Aditeya Baral
commited on
Add new CrossEncoder model
Browse files- README.md +288 -288
- 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
|
|
@@ -405,281 +405,281 @@ You can finetune this model on your own dataset.
|
|
| 405 |
| Epoch | Step | Training Loss | Validation Loss | val_average_precision | test_average_precision |
|
| 406 |
|:-----------:|:----------:|:-------------:|:---------------:|:---------------------:|:----------------------:|
|
| 407 |
| -1 | -1 | - | - | 0.7676 | 0.6907 |
|
| 408 |
-
| 0.1818 | 1000 | 0.3058 | 0.3991 | - | 0.
|
| 409 |
-
| 0.3636 | 2000 | 0.2417 | 0.3729 | - | 0.
|
| 410 |
-
| 0.5455 | 3000 | 0.2287 | 0.3356 | - | 0.
|
| 411 |
-
| 0.7273 | 4000 | 0.2183 | 0.3729 | - | 0.
|
| 412 |
-
| 0.9091 | 5000 | 0.212 | 0.3404 | - | 0.
|
| 413 |
-
| 1.0909 | 6000 | 0.1999 | 0.3171 | - | 0.
|
| 414 |
-
| 1.2727 | 7000 | 0.1944 | 0.3131 | - | 0.
|
| 415 |
-
| 1.4545 | 8000 | 0.1933 | 0.3116 | - | 0.
|
| 416 |
-
| 1.6364 | 9000 | 0.193 | 0.3211 | - | 0.
|
| 417 |
-
| 1.8182 | 10000 | 0.1879 | 0.2984 | - | 0.
|
| 418 |
-
| 2.0 | 11000 | 0.1869 | 0.2983 | - | 0.
|
| 419 |
-
| 2.1818 | 12000 | 0.1726 | 0.3009 | - | 0.
|
| 420 |
-
| 2.3636 | 13000 | 0.1725 | 0.3058 | - | 0.
|
| 421 |
-
| 2.5455 | 14000 | 0.1743 | 0.2991 | - | 0.
|
| 422 |
-
| 2.7273 | 15000 | 0.1724 | 0.2875 | - | 0.
|
| 423 |
-
| 2.9091 | 16000 | 0.173 | 0.2872 | - | 0.
|
| 424 |
-
| 3.0909 | 17000 | 0.1652 | 0.2840 | - | 0.
|
| 425 |
-
| 3.2727 | 18000 | 0.1597 | 0.2825 | - | 0.
|
| 426 |
-
| 3.4545 | 19000 | 0.1613 | 0.2988 | - | 0.
|
| 427 |
-
| 3.6364 | 20000 | 0.1587 | 0.2868 | - | 0.
|
| 428 |
-
| 3.8182 | 21000 | 0.16 | 0.2863 | - | 0.
|
| 429 |
-
| 4.0 | 22000 | 0.1599 | 0.2853 | - | 0.
|
| 430 |
-
| 4.1818 | 23000 | 0.146 | 0.2876 | - | 0.
|
| 431 |
-
| 4.3636 | 24000 | 0.1481 | 0.2813 | - | 0.
|
| 432 |
-
| 4.5455 | 25000 | 0.1477 | 0.2831 | - | 0.
|
| 433 |
-
| 4.7273 | 26000 | 0.148 | 0.2769 | - | 0.
|
| 434 |
-
| 4.9091 | 27000 | 0.1485 | 0.2758 | - | 0.
|
| 435 |
| 5.0909 | 28000 | 0.142 | 0.2771 | - | 0.9409 |
|
| 436 |
-
| 5.2727 | 29000 | 0.1359 | 0.2878 | - | 0.
|
| 437 |
-
| 5.4545 | 30000 | 0.1368 | 0.2777 | - | 0.
|
| 438 |
-
| 5.6364 | 31000 | 0.1397 | 0.2797 | - | 0.
|
| 439 |
-
| 5.8182 | 32000 | 0.1395 | 0.2771 | - | 0.
|
| 440 |
-
| 6.0 | 33000 | 0.1393 | 0.2883 | - | 0.
|
| 441 |
-
| 6.1818 | 34000 | 0.1249 | 0.2822 | - | 0.
|
| 442 |
-
| 6.3636 | 35000 | 0.127 | 0.2739 | - | 0.
|
| 443 |
-
| 6.5455 | 36000 | 0.13 | 0.2797 | - | 0.
|
| 444 |
-
| 6.7273 | 37000 | 0.1304 | 0.2796 | - | 0.
|
| 445 |
-
| 6.9091 | 38000 | 0.1306 | 0.2750 | - | 0.
|
| 446 |
-
| 7.0909 | 39000 | 0.1236 | 0.2820 | - | 0.
|
| 447 |
-
| 7.2727 | 40000 | 0.1185 | 0.2898 | - | 0.
|
| 448 |
-
| 7.4545 | 41000 | 0.119 | 0.2863 | - | 0.
|
| 449 |
-
| 7.6364 | 42000 | 0.1206 | 0.2761 | - | 0.
|
| 450 |
-
| 7.8182 | 43000 | 0.1216 | 0.2702 | - | 0.
|
| 451 |
-
| 8.0 | 44000 | 0.1221 | 0.2771 | - | 0.
|
| 452 |
-
| 8.1818 | 45000 | 0.1083 | 0.2836 | - | 0.
|
| 453 |
-
| 8.3636 | 46000 | 0.1124 | 0.2889 | - | 0.
|
| 454 |
-
| 8.5455 | 47000 | 0.1106 | 0.2755 | - | 0.
|
| 455 |
-
| 8.7273 | 48000 | 0.1134 | 0.2853 | - | 0.
|
| 456 |
-
| 8.9091 | 49000 | 0.114 | 0.2845 | - | 0.
|
| 457 |
-
| 9.0909 | 50000 | 0.1095 | 0.2852 | - | 0.
|
| 458 |
-
| 9.2727 | 51000 | 0.1028 | 0.2880 | - | 0.
|
| 459 |
| 9.4545 | 52000 | 0.103 | 0.2796 | - | 0.9435 |
|
| 460 |
-
| 9.6364 | 53000 | 0.1048 | 0.2794 | - | 0.
|
| 461 |
-
| 9.8182 | 54000 | 0.105 | 0.2838 | - | 0.
|
| 462 |
-
| 10.0 | 55000 | 0.1086 | 0.2866 | - | 0.
|
| 463 |
-
| 10.1818 | 56000 | 0.0938 | 0.2809 | - | 0.
|
| 464 |
-
| 10.3636 | 57000 | 0.0969 | 0.3018 | - | 0.
|
| 465 |
-
| 10.5455 | 58000 | 0.0975 | 0.2823 | - | 0.
|
| 466 |
-
| 10.7273 | 59000 | 0.0971 | 0.2943 | - | 0.
|
| 467 |
-
| 10.9091 | 60000 | 0.1002 | 0.2915 | - | 0.
|
| 468 |
-
| 11.0909 | 61000 | 0.0939 | 0.2980 | - | 0.
|
| 469 |
-
| 11.2727 | 62000 | 0.0869 | 0.2932 | - | 0.
|
| 470 |
-
| 11.4545 | 63000 | 0.0888 | 0.2885 | - | 0.
|
| 471 |
-
| 11.6364 | 64000 | 0.0915 | 0.2844 | - | 0.
|
| 472 |
-
| 11.8182 | 65000 | 0.092 | 0.3085 | - | 0.
|
| 473 |
-
| 12.0 | 66000 | 0.0933 | 0.2833 | - | 0.
|
| 474 |
-
| 12.1818 | 67000 | 0.0796 | 0.3031 | - | 0.
|
| 475 |
-
| 12.3636 | 68000 | 0.082 | 0.2934 | - | 0.
|
| 476 |
-
| 12.5455 | 69000 | 0.0865 | 0.3030 | - | 0.
|
| 477 |
-
| 12.7273 | 70000 | 0.0858 | 0.3028 | - | 0.
|
| 478 |
-
| 12.9091 | 71000 | 0.0877 | 0.2930 | - | 0.
