Add new CrossEncoder model
Browse files- README.md +290 -290
- model.safetensors +1 -1
README.md
CHANGED
@@ -66,25 +66,25 @@ model-index:
|
|
66 |
type: test
|
67 |
metrics:
|
68 |
- type: accuracy
|
69 |
-
value: 0.
|
70 |
name: Accuracy
|
71 |
- type: accuracy_threshold
|
72 |
-
value: 0.
|
73 |
name: Accuracy Threshold
|
74 |
- type: f1
|
75 |
-
value: 0.
|
76 |
name: F1
|
77 |
- type: f1_threshold
|
78 |
-
value: 0.
|
79 |
name: F1 Threshold
|
80 |
- type: precision
|
81 |
-
value: 0.
|
82 |
name: Precision
|
83 |
- type: recall
|
84 |
-
value: 0.
|
85 |
name: Recall
|
86 |
- type: average_precision
|
87 |
-
value: 0.
|
88 |
name: Average Precision
|
89 |
---
|
90 |
|
@@ -188,13 +188,13 @@ You can finetune this model on your own dataset.
|
|
188 |
|
189 |
| Metric | val | test |
|
190 |
|:----------------------|:-----------|:-----------|
|
191 |
-
| accuracy | 0.7718 | 0.
|
192 |
-
| accuracy_threshold | 0.8927 | 0.
|
193 |
-
| f1 | 0.6934 | 0.
|
194 |
-
| f1_threshold | 0.8759 | 0.
|
195 |
-
| precision | 0.6788 | 0.
|
196 |
-
| recall | 0.7086 | 0.
|
197 |
-
| **average_precision** | **0.7676** | **0.
|
198 |
|
199 |
<!--
|
200 |
## Bias, Risks and Limitations
|
@@ -324,7 +324,7 @@ You can finetune this model on your own dataset.
|
|
324 |
- `bf16_full_eval`: False
|
325 |
- `fp16_full_eval`: False
|
326 |
- `tf32`: None
|
327 |
-
- `local_rank`:
|
328 |
- `ddp_backend`: None
|
329 |
- `tpu_num_cores`: None
|
330 |
- `tpu_metrics_debug`: False
|
@@ -402,281 +402,281 @@ You can finetune this model on your own dataset.
|
|
402 |
### Training Logs
|
403 |
<details><summary>Click to expand</summary>
|
404 |
|
405 |
-
| Epoch
|
406 |
-
|
407 |
-
| -1
|
408 |
-
| 0.1833
|
409 |
-
| 0.3666
|
410 |
-
| 0.5499
|
411 |
-
| 0.7331
|
412 |
-
| 0.9164
|
413 |
-
| 1.0997
|
414 |
-
| 1.2830
|
415 |
-
| 1.4663
|
416 |
-
| 1.6496
|
417 |
-
| 1.8328
|
418 |
-
| 2.0161
|
419 |
-
| 2.1994
|
420 |
-
| 2.3827
|
421 |
-
| 2.5660
|
422 |
-
| 2.7493
|
423 |
-
| 2.9326
|
424 |
-
| 3.1158
|
425 |
-
| 3.2991
|
426 |
-
| 3.4824
|
427 |
-
| 3.6657
|
428 |
-
| 3.8490
|
429 |
-
| 4.0323
|
430 |
-
| 4.2155
|
431 |
-
| 4.3988
|
432 |
-
| 4.5821
|
433 |
-
| 4.7654
|
434 |
-
| 4.9487
|
435 |
-
| 5.1320
|
436 |
-
| 5.3152
|
437 |
-
| 5.4985
|
438 |
-
| 5.6818
|
439 |
-
| 5.8651
|
440 |
-
| 6.0484
|
441 |
-
| 6.2317
|
442 |
-
| 6.4150
|
443 |
-
| 6.5982
|
444 |
-
| 6.7815
|
445 |
-
| 6.9648
|
446 |
-
| 7.1481
|
447 |
-
| 7.3314
|
448 |
-
| 7.5147
|
449 |
-
| 7.6979
|
450 |
-
| 7.8812
|
451 |
-
| 8.0645
|
452 |
-
| 8.2478
|
453 |
-
| 8.4311
|
454 |
-
| 8.6144
|
455 |
-
| 8.7977
|
456 |
-
| 8.9809
|
457 |
-
| 9.1642
|
458 |
-
| 9.3475
|
459 |
-
| 9.5308
|
460 |
-
| 9.7141
|
461 |
-
| 9.8974
|
462 |
-
| 10.0806
|
463 |
-
| 10.2639
|
464 |
-
| 10.4472
|
465 |
-
| 10.6305
|
466 |
-
| 10.8138
|
467 |
-
| 10.9971
|
468 |
-
| 11.1804
|
469 |
-
| 11.3636
|
470 |
-
| 11.5469
|
471 |
-
| 11.7302
|
472 |
-
| 11.9135
|
473 |
-
| 12.0968
|
474 |
-
| 12.2801
|
475 |
-
| 12.4633
|
476 |
-
| 12.6466
|
477 |
-
| 12.8299
|
478 |
-
| 13.0132
|
479 |
-
| 13.1965
|
480 |
-
| 13.3798
|
481 |
-
| 13.5630
|
482 |
-
| 13.7463
|
483 |
-
| 13.9296
|
484 |
-
| 14.1129
|
485 |
-
| 14.2962
|
486 |
-
| 14.4795
|
487 |
-
| 14.6628
|
488 |
-
| 14.8460
|
489 |
-
| 15.0293
|
490 |
-
| 15.2126
|
491 |
-
| 15.3959
|
492 |
-
| 15.5792
|
493 |
-
| 15.7625
|
494 |
-
| 15.9457
|
495 |
-
| 16.1290
|
496 |
-
| 16.3123
|
497 |
-
| 16.4956
|
498 |
-
| 16.6789
|
499 |
-
| 16.8622
|
500 |
-
| 17.0455
|
501 |
-
| 17.2287
|
502 |
-
| 17.4120
|
503 |
-
| 17.5953
|
504 |
-
