Training in progress, step 750, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 527048968
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e70fb031762fcfd8c2a1f24a8bd93eb87a81e3c17768955c081c28620420fc2
|
| 3 |
size 527048968
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1054136250
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1fe1a49d9560e0ca1782d1d6f8e87b1fe1f66e212ac402fe9c344df8a527655
|
| 3 |
size 1054136250
|
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 sha256:2f2273afa8515c993e20ab8b02a38f3946423176fb53d9323aa6e0510256a9c8
|
| 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 1256
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f47df519d3e34f85833ffe9513be298918979811657719c019fec7ab68351e14
|
| 3 |
size 1256
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "./output/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 150,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -402,6 +402,296 @@
|
|
| 402 |
"EMA_steps_per_second": 22.503,
|
| 403 |
"epoch": 10.0,
|
| 404 |
"step": 450
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 405 |
}
|
| 406 |
],
|
| 407 |
"logging_steps": 10,
|
|
@@ -421,7 +711,7 @@
|
|
| 421 |
"attributes": {}
|
| 422 |
}
|
| 423 |
},
|
| 424 |
-
"total_flos":
|
| 425 |
"train_batch_size": 2,
|
| 426 |
"trial_name": null,
|
| 427 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.7214915752410889,
|
| 3 |
+
"best_model_checkpoint": "./output/checkpoint-750",
|
| 4 |
+
"epoch": 16.666666666666668,
|
| 5 |
"eval_steps": 150,
|
| 6 |
+
"global_step": 750,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 402 |
"EMA_steps_per_second": 22.503,
|
| 403 |
"epoch": 10.0,
|
| 404 |
"step": 450
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 10.222222222222221,
|
| 408 |
+
"grad_norm": 2.220747470855713,
|
| 409 |
+
"learning_rate": 2.9996147467351836e-05,
|
| 410 |
+
"loss": 0.5056,
|
| 411 |
+
"step": 460
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 10.444444444444445,
|
| 415 |
+
"grad_norm": 1.4205608367919922,
|
| 416 |
+
"learning_rate": 2.9995930474939753e-05,
|
| 417 |
+
"loss": 0.4901,
|
| 418 |
+
"step": 470
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 10.666666666666666,
|
| 422 |
+
"grad_norm": 1.9306081533432007,
|
| 423 |
+
"learning_rate": 2.9995707538619954e-05,
|
| 424 |
+
"loss": 0.6361,
|
| 425 |
+
"step": 480
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 10.88888888888889,
|
| 429 |
+
"grad_norm": 2.1457133293151855,
|
| 430 |
+
"learning_rate": 2.9995478658480802e-05,
|
| 431 |
+
"loss": 0.5528,
|
| 432 |
+
"step": 490
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 11.11111111111111,
|
| 436 |
+
"grad_norm": 1.8677959442138672,
|
| 437 |
+
"learning_rate": 2.9995243834613023e-05,
|
| 438 |
+
"loss": 0.5233,
|
| 439 |
+
"step": 500
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 11.333333333333334,
|
| 443 |
+
"grad_norm": 1.6708972454071045,
|
| 444 |
+
"learning_rate": 2.9995003067109687e-05,
|
| 445 |
+
"loss": 0.5387,
|
| 446 |
+
"step": 510
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 11.555555555555555,
|
| 450 |
+
"grad_norm": 2.6434991359710693,
|
| 451 |
+
"learning_rate": 2.9994756356066226e-05,
|
| 452 |
+
"loss": 0.5847,
|
| 453 |
+
"step": 520
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 11.777777777777779,
|
| 457 |
+
"grad_norm": 2.2601070404052734,
|
| 458 |
+
"learning_rate": 2.999450370158044e-05,
|
| 459 |
+
"loss": 0.5341,
|
| 460 |
+
"step": 530
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 12.0,
|
| 464 |
+
"grad_norm": 1.5335863828659058,
|
| 465 |
+
"learning_rate": 2.9994245103752457e-05,
|
| 466 |
+
"loss": 0.5242,
|
| 467 |
+
"step": 540
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 12.222222222222221,
|
| 471 |
+
"grad_norm": 1.2394074201583862,
|
