Add new SentenceTransformer model
Browse files- README.md +212 -175
- model.safetensors +1 -1
README.md
CHANGED
@@ -7,132 +7,168 @@ tags:
|
|
7 |
- sentence-similarity
|
8 |
- feature-extraction
|
9 |
- generated_from_trainer
|
10 |
-
- dataset_size:
|
11 |
- loss:MatryoshkaLoss
|
12 |
- loss:MultipleNegativesRankingLoss
|
13 |
base_model: nomic-ai/modernbert-embed-base
|
14 |
widget:
|
15 |
-
- source_sentence:
|
16 |
sentences:
|
17 |
-
- '
|
18 |
-
|
19 |
-
- ([Andy Richter Net Worth | Celebrity Net Worth](https://www.celebritynetworth.com))
|
20 |
-
|
21 |
|
22 |
-
|
23 |
|
24 |
-
|
25 |
|
26 |
-
|
27 |
-
- "Description: Max Weinberg led the band on 'Late Night' and 'The Tonight Show\
|
28 |
-
\ with Conan O'Brien' before departing in 2010.\n- TBS-era bandleader jimmy_vivino\
|
29 |
-
\ (Strength: strong)\n Description: Jimmy Vivino took over as bandleader on Conan's\
|
30 |
-
\ TBS show after Max Weinberg stepped away.\n- Spouse liza_powel_obrien (Strength:\
|
31 |
-
\ very strong)"
|
32 |
-
- "Relationships:\n- Owner team_coco (Strength: strong)\n Description: SiriusXM\
|
33 |
-
\ owns Team Coco and its digital content library.\n- On-air talent conan_obrien\
|
34 |
-
\ (Strength: strong)\n Description: Conan signed a multi-year deal with SiriusXM\
|
35 |
-
\ to produce content.\n\nAwards and Recognitions:\n- Leader in comedy audio"
|
36 |
-
- source_sentence: What webcomic did Pierre Bernard co-create with Conan O'Brien?
|
37 |
-
sentences:
|
38 |
-
- 'Graph: Team Coco Knowledge Graph
|
39 |
|
40 |
-
|
41 |
|
42 |
-
Category: people
|
43 |
|
44 |
-
|
|
|
|
|
45 |
|
46 |
-
Type: Person
|
47 |
|
|
|
48 |
|
49 |
-
|
50 |
-
|
51 |
-
|
52 |
-
-
|
53 |
-
|
54 |
-
|
55 |
-
|
56 |
-
|
57 |
-
- "Relationships:\n-
|
58 |
-
\
|
59 |
-
|
60 |
-
\
|
61 |
-
- source_sentence:
|
62 |
sentences:
|
63 |
- 'Graph: Team Coco Knowledge Graph
|
64 |
|
65 |
-
Node ID:
|
66 |
|
67 |
Category: events
|
68 |
|
69 |
-
Name:
|
70 |
|
71 |
Type: Event
|
72 |
|
73 |
|
74 |
-
Description:
|
75 |
-
|
|
|
76 |
|
77 |
|
78 |
Relationships:
|
79 |
|
80 |
-
-
|
81 |
|
82 |
-
-
|
83 |
-
- "Relationships:\n- Late-night host conan_obrien (Strength: strong)\n Description:\
|
84 |
-
\ Conan headlined TBS's late-night lineup for 11 years.\n- Digital content partner\
|
85 |
-
\ team_coco (Strength: strong)\n Description: Team Coco produced many online\
|
86 |
-
\ segments during the TBS era.\n\nAwards and Recognitions:\n- Innovative blend\
|
87 |
-
\ of on-air and online content\n- Consistent ratings success"
|
88 |
-
- 'Graph: Team Coco Knowledge Graph
|
89 |
-
|
90 |
-
Node ID: liza_powel_obrien
|
91 |
|
92 |
-
|
|
|
93 |
|
94 |
-
|
95 |
|
96 |
-
|
97 |
-
-
|
|
|
98 |
sentences:
|
99 |
-
-
|
|
|
|
|
|
|
100 |
- 'Major Events:
|
101 |
|
102 |
-
-
|
103 |
|
104 |
-
- 2009
|
105 |
-
|
106 |
-
|
107 |
-
-
|
|
|
|
|
|
|
108 |
sentences:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
109 |
- 'Graph: Team Coco Knowledge Graph
|
110 |
|
111 |
-
Node ID:
|
112 |
|
113 |
-
Category:
|
114 |
|
115 |
-
Name:
|
116 |
|
117 |
-
Type:
|
118 |
|
119 |
|
120 |
-
Description:
|
121 |
-
|
122 |
-
|
123 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
124 |
|
125 |
-
-
|
126 |
-
- Wikipedia](https://en.wikipedia.org/wiki/Late_Night_with_Conan_O%27Brien))
|
127 |
|
128 |
-
-
|
129 |
|
130 |
-
-
|
131 |
-
|
132 |
-
|
133 |
-
|
134 |
-
|
135 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
136 |
pipeline_tag: sentence-similarity
|
137 |
library_name: sentence-transformers
|
138 |
metrics:
|
@@ -168,10 +204,10 @@ model-index:
|
|
168 |
value: 0.8611111111111112
|
169 |
name: Cosine Accuracy@3
|
170 |
- type: cosine_accuracy@5
|
171 |
-
value: 0.
|
172 |
name: Cosine Accuracy@5
|
173 |
- type: cosine_accuracy@10
|
174 |
-
value:
|
175 |
name: Cosine Accuracy@10
|
176 |
- type: cosine_precision@1
|
177 |
value: 0.7222222222222222
|
@@ -180,10 +216,10 @@ model-index:
|
|
180 |
value: 0.2870370370370371
|
181 |
name: Cosine Precision@3
|
182 |
- type: cosine_precision@5
|
183 |
-
value: 0.
