multi stage tuning
Browse files- README.md +322 -324
- model.safetensors +1 -1
README.md
CHANGED
@@ -6,7 +6,7 @@ tags:
|
|
6 |
- sentence-similarity
|
7 |
- feature-extraction
|
8 |
- generated_from_trainer
|
9 |
-
- dataset_size:
|
10 |
- loss:TripletLoss
|
11 |
datasets: []
|
12 |
metrics:
|
@@ -38,52 +38,48 @@ metrics:
|
|
38 |
- dot_mrr@10
|
39 |
- dot_map@10
|
40 |
widget:
|
41 |
-
- source_sentence: 'search_query:
|
42 |
sentences:
|
43 |
-
- 'search_document:
|
44 |
-
|
45 |
-
|
46 |
-
|
47 |
-
|
48 |
-
-
|
|
|
49 |
sentences:
|
50 |
-
- 'search_document:
|
51 |
-
|
52 |
-
|
53 |
-
|
54 |
-
|
55 |
-
- 'search_document:
|
56 |
-
|
57 |
-
|
|
|
58 |
sentences:
|
59 |
-
- 'search_document:
|
60 |
-
|
61 |
-
|
62 |
-
|
63 |
-
|
64 |
-
|
65 |
-
|
66 |
-
LSK, Black'
|
67 |
-
- source_sentence: 'search_query: cozy lights bedroom'
|
68 |
sentences:
|
69 |
-
- 'search_document:
|
70 |
-
|
71 |
-
|
72 |
-
|
73 |
-
|
74 |
-
|
75 |
-
- 'search_document: PARMIDA 6 inch Dimmable LED Square Recessed Retrofit Lighting,
|
76 |
-
Easy Downlight Installation, 12W (100W Eqv.), 950lm, Ceiling Can Lights, Energy
|
77 |
-
Star & ETL-Listed, 5 Year Warranty, 3000K - 4 Pack, Parmida LED Technologies,
|
78 |
-
3000k (Soft White)'
|
79 |
-
- source_sentence: 'search_query: punxhing bag'
|
80 |
sentences:
|
81 |
-
- 'search_document:
|
82 |
-
|
83 |
-
|
84 |
-
|
85 |
-
|
86 |
-
|
|
|
87 |
pipeline_tag: sentence-similarity
|
88 |
model-index:
|
89 |
- name: SentenceTransformer
|
@@ -96,19 +92,19 @@ model-index:
|
|
96 |
type: unknown
|
97 |
metrics:
|
98 |
- type: cosine_accuracy
|
99 |
-
value: 0.
|
100 |
name: Cosine Accuracy
|
101 |
- type: dot_accuracy
|
102 |
-
value: 0.
|
103 |
name: Dot Accuracy
|
104 |
- type: manhattan_accuracy
|
105 |
-
value: 0.
|
106 |
name: Manhattan Accuracy
|
107 |
- type: euclidean_accuracy
|
108 |
-
value: 0.
|
109 |
name: Euclidean Accuracy
|
110 |
- type: max_accuracy
|
111 |
-
value: 0.
|
112 |
name: Max Accuracy
|
113 |
- task:
|
114 |
type: semantic-similarity
|
@@ -118,34 +114,34 @@ model-index:
|
|
118 |
type: unknown
|
119 |
metrics:
|
120 |
- type: pearson_cosine
|
121 |
-
value: 0.
|
122 |
name: Pearson Cosine
|
123 |
- type: spearman_cosine
|
124 |
-
value: 0.
|
125 |
name: Spearman Cosine
|
126 |
- type: pearson_manhattan
|
127 |
-
value: 0.
|
128 |
name: Pearson Manhattan
|
129 |
- type: spearman_manhattan
|
130 |
-
value: 0.
|
131 |
name: Spearman Manhattan
|
132 |
- type: pearson_euclidean
|
133 |
-
value: 0.
|
134 |
name: Pearson Euclidean
|
135 |
- type: spearman_euclidean
|
136 |
-
value: 0.
|
137 |
name: Spearman Euclidean
|
138 |
- type: pearson_dot
|
139 |
-
value: 0.
|
140 |
name: Pearson Dot
|
141 |
- type: spearman_dot
|
142 |
-
value: 0.
|
143 |
name: Spearman Dot
|
144 |
- type: pearson_max
|
145 |
-
value: 0.
|
146 |
name: Pearson Max
|
147 |
- type: spearman_max
|
148 |
-
value: 0.
|
149 |
name: Spearman Max
|
150 |
- task:
|
151 |
type: information-retrieval
|
@@ -155,40 +151,40 @@ model-index:
|
|
155 |
type: unknown
|
156 |
metrics:
|
157 |
- type: cosine_accuracy@10
|
158 |
-
value: 0.
|
159 |
name: Cosine Accuracy@10
|
160 |
- type: cosine_precision@10
|
161 |
-
value: 0.
|
162 |
name: Cosine Precision@10
|
163 |
- type: cosine_recall@10
|
164 |
-
value: 0.
|
165 |
name: Cosine Recall@10
|
166 |
- type: cosine_ndcg@10
|
167 |
-
value: 0.
|
168 |
name: Cosine Ndcg@10
|
169 |
- type: cosine_mrr@10
|
170 |
-
value: 0.
|
171 |
name: Cosine Mrr@10
|
172 |
- type: cosine_map@10
|
173 |
-
value: 0.
|
174 |
name: Cosine Map@10
|
175 |
- type: dot_accuracy@10
|
176 |
-
value: 0.
|
177 |
name: Dot Accuracy@10
|
178 |
- type: dot_precision@10
|
179 |
-
value: 0.
|
180 |
name: Dot Precision@10
|
181 |
- type: dot_recall@10
|
182 |
-
value: 0.
|
183 |
name: Dot Recall@10
|
184 |
- type: dot_ndcg@10
|
185 |
-
value: 0.
|
186 |
name: Dot Ndcg@10
|
187 |
- type: dot_mrr@10
|
188 |
-
value: 0.
|
189 |
name: Dot Mrr@10
|
190 |
- type: dot_map@10
|
191 |
-
value: 0.
|
192 |
name: Dot Map@10
|
193 |
---
|
194 |
|
@@ -242,9 +238,9 @@ from sentence_transformers import SentenceTransformer
|
|
242 |
model = SentenceTransformer("lv12/esci-nomic-embed-text-v1_5_4")
|
243 |
# Run inference
|
244 |
sentences = [
|
245 |
-
'search_query:
|
246 |
-
'search_document:
|
247 |
-
'search_document:
|
248 |
]
|
249 |
embeddings = model.encode(sentences)
|
250 |
print(embeddings.shape)
|
@@ -290,11 +286,11 @@ You can finetune this model on your own dataset.
|
|
290 |
|
291 |
| Metric | Value |
|
292 |
|:--------------------|:-----------|
|
293 |
-
| **cosine_accuracy** | **0.
|
294 |
-
| dot_accuracy | 0.
|
295 |
-
| manhattan_accuracy | 0.
|
296 |
-
| euclidean_accuracy | 0.
|
297 |
-
| max_accuracy | 0.