| 472 |
+
"learning_rate": 2.999398056268479e-05,
|
| 473 |
+
"loss": 0.5356,
|
| 474 |
+
"step": 550
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 12.444444444444445,
|
| 478 |
+
"grad_norm": 1.472650170326233,
|
| 479 |
+
"learning_rate": 2.9993710078482286e-05,
|
| 480 |
+
"loss": 0.415,
|
| 481 |
+
"step": 560
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 12.666666666666666,
|
| 485 |
+
"grad_norm": 3.3844995498657227,
|
| 486 |
+
"learning_rate": 2.9993433651252164e-05,
|
| 487 |
+
"loss": 0.6192,
|
| 488 |
+
"step": 570
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 12.88888888888889,
|
| 492 |
+
"grad_norm": 1.4811444282531738,
|
| 493 |
+
"learning_rate": 2.9993151281103986e-05,
|
| 494 |
+
"loss": 0.5351,
|
| 495 |
+
"step": 580
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 13.11111111111111,
|
| 499 |
+
"grad_norm": 2.4430384635925293,
|
| 500 |
+
"learning_rate": 2.9992862968149675e-05,
|
| 501 |
+
"loss": 0.4177,
|
| 502 |
+
"step": 590
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 13.333333333333334,
|
| 506 |
+
"grad_norm": 2.456298351287842,
|
| 507 |
+
"learning_rate": 2.9992568712503513e-05,
|
| 508 |
+
"loss": 0.5317,
|
| 509 |
+
"step": 600
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 13.333333333333334,
|
| 513 |
+
"eval_loss": 0.7220126986503601,
|
| 514 |
+
"eval_runtime": 0.5023,
|
| 515 |
+
"eval_samples_per_second": 19.91,
|
| 516 |
+
"eval_steps_per_second": 19.91,
|
| 517 |
+
"step": 600
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"Start_State_loss": 0.7391407489776611,
|
| 521 |
+
"Start_State_runtime": 0.4727,
|
| 522 |
+
"Start_State_samples_per_second": 21.154,
|
| 523 |
+
"Start_State_steps_per_second": 21.154,
|
| 524 |
+
"epoch": 13.333333333333334,
|
| 525 |
+
"step": 600
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"Raw_Model_loss": 0.7220126986503601,
|
| 529 |
+
"Raw_Model_runtime": 0.5347,
|
| 530 |
+
"Raw_Model_samples_per_second": 18.703,
|
| 531 |
+
"Raw_Model_steps_per_second": 18.703,
|
| 532 |
+
"epoch": 13.333333333333334,
|
| 533 |
+
"step": 600
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"SWA_loss": 0.7282296419143677,
|
| 537 |
+
"SWA_runtime": 0.5752,
|
| 538 |
+
"SWA_samples_per_second": 17.384,
|
| 539 |
+
"SWA_steps_per_second": 17.384,
|
| 540 |
+
"epoch": 13.333333333333334,
|
| 541 |
+
"step": 600
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"EMA_loss": 0.7385488748550415,
|
| 545 |
+
"EMA_runtime": 0.5662,
|
| 546 |
+
"EMA_samples_per_second": 17.661,
|
| 547 |
+
"EMA_steps_per_second": 17.661,
|
| 548 |
+
"epoch": 13.333333333333334,
|
| 549 |
+
"step": 600
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 13.555555555555555,
|
| 553 |
+
"grad_norm": 2.3377010822296143,
|
| 554 |
+
"learning_rate": 2.9992268514282122e-05,
|
| 555 |
+
"loss": 0.565,
|
| 556 |
+
"step": 610
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 13.777777777777779,
|
| 560 |
+
"grad_norm": 2.2196319103240967,
|
| 561 |
+
"learning_rate": 2.99919623736045e-05,
|
| 562 |
+
"loss": 0.441,
|
| 563 |
+
"step": 620
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 14.0,
|
| 567 |
+
"grad_norm": 2.2767350673675537,
|
| 568 |
+
"learning_rate": 2.9991650290591996e-05,
|
| 569 |
+
"loss": 0.6033,
|
| 570 |
+
"step": 630
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 14.222222222222221,
|
| 574 |
+
"grad_norm": 2.253643035888672,
|
| 575 |
+
"learning_rate": 2.99913322653683e-05,
|
| 576 |
+
"loss": 0.4925,
|
| 577 |
+
"step": 640
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 14.444444444444445,
|
| 581 |
+
"grad_norm": 1.8424692153930664,
|
| 582 |
+
"learning_rate": 2.9991008298059473e-05,
|
| 583 |
+
"loss": 0.5007,
|
| 584 |
+
"step": 650
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 14.666666666666666,
|