|
184 |
name: Cosine Precision@5
|
185 |
- type: cosine_precision@10
|
186 |
-
value: 0.
|
187 |
name: Cosine Precision@10
|
188 |
- type: cosine_recall@1
|
189 |
value: 0.7222222222222222
|
@@ -192,19 +228,19 @@ model-index:
|
|
192 |
value: 0.8611111111111112
|
193 |
name: Cosine Recall@3
|
194 |
- type: cosine_recall@5
|
195 |
-
value: 0.
|
196 |
name: Cosine Recall@5
|
197 |
- type: cosine_recall@10
|
198 |
-
value:
|
199 |
name: Cosine Recall@10
|
200 |
- type: cosine_ndcg@10
|
201 |
-
value: 0.
|
202 |
name: Cosine Ndcg@10
|
203 |
- type: cosine_mrr@10
|
204 |
-
value: 0.
|
205 |
name: Cosine Mrr@10
|
206 |
- type: cosine_map@100
|
207 |
-
value: 0.
|
208 |
name: Cosine Map@100
|
209 |
- task:
|
210 |
type: information-retrieval
|
@@ -217,46 +253,46 @@ model-index:
|
|
217 |
value: 0.6944444444444444
|
218 |
name: Cosine Accuracy@1
|
219 |
- type: cosine_accuracy@3
|
220 |
-
value: 0.
|
221 |
name: Cosine Accuracy@3
|
222 |
- type: cosine_accuracy@5
|
223 |
-
value: 0.
|
224 |
name: Cosine Accuracy@5
|
225 |
- type: cosine_accuracy@10
|
226 |
-
value:
|
227 |
name: Cosine Accuracy@10
|
228 |
- type: cosine_precision@1
|
229 |
value: 0.6944444444444444
|
230 |
name: Cosine Precision@1
|
231 |
- type: cosine_precision@3
|
232 |
-
value: 0.
|
233 |
name: Cosine Precision@3
|
234 |
- type: cosine_precision@5
|
235 |
-
value: 0.
|
236 |
name: Cosine Precision@5
|
237 |
- type: cosine_precision@10
|
238 |
-
value: 0.
|
239 |
name: Cosine Precision@10
|
240 |
- type: cosine_recall@1
|
241 |
value: 0.6944444444444444
|
242 |
name: Cosine Recall@1
|
243 |
- type: cosine_recall@3
|
244 |
-
value: 0.
|
245 |
name: Cosine Recall@3
|
246 |
- type: cosine_recall@5
|
247 |
-
value: 0.
|
248 |
name: Cosine Recall@5
|
249 |
- type: cosine_recall@10
|
250 |
-
value:
|
251 |
name: Cosine Recall@10
|
252 |
- type: cosine_ndcg@10
|
253 |
-
value: 0.
|
254 |
name: Cosine Ndcg@10
|
255 |
- type: cosine_mrr@10
|
256 |
-
value: 0.
|
257 |
name: Cosine Mrr@10
|
258 |
- type: cosine_map@100
|
259 |
-
value: 0.
|
260 |
name: Cosine Map@100
|
261 |
- task:
|
262 |
type: information-retrieval
|
@@ -266,49 +302,49 @@ model-index:
|
|
266 |
type: dim_256
|
267 |
metrics:
|
268 |
- type: cosine_accuracy@1
|
269 |
-
value: 0.
|
270 |
name: Cosine Accuracy@1
|
271 |
- type: cosine_accuracy@3
|
272 |
-
value: 0.
|
273 |
name: Cosine Accuracy@3
|
274 |
- type: cosine_accuracy@5
|
275 |
-
value: 0.
|
276 |
name: Cosine Accuracy@5
|
277 |
- type: cosine_accuracy@10
|
278 |
-
value:
|
279 |
name: Cosine Accuracy@10
|
280 |
- type: cosine_precision@1
|
281 |
-
value: 0.
|
282 |
name: Cosine Precision@1
|
283 |
- type: cosine_precision@3
|
284 |
-
value: 0.
|
285 |
name: Cosine Precision@3
|
286 |
- type: cosine_precision@5
|
287 |
-
value: 0.
|
288 |
name: Cosine Precision@5
|
289 |
- type: cosine_precision@10
|
290 |
-
value: 0.
|
291 |
name: Cosine Precision@10
|
292 |
- type: cosine_recall@1
|
293 |
-
value: 0.
|
294 |
name: Cosine Recall@1
|
295 |
- type: cosine_recall@3
|
296 |
-
value: 0.
|
297 |
name: Cosine Recall@3
|
298 |
- type: cosine_recall@5
|
299 |
-
value: 0.
|
300 |
name: Cosine Recall@5
|
301 |
- type: cosine_recall@10
|
302 |
-
value:
|
303 |
name: Cosine Recall@10
|
304 |
- type: cosine_ndcg@10
|
305 |
-
value: 0.
|
306 |
name: Cosine Ndcg@10
|
307 |
- type: cosine_mrr@10
|
308 |
-
value: 0.
|
309 |
name: Cosine Mrr@10
|
310 |
- type: cosine_map@100
|
311 |
-
value: 0.
|
312 |
name: Cosine Map@100
|
313 |
- task:
|
314 |
type: information-retrieval
|
@@ -318,49 +354,49 @@ model-index:
|
|
318 |
type: dim_128
|
319 |
metrics:
|
320 |
- type: cosine_accuracy@1
|
321 |
-
value: 0.