|
298 |
|
299 |
#### Semantic Similarity
|
300 |
|
@@ -302,16 +298,16 @@ You can finetune this model on your own dataset.
|
|
302 |
|
303 |
| Metric | Value |
|
304 |
|:--------------------|:-----------|
|
305 |
-
| pearson_cosine | 0.
|
306 |
-
| **spearman_cosine** | **0.
|
307 |
-
| pearson_manhattan | 0.
|
308 |
-
| spearman_manhattan | 0.
|
309 |
-
| pearson_euclidean | 0.
|
310 |
-
| spearman_euclidean | 0.
|
311 |
-
| pearson_dot | 0.
|
312 |
-
| spearman_dot | 0.
|
313 |
-
| pearson_max | 0.
|
314 |
-
| spearman_max | 0.
|
315 |
|
316 |
#### Information Retrieval
|
317 |
|
@@ -319,18 +315,18 @@ You can finetune this model on your own dataset.
|
|
319 |
|
320 |
| Metric | Value |
|
321 |
|:--------------------|:-----------|
|
322 |
-
| cosine_accuracy@10 | 0.
|
323 |
-
| cosine_precision@10 | 0.
|
324 |
-
| cosine_recall@10 | 0.
|
325 |
-
| cosine_ndcg@10 | 0.
|
326 |
-
| cosine_mrr@10 | 0.
|
327 |
-
| **cosine_map@10** | **0.
|
328 |
-
| dot_accuracy@10 | 0.
|
329 |
-
| dot_precision@10 | 0.
|
330 |
-
| dot_recall@10 | 0.
|
331 |
-
| dot_ndcg@10 | 0.
|
332 |
-
| dot_mrr@10 | 0.
|
333 |
-
| dot_map@10 | 0.
|
334 |
|
335 |
<!--
|
336 |
## Bias, Risks and Limitations
|
@@ -351,24 +347,24 @@ You can finetune this model on your own dataset.
|
|
351 |
#### triplets
|
352 |
|
353 |
* Dataset: triplets
|
354 |
-
* Size: 1,
|
355 |
* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
|
356 |
* Approximate statistics based on the first 1000 samples:
|
357 |
-
| | anchor
|
358 |
-
|
359 |
-
| type | string
|
360 |
-
| details | <ul><li>min: 7 tokens</li><li>mean: 11.
|
361 |
* Samples:
|
362 |
-
| anchor
|
363 |
-
|
364 |
-
| <code>search_query:
|
365 |
-
| <code>search_query:
|
366 |
-
| <code>search_query:
|
367 |
* Loss: [<code>TripletLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#tripletloss) with these parameters:
|
368 |
```json
|
369 |
{
|
370 |
"distance_metric": "TripletDistanceMetric.COSINE",
|
371 |
-
"triplet_margin": 0.
|
372 |
}
|
373 |
```
|
374 |
|
@@ -377,37 +373,39 @@ You can finetune this model on your own dataset.
|
|
377 |
#### triplets
|
378 |
|
379 |
* Dataset: triplets
|
380 |
-
* Size:
|
381 |
* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
|
382 |
* Approximate statistics based on the first 1000 samples:
|
383 |
-
| | anchor | positive | negative
|
384 |
-
|
385 |
-
| type | string | string | string
|
386 |
-
| details | <ul><li>min: 7 tokens</li><li>mean: 11.
|
387 |
* Samples:
|
388 |
-
| anchor
|
389 |
-
|
390 |
-
| <code>search_query:
|
391 |
-
| <code>search_query:
|
392 |
-
| <code>search_query:
|
393 |
* Loss: [<code>TripletLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#tripletloss) with these parameters:
|
394 |
```json
|
395 |
{
|
396 |
"distance_metric": "TripletDistanceMetric.COSINE",
|
397 |
-
"triplet_margin": 0.
|
398 |
}
|
399 |
```
|
400 |
|
401 |
### Training Hyperparameters
|
402 |
#### Non-Default Hyperparameters
|
403 |
|
404 |
-
- `per_device_train_batch_size`:
|
405 |
- `per_device_eval_batch_size`: 16
|
406 |
- `gradient_accumulation_steps`: 2
|
407 |
- `learning_rate`: 1e-07
|
|
|
408 |
- `lr_scheduler_type`: polynomial
|
409 |
- `lr_scheduler_kwargs`: {'lr_end': 1e-08, 'power': 2.0}
|
410 |
- `warmup_ratio`: 0.05
|
|
|
411 |
- `dataloader_num_workers`: 4
|
412 |
- `dataloader_prefetch_factor`: 4
|
413 |
- `load_best_model_at_end`: True
|
@@ -421,7 +419,7 @@ You can finetune this model on your own dataset.
|
|
421 |
- `overwrite_output_dir`: False
|
422 |
- `do_predict`: False
|
423 |
- `prediction_loss_only`: True
|
424 |
-
- `per_device_train_batch_size`:
|
425 |
- `per_device_eval_batch_size`: 16
|
426 |
- `per_gpu_train_batch_size`: None
|
427 |
- `per_gpu_eval_batch_size`: None
|
@@ -433,7 +431,7 @@ You can finetune this model on your own dataset.
|
|
433 |
- `adam_beta2`: 0.999
|
434 |
- `adam_epsilon`: 1e-08
|
435 |
- `max_grad_norm`: 1.0
|
436 |
-
- `num_train_epochs`:
|
437 |
- `max_steps`: -1
|
438 |
- `lr_scheduler_type`: polynomial
|
439 |
- `lr_scheduler_kwargs`: {'lr_end': 1e-08, 'power': 2.0}
|
@@ -529,206 +527,206 @@ You can finetune this model on your own dataset.
|
|
529 |
|
530 |
| Epoch | Step | Training Loss | triplets loss | cosine_accuracy | cosine_map@10 | spearman_cosine |
|
531 |
|:------:|:----:|:-------------:|:-------------:|:---------------:|:-------------:|:---------------:|
|
532 |
-
| 0.
|
533 |
-
| 0.
|
534 |
-
| 0.
|
535 |
-
| 0.
|
536 |
-
| 0.
|
537 |
-
| 0.
|
538 |
-
| 0.
|
539 |
-
| 0.
|
540 |
-
| 0.
|
541 |
-
| 0.
|
542 |
-
| 0.
|
543 |
-
| 0.
|
544 |
-
| 0.
|
545 |
-
| 0.
|
546 |
-
| 0.
|
547 |
-
| 0.
|
548 |
-
| 0.
|
549 |
-
| 0.
|
550 |
-
| 0.
|
551 |
-
| 0.
|
552 |
-
| 0.
|
553 |
-
| 0.
|
554 |
-
| 0.
|
555 |
-
| 0.
|
556 |
-
| 0.
|
557 |
-
| 0.
|
558 |
-
| 0.
|
559 |
-
| 0.
|
560 |
-
| 0.
|
561 |
-
| 0.
|
562 |
-
| 0.
|
563 |
-
| 0.
|
564 |
-
| 0.
|
565 |
-
| 0.
|
566 |
-
| 0.
|
567 |
-
| 0.
|
568 |
-
| 0.
|
569 |
-
| 0.
|
570 |
-
| 0.
|
571 |
-
| 0.
|
572 |
-
| 0.
