Training in progress, step 1000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 735217848
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c854e311156a00fb209c1d5b18bf088757f9e875811a4af0292d4b051e6c6446
|
| 3 |
size 735217848
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1470521978
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de307672e8d7a91febef716662f5657dacb787fa03178bc23fb37badcafa7ed1
|
| 3 |
size 1470521978
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:038ef74d9d7647e927602a31e3ff40ed015ce2147efee9b81efc43a4be3f559b
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1000
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fca3c514eb217652ef846414a7b25fe2d542ec928f14020a84d1e47090ecb880
|
| 3 |
size 1000
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 100,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -437,6 +437,436 @@
|
|
| 437 |
"eval_spearman_manhattan": 0.8187222998801444,
|
| 438 |
"eval_steps_per_second": 15.744,
|
| 439 |
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 440 |
}
|
| 441 |
],
|
| 442 |
"logging_steps": 10,
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.46860356138706655,
|
| 5 |
"eval_steps": 100,
|
| 6 |
+
"global_step": 1000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 437 |
"eval_spearman_manhattan": 0.8187222998801444,
|
| 438 |
"eval_steps_per_second": 15.744,
|
| 439 |
"step": 500
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.23898781630740393,
|
| 443 |
+
"grad_norm": 1.9643880128860474,
|
| 444 |
+
"learning_rate": 4.850632614807873e-05,
|
| 445 |
+
"loss": 0.4231,
|
| 446 |
+
"step": 510
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.2436738519212746,
|
| 450 |
+
"grad_norm": 1.7972699403762817,
|
| 451 |
+
"learning_rate": 4.847703842549204e-05,
|
| 452 |
+
"loss": 0.3893,
|
| 453 |
+
"step": 520
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.24835988753514526,
|
| 457 |
+
"grad_norm": 1.6312799453735352,
|
| 458 |
+
"learning_rate": 4.844775070290534e-05,
|
| 459 |
+
"loss": 0.3869,
|
| 460 |
+
"step": 530
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.2530459231490159,
|
| 464 |
+
"grad_norm": 1.8009634017944336,
|
| 465 |
+
"learning_rate": 4.841846298031865e-05,
|
| 466 |
+
"loss": 0.4,
|
| 467 |
+
"step": 540
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.25773195876288657,
|
| 471 |
+
"grad_norm": 1.1453664302825928,
|
| 472 |
+
"learning_rate": 4.838917525773196e-05,
|
| 473 |
+
"loss": 0.3568,
|
| 474 |
+
"step": 550
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.2624179943767573,
|
| 478 |
+
"grad_norm": 1.683673620223999,
|
| 479 |
+
"learning_rate": 4.8359887535145274e-05,
|
| 480 |
+
"loss": 0.3674,
|
| 481 |
+
"step": 560
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.26710402999062793,
|
| 485 |
+
"grad_norm": 1.3695913553237915,
|
| 486 |
+
"learning_rate": 4.833059981255858e-05,
|
| 487 |
+
"loss": 0.3817,
|
| 488 |
+
"step": 570
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.2717900656044986,
|
| 492 |
+
"grad_norm": 1.8631620407104492,
|
| 493 |
+
"learning_rate": 4.8301312089971884e-05,
|
| 494 |
+
"loss": 0.3546,
|
| 495 |
+
"step": 580
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.27647610121836924,
