>mean: 88.32 tokens</li><li>max: 356 tokens</li></ul> |
441
+ * Samples:
442
+ | anchor | positive | negative |
443
+ |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
444
+ | <code>Which actress, known for her role as Harper Munroe on the MTV comedy series "Happyland", starred alongside Laura Marano, Parker Mack, Michelle Clunie and Kathleen Wilhoite in the film A Sort of Homecoming?</code> | <code>A Sort of Homecoming (film) A Sort of Homecoming is an American drama directed by Maria Burton, her fifth feature film. The films stars Katherine McNamara, Laura Marano, Parker Mack, Michelle Clunie and Kathleen Wilhoite. The film premiered March 14, 2015 at the Omaha Film Festival.</code> | <code>Nellie Bellflower Nellie Bellflower (born May 1, 1946 in Phoenix, Arizona) is an American actress and voice artist who provided the voice of Princess Ariel in the Ruby-Spears animated television series "Thundarr the Barbarian". She has also been in "The Last Unicorn" (voice), Rankin/Bass "The Return of the King", "Americathon", the miniseries "East of Eden", and guest roles on various TV shows such as "Barnaby Jones", "Barney Miller", "Starsky and Hutch", and "Happy Days" as Fonzie's ex-fiancée Maureen Johnson, a.k.a. "The Lone Stripper", in the Season 2 episode of the series titled "Fonzie's Getting Married" (episode #13). Nellie has been involved in movie production with three projects: "The Girl in Melanie Klein" (2008), "Miss Pettigrew Lives for a Day" (2008) and "Finding Neverland" (2004), for which she was nominated for an Academy Award as Producer for Best Picture. She is married to Michael Mislove.</code> |
445
+ | <code>Between Pizza Fusion and Pizzeria Venti, which restaurant emphasizes organic ingredients and green building methods?</code> | <code>Pizza Fusion Pizza Fusion is a Deerfield Beach, Florida-based pizza restaurant chain. Using mostly organic ingredients and emphasizing green building methods, the restaurants operate under the tagline Saving the Earth, One Pizza at a Time.</code> | <code>Pizza Schmizza Pizza Schmizza is an American pizza chain with 23 locations throughout the Portland, Oregon area, and two in southern Oregon. Pizza Schmizza, primarily selling thin crust pizza by-the-slice.</code> |
446
+ | <code>What company distributed the stop motion spin-off special "The Year Without a Santa Claus," which aired on December 10, 1974?</code> | <code>A Miser Brothers' Christmas A Miser Brothers' Christmas is a stop motion spin-off special based on some of the characters from the 1974 Rankin-Bass special "The Year Without a Santa Claus". Distributed by Warner Bros. Animation under their Warner Premiere label (the rights holders of the post-1974 Rankin-Bass library) and Toronto-based Cuppa Coffee Studios, the one-hour special premiered on ABC Family on Saturday, December 13, 2008, during the network's annual The 25 Days of Christmas programming. Mickey Rooney