|
573 |
-
| 0.
|
574 |
-
| 0.
|
575 |
-
| 0.
|
576 |
-
| 0.
|
577 |
-
| 0.
|
578 |
-
| 0.
|
579 |
-
| 0.
|
580 |
-
| 0.
|
581 |
-
| 0.
|
582 |
-
| 0.
|
583 |
-
| 0.
|
584 |
-
| 0.
|
585 |
-
| 0.
|
586 |
-
| 0.
|
587 |
-
| 0.
|
588 |
-
| 0.
|
589 |
-
| 0.
|
590 |
-
| 0.
|
591 |
-
| 0.
|
592 |
-
| 0.
|
593 |
-
| 0.
|
594 |
-
| 0.
|
595 |
-
| 0.
|
596 |
-
| 0.
|
597 |
-
| 0.
|
598 |
-
| 0.
|
599 |
-
| 0.
|
600 |
-
| 0.
|
601 |
-
| 0.
|
602 |
-
| 0.
|
603 |
-
| 0.
|
604 |
-
| 0.
|
605 |
-
| 0.
|
606 |
-
| 0.
|
607 |
-
| 0.
|
608 |
-
| 0.
|
609 |
-
| 0.
|
610 |
-
| 0.
|
611 |
-
| 0.
|
612 |
-
| 0.
|
613 |
-
| 0.
|
614 |
-
| 0.
|
615 |
-
| 0.
|
616 |
-
| 0.
|
617 |
-
| 0.
|
618 |
-
| 0.
|
619 |
-
| 0.
|
620 |
-
| 0.
|
621 |
-
| 0.
|
622 |
-
| 0.
|
623 |
-
| 0.
|
624 |
-
| 0.
|
625 |
-
| 0.
|
626 |
-
| 0.
|
627 |
-
| 0.
|
628 |
-
| 0.
|
629 |
-
| 0.
|
630 |
-
| 0.
|
631 |
-
| 0.
|
632 |
-
| 0.
|
633 |
-
| 0.
|
634 |
-
| 0.
|
635 |
-
| 0.
|
636 |
-
| 0.
|
637 |
-
| 0.
|
638 |
-
| 0.
|
639 |
-
| 0.
|
640 |
-
| 0.
|
641 |
-
| 0.
|
642 |
-
| 0.
|
643 |
-
| 0.
|
644 |
-
| 0.
|
645 |
-
| 0.
|
646 |
-
| 0.
|
647 |
-
| 0.
|
648 |
-
| 0.
|
649 |
-
| 0.
|
650 |
-
| 0.
|
651 |
-
| 0.
|
652 |
-
| 0.
|
653 |
-
| 0.
|
654 |
-
| 0.
|
655 |
-
| 0.
|
656 |
-
| 0.
|
657 |
-
| 0.
|
658 |
-
| 0.
|
659 |
-
| 0.
|
660 |
-
| 0.
|
661 |
-
| 0.
|
662 |
-
| 0.
|
663 |
-
| 0.
|
664 |
-
| 0.
|
665 |
-
| 0.
|
666 |
-
| 0.
|
667 |
-
| 0.
|
668 |
-
| 0.
|
669 |
-
| 0.
|
670 |
-
| 0.
|
671 |
-
| 0.
|
672 |
-
| 0.
|
673 |
-
| 0.
|
674 |
-
| 0.
|
675 |
-
| 0.
|
676 |
-
| 0.
|
677 |
-
| 0.
|
678 |
-
| 0.
|
679 |
-
| 0.
|
680 |
-
| 0.
|
681 |
-
| 0.
|
682 |
-
| 0.
|
683 |
-
| 0.
|
684 |
-
| 0.
|
685 |
-
| 0.
|
686 |
-
| 0.
|
687 |
-
| 0.
|
688 |
-
| 0.
|
689 |
-
| 0.
|
690 |
-
| 0.
|
691 |
-
| 0.
|
692 |
-
| 0.
|
693 |
-
| 0.
|
694 |
-
| 0.
|
695 |
-
| 0.
|
696 |
-
| 0.
|
697 |
-
| 0.
|
698 |
-
| 0.
|
699 |
-
| 0.
|
700 |
-
| 0.
|
701 |
-
| 0.
|
702 |
-
| 0.
|
703 |
-
| 0.
|
704 |
-
| 0.
|
705 |
-
| 0.
|
706 |
-
| 0.
|
707 |
-
| 0.
|
708 |
-
| 0.
|
709 |
-
| 0.
|
710 |
-
| 0.
|
711 |
-
| 0.
|
712 |
-
| 0.
|
713 |
-
| 0.
|
714 |
-
| 0.
|
715 |
-
| 0.
|
716 |
-
| 0.
|
717 |
-
| 0.
|
718 |
-
| 0.
|
719 |
-
| 0.
|
720 |
-
| 0.
|
721 |
-
| 0.
|
722 |
-
| 0.
|
723 |
-
| 0.
|
724 |
-
| 0.
|
725 |
-
| 0.
|
726 |
-
| 0.
|
727 |
-
| 0.
|
728 |
-
| 0.
|
729 |
-
| 0.
|
730 |
-
| 0.
|
731 |
-
| 0.
