Hugging Face's logo

QuangDuy
/
gn-trvn-bert-tiny-stage2

Safetensors
modernbert
Model card Files
xet
 Community
QuangDuy commited on
Commit
ca7a3eb
·
verified ·
1 Parent(s): fa6a4af

Update exported model

Browse files
Files changed (2) hide show
  1. README.md +205 -125
  2. model.safetensors +1 -1
README.md CHANGED
@@ -282,9 +282,9 @@ print(embeddings.shape)
282
  # Get the similarity scores for the embeddings
283
  similarities = model.similarity(embeddings, embeddings)
284
  print(similarities)
285
- # tensor([[1.0000, 0.6222, 0.4305],
286
- # [0.6222, 0.9999, 0.4534],
287
- # [0.4305, 0.4534, 1.0000]])
288
  ```
289
 
290
  <!--
@@ -502,128 +502,208 @@ You can finetune this model on your own dataset.
502
  ### Training Logs
503
  <details><summary>Click to expand</summary>
504
 
505
- | Epoch | Step | Training Loss | validation loss |
506
- |:------:|:----:|:-------------:|:---------------:|
507
- | 0.0088 | 50 | 17.9385 | - |
508
- | 0.0175 | 100 | 14.3738 | - |
509
- | 0.0263 | 150 | 9.8859 | - |
510
- | 0.0350 | 200 | 6.4649 | - |
511
- | 0.0438 | 250 | 4.9783 | - |
512
- | 0.0525 | 300 | 4.2985 | - |
513
- | 0.0613 | 350 | 3.9206 | - |
514
- | 0.0701 | 400 | 3.4734 | - |
515
- | 0.0788 | 450 | 3.2029 | - |
516
- | 0.0876 | 500 | 3.0987 | - |
517
- | 0.0963 | 550 | 2.7411 | - |
518
- | 0.1051 | 600 | 2.6607 | - |
519
- | 0.1138 | 650 | 2.6816 | - |
520
- | 0.1226 | 700 | 2.4956 | - |
521
- | 0.1313 | 750 | 2.2048 | - |
522
- | 0.1401 | 800 | 2.2066 | - |
523
- | 0.1489 | 850 | 2.1267 | - |
524
- | 0.1576 | 900 | 2.1561 | - |
525
- | 0.1664 | 950 | 1.9648 | - |
526
- | 0.1751 | 1000 | 1.8996 | - |
527
- | 0.1839 | 1050 | 1.9579 | - |
528
- | 0.1926 | 1100 | 1.8008 | - |
529
- | 0.2014 | 1150 | 1.7214 | - |
530
- | 0.2102 | 1200 | 1.9004 | - |
531
- | 0.2189 | 1250 | 1.6161 | - |
532
- | 0.2277 | 1300 | 1.7509 | - |
533
- | 0.2364 | 1350 | 1.714 | - |
534
- | 0.2452 | 1400 | 1.6249 | - |
535
- | 0.2539 | 1450 | 1.5886 | - |
536
- | 0.2627 | 1500 | 1.6041 | - |
537
- | 0.2715 | 1550 | 1.5227 | - |
538
- | 0.2802 | 1600 | 1.4853 | - |
539
- | 0.2890 | 1650 | 1.5423 | - |
540
- | 0.2977 | 1700 | 1.4331 | - |
541
- | 0.3065 | 1750 | 1.4789 | - |
542
- | 0.3152 | 1800 | 1.3921 | - |
543
- | 0.3240 | 1850 | 1.3465 | - |
544