and George S. Irving reprised their respective roles as Santa Claus and Heat Miser at ages 88 and 86. Snow Miser, originally portrayed by Dick Shawn who died in 1987, was voiced by Juan Chioran, while Mrs. Claus, voiced by Shirley Booth in the original, was portrayed by Catherine Disher (because Booth had died in 1992). The movie aimed to emulate the Rankin/Bass animation style. This is the last Christmas special to feature Mickey Rooney as Santa Claus, as he died in 2014, as well as the last time George Irving voiced Heat Miser, as he died in 2016.</code> | <code>Holidaze: The Christmas That Almost Didn't Happen Holidaze: The Christmas That Almost Didn't Happen is an American stop-motion animated Christmas television special directed by David H. Brooks, that originally aired in 2006 and produced by BixPix Entertainment, Once Upon a Frog and Madison Street Entertainment. The show's plot has Rusty Reindeer (Fred Savage) the brother of Rudolph the Red Nosed Reindeer joining a support group for depressed holiday icons, and he and the other characters search for the meaning of Christmas and help a young boy (Dylan and Cole Sprouse) to get on Santa's nice list. Rusty's cohorts include Candie, the Easter Bunny (Gladys Knight); Mr. C, the grouchy cherub (Paul Rodriguez); Albert, the Thanksgiving Turkey (Harland Williams); And Trick and Treat (Brenda Song and Emily Osment) the teenage Halloween Ghosts.</code> |
447
+ * Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
448
+ ```json
449
+ {
450
+ "loss": "TripletLoss",
451
+ "matryoshka_dims": [
452
+ 384,
453
+ 256,
454
+ 128,
455
+ 64
456
+ ],
457
+ "matryoshka_weights": [
458
+ 1,
459
+ 1,
460
+ 1,
461
+ 1
462
+ ],
463
+ "n_dims_per_step": -1
464
+ }
465
+ ```
466
+
467
+ ### Training Hyperparameters
468
+ #### Non-Default Hyperparameters
469
+
470
+ - `eval_strategy`: steps
471
+ - `per_device_train_batch_size`: 32
472
+ - `per_device_eval_batch_size`: 32
473
+ - `gradient_accumulation_steps`: 16
474
+ - `learning_rate`: 2e-05
475
+ - `num_train_epochs`: 50
476
+ - `lr_scheduler_type`: cosine
477
+ - `warmup_ratio`: 0.1
478
+ - `bf16`: True
479
+ - `tf32`: True
480
+ - `load_best_model_at_end`: True
481
+ - `optim`: adamw_torch_fused
482
+ - `resume_from_checkpoint`: bge-small-hotpotwa-matryoshka
483
+ - `batch_sampler`: no_duplicates
484
+
485
+ #### All Hyperparameters
486
+ <details><summary>Click to expand</summary>
487
+
488
+ - `overwrite_output_dir`: False
489
+ - `do_predict`: False
490
+ - `eval_strategy`: steps
491
+ - `prediction_loss_only`: True
492
+ - `per_device_train_batch_size`: 32
493
+ - `per_device_eval_batch_size`: 32
494
+ - `per_gpu_train_batch_size`: None
495
+ - `per_gpu_eval_batch_size`: None
496
+ - `gradient_accumulation_steps`: 16
497
+ - `eval_accumulation_steps`: None
498
+ - `learning_rate`: 2e-05
499
+ - `weight_decay`: 0.0
500
+ - `adam_beta1`: 0.9
501
+ - `adam_beta2`: 0.999
502