| 17.7786
|
505 |
-
| 17.9619
|
506 |
-
| 18.1452
|
507 |
-
| 18.3284
|
508 |
-
| 18.5117
|
509 |
-
| 18.6950
|
510 |
-
| 18.8783
|
511 |
-
| 19.0616
|
512 |
-
| 19.2449
|
513 |
-
| 19.4282
|
514 |
-
| 19.6114
|
515 |
-
| 19.7947
|
516 |
-
| 19.9780
|
517 |
-
| 20.1613
|
518 |
-
| 20.3446
|
519 |
-
| 20.5279
|
520 |
-
| 20.7111
|
521 |
-
| 20.8944
|
522 |
-
| 21.0777
|
523 |
-
| 21.2610
|
524 |
-
| 21.4443
|
525 |
-
| 21.6276
|
526 |
-
| 21.8109
|
527 |
-
| 21.9941
|
528 |
-
| 22.1774
|
529 |
-
| 22.3607
|
530 |
-
| 22.5440
|
531 |
-
| 22.7273
|
532 |
-
| 22.9106
|
533 |
-
| 23.0938
|
534 |
-
| 23.2771
|
535 |
-
| 23.4604
|
536 |
-
| 23.6437
|
537 |
-
| 23.8270
|
538 |
-
| 24.0103
|
539 |
-
| 24.1935
|
540 |
-
| 24.3768
|
541 |
-
| 24.5601
|
542 |
-
| 24.7434
|
543 |
-
| 24.9267
|
544 |
-
| 25.1100
|
545 |
-
| 25.2933
|
546 |
-
| 25.4765
|
547 |
-
| 25.6598
|
548 |
-
| 25.8431
|
549 |
-
| 26.0264
|
550 |
-
| 26.2097
|
551 |
-
| 26.3930
|
552 |
-
| 26.5762
|
553 |
-
| 26.7595
|
554 |
-
| 26.9428
|
555 |
-
| 27.1261
|
556 |
-
| 27.3094
|
557 |
-
| 27.4927
|
558 |
-
| 27.6760
|
559 |
-
| 27.8592
|
560 |
-
| 28.0425
|
561 |
-
| 28.2258
|
562 |
-
| 28.4091
|
563 |
-
| 28.5924
|
564 |
-
| 28.7757
|
565 |
-
| 28.9589
|
566 |
-
| 29.1422
|
567 |
-
| 29.3255
|
568 |
-
| 29.5088
|
569 |
-
| 29.6921
|
570 |
-
| 29.8754
|
571 |
-
| 30.0587
|
572 |
-
| 30.2419
|
573 |
-
| 30.4252
|
574 |
-
| 30.6085
|
575 |
-
| 30.7918
|
576 |
-
| 30.9751
|
577 |
-
| 31.1584
|
578 |
-
| 31.3416
|
579 |
-
| 31.5249
|
580 |
-
| 31.7082
|
581 |
-
| 31.8915
|
582 |
-
| 32.0748
|
583 |
-
| 32.2581
|
584 |
-
| 32.4413
|
585 |
-
| 32.6246
|
586 |
-
| 32.8079
|
587 |
-
| 32.9912
|
588 |
-
| 33.1745
|
589 |
-
| 33.3578
|
590 |
-
| 33.5411
|
591 |
-
| 33.7243
|
592 |
-
| 33.9076
|
593 |
-
| 34.0909
|
594 |
-
| 34.2742
|
595 |
-
| 34.4575
|
596 |
-
| 34.6408
|
597 |
-
| 34.
|
598 |
-
| 35.0073
|
599 |
-
| 35.1906
|
600 |
-
| 35.3739
|
601 |
-
| 35.5572
|
602 |
-
| 35.7405
|
603 |
-
| 35.9238
|
604 |
-
| 36.1070
|
605 |
-
| 36.2903
|
606 |
-
| 36.4736
|
607 |
-
| 36.6569
|
608 |
-
| 36.8402
|
609 |
-
| 37.0235
|
610 |
-
| 37.2067
|
611 |
-
| 37.3900
|
612 |
-
| 37.5733
|
613 |
-
| 37.7566
|
614 |
-
| 37.9399
|
615 |
-
| 38.1232
|
616 |
-
| 38.3065
|
617 |
-
| 38.4897
|
618 |
-
| 38.6730
|
619 |
-
| 38.8563
|
620 |
-
| 39.0396
|
621 |
-
| 39.2229
|
622 |
-
| 39.4062
|
623 |
-
| 39.5894
|
624 |
-
| 39.7727
|
625 |
-
| 39.9560
|
626 |
-
| 40.1393
|
627 |
-
| 40.3226
|
628 |
-
| 40.5059
|
629 |
-
| 40.6891
|
630 |
-
| 40.8724
|
631 |
-
| 41.0557
|
632 |
-
| 41.2390
|
633 |
-
| 41.4223
|
634 |
-
| 41.6056
|
635 |
-
| 41.7889
|
636 |
-
| 41.9721
|
637 |
-
| 42.1554
|
638 |
-
| 42.3387
|
639 |
-
| 42.5220
|
640 |
-
|
|
641 |
-
| 42.8886
|
642 |
-
| 43.0718
|
643 |
-
| 43.2551
|
644 |
-
| 43.4384
|
645 |
-
| 43.6217
|
646 |
-
| 43.8050
|
647 |
-
| 43.9883
|
648 |
-
| 44.1716
|
649 |
-
| 44.3548
|
650 |
-
| 44.5381
|
651 |
-
| 44.7214
|
652 |
-
| 44.9047
|
653 |
-
| 45.0880
|
654 |
-
| 45.2713
|
655 |
-
| 45.4545
|
656 |
-
| 45.6378
|
657 |
-
| 45.8211
|
658 |
-
| 46.0044
|
659 |
-
| 46.1877
|
660 |
-
| 46.3710
|
661 |
-
| 46.5543
|
662 |
-
| 46.7375
|
663 |
-
| 46.9208
|
664 |
-
| 47.1041
|
665 |
-
| 47.2874
|
666 |
-
| 47.4707
|
667 |
-
| 47.6540
|
668 |
-
| 47.8372
|
669 |
-
| 48.0205
|
670 |
-
| 48.2038
|
671 |
-
| 48.3871
|
672 |
-
| 48.5704
|
673 |
-
| 48.7537
|
674 |
-
| 48.9370
|
675 |
-
| 49.1202
|
676 |
-
| 49.3035
|
677 |
-
| 49.4868
|
678 |
-
| 49.6701
|
679 |
-
| 49.8534
|
680 |
|
681 |
* The bold row denotes the saved checkpoint.