- | 0.3327 | 1900 | 1.4211 | - |
545
- | 0.3415 | 1950 | 1.4408 | - |
546
- | 0.3503 | 2000 | 1.2844 | 9.6357 |
547
- | 0.3590 | 2050 | 1.2777 | - |
548
- | 0.3678 | 2100 | 1.2881 | - |
549
- | 0.3765 | 2150 | 1.2529 | - |
550
- | 0.3853 | 2200 | 1.1927 | - |
551
- | 0.3940 | 2250 | 1.2601 | - |
552
- | 0.4028 | 2300 | 1.2153 | - |
553
- | 0.4116 | 2350 | 1.2032 | - |
554
- | 0.4203 | 2400 | 1.1426 | - |
555
- | 0.4291 | 2450 | 1.1638 | - |
556
- | 0.4378 | 2500 | 1.1799 | - |
557
- | 0.4466 | 2550 | 1.1008 | - |
558
- | 0.4553 | 2600 | 1.0525 | - |
559
- | 0.4641 | 2650 | 1.1515 | - |
560
- | 0.4729 | 2700 | 1.1181 | - |
561
- | 0.4816 | 2750 | 1.0531 | - |
562
- | 0.4904 | 2800 | 1.0654 | - |
563
- | 0.4991 | 2850 | 1.0744 | - |
564
- | 0.5079 | 2900 | 0.9993 | - |
565
- | 0.5166 | 2950 | 0.9832 | - |
566
- | 0.5254 | 3000 | 1.0254 | - |
567
- | 0.5342 | 3050 | 0.9355 | - |
568
- | 0.5429 | 3100 | 0.9367 | - |
569
- | 0.5517 | 3150 | 1.0016 | - |
570
- | 0.5604 | 3200 | 1.0177 | - |
571
- | 0.5692 | 3250 | 0.9979 | - |
572
- | 0.5779 | 3300 | 0.9969 | - |
573
- | 0.5867 | 3350 | 0.8659 | - |
574
- | 0.5954 | 3400 | 0.9967 | - |
575
- | 0.6042 | 3450 | 0.89 | - |
576
- | 0.6130 | 3500 | 0.9045 | - |
577
- | 0.6217 | 3550 | 0.9522 | - |
578
- | 0.6305 | 3600 | 0.9215 | - |
579
- | 0.6392 | 3650 | 0.9276 | - |
580
- | 0.6480 | 3700 | 0.8975 | - |
581
- | 0.6567 | 3750 | 0.9318 | - |
582
- | 0.6655 | 3800 | 0.9357 | - |
583
- | 0.6743 | 3850 | 0.8745 | - |
584
- | 0.6830 | 3900 | 0.8377 | - |
585
- | 0.6918 | 3950 | 0.8657 | - |
586
- | 0.7005 | 4000 | 0.8064 | 9.4910 |
587
- | 0.7093 | 4050 | 0.8466 | - |
588
- | 0.7180 | 4100 | 0.8201 | - |
589
- | 0.7268 | 4150 | 0.7865 | - |
590
- | 0.7356 | 4200 | 0.7776 | - |
591
- | 0.7443 | 4250 | 0.7653 | - |
592
- | 0.7531 | 4300 | 0.7666 | - |
593
- | 0.7618 | 4350 | 0.82 | - |
594
- | 0.7706 | 4400 | 0.7563 | - |
595
- | 0.7793 | 4450 | 0.8203 | - |
596
- | 0.7881 | 4500 | 0.7346 | - |
597
- | 0.7968 | 4550 | 0.7373 | - |
598
- | 0.8056 | 4600 | 0.7329 | - |
599
- | 0.8144 | 4650 | 0.7178 | - |
600
- | 0.8231 | 4700 | 0.7236 | - |
601
- | 0.8319 | 4750 | 0.6998 | - |
602
- | 0.8406 | 4800 | 0.7972 | - |
603
- | 0.8494 | 4850 | 0.6816 | - |
604
- | 0.8581 | 4900 | 0.6698 | - |
605
