Training in progress, epoch 1, checkpoint
Browse files- last-checkpoint/adapter_model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +465 -3
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 45118424
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9566d2bb35b3efac00e6f024a3f58e76b62fe383437bf020ec3ff0105be7e256
|
| 3 |
size 45118424
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 23159290
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9bfbf91976fd2594364b459f383f8776bb71435cb782a16df2c7d5ab54cd529
|
| 3 |
size 23159290
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a430faf8aace51631e3c4ad9c29dbf3c7d22176b310e266c5f0988983044379
|
| 3 |
size 14960
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b957a0d6b826ae6bc7dd5d90a005564ed0359705eb81c7b131bf6ab2358321df
|
| 3 |
size 15024
|
last-checkpoint/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a211c4323f558171618d3684a051961a90e9d2fc00dd4c60917b3190ec01123f
|
| 3 |
size 15024
|
last-checkpoint/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8572c959a4561dbaa2f6e6906506e661a20c73b57d7f1bec98e41dbba87dd7e2
|
| 3 |
size 15024
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab1dd6570c09bbf6fb7ec228c23e5651edd0d137b28979a40f037bdfd8671fa8
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -469,6 +469,468 @@
|
|
| 469 |
"learning_rate": 0.00015954597044352234,
|
| 470 |
"loss": 0.8848,
|
| 471 |
"step": 66
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 472 |
}
|
| 473 |
],
|
| 474 |
"logging_steps": 1,
|
|
@@ -488,7 +950,7 @@
|
|
| 488 |
"attributes": {}
|
| 489 |
}
|
| 490 |
},
|
| 491 |
-
"total_flos":
|
| 492 |
"train_batch_size": 18,
|
| 493 |
"trial_name": null,
|
| 494 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.9899497487437185,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 132,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 469 |
"learning_rate": 0.00015954597044352234,
|
| 470 |
"loss": 0.8848,
|
| 471 |
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.0100502512562815,
|
| 475 |
+
"grad_norm": 0.39075490832328796,
|
| 476 |
+
"learning_rate": 0.00015832281562840856,
|
| 477 |
+
"loss": 1.0625,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 1.0251256281407035,
|
| 482 |
+
"grad_norm": 0.42702537775039673,
|
| 483 |
+
"learning_rate": 0.00015708698899239172,
|
| 484 |
+
"loss": 1.1133,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 1.0402010050251256,
|
| 489 |
+
"grad_norm": 0.4092056155204773,
|
| 490 |
+
"learning_rate": 0.00015583881460958868,
|
| 491 |
+
"loss": 1.0902,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 1.0552763819095476,
|
| 496 |
+
"grad_norm": 0.37982651591300964,
|
| 497 |
+
"learning_rate": 0.0001545786197920989,
|
| 498 |
+
"loss": 1.0461,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 1.07035175879397,
|
| 503 |
+
"grad_norm": 0.3565632402896881,
|
| 504 |
+
"learning_rate": 0.0001533067350041725,
|
| 505 |
+
"loss": 1.0392,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.085427135678392,
|
| 510 |
+
"grad_norm": 0.309384822845459,
|
| 511 |
+
"learning_rate": 0.00015202349377555166,
|
| 512 |
+
"loss": 0.9599,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.100502512562814,
|
| 517 |
+
"grad_norm": 0.3414682149887085,
|
| 518 |
+
"learning_rate": 0.0001507292326140085,
|
| 519 |
+
"loss": 0.9381,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.1155778894472361,
|
| 524 |
+
"grad_norm": 0.36480242013931274,
|
| 525 |
+
"learning_rate": 0.00014942429091710141,
|
| 526 |
+
"loss": 0.8947,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.1306532663316582,
|
| 531 |
+
"grad_norm": 0.42747026681900024,
|
| 532 |
+
"learning_rate": 0.00014810901088317414,
|
| 533 |
+
"loss": 0.8695,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.1457286432160805,
|
| 538 |
+
"grad_norm": 0.46534058451652527,
|
| 539 |
+
"learning_rate": 0.00014678373742162007,
|
| 540 |
+
"loss": 0.9033,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.1608040201005025,
|
| 545 |
+
"grad_norm": 0.48176416754722595,
|
| 546 |
+
"learning_rate": 0.00014544881806243583,
|
| 547 |
+
"loss": 0.8566,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.1758793969849246,
|
| 552 |
+
"grad_norm": 0.4470821022987366,
|
| 553 |
+
"learning_rate": 0.00014410460286508762,
|
| 554 |
+
"loss": 0.81,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.1909547738693467,
|
| 559 |
+
"grad_norm": 0.4553522765636444,
|
| 560 |
+
"learning_rate": 0.0001427514443267139,
|
| 561 |
+
"loss": 0.8016,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.2060301507537687,
|
| 566 |
+
"grad_norm": 0.37652871012687683,
|
| 567 |
+
"learning_rate": 0.0001413896972896894,
|
| 568 |
+
"loss": 1.1188,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.221105527638191,