|
| 479 |
-
| 13.0909 | 72000 | 0.0791 | 0.3105 | - | 0.
|
| 480 |
-
| 13.2727 | 73000 | 0.0754 | 0.3189 | - | 0.
|
| 481 |
-
| 13.4545 | 74000 | 0.0777 | 0.2985 | - | 0.
|
| 482 |
-
| 13.6364 | 75000 | 0.0796 | 0.3170 | - | 0.
|
| 483 |
-
| 13.8182 | 76000 | 0.0799 | 0.2851 | - | 0.
|
| 484 |
-
| 14.0 | 77000 | 0.0816 | 0.3022 | - | 0.
|
| 485 |
-
| 14.1818 | 78000 | 0.0706 | 0.3169 | - | 0.
|
| 486 |
-
| 14.3636 | 79000 | 0.0727 | 0.3114 | - | 0.
|
| 487 |
-
| 14.5455 | 80000 | 0.073 | 0.3059 | - | 0.
|
| 488 |
-
| 14.7273 | 81000 | 0.0745 | 0.3108 | - | 0.
|
| 489 |
-
| 14.9091 | 82000 | 0.0741 | 0.3149 | - | 0.
|
| 490 |
-
| 15.0909 | 83000 | 0.0704 | 0.3213 | - | 0.
|
| 491 |
-
| 15.2727 | 84000 | 0.0649 | 0.3245 | - | 0.
|
| 492 |
-
| 15.4545 | 85000 | 0.0684 | 0.3180 | - | 0.
|
| 493 |
-
| 15.6364 | 86000 | 0.0694 | 0.3320 | - | 0.
|
| 494 |
-
| 15.8182 | 87000 | 0.0681 | 0.3138 | - | 0.
|
| 495 |
-
| 16.0 | 88000 | 0.0691 | 0.3158 | - | 0.
|
| 496 |
-
| 16.1818 | 89000 | 0.0608 | 0.3317 | - | 0.
|
| 497 |
-
| 16.3636 | 90000 | 0.0609 | 0.3253 | - | 0.
|
| 498 |
-
| 16.5455 | 91000 | 0.0621 | 0.3298 | - | 0.
|
| 499 |
-
| 16.7273 | 92000 | 0.0648 | 0.3246 | - | 0.
|
| 500 |
-
| 16.9091 | 93000 | 0.0657 | 0.3229 | - | 0.
|
| 501 |
-
| 17.0909 | 94000 | 0.0596 | 0.3327 | - | 0.
|
| 502 |
-
| 17.2727 | 95000 | 0.0579 | 0.3186 | - | 0.
|
| 503 |
-
| 17.4545 | 96000 | 0.0581 | 0.3272 | - | 0.
|
| 504 |
-
| 17.6364 | 97000 | 0.0592 | 0.3344 | - | 0.
|
| 505 |
-
| 17.8182 | 98000 | 0.06 | 0.3446 | - | 0.
|
| 506 |
-
| 18.0 | 99000 | 0.0598 | 0.3280 | - | 0.
|
| 507 |
-
| 18.1818 | 100000 | 0.0515 | 0.3577 | - | 0.
|
| 508 |
-
| 18.3636 | 101000 | 0.0539 | 0.3418 | - | 0.
|
| 509 |
-
| 18.5455 | 102000 | 0.0544 | 0.3365 | - | 0.
|
| 510 |
-
| 18.7273 | 103000 | 0.054 | 0.3294 | - | 0.
|
| 511 |
-
| 18.9091 | 104000 | 0.0568 | 0.3420 | - | 0.
|
| 512 |
-
| 19.0909 | 105000 | 0.0516 | 0.3650 | - | 0.
|
| 513 |
-
| 19.2727 | 106000 | 0.0482 | 0.3546 | - | 0.
|
| 514 |
-
| 19.4545 | 107000 | 0.0497 | 0.3338 | - | 0.
|
| 515 |
-
| 19.6364 | 108000 | 0.0495 | 0.3524 | - | 0.
|
| 516 |
-
| 19.8182 | 109000 | 0.051 | 0.3556 | - | 0.
|
| 517 |
-
| 20.0 | 110000 | 0.0512 | 0.3323 | - | 0.
|
| 518 |
-
| 20.1818 | 111000 | 0.0433 | 0.3572 | - | 0.
|
| 519 |
-
| 20.3636 | 112000 | 0.045 | 0.3678 | - | 0.
|
| 520 |
-
| 20.5455 | 113000 | 0.0466 | 0.3450 | - | 0.
|
| 521 |
-
| 20.7273 | 114000 | 0.047 | 0.3616 | - | 0.
|
| 522 |
-
| 20.9091 | 115000 | 0.048 | 0.3538 | - | 0.
|
| 523 |
-
| 21.0909 | 116000 | 0.044 | 0.3638 | - | 0.
|
| 524 |
-
| 21.2727 | 117000 | 0.0417 | 0.3767 | - | 0.
|
| 525 |
-
| 21.4545 | 118000 | 0.0428 | 0.3773 | - | 0.
|
| 526 |
-
| 21.6364 | 119000 | 0.0421 | 0.3613 | - | 0.
|
| 527 |
-
| 21.8182 | 120000 | 0.0442 | 0.3795 | - | 0.
|
| 528 |
-
| 22.0 | 121000 | 0.0453 | 0.3758 | - | 0.
|
| 529 |
-
| 22.1818 | 122000 | 0.0379 | 0.3819 | - | 0.
|
| 530 |
-
| 22.3636 | 123000 | 0.0397 | 0.3665 | - | 0.
|
| 531 |
-
| 22.5455 | 124000 | 0.039 | 0.3871 | - | 0.
|
| 532 |
-
| 22.7273 | 125000 | 0.0398 | 0.3752 | - | 0.
|
| 533 |
-
| 22.9091 | 126000 | 0.0408 | 0.3755 | - | 0.
|
| 534 |
-
| 23.0909 | 127000 | 0.0388 | 0.3698 | - | 0.
|
| 535 |
-
| 23.2727 | 128000 | 0.0348 | 0.3828 | - | 0.
|
| 536 |
-
| 23.4545 | 129000 | 0.0353 | 0.3814 | - | 0.
|
| 537 |
-
| 23.6364 | 130000 | 0.0375 | 0.3907 | - | 0.
|
| 538 |
-
| 23.8182 | 131000 | 0.0366 | 0.4085 | - | 0.
|
| 539 |
-
| 24.0 | 132000 | 0.0388 | 0.3734 | - | 0.
|
| 540 |
-
| 24.1818 | 133000 | 0.0321 | 0.4105 | - | 0.
|
| 541 |
-
| 24.3636 | 134000 | 0.0329 | 0.4038 | - | 0.
|
| 542 |
-
| 24.5455 | 135000 | 0.0335 | 0.4123 | - | 0.
|
| 543 |
-
| 24.7273 | 136000 | 0.0351 | 0.3945 | - | 0.
|
| 544 |
-
| 24.9091 | 137000 | 0.0347 | 0.3995 | - | 0.
|
| 545 |
-
| 25.0909 | 138000 | 0.0322 | 0.4154 | - | 0.
|
| 546 |
-
| 25.2727 | 139000 | 0.0312 | 0.3900 | - | 0.
|
| 547 |
-
| 25.4545 | 140000 | 0.0301 | 0.4083 | - | 0.
|
| 548 |
-
| 25.6364 | 141000 | 0.0318 | 0.4146 | - | 0.
|
| 549 |
-
| 25.8182 | 142000 | 0.0321 | 0.4198 | - | 0.
|
| 550 |
-
| 26.0 | 143000 | 0.032 | 0.4168 | - | 0.
|
| 551 |
-
| 26.1818 | 144000 | 0.0266 | 0.4293 | - | 0.
|
| 552 |
-
| 26.3636 | 145000 | 0.0277 | 0.4234 | - | 0.
|
| 553 |
-
| 26.5455 | 146000 | 0.0288 | 0.4309 | - | 0.
|
| 554 |
-
| 26.7273 | 147000 | 0.0292 | 0.4215 | - | 0.
