|
12 | 12 | <table style="width:100%;" cellpadding="2" cellspacing="0" border="1" bordercolor="#000000">
|
13 | 13 | <tbody>
|
14 | 14 | <tr>
|
15 |
| - <td style="text-align:center"> |
| 15 | + <td style="text-align:center;vertical-align:middle"> |
16 | 16 | <span style="font-size:18px;">Arch</span>
|
17 | 17 | </td>
|
18 | 18 | <td style="text-align:center">
|
|
321 | 321 | </td>
|
322 | 322 | </tr>
|
323 | 323 | <tr>
|
324 |
| - <td rowspan=5 align=center> 6L768H </td> |
| 324 | + <td rowspan=5 align=center> 6L768H </td> |
325 | 325 | <td style="text-align:center">
|
326 | 326 | <span style="font-size:18px">ERNIE 3.0-Medium-zh</span>
|
327 | 327 | </td>
|
328 | 328 | <td style="text-align:center">
|
329 |
| - <span style="font-size:18px"><b>72.49</b></span> |
| 329 | + <span style="font-size:18px"><b>72.49</b></span> |
330 | 330 | </td>
|
331 | 331 | <td style="text-align:center">
|
332 |
| - <span style="font-size:18px"><b>73.37</b></span> |
| 332 | + <span style="font-size:18px"><b>73.37</b></span> |
333 | 333 | </td>
|
334 | 334 | <td style="text-align:center">
|
335 |
| - <span style="font-size:18px"><b>57.00</b></span> |
| 335 | + <span style="font-size:18px"><b>57.00</b></span> |
336 | 336 | </td>
|
337 | 337 | <td style="text-align:center">
|
338 |
| - <span style="font-size:18px"><b>60.67</b></span> |
| 338 | + <span style="font-size:18px"><b>60.67</b></span> |
339 | 339 | </td>
|
340 | 340 | <td style="text-align:center">
|
341 |
| - <span style="font-size:18px"><b>80.64</b></span> |
| 341 | + <span style="font-size:18px"><b>80.64</b></span> |
342 | 342 | </td>
|
343 | 343 | <td style="text-align:center">
|
344 |
| - <span style="font-size:18px"><b>76.88</b></span> |
| 344 | + <span style="font-size:18px"><b>76.88</b></span> |
345 | 345 | </td>
|
346 | 346 | <td style="text-align:center">
|
347 |
| - <span style="font-size:18px"><b>79.28</b></span> |
| 347 | + <span style="font-size:18px"><b>79.28</b></span> |
348 | 348 | </td>
|
349 | 349 | <td style="text-align:center">
|
350 |
| - <span style="font-size:18px"><b>81.60</b></span> |
| 350 | + <span style="font-size:18px"><b>81.60</b></span> |
351 | 351 | </td>
|
352 | 352 | <td style="text-align:center">
|
353 |
| - <span style="font-size:18px"><b>65.83/87.30</b></span> |
| 353 | + <span style="font-size:18px"><b>65.83/87.30</b></span> |
354 | 354 | </td>
|
355 | 355 | <td style="text-align:center">
|
356 |
| - <span style="font-size:18px"><b>79.91</b></span> |
| 356 | + <span style="font-size:18px"><b>79.91</b></span> |
357 | 357 | </td>
|
358 | 358 | <td style="text-align:center">
|
359 |
| - <span style="font-size:18px"><b>69.73</b></span> |
| 359 | + <span style="font-size:18px"><b>69.73</b></span> |
360 | 360 | </td>
|
361 | 361 | </tr>
|
362 | 362 | <tr>
|
|
402 | 402 | <span style="font-size:18px">TinyBERT<sub>6</sub>, Chinese</span>
|
403 | 403 | </td>
|
404 | 404 | <td style="text-align:center">
|
405 |
| - <span style="font-size:18px">69.58</span> |
| 405 | + <span style="font-size:18px">69.58</span> |
406 | 406 | </td>
|
407 | 407 | <td style="text-align:center">