|
732 |
|
733 |
</details>
|
734 |
|
|
|
6 |
- sentence-similarity
|
7 |
- feature-extraction
|
8 |
- generated_from_trainer
|
9 |
+
- dataset_size:1600000
|
10 |
- loss:TripletLoss
|
11 |
datasets: []
|
12 |
metrics:
|
|
|
38 |
- dot_mrr@10
|
39 |
- dot_map@10
|
40 |
widget:
|
41 |
+
- source_sentence: 'search_query: pokemon card mewtwo'
|
42 |
sentences:
|
43 |
+
- 'search_document: Personal AM/FM Pocket Radio Portable VR-robot, Mini Digital
|
44 |
+
Tuning Walkman Radio, with Rechargeable Battery, Earphone, Lock Screen for Walk/Jogging/Gym/Camping,
|
45 |
+
VR-robot, Electronics'
|
46 |
+
- 'search_document: Pokemon Mewtwo & Pikachu XY Evolutions TCG Card Game Decks -
|
47 |
+
60 Cards Each, Pokemon, '
|
48 |
+
- 'search_document: Ultra Pro Pokemon: Charizard Album, 2", Ultra Pro, '
|
49 |
+
- source_sentence: 'search_query: table runners 108 inches'
|
50 |
sentences:
|
51 |
+
- 'search_document: Sambosk Fall Buffalo Pumpkin Table Runner, Autumn Farmhouse
|
52 |
+
Table Runners for Kitchen Dining Coffee or Indoor and Outdoor Home Parties Decor
|
53 |
+
13 x 72 Inches SK006, Sambosk, Black White'
|
54 |
+
- 'search_document: EYEGUARD Readers 4 Pack of Thin and Elegant Womens Reading Glasses
|
55 |
+
with Beautiful Patterns for Ladies 1.00, EYEGUARD, Mix'
|
56 |
+
- 'search_document: Sunfiy 4 Pack Red Satin Table Runner 12 x 108 Inch Long Table
|
57 |
+
Runners for Wedding Birthday Parties Banquets Graduations Engagements, Sunfiy,
|
58 |
+
Red'
|
59 |
+
- source_sentence: 'search_query: nursing shoes for women'
|
60 |
sentences:
|
61 |
+
- 'search_document: Hawkwell Women''s Lightweight Comfort Slip Resistant Nursing
|
62 |
+
Shoes,White PU,10 M US, Hawkwell, 1923/White'
|
63 |
+
- 'search_document: REESE''S Peanut Butter Milk Chocolate You''re Amazing Appreciation
|
64 |
+
Candy Bars for Christmas and Holiday Season, 4.2 oz Bars, 12 Count, Reese''s, '
|
65 |
+
- 'search_document: adidas womens Cloudfoam Pure Running Shoe, Black/Black, 7.5
|
66 |
+
US, adidas, Black/Black/White'
|
67 |
+
- source_sentence: 'search_query: mens socks black and white'
|
|
|
|
|
68 |
sentences:
|
69 |
+
- 'search_document: Fruit of the Loom Men''s Essential 6 Pack Casual Crew Socks
|
70 |
+
| Arch Support | Black & White, Black, Shoe Size: 6-12, Fruit of the Loom, Black'
|
71 |
+
- 'search_document: adidas Originals Men''s Trefoil Crew Socks (6-Pair), White/Black
|
72 |
+
Black/White, Large, (Shoe Size 6-12), adidas Originals, White/Black'
|
73 |
+
- 'search_document: Fifty Shades of Grey, , '
|
74 |
+
- source_sentence: 'search_query: karoke set 2 microphone for adults'
|
|
|
|
|
|
|
|
|
|
|
75 |
sentences:
|
76 |
+
- 'search_document: EARISE T26 Portable Karaoke Machine Bluetooth Speaker with Wireless
|
77 |
+
Microphone, Rechargeable PA System with FM Radio, Audio Recording, Remote Control,
|
78 |
+
Supports TF Card/USB, Perfect for Party, EARISE, '
|
79 |
+
- 'search_document: FunWorld Men''s Complete 3D Zombie Costume, Grey, One Size,
|
80 |
+
Fun World, Multi'
|
81 |
+
- 'search_document: Starion KS829-B Bluetooth Karaoke Machine l Pedestal Design
|
82 |
+
w/Light Show l Two Karaoke Microphones, Starion, Black'
|
83 |
pipeline_tag: sentence-similarity
|
84 |
model-index:
|
85 |
- name: SentenceTransformer
|
|
|
92 |
type: unknown
|
93 |
metrics:
|
94 |
- type: cosine_accuracy
|
95 |
+
value: 0.7298125
|
96 |
name: Cosine Accuracy
|
97 |
- type: dot_accuracy
|
98 |
+
value: 0.2831875
|
99 |
name: Dot Accuracy
|
100 |
- type: manhattan_accuracy
|
101 |
+
value: 0.72825
|
102 |
name: Manhattan Accuracy
|
103 |
- type: euclidean_accuracy
|
104 |
+
value: 0.729875
|
105 |
name: Euclidean Accuracy
|
106 |
- type: max_accuracy
|
107 |
+
value: 0.729875
|
108 |
name: Max Accuracy
|
109 |
- task:
|
110 |
type: semantic-similarity
|
|
|
114 |
type: unknown
|
115 |
metrics:
|
116 |
- type: pearson_cosine
|
117 |
+
value: 0.4148003591706621
|
118 |
name: Pearson Cosine
|
119 |
- type: spearman_cosine
|
120 |
+
value: 0.39973675544358156
|
121 |
name: Spearman Cosine
|
122 |
- type: pearson_manhattan
|
123 |
+
value: 0.37708819507475255
|
124 |
name: Pearson Manhattan
|
125 |
- type: spearman_manhattan
|
126 |
+
value: 0.36992167570513307
|
127 |
name: Spearman Manhattan
|
128 |
- type: pearson_euclidean
|
129 |
+
value: 0.3777862291730549
|
130 |
name: Pearson Euclidean
|
131 |
- type: spearman_euclidean
|
132 |
+
value: 0.3707889635811508
|
133 |
name: Spearman Euclidean
|
134 |
- type: pearson_dot
|
135 |
+
value: 0.3813644395159763
|
136 |
name: Pearson Dot
|
137 |
- type: spearman_dot
|
138 |
+
value: 0.3817136551173837
|
139 |
name: Spearman Dot
|
140 |
- type: pearson_max
|
141 |
+
value: 0.4148003591706621
|
142 |
name: Pearson Max
|
143 |
- type: spearman_max
|
144 |
+
value: 0.39973675544358156
|
145 |
name: Spearman Max
|
146 |
- task:
|
147 |
type: information-retrieval
|
|
|
151 |
type: unknown
|
152 |
metrics:
|
153 |
- type: cosine_accuracy@10
|
154 |
+
value: 0.967
|
155 |
name: Cosine Accuracy@10
|
156 |
- type: cosine_precision@10
|