| 588 |
+
"grad_norm": 1.5401960611343384,
|
| 589 |
+
"learning_rate": 2.9990678388793924e-05,
|
| 590 |
+
"loss": 0.5318,
|
| 591 |
+
"step": 660
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 14.88888888888889,
|
| 595 |
+
"grad_norm": 1.2824598550796509,
|
| 596 |
+
"learning_rate": 2.999034253770242e-05,
|
| 597 |
+
"loss": 0.4575,
|
| 598 |
+
"step": 670
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 15.11111111111111,
|
| 602 |
+
"grad_norm": 2.5211098194122314,
|
| 603 |
+
"learning_rate": 2.9990000744918076e-05,
|
| 604 |
+
"loss": 0.449,
|
| 605 |
+
"step": 680
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 15.333333333333334,
|
| 609 |
+
"grad_norm": 1.6035919189453125,
|
| 610 |
+
"learning_rate": 2.9989653010576372e-05,
|
| 611 |
+
"loss": 0.4529,
|
| 612 |
+
"step": 690
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 15.555555555555555,
|
| 616 |
+
"grad_norm": 1.4720438718795776,
|
| 617 |
+
"learning_rate": 2.9989299334815138e-05,
|
| 618 |
+
"loss": 0.4804,
|
| 619 |
+
"step": 700
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 15.777777777777779,
|
| 623 |
+
"grad_norm": 2.241570472717285,
|
| 624 |
+
"learning_rate": 2.9988939717774558e-05,
|
| 625 |
+
"loss": 0.524,
|
| 626 |
+
"step": 710
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 16.0,
|
| 630 |
+
"grad_norm": 1.3463960886001587,
|
| 631 |
+
"learning_rate": 2.9988574159597174e-05,
|
| 632 |
+
"loss": 0.5105,
|
| 633 |
+
"step": 720
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 16.22222222222222,
|
| 637 |
+
"grad_norm": 2.1436588764190674,
|
| 638 |
+
"learning_rate": 2.9988202660427887e-05,
|
| 639 |
+
"loss": 0.4644,
|
| 640 |
+
"step": 730
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 16.444444444444443,
|
| 644 |
+
"grad_norm": 3.0679702758789062,
|
| 645 |
+
"learning_rate": 2.9987825220413937e-05,
|
| 646 |
+
"loss": 0.5349,
|
| 647 |
+
"step": 740
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 16.666666666666668,
|
| 651 |
+
"grad_norm": 1.908082127571106,
|
| 652 |
+
"learning_rate": 2.998744183970494e-05,
|
| 653 |
+
"loss": 0.4263,
|
| 654 |
+
"step": 750
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 16.666666666666668,
|
| 658 |
+
"eval_loss": 0.7214915752410889,
|
| 659 |
+
"eval_runtime": 0.4155,
|
| 660 |
+
"eval_samples_per_second": 24.069,
|
| 661 |
+
"eval_steps_per_second": 24.069,
|
| 662 |
+
"step": 750
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"Start_State_loss": 0.7391407489776611,
|
| 666 |
+
"Start_State_runtime": 0.4325,
|
| 667 |
+
"Start_State_samples_per_second": 23.123,
|
| 668 |
+
"Start_State_steps_per_second": 23.123,
|
| 669 |
+
"epoch": 16.666666666666668,
|
| 670 |
+
"step": 750
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"Raw_Model_loss": 0.7214915752410889,
|
| 674 |
+
"Raw_Model_runtime": 0.4148,
|
| 675 |
+
"Raw_Model_samples_per_second": 24.108,
|
| 676 |
+
"Raw_Model_steps_per_second": 24.108,
|
| 677 |
+
"epoch": 16.666666666666668,
|
| 678 |
+
"step": 750
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"SWA_loss": 0.7257974147796631,
|
| 682 |
+
"SWA_runtime": 0.4246,
|
| 683 |
+
"SWA_samples_per_second": 23.553,
|
| 684 |
+
"SWA_steps_per_second": 23.553,
|
| 685 |
+
"epoch": 16.666666666666668,
|
| 686 |
+
"step": 750
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"EMA_loss": 0.7391572594642639,
|
| 690 |
+
"EMA_runtime": 0.4233,
|
| 691 |
+
"EMA_samples_per_second": 23.622,
|
| 692 |
+
"EMA_steps_per_second": 23.622,
|
| 693 |
+
"epoch": 16.666666666666668,
|
| 694 |
+
"step": 750
|
| 695 |
}
|
| 696 |
],
|
| 697 |
"logging_steps": 10,
|
|
|
|
| 711 |
"attributes": {}
|
| 712 |
}
|
| 713 |
},
|
| 714 |
+
"total_flos": 7981049240027136.0,
|
| 715 |
"train_batch_size": 2,
|
| 716 |
"trial_name": null,
|
| 717 |
"trial_params": null
|