|
682 |
</details>
|
|
|
66 |
type: test
|
67 |
metrics:
|
68 |
- type: accuracy
|
69 |
+
value: 0.8947292046242402
|
70 |
name: Accuracy
|
71 |
- type: accuracy_threshold
|
72 |
+
value: 0.8615613579750061
|
73 |
name: Accuracy Threshold
|
74 |
- type: f1
|
75 |
+
value: 0.8797439414723366
|
76 |
name: F1
|
77 |
- type: f1_threshold
|
78 |
+
value: 0.503699541091919
|
79 |
name: F1 Threshold
|
80 |
- type: precision
|
81 |
+
value: 0.8643306379155435
|
82 |
name: Precision
|
83 |
- type: recall
|
84 |
+
value: 0.8957169459962756
|
85 |
name: Recall
|
86 |
- type: average_precision
|
87 |
+
value: 0.934515467879065
|
88 |
name: Average Precision
|
89 |
---
|
90 |
|
|
|
188 |
|
189 |
| Metric | val | test |
|
190 |
|:----------------------|:-----------|:-----------|
|
191 |
+
| accuracy | 0.7718 | 0.8947 |
|
192 |
+
| accuracy_threshold | 0.8927 | 0.8616 |
|
193 |
+
| f1 | 0.6934 | 0.8797 |
|
194 |
+
| f1_threshold | 0.8759 | 0.5037 |
|
195 |
+
| precision | 0.6788 | 0.8643 |
|
196 |
+
| recall | 0.7086 | 0.8957 |
|
197 |
+
| **average_precision** | **0.7676** | **0.9345** |
|
198 |
|
199 |
<!--
|
200 |
## Bias, Risks and Limitations
|
|
|
324 |
- `bf16_full_eval`: False
|
325 |
- `fp16_full_eval`: False
|
326 |
- `tf32`: None
|
327 |
+
- `local_rank`: 0
|
328 |
- `ddp_backend`: None
|
329 |
- `tpu_num_cores`: None
|
330 |
- `tpu_metrics_debug`: False
|
|
|
402 |
### Training Logs
|
403 |
<details><summary>Click to expand</summary>
|
404 |
|
405 |
+
| Epoch | Step | Training Loss | Validation Loss | val_average_precision | test_average_precision |
|
406 |
+
|:----------:|:----------:|:-------------:|:---------------:|:---------------------:|:----------------------:|
|
407 |
+
| -1 | -1 | - | - | 0.7676 | 0.6907 |
|
408 |
+
| 0.1833 | 1000 | 0.2986 | 0.3912 | - | 0.8585 |
|
409 |
+
| 0.3666 | 2000 | 0.2465 | 0.3856 | - | 0.8956 |
|
410 |
+
| 0.5499 | 3000 | 0.2287 | 0.3362 | - | 0.9160 |
|
411 |
+
| 0.7331 | 4000 | 0.2171 | 0.3408 | - | 0.9071 |
|
412 |
+
| 0.9164 | 5000 | 0.2068 | 0.3182 | - | 0.9220 |
|
413 |
+
| 1.0997 | 6000 | 0.1991 | 0.3458 | - | 0.8686 |
|
414 |
+
| 1.2830 | 7000 | 0.1939 | 0.3188 | - | 0.9244 |
|
415 |
+
| 1.4663 | 8000 | 0.1917 | 0.3120 | - | 0.9287 |
|
416 |
+
| 1.6496 | 9000 | 0.1906 | 0.3015 | - | 0.9279 |
|
417 |
+
| 1.8328 | 10000 | 0.1884 | 0.2986 | - | 0.9316 |
|
418 |
+
| 2.0161 | 11000 | 0.183 | 0.3065 | - | 0.9320 |
|
419 |
+
| 2.1994 | 12000 | 0.1714 | 0.3046 | - | 0.9180 |
|
420 |
+
| 2.3827 | 13000 | 0.1738 | 0.2994 | - | 0.9315 |
|
421 |
+
| 2.5660 | 14000 | 0.1709 | 0.2965 | - | 0.9347 |
|
422 |
+
| 2.7493 | 15000 | 0.1717 | 0.2911 | - | 0.9309 |
|
423 |
+
| 2.9326 | 16000 | 0.1698 | 0.2900 | - | 0.9354 |
|
424 |
+
| 3.1158 | 17000 | 0.16 | 0.2894 | - | 0.9377 |
|
425 |
+
| 3.2991 | 18000 | 0.1589 | 0.2830 | - | 0.9356 |
|
426 |
+
| 3.4824 | 19000 | 0.1574 | 0.2829 | - | 0.9337 |
|
427 |
+
| 3.6657 | 20000 | 0.1572 | 0.2818 | - | 0.9324 |
|
428 |
+
| 3.8490 | 21000 | 0.1587 | 0.2866 | - | 0.9365 |
|
429 |
+
| 4.0323 | 22000 | 0.1543 | 0.2923 | - | 0.9389 |
|
430 |
+
| 4.2155 | 23000 | 0.1445 | 0.2871 | - | 0.9430 |
|
431 |