|
| 555 |
-
| 26.9091 | 148000 | 0.0294 | 0.4020 | - | 0.
|
| 556 |
-
| 27.0909 | 149000 | 0.0272 | 0.4342 | - | 0.
|
| 557 |
-
| 27.2727 | 150000 | 0.025 | 0.4434 | - | 0.
|
| 558 |
-
| 27.4545 | 151000 | 0.027 | 0.4178 | - | 0.
|
| 559 |
-
| 27.6364 | 152000 | 0.0257 | 0.4396 | - | 0.
|
| 560 |
-
| 27.8182 | 153000 | 0.028 | 0.4099 | - | 0.
|
| 561 |
-
| 28.0 | 154000 | 0.0275 | 0.4185 | - | 0.
|
| 562 |
-
| 28.1818 | 155000 | 0.0236 | 0.4375 | - | 0.
|
| 563 |
-
| 28.3636 | 156000 | 0.0237 | 0.4232 | - | 0.
|
| 564 |
-
| 28.5455 | 157000 | 0.0237 | 0.4642 | - | 0.
|
| 565 |
-
| 28.7273 | 158000 | 0.0249 | 0.4374 | - | 0.
|
| 566 |
-
| 28.9091 | 159000 | 0.0258 | 0.4329 | - | 0.
|
| 567 |
-
| 29.0909 | 160000 | 0.0219 | 0.4867 | - | 0.
|
| 568 |
-
| 29.2727 | 161000 | 0.0216 | 0.4737 | - | 0.
|
| 569 |
-
| 29.4545 | 162000 | 0.0218 | 0.4577 | - | 0.
|
| 570 |
-
| 29.6364 | 163000 | 0.0223 | 0.4589 | - | 0.
|
| 571 |
-
| 29.8182 | 164000 | 0.0223 | 0.4410 | - | 0.
|
| 572 |
-
| 30.0 | 165000 | 0.0236 | 0.4477 | - | 0.
|
| 573 |
-
| 30.1818 | 166000 | 0.0203 | 0.4798 | - | 0.
|
| 574 |
-
| 30.3636 | 167000 | 0.02 | 0.4600 | - | 0.
|
| 575 |
-
| 30.5455 | 168000 | 0.0206 | 0.4492 | - | 0.
|
| 576 |
-
| 30.7273 | 169000 | 0.0203 | 0.4839 | - | 0.
|
| 577 |
-
| 30.9091 | 170000 | 0.0212 | 0.4731 | - | 0.
|
| 578 |
-
| 31.0909 | 171000 | 0.0196 | 0.4621 | - | 0.
|
| 579 |
-
| 31.2727 | 172000 | 0.0178 | 0.4986 | - | 0.
|
| 580 |
-
| 31.4545 | 173000 | 0.0177 | 0.4871 | - | 0.
|
| 581 |
-
| 31.6364 | 174000 | 0.0201 | 0.4520 | - | 0.
|
| 582 |
-
| 31.8182 | 175000 | 0.0191 | 0.4571 | - | 0.
|
| 583 |
-
| 32.0 | 176000 | 0.0201 | 0.4871 | - | 0.
|
| 584 |
-
| 32.1818 | 177000 | 0.0156 | 0.5061 | - | 0.
|
| 585 |
-
| 32.3636 | 178000 | 0.0174 | 0.4704 | - | 0.
|
| 586 |
-
| 32.5455 | 179000 | 0.0175 | 0.4900 | - | 0.
|
| 587 |
-
| 32.7273 | 180000 | 0.0175 | 0.4861 | - | 0.
|
| 588 |
-
| 32.9091 | 181000 | 0.0178 | 0.5005 | - | 0.
|
| 589 |
-
| 33.0909 | 182000 | 0.0163 | 0.4934 | - | 0.
|
| 590 |
-
| 33.2727 | 183000 | 0.0149 | 0.5065 | - | 0.
|
| 591 |
-
| 33.4545 | 184000 | 0.0157 | 0.4973 | - | 0.
|
| 592 |
-
| 33.6364 | 185000 | 0.0164 | 0.4993 | - | 0.
|
| 593 |
-
| 33.8182 | 186000 | 0.0164 | 0.4904 | - | 0.
|
| 594 |
-
| 34.0 | 187000 | 0.0167 | 0.5096 | - | 0.
|
| 595 |
-
| 34.1818 | 188000 | 0.0136 | 0.4960 | - | 0.
|
| 596 |
-
| 34.3636 | 189000 | 0.0142 | 0.5188 | - | 0.
|
| 597 |
-
| 34.5455 | 190000 | 0.0144 | 0.5139 | - | 0.
|
| 598 |
-
| 34.7273 | 191000 | 0.0149 | 0.4919 | - | 0.
|
| 599 |
-
| 34.9091 | 192000 | 0.0149 | 0.4775 | - | 0.
|
| 600 |
-
| 35.0909 | 193000 | 0.0127 | 0.5546 | - | 0.
|
| 601 |
-
| 35.2727 | 194000 | 0.0124 | 0.5440 | - | 0.
|
| 602 |
-
| 35.4545 | 195000 | 0.0126 | 0.5571 | - | 0.
|
| 603 |
-
| 35.6364 | 196000 | 0.0131 | 0.5127 | - | 0.
|
| 604 |
-
| 35.8182 | 197000 | 0.0134 | 0.5167 | - | 0.
|
| 605 |
-
| 36.0 | 198000 | 0.0134 | 0.4939 | - | 0.
|
| 606 |
-
| 36.1818 | 199000 | 0.011 | 0.5279 | - | 0.
|
| 607 |
-
| 36.3636 | 200000 | 0.0115 | 0.5336 | - | 0.
|
| 608 |
-
| 36.5455 | 201000 | 0.0113 | 0.5626 | - | 0.
|
| 609 |
-
| 36.7273 | 202000 | 0.012 | 0.5316 | - | 0.
|
| 610 |
-
| 36.9091 | 203000 | 0.0121 | 0.5222 | - | 0.
|
| 611 |
-
| 37.0909 | 204000 | 0.0107 | 0.5618 | - | 0.
|
| 612 |
-
| 37.2727 | 205000 | 0.0107 | 0.5508 | - | 0.
|
| 613 |
-
| 37.4545 | 206000 | 0.0106 | 0.5414 | - | 0.
|
| 614 |
-
| 37.6364 | 207000 | 0.0106 | 0.5522 | - | 0.
|
| 615 |
-
| 37.8182 | 208000 | 0.0111 | 0.5524 | - | 0.
|
| 616 |
-
| 38.0 | 209000 | 0.012 | 0.5176 | - | 0.
|
| 617 |
-
| 38.1818 | 210000 | 0.0087 | 0.5742 | - | 0.
|
| 618 |
-
| 38.3636 | 211000 | 0.0092 | 0.5686 | - | 0.
|
| 619 |
-
| 38.5455 | 212000 | 0.0099 | 0.5699 | - | 0.
|
| 620 |
-
| 38.7273 | 213000 | 0.0094 | 0.5733 | - | 0.
|
| 621 |
-
| 38.9091
|
| 622 |
-
| 39.0909 | 215000 | 0.009 | 0.5923 | - | 0.
|
| 623 |
-
| 39.2727 | 216000 | 0.0078 | 0.5925 | - | 0.
|
| 624 |
-
| 39.4545 | 217000 | 0.0086 | 0.5703 | - | 0.
|
| 625 |
-
| 39.6364 | 218000 | 0.0087 | 0.5921 | - | 0.
|
| 626 |
-
| 39.8182 | 219000 | 0.0085 | 0.5859 | - | 0.
|
| 627 |
-
| 40.0 | 220000 | 0.0091 | 0.5577 | - | 0.
|
| 628 |
-
| 40.1818 | 221000 | 0.0077 | 0.5844 | - | 0.
|
| 629 |
-
| 40.3636 | 222000 | 0.0077 | 0.5691 | - | 0.
|
| 630 |
-
| 40.5455 | 223000 | 0.008 | 0.5794 | - | 0.