+ - `adam_epsilon`: 1e-08
503
+ - `max_grad_norm`: 1.0
504
+ - `num_train_epochs`: 50
505
+ - `max_steps`: -1
506
+ - `lr_scheduler_type`: cosine
507
+ - `lr_scheduler_kwargs`: {}
508
+ - `warmup_ratio`: 0.1
509
+ - `warmup_steps`: 0
510
+ - `log_level`: passive
511
+ - `log_level_replica`: warning
512
+ - `log_on_each_node`: True
513
+ - `logging_nan_inf_filter`: True
514
+ - `save_safetensors`: True
515
+ - `save_on_each_node`: False
516
+ - `save_only_model`: False
517
+ - `restore_callback_states_from_checkpoint`: False
518
+ - `no_cuda`: False
519
+ - `use_cpu`: False
520
+ - `use_mps_device`: False
521
+ - `seed`: 42
522
+ - `data_seed`: None
523
+ - `jit_mode_eval`: False
524
+ - `use_ipex`: False
525
+ - `bf16`: True
526
+ - `fp16`: False
527
+ - `fp16_opt_level`: O1
528
+ - `half_precision_backend`: auto
529
+ - `bf16_full_eval`: False
530
+ - `fp16_full_eval`: False
531
+ - `tf32`: True
532
+ - `local_rank`: 0
533
+ - `ddp_backend`: None
534
+ - `tpu_num_cores`: None
535
+ - `tpu_metrics_debug`: False
536
+ - `debug`: []
537
+ - `dataloader_drop_last`: False
538
+ - `dataloader_num_workers`: 0
539
+ - `dataloader_prefetch_factor`: None
540
+ - `past_index`: -1
541
+ - `disable_tqdm`: False
542
+ - `remove_unused_columns`: True
543
+ - `label_names`: None
544
+ - `load_best_model_at_end`: True
545
+ - `ignore_data_skip`: False
546
+ - `fsdp`: []
547
+ - `fsdp_min_num_params`: 0
548
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
549
+ - `fsdp_transformer_layer_cls_to_wrap`: None
550
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
551
+ - `deepspeed`: None
552
+ - `label_smoothing_factor`: 0.0
553
+ - `optim`: adamw_torch_fused
554
+ - `optim_args`: None
555
+ - `adafactor`: False
556
+ - `group_by_length`: False
557
+ - `length_column_name`: length
558
+ - `ddp_find_unused_parameters`: None
559
+ - `ddp_bucket_cap_mb`: None
560
+ - `ddp_broadcast_buffers`: False
561
+ - `dataloader_pin_memory`: True
562
+ - `dataloader_persistent_workers`: False
563
+ - `skip_memory_metrics`: True
564
+ - `use_legacy_prediction_loop`: False
565
+ - `push_to_hub`: False
566
+ - `resume_from_checkpoint`: bge-small-hotpotwa-matryoshka
567
+ - `hub_model_id`: None
568
+ - `hub_strategy`: every_save
569
+ - `hub_private_repo`: False
570
+ - `hub_always_push`: False
571
+ - `gradient_checkpointing`: False
572
+ - `gradient_checkpointing_kwargs`: None
573
+ - `include_inputs_for_metrics`: False
574
+ - `eval_do_concat_batches`: True
575
+ - `fp16_backend`: auto
576
+ - `push_to_hub_model_id`: None
577
+ - `push_to_hub_organization`: None
578
+ - `mp_parameters`:
579
+ - `auto_find_batch_size`: False
580
+ - `full_determinism`: False
581
+ - `torchdynamo`: None
582
+ - `ray_scope`: last
583
+ - `ddp_timeout`: 1800
584
+ - `torch_compile`: False
585
+ - `torch_compile_backend`: None
586
+ - `torch_compile_mode`: None
587
+ - `dispatch_batches`: None
588
+ - `split_batches`: None
589