|
322 |
name: Cosine Accuracy@1
|
323 |
- type: cosine_accuracy@3
|
324 |
-
value: 0.
|
325 |
name: Cosine Accuracy@3
|
326 |
- type: cosine_accuracy@5
|
327 |
-
value: 0.
|
328 |
name: Cosine Accuracy@5
|
329 |
- type: cosine_accuracy@10
|
330 |
-
value: 0.
|
331 |
name: Cosine Accuracy@10
|
332 |
- type: cosine_precision@1
|
333 |
-
value: 0.
|
334 |
name: Cosine Precision@1
|
335 |
- type: cosine_precision@3
|
336 |
-
value: 0.
|
337 |
name: Cosine Precision@3
|
338 |
- type: cosine_precision@5
|
339 |
-
value: 0.
|
340 |
name: Cosine Precision@5
|
341 |
- type: cosine_precision@10
|
342 |
-
value: 0.
|
343 |
name: Cosine Precision@10
|
344 |
- type: cosine_recall@1
|
345 |
-
value: 0.
|
346 |
name: Cosine Recall@1
|
347 |
- type: cosine_recall@3
|
348 |
-
value: 0.
|
349 |
name: Cosine Recall@3
|
350 |
- type: cosine_recall@5
|
351 |
-
value: 0.
|
352 |
name: Cosine Recall@5
|
353 |
- type: cosine_recall@10
|
354 |
-
value: 0.
|
355 |
name: Cosine Recall@10
|
356 |
- type: cosine_ndcg@10
|
357 |
-
value: 0.
|
358 |
name: Cosine Ndcg@10
|
359 |
- type: cosine_mrr@10
|
360 |
-
value: 0.
|
361 |
name: Cosine Mrr@10
|
362 |
- type: cosine_map@100
|
363 |
-
value: 0.
|
364 |
name: Cosine Map@100
|
365 |
- task:
|
366 |
type: information-retrieval
|
@@ -370,49 +406,49 @@ model-index:
|
|
370 |
type: dim_64
|
371 |
metrics:
|
372 |
- type: cosine_accuracy@1
|
373 |
-
value: 0.
|
374 |
name: Cosine Accuracy@1
|
375 |
- type: cosine_accuracy@3
|
376 |
-
value: 0.
|
377 |
name: Cosine Accuracy@3
|
378 |
- type: cosine_accuracy@5
|
379 |
-
value: 0.
|
380 |
name: Cosine Accuracy@5
|
381 |
- type: cosine_accuracy@10
|
382 |
value: 0.9166666666666666
|
383 |
name: Cosine Accuracy@10
|
384 |
- type: cosine_precision@1
|
385 |
-
value: 0.
|
386 |
name: Cosine Precision@1
|
387 |
- type: cosine_precision@3
|
388 |
-
value: 0.
|
389 |
name: Cosine Precision@3
|
390 |
- type: cosine_precision@5
|
391 |
-
value: 0.
|
392 |
name: Cosine Precision@5
|
393 |
- type: cosine_precision@10
|
394 |
value: 0.09166666666666669
|
395 |
name: Cosine Precision@10
|
396 |
- type: cosine_recall@1
|
397 |
-
value: 0.
|
398 |
name: Cosine Recall@1
|
399 |
- type: cosine_recall@3
|
400 |
-
value: 0.
|
401 |
name: Cosine Recall@3
|
402 |
- type: cosine_recall@5
|
403 |
-
value: 0.
|
404 |
name: Cosine Recall@5
|
405 |
- type: cosine_recall@10
|
406 |
value: 0.9166666666666666
|
407 |
name: Cosine Recall@10
|
408 |
- type: cosine_ndcg@10
|
409 |
-
value: 0.
|
410 |
name: Cosine Ndcg@10
|
411 |
- type: cosine_mrr@10
|
412 |
-
value: 0.
|
413 |
name: Cosine Mrr@10
|
414 |
- type: cosine_map@100
|
415 |
-
value: 0.
|
416 |
name: Cosine Map@100
|
417 |
---
|
418 |
|
@@ -466,9 +502,9 @@ from sentence_transformers import SentenceTransformer
|
|
466 |
model = SentenceTransformer("densonsmith/modernbert-embed-quickb")
|
467 |
# Run inference
|
468 |
sentences = [
|
469 |
-
|
470 |
-
"
|
471 |
-
"
|
472 |
]
|
473 |
embeddings = model.encode(sentences)
|
474 |
print(embeddings.shape)
|
@@ -515,21 +551,21 @@ You can finetune this model on your own dataset.
|
|
515 |
|
516 |
| Metric | dim_768 | dim_512 | dim_256 | dim_128 | dim_64 |
|
517 |
|:--------------------|:-----------|:----------|:-----------|:-----------|:-----------|
|
518 |
-
| cosine_accuracy@1 | 0.7222 | 0.6944 | 0.
|
519 |
-
| cosine_accuracy@3 | 0.8611 | 0.
|
520 |
-
| cosine_accuracy@5 | 0.
|
521 |
-
| cosine_accuracy@10 |
|
522 |
-
| cosine_precision@1 | 0.7222 | 0.6944 | 0.
|
523 |
-
| cosine_precision@3 | 0.287 | 0.
|
524 |
-
| cosine_precision@5 | 0.
|
525 |
-
| cosine_precision@10 | 0.
|
526 |
-
| cosine_recall@1 | 0.7222 | 0.6944 | 0.
|
527 |
-
| cosine_recall@3 | 0.8611 | 0.
|
528 |
-
| cosine_recall@5 | 0.