|
| 631 |
-
| 40.7273 | 224000 | 0.0073 | 0.6036 | - | 0.
|
| 632 |
-
| 40.9091 | 225000 | 0.0083 | 0.5754 | - | 0.
|
| 633 |
-
| 41.0909 | 226000 | 0.0078 | 0.6141 | - | 0.
|
| 634 |
-
| 41.2727 | 227000 | 0.0069 | 0.6332 | - | 0.
|
| 635 |
-
| 41.4545 | 228000 | 0.007 | 0.6220 | - | 0.
|
| 636 |
-
| 41.6364 | 229000 | 0.0075 | 0.6110 | - | 0.
|
| 637 |
-
| 41.8182 | 230000 | 0.007 | 0.6248 | - | 0.
|
| 638 |
-
| 42.0 | 231000 | 0.0072 | 0.5950 | - | 0.
|
| 639 |
-
| 42.1818 | 232000 | 0.0059 | 0.6428 | - | 0.
|
| 640 |
-
| 42.3636 | 233000 | 0.0065 | 0.6298 | - | 0.
|
| 641 |
-
| 42.5455 | 234000 | 0.0065 | 0.6166 | - | 0.
|
| 642 |
-
| 42.7273 | 235000 | 0.0066 | 0.5990 | - | 0.
|
| 643 |
-
| 42.9091 | 236000 | 0.0065 | 0.6297 | - | 0.
|
| 644 |
-
| 43.0909 | 237000 | 0.0057 | 0.6483 | - | 0.
|
| 645 |
-
| 43.2727 | 238000 | 0.0058 | 0.6077 | - | 0.
|
| 646 |
-
| 43.4545 | 239000 | 0.0056 | 0.6420 | - | 0.
|
| 647 |
-
| 43.6364 | 240000 | 0.0059 | 0.6574 | - | 0.
|
| 648 |
-
| 43.8182 | 241000 | 0.0051 | 0.6819 | - | 0.
|
| 649 |
-
| 44.0 | 242000 | 0.0055 | 0.6567 | - | 0.
|
| 650 |
-
| 44.1818 | 243000 | 0.0051 | 0.6697 | - | 0.
|
| 651 |
-
| 44.3636 | 244000 | 0.005 | 0.6459 | - | 0.
|
| 652 |
-
| 44.5455 | 245000 | 0.0047 | 0.6693 | - | 0.
|
| 653 |
-
| 44.7273 | 246000 | 0.0054 | 0.6589 | - | 0.
|
| 654 |
-
| 44.9091 | 247000 | 0.0051 | 0.6886 | - | 0.
|
| 655 |
-
| 45.0909 | 248000 | 0.0047 | 0.6886 | - | 0.
|
| 656 |
-
| 45.2727 | 249000 | 0.0045 | 0.6959 | - | 0.
|
| 657 |
-
| 45.4545 | 250000 | 0.0045 | 0.6827 | - | 0.
|
| 658 |
-
| 45.6364 | 251000 | 0.0042 | 0.6706 | - | 0.
|
| 659 |
-
| 45.8182 | 252000 | 0.0043 | 0.6858 | - | 0.
|
| 660 |
-
| 46.0 | 253000 | 0.0045 | 0.6926 | - | 0.
|
| 661 |
-
| 46.1818 | 254000 | 0.0041 | 0.7091 | - | 0.
|
| 662 |
-
| 46.3636 | 255000 | 0.0038 | 0.7110 | - | 0.
|
| 663 |
-
| 46.5455 | 256000 | 0.0039 | 0.6991 | - | 0.
|
| 664 |
-
| 46.7273 | 257000 | 0.0038 | 0.7068 | - | 0.
|
| 665 |
-
| 46.9091 | 258000 | 0.0043 | 0.7026 | - | 0.
|
| 666 |
-
| 47.0909 | 259000 | 0.0041 | 0.7031 | - | 0.
|
| 667 |
-
| 47.2727 | 260000 | 0.0037 | 0.6905 | - | 0.
|
| 668 |
-
| 47.4545 | 261000 | 0.0035 | 0.7044 | - | 0.
|
| 669 |
-
| 47.6364 | 262000 | 0.0038 | 0.7005 | - | 0.
|
| 670 |
-
| 47.8182 | 263000 | 0.0039 | 0.7064 | - | 0.
|
| 671 |
-
| 48.0 | 264000 | 0.0034 | 0.7112 | - | 0.
|
| 672 |
-
| 48.1818 | 265000 | 0.0034 | 0.7092 | - | 0.
|
| 673 |
-
| 48.3636 | 266000 | 0.0029 | 0.7286 | - | 0.
|
| 674 |
-
|
|
| 675 |
-
| 48.7273 | 268000 | 0.0035 | 0.7101 | - | 0.
|
| 676 |
-
| 48.9091 | 269000 | 0.0035 | 0.7127 | - | 0.
|
| 677 |
-
| 49.0909 | 270000 | 0.0031 | 0.7228 | - | 0.
|
| 678 |
-
| 49.2727 | 271000 | 0.0029 | 0.7289 | - | 0.
|
| 679 |
-
| 49.4545 | 272000 | 0.003 | 0.7309 | - | 0.
|
| 680 |
-
| 49.6364 | 273000 | 0.003 | 0.7308 | - | 0.
|
| 681 |
-
| 49.8182 | 274000 | 0.0033 | 0.7293 | - | 0.
|
| 682 |
-
| 50.0 | 275000 | 0.003 | 0.7302 | - | 0.
|
| 683 |
|
| 684 |
* The bold row denotes the saved checkpoint.
|
| 685 |
</details>
|
|
|
|
| 66 |
type: test
|
| 67 |
metrics:
|
| 68 |
- type: accuracy
|
| 69 |
+
value: 0.8928104996694668
|
| 70 |
name: Accuracy
|
| 71 |
- type: accuracy_threshold
|
| 72 |
+
value: 0.8323618173599243
|
| 73 |
name: Accuracy Threshold
|
| 74 |
- type: f1
|
| 75 |
+
value: 0.8770841270705202
|
| 76 |
name: F1
|
| 77 |
- type: f1_threshold
|
| 78 |
+
value: 0.10187823325395584
|
| 79 |
name: F1 Threshold
|
| 80 |
- type: precision
|
| 81 |
+
value: 0.8550709257490537
|
| 82 |
name: Precision
|
| 83 |
- type: recall
|
| 84 |
+
value: 0.9002607076350093
|
| 85 |
name: Recall
|
| 86 |
- type: average_precision
|
| 87 |
+
value: 0.9337832234143917
|
| 88 |
name: Average Precision
|
| 89 |
---
|
| 90 |
|
|
|
|
| 188 |
|
| 189 |
| Metric | val | test |
|
| 190 |
|:----------------------|:-----------|:-----------|
|
| 191 |
+
| accuracy | 0.7718 | 0.8928 |
|
| 192 |
+
| accuracy_threshold | 0.8927 | 0.8324 |
|
| 193 |
+
| f1 | 0.6934 | 0.8771 |
|
| 194 |
+
| f1_threshold | 0.8759 | 0.1019 |
|
| 195 |
+
| precision | 0.6788 | 0.8551 |
|
| 196 |
+
| recall | 0.7086 | 0.9003 |
|
| 197 |
+
| **average_precision** | **0.7676** | **0.9338** |
|
| 198 |
|
| 199 |
<!--
|
| 200 |
## Bias, Risks and Limitations
|
|
|
|
| 324 |
- `bf16_full_eval`: False
|
| 325 |
- `fp16_full_eval`: False
|
| 326 |
- `tf32`: None
|
| 327 |
+
- `local_rank`: 3
|
| 328 |
- `ddp_backend`: None
|
| 329 |
- `tpu_num_cores`: None
|
| 330 |