+
| 4.3988 | 24000 | 0.1447 | 0.2793 | - | 0.9429 |
|
432 |
+
| 4.5821 | 25000 | 0.1473 | 0.2791 | - | 0.9386 |
|
433 |
+
| 4.7654 | 26000 | 0.146 | 0.2700 | - | 0.9417 |
|
434 |
+
| 4.9487 | 27000 | 0.1473 | 0.2697 | - | 0.9419 |
|
435 |
+
| 5.1320 | 28000 | 0.1365 | 0.2810 | - | 0.9411 |
|
436 |
+
| 5.3152 | 29000 | 0.1331 | 0.2764 | - | 0.9397 |
|
437 |
+
| 5.4985 | 30000 | 0.1372 | 0.2794 | - | 0.9416 |
|
438 |
+
| 5.6818 | 31000 | 0.1365 | 0.2751 | - | 0.9408 |
|
439 |
+
| 5.8651 | 32000 | 0.1365 | 0.2724 | - | 0.9411 |
|
440 |
+
| 6.0484 | 33000 | 0.1348 | 0.2767 | - | 0.9378 |
|
441 |
+
| 6.2317 | 34000 | 0.1236 | 0.2840 | - | 0.9388 |
|
442 |
+
| 6.4150 | 35000 | 0.1262 | 0.2845 | - | 0.9437 |
|
443 |
+
| 6.5982 | 36000 | 0.1277 | 0.2781 | - | 0.9446 |
|
444 |
+
| 6.7815 | 37000 | 0.129 | 0.2705 | - | 0.9427 |
|
445 |
+
| 6.9648 | 38000 | 0.1279 | 0.2773 | - | 0.9381 |
|
446 |
+
| 7.1481 | 39000 | 0.1173 | 0.2875 | - | 0.9420 |
|
447 |
+
| 7.3314 | 40000 | 0.1175 | 0.2901 | - | 0.9438 |
|
448 |
+
| 7.5147 | 41000 | 0.1174 | 0.2787 | - | 0.9420 |
|
449 |
+
| 7.6979 | 42000 | 0.118 | 0.2879 | - | 0.9424 |
|
450 |
+
| 7.8812 | 43000 | 0.1201 | 0.2826 | - | 0.9450 |
|
451 |
+
| 8.0645 | 44000 | 0.1168 | 0.2851 | - | 0.9419 |
|
452 |
+
| 8.2478 | 45000 | 0.1062 | 0.2913 | - | 0.9450 |
|
453 |
+
| 8.4311 | 46000 | 0.1091 | 0.2918 | - | 0.9454 |
|
454 |
+
| 8.6144 | 47000 | 0.1117 | 0.2799 | - | 0.9445 |
|
455 |
+
| 8.7977 | 48000 | 0.1123 | 0.2762 | - | 0.9443 |
|
456 |
+
| 8.9809 | 49000 | 0.1132 | 0.2772 | - | 0.9455 |
|
457 |
+
| 9.1642 | 50000 | 0.1016 | 0.2943 | - | 0.9433 |
|
458 |
+
| 9.3475 | 51000 | 0.1012 | 0.2879 | - | 0.9441 |
|
459 |
+
| 9.5308 | 52000 | 0.1029 | 0.2851 | - | 0.9442 |
|
460 |
+
| 9.7141 | 53000 | 0.105 | 0.2905 | - | 0.9448 |
|
461 |
+
| 9.8974 | 54000 | 0.1062 | 0.2960 | - | 0.9425 |
|
462 |
+
| 10.0806 | 55000 | 0.0996 | 0.2984 | - | 0.9430 |
|
463 |
+
| 10.2639 | 56000 | 0.0924 | 0.2947 | - | 0.9432 |
|
464 |
+
| 10.4472 | 57000 | 0.0939 | 0.2918 | - | 0.9421 |
|
465 |
+
| 10.6305 | 58000 | 0.0977 | 0.2895 | - | 0.9438 |
|
466 |
+
| 10.8138 | 59000 | 0.0977 | 0.2905 | - | 0.9446 |
|
467 |
+
| 10.9971 | 60000 | 0.0985 | 0.2882 | - | 0.9403 |
|
468 |
+
| 11.1804 | 61000 | 0.0857 | 0.3025 | - | 0.9435 |
|
469 |
+
| 11.3636 | 62000 | 0.0869 | 0.2997 | - | 0.9450 |
|
470 |
+
| 11.5469 | 63000 | 0.0886 | 0.3025 | - | 0.9459 |
|
471 |
+
| 11.7302 | 64000 | 0.0901 | 0.3000 | - | 0.9443 |
|
472 |
+
| 11.9135 | 65000 | 0.092 | 0.2913 | - | 0.9424 |
|
473 |
+
| 12.0968 | 66000 | 0.085 | 0.3017 | - | 0.9443 |
|
474 |
+
| 12.2801 | 67000 | 0.0801 | 0.3101 | - | 0.9449 |
|
475 |
+
| 12.4633 | 68000 | 0.0823 | 0.3018 | - | 0.9468 |
|
476 |
+
| 12.6466 | 69000 | 0.0841 | 0.2971 | - | 0.9457 |
|
477 |
+
| 12.8299 | 70000 | 0.0855 | 0.3063 | - | 0.9428 |
|
478 |
+
| 13.0132 | 71000 | 0.0854 | 0.3105 | - | 0.9436 |
|
479 |
+
| 13.1965 | 72000 | 0.0744 | 0.3017 | - | 0.9451 |
|
480 |
+
| 13.3798 | 73000 | 0.0763 | 0.3024 | - | 0.9425 |
|
481 |
+
| 13.5630 | 74000 | 0.0777 | 0.2948 | - | 0.9461 |
|
482 |
+
| 13.7463 | 75000 | 0.0791 | 0.3006 | - | 0.9466 |