|
| 499 |
+
"grad_norm": 1.5883185863494873,
|
| 500 |
+
"learning_rate": 4.827202436738519e-05,
|
| 501 |
+
"loss": 0.3973,
|
| 502 |
+
"step": 590
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 0.28116213683223995,
|
| 506 |
+
"grad_norm": 1.7056660652160645,
|
| 507 |
+
"learning_rate": 4.82427366447985e-05,
|
| 508 |
+
"loss": 0.3754,
|
| 509 |
+
"step": 600
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 0.28116213683223995,
|
| 513 |
+
"eval_loss": 0.059529613703489304,
|
| 514 |
+
"eval_pearson_cosine": 0.8104839357699305,
|
| 515 |
+
"eval_pearson_dot": 0.7706455959096417,
|
| 516 |
+
"eval_pearson_euclidean": 0.8087417307856555,
|
| 517 |
+
"eval_pearson_manhattan": 0.8101299227665919,
|
| 518 |
+
"eval_runtime": 6.0212,
|
| 519 |
+
"eval_samples_per_second": 249.121,
|
| 520 |
+
"eval_spearman_cosine": 0.8125251228747598,
|
| 521 |
+
"eval_spearman_dot": 0.7680727600884657,
|
| 522 |
+
"eval_spearman_euclidean": 0.8146128693278114,
|
| 523 |
+
"eval_spearman_manhattan": 0.8161621120875591,
|
| 524 |
+
"eval_steps_per_second": 15.612,
|
| 525 |
+
"step": 600
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.2858481724461106,
|
| 529 |
+
"grad_norm": 1.8564058542251587,
|
| 530 |
+
"learning_rate": 4.821344892221181e-05,
|
| 531 |
+
"loss": 0.4016,
|
| 532 |
+
"step": 610
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.29053420805998126,
|
| 536 |
+
"grad_norm": 1.467993974685669,
|
| 537 |
+
"learning_rate": 4.818416119962512e-05,
|
| 538 |
+
"loss": 0.3858,
|
| 539 |
+
"step": 620
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.2952202436738519,
|
| 543 |
+
"grad_norm": 2.3624465465545654,
|
| 544 |
+
"learning_rate": 4.815487347703843e-05,
|
| 545 |
+
"loss": 0.3796,
|
| 546 |
+
"step": 630
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.29990627928772257,
|
| 550 |
+
"grad_norm": 1.588629126548767,
|
| 551 |
+
"learning_rate": 4.8125585754451736e-05,
|
| 552 |
+
"loss": 0.3667,
|
| 553 |
+
"step": 640
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.3045923149015933,
|
| 557 |
+
"grad_norm": 1.380112886428833,
|
| 558 |
+
"learning_rate": 4.8096298031865044e-05,
|
| 559 |
+
"loss": 0.3453,
|
| 560 |
+
"step": 650
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.30927835051546393,
|
| 564 |
+
"grad_norm": 1.4270693063735962,
|
| 565 |
+
"learning_rate": 4.806701030927835e-05,
|
| 566 |
+
"loss": 0.3345,
|
| 567 |
+
"step": 660
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.3139643861293346,
|
| 571 |
+
"grad_norm": 2.204744338989258,
|
| 572 |
+
"learning_rate": 4.803772258669166e-05,
|
| 573 |
+
"loss": 0.395,
|
| 574 |
+
"step": 670
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 0.31865042174320524,
|
| 578 |
+
"grad_norm": 1.4480923414230347,
|
| 579 |
+
"learning_rate": 4.800843486410497e-05,
|
| 580 |
+
"loss": 0.3691,
|
| 581 |
+
"step": 680
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 0.3233364573570759,
|
| 585 |
+
"grad_norm": 1.8864325284957886,
|
| 586 |
+
"learning_rate": 4.797914714151828e-05,
|
| 587 |
+
"loss": 0.3986,
|
| 588 |
+
"step": 690
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 0.3280224929709466,
|
| 592 |
+
"grad_norm": 1.3784370422363281,
|