- `tpu_metrics_debug`: False
|
|
|
|
| 405 |
| Epoch | Step | Training Loss | Validation Loss | val_average_precision | test_average_precision |
|
| 406 |
|:-----------:|:----------:|:-------------:|:---------------:|:---------------------:|:----------------------:|
|
| 407 |
| -1 | -1 | - | - | 0.7676 | 0.6907 |
|
| 408 |
+
| 0.1818 | 1000 | 0.3058 | 0.3991 | - | 0.8704 |
|
| 409 |
+
| 0.3636 | 2000 | 0.2417 | 0.3729 | - | 0.9010 |
|
| 410 |
+
| 0.5455 | 3000 | 0.2287 | 0.3356 | - | 0.9009 |
|
| 411 |
+
| 0.7273 | 4000 | 0.2183 | 0.3729 | - | 0.8841 |
|
| 412 |
+
| 0.9091 | 5000 | 0.212 | 0.3404 | - | 0.9142 |
|
| 413 |
+
| 1.0909 | 6000 | 0.1999 | 0.3171 | - | 0.9115 |
|
| 414 |
+
| 1.2727 | 7000 | 0.1944 | 0.3131 | - | 0.9162 |
|
| 415 |
+
| 1.4545 | 8000 | 0.1933 | 0.3116 | - | 0.9234 |
|
| 416 |
+
| 1.6364 | 9000 | 0.193 | 0.3211 | - | 0.9276 |
|
| 417 |
+
| 1.8182 | 10000 | 0.1879 | 0.2984 | - | 0.9292 |
|
| 418 |
+
| 2.0 | 11000 | 0.1869 | 0.2983 | - | 0.9267 |
|
| 419 |
+
| 2.1818 | 12000 | 0.1726 | 0.3009 | - | 0.9300 |
|
| 420 |
+
| 2.3636 | 13000 | 0.1725 | 0.3058 | - | 0.9294 |
|
| 421 |
+
| 2.5455 | 14000 | 0.1743 | 0.2991 | - | 0.9334 |
|
| 422 |
+
| 2.7273 | 15000 | 0.1724 | 0.2875 | - | 0.9339 |
|
| 423 |
+
| 2.9091 | 16000 | 0.173 | 0.2872 | - | 0.9326 |
|
| 424 |
+
| 3.0909 | 17000 | 0.1652 | 0.2840 | - | 0.9352 |
|
| 425 |
+
| 3.2727 | 18000 | 0.1597 | 0.2825 | - | 0.9348 |
|
| 426 |
+
| 3.4545 | 19000 | 0.1613 | 0.2988 | - | 0.9356 |
|
| 427 |
+
| 3.6364 | 20000 | 0.1587 | 0.2868 | - | 0.9349 |
|
| 428 |
+
| 3.8182 | 21000 | 0.16 | 0.2863 | - | 0.9387 |
|
| 429 |
+
| 4.0 | 22000 | 0.1599 | 0.2853 | - | 0.9322 |
|
| 430 |
+
| 4.1818 | 23000 | 0.146 | 0.2876 | - | 0.9369 |
|
| 431 |
+
| 4.3636 | 24000 | 0.1481 | 0.2813 | - | 0.9371 |
|
| 432 |
+
| 4.5455 | 25000 | 0.1477 | 0.2831 | - | 0.9388 |
|
| 433 |
+
| 4.7273 | 26000 | 0.148 | 0.2769 | - | 0.9361 |
|
| 434 |
+
| 4.9091 | 27000 | 0.1485 | 0.2758 | - | 0.9378 |
|
| 435 |
| 5.0909 | 28000 | 0.142 | 0.2771 | - | 0.9409 |
|
| 436 |
+
| 5.2727 | 29000 | 0.1359 | 0.2878 | - | 0.9332 |
|
| 437 |
+
| 5.4545 | 30000 | 0.1368 | 0.2777 | - | 0.9389 |
|
| 438 |
+
| 5.6364 | 31000 | 0.1397 | 0.2797 | - | 0.9315 |
|
| 439 |
+
| 5.8182 | 32000 | 0.1395 | 0.2771 | - | 0.9397 |
|
| 440 |
+
| 6.0 | 33000 | 0.1393 | 0.2883 | - | 0.9442 |
|
| 441 |
+
| 6.1818 | 34000 | 0.1249 | 0.2822 | - | 0.9398 |
|
| 442 |
+
| 6.3636 | 35000 | 0.127 | 0.2739 | - | 0.9446 |
|
| 443 |
+
| 6.5455 | 36000 | 0.13 | 0.2797 | - | 0.9439 |
|
| 444 |
+
| 6.7273 | 37000 | 0.1304 | 0.2796 | - | 0.9423 |
|
| 445 |
+
| 6.9091 | 38000 | 0.1306 | 0.2750 | - | 0.9412 |
|
| 446 |
+
| 7.0909 | 39000 | 0.1236 | 0.2820 | - | 0.9413 |
|
| 447 |
+
| 7.2727 | 40000 | 0.1185 | 0.2898 | - | 0.9387 |
|
| 448 |
+
| 7.4545 | 41000 | 0.119 | 0.2863 | - | 0.9412 |
|
| 449 |
+
| 7.6364 | 42000 | 0.1206 | 0.2761 | - | 0.9431 |
|
| 450 |
+
| 7.8182 | 43000 | 0.1216 | 0.2702 | - | 0.9450 |
|
| 451 |
+
| 8.0 | 44000 | 0.1221 | 0.2771 | - | 0.9431 |
|
| 452 |
+
| 8.1818 | 45000 | 0.1083 | 0.2836 | - | 0.9433 |
|
| 453 |
+
| 8.3636 | 46000 | 0.1124 | 0.2889 | - | 0.9437 |
|
| 454 |
+
| 8.5455 | 47000 | 0.1106 | 0.2755 | - | 0.9443 |
|
| 455 |
+
| 8.7273 | 48000 | 0.1134 | 0.2853 | - | 0.9450 |
|
| 456 |
+
| 8.9091 | 49000 | 0.114 | 0.2845 | - | 0.9442 |
|
| 457 |
+
| 9.0909 | 50000 | 0.1095 | 0.2852 | - | 0.9426 |
|
| 458 |
+
| 9.2727 | 51000 | 0.1028 | 0.2880 | - | 0.9428 |
|
| 459 |
| 9.4545 | 52000 | 0.103 | 0.2796 | - | 0.9435 |
|
| 460 |
+
| 9.6364 | 53000 | 0.1048 | 0.2794 | - | 0.9427 |
|
| 461 |
+
| 9.8182 | 54000 | 0.105 | 0.2838 | - | 0.9424 |
|
| 462 |
+
| 10.0 | 55000 | 0.1086 | 0.2866 | - | 0.9439 |
|
| 463 |
+
| 10.1818 | 56000 | 0.0938 | 0.2809 | - | 0.9430 |
|
| 464 |
+
| 10.3636 | 57000 | 0.0969 | 0.3018 | - | 0.9409 |
|
| 465 |
+
| 10.5455 | 58000 | 0.0975 | 0.2823 | - | 0.9410 |
|
| 466 |
+
| 10.7273 | 59000 | 0.0971 | 0.2943 | - | 0.9448 |
|
| 467 |
+
| 10.9091 | 60000 | 0.1002 | 0.2915 | - | 0.9432 |
|
| 468 |
+
| 11.0909 | 61000 | 0.0939 | 0.2980 | - | 0.9411 |
|
| 469 |
+
| 11.2727 | 62000 | 0.0869 | 0.2932 | - | 0.9417 |
|
| 470 |
+
| 11.4545 | 63000 | 0.0888 | 0.2885 | - | 0.9411 |
|
| 471 |
+
| 11.6364 | 64000 | 0.0915 | 0.2844 | - | 0.9408 |
|
| 472 |
+
| 11.8182 | 65000 | 0.092 | 0.3085 | - | 0.9415 |
|
| 473 |
+
| 12.0 | 66000 | 0.0933 | 0.2833 | - | 0.9417 |
|
| 474 |
+
| 12.1818 | 67000 | 0.0796 | 0.3031 | - | 0.9411 |
|
| 475 |
+
| 12.3636 | 68000 | 0.082 | 0.2934 | - | 0.9434 |