|
408 |
| - <span style="font-size:18px">72.22</span> |
| 408 | + <span style="font-size:18px">72.22</span> |
409 | 409 | </td>
|
410 | 410 | <td style="text-align:center">
|
411 |
| - <span style="font-size:18px">55.70</span> |
| 411 | + <span style="font-size:18px">55.70</span> |
412 | 412 | </td>
|
413 | 413 | <td style="text-align:center">
|
414 |
| - <span style="font-size:18px">54.48</span> |
| 414 | + <span style="font-size:18px">54.48</span> |
415 | 415 | </td>
|
416 | 416 | <td style="text-align:center">
|
417 |
| - <span style="font-size:18px">79.12</span> |
| 417 | + <span style="font-size:18px">79.12</span> |
418 | 418 | </td>
|
419 | 419 | <td style="text-align:center">
|
420 |
| - <span style="font-size:18px">74.07</span> |
| 420 | + <span style="font-size:18px">74.07</span> |
421 | 421 | </td>
|
422 | 422 | <td style="text-align:center">
|
423 |
| - <span style="font-size:18px">77.63</span> |
| 423 | + <span style="font-size:18px">77.63</span> |
424 | 424 | </td>
|
425 | 425 | <td style="text-align:center">
|
426 |
| - <span style="font-size:18px">80.17</span> |
| 426 | + <span style="font-size:18px">80.17</span> |
427 | 427 | </td>
|
428 | 428 | <td style="text-align:center">
|
429 |
| - <span style="font-size:18px">62.63/83.72</span> |
| 429 | + <span style="font-size:18px">62.63/83.72</span> |
430 | 430 | </td>
|
431 | 431 | <td style="text-align:center">
|
432 |
| - <span style="font-size:18px">77.64</span> |
| 432 | + <span style="font-size:18px">77.64</span> |
433 | 433 | </td>
|
434 | 434 | <td style="text-align:center">
|
435 |
| - <span style="font-size:18px">62.11</span> |
| 435 | + <span style="font-size:18px">62.11</span> |
436 | 436 | </td>
|
437 | 437 | </tr>
|
438 | 438 | <td style="text-align:center">
|
439 | 439 | <span style="font-size:18px">RoFormerV2 Small</span>
|
440 | 440 | </td>
|
441 | 441 | <td style="text-align:center">
|
442 |
| - <span style="font-size:18px">68.52</span> |
| 442 | + <span style="font-size:18px">68.52</span> |
443 | 443 | </td>
|
444 | 444 | <td style="text-align:center">
|
445 |
| - <span style="font-size:18px">72.47</span> |
| 445 | + <span style="font-size:18px">72.47</span> |
446 | 446 | </td>
|
447 | 447 | <td style="text-align:center">
|
448 |
| - <span style="font-size:18px">56.53</span> |
| 448 | + <span style="font-size:18px">56.53</span> |
449 | 449 | </td>
|
450 | 450 | <td style="text-align:center">
|
451 |
| - <span style="font-size:18px">60.72</span> |
| 451 | + <span style="font-size:18px">60.72</span> |
452 | 452 | </td>
|
453 | 453 | <td style="text-align:center">
|
454 |
| - <span style="font-size:18px">76.37</span> |
| 454 | + <span style="font-size:18px">76.37</span> |
455 | 455 | </td>
|
456 | 456 | <td style="text-align:center">
|
457 |
| - <span style="font-size:18px">72.95</span> |
| 457 | + <span style="font-size:18px">72.95</span> |
458 | 458 | </td>
|
459 | 459 | <td style="text-align:center">
|
460 |
| - <span style="font-size:18px">75.00</span> |
| 460 | + <span style="font-size:18px">75.00</span> |
461 | 461 | </td>
|