|
529 |
-
| cosine_recall@10 |
|
530 |
-
| **cosine_ndcg@10** | **0.
|
531 |
-
| cosine_mrr@10 | 0.
|
532 |
-
| cosine_map@100 | 0.
|
533 |
|
534 |
<!--
|
535 |
## Bias, Risks and Limitations
|
@@ -549,19 +585,19 @@ You can finetune this model on your own dataset.
|
|
549 |
|
550 |
#### Unnamed Dataset
|
551 |
|
552 |
-
* Size:
|
553 |
* Columns: <code>anchor</code> and <code>positive</code>
|
554 |
-
* Approximate statistics based on the first
|
555 |
-
| | anchor | positive
|
556 |
-
|
557 |
-
| type | string | string
|
558 |
-
| details | <ul><li>min: 7 tokens</li><li>mean: 14.
|
559 |
* Samples:
|
560 |
-
| anchor
|
561 |
-
|
562 |
-
| <code>What
|
563 |
-
| <code>
|
564 |
-
| <code>What is the strength
|
565 |
* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
|
566 |
```json
|
567 |
{
|
@@ -724,10 +760,11 @@ You can finetune this model on your own dataset.
|
|
724 |
### Training Logs
|
725 |
| Epoch | Step | Training Loss | dim_768_cosine_ndcg@10 | dim_512_cosine_ndcg@10 | dim_256_cosine_ndcg@10 | dim_128_cosine_ndcg@10 | dim_64_cosine_ndcg@10 |
|
726 |
|:-------:|:------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|
|
727 |
-
| 1.0 |
|
728 |
-
|
|
729 |
-
| **
|
730 |
-
|
|
|
|
731 |
|
732 |
* The bold row denotes the saved checkpoint.
|
733 |
|
|
|
7 |
- sentence-similarity
|
8 |
- feature-extraction
|
9 |
- generated_from_trainer
|
10 |
+
- dataset_size:321
|
11 |
- loss:MatryoshkaLoss
|
12 |
- loss:MultipleNegativesRankingLoss
|
13 |
base_model: nomic-ai/modernbert-embed-base
|
14 |
widget:
|
15 |
+
- source_sentence: Since what year have they been married?
|
16 |
sentences:
|
17 |
+
- 'Graph: Team Coco Knowledge Graph
|
|
|
|
|
|
|
18 |
|
19 |
+
Node ID: 2015_conan_cuba
|
20 |
|
21 |
+
Category: events
|
22 |
|
23 |
+
Name: Conan in Cuba
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
|
25 |
+
Type: Event
|
26 |
|
|
|
27 |
|
28 |
+
Description: Conan O''Brien traveled to Havana to film a historic episode—the
|
29 |
+
first by an American late-night host in over 50 years—part of his ''Conan Without
|
30 |
+
Borders'' specials.
|
31 |
|
|
|
32 |
|
33 |
+
Relationships:
|
34 |
|
35 |
+
- Host conan_obrien
|
36 |
+
|
37 |
+
- Occurred during conan_tbs'
|
38 |
+
- 'Description: Liza Powel O''Brien is an American playwright and podcast host.
|
39 |
+
She met Conan O''Brien in 2000 while working at an advertising agency, and they
|
40 |
+
married in 2002. She has written numerous plays staged at theaters like the Geffen
|
41 |
+
Playhouse and Ojai Playwrights Conference, and in 2022 she launched the history
|
42 |
+
podcast "Significant Others" on Conan''s Team Coco network.'
|
43 |
+
- "Relationships:\n- Spouse conan_obrien (Strength: very strong)\n Description:\
|
44 |
+
\ Married since 2002; they have two children together.\n- Podcast host team_coco\
|
45 |
+
\ (Strength: moderate)\n Description: Hosts the \"Significant Others\" podcast\
|
46 |
+
\ under the Team Coco banner."
|
47 |
+
- source_sentence: Which team produced Conan's final late night episode?
|
48 |
sentences:
|
49 |
- 'Graph: Team Coco Knowledge Graph
|
50 |
|
51 |
+
Node ID: 2021_conan_finale
|
52 |
|
53 |
Category: events
|
54 |
|
55 |
+
Name: Conan''s Final Late Night Episode
|
56 |
|
57 |
Type: Event
|
58 |
|
59 |
|
60 |
+
Description: The final episode of ''Conan'' on TBS, marking the end of Conan O''Brien''s
|
61 |
+
28-year run as a late-night host with heartfelt goodbyes and memorable comedy
|
62 |
+
moments.
|
63 |
|
64 |
|
65 |
Relationships:
|
66 |
|
67 |
+
- Honoree conan_obrien
|
68 |
|
69 |
+
- Participant andy_richter
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
70 |
|
71 |
+
- Producer team_coco'
|
72 |
+
- 'References:
|
73 |
|
74 |
+
- ([Conan O''Brien - Wikipedia](https://en.wikipedia.org/wiki/Conan_O%27Brien))
|
75 |
|
76 |
+
- ([Andy Richter Net Worth | Celebrity Net Worth](https://www.celebritynetworth.com))'
|
77 |
+
- 'Description: Airing on SiriusXM''s Team Coco Radio channel.'
|
78 |
+
- source_sentence: What type of document is referenced for the tour?