|
| 476 |
+
| 12.5455 | 69000 | 0.0865 | 0.3030 | - | 0.9446 |
|
| 477 |
+
| 12.7273 | 70000 | 0.0858 | 0.3028 | - | 0.9448 |
|
| 478 |
+
| 12.9091 | 71000 | 0.0877 | 0.2930 | - | 0.9419 |
|
| 479 |
+
| 13.0909 | 72000 | 0.0791 | 0.3105 | - | 0.9389 |
|
| 480 |
+
| 13.2727 | 73000 | 0.0754 | 0.3189 | - | 0.9445 |
|
| 481 |
+
| 13.4545 | 74000 | 0.0777 | 0.2985 | - | 0.9429 |
|
| 482 |
+
| 13.6364 | 75000 | 0.0796 | 0.3170 | - | 0.9445 |
|
| 483 |
+
| 13.8182 | 76000 | 0.0799 | 0.2851 | - | 0.9460 |
|
| 484 |
+
| 14.0 | 77000 | 0.0816 | 0.3022 | - | 0.9436 |
|
| 485 |
+
| 14.1818 | 78000 | 0.0706 | 0.3169 | - | 0.9429 |
|
| 486 |
+
| 14.3636 | 79000 | 0.0727 | 0.3114 | - | 0.9444 |
|
| 487 |
+
| 14.5455 | 80000 | 0.073 | 0.3059 | - | 0.9460 |
|
| 488 |
+
| 14.7273 | 81000 | 0.0745 | 0.3108 | - | 0.9458 |
|
| 489 |
+
| 14.9091 | 82000 | 0.0741 | 0.3149 | - | 0.9416 |
|
| 490 |
+
| 15.0909 | 83000 | 0.0704 | 0.3213 | - | 0.9426 |
|
| 491 |
+
| 15.2727 | 84000 | 0.0649 | 0.3245 | - | 0.9446 |
|
| 492 |
+
| 15.4545 | 85000 | 0.0684 | 0.3180 | - | 0.9437 |
|
| 493 |
+
| 15.6364 | 86000 | 0.0694 | 0.3320 | - | 0.9449 |
|
| 494 |
+
| 15.8182 | 87000 | 0.0681 | 0.3138 | - | 0.9422 |
|
| 495 |
+
| 16.0 | 88000 | 0.0691 | 0.3158 | - | 0.9393 |
|
| 496 |
+
| 16.1818 | 89000 | 0.0608 | 0.3317 | - | 0.9447 |
|
| 497 |
+
| 16.3636 | 90000 | 0.0609 | 0.3253 | - | 0.9455 |
|
| 498 |
+
| 16.5455 | 91000 | 0.0621 | 0.3298 | - | 0.9408 |
|
| 499 |
+
| 16.7273 | 92000 | 0.0648 | 0.3246 | - | 0.9462 |
|
| 500 |
+
| 16.9091 | 93000 | 0.0657 | 0.3229 | - | 0.9440 |
|
| 501 |
+
| 17.0909 | 94000 | 0.0596 | 0.3327 | - | 0.9431 |
|
| 502 |
+
| 17.2727 | 95000 | 0.0579 | 0.3186 | - | 0.9418 |
|
| 503 |
+
| 17.4545 | 96000 | 0.0581 | 0.3272 | - | 0.9415 |
|
| 504 |
+
| 17.6364 | 97000 | 0.0592 | 0.3344 | - | 0.9456 |
|
| 505 |
+
| 17.8182 | 98000 | 0.06 | 0.3446 | - | 0.9438 |
|
| 506 |
+
| 18.0 | 99000 | 0.0598 | 0.3280 | - | 0.9469 |
|
| 507 |
+
| 18.1818 | 100000 | 0.0515 | 0.3577 | - | 0.9399 |
|
| 508 |
+
| 18.3636 | 101000 | 0.0539 | 0.3418 | - | 0.9413 |
|
| 509 |
+
| 18.5455 | 102000 | 0.0544 | 0.3365 | - | 0.9415 |
|
| 510 |
+
| 18.7273 | 103000 | 0.054 | 0.3294 | - | 0.9422 |
|
| 511 |
+
| 18.9091 | 104000 | 0.0568 | 0.3420 | - | 0.9452 |
|
| 512 |
+
| 19.0909 | 105000 | 0.0516 | 0.3650 | - | 0.9448 |
|
| 513 |
+
| 19.2727 | 106000 | 0.0482 | 0.3546 | - | 0.9442 |
|
| 514 |
+
| 19.4545 | 107000 | 0.0497 | 0.3338 | - | 0.9427 |
|
| 515 |
+
| 19.6364 | 108000 | 0.0495 | 0.3524 | - | 0.9414 |
|
| 516 |
+
| 19.8182 | 109000 | 0.051 | 0.3556 | - | 0.9397 |
|
| 517 |
+
| 20.0 | 110000 | 0.0512 | 0.3323 | - | 0.9436 |
|
| 518 |
+
| 20.1818 | 111000 | 0.0433 | 0.3572 | - | 0.9387 |
|
| 519 |
+
| 20.3636 | 112000 | 0.045 | 0.3678 | - | 0.9426 |
|
| 520 |
+
| 20.5455 | 113000 | 0.0466 | 0.3450 | - | 0.9425 |
|
| 521 |
+
| 20.7273 | 114000 | 0.047 | 0.3616 | - | 0.9441 |
|
| 522 |
+
| 20.9091 | 115000 | 0.048 | 0.3538 | - | 0.9424 |
|
| 523 |
+
| 21.0909 | 116000 | 0.044 | 0.3638 | - | 0.9376 |
|
| 524 |
+
| 21.2727 | 117000 | 0.0417 | 0.3767 | - | 0.9366 |
|
| 525 |
+
| 21.4545 | 118000 | 0.0428 | 0.3773 | - | 0.9383 |
|
| 526 |
+
| 21.6364 | 119000 | 0.0421 | 0.3613 | - | 0.9435 |
|
| 527 |
+
| 21.8182 | 120000 | 0.0442 | 0.3795 | - | 0.9348 |
|
| 528 |
+
| 22.0 | 121000 | 0.0453 | 0.3758 | - | 0.9394 |
|
| 529 |
+
| 22.1818 | 122000 | 0.0379 | 0.3819 | - | 0.9445 |
|
| 530 |
+
| 22.3636 | 123000 | 0.0397 | 0.3665 | - | 0.9420 |
|
| 531 |
+
| 22.5455 | 124000 | 0.039 | 0.3871 | - | 0.9426 |
|
| 532 |
+
| 22.7273 | 125000 | 0.0398 | 0.3752 | - | 0.9421 |
|
| 533 |
+
| 22.9091 | 126000 | 0.0408 | 0.3755 | - | 0.9402 |
|
| 534 |
+
| 23.0909 | 127000 | 0.0388 | 0.3698 | - | 0.9420 |
|
| 535 |
+
| 23.2727 | 128000 | 0.0348 | 0.3828 | - | 0.9442 |
|
| 536 |
+
| 23.4545 | 129000 | 0.0353 | 0.3814 | - | 0.9438 |
|
| 537 |
+
| 23.6364 | 130000 | 0.0375 | 0.3907 | - | 0.9432 |
|
| 538 |
+
| 23.8182 | 131000 | 0.0366 | 0.4085 | - | 0.9402 |
|
| 539 |
+
| 24.0 | 132000 | 0.0388 | 0.3734 | - | 0.9434 |
|
| 540 |
+
| 24.1818 | 133000 | 0.0321 | 0.4105 | - | 0.9433 |
|
| 541 |
+
| 24.3636 | 134000 | 0.0329 | 0.4038 | - | 0.9420 |
|
| 542 |
+
| 24.5455 | 135000 | 0.0335 | 0.4123 | - | 0.9436 |
|
| 543 |
+
| 24.7273 | 136000 | 0.0351 | 0.3945 | - | 0.9460 |
|
| 544 |
+
| 24.9091 | 137000 | 0.0347 | 0.3995 | - | 0.9420 |
|
| 545 |
+
| 25.0909 | 138000 | 0.0322 | 0.4154 | - | 0.9431 |
|
| 546 |
+