- | 0.8669 | 4950 | 0.6952 | - |
606
- | 0.8757 | 5000 | 0.6676 | - |
607
- | 0.8844 | 5050 | 0.7253 | - |
608
- | 0.8932 | 5100 | 0.6664 | - |
609
- | 0.9019 | 5150 | 0.6941 | - |
610
- | 0.9107 | 5200 | 0.6742 | - |
611
- | 0.9194 | 5250 | 0.6384 | - |
612
- | 0.9282 | 5300 | 0.6638 | - |
613
- | 0.9370 | 5350 | 0.6365 | - |
614
- | 0.9457 | 5400 | 0.6083 | - |
615
- | 0.9545 | 5450 | 0.6917 | - |
616
- | 0.9632 | 5500 | 0.6158 | - |
617
- | 0.9720 | 5550 | 0.6413 | - |
618
- | 0.9807 | 5600 | 0.6646 | - |
619
- | 0.9895 | 5650 | 0.6208 | - |
620
- | 0.9982 | 5700 | 0.635 | - |
621
- | 1.0070 | 5750 | 0.5248 | - |
622
- | 1.0158 | 5800 | 0.4615 | - |
623
- | 1.0245 | 5850 | 0.4619 | - |
624
- | 1.0333 | 5900 | 0.4536 | - |
625
- | 1.0420 | 5950 | 0.4719 | - |
626
- | 1.0508 | 6000 | 0.4483 | - |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
627
 
628
  </details>
629
 
 
282
  # Get the similarity scores for the embeddings
283
  similarities = model.similarity(embeddings, embeddings)
284
  print(similarities)
285
+ # tensor([[1.0000, 0.6550, 0.3175],
286
+ # [0.6550, 1.0000, 0.3404],
287
+ # [0.3175, 0.3404, 1.0001]])
288
  ```
289
 
290
  <!--
 
502
  ### Training Logs
503
  <details><summary>Click to expand</summary>
504
 
505
+ | Epoch | Step | Training Loss | validation loss |
506
+ |:------:|:-----:|:-------------:|:---------------:|
507
+ | 0.0088 | 50 | 17.9385 | - |
508
+ | 0.0175 | 100 | 14.3738 | - |
509
+ | 0.0263 | 150 | 9.8859 | - |
510
+ | 0.0350 | 200 | 6.4649 | - |
511
+ | 0.0438 | 250 | 4.9783 | - |
512
+ | 0.0525 | 300 | 4.2985 | - |
513
+ | 0.0613 | 350 | 3.9206 | - |
514
+ | 0.0701 | 400 | 3.4734 | - |
515
+ | 0.0788 | 450 | 3.2029 | - |
516
+ | 0.0876 | 500 | 3.0987 | - |
517
+ | 0.0963 | 550 | 2.7411 | - |
518
+ | 0.1051 | 600 | 2.6607 | - |
519
+ | 0.1138 | 650 | 2.6816 | - |
520
+ | 0.1226 | 700 | 2.4956 | - |
521
+ | 0.1313 | 750 | 2.2048 | - |
522
+ | 0.1401 | 800 | 2.2066 | - |
523
+ | 0.1489 | 850 | 2.1267 | - |
524
+ | 0.1576 | 900 | 2.1561 | - |
525
+ | 0.1664 | 950 | 1.9648 | - |
526
+ | 0.1751 | 1000 | 1.8996 | - |
527
+ | 0.1839 | 1050 | 1.9579 | - |
528
+ | 0.1926 | 1100 | 1.8008 | - |
529
+ | 0.2014 | 1150 | 1.7214 | - |
530
+ | 0.2102 | 1200 | 1.9004 | - |
531
+ | 0.2189 | 1250 | 1.6161 | - |