| 593 |
+
"learning_rate": 4.794985941893159e-05,
|
| 594 |
+
"loss": 0.3729,
|
| 595 |
+
"step": 700
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 0.3280224929709466,
|
| 599 |
+
"eval_loss": 0.061924997717142105,
|
| 600 |
+
"eval_pearson_cosine": 0.8155259960165324,
|
| 601 |
+
"eval_pearson_dot": 0.7761366153485074,
|
| 602 |
+
"eval_pearson_euclidean": 0.8127568794877789,
|
| 603 |
+
"eval_pearson_manhattan": 0.8144288026347226,
|
| 604 |
+
"eval_runtime": 6.0626,
|
| 605 |
+
"eval_samples_per_second": 247.42,
|
| 606 |
+
"eval_spearman_cosine": 0.8175981152530937,
|
| 607 |
+
"eval_spearman_dot": 0.7736443532595881,
|
| 608 |
+
"eval_spearman_euclidean": 0.8195662973032031,
|
| 609 |
+
"eval_spearman_manhattan": 0.8212465310439688,
|
| 610 |
+
"eval_steps_per_second": 15.505,
|
| 611 |
+
"step": 700
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.33270852858481725,
|
| 615 |
+
"grad_norm": 1.7109017372131348,
|
| 616 |
+
"learning_rate": 4.7920571696344895e-05,
|
| 617 |
+
"loss": 0.3345,
|
| 618 |
+
"step": 710
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.3373945641986879,
|
| 622 |
+
"grad_norm": 1.8547511100769043,
|
| 623 |
+
"learning_rate": 4.7891283973758204e-05,
|
| 624 |
+
"loss": 0.3735,
|
| 625 |
+
"step": 720
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.34208059981255856,
|
| 629 |
+
"grad_norm": 1.5369923114776611,
|
| 630 |
+
"learning_rate": 4.786199625117151e-05,
|
| 631 |
+
"loss": 0.3304,
|
| 632 |
+
"step": 730
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.3467666354264292,
|
| 636 |
+
"grad_norm": 1.308568000793457,
|
| 637 |
+
"learning_rate": 4.783270852858482e-05,
|
| 638 |
+
"loss": 0.3717,
|
| 639 |
+
"step": 740
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.3514526710402999,
|
| 643 |
+
"grad_norm": 1.3743574619293213,
|
| 644 |
+
"learning_rate": 4.780342080599813e-05,
|
| 645 |
+
"loss": 0.3381,
|
| 646 |
+
"step": 750
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.3561387066541706,
|
| 650 |
+
"grad_norm": 1.874657154083252,
|
| 651 |
+
"learning_rate": 4.777413308341144e-05,
|
| 652 |
+
"loss": 0.3193,
|
| 653 |
+
"step": 760
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.36082474226804123,
|
| 657 |
+
"grad_norm": 1.4700101613998413,
|
| 658 |
+
"learning_rate": 4.774484536082475e-05,
|
| 659 |
+
"loss": 0.3799,
|
| 660 |
+
"step": 770
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.3655107778819119,
|
| 664 |
+
"grad_norm": 1.5662988424301147,
|
| 665 |
+
"learning_rate": 4.771555763823805e-05,
|
| 666 |
+
"loss": 0.3453,
|
| 667 |
+
"step": 780
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.3701968134957826,
|
| 671 |
+
"grad_norm": 1.4666754007339478,
|
| 672 |
+
"learning_rate": 4.768626991565136e-05,
|
| 673 |
+
"loss": 0.3175,
|
| 674 |
+
"step": 790
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.37488284910965325,
|
| 678 |
+
"grad_norm": 1.3993242979049683,
|
| 679 |
+
"learning_rate": 4.765698219306467e-05,
|
| 680 |
+
"loss": 0.341,
|
| 681 |
+
"step": 800
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.37488284910965325,
|
| 685 |
+
"eval_loss": 0.05296875163912773,
|
| 686 |
+
"eval_pearson_cosine": 0.8137295797811834,
|
| 687 |
+