+ - `include_tokens_per_second`: False
590
+ - `include_num_input_tokens_seen`: False
591
+ - `neftune_noise_alpha`: None
592
+ - `optim_target_modules`: None
593
+ - `batch_eval_metrics`: False
594
+ - `batch_sampler`: no_duplicates
595
+ - `multi_dataset_batch_sampler`: proportional
596
+
597
+ </details>
598
+
599
+ ### Training Logs
600
+ | Epoch | Step | Training Loss | loss | dim_128_cosine_accuracy | dim_256_cosine_accuracy | dim_384_cosine_accuracy | dim_64_cosine_accuracy |
601
+ |:-------:|:----:|:-------------:|:-------:|:-----------------------:|:-----------------------:|:-----------------------:|:----------------------:|
602
+ | 0.3366 | 50 | 19.5758 | 19.3933 | 0.9552 | 0.9663 | 0.9668 | 0.9359 |
603
+ | 0.6731 | 100 | 19.4573 | 19.0971 | 0.9571 | 0.9646 | 0.9653 | 0.9450 |
604
+ | 1.0097 | 150 | 19.1409 | 18.4070 | 0.9385 | 0.9434 | 0.9473 | 0.9307 |
605
+ | 1.3462 | 200 | 18.6431 | 17.3292 | 0.9126 | 0.9164 | 0.9184 | 0.9094 |
606
+ | 1.6828 | 250 | 18.2288 | 16.8751 | 0.9063 | 0.9071 | 0.9100 | 0.9023 |
607
+ | 2.0194 | 300 | 18.0425 | 16.6981 | 0.9020 | 0.9032 | 0.9045 | 0.8990 |
608
+ | 2.3559 | 350 | 17.9458 | 16.6155 | 0.9037 | 0.9013 | 0.9022 | 0.8984 |
609
+ | 2.6925 | 400 | 17.8525 | 16.5536 | 0.8978 | 0.8971 | 0.8974 | 0.8948 |
610
+ | 3.0290 | 450 | 17.7529 | 16.5136 | 0.8980 | 0.8956 | 0.8953 | 0.8951 |
611
+ | 3.3656 | 500 | 17.6709 | 16.4824 | 0.8932 | 0.8914 | 0.8928 | 0.8907 |
612
+ | 3.7021 | 550 | 17.5348 | 16.4632 | 0.8863 | 0.8858 | 0.8859 | 0.8849 |
613
+ | 4.0387 | 600 | 17.4198 | 16.4601 | 0.8852 | 0.8862 | 0.8859 | 0.8839 |
614
+ | 4.3753 | 650 | 17.3673 | 16.4405 | 0.8854 | 0.8864 | 0.8865 | 0.8842 |
615
+ | 4.7118 | 700 | 17.2603 | 16.4356 | 0.8835 | 0.8838 | 0.8838 | 0.8807 |
616
+ | 5.0484 | 750 | 17.1807 | 16.4443 | 0.8850 | 0.8864 | 0.8859 | 0.8838 |
617
+ | 5.3849 | 800 | 17.1629 | 16.4202 | 0.8848 | 0.8862 | 0.8867 | 0.8842 |
618
+ | 5.7215 | 850 | 17.0747 | 16.4162 | 0.8854 | 0.8875 | 0.8869 | 0.8837 |
619
+ | 6.0581 | 900 | 17.0161 | 16.4192 | 0.8852 | 0.8863 | 0.8856 | 0.8856 |
620
+ | 6.3946 | 950 | 17.0146 | 16.4033 | 0.8849 | 0.8854 | 0.8856 | 0.8844 |
621
+ | 6.7312 | 1000 | 16.9393 | 16.4053 | 0.8829 | 0.8839 | 0.8848 | 0.8835 |
622
+ | 7.0677 | 1050 | 16.899 | 16.4162 | 0.8826 | 0.8829 | 0.8833 | 0.8818 |
623
+ | 7.4043 | 1100 | 16.9112 | 16.4051 | 0.8829 | 0.8835 | 0.8833 | 0.8820 |
624
+ | 7.7408 | 1150 | 16.8508 | 16.4044 | 0.8822 | 0.8825 | 0.8830 | 0.8820 |
625
+ | 8.0774 | 1200 | 16.8104 | 16.4063 | 0.8816 | 0.8816 | 0.8814 | 0.8817 |
626
+ | 8.4140 | 1250 | 16.8212 | 16.4040 | 0.8835 | 0.8822 | 0.8822 | 0.8820 |
627
+ | 8.7505 | 1300 | 16.7743 | 16.3934 | 0.8822 | 0.8824 | 0.8817 | 0.8810 |
628
+ | 9.0871 | 1350 | 16.7383 | 16.3963 | 0.8810 | 0.8820 | 0.8807 | 0.8800 |
629
+ | 9.4236 | 1400 | 16.743 | 16.4067 | 0.8819 | 0.8822 | 0.8819 | 0.8798 |
630
+ | 9.7602 | 1450 | 16.7047 | 16.3959 | 0.8804 | 0.8810 | 0.8810 | 0.8797 |