|
79 |
sentences:
|
80 |
+
- "Relationships:\n- Late-night host conan_obrien (Strength: core talent)\n Description:\
|
81 |
+
\ Conan's break in late night came through NBC.\n- Production partner conaco (Strength:\
|
82 |
+
\ strong)\n Description: NBC worked with Conaco on Conan's shows.\n\nAwards and\
|
83 |
+
\ Recognitions:\n- Legacy of late-night programming"
|
84 |
- 'Major Events:
|
85 |
|
86 |
+
- 1993 Joined ''Late Night'' with Conan
|
87 |
|
88 |
+
- 2009 Transitioned to ''The Tonight Show''
|
89 |
+
|
90 |
+
- 2010 Concluded run as Conan''s bandleader'
|
91 |
+
- 'References:
|
92 |
+
|
93 |
+
- ([The Legally Prohibited from Being Funny on Television Tour - Wikipedia](https://en.wikipedia.org/wiki/The_Legally_Prohibited_from_Being_Funny_on_Television_Tour))'
|
94 |
+
- source_sentence: In what year did Triumph the Insult Comic Dog debut?
|
95 |
sentences:
|
96 |
+
- "Relationships:\n- Host-guest (Prankster) conan_obrien (Strength: moderate)\n\
|
97 |
+
\ Description: Repeatedly played the 'Mac and Me' gag, to Conan's feigned exasperation.\n\
|
98 |
+
\nMajor Events:\n- 2004 First Mac and Me Gag on 'Late Night'\n- 2021 Final TBS\
|
99 |
+
\ Show Prank cameo"
|
100 |
+
- 'Awards and Recognitions:
|
101 |
+
|
102 |
+
- MFA in Fiction Writing from Columbia University
|
103 |
+
|
104 |
+
- Playwright with works at the Geffen Playhouse and Ojai Playwrights Conference
|
105 |
+
|
106 |
+
- Host of the "Significant Others" podcast (2022–present)'
|
107 |
- 'Graph: Team Coco Knowledge Graph
|
108 |
|
109 |
+
Node ID: triumph_insult_comic_dog
|
110 |
|
111 |
+
Category: creative works
|
112 |
|
113 |
+
Name: Triumph the Insult Comic Dog
|
114 |
|
115 |
+
Type: Puppet character
|
116 |
|
117 |
|
118 |
+
Description: A recurring canine puppet character, voiced by Robert Smigel, that
|
119 |
+
debuted on Conan''s ''Late Night'' in 1997, known for roasting celebrities and
|
120 |
+
absurd humor.
|
121 |
+
|
122 |
+
|
123 |
+
Relationships:
|
124 |
+
|
125 |
+
- Creator/performer robert_smigel
|
126 |
+
|
127 |
+
- Host platform conan_obrien'
|
128 |
+
- source_sentence: Who are the hosts of The Conan & Jordan Show?
|
129 |
+
sentences:
|
130 |
+
- 'Awards and Recognitions:
|
131 |
|
132 |
+
- 7 Primetime Emmy nominations for writing on Conan''s shows
|
|
|
133 |
|
134 |
+
- 10 WGA Award nominations (with 2 wins)
|
135 |
|
136 |
+
- 2 Daytime Emmy nominations for Animated Program performance
|
137 |
+
|
138 |
+
|
139 |
+
Major Events:
|
140 |
+
|
141 |
+
- 1993 Late Night Debut – Joined Conan''s first show as sidekick.
|
142 |
+
|
143 |
+
- 2000 Departure – Left ''Late Night'' to pursue acting.
|
144 |
+
|
145 |
+
- 2010 Tour & TBS Move – Reunited with Conan on the live tour and TBS.'
|
146 |
+
- 'Graph: Team Coco Knowledge Graph
|
147 |
+
|
148 |
+
Node ID: the_conan_and_jordan_show
|
149 |
+
|
150 |
+
Category: shows
|
151 |
+
|
152 |
+
Name: The Conan & Jordan Show (radio program)
|
153 |
+
|
154 |
+
Type: Show
|
155 |
+
|
156 |
+
|
157 |
+
Description: A spin-off audio series on SiriusXM''s Team Coco Radio, launched
|
158 |
+
in 2023, featuring Conan O''Brien and Jordan Schlansky continuing their comedic
|
159 |
+
odd-couple dynamic.'
|
160 |
+
- 'Major Events:
|
161 |
+
|
162 |
+
- 2010 Premiere – ''Conan'' debuted on TBS.
|
163 |
+
|
164 |
+
- 2015 ''Conan Without Borders'' – International travel specials aired.
|
165 |
+
|
166 |
+
- 2021 Finale – Conan ended his TBS run.