|
483 |
+
| 13.9296 | 76000 | 0.0803 | 0.3001 | - | 0.9446 |
|
484 |
+
| 14.1129 | 77000 | 0.0721 | 0.3229 | - | 0.9445 |
|
485 |
+
| 14.2962 | 78000 | 0.0692 | 0.3231 | - | 0.9437 |
|
486 |
+
| 14.4795 | 79000 | 0.0703 | 0.3242 | - | 0.9458 |
|
487 |
+
| 14.6628 | 80000 | 0.073 | 0.3078 | - | 0.9469 |
|
488 |
+
| 14.8460 | 81000 | 0.073 | 0.3111 | - | 0.9448 |
|
489 |
+
| 15.0293 | 82000 | 0.0731 | 0.3319 | - | 0.9459 |
|
490 |
+
| 15.2126 | 83000 | 0.0629 | 0.3094 | - | 0.9464 |
|
491 |
+
| 15.3959 | 84000 | 0.0644 | 0.3440 | - | 0.9427 |
|
492 |
+
| 15.5792 | 85000 | 0.0673 | 0.3234 | - | 0.9457 |
|
493 |
+
| 15.7625 | 86000 | 0.068 | 0.3192 | - | 0.9430 |
|
494 |
+
| 15.9457 | 87000 | 0.0687 | 0.3097 | - | 0.9428 |
|
495 |
+
| 16.1290 | 88000 | 0.0618 | 0.3379 | - | 0.9466 |
|
496 |
+
| 16.3123 | 89000 | 0.0615 | 0.3192 | - | 0.9436 |
|
497 |
+
| 16.4956 | 90000 | 0.0605 | 0.3303 | - | 0.9452 |
|
498 |
+
| 16.6789 | 91000 | 0.0635 | 0.3154 | - | 0.9445 |
|
499 |
+
| 16.8622 | 92000 | 0.0637 | 0.3324 | - | 0.9467 |
|
500 |
+
| 17.0455 | 93000 | 0.0615 | 0.3365 | - | 0.9424 |
|
501 |
+
| 17.2287 | 94000 | 0.056 | 0.3332 | - | 0.9446 |
|
502 |
+
| 17.4120 | 95000 | 0.0567 | 0.3412 | - | 0.9432 |
|
503 |
+
| 17.5953 | 96000 | 0.0571 | 0.3419 | - | 0.9444 |
|
504 |
+
| 17.7786 | 97000 | 0.0589 | 0.3271 | - | 0.9403 |
|
505 |
+
| 17.9619 | 98000 | 0.0588 | 0.3281 | - | 0.9440 |
|
506 |
+
| 18.1452 | 99000 | 0.053 | 0.3282 | - | 0.9475 |
|
507 |
+
| 18.3284 | 100000 | 0.0525 | 0.3414 | - | 0.9470 |
|
508 |
+
| 18.5117 | 101000 | 0.0528 | 0.3263 | - | 0.9450 |
|
509 |
+
| 18.6950 | 102000 | 0.0539 | 0.3363 | - | 0.9428 |
|
510 |
+
| 18.8783 | 103000 | 0.056 | 0.3487 | - | 0.9454 |
|
511 |
+
| 19.0616 | 104000 | 0.0528 | 0.3701 | - | 0.9465 |
|
512 |
+
| 19.2449 | 105000 | 0.0464 | 0.3877 | - | 0.9328 |
|
513 |
+
| 19.4282 | 106000 | 0.0499 | 0.3379 | - | 0.9451 |
|
514 |
+
| 19.6114 | 107000 | 0.0496 | 0.3500 | - | 0.9442 |
|
515 |
+
| 19.7947 | 108000 | 0.0502 | 0.3420 | - | 0.9444 |
|
516 |
+
| 19.9780 | 109000 | 0.0519 | 0.3459 | - | 0.9442 |
|
517 |
+
| 20.1613 | 110000 | 0.0443 | 0.3755 | - | 0.9449 |
|
518 |
+
| 20.3446 | 111000 | 0.0449 | 0.3588 | - | 0.9447 |
|
519 |
+
| 20.5279 | 112000 | 0.0448 | 0.3616 | - | 0.9448 |
|
520 |
+
| 20.7111 | 113000 | 0.0471 | 0.3463 | - | 0.9426 |
|
521 |
+
| 20.8944 | 114000 | 0.0474 | 0.3784 | - | 0.9400 |
|
522 |
+
| 21.0777 | 115000 | 0.0451 | 0.3493 | - | 0.9447 |
|
523 |
+
| 21.2610 | 116000 | 0.0415 | 0.3633 | - | 0.9448 |
|
524 |
+
| 21.4443 | 117000 | 0.0412 | 0.3635 | - | 0.9472 |
|
525 |
+
| 21.6276 | 118000 | 0.0441 | 0.3710 | - | 0.9454 |
|
526 |
+
| 21.8109 | 119000 | 0.0427 | 0.3696 | - | 0.9459 |
|
527 |
+
| 21.9941 | 120000 | 0.045 | 0.3571 | - | 0.9440 |
|
528 |
+
| 22.1774 | 121000 | 0.0384 | 0.3815 | - | 0.9431 |
|
529 |
+
| 22.3607 | 122000 | 0.0389 | 0.3832 | - | 0.9428 |
|
530 |
+
| 22.5440 | 123000 | 0.0397 | 0.3773 | - | 0.9461 |
|
531 |
+
| 22.7273 | 124000 | 0.0402 | 0.3977 | - | 0.9415 |
|
532 |
+
| 22.9106 | 125000 | 0.0399 | 0.3870 | - | 0.9354 |
|
533 |
+
| 23.0938 | 126000 | 0.0376 | 0.3820 | - | 0.9409 |