631
+ | 10.0968 | 1500 | 16.6782 | 16.3986 | 0.8788 | 0.8791 | 0.8796 | 0.8784 |
632
+ | 10.4333 | 1550 | 16.6708 | 16.4016 | 0.8794 | 0.8792 | 0.8797 | 0.8791 |
633
+ | 10.7699 | 1600 | 16.6485 | 16.3963 | 0.8790 | 0.8801 | 0.8791 | 0.8781 |
634
+ | 11.1064 | 1650 | 16.6205 | 16.4012 | 0.8779 | 0.8787 | 0.8793 | 0.8771 |
635
+ | 11.4430 | 1700 | 16.6095 | 16.4131 | 0.8786 | 0.8790 | 0.8794 | 0.8791 |
636
+ | 11.7796 | 1750 | 16.5891 | 16.4070 | 0.8807 | 0.8805 | 0.8810 | 0.8801 |
637
+ | 12.1161 | 1800 | 16.5619 | 16.3963 | 0.8794 | 0.8800 | 0.8797 | 0.8780 |
638
+ | 12.4527 | 1850 | 16.5467 | 16.3991 | 0.8796 | 0.8806 | 0.8804 | 0.8790 |
639
+ | 12.7892 | 1900 | 16.5398 | 16.3970 | 0.8792 | 0.8798 | 0.8801 | 0.8788 |
640
+ | 13.1258 | 1950 | 16.5047 | 16.3964 | 0.8796 | 0.8804 | 0.8804 | 0.8788 |
641
+ | 13.4623 | 2000 | 16.4985 | 16.4025 | 0.8793 | 0.8798 | 0.8807 | 0.8790 |
642
+ | 13.7989 | 2050 | 16.4852 | 16.4107 | 0.8801 | 0.8810 | 0.8800 | 0.8793 |
643
+ | 14.1355 | 2100 | 16.4526 | 16.3929 | 0.8797 | 0.8801 | 0.8809 | 0.8779 |
644
+ | 14.4720 | 2150 | 16.4343 | 16.4075 | 0.8788 | 0.8791 | 0.8797 | 0.8774 |
645
+ | 14.8086 | 2200 | 16.4244 | 16.4027 | 0.8804 | 0.8819 | 0.8820 | 0.8809 |
646
+ | 15.1451 | 2250 | 16.3947 | 16.4102 | 0.8791 | 0.8792 | 0.8803 | 0.8773 |
647
+ | 15.4817 | 2300 | 16.3827 | 16.4042 | 0.8804 | 0.8813 | 0.8813 | 0.8781 |
648
+ | 15.8183 | 2350 | 16.3719 | 16.4003 | 0.8801 | 0.8818 | 0.8820 | 0.8791 |
649
+ | 16.1548 | 2400 | 16.3403 | 16.4132 | 0.8781 | 0.8791 | 0.8799 | 0.8767 |
650
+ | 16.4914 | 2450 | 16.3357 | 16.4149 | 0.8804 | 0.8809 | 0.8807 | 0.8792 |
651
+ | 16.8279 | 2500 | 16.3203 | 16.4081 | 0.8804 | 0.8814 | 0.8816 | 0.8791 |
652
+ | 17.1645 | 2550 | 16.2986 | 16.4139 | 0.8798 | 0.8800 | 0.8820 | 0.8791 |
653
+ | 17.5011 | 2600 | 16.2923 | 16.4062 | 0.8786 | 0.8792 | 0.8799 | 0.8768 |
654
+ | 17.8376 | 2650 | 16.2649 | 16.4106 | 0.8800 | 0.8807 | 0.8814 | 0.8787 |
655
+ | 18.1742 | 2700 | 16.2505 | 16.4188 | 0.8786 | 0.8793 | 0.8803 | 0.8771 |
656
+ | 18.5107 | 2750 | 16.226 | 16.4149 | 0.8771 | 0.8781 | 0.8780 | 0.8766 |
657
+ | 18.8473 | 2800 | 16.2106 | 16.4230 | 0.8780 | 0.8799 | 0.8791 | 0.8767 |
658
+ | 19.1838 | 2850 | 16.2052 | 16.4351 | 0.8770 | 0.8777 | 0.8785 | 0.8745 |
659
+ | 19.5204 | 2900 | 16.186 | 16.4331 | 0.8777 | 0.8793 | 0.8792 | 0.8762 |
660
+ | 19.8570 | 2950 | 16.1496 | 16.4377 | 0.8774 | 0.8781 | 0.8780 | 0.8771 |
661
+ | 20.1935 | 3000 | 16.151 | 16.4407 | 0.8766 | 0.8780 | 0.8780 | 0.8751 |
662
+ | 20.5301 | 3050 | 16.1081 | 16.4426 | 0.8759 | 0.8775 | 0.8774 | 0.8749 |
663
+ | 20.8666 | 3100 | 16.0864 | 16.4412 | 0.8774 | 0.8781 | 0.8787 | 0.8746 |
664
+ | 21.2032 | 3150 | 16.0934 | 16.4547 | 0.8768 | 0.8783 | 0.8794 | 0.8746 |
665
+ | 21.5398 | 3200 | 16.0382 | 16.4589 | 0.8742 | 0.8752 | 0.8766 | 0.8723 |
666
+ | 21.8763 | 3250 | 16.0279 | 16.4668 | 0.8752 | 0.8766 | 0.8773 | 0.8728 |