|
167 |
+
|
168 |
+
|
169 |
+
References:
|
170 |
+
|
171 |
+
- ([Conan O''Brien - Wikipedia](https://en.wikipedia.org/wiki/Conan_O%27Brien))'
|
172 |
pipeline_tag: sentence-similarity
|
173 |
library_name: sentence-transformers
|
174 |
metrics:
|
|
|
204 |
value: 0.8611111111111112
|
205 |
name: Cosine Accuracy@3
|
206 |
- type: cosine_accuracy@5
|
207 |
+
value: 0.9166666666666666
|
208 |
name: Cosine Accuracy@5
|
209 |
- type: cosine_accuracy@10
|
210 |
+
value: 0.9444444444444444
|
211 |
name: Cosine Accuracy@10
|
212 |
- type: cosine_precision@1
|
213 |
value: 0.7222222222222222
|
|
|
216 |
value: 0.2870370370370371
|
217 |
name: Cosine Precision@3
|
218 |
- type: cosine_precision@5
|
219 |
+
value: 0.18333333333333338
|
220 |
name: Cosine Precision@5
|
221 |
- type: cosine_precision@10
|
222 |
+
value: 0.09444444444444446
|
223 |
name: Cosine Precision@10
|
224 |
- type: cosine_recall@1
|
225 |
value: 0.7222222222222222
|
|
|
228 |
value: 0.8611111111111112
|
229 |
name: Cosine Recall@3
|
230 |
- type: cosine_recall@5
|
231 |
+
value: 0.9166666666666666
|
232 |
name: Cosine Recall@5
|
233 |
- type: cosine_recall@10
|
234 |
+
value: 0.9444444444444444
|
235 |
name: Cosine Recall@10
|
236 |
- type: cosine_ndcg@10
|
237 |
+
value: 0.8363985989991439
|
238 |
name: Cosine Ndcg@10
|
239 |
- type: cosine_mrr@10
|
240 |
+
value: 0.800925925925926
|
241 |
name: Cosine Mrr@10
|
242 |
- type: cosine_map@100
|
243 |
+
value: 0.8041634291634291
|
244 |
name: Cosine Map@100
|
245 |
- task:
|
246 |
type: information-retrieval
|
|
|
253 |
value: 0.6944444444444444
|
254 |
name: Cosine Accuracy@1
|
255 |
- type: cosine_accuracy@3
|
256 |
+
value: 0.8888888888888888
|
257 |
name: Cosine Accuracy@3
|
258 |
- type: cosine_accuracy@5
|
259 |
+
value: 0.9166666666666666
|
260 |
name: Cosine Accuracy@5
|
261 |
- type: cosine_accuracy@10
|
262 |
+
value: 0.9722222222222222
|
263 |
name: Cosine Accuracy@10
|
264 |
- type: cosine_precision@1
|
265 |
value: 0.6944444444444444
|
266 |
name: Cosine Precision@1
|
267 |
- type: cosine_precision@3
|
268 |
+
value: 0.29629629629629634
|
269 |
name: Cosine Precision@3
|
270 |
- type: cosine_precision@5
|
271 |
+
value: 0.18333333333333335
|
272 |
name: Cosine Precision@5
|
273 |
- type: cosine_precision@10
|
274 |
+
value: 0.09722222222222224
|
275 |
name: Cosine Precision@10
|
276 |
- type: cosine_recall@1
|
277 |
value: 0.6944444444444444
|
278 |
name: Cosine Recall@1
|
279 |
- type: cosine_recall@3
|
280 |
+
value: 0.8888888888888888
|
281 |
name: Cosine Recall@3
|
282 |
- type: cosine_recall@5
|
283 |
+
value: 0.9166666666666666
|
284 |
name: Cosine Recall@5
|
285 |
- type: cosine_recall@10
|
286 |
+
value: 0.9722222222222222
|
287 |
name: Cosine Recall@10
|
288 |
- type: cosine_ndcg@10
|
289 |
+
value: 0.8349701465406345
|
290 |
name: Cosine Ndcg@10
|
291 |
- type: cosine_mrr@10
|
292 |
+
value: 0.7909722222222222
|
293 |
name: Cosine Mrr@10
|
294 |
- type: cosine_map@100
|
295 |
+
value: 0.791703216374269
|
296 |
name: Cosine Map@100
|
297 |
- task:
|
298 |
type: information-retrieval
|
|
|
302 |
type: dim_256
|
303 |
metrics:
|
304 |
- type: cosine_accuracy@1
|
305 |
+
value: 0.6666666666666666
|
306 |
name: Cosine Accuracy@1
|
307 |
- type: cosine_accuracy@3
|
308 |
+
value: 0.8611111111111112
|
309 |
name: Cosine Accuracy@3
|
310 |
- type: cosine_accuracy@5
|
311 |
+
value: 0.9166666666666666
|
312 |
name: Cosine Accuracy@5
|
313 |
- type: cosine_accuracy@10
|
314 |
+
value: 0.9444444444444444
|
315 |
name: Cosine Accuracy@10
|
316 |
- type: cosine_precision@1
|
317 |
+
value: 0.6666666666666666
|
318 |
name: Cosine Precision@1
|
319 |
- type: cosine_precision@3
|
320 |
+
value: 0.28703703703703703
|
321 |
name: Cosine Precision@3
|
322 |
- type: cosine_precision@5
|
323 |
+
value: 0.18333333333333335
|
324 |
name: Cosine Precision@5
|
325 |
- type: cosine_precision@10
|
326 |
+
value: 0.09444444444444446
|
327 |
name: Cosine Precision@10
|
328 |
- type: cosine_recall@1
|
329 |
+
value: 0.6666666666666666
|
330 |
name: Cosine Recall@1
|
331 |
- type: cosine_recall@3
|
332 |
+
value: 0.8611111111111112
|
333 |
name: Cosine Recall@3
|
334 |
- type: cosine_recall@5
|
335 |
+
value: 0.9166666666666666
|
336 |
name: Cosine Recall@5
|
337 |
- type: cosine_recall@10
|
338 |
+
value: 0.9444444444444444
|
339 |
name: Cosine Recall@10
|
340 |