462 | 462 | <td style="text-align:center">
|
463 |
| - <span style="font-size:18px">81.07</span> |
| 463 | + <span style="font-size:18px">81.07</span> |
464 | 464 | </td>
|
465 | 465 | <td style="text-align:center">
|
466 |
| - <span style="font-size:18px">62.97/83.64</span> |
| 466 | + <span style="font-size:18px">62.97/83.64</span> |
467 | 467 | </td>
|
468 | 468 | <td style="text-align:center">
|
469 |
| - <span style="font-size:18px">67.66</span> |
| 469 | + <span style="font-size:18px">67.66</span> |
470 | 470 | </td>
|
471 | 471 | <td style="text-align:center">
|
472 |
| - <span style="font-size:18px">59.41</span> |
| 472 | + <span style="font-size:18px">59.41</span> |
473 | 473 | </td>
|
474 | 474 | </tr>
|
475 | 475 | <tr>
|
476 | 476 | <td style="text-align:center">
|
477 | 477 | <span style="font-size:18px">UER/Chinese-RoBERTa (L6-H768)</span>
|
478 | 478 | </td>
|
479 | 479 | <td style="text-align:center">
|
480 |
| - <span style="font-size:18px">66.67</span> |
| 480 | + <span style="font-size:18px">66.67</span> |
| 481 | + </td> |
| 482 | + <td style="text-align:center"> |
| 483 | + <span style="font-size:18px">70.13</span> |
| 484 | + </td> |
| 485 | + <td style="text-align:center"> |
| 486 | + <span style="font-size:18px">56.41</span> |
| 487 | + </td> |
| 488 | + <td style="text-align:center"> |
| 489 | + <span style="font-size:18px">59.79</span> |
| 490 | + </td> |
| 491 | + <td style="text-align:center"> |
| 492 | + <span style="font-size:18px">77.38</span> |
| 493 | + </td> |
| 494 | + <td style="text-align:center"> |
| 495 | + <span style="font-size:18px">71.86</span> |
| 496 | + </td> |
| 497 | + <td style="text-align:center"> |
| 498 | + <span style="font-size:18px">69.41</span> |
| 499 | + </td> |
| 500 | + <td style="text-align:center"> |
| 501 | + <span style="font-size:18px">76.73</span> |
| 502 | + </td> |
| 503 | + <td style="text-align:center"> |
| 504 | + <span style="font-size:18px">53.22/75.03</span> |
| 505 | + </td> |
| 506 | + <td style="text-align:center"> |
| 507 | + <span style="font-size:18px">77.00</span> |
| 508 | + </td> |
| 509 | + <td style="text-align:center"> |
| 510 | + <span style="font-size:18px">54.77</span> |
| 511 | + </td> |
| 512 | + </tr> |
| 513 | + <tr> |
| 514 | + <td rowspan=1 align=center> 6L384H </td> |
| 515 | + <td style="text-align:center"> |
| 516 | + <span style="font-size:18px">ERNIE 3.0-Mini-zh</span> |
| 517 | + </td> |
| 518 | + <td style="text-align:center"> |
| 519 | + <span style="font-size:18px"><b>66.90</b></span> |
| 520 | + </td> |
| 521 | + <td style="text-align:center"> |
| 522 | + <span style="font-size:18px"><b>71.85</b></span> |
| 523 | + </td> |
| 524 | + <td style="text-align:center"> |
| 525 | + <span style="font-size:18px"><b>55.24</b></span> |
| 526 | + </td> |
| 527 | + <td style="text-align:center"> |
| 528 | + <span style="font-size:18px"><b>54.48</b></span> |
| 529 | + </td> |
| 530 | + <td style="text-align:center"> |
| 531 | + <span style="font-size:18px"><b>77.19</b></span> |
| 532 | + </td> |
| 533 | + <td style="text-align:center"> |