|
534 |
+
| 23.2771 | 127000 | 0.0362 | 0.3755 | - | 0.9411 |
|
535 |
+
| 23.4604 | 128000 | 0.0358 | 0.3915 | - | 0.9461 |
|
536 |
+
| 23.6437 | 129000 | 0.0368 | 0.3688 | - | 0.9411 |
|
537 |
+
| 23.8270 | 130000 | 0.0374 | 0.4068 | - | 0.9427 |
|
538 |
+
| 24.0103 | 131000 | 0.0376 | 0.4155 | - | 0.9445 |
|
539 |
+
| 24.1935 | 132000 | 0.0325 | 0.3967 | - | 0.9434 |
|
540 |
+
| 24.3768 | 133000 | 0.0333 | 0.4209 | - | 0.9425 |
|
541 |
+
| 24.5601 | 134000 | 0.0335 | 0.4018 | - | 0.9432 |
|
542 |
+
| 24.7434 | 135000 | 0.0343 | 0.4250 | - | 0.9443 |
|
543 |
+
| 24.9267 | 136000 | 0.0345 | 0.4185 | - | 0.9414 |
|
544 |
+
| 25.1100 | 137000 | 0.0316 | 0.4075 | - | 0.9454 |
|
545 |
+
| 25.2933 | 138000 | 0.0299 | 0.4096 | - | 0.9454 |
|
546 |
+
| 25.4765 | 139000 | 0.0294 | 0.4135 | - | 0.9459 |
|
547 |
+
| 25.6598 | 140000 | 0.0317 | 0.3997 | - | 0.9445 |
|
548 |
+
| 25.8431 | 141000 | 0.0328 | 0.4093 | - | 0.9438 |
|
549 |
+
| 26.0264 | 142000 | 0.0317 | 0.4361 | - | 0.9404 |
|
550 |
+
| 26.2097 | 143000 | 0.027 | 0.4347 | - | 0.9454 |
|
551 |
+
| 26.3930 | 144000 | 0.0281 | 0.4149 | - | 0.9413 |
|
552 |
+
| 26.5762 | 145000 | 0.0283 | 0.4151 | - | 0.9454 |
|
553 |
+
| 26.7595 | 146000 | 0.0302 | 0.4041 | - | 0.9416 |
|
554 |
+
| 26.9428 | 147000 | 0.0301 | 0.4265 | - | 0.9340 |
|
555 |
+
| 27.1261 | 148000 | 0.026 | 0.4223 | - | 0.9426 |
|
556 |
+
| 27.3094 | 149000 | 0.0267 | 0.4237 | - | 0.9430 |
|
557 |
+
| 27.4927 | 150000 | 0.0268 | 0.4281 | - | 0.9458 |
|
558 |
+
| 27.6760 | 151000 | 0.0262 | 0.4193 | - | 0.9426 |
|
559 |
+
| 27.8592 | 152000 | 0.0262 | 0.4412 | - | 0.9402 |
|
560 |
+
| 28.0425 | 153000 | 0.0261 | 0.4795 | - | 0.9425 |
|
561 |
+
| 28.2258 | 154000 | 0.024 | 0.4519 | - | 0.9442 |
|
562 |
+
| 28.4091 | 155000 | 0.024 | 0.4395 | - | 0.9440 |
|
563 |
+
| 28.5924 | 156000 | 0.025 | 0.4549 | - | 0.9456 |
|
564 |
+
| 28.7757 | 157000 | 0.0253 | 0.4446 | - | 0.9429 |
|
565 |
+
| 28.9589 | 158000 | 0.0258 | 0.4349 | - | 0.9425 |
|
566 |
+
| 29.1422 | 159000 | 0.0211 | 0.4490 | - | 0.9430 |
|
567 |
+
| 29.3255 | 160000 | 0.0218 | 0.4538 | - | 0.9455 |
|
568 |
+
| 29.5088 | 161000 | 0.0217 | 0.4771 | - | 0.9435 |
|
569 |
+
| 29.6921 | 162000 | 0.0228 | 0.4238 | - | 0.9440 |
|
570 |
+
| 29.8754 | 163000 | 0.022 | 0.4731 | - | 0.9412 |
|
571 |
+
| 30.0587 | 164000 | 0.0227 | 0.4630 | - | 0.9450 |
|
572 |
+
| 30.2419 | 165000 | 0.0197 | 0.4840 | - | 0.9453 |
|
573 |
+
| 30.4252 | 166000 | 0.0198 | 0.4799 | - | 0.9434 |
|
574 |
+
| 30.6085 | 167000 | 0.022 | 0.4650 | - | 0.9453 |
|
575 |
+
| 30.7918 | 168000 | 0.0211 | 0.4592 | - | 0.9465 |
|
576 |
+
| 30.9751 | 169000 | 0.022 | 0.4727 | - | 0.9405 |
|
577 |
+
| 31.1584 | 170000 | 0.0184 | 0.4802 | - | 0.9460 |
|
578 |
+
| 31.3416 | 171000 | 0.0186 | 0.4953 | - | 0.9449 |
|
579 |
+
| 31.5249 | 172000 | 0.0187 | 0.4516 | - | 0.9424 |
|
580 |
+
| 31.7082 | 173000 | 0.019 | 0.4803 | - | 0.9444 |
|
581 |
+
| 31.8915 | 174000 | 0.0186 | 0.4499 | - | 0.9448 |
|
582 |
+
| 32.0748 | 175000 | 0.0181 | 0.5211 | - | 0.9377 |
|
583 |
+
| 32.2581 | 176000 | 0.0163 | 0.4941 | - | 0.9434 |
|
584 |