- type: cosine_ndcg@10
|
341 |
+
value: 0.8074890903790802
|
342 |
name: Cosine Ndcg@10
|
343 |
- type: cosine_mrr@10
|
344 |
+
value: 0.7627314814814814
|
345 |
name: Cosine Mrr@10
|
346 |
- type: cosine_map@100
|
347 |
+
value: 0.7662037037037037
|
348 |
name: Cosine Map@100
|
349 |
- task:
|
350 |
type: information-retrieval
|
|
|
354 |
type: dim_128
|
355 |
metrics:
|
356 |
- type: cosine_accuracy@1
|
357 |
+
value: 0.6388888888888888
|
358 |
name: Cosine Accuracy@1
|
359 |
- type: cosine_accuracy@3
|
360 |
+
value: 0.8611111111111112
|
361 |
name: Cosine Accuracy@3
|
362 |
- type: cosine_accuracy@5
|
363 |
+
value: 0.9166666666666666
|
364 |
name: Cosine Accuracy@5
|
365 |
- type: cosine_accuracy@10
|
366 |
+
value: 0.9444444444444444
|
367 |
name: Cosine Accuracy@10
|
368 |
- type: cosine_precision@1
|
369 |
+
value: 0.6388888888888888
|
370 |
name: Cosine Precision@1
|
371 |
- type: cosine_precision@3
|
372 |
+
value: 0.2870370370370371
|
373 |
name: Cosine Precision@3
|
374 |
- type: cosine_precision@5
|
375 |
+
value: 0.18333333333333338
|
376 |
name: Cosine Precision@5
|
377 |
- type: cosine_precision@10
|
378 |
+
value: 0.09444444444444446
|
379 |
name: Cosine Precision@10
|
380 |
- type: cosine_recall@1
|
381 |
+
value: 0.6388888888888888
|
382 |
name: Cosine Recall@1
|
383 |
- type: cosine_recall@3
|
384 |
+
value: 0.8611111111111112
|
385 |
name: Cosine Recall@3
|
386 |
- type: cosine_recall@5
|
387 |
+
value: 0.9166666666666666
|
388 |
name: Cosine Recall@5
|
389 |
- type: cosine_recall@10
|
390 |
+
value: 0.9444444444444444
|
391 |
name: Cosine Recall@10
|
392 |
- type: cosine_ndcg@10
|
393 |
+
value: 0.803777679552595
|
394 |
name: Cosine Ndcg@10
|
395 |
- type: cosine_mrr@10
|
396 |
+
value: 0.7574074074074074
|
397 |
name: Cosine Mrr@10
|
398 |
- type: cosine_map@100
|
399 |
+
value: 0.7597654530591711
|
400 |
name: Cosine Map@100
|
401 |
- task:
|
402 |
type: information-retrieval
|
|
|
406 |
type: dim_64
|
407 |
metrics:
|
408 |
- type: cosine_accuracy@1
|
409 |
+
value: 0.6111111111111112
|
410 |
name: Cosine Accuracy@1
|
411 |
- type: cosine_accuracy@3
|
412 |
+
value: 0.7777777777777778
|
413 |
name: Cosine Accuracy@3
|
414 |
- type: cosine_accuracy@5
|
415 |
+
value: 0.8333333333333334
|
416 |
name: Cosine Accuracy@5
|
417 |
- type: cosine_accuracy@10
|
418 |
value: 0.9166666666666666
|
419 |
name: Cosine Accuracy@10
|
420 |
- type: cosine_precision@1
|
421 |
+
value: 0.6111111111111112
|
422 |
name: Cosine Precision@1
|
423 |
- type: cosine_precision@3
|
424 |
+
value: 0.2592592592592593
|
425 |
name: Cosine Precision@3
|
426 |
- type: cosine_precision@5
|
427 |
+
value: 0.16666666666666669
|
428 |
name: Cosine Precision@5
|
429 |
- type: cosine_precision@10
|
430 |
value: 0.09166666666666669
|
431 |
name: Cosine Precision@10
|
432 |
- type: cosine_recall@1
|
433 |
+
value: 0.6111111111111112
|
434 |
name: Cosine Recall@1
|
435 |
- type: cosine_recall@3
|
436 |
+
value: 0.7777777777777778
|
437 |
name: Cosine Recall@3
|
438 |
- type: cosine_recall@5
|
439 |
+
value: 0.8333333333333334
|
440 |
name: Cosine Recall@5
|
441 |
- type: cosine_recall@10
|
442 |
value: 0.9166666666666666
|
443 |
name: Cosine Recall@10
|
444 |
- type: cosine_ndcg@10
|
445 |
+
value: 0.7608354868794361
|
446 |
name: Cosine Ndcg@10
|
447 |
- type: cosine_mrr@10
|
448 |
+
value: 0.7111441798941799
|
449 |
name: Cosine Mrr@10
|
450 |
- type: cosine_map@100
|
451 |
+
value: 0.7139831037236697
|
452 |
name: Cosine Map@100
|
453 |
---
|
454 |
|
|
|
502 |
model = SentenceTransformer("densonsmith/modernbert-embed-quickb")
|
503 |
# Run inference
|
504 |
sentences = [
|
505 |
+
'Who are the hosts of The Conan & Jordan Show?',
|
506 |
+
"Graph: Team Coco Knowledge Graph\nNode ID: the_conan_and_jordan_show\nCategory: shows\nName: The Conan & Jordan Show (radio program)\nType: Show\n\nDescription: A spin-off audio series on SiriusXM's Team Coco Radio, launched in 2023, featuring Conan O'Brien and Jordan Schlansky continuing their comedic odd-couple dynamic.",
|
507 |
+
"Awards and Recognitions:\n- 7 Primetime Emmy nominations for writing on Conan's shows\n- 10 WGA Award nominations (with 2 wins)\n- 2 Daytime Emmy nominations for Animated Program performance\n\nMajor Events:\n- 1993 Late Night Debut – Joined Conan's first show as sidekick.\n- 2000 Departure – Left 'Late Night' to pursue acting.\n- 2010 Tour & TBS Move – Reunited with Conan on the live tour and TBS.",