667
+ | 22.2129 | 3300 | 16.0327 | 16.4737 | 0.8742 | 0.8768 | 0.8773 | 0.8727 |
668
+ | 22.5494 | 3350 | 15.979 | 16.4686 | 0.8740 | 0.8771 | 0.8771 | 0.8722 |
669
+ | 22.8860 | 3400 | 15.9622 | 16.4736 | 0.8743 | 0.8760 | 0.8765 | 0.8721 |
670
+ | 23.2225 | 3450 | 15.9881 | 16.4802 | 0.8743 | 0.8757 | 0.8755 | 0.8723 |
671
+ | 23.5591 | 3500 | 15.9482 | 16.4821 | 0.8725 | 0.8761 | 0.8761 | 0.8710 |
672
+ | 23.8957 | 3550 | 15.9228 | 16.4996 | 0.8726 | 0.8748 | 0.8751 | 0.8709 |
673
+ | 24.2322 | 3600 | 15.9418 | 16.4973 | 0.8709 | 0.8728 | 0.8734 | 0.8699 |
674
+ | 24.5688 | 3650 | 15.896 | 16.4985 | 0.8696 | 0.8716 | 0.8727 | 0.8686 |
675
+ | 24.9053 | 3700 | 15.8788 | 16.5172 | 0.8691 | 0.8715 | 0.8717 | 0.8662 |
676
+ | 25.2419 | 3750 | 15.9147 | 16.5062 | 0.8677 | 0.8706 | 0.8712 | 0.8662 |
677
+ | 25.5785 | 3800 | 15.857 | 16.5058 | 0.8683 | 0.8717 | 0.8732 | 0.8663 |
678
+ | 25.9150 | 3850 | 15.8291 | 16.5207 | 0.8674 | 0.8702 | 0.8706 | 0.8644 |
679
+ | 26.2516 | 3900 | 15.8802 | 16.5233 | 0.8678 | 0.8697 | 0.8714 | 0.8664 |
680
+ | 26.5881 | 3950 | 15.846 | 16.5170 | 0.8686 | 0.8713 | 0.8717 | 0.8655 |
681
+ | 26.9247 | 4000 | 15.8012 | 16.5336 | 0.8663 | 0.8682 | 0.8699 | 0.8635 |
682
+
683
+
684
+ ### Framework Versions
685
+ - Python: 3.10.10
686
+ - Sentence Transformers: 3.0.1
687
+ - Transformers: 4.41.2
688
+ - PyTorch: 2.1.2+cu121
689
+ - Accelerate: 0.33.0
690
+ - Datasets: 2.19.1
691
+ - Tokenizers: 0.19.1
692
+
693
+ ## Citation
694
+
695
+ ### BibTeX
696
+
697
+ #### Sentence Transformers
698
+ ```bibtex
699
+ @inproceedings{reimers-2019-sentence-bert,
700
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
701
+ author = "Reimers, Nils and Gurevych, Iryna",
702
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
703
+ month = "11",
704
+ year = "2019",
705
+ publisher = "Association for Computational Linguistics",
706
+ url = "https://arxiv.org/abs/1908.10084",
707
+ }
708
+ ```
709
+
710
+ #### MatryoshkaLoss
711
+ ```bibtex
712
+ @misc{kusupati2024matryoshka,
713
+ title={Matryoshka Representation Learning},
714
+ author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
715
+ year={2024},
716
+ eprint={2205.13147},
717
+ archivePrefix={arXiv},
718
+ primaryClass={cs.LG}
719
+ }
720
+ ```
721
+
722
+ #### TripletLoss
723
+ ```bibtex
724
+ @misc{hermans2017defense,
725
+ title={In Defense of the Triplet Loss for Person Re-Identification},
726
+ author={Alexander Hermans and Lucas Beyer and Bastian Leibe},
727
+ year={2017},
728
+ eprint={1703.07737},
729
+ archivePrefix={arXiv},
730
+ primaryClass={cs.CV}
731
+ }
732
+ ```
733
+
734
+ <!--
735
+ ## Glossary
736
+
737
+ *Clearly define terms in order to be accessible across audiences.*
738
+ -->
739
+
740
+ <!--
741
+ ## Model Card Authors
742
+
743
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
744
+ -->
745
+
746
+ <!--
747
+ ## Model Card Contact
748
+
749