"eval_pearson_dot": 0.7695932846417932,
|
| 688 |
+
"eval_pearson_euclidean": 0.8189567419998482,
|
| 689 |
+
"eval_pearson_manhattan": 0.8200667930673546,
|
| 690 |
+
"eval_runtime": 6.3175,
|
| 691 |
+
"eval_samples_per_second": 237.436,
|
| 692 |
+
"eval_spearman_cosine": 0.815541427803139,
|
| 693 |
+
"eval_spearman_dot": 0.7663341686268886,
|
| 694 |
+
"eval_spearman_euclidean": 0.8233566840888671,
|
| 695 |
+
"eval_spearman_manhattan": 0.8246092914965037,
|
| 696 |
+
"eval_steps_per_second": 14.879,
|
| 697 |
+
"step": 800
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.3795688847235239,
|
| 701 |
+
"grad_norm": 1.4209802150726318,
|
| 702 |
+
"learning_rate": 4.762769447047798e-05,
|
| 703 |
+
"loss": 0.3831,
|
| 704 |
+
"step": 810
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.38425492033739456,
|
| 708 |
+
"grad_norm": 1.4097892045974731,
|
| 709 |
+
"learning_rate": 4.759840674789129e-05,
|
| 710 |
+
"loss": 0.3318,
|
| 711 |
+
"step": 820
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.3889409559512652,
|
| 715 |
+
"grad_norm": 1.706900715827942,
|
| 716 |
+
"learning_rate": 4.756911902530459e-05,
|
| 717 |
+
"loss": 0.3328,
|
| 718 |
+
"step": 830
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.3936269915651359,
|
| 722 |
+
"grad_norm": 1.610275149345398,
|
| 723 |
+
"learning_rate": 4.75398313027179e-05,
|
| 724 |
+
"loss": 0.3575,
|
| 725 |
+
"step": 840
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.3983130271790066,
|
| 729 |
+
"grad_norm": 1.4575105905532837,
|
| 730 |
+
"learning_rate": 4.751054358013121e-05,
|
| 731 |
+
"loss": 0.307,
|
| 732 |
+
"step": 850
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.4029990627928772,
|
| 736 |
+
"grad_norm": 1.638424277305603,
|
| 737 |
+
"learning_rate": 4.7481255857544524e-05,
|
| 738 |
+
"loss": 0.3504,
|
| 739 |
+
"step": 860
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 0.4076850984067479,
|
| 743 |
+
"grad_norm": 1.8157601356506348,
|
| 744 |
+
"learning_rate": 4.745196813495783e-05,
|
| 745 |
+
"loss": 0.3931,
|
| 746 |
+
"step": 870
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.41237113402061853,
|
| 750 |
+
"grad_norm": 1.6680104732513428,
|
| 751 |
+
"learning_rate": 4.7422680412371134e-05,
|
| 752 |
+
"loss": 0.362,
|
| 753 |
+
"step": 880
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.41705716963448924,
|
| 757 |
+
"grad_norm": 1.4331028461456299,
|
| 758 |
+
"learning_rate": 4.739339268978444e-05,
|
| 759 |
+
"loss": 0.3451,
|
| 760 |
+
"step": 890
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 0.4217432052483599,
|
| 764 |
+
"grad_norm": 1.3940101861953735,
|
| 765 |
+
"learning_rate": 4.736410496719775e-05,
|
| 766 |
+
"loss": 0.3161,
|
| 767 |
+
"step": 900
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 0.4217432052483599,
|
| 771 |
+
"eval_loss": 0.05680527910590172,
|
| 772 |
+
"eval_pearson_cosine": 0.816164907471336,
|
| 773 |
+
"eval_pearson_dot": 0.7659985241939467,
|
| 774 |
+
"eval_pearson_euclidean": 0.8198292531320703,
|
| 775 |
+
"eval_pearson_manhattan": 0.8209187797411488,
|
| 776 |
+
"eval_runtime": 6.6335,
|
| 777 |
+
"eval_samples_per_second": 226.126,
|
| 778 |
+
"eval_spearman_cosine": 0.8181742542924034,
|
| 779 |