+
| 32.4413 | 177000 | 0.0168 | 0.4672 | - | 0.9433 |
|
585 |
+
| 32.6246 | 178000 | 0.0171 | 0.4990 | - | 0.9414 |
|
586 |
+
| 32.8079 | 179000 | 0.0185 | 0.4537 | - | 0.9444 |
|
587 |
+
| 32.9912 | 180000 | 0.0179 | 0.4929 | - | 0.9460 |
|
588 |
+
| 33.1745 | 181000 | 0.0144 | 0.5037 | - | 0.9407 |
|
589 |
+
| 33.3578 | 182000 | 0.0143 | 0.4986 | - | 0.9449 |
|
590 |
+
| 33.5411 | 183000 | 0.016 | 0.5043 | - | 0.9452 |
|
591 |
+
| 33.7243 | 184000 | 0.0152 | 0.5090 | - | 0.9427 |
|
592 |
+
| 33.9076 | 185000 | 0.0154 | 0.5100 | - | 0.9414 |
|
593 |
+
| 34.0909 | 186000 | 0.0146 | 0.5367 | - | 0.9386 |
|
594 |
+
| 34.2742 | 187000 | 0.0138 | 0.5063 | - | 0.9395 |
|
595 |
+
| 34.4575 | 188000 | 0.0143 | 0.4871 | - | 0.9446 |
|
596 |
+
| 34.6408 | 189000 | 0.014 | 0.4947 | - | 0.9483 |
|
597 |
+
| **34.824** | **190000** | **0.0142** | **0.5079** | **-** | **0.9467** |
|
598 |
+
| 35.0073 | 191000 | 0.014 | 0.5062 | - | 0.9439 |
|
599 |
+
| 35.1906 | 192000 | 0.0122 | 0.5293 | - | 0.9410 |
|
600 |
+
| 35.3739 | 193000 | 0.0127 | 0.5351 | - | 0.9401 |
|
601 |
+
| 35.5572 | 194000 | 0.0132 | 0.5263 | - | 0.9369 |
|
602 |
+
| 35.7405 | 195000 | 0.0134 | 0.5300 | - | 0.9427 |
|
603 |
+
| 35.9238 | 196000 | 0.0138 | 0.5230 | - | 0.9416 |
|
604 |
+
| 36.1070 | 197000 | 0.0129 | 0.5399 | - | 0.9417 |
|
605 |
+
| 36.2903 | 198000 | 0.0109 | 0.5352 | - | 0.9433 |
|
606 |
+
| 36.4736 | 199000 | 0.0114 | 0.5587 | - | 0.9404 |
|
607 |
+
| 36.6569 | 200000 | 0.012 | 0.5289 | - | 0.9441 |
|
608 |
+
| 36.8402 | 201000 | 0.012 | 0.5516 | - | 0.9434 |
|
609 |
+
| 37.0235 | 202000 | 0.0121 | 0.5467 | - | 0.9418 |
|
610 |
+
| 37.2067 | 203000 | 0.0108 | 0.5499 | - | 0.9412 |
|
611 |
+
| 37.3900 | 204000 | 0.0107 | 0.5459 | - | 0.9427 |
|
612 |
+
| 37.5733 | 205000 | 0.0105 | 0.5375 | - | 0.9414 |
|
613 |
+
| 37.7566 | 206000 | 0.0109 | 0.5566 | - | 0.9421 |
|
614 |
+
| 37.9399 | 207000 | 0.011 | 0.5601 | - | 0.9428 |
|
615 |
+
| 38.1232 | 208000 | 0.0095 | 0.5700 | - | 0.9406 |
|
616 |
+
| 38.3065 | 209000 | 0.0098 | 0.5493 | - | 0.9417 |
|
617 |
+
| 38.4897 | 210000 | 0.0093 | 0.5867 | - | 0.9372 |
|
618 |
+
| 38.6730 | 211000 | 0.0095 | 0.6087 | - | 0.9394 |
|
619 |
+
| 38.8563 | 212000 | 0.0096 | 0.5888 | - | 0.9397 |
|
620 |
+
| 39.0396 | 213000 | 0.0094 | 0.5806 | - | 0.9380 |
|
621 |
+
| 39.2229 | 214000 | 0.0087 | 0.5927 | - | 0.9393 |
|
622 |
+
| 39.4062 | 215000 | 0.0079 | 0.6153 | - | 0.9376 |
|
623 |
+
| 39.5894 | 216000 | 0.009 | 0.6151 | - | 0.9398 |
|
624 |
+
| 39.7727 | 217000 | 0.009 | 0.5601 | - | 0.9379 |
|
625 |
+
| 39.9560 | 218000 | 0.0086 | 0.5845 | - | 0.9409 |
|
626 |
+
| 40.1393 | 219000 | 0.0078 | 0.5929 | - | 0.9396 |
|
627 |
+
| 40.3226 | 220000 | 0.0077 | 0.6086 | - | 0.9417 |
|
628 |
+
| 40.5059 | 221000 | 0.0075 | 0.6053 | - | 0.9418 |
|
629 |
+
| 40.6891 | 222000 | 0.008 | 0.6078 | - | 0.9394 |
|
630 |
+
| 40.8724 | 223000 | 0.0084 | 0.5975 | - | 0.9423 |
|
631 |
+
| 41.0557 | 224000 | 0.0068 | 0.6410 | - | 0.9400 |
|
632 |
+
| 41.2390 | 225000 | 0.0067 | 0.6183 | - | 0.9409 |
|
633 |
+
| 41.4223 | 226000 | 0.0067 | 0.6239 | - | 0.9401 |
|
634 |
+