157 |
+
value: 0.6951
|
158 |
name: Cosine Precision@10
|
159 |
- type: cosine_recall@10
|
160 |
+
value: 0.6216729831257005
|
161 |
name: Cosine Recall@10
|
162 |
- type: cosine_ndcg@10
|
163 |
+
value: 0.8300106033542061
|
164 |
name: Cosine Ndcg@10
|
165 |
- type: cosine_mrr@10
|
166 |
+
value: 0.9111154761904765
|
167 |
name: Cosine Mrr@10
|
168 |
- type: cosine_map@10
|
169 |
+
value: 0.7758485833963215
|
170 |
name: Cosine Map@10
|
171 |
- type: dot_accuracy@10
|
172 |
+
value: 0.946
|
173 |
name: Dot Accuracy@10
|
174 |
- type: dot_precision@10
|
175 |
+
value: 0.6369
|
176 |
name: Dot Precision@10
|
177 |
- type: dot_recall@10
|
178 |
+
value: 0.5693415261440723
|
179 |
name: Dot Recall@10
|
180 |
- type: dot_ndcg@10
|
181 |
+
value: 0.7668657376718138
|
182 |
name: Dot Ndcg@10
|
183 |
- type: dot_mrr@10
|
184 |
+
value: 0.8754059523809526
|
185 |
name: Dot Mrr@10
|
186 |
- type: dot_map@10
|
187 |
+
value: 0.6962231903502142
|
188 |
name: Dot Map@10
|
189 |
---
|
190 |
|
|
|
238 |
model = SentenceTransformer("lv12/esci-nomic-embed-text-v1_5_4")
|
239 |
# Run inference
|
240 |
sentences = [
|
241 |
+
'search_query: karoke set 2 microphone for adults',
|
242 |
+
'search_document: Starion KS829-B Bluetooth Karaoke Machine l Pedestal Design w/Light Show l Two Karaoke Microphones, Starion, Black',
|
243 |
+
'search_document: EARISE T26 Portable Karaoke Machine Bluetooth Speaker with Wireless Microphone, Rechargeable PA System with FM Radio, Audio Recording, Remote Control, Supports TF Card/USB, Perfect for Party, EARISE, ',
|
244 |
]
|
245 |
embeddings = model.encode(sentences)
|
246 |
print(embeddings.shape)
|
|
|
286 |
|
287 |
| Metric | Value |
|
288 |
|:--------------------|:-----------|
|
289 |
+
| **cosine_accuracy** | **0.7298** |
|
290 |
+
| dot_accuracy | 0.2832 |
|
291 |
+
| manhattan_accuracy | 0.7282 |
|
292 |
+
| euclidean_accuracy | 0.7299 |
|
293 |
+
| max_accuracy | 0.7299 |
|
294 |
|
295 |
#### Semantic Similarity
|
296 |
|
|
|
298 |
|
299 |
| Metric | Value |
|
300 |
|:--------------------|:-----------|
|
301 |
+
| pearson_cosine | 0.4148 |
|
302 |
+
| **spearman_cosine** | **0.3997** |
|
303 |
+
| pearson_manhattan | 0.3771 |
|
304 |
+
| spearman_manhattan | 0.3699 |
|
305 |
+
| pearson_euclidean | 0.3778 |
|
306 |
+
| spearman_euclidean | 0.3708 |
|
307 |
+
| pearson_dot | 0.3814 |
|
308 |
+
| spearman_dot | 0.3817 |
|
309 |
+
| pearson_max | 0.4148 |
|
310 |
+
| spearman_max | 0.3997 |
|
311 |
|
312 |
#### Information Retrieval
|
313 |
|
|
|
315 |
|
316 |
| Metric | Value |
|
317 |
|:--------------------|:-----------|
|
318 |
+
| cosine_accuracy@10 | 0.967 |
|
319 |
+
| cosine_precision@10 | 0.6951 |
|
320 |
+
| cosine_recall@10 | 0.6217 |
|
321 |
+
| cosine_ndcg@10 | 0.83 |
|
322 |
+
| cosine_mrr@10 | 0.9111 |
|
323 |
+
| **cosine_map@10** | **0.7758** |
|
324 |
+
| dot_accuracy@10 | 0.946 |
|
325 |
+
| dot_precision@10 | 0.6369 |
|
326 |
+
| dot_recall@10 | 0.5693 |
|
327 |
+
| dot_ndcg@10 | 0.7669 |
|
328 |
+
| dot_mrr@10 | 0.8754 |
|
329 |
+
| dot_map@10 | 0.6962 |
|
330 |
|
331 |
<!--
|
332 |
## Bias, Risks and Limitations
|
|
|
347 |
#### triplets
|
348 |
|
349 |
* Dataset: triplets
|
350 |
+
* Size: 1,600,000 training samples
|
351 |
* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
|
352 |
* Approximate statistics based on the first 1000 samples:
|
353 |
+
| | anchor | positive | negative |
|
354 |
+
|:--------|:----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
|
355 |
+
| type | string | string | string |
|
356 |
+
| details | <ul><li>min: 7 tokens</li><li>mean: 11.03 tokens</li><li>max: 39 tokens</li></ul> | <ul><li>min: 10 tokens</li><li>mean: 39.86 tokens</li><li>max: 104 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 39.73 tokens</li><li>max: 159 tokens</li></ul> |
|
357 |
* Samples:
|
358 |
+
| anchor | positive | negative |
|
359 |
+
|:--------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
360 |
+
| <code>search_query: udt hydraulic fluid</code> | <code>search_document: Triax Agra UTTO XL Synthetic Blend Tractor Transmission and Hydraulic Oil, 6,000 Hour Life, 50% Less wear, 36F Pour Point, Replaces All OEM Tractor Fluids (5 Gallon Pail), TRIAX, </code> | <code>search_document: Shell Rotella T5 Synthetic Blend 15W-40 Diesel Engine Oil (1-Gallon, Case of 3), Shell Rotella, </code> |
|
361 |
+
| <code>search_query: cheetah print iphone xs case</code> | <code>search_document: iPhone Xs Case, iPhone Xs Case,Doowear Leopard Cheetah Protective Cover Shell For Girls Women,Slim Fit Anti Scratch Shockproof Soft TPU Bumper Flexible Rubber Gel Silicone Case for iPhone Xs / X-1, Ebetterr, 1</code> | <code>search_document: iPhone Xs & iPhone X Case, J.west Luxury Sparkle Bling Translucent Leopard Print Soft Silicone Phone Case Cover for Girls Women Flex Slim Design Pattern Drop Protective Case for iPhone Xs/x 5.8 inch, J.west, Leopard</code> |
|
362 |
+