|
508 |
]
|
509 |
embeddings = model.encode(sentences)
|
510 |
print(embeddings.shape)
|
|
|
551 |
|
552 |
| Metric | dim_768 | dim_512 | dim_256 | dim_128 | dim_64 |
|
553 |
|:--------------------|:-----------|:----------|:-----------|:-----------|:-----------|
|
554 |
+
| cosine_accuracy@1 | 0.7222 | 0.6944 | 0.6667 | 0.6389 | 0.6111 |
|
555 |
+
| cosine_accuracy@3 | 0.8611 | 0.8889 | 0.8611 | 0.8611 | 0.7778 |
|
556 |
+
| cosine_accuracy@5 | 0.9167 | 0.9167 | 0.9167 | 0.9167 | 0.8333 |
|
557 |
+
| cosine_accuracy@10 | 0.9444 | 0.9722 | 0.9444 | 0.9444 | 0.9167 |
|
558 |
+
| cosine_precision@1 | 0.7222 | 0.6944 | 0.6667 | 0.6389 | 0.6111 |
|
559 |
+
| cosine_precision@3 | 0.287 | 0.2963 | 0.287 | 0.287 | 0.2593 |
|
560 |
+
| cosine_precision@5 | 0.1833 | 0.1833 | 0.1833 | 0.1833 | 0.1667 |
|
561 |
+
| cosine_precision@10 | 0.0944 | 0.0972 | 0.0944 | 0.0944 | 0.0917 |
|
562 |
+
| cosine_recall@1 | 0.7222 | 0.6944 | 0.6667 | 0.6389 | 0.6111 |
|
563 |
+
| cosine_recall@3 | 0.8611 | 0.8889 | 0.8611 | 0.8611 | 0.7778 |
|
564 |
+
| cosine_recall@5 | 0.9167 | 0.9167 | 0.9167 | 0.9167 | 0.8333 |
|
565 |
+
| cosine_recall@10 | 0.9444 | 0.9722 | 0.9444 | 0.9444 | 0.9167 |
|
566 |
+
| **cosine_ndcg@10** | **0.8364** | **0.835** | **0.8075** | **0.8038** | **0.7608** |
|
567 |
+
| cosine_mrr@10 | 0.8009 | 0.791 | 0.7627 | 0.7574 | 0.7111 |
|
568 |
+
| cosine_map@100 | 0.8042 | 0.7917 | 0.7662 | 0.7598 | 0.714 |
|
569 |
|
570 |
<!--
|
571 |
## Bias, Risks and Limitations
|
|
|
585 |
|
586 |
#### Unnamed Dataset
|
587 |
|
588 |
+
* Size: 321 training samples
|
589 |
* Columns: <code>anchor</code> and <code>positive</code>
|
590 |
+
* Approximate statistics based on the first 321 samples:
|
591 |
+
| | anchor | positive |
|
592 |
+
|:--------|:----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
|
593 |
+
| type | string | string |
|
594 |
+
| details | <ul><li>min: 7 tokens</li><li>mean: 14.03 tokens</li><li>max: 24 tokens</li></ul> | <ul><li>min: 15 tokens</li><li>mean: 74.79 tokens</li><li>max: 117 tokens</li></ul> |
|
595 |
* Samples:
|
596 |
+
| anchor | positive |
|
597 |
+
|:--------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
598 |
+
| <code>What brand did Jeff Ross help establish?</code> | <code>Graph: Team Coco Knowledge Graph<br>Node ID: jeff_ross_producer<br>Category: people<br>Name: Jeff Ross (Producer)<br>Type: Person<br><br>Description: Jeff Ross is a television producer who has served as Conan O'Brien's executive producer since 1993. He is a key business partner in Conan's media ventures and helped establish the Team Coco brand.</code> |
|
599 |
+
| <code>In what year did Conan O'Brien launch the travel show 'Conan O'Brien Must Go'?</code> | <code>Description: Conan O'Brien is an American television host, comedian, writer, actor, and producer, best known for hosting late-night shows including "Late Night with Conan O'Brien", "The Tonight Show with Conan O'Brien", and "Conan". He also hosts the podcast "Conan O'Brien Needs a Friend" and, in 2024, launched the travel show "Conan O'Brien Must Go" on Max.</code> |
|
600 |
+
| <code>What is the strength of the network TBS?</code> | <code>- Network tbs (Strength: parent)<br> Description: TBS provided the platform for the show.</code> |
|
601 |
* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
|
602 |
```json
|
603 |
{
|
|
|
760 |
### Training Logs
|
761 |
| Epoch | Step | Training Loss | dim_768_cosine_ndcg@10 | dim_512_cosine_ndcg@10 | dim_256_cosine_ndcg@10 | dim_128_cosine_ndcg@10 | dim_64_cosine_ndcg@10 |
|
762 |
|:-------:|:------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|
|
763 |
+
| 1.0 | 6 | - | 0.7909 | 0.8034 | 0.7711 | 0.7992 | 0.6908 |
|
764 |
+
| 1.7901 | 10 | 16.3044 | - | - | - | - | - |
|
765 |
+
| **2.0** | **12** | **-** | **0.8364** | **0.8294** | **0.8022** | **0.8038** | **0.7691** |
|
766 |
+
| 3.0 | 18 | - | 0.8364 | 0.8313 | 0.8059 | 0.7938 | 0.7599 |
|
767 |
+
| 3.3951 | 20 | 5.6348 | 0.8364 | 0.8350 | 0.8075 | 0.8038 | 0.7608 |
|
768 |
|
769 |
* The bold row denotes the saved checkpoint.
|
770 |
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 596070136
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0e8097896bbf1d21fed4e34fc84e2ba906a3dd91944327abe7cfb599b5adc63
|
3 |
size 596070136
|