532
+ | 0.2277 | 1300 | 1.7509 | - |
533
+ | 0.2364 | 1350 | 1.714 | - |
534
+ | 0.2452 | 1400 | 1.6249 | - |
535
+ | 0.2539 | 1450 | 1.5886 | - |
536
+ | 0.2627 | 1500 | 1.6041 | - |
537
+ | 0.2715 | 1550 | 1.5227 | - |
538
+ | 0.2802 | 1600 | 1.4853 | - |
539
+ | 0.2890 | 1650 | 1.5423 | - |
540
+ | 0.2977 | 1700 | 1.4331 | - |
541
+ | 0.3065 | 1750 | 1.4789 | - |
542
+ | 0.3152 | 1800 | 1.3921 | - |
543
+ | 0.3240 | 1850 | 1.3465 | - |
544
+ | 0.3327 | 1900 | 1.4211 | - |
545
+ | 0.3415 | 1950 | 1.4408 | - |
546
+ | 0.3503 | 2000 | 1.2844 | 9.6357 |
547
+ | 0.3590 | 2050 | 1.2777 | - |
548
+ | 0.3678 | 2100 | 1.2881 | - |
549
+ | 0.3765 | 2150 | 1.2529 | - |
550
+ | 0.3853 | 2200 | 1.1927 | - |
551
+ | 0.3940 | 2250 | 1.2601 | - |
552
+ | 0.4028 | 2300 | 1.2153 | - |
553
+ | 0.4116 | 2350 | 1.2032 | - |
554
+ | 0.4203 | 2400 | 1.1426 | - |
555
+ | 0.4291 | 2450 | 1.1638 | - |
556
+ | 0.4378 | 2500 | 1.1799 | - |
557
+ | 0.4466 | 2550 | 1.1008 | - |
558
+ | 0.4553 | 2600 | 1.0525 | - |
559
+ | 0.4641 | 2650 | 1.1515 | - |
560
+ | 0.4729 | 2700 | 1.1181 | - |
561
+ | 0.4816 | 2750 | 1.0531 | - |
562
+ | 0.4904 | 2800 | 1.0654 | - |
563
+ | 0.4991 | 2850 | 1.0744 | - |
564
+ | 0.5079 | 2900 | 0.9993 | - |
565
+ | 0.5166 | 2950 | 0.9832 | - |
566
+ | 0.5254 | 3000 | 1.0254 | - |
567
+ | 0.5342 | 3050 | 0.9355 | - |
568
+ | 0.5429 | 3100 | 0.9367 | - |
569
+ | 0.5517 | 3150 | 1.0016 | - |
570
+ | 0.5604 | 3200 | 1.0177 | - |
571
+ | 0.5692 | 3250 | 0.9979 | - |
572
+ | 0.5779 | 3300 | 0.9969 | - |
573
+ | 0.5867 | 3350 | 0.8659 | - |
574
+ | 0.5954 | 3400 | 0.9967 | - |
575
+ | 0.6042 | 3450 | 0.89 | - |
576
+ | 0.6130 | 3500 | 0.9045 | - |
577
+ | 0.6217 | 3550 | 0.9522 | - |
578
+ | 0.6305 | 3600 | 0.9215 | - |
579
+ | 0.6392 | 3650 | 0.9276 | - |
580
+ | 0.6480 | 3700 | 0.8975 | - |
581
+ | 0.6567 | 3750 | 0.9318 | - |
582
+ | 0.6655 | 3800 | 0.9357 | - |
583
+ | 0.6743 | 3850 | 0.8745 | - |
584
+ | 0.6830 | 3900 | 0.8377 | - |
585
+ | 0.6918 | 3950 | 0.8657 | - |
586
+ | 0.7005 | 4000 | 0.8064 | 9.4910 |
587
+ | 0.7093 | 4050 | 0.8466 | - |
588
+ | 0.7180 | 4100 | 0.8201 | - |
589
+ | 0.7268 | 4150 | 0.7865 | - |
590
+ | 0.7356 | 4200 | 0.7776 | - |
591
+ | 0.7443 | 4250 | 0.7653 | - |
592
+ | 0.7531 | 4300 | 0.7666 | - |