| <code>search_query: platform shoes</code> | <code>search_document: Teva Women's Flatform Universal Platform Sandal, Black, 5 M US, Teva, Black</code> | <code>search_document: Vans Women's Old Skool Platform Trainers, (Black/White Y28), 5 UK 38 EU, Vans, Black/White</code> |
|
363 |
* Loss: [<code>TripletLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#tripletloss) with these parameters:
|
364 |
```json
|
365 |
{
|
366 |
"distance_metric": "TripletDistanceMetric.COSINE",
|
367 |
+
"triplet_margin": 0.8
|
368 |
}
|
369 |
```
|
370 |
|
|
|
373 |
#### triplets
|
374 |
|
375 |
* Dataset: triplets
|
376 |
+
* Size: 16,000 evaluation samples
|
377 |
* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
|
378 |
* Approximate statistics based on the first 1000 samples:
|
379 |
+
| | anchor | positive | negative |
|
380 |
+
|:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
|
381 |
+
| type | string | string | string |
|
382 |
+
| details | <ul><li>min: 7 tokens</li><li>mean: 11.02 tokens</li><li>max: 29 tokens</li></ul> | <ul><li>min: 10 tokens</li><li>mean: 38.78 tokens</li><li>max: 87 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 38.81 tokens</li><li>max: 91 tokens</li></ul> |
|
383 |
* Samples:
|
384 |
+
| anchor | positive | negative |
|
385 |
+
|:---------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------|
|
386 |
+
| <code>search_query: hogknobz</code> | <code>search_document: Black 2014-2015 HDsmallPARTS/LocEzy Saddlebag Mounting Hardware Knobs are replacement/compatible for Saddlebag Quick Release Pins on Harley Davidson Touring Motorcycles Theft Deterrent, LocEzy, </code> | <code>search_document: HANSWD Saddlebag Support Bars Brackets For SUZUKI YAMAHA KAWASAKI (Black), HANSWD, Black</code> |
|
387 |
+
| <code>search_query: tile sticker key finder</code> | <code>search_document: Tile Sticker (2020) 2-pack - Small, Adhesive Bluetooth Tracker, Item Locator and Finder for Remotes, Headphones, Gadgets and More, Tile, </code> | <code>search_document: Tile Pro Combo (2017) - 2 Pack (1 x Sport, 1 x Style) - Discontinued by Manufacturer, Tile, Graphite/Gold</code> |
|
388 |
+
| <code>search_query: adobe incense burner</code> | <code>search_document: AM Incense Burner Frankincense Resin - Luxury Globe Charcoal Bakhoor Burners for Office & Home Decor (Brown), AM, Brown</code> | <code>search_document: semli Large Incense Burner Backflow Incense Burner Holder Incense Stick Holder Home Office Decor, Semli, </code> |
|
389 |
* Loss: [<code>TripletLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#tripletloss) with these parameters:
|
390 |
```json
|
391 |
{
|
392 |
"distance_metric": "TripletDistanceMetric.COSINE",
|
393 |
+
"triplet_margin": 0.8
|
394 |
}
|
395 |
```
|
396 |
|
397 |
### Training Hyperparameters
|
398 |
#### Non-Default Hyperparameters
|
399 |
|
400 |
+
- `per_device_train_batch_size`: 64
|
401 |
- `per_device_eval_batch_size`: 16
|
402 |
- `gradient_accumulation_steps`: 2
|
403 |
- `learning_rate`: 1e-07
|
404 |
+
- `num_train_epochs`: 5
|
405 |
- `lr_scheduler_type`: polynomial
|
406 |
- `lr_scheduler_kwargs`: {'lr_end': 1e-08, 'power': 2.0}
|
407 |
- `warmup_ratio`: 0.05
|
408 |
+
- `dataloader_drop_last`: True
|
409 |
- `dataloader_num_workers`: 4
|
410 |
- `dataloader_prefetch_factor`: 4
|
411 |
- `load_best_model_at_end`: True
|
|
|
419 |
- `overwrite_output_dir`: False
|
420 |
- `do_predict`: False
|
421 |
- `prediction_loss_only`: True
|
422 |
+
- `per_device_train_batch_size`: 64
|
423 |
- `per_device_eval_batch_size`: 16
|
424 |
- `per_gpu_train_batch_size`: None
|
425 |
- `per_gpu_eval_batch_size`: None
|
|
|
431 |
- `adam_beta2`: 0.999
|
432 |
- `adam_epsilon`: 1e-08
|
433 |
- `max_grad_norm`: 1.0
|
434 |
+
- `num_train_epochs`: 5
|
435 |
- `max_steps`: -1
|
436 |
- `lr_scheduler_type`: polynomial
|
437 |
- `lr_scheduler_kwargs`: {'lr_end': 1e-08, 'power': 2.0}
|
|
|
527 |
|
528 |
| Epoch | Step | Training Loss | triplets loss | cosine_accuracy | cosine_map@10 | spearman_cosine |
|
529 |
|:------:|:----:|:-------------:|:-------------:|:---------------:|:-------------:|:---------------:|
|
530 |
+
| 0.0008 | 10 | 0.7505 | - | - | - | - |
|
531 |
+
| 0.0016 | 20 | 0.7499 | - | - | - | - |
|
532 |
+
| 0.0024 | 30 | 0.7524 | - | - | - | - |
|
533 |
+
| 0.0032 | 40 | 0.7486 | - | - | - | - |
|
534 |
+
| 0.004 | 50 | 0.7493 | - | - | - | - |
|
535 |
+
| 0.0048 | 60 | 0.7476 | - | - | - | - |
|
536 |
+
| 0.0056 | 70 | 0.7483 | - | - | - | - |
|
537 |
+
| 0.0064 | 80 | 0.7487 | - | - | - | - |
|
538 |
+
| 0.0072 | 90 | 0.7496 | - | - | - | - |
|
539 |
+
| 0.008 | 100 | 0.7515 | 0.7559 | 0.7263 | 0.7684 | 0.3941 |
|
540 |
+
| 0.0088 | 110 | 0.7523 | - | - | - | - |
|
541 |
+
| 0.0096 | 120 | 0.7517 | - | - | - | - |
|
542 |
+
| 0.0104 | 130 | 0.7534 | - | - | - | - |
|
543 |
+
| 0.0112 | 140 | 0.746 | - | - | - | - |
|
544 |
+
| 0.012 | 150 | 0.7528 | - | - | - | - |
|
545 |
+
| 0.0128 | 160 | 0.7511 | - | - | - | - |
|
546 |
+
| 0.0136 | 170 | 0.7491 | - | - | - | - |
|
547 |
+
| 0.0144 | 180 | 0.752 | - | - | - | - |
|
548 |
+
| 0.0152 | 190 | 0.7512 | - | - | - | - |
|
549 |
+