| 534 | + <span style="font-size:18px"><b>73.08</b></span> |
| 535 | + </td> |
| 536 | + <td style="text-align:center"> |
| 537 | + <span style="font-size:18px"><b>71.05</b></span> |
481 | 538 | </td>
|
482 | 539 | <td style="text-align:center">
|
483 |
| - <span style="font-size:18px">70.13</span> |
| 540 | + <span style="font-size:18px"><b>79.30</b></span> |
484 | 541 | </td>
|
485 | 542 | <td style="text-align:center">
|
486 |
| - <span style="font-size:18px">56.41</span> |
| 543 | + <span style="font-size:18px"><b>58.53/81.97</b></span> |
487 | 544 | </td>
|
488 | 545 | <td style="text-align:center">
|
489 |
| - <span style="font-size:18px">59.79</span> |
| 546 | + <span style="font-size:18px"><b>69.71</b></span> |
| 547 | + </td> |
| 548 | + <td style="text-align:center"> |
| 549 | + <span style="font-size:18px"><b>58.60</b></span> |
| 550 | + </td> |
| 551 | + </tr> |
| 552 | + <tr> |
| 553 | + <td rowspan=1 align=center> 4L384H </td> |
| 554 | + <td style="text-align:center"> |
| 555 | + <span style="font-size:18px">ERNIE 3.0-Micro-zh</span> |
| 556 | + </td> |
| 557 | + <td style="text-align:center"> |
| 558 | + <span style="font-size:18px"><b>64.21</b></span> |
| 559 | + </td> |
| 560 | + <td style="text-align:center"> |
| 561 | + <span style="font-size:18px"><b>71.15</b></span> |
| 562 | + </td> |
| 563 | + <td style="text-align:center"> |
| 564 | + <span style="font-size:18px"><b>55.05</b></span> |
| 565 | + </td> |
| 566 | + <td style="text-align:center"> |
| 567 | + <span style="font-size:18px"><b>53.83</b></span> |
| 568 | + </td> |
| 569 | + <td style="text-align:center"> |
| 570 | + <span style="font-size:18px"><b>74.81</b></span> |
| 571 | + </td> |
| 572 | + <td style="text-align:center"> |
| 573 | + <span style="font-size:18px"><b>70.41</b></span> |
| 574 | + </td> |
| 575 | + <td style="text-align:center"> |
| 576 | + <span style="font-size:18px"><b>69.08</b></span> |
490 | 577 | </td>
|
491 | 578 | <td style="text-align:center">
|
492 |
| - <span style="font-size:18px">77.38</span> |
| 579 | + <span style="font-size:18px"><b>76.50</b></span> |
493 | 580 | </td>
|
494 | 581 | <td style="text-align:center">
|
495 |
| - <span style="font-size:18px">71.86</span> |
| 582 | + <span style="font-size:18px"><b>53.77/77.82</b></span> |
496 | 583 | </td>
|
497 | 584 | <td style="text-align:center">
|
498 |
| - <span style="font-size:18px">69.41</span> |
| 585 | + <span style="font-size:18px"><b>62.26</b></span> |
| 586 | + </td> |
| 587 | + <td style="text-align:center"> |
| 588 | + <span style="font-size:18px"><b>55.53</b></span> |
| 589 | + </td> |
| 590 | + </tr> |
| 591 | + <tr> |
| 592 | + <td rowspan=1 align=center> 4L312H </td> |
| 593 | + <td style="text-align:center"> |
| 594 | + <span style="font-size:18px">ERNIE 3.0-Nano-zh</span> |
| 595 | + </td> |
| 596 | + <td style="text-align:center"> |
| 597 | + <span style="font-size:18px"><b>62.97</b></span> |
| 598 | + </td> |
| 599 | + <td style="text-align:center"> |
| 600 | + <span style="font-size:18px"><b>70.51</b></span> |
499 | 601 | </td>
|