593
+ | 0.7618 | 4350 | 0.82 | - |
594
+ | 0.7706 | 4400 | 0.7563 | - |
595
+ | 0.7793 | 4450 | 0.8203 | - |
596
+ | 0.7881 | 4500 | 0.7346 | - |
597
+ | 0.7968 | 4550 | 0.7373 | - |
598
+ | 0.8056 | 4600 | 0.7329 | - |
599
+ | 0.8144 | 4650 | 0.7178 | - |
600
+ | 0.8231 | 4700 | 0.7236 | - |
601
+ | 0.8319 | 4750 | 0.6998 | - |
602
+ | 0.8406 | 4800 | 0.7972 | - |
603
+ | 0.8494 | 4850 | 0.6816 | - |
604
+ | 0.8581 | 4900 | 0.6698 | - |
605
+ | 0.8669 | 4950 | 0.6952 | - |
606
+ | 0.8757 | 5000 | 0.6676 | - |
607
+ | 0.8844 | 5050 | 0.7253 | - |
608
+ | 0.8932 | 5100 | 0.6664 | - |
609
+ | 0.9019 | 5150 | 0.6941 | - |
610
+ | 0.9107 | 5200 | 0.6742 | - |
611
+ | 0.9194 | 5250 | 0.6384 | - |
612
+ | 0.9282 | 5300 | 0.6638 | - |
613
+ | 0.9370 | 5350 | 0.6365 | - |
614
+ | 0.9457 | 5400 | 0.6083 | - |
615
+ | 0.9545 | 5450 | 0.6917 | - |
616
+ | 0.9632 | 5500 | 0.6158 | - |
617
+ | 0.9720 | 5550 | 0.6413 | - |
618
+ | 0.9807 | 5600 | 0.6646 | - |
619
+ | 0.9895 | 5650 | 0.6208 | - |
620
+ | 0.9982 | 5700 | 0.635 | - |
621
+ | 1.0070 | 5750 | 0.5248 | - |
622
+ | 1.0158 | 5800 | 0.4615 | - |
623
+ | 1.0245 | 5850 | 0.4619 | - |
624
+ | 1.0333 | 5900 | 0.4536 | - |
625
+ | 1.0420 | 5950 | 0.4719 | - |
626
+ | 1.0508 | 6000 | 0.4483 | 9.4902 |
627
+ | 1.0595 | 6050 | 0.4447 | - |
628
+ | 1.0683 | 6100 | 0.4553 | - |
629
+ | 1.0771 | 6150 | 0.4812 | - |
630
+ | 1.0858 | 6200 | 0.4556 | - |
631
+ | 1.0946 | 6250 | 0.4707 | - |
632
+ | 1.1033 | 6300 | 0.4423 | - |
633
+ | 1.1121 | 6350 | 0.4528 | - |
634
+ | 1.1208 | 6400 | 0.4562 | - |
635
+ | 1.1296 | 6450 | 0.4242 | - |
636
+ | 1.1384 | 6500 | 0.4329 | - |
637
+ | 1.1471 | 6550 | 0.4491 | - |
638
+ | 1.1559 | 6600 | 0.4293 | - |
639
+ | 1.1646 | 6650 | 0.4623 | - |
640
+ | 1.1734 | 6700 | 0.4383 | - |
641
+ | 1.1821 | 6750 | 0.4486 | - |
642
+ | 1.1909 | 6800 | 0.4475 | - |
643
+ | 1.1996 | 6850 | 0.4425 | - |
644
+ | 1.2084 | 6900 | 0.4173 | - |
645
+ | 1.2172 | 6950 | 0.424 | - |
646
+ | 1.2259 | 7000 | 0.3968 | - |
647
+ | 1.2347 | 7050 | 0.4104 | - |
648
+ | 1.2434 | 7100 | 0.415 | - |
649
+ | 1.2522 | 7150 | 0.4109 | - |
650
+ | 1.2609 | 7200 | 0.4627 | - |
651
+ | 1.2697 | 7250 | 0.3882 | - |
652
+ | 1.2785 | 7300 | 0.4055 | - |
653
+ | 1.2872 | 7350 | 0.451 | - |