| 0.016 | 200 | 0.7513 | 0.7557 | 0.7259 | 0.7688 | 0.3942 |
|
550 |
+
| 0.0168 | 210 | 0.7505 | - | - | - | - |
|
551 |
+
| 0.0176 | 220 | 0.7481 | - | - | - | - |
|
552 |
+
| 0.0184 | 230 | 0.7516 | - | - | - | - |
|
553 |
+
| 0.0192 | 240 | 0.7504 | - | - | - | - |
|
554 |
+
| 0.02 | 250 | 0.7498 | - | - | - | - |
|
555 |
+
| 0.0208 | 260 | 0.7506 | - | - | - | - |
|
556 |
+
| 0.0216 | 270 | 0.7486 | - | - | - | - |
|
557 |
+
| 0.0224 | 280 | 0.7471 | - | - | - | - |
|
558 |
+
| 0.0232 | 290 | 0.7511 | - | - | - | - |
|
559 |
+
| 0.024 | 300 | 0.7506 | 0.7553 | 0.7258 | 0.7692 | 0.3943 |
|
560 |
+
| 0.0248 | 310 | 0.7485 | - | - | - | - |
|
561 |
+
| 0.0256 | 320 | 0.7504 | - | - | - | - |
|
562 |
+
| 0.0264 | 330 | 0.7456 | - | - | - | - |
|
563 |
+
| 0.0272 | 340 | 0.7461 | - | - | - | - |
|
564 |
+
| 0.028 | 350 | 0.7496 | - | - | - | - |
|
565 |
+
| 0.0288 | 360 | 0.7518 | - | - | - | - |
|
566 |
+
| 0.0296 | 370 | 0.7514 | - | - | - | - |
|
567 |
+
| 0.0304 | 380 | 0.7479 | - | - | - | - |
|
568 |
+
| 0.0312 | 390 | 0.7507 | - | - | - | - |
|
569 |
+
| 0.032 | 400 | 0.7511 | 0.7547 | 0.7258 | 0.7695 | 0.3945 |
|
570 |
+
| 0.0328 | 410 | 0.7491 | - | - | - | - |
|
571 |
+
| 0.0336 | 420 | 0.7487 | - | - | - | - |
|
572 |
+
| 0.0344 | 430 | 0.7496 | - | - | - | - |
|
573 |
+
| 0.0352 | 440 | 0.7464 | - | - | - | - |
|
574 |
+
| 0.036 | 450 | 0.7518 | - | - | - | - |
|
575 |
+
| 0.0368 | 460 | 0.7481 | - | - | - | - |
|
576 |
+
| 0.0376 | 470 | 0.7493 | - | - | - | - |
|
577 |
+
| 0.0384 | 480 | 0.753 | - | - | - | - |
|
578 |
+
| 0.0392 | 490 | 0.7475 | - | - | - | - |
|
579 |
+
| 0.04 | 500 | 0.7498 | 0.7540 | 0.7262 | 0.7700 | 0.3948 |
|
580 |
+
| 0.0408 | 510 | 0.7464 | - | - | - | - |
|
581 |
+
| 0.0416 | 520 | 0.7506 | - | - | - | - |
|
582 |
+
| 0.0424 | 530 | 0.747 | - | - | - | - |
|
583 |
+
| 0.0432 | 540 | 0.7462 | - | - | - | - |
|
584 |
+
| 0.044 | 550 | 0.75 | - | - | - | - |
|
585 |
+
| 0.0448 | 560 | 0.7522 | - | - | - | - |
|
586 |
+
| 0.0456 | 570 | 0.7452 | - | - | - | - |
|
587 |
+
| 0.0464 | 580 | 0.7475 | - | - | - | - |
|
588 |
+
| 0.0472 | 590 | 0.7507 | - | - | - | - |
|
589 |
+
| 0.048 | 600 | 0.7494 | 0.7531 | 0.7269 | 0.7707 | 0.3951 |
|
590 |
+
| 0.0488 | 610 | 0.7525 | - | - | - | - |
|
591 |
+
| 0.0496 | 620 | 0.7446 | - | - | - | - |
|
592 |
+
| 0.0504 | 630 | 0.7457 | - | - | - | - |
|
593 |
+
| 0.0512 | 640 | 0.7462 | - | - | - | - |
|
594 |
+
| 0.052 | 650 | 0.7478 | - | - | - | - |
|
595 |
+
| 0.0528 | 660 | 0.7459 | - | - | - | - |
|
596 |
+
| 0.0536 | 670 | 0.7465 | - | - | - | - |
|
597 |
+
| 0.0544 | 680 | 0.7495 | - | - | - | - |
|
598 |
+
| 0.0552 | 690 | 0.7513 | - | - | - | - |
|
599 |
+
| 0.056 | 700 | 0.7445 | 0.7520 | 0.7274 | 0.7705 | 0.3954 |
|
600 |
+
| 0.0568 | 710 | 0.7446 | - | - | - | - |
|
601 |
+
| 0.0576 | 720 | 0.746 | - | - | - | - |
|
602 |
+
| 0.0584 | 730 | 0.7452 | - | - | - | - |
|
603 |
+
| 0.0592 | 740 | 0.7459 | - | - | - | - |
|
604 |
+
| 0.06 | 750 | 0.7419 | - | - | - | - |
|
605 |
+
| 0.0608 | 760 | 0.7462 | - | - | - | - |
|
606 |
+
| 0.0616 | 770 | 0.7414 | - | - | - | - |
|
607 |
+
| 0.0624 | 780 | 0.7444 | - | - | - | - |
|
608 |
+
| 0.0632 | 790 | 0.7419 | - | - | - | - |
|
609 |
+
| 0.064 | 800 | 0.7438 | 0.7508 | 0.7273 | 0.7712 | 0.3957 |
|
610 |
+
| 0.0648 | 810 | 0.7503 | - | - | - | - |
|
611 |
+
| 0.0656 | 820 | 0.7402 | - | - | - | - |
|
612 |
+
| 0.0664 | 830 | 0.7435 | - | - | - | - |
|
613 |
+
| 0.0672 | 840 | 0.741 | - | - | - | - |
|
614 |
+
| 0.068 | 850 | 0.7386 | - | - | - | - |
|
615 |
+
| 0.0688 | 860 | 0.7416 | - | - | - | - |
|
616 |
+
| 0.0696 | 870 | 0.7473 | - | - | - | - |
|
617 |
+
| 0.0704 | 880 | 0.7438 | - | - | - | - |
|
618 |
+
| 0.0712 | 890 | 0.7458 | - | - | - | - |
|
619 |
+
| 0.072 | 900 | 0.7446 | 0.7494 | 0.7279 | 0.7718 | 0.3961 |
|
620 |
+
| 0.0728 | 910 | 0.7483 | - | - | - | - |
|
621 |
+
| 0.0736 | 920 | 0.7458 | - | - | - | - |
|
622 |
+
| 0.0744 | 930 | 0.7473 | - | - | - | - |
|
623 |
+
| 0.0752 | 940 | 0.7431 | - | - | - | - |
|
624 |
+
| 0.076 | 950 | 0.7428 | - | - | - | - |
|
625 |
+
| 0.0768 | 960 | 0.7385 | - | - | - | - |
|
626 |
+
| 0.0776 | 970 | 0.7438 | - | - | - | - |
|
627 |
+
| 0.0784 | 980 | 0.7406 | - | - | - | - |
|
628 |
+
| 0.0792 | 990 | 0.7426 | - | - | - | - |
|
629 |
+
| 0.08 | 1000 | 0.7372 | 0.7478 | 0.7282 | 0.7725 | 0.3965 |
|
630 |
+
| 0.0808 | 1010 | 0.7396 | - | - | - | - |
|
631 |
+
| 0.0816 | 1020 | 0.7398 | - | - | - | - |
|
632 |
+
| 0.0824 | 1030 | 0.7376 | - | - | - | - |
|
633 |
+
| 0.0832 | 1040 | 0.7417 | - | - | - | - |
|
634 |
+
| 0.084 | 1050 | 0.7408 | - | - | - | - |
|
635 |
+
| 0.0848 | 1060 | 0.7415 | - | - | - | - |
|
636 |
+
| 0.0856 | 1070 | 0.7468 | - | - | - | - |
|
637 |
+
| 0.0864 | 1080 | 0.7427 | - | - | - | - |
|
638 |
+
| 0.0872 | 1090 | 0.7371 | - | - | - | - |
|
639 |
+
| 0.088 | 1100 | 0.7375 | 0.7460 | 0.7279 | 0.7742 | 0.3970 |
|
640 |
+
| 0.0888 | 1110 | 0.7434 | - | - | - | - |
|
641 |
+
| 0.0896 | 1120 | 0.7441 | - | - | - | - |
|
642 |
+