| 25.2727 | 139000 | 0.0312 | 0.3900 | - | 0.9411 |
|
| 547 |
+
| 25.4545 | 140000 | 0.0301 | 0.4083 | - | 0.9421 |
|
| 548 |
+
| 25.6364 | 141000 | 0.0318 | 0.4146 | - | 0.9373 |
|
| 549 |
+
| 25.8182 | 142000 | 0.0321 | 0.4198 | - | 0.9414 |
|
| 550 |
+
| 26.0 | 143000 | 0.032 | 0.4168 | - | 0.9397 |
|
| 551 |
+
| 26.1818 | 144000 | 0.0266 | 0.4293 | - | 0.9417 |
|
| 552 |
+
| 26.3636 | 145000 | 0.0277 | 0.4234 | - | 0.9417 |
|
| 553 |
+
| 26.5455 | 146000 | 0.0288 | 0.4309 | - | 0.9405 |
|
| 554 |
+
| 26.7273 | 147000 | 0.0292 | 0.4215 | - | 0.9419 |
|
| 555 |
+
| 26.9091 | 148000 | 0.0294 | 0.4020 | - | 0.9398 |
|
| 556 |
+
| 27.0909 | 149000 | 0.0272 | 0.4342 | - | 0.9404 |
|
| 557 |
+
| 27.2727 | 150000 | 0.025 | 0.4434 | - | 0.9410 |
|
| 558 |
+
| 27.4545 | 151000 | 0.027 | 0.4178 | - | 0.9396 |
|
| 559 |
+
| 27.6364 | 152000 | 0.0257 | 0.4396 | - | 0.9352 |
|
| 560 |
+
| 27.8182 | 153000 | 0.028 | 0.4099 | - | 0.9395 |
|
| 561 |
+
| 28.0 | 154000 | 0.0275 | 0.4185 | - | 0.9385 |
|
| 562 |
+
| 28.1818 | 155000 | 0.0236 | 0.4375 | - | 0.9416 |
|
| 563 |
+
| 28.3636 | 156000 | 0.0237 | 0.4232 | - | 0.9400 |
|
| 564 |
+
| 28.5455 | 157000 | 0.0237 | 0.4642 | - | 0.9311 |
|
| 565 |
+
| 28.7273 | 158000 | 0.0249 | 0.4374 | - | 0.9422 |
|
| 566 |
+
| 28.9091 | 159000 | 0.0258 | 0.4329 | - | 0.9414 |
|
| 567 |
+
| 29.0909 | 160000 | 0.0219 | 0.4867 | - | 0.9415 |
|
| 568 |
+
| 29.2727 | 161000 | 0.0216 | 0.4737 | - | 0.9360 |
|
| 569 |
+
| 29.4545 | 162000 | 0.0218 | 0.4577 | - | 0.9393 |
|
| 570 |
+
| 29.6364 | 163000 | 0.0223 | 0.4589 | - | 0.9418 |
|
| 571 |
+
| 29.8182 | 164000 | 0.0223 | 0.4410 | - | 0.9416 |
|
| 572 |
+
| 30.0 | 165000 | 0.0236 | 0.4477 | - | 0.9426 |
|
| 573 |
+
| 30.1818 | 166000 | 0.0203 | 0.4798 | - | 0.9418 |
|
| 574 |
+
| 30.3636 | 167000 | 0.02 | 0.4600 | - | 0.9402 |
|
| 575 |
+
| 30.5455 | 168000 | 0.0206 | 0.4492 | - | 0.9434 |
|
| 576 |
+
| 30.7273 | 169000 | 0.0203 | 0.4839 | - | 0.9405 |
|
| 577 |
+
| 30.9091 | 170000 | 0.0212 | 0.4731 | - | 0.9394 |
|
| 578 |
+
| 31.0909 | 171000 | 0.0196 | 0.4621 | - | 0.9422 |
|
| 579 |
+
| 31.2727 | 172000 | 0.0178 | 0.4986 | - | 0.9411 |
|
| 580 |
+
| 31.4545 | 173000 | 0.0177 | 0.4871 | - | 0.9412 |
|
| 581 |
+
| 31.6364 | 174000 | 0.0201 | 0.4520 | - | 0.9429 |
|
| 582 |
+
| 31.8182 | 175000 | 0.0191 | 0.4571 | - | 0.9416 |
|
| 583 |
+
| 32.0 | 176000 | 0.0201 | 0.4871 | - | 0.9409 |
|
| 584 |
+
| 32.1818 | 177000 | 0.0156 | 0.5061 | - | 0.9422 |
|
| 585 |
+
| 32.3636 | 178000 | 0.0174 | 0.4704 | - | 0.9405 |
|
| 586 |
+
| 32.5455 | 179000 | 0.0175 | 0.4900 | - | 0.9424 |
|
| 587 |
+
| 32.7273 | 180000 | 0.0175 | 0.4861 | - | 0.9417 |
|
| 588 |
+
| 32.9091 | 181000 | 0.0178 | 0.5005 | - | 0.9433 |
|
| 589 |
+
| 33.0909 | 182000 | 0.0163 | 0.4934 | - | 0.9408 |
|
| 590 |
+
| 33.2727 | 183000 | 0.0149 | 0.5065 | - | 0.9340 |
|
| 591 |
+
| 33.4545 | 184000 | 0.0157 | 0.4973 | - | 0.9394 |
|
| 592 |
+
| 33.6364 | 185000 | 0.0164 | 0.4993 | - | 0.9377 |
|
| 593 |
+
| 33.8182 | 186000 | 0.0164 | 0.4904 | - | 0.9407 |
|
| 594 |
+
| 34.0 | 187000 | 0.0167 | 0.5096 | - | 0.9391 |
|
| 595 |
+
| 34.1818 | 188000 | 0.0136 | 0.4960 | - | 0.9417 |
|
| 596 |
+
| 34.3636 | 189000 | 0.0142 | 0.5188 | - | 0.9388 |
|
| 597 |
+
| 34.5455 | 190000 | 0.0144 | 0.5139 | - | 0.9365 |
|
| 598 |
+
| 34.7273 | 191000 | 0.0149 | 0.4919 | - | 0.9407 |
|
| 599 |
+
| 34.9091 | 192000 | 0.0149 | 0.4775 | - | 0.9417 |
|
| 600 |
+
| 35.0909 | 193000 | 0.0127 | 0.5546 | - | 0.9418 |
|
| 601 |
+
| 35.2727 | 194000 | 0.0124 | 0.5440 | - | 0.9377 |
|
| 602 |
+
| 35.4545 | 195000 | 0.0126 | 0.5571 | - | 0.9386 |
|
| 603 |
+
| 35.6364 | 196000 | 0.0131 | 0.5127 | - | 0.9410 |
|
| 604 |
+
| 35.8182 | 197000 | 0.0134 | 0.5167 | - | 0.9370 |
|
| 605 |
+
| 36.0 | 198000 | 0.0134 | 0.4939 | - | 0.9384 |
|
| 606 |
+
| 36.1818 | 199000 | 0.011 | 0.5279 | - | 0.9374 |
|
| 607 |
+
| 36.3636 | 200000 | 0.0115 | 0.5336 | - | 0.9357 |
|
| 608 |
+
| 36.5455 | 201000 | 0.0113 | 0.5626 | - | 0.9374 |
|
| 609 |
+
| 36.7273 | 202000 | 0.012 | 0.5316 | - | 0.9382 |
|
| 610 |
+
| 36.9091 | 203000 | 0.0121 | 0.5222 | - | 0.9404 |
|
| 611 |
+
| 37.0909 | 204000 | 0.0107 | 0.5618 | - | 0.9407 |
|
| 612 |
+
| 37.2727 | 205000 | 0.0107 | 0.5508 | - | 0.9390 |
|
| 613 |
+
| 37.4545 | 206000 | 0.0106 | 0.5414 | - | 0.9359 |
|
| 614 |
+
| 37.6364 | 207000 | 0.0106 | 0.5522 | - | 0.9330 |
|
| 615 |
+
| 37.8182 | 208000 | 0.0111 | 0.5524 | - | 0.9365 |
|
| 616 |
+