654
+ | 1.2960 | 7400 | 0.4085 | - |
655
+ | 1.3047 | 7450 | 0.4268 | - |
656
+ | 1.3135 | 7500 | 0.4094 | - |
657
+ | 1.3222 | 7550 | 0.3805 | - |
658
+ | 1.3310 | 7600 | 0.3736 | - |
659
+ | 1.3398 | 7650 | 0.4241 | - |
660
+ | 1.3485 | 7700 | 0.3913 | - |
661
+ | 1.3573 | 7750 | 0.407 | - |
662
+ | 1.3660 | 7800 | 0.4 | - |
663
+ | 1.3748 | 7850 | 0.3972 | - |
664
+ | 1.3835 | 7900 | 0.3495 | - |
665
+ | 1.3923 | 7950 | 0.3656 | - |
666
+ | 1.4011 | 8000 | 0.3846 | 9.5093 |
667
+ | 1.4098 | 8050 | 0.3742 | - |
668
+ | 1.4186 | 8100 | 0.373 | - |
669
+ | 1.4273 | 8150 | 0.3649 | - |
670
+ | 1.4361 | 8200 | 0.3576 | - |
671
+ | 1.4448 | 8250 | 0.3687 | - |
672
+ | 1.4536 | 8300 | 0.3712 | - |
673
+ | 1.4623 | 8350 | 0.3936 | - |
674
+ | 1.4711 | 8400 | 0.4036 | - |
675
+ | 1.4799 | 8450 | 0.3433 | - |
676
+ | 1.4886 | 8500 | 0.3586 | - |
677
+ | 1.4974 | 8550 | 0.3323 | - |
678
+ | 1.5061 | 8600 | 0.3595 | - |
679
+ | 1.5149 | 8650 | 0.3748 | - |
680
+ | 1.5236 | 8700 | 0.3493 | - |
681
+ | 1.5324 | 8750 | 0.3858 | - |
682
+ | 1.5412 | 8800 | 0.3738 | - |
683
+ | 1.5499 | 8850 | 0.3405 | - |
684
+ | 1.5587 | 8900 | 0.3394 | - |
685
+ | 1.5674 | 8950 | 0.3424 | - |
686
+ | 1.5762 | 9000 | 0.3455 | - |
687
+ | 1.5849 | 9050 | 0.3481 | - |
688
+ | 1.5937 | 9100 | 0.3259 | - |
689
+ | 1.6025 | 9150 | 0.3336 | - |
690
+ | 1.6112 | 9200 | 0.3082 | - |
691
+ | 1.6200 | 9250 | 0.3202 | - |
692
+ | 1.6287 | 9300 | 0.3123 | - |
693
+ | 1.6375 | 9350 | 0.322 | - |
694
+ | 1.6462 | 9400 | 0.3096 | - |
695
+ | 1.6550 | 9450 | 0.3111 | - |
696
+ | 1.6637 | 9500 | 0.3032 | - |
697
+ | 1.6725 | 9550 | 0.3286 | - |
698
+ | 1.6813 | 9600 | 0.3257 | - |
699
+ | 1.6900 | 9650 | 0.3297 | - |
700
+ | 1.6988 | 9700 | 0.2979 | - |
701
+ | 1.7075 | 9750 | 0.3027 | - |
702
+ | 1.7163 | 9800 | 0.3147 | - |
703
+ | 1.7250 | 9850 | 0.3046 | - |
704
+ | 1.7338 | 9900 | 0.314 | - |
705
+ | 1.7426 | 9950 | 0.3131 | - |
706
+ | 1.7513 | 10000 | 0.3096 | - |
707
 
708
  </details>
709
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c429db183b6c06eb7751745efd4a53e9e5720d7db57717559391e41cfc45b1d8
3
  size 125965616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23a418904d26179f177828d376cf2fc94fd0a6cb6fa664e923559b6d69d54757
3
  size 125965616