| 0.0904 | 1130 | 0.7378 | - | - | - | - |
|
643 |
+
| 0.0912 | 1140 | 0.735 | - | - | - | - |
|
644 |
+
| 0.092 | 1150 | 0.739 | - | - | - | - |
|
645 |
+
| 0.0928 | 1160 | 0.7408 | - | - | - | - |
|
646 |
+
| 0.0936 | 1170 | 0.7346 | - | - | - | - |
|
647 |
+
| 0.0944 | 1180 | 0.7389 | - | - | - | - |
|
648 |
+
| 0.0952 | 1190 | 0.7367 | - | - | - | - |
|
649 |
+
| 0.096 | 1200 | 0.7358 | 0.7440 | 0.729 | 0.7747 | 0.3975 |
|
650 |
+
| 0.0968 | 1210 | 0.7381 | - | - | - | - |
|
651 |
+
| 0.0976 | 1220 | 0.7405 | - | - | - | - |
|
652 |
+
| 0.0984 | 1230 | 0.7348 | - | - | - | - |
|
653 |
+
| 0.0992 | 1240 | 0.737 | - | - | - | - |
|
654 |
+
| 0.1 | 1250 | 0.7393 | - | - | - | - |
|
655 |
+
| 0.1008 | 1260 | 0.7411 | - | - | - | - |
|
656 |
+
| 0.1016 | 1270 | 0.7359 | - | - | - | - |
|
657 |
+
| 0.1024 | 1280 | 0.7276 | - | - | - | - |
|
658 |
+
| 0.1032 | 1290 | 0.7364 | - | - | - | - |
|
659 |
+
| 0.104 | 1300 | 0.7333 | 0.7418 | 0.7293 | 0.7747 | 0.3979 |
|
660 |
+
| 0.1048 | 1310 | 0.7367 | - | - | - | - |
|
661 |
+
| 0.1056 | 1320 | 0.7352 | - | - | - | - |
|
662 |
+
| 0.1064 | 1330 | 0.7333 | - | - | - | - |
|
663 |
+
| 0.1072 | 1340 | 0.737 | - | - | - | - |
|
664 |
+
| 0.108 | 1350 | 0.7361 | - | - | - | - |
|
665 |
+
| 0.1088 | 1360 | 0.7299 | - | - | - | - |
|
666 |
+
| 0.1096 | 1370 | 0.7339 | - | - | - | - |
|
667 |
+
| 0.1104 | 1380 | 0.7349 | - | - | - | - |
|
668 |
+
| 0.1112 | 1390 | 0.7318 | - | - | - | - |
|
669 |
+
| 0.112 | 1400 | 0.7336 | 0.7394 | 0.7292 | 0.7749 | 0.3983 |
|
670 |
+
| 0.1128 | 1410 | 0.7326 | - | - | - | - |
|
671 |
+
| 0.1136 | 1420 | 0.7317 | - | - | - | - |
|
672 |
+
| 0.1144 | 1430 | 0.7315 | - | - | - | - |
|
673 |
+
| 0.1152 | 1440 | 0.7321 | - | - | - | - |
|
674 |
+
| 0.116 | 1450 | 0.7284 | - | - | - | - |
|
675 |
+
| 0.1168 | 1460 | 0.7308 | - | - | - | - |
|
676 |
+
| 0.1176 | 1470 | 0.7287 | - | - | - | - |
|
677 |
+
| 0.1184 | 1480 | 0.727 | - | - | - | - |
|
678 |
+
| 0.1192 | 1490 | 0.7298 | - | - | - | - |
|
679 |
+
| 0.12 | 1500 | 0.7306 | 0.7368 | 0.7301 | 0.7755 | 0.3988 |
|
680 |
+
| 0.1208 | 1510 | 0.7269 | - | - | - | - |
|
681 |
+
| 0.1216 | 1520 | 0.7299 | - | - | - | - |
|
682 |
+
| 0.1224 | 1530 | 0.7256 | - | - | - | - |
|
683 |
+
| 0.1232 | 1540 | 0.721 | - | - | - | - |
|
684 |
+
| 0.124 | 1550 | 0.7274 | - | - | - | - |
|
685 |
+
| 0.1248 | 1560 | 0.7251 | - | - | - | - |
|
686 |
+
| 0.1256 | 1570 | 0.7248 | - | - | - | - |
|
687 |
+
| 0.1264 | 1580 | 0.7244 | - | - | - | - |
|
688 |
+
| 0.1272 | 1590 | 0.7275 | - | - | - | - |
|
689 |
+
| 0.128 | 1600 | 0.7264 | 0.7339 | 0.7298 | 0.7756 | 0.3991 |
|
690 |
+
| 0.1288 | 1610 | 0.7252 | - | - | - | - |
|
691 |
+
| 0.1296 | 1620 | 0.7287 | - | - | - | - |
|
692 |
+
| 0.1304 | 1630 | 0.7263 | - | - | - | - |
|
693 |
+
| 0.1312 | 1640 | 0.7216 | - | - | - | - |
|
694 |
+
| 0.132 | 1650 | 0.7231 | - | - | - | - |
|
695 |
+
| 0.1328 | 1660 | 0.728 | - | - | - | - |
|
696 |
+
| 0.1336 | 1670 | 0.7309 | - | - | - | - |
|
697 |
+
| 0.1344 | 1680 | 0.7243 | - | - | - | - |
|
698 |
+
| 0.1352 | 1690 | 0.7239 | - | - | - | - |
|
699 |
+
| 0.136 | 1700 | 0.7219 | 0.7309 | 0.7302 | 0.7768 | 0.3994 |
|
700 |
+
| 0.1368 | 1710 | 0.7212 | - | - | - | - |
|
701 |
+
| 0.1376 | 1720 | 0.7217 | - | - | - | - |
|
702 |
+
| 0.1384 | 1730 | 0.7118 | - | - | - | - |
|
703 |
+
| 0.1392 | 1740 | 0.7226 | - | - | - | - |
|
704 |
+
| 0.14 | 1750 | 0.7185 | - | - | - | - |
|
705 |
+
| 0.1408 | 1760 | 0.7228 | - | - | - | - |
|
706 |
+
| 0.1416 | 1770 | 0.7257 | - | - | - | - |
|
707 |
+
| 0.1424 | 1780 | 0.7177 | - | - | - | - |
|
708 |
+
| 0.1432 | 1790 | 0.722 | - | - | - | - |
|
709 |
+
| 0.144 | 1800 | 0.712 | 0.7276 | 0.7307 | 0.7763 | 0.3997 |
|
710 |
+
| 0.1448 | 1810 | 0.7193 | - | - | - | - |
|
711 |
+
| 0.1456 | 1820 | 0.7138 | - | - | - | - |
|
712 |
+
| 0.1464 | 1830 | 0.7171 | - | - | - | - |
|
713 |
+
| 0.1472 | 1840 | 0.7191 | - | - | - | - |
|
714 |
+
| 0.148 | 1850 | 0.7172 | - | - | - | - |
|
715 |
+
| 0.1488 | 1860 | 0.7168 | - | - | - | - |
|
716 |
+
| 0.1496 | 1870 | 0.7111 | - | - | - | - |
|
717 |
+
| 0.1504 | 1880 | 0.7203 | - | - | - | - |
|
718 |
+
| 0.1512 | 1890 | 0.7095 | - | - | - | - |
|
719 |
+
| 0.152 | 1900 | 0.7064 | 0.7240 | 0.7301 | 0.7762 | 0.3998 |
|
720 |
+
| 0.1528 | 1910 | 0.7147 | - | - | - | - |
|
721 |
+
| 0.1536 | 1920 | 0.7098 | - | - | - | - |
|
722 |
+
| 0.1544 | 1930 | 0.7193 | - | - | - | - |
|
723 |
+
| 0.1552 | 1940 | 0.7096 | - | - | - | - |
|
724 |
+
| 0.156 | 1950 | 0.7107 | - | - | - | - |
|
725 |
+
| 0.1568 | 1960 | 0.7146 | - | - | - | - |
|
726 |
+
| 0.1576 | 1970 | 0.7106 | - | - | - | - |
|
727 |
+
| 0.1584 | 1980 | 0.7079 | - | - | - | - |
|
728 |
+
| 0.1592 | 1990 | 0.7097 | - | - | - | - |
|
729 |
+
| 0.16 | 2000 | 0.71 | 0.7202 | 0.7298 | 0.7758 | 0.3997 |
|
730 |
|
731 |
</details>
|
732 |
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 546938168
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b395b636e2dc670c0f323ade7bd13eaa584aa5371b726d2d29dfa7d10df25e5
|
3 |
size 546938168
|