+
"eval_spearman_dot": 0.7624851760530289,
|
| 780 |
+
"eval_spearman_euclidean": 0.8251528076462932,
|
| 781 |
+
"eval_spearman_manhattan": 0.8261936560831687,
|
| 782 |
+
"eval_steps_per_second": 14.171,
|
| 783 |
+
"step": 900
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.42642924086223055,
|
| 787 |
+
"grad_norm": 1.5849499702453613,
|
| 788 |
+
"learning_rate": 4.733481724461106e-05,
|
| 789 |
+
"loss": 0.2852,
|
| 790 |
+
"step": 910
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.4311152764761012,
|
| 794 |
+
"grad_norm": 1.8611364364624023,
|
| 795 |
+
"learning_rate": 4.7305529522024375e-05,
|
| 796 |
+
"loss": 0.3517,
|
| 797 |
+
"step": 920
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.43580131208997186,
|
| 801 |
+
"grad_norm": 1.759479284286499,
|
| 802 |
+
"learning_rate": 4.727624179943768e-05,
|
| 803 |
+
"loss": 0.3309,
|
| 804 |
+
"step": 930
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.44048734770384257,
|
| 808 |
+
"grad_norm": 1.3715683221817017,
|
| 809 |
+
"learning_rate": 4.7246954076850985e-05,
|
| 810 |
+
"loss": 0.2964,
|
| 811 |
+
"step": 940
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 0.4451733833177132,
|
| 815 |
+
"grad_norm": 1.6326545476913452,
|
| 816 |
+
"learning_rate": 4.7217666354264294e-05,
|
| 817 |
+
"loss": 0.3501,
|
| 818 |
+
"step": 950
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.4498594189315839,
|
| 822 |
+
"grad_norm": 1.238206148147583,
|
| 823 |
+
"learning_rate": 4.71883786316776e-05,
|
| 824 |
+
"loss": 0.3366,
|
| 825 |
+
"step": 960
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.45454545454545453,
|
| 829 |
+
"grad_norm": 1.6656396389007568,
|
| 830 |
+
"learning_rate": 4.715909090909091e-05,
|
| 831 |
+
"loss": 0.3594,
|
| 832 |
+
"step": 970
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 0.4592314901593252,
|
| 836 |
+
"grad_norm": 1.5264825820922852,
|
| 837 |
+
"learning_rate": 4.712980318650422e-05,
|
| 838 |
+
"loss": 0.3309,
|
| 839 |
+
"step": 980
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 0.4639175257731959,
|
| 843 |
+
"grad_norm": 1.4031989574432373,
|
| 844 |
+
"learning_rate": 4.710051546391753e-05,
|
| 845 |
+
"loss": 0.3616,
|
| 846 |
+
"step": 990
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 0.46860356138706655,
|
| 850 |
+
"grad_norm": 1.439453125,
|
| 851 |
+
"learning_rate": 4.7071227741330836e-05,
|
| 852 |
+
"loss": 0.3122,
|
| 853 |
+
"step": 1000
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 0.46860356138706655,
|
| 857 |
+
"eval_loss": 0.05414344370365143,
|
| 858 |
+
"eval_pearson_cosine": 0.8215390057088641,
|
| 859 |
+
"eval_pearson_dot": 0.7789934072191471,
|
| 860 |
+
"eval_pearson_euclidean": 0.8206818537339018,
|
| 861 |
+
"eval_pearson_manhattan": 0.8219733991381624,
|
| 862 |
+
"eval_runtime": 6.2607,
|
| 863 |
+
"eval_samples_per_second": 239.588,
|
| 864 |
+
"eval_spearman_cosine": 0.8235945278831797,
|
| 865 |
+
"eval_spearman_dot": 0.7745226194646113,
|
| 866 |
+
"eval_spearman_euclidean": 0.8268444005248111,
|
| 867 |
+
"eval_spearman_manhattan": 0.8284194308491212,
|
| 868 |
+
"eval_steps_per_second": 15.014,
|
| 869 |
+
"step": 1000
|
| 870 |
}
|
| 871 |
],
|
| 872 |
"logging_steps": 10,
|