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
750
+ -->
README.md:Zone.Identifier ADDED
File without changes
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "BAAI/bge-small-en",
3
+ "architectures": [
4
+ "BertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 384,
11
+ "id2label": {
12
+ "0": "LABEL_0"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 1536,
16
+ "label2id": {
17
+ "LABEL_0": 0
18
+ },
19
+ "layer_norm_eps": 1e-12,
20
+ "max_position_embeddings": 512,
21
+ "model_type": "bert",
22
+ "num_attention_heads": 12,
23
+ "num_hidden_layers": 12,
24
+ "pad_token_id": 0,
25
+ "position_embedding_type": "absolute",
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.41.2",
28
+ "type_vocab_size": 2,
29
+ "use_cache": true,
30
+ "vocab_size": 30522
31
+ }
config.json:Zone.Identifier ADDED
File without changes
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.0.1",
4
+ "transformers": "4.41.2",
5
+ "pytorch": "2.1.2+cu121"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null,
9
+ "similarity_fn_name": null
10
+ }
config_sentence_transformers.json:Zone.Identifier ADDED
File without changes
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32c68a323fc2f3bcbda00ad2a1f363f61bc7b83fc043add0d2b3b1a3ed52d464
3
+ size 133462128
model.safetensors:Zone.Identifier ADDED
File without changes
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
+ ]
modules.json:Zone.Identifier ADDED
File without changes
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1d16a07efdf00707049d4fe19f5dec2260120f832764d37bb7c5a1ebe56f2d8
3
+ size 265864826
optimizer.pt:Zone.Identifier ADDED
File without changes
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c726cd6df5d0f6335ea7a2dff309473ebaa68b01c9de1540a1d24ee6255e5db
3
+ size 14244
rng_state.pth:Zone.Identifier ADDED
File without changes
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ce31c572ec8e79b27f5037d372accc83087de1b2e8743916a5ce48a76016091
3
+ size 1064
scheduler.pt:Zone.Identifier ADDED
File without changes
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 512,
3
+ "do_lower_case": true
4
+ }
sentence_bert_config.json:Zone.Identifier ADDED
File without changes
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
+ }
special_tokens_map.json:Zone.Identifier ADDED
File without changes
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.json:Zone.Identifier ADDED
File without changes
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
tokenizer_config.json:Zone.Identifier ADDED
File without changes
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
trainer_state.json:Zone.Identifier ADDED
File without changes
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe26c00a13b1f876cc56db695e59e808d1e214b61eac1c9292a292294b0541d3
3
+ size 5432
training_args.bin:Zone.Identifier ADDED
File without changes
vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
vocab.txt:Zone.Identifier ADDED
File without changes