| 38.0 | 209000 | 0.012 | 0.5176 | - | 0.9402 |
|
| 617 |
+
| 38.1818 | 210000 | 0.0087 | 0.5742 | - | 0.9388 |
|
| 618 |
+
| 38.3636 | 211000 | 0.0092 | 0.5686 | - | 0.9405 |
|
| 619 |
+
| 38.5455 | 212000 | 0.0099 | 0.5699 | - | 0.9338 |
|
| 620 |
+
| 38.7273 | 213000 | 0.0094 | 0.5733 | - | 0.9377 |
|
| 621 |
+
| **38.9091** | **214000** | **0.0097** | **0.5516** | **-** | **0.9416** |
|
| 622 |
+
| 39.0909 | 215000 | 0.009 | 0.5923 | - | 0.9385 |
|
| 623 |
+
| 39.2727 | 216000 | 0.0078 | 0.5925 | - | 0.9412 |
|
| 624 |
+
| 39.4545 | 217000 | 0.0086 | 0.5703 | - | 0.9369 |
|
| 625 |
+
| 39.6364 | 218000 | 0.0087 | 0.5921 | - | 0.9387 |
|
| 626 |
+
| 39.8182 | 219000 | 0.0085 | 0.5859 | - | 0.9304 |
|
| 627 |
+
| 40.0 | 220000 | 0.0091 | 0.5577 | - | 0.9396 |
|
| 628 |
+
| 40.1818 | 221000 | 0.0077 | 0.5844 | - | 0.9395 |
|
| 629 |
+
| 40.3636 | 222000 | 0.0077 | 0.5691 | - | 0.9385 |
|
| 630 |
+
| 40.5455 | 223000 | 0.008 | 0.5794 | - | 0.9372 |
|
| 631 |
+
| 40.7273 | 224000 | 0.0073 | 0.6036 | - | 0.9363 |
|
| 632 |
+
| 40.9091 | 225000 | 0.0083 | 0.5754 | - | 0.9340 |
|
| 633 |
+
| 41.0909 | 226000 | 0.0078 | 0.6141 | - | 0.9378 |
|
| 634 |
+
| 41.2727 | 227000 | 0.0069 | 0.6332 | - | 0.9358 |
|
| 635 |
+
| 41.4545 | 228000 | 0.007 | 0.6220 | - | 0.9321 |
|
| 636 |
+
| 41.6364 | 229000 | 0.0075 | 0.6110 | - | 0.9342 |
|
| 637 |
+
| 41.8182 | 230000 | 0.007 | 0.6248 | - | 0.9331 |
|
| 638 |
+
| 42.0 | 231000 | 0.0072 | 0.5950 | - | 0.9343 |
|
| 639 |
+
| 42.1818 | 232000 | 0.0059 | 0.6428 | - | 0.9363 |
|
| 640 |
+
| 42.3636 | 233000 | 0.0065 | 0.6298 | - | 0.9381 |
|
| 641 |
+
| 42.5455 | 234000 | 0.0065 | 0.6166 | - | 0.9370 |
|
| 642 |
+
| 42.7273 | 235000 | 0.0066 | 0.5990 | - | 0.9390 |
|
| 643 |
+
| 42.9091 | 236000 | 0.0065 | 0.6297 | - | 0.9357 |
|
| 644 |
+
| 43.0909 | 237000 | 0.0057 | 0.6483 | - | 0.9362 |
|
| 645 |
+
| 43.2727 | 238000 | 0.0058 | 0.6077 | - | 0.9353 |
|
| 646 |
+
| 43.4545 | 239000 | 0.0056 | 0.6420 | - | 0.9320 |
|
| 647 |
+
| 43.6364 | 240000 | 0.0059 | 0.6574 | - | 0.9321 |
|
| 648 |
+
| 43.8182 | 241000 | 0.0051 | 0.6819 | - | 0.9320 |
|
| 649 |
+
| 44.0 | 242000 | 0.0055 | 0.6567 | - | 0.9335 |
|
| 650 |
+
| 44.1818 | 243000 | 0.0051 | 0.6697 | - | 0.9349 |
|
| 651 |
+
| 44.3636 | 244000 | 0.005 | 0.6459 | - | 0.9366 |
|
| 652 |
+
| 44.5455 | 245000 | 0.0047 | 0.6693 | - | 0.9342 |
|
| 653 |
+
| 44.7273 | 246000 | 0.0054 | 0.6589 | - | 0.9336 |
|
| 654 |
+
| 44.9091 | 247000 | 0.0051 | 0.6886 | - | 0.9334 |
|
| 655 |
+
| 45.0909 | 248000 | 0.0047 | 0.6886 | - | 0.9334 |
|
| 656 |
+
| 45.2727 | 249000 | 0.0045 | 0.6959 | - | 0.9301 |
|
| 657 |
+
| 45.4545 | 250000 | 0.0045 | 0.6827 | - | 0.9350 |
|
| 658 |
+
| 45.6364 | 251000 | 0.0042 | 0.6706 | - | 0.9353 |
|
| 659 |
+
| 45.8182 | 252000 | 0.0043 | 0.6858 | - | 0.9349 |
|
| 660 |
+
| 46.0 | 253000 | 0.0045 | 0.6926 | - | 0.9344 |
|
| 661 |
+
| 46.1818 | 254000 | 0.0041 | 0.7091 | - | 0.9326 |
|
| 662 |
+
| 46.3636 | 255000 | 0.0038 | 0.7110 | - | 0.9311 |
|
| 663 |
+
| 46.5455 | 256000 | 0.0039 | 0.6991 | - | 0.9315 |
|
| 664 |
+
| 46.7273 | 257000 | 0.0038 | 0.7068 | - | 0.9323 |
|
| 665 |
+
| 46.9091 | 258000 | 0.0043 | 0.7026 | - | 0.9322 |
|
| 666 |
+
| 47.0909 | 259000 | 0.0041 | 0.7031 | - | 0.9316 |
|
| 667 |
+
| 47.2727 | 260000 | 0.0037 | 0.6905 | - | 0.9344 |
|
| 668 |
+
| 47.4545 | 261000 | 0.0035 | 0.7044 | - | 0.9312 |
|
| 669 |
+
| 47.6364 | 262000 | 0.0038 | 0.7005 | - | 0.9307 |
|
| 670 |
+
| 47.8182 | 263000 | 0.0039 | 0.7064 | - | 0.9310 |
|
| 671 |
+
| 48.0 | 264000 | 0.0034 | 0.7112 | - | 0.9309 |
|
| 672 |
+
| 48.1818 | 265000 | 0.0034 | 0.7092 | - | 0.9306 |
|
| 673 |
+
| 48.3636 | 266000 | 0.0029 | 0.7286 | - | 0.9295 |
|
| 674 |
+
| 48.5455 | 267000 | 0.0034 | 0.7270 | - | 0.9278 |
|
| 675 |
+
| 48.7273 | 268000 | 0.0035 | 0.7101 | - | 0.9320 |
|
| 676 |
+
| 48.9091 | 269000 | 0.0035 | 0.7127 | - | 0.9318 |
|
| 677 |
+
| 49.0909 | 270000 | 0.0031 | 0.7228 | - | 0.9331 |
|
| 678 |
+
| 49.2727 | 271000 | 0.0029 | 0.7289 | - | 0.9338 |
|
| 679 |
+
| 49.4545 | 272000 | 0.003 | 0.7309 | - | 0.9336 |
|
| 680 |
+
| 49.6364 | 273000 | 0.003 | 0.7308 | - | 0.9336 |
|
| 681 |
+
| 49.8182 | 274000 | 0.0033 | 0.7293 | - | 0.9339 |
|
| 682 |
+
| 50.0 | 275000 | 0.003 | 0.7302 | - | 0.9338 |
|
| 683 |
|
| 684 |
* The bold row denotes the saved checkpoint.
|
| 685 |
</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:a774f34456132e1cb9114da7d2fbc106df23ee1154971fb6b89c73166cf0ba55
|
| 3 |
size 598436708
|