500 | 602 | <td style="text-align:center">
|
501 |
| - <span style="font-size:18px">76.73</span> |
| 603 | + <span style="font-size:18px"><b>54.57</b></span> |
502 | 604 | </td>
|
503 | 605 | <td style="text-align:center">
|
504 |
| - <span style="font-size:18px">53.22/75.03</span> |
| 606 | + <span style="font-size:18px"><b>48.36</b></span> |
505 | 607 | </td>
|
506 | 608 | <td style="text-align:center">
|
507 |
| - <span style="font-size:18px">77.00</span> |
| 609 | + <span style="font-size:18px"><b>74.97</b></span> |
508 | 610 | </td>
|
509 | 611 | <td style="text-align:center">
|
510 |
| - <span style="font-size:18px">54.77</span> |
| 612 | + <span style="font-size:18px"><b>70.61</b></span> |
| 613 | + </td> |
| 614 | + <td style="text-align:center"> |
| 615 | + <span style="font-size:18px"><b>68.75</b></span> |
| 616 | + </td> |
| 617 | + <td style="text-align:center"> |
| 618 | + <span style="font-size:18px"><b>75.93</b></span> |
| 619 | + </td> |
| 620 | + <td style="text-align:center"> |
| 621 | + <span style="font-size:18px"><b>52.00/76.35</b></span> |
| 622 | + </td> |
| 623 | + <td style="text-align:center"> |
| 624 | + <span style="font-size:18px"><b>58.91</b></span> |
| 625 | + </td> |
| 626 | + <td style="text-align:center"> |
| 627 | + <span style="font-size:18px"><b>55.11</b></span> |
511 | 628 | </td>
|
512 | 629 | </tr>
|
513 | 630 | <tbody>
|
@@ -551,9 +668,12 @@ AFQMC、TNEWS、IFLYTEK、CMNLI、OCNLI、CLUEWSC2020、CSL 、CHID 和 C<sup>3<
|
551 | 668 | | RoFormerV2 Small | 5e-5,16 | 2e-5,16 | 5e-5,16 | 5e-5,32 | 2e-5,16 | 3e-5,8 | 3e-5,16 | 3e-5,24 | 3e-5,24 | 3e-5,24 |
|
552 | 669 | | HLF/RBT6, Chinese | 3e-5,16 | 5e-5,16 | 5e-5,16 | 5e-5,64 | 3e-5,32 | 3e-5,32 | 3e-5,16 | 3e-5,32 | 3e-5,24 | 3e-5,24 |
|
553 | 670 | | UER/Chinese-RoBERTa (L6-H768) | 2e-5,16 | 5e-5,32 | 5e-5,16 | 5e-5,32 | 3e-5,16 | 5e-5,8 | 3e-5,16 | 3e-5,24 | 3e-5,24 | 3e-5,32 |
|
| 671 | +| ERNIE 3.0-Mini-zh | 5e-5,64 | 5e-5,64 | 5e-5,16 | 5e-5,32 | 2e-5,16 | 2e-5,8 | 2e-5,16 | 3e-5,24 | 3e-5,24 | 3e-5,24 | |
| 672 | +| ERNIE 3.0-Micro-zh | 3e-5,16 | 5e-5,32 | 5e-5,16 | 5e-5,16 | 2e-5,32 | 5e-5,16 | 3e-5,64 | 3e-5,24 | 3e-5,32 | 3e-5,24 | |
| 673 | +| ERNIE 3.0-Nano-zh | 2e-5,32 | 5e-5,16 | 5e-5,16 | 5e-5,16 | 3e-5,16 | 1e-5,8 | 3e-5,32 | 3e-5,24 | 3e-5,24 | 2e-5,24 | |
554 | 674 |
|
555 | 675 |
|
556 |
| -其中,`ERNIE 3.0-Base-zh`、`ERNIE 3.0-Medium-zh`、`ERNIE-Gram-zh`、`ERNIE 1.0` 在 CLUEWSC2020 处的 dropout_prob 为 0.0,`ERNIE 3.0-Base-zh`、`HLF/RBT6, Chinese`、`Mengzi-BERT-Base`、`ERNIE-Gram-zh`、`ERNIE 1.0` 、`TinyBERT6, Chinese`、`UER/Chinese-RoBERTa (L6-H768)` 在 IFLYTEK 处的 dropout_prob 为 0.0。 |
| 676 | +其中,`ERNIE 3.0-Base-zh`、`ERNIE 3.0-Medium-zh`、`ERNIE-Gram-zh`、`ERNIE 1.0`、`ERNIE 3.0-Mini-zh`、`ERNIE 3.0-Micro-zh`、`ERNIE 3.0-Nano-zh` 在 CLUEWSC2020 处的 dropout_prob 为 0.0,`ERNIE 3.0-Base-zh`、`HLF/RBT6, Chinese`、`Mengzi-BERT-Base`、`ERNIE-Gram-zh`、`ERNIE 1.0` 、`TinyBERT6, Chinese`、`UER/Chinese-RoBERTa (L6-H768)`、`ERNIE 3.0-Mini-zh`、`ERNIE 3.0-Micro-zh`、`ERNIE 3.0-Nano-zh` 在 IFLYTEK 处的 dropout_prob 为 0.0。 |
557 | 677 |
|
558 | 678 |
|
559 | 679 | ## 一键复现模型效果
|
|
0 commit comments