| 41.6056 | 227000 | 0.0075 | 0.5971 | - | 0.9408 |
|
635 |
+
| 41.7889 | 228000 | 0.0069 | 0.6458 | - | 0.9396 |
|
636 |
+
| 41.9721 | 229000 | 0.0073 | 0.6289 | - | 0.9337 |
|
637 |
+
| 42.1554 | 230000 | 0.0061 | 0.6311 | - | 0.9351 |
|
638 |
+
| 42.3387 | 231000 | 0.0064 | 0.6371 | - | 0.9254 |
|
639 |
+
| 42.5220 | 232000 | 0.0067 | 0.6119 | - | 0.9238 |
|
640 |
+
| 42.7053 | 233000 | 0.0068 | 0.6045 | - | 0.9435 |
|
641 |
+
| 42.8886 | 234000 | 0.0064 | 0.6246 | - | 0.9403 |
|
642 |
+
| 43.0718 | 235000 | 0.0066 | 0.6077 | - | 0.9355 |
|
643 |
+
| 43.2551 | 236000 | 0.0054 | 0.6348 | - | 0.9429 |
|
644 |
+
| 43.4384 | 237000 | 0.0053 | 0.6606 | - | 0.9414 |
|
645 |
+
| 43.6217 | 238000 | 0.0054 | 0.6373 | - | 0.9421 |
|
646 |
+
| 43.8050 | 239000 | 0.006 | 0.6122 | - | 0.9391 |
|
647 |
+
| 43.9883 | 240000 | 0.0058 | 0.6438 | - | 0.9380 |
|
648 |
+
| 44.1716 | 241000 | 0.0051 | 0.6474 | - | 0.9392 |
|
649 |
+
| 44.3548 | 242000 | 0.0049 | 0.6637 | - | 0.9399 |
|
650 |
+
| 44.5381 | 243000 | 0.005 | 0.6765 | - | 0.9420 |
|
651 |
+
| 44.7214 | 244000 | 0.0052 | 0.6585 | - | 0.9406 |
|
652 |
+
| 44.9047 | 245000 | 0.005 | 0.6609 | - | 0.9420 |
|
653 |
+
| 45.0880 | 246000 | 0.0048 | 0.6725 | - | 0.9417 |
|
654 |
+
| 45.2713 | 247000 | 0.0044 | 0.6597 | - | 0.9411 |
|
655 |
+
| 45.4545 | 248000 | 0.0045 | 0.6717 | - | 0.9381 |
|
656 |
+
| 45.6378 | 249000 | 0.0046 | 0.6689 | - | 0.9361 |
|
657 |
+
| 45.8211 | 250000 | 0.0046 | 0.6703 | - | 0.9334 |
|
658 |
+
| 46.0044 | 251000 | 0.0044 | 0.6958 | - | 0.9324 |
|
659 |
+
| 46.1877 | 252000 | 0.0041 | 0.6884 | - | 0.9380 |
|
660 |
+
| 46.3710 | 253000 | 0.0041 | 0.6958 | - | 0.9342 |
|
661 |
+
| 46.5543 | 254000 | 0.004 | 0.6796 | - | 0.9375 |
|
662 |
+
| 46.7375 | 255000 | 0.0042 | 0.6735 | - | 0.9311 |
|
663 |
+
| 46.9208 | 256000 | 0.004 | 0.7004 | - | 0.9264 |
|
664 |
+
| 47.1041 | 257000 | 0.0041 | 0.6798 | - | 0.9303 |
|
665 |
+
| 47.2874 | 258000 | 0.0036 | 0.7039 | - | 0.9330 |
|
666 |
+
| 47.4707 | 259000 | 0.0037 | 0.7133 | - | 0.9277 |
|
667 |
+
| 47.6540 | 260000 | 0.0033 | 0.7200 | - | 0.9250 |
|
668 |
+
| 47.8372 | 261000 | 0.0038 | 0.7204 | - | 0.9292 |
|
669 |
+
| 48.0205 | 262000 | 0.0034 | 0.7214 | - | 0.9336 |
|
670 |
+
| 48.2038 | 263000 | 0.0037 | 0.7077 | - | 0.9313 |
|
671 |
+
| 48.3871 | 264000 | 0.0033 | 0.7218 | - | 0.9289 |
|
672 |
+
| 48.5704 | 265000 | 0.0033 | 0.7258 | - | 0.9328 |
|
673 |
+
| 48.7537 | 266000 | 0.0034 | 0.7215 | - | 0.9346 |
|
674 |
+
| 48.9370 | 267000 | 0.0031 | 0.7300 | - | 0.9347 |
|
675 |
+
| 49.1202 | 268000 | 0.0033 | 0.7242 | - | 0.9350 |
|
676 |
+
| 49.3035 | 269000 | 0.0028 | 0.7320 | - | 0.9345 |
|
677 |
+
| 49.4868 | 270000 | 0.003 | 0.7397 | - | 0.9341 |
|
678 |
+
| 49.6701 | 271000 | 0.0029 | 0.7410 | - | 0.9342 |
|
679 |
+
| 49.8534 | 272000 | 0.0029 | 0.7426 | - | 0.9345 |
|
680 |
|
681 |
* The bold row denotes the saved checkpoint.
|
682 |
</details>
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 598436708
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0e7c5715d82cb05182e522e16b2a21437fd09403bfe19d9e0aeaed984f68cc7
|
3 |
size 598436708
|