|
| 573 |
+
"grad_norm": 0.36291682720184326,
|
| 574 |
+
"learning_rate": 0.0001400197188485739,
|
| 575 |
+
"loss": 1.109,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.236180904522613,
|
| 580 |
+
"grad_norm": 0.43163785338401794,
|
| 581 |
+
"learning_rate": 0.00013864186825646995,
|
| 582 |
+
"loss": 1.0842,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 1.2512562814070352,
|
| 587 |
+
"grad_norm": 0.4752475619316101,
|
| 588 |
+
"learning_rate": 0.00013725650683081556,
|
| 589 |
+
"loss": 1.0216,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.2663316582914572,
|
| 594 |
+
"grad_norm": 0.47904953360557556,
|
| 595 |
+
"learning_rate": 0.00013586399785863454,
|
| 596 |
+
"loss": 0.9856,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.2814070351758793,
|
| 601 |
+
"grad_norm": 0.4482368230819702,
|
| 602 |
+
"learning_rate": 0.0001344647065012709,
|
| 603 |
+
"loss": 0.962,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.2964824120603016,
|
| 608 |
+
"grad_norm": 0.40822041034698486,
|
| 609 |
+
"learning_rate": 0.0001330589996986315,
|
| 610 |
+
"loss": 0.8775,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.3115577889447236,
|
| 615 |
+
"grad_norm": 0.39425739645957947,
|
| 616 |
+
"learning_rate": 0.00013164724607296285,
|
| 617 |
+
"loss": 0.8851,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.3266331658291457,
|
| 622 |
+
"grad_norm": 0.40144336223602295,
|
| 623 |
+
"learning_rate": 0.00013022981583218565,
|
| 624 |
+
"loss": 0.8532,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.3417085427135678,
|
| 629 |
+
"grad_norm": 0.4694520831108093,
|
| 630 |
+
"learning_rate": 0.00012880708067281477,
|
| 631 |
+
"loss": 0.8961,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.3567839195979898,
|
| 636 |
+
"grad_norm": 0.467843234539032,
|
| 637 |
+
"learning_rate": 0.00012737941368248792,
|
| 638 |
+
"loss": 0.7872,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.3718592964824121,
|
| 643 |
+
"grad_norm": 0.5175732374191284,
|
| 644 |
+
"learning_rate": 0.00012594718924213008,
|
| 645 |
+
"loss": 0.7416,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.3869346733668342,
|
| 650 |
+
"grad_norm": 0.44360604882240295,
|
| 651 |
+
"learning_rate": 0.00012451078292777837,
|
| 652 |
+
"loss": 1.0284,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.4020100502512562,
|
| 657 |
+
"grad_norm": 0.4175772964954376,
|
| 658 |
+
"learning_rate": 0.00012307057141209415,
|
| 659 |
+
"loss": 1.1058,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.4170854271356783,
|
| 664 |
+
"grad_norm": 0.36412638425827026,
|
| 665 |
+
"learning_rate": 0.00012162693236558658,
|
| 666 |
+
"loss": 1.071,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.4321608040201004,
|
| 671 |
+
"grad_norm": 0.35895222425460815,
|
| 672 |
+
"learning_rate": 0.0001201802443575756,
|
| 673 |
+
"loss": 1.0445,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.4472361809045227,
|
| 678 |
+
"grad_norm": 0.41202953457832336,
|
| 679 |
+
"learning_rate": 0.00011873088675691835,
|
| 680 |
+
"loss": 0.9895,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.4623115577889447,
|
| 685 |
+
"grad_norm": 0.49337854981422424,
|
| 686 |
+
"learning_rate": 0.0001172792396325264,
|
| 687 |
+
"loss": 1.0112,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.4773869346733668,
|
| 692 |
+
"grad_norm": 0.45489662885665894,
|
| 693 |
+
"learning_rate": 0.00011582568365369924,
|
| 694 |
+
"loss": 0.9251,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 1.492462311557789,
|
| 699 |
+
"grad_norm": 0.476253479719162,
|
| 700 |
+
"learning_rate": 0.00011437059999030035,
|
| 701 |
+
"loss": 0.9277,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.507537688442211,
|
| 706 |
+
"grad_norm": 0.37511464953422546,
|
| 707 |
+
"learning_rate": 0.00011291437021280205,
|
| 708 |
+
"loss": 0.8723,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.5226130653266332,
|
| 713 |
+
"grad_norm": 0.4103985130786896,
|
| 714 |
+
"learning_rate": 0.00011145737619222516,
|
| 715 |
+
"loss": 0.8183,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 1.5376884422110553,
|
| 720 |
+
"grad_norm": 0.4598234295845032,
|
| 721 |
+
"learning_rate": 0.00011000000000000002,
|
| 722 |
+
"loss": 0.8668,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.5527638190954773,
|
| 727 |
+
"grad_norm": 0.45140963792800903,
|
| 728 |
+
"learning_rate": 0.00010854262380777486,
|
| 729 |
+
"loss": 0.7755,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.5678391959798996,
|
| 734 |
+
"grad_norm": 0.5093435645103455,
|
| 735 |
+
"learning_rate": 0.000107085629787198,
|
| 736 |
+
"loss": 0.7673,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.5829145728643215,
|
| 741 |
+
"grad_norm": 0.360904723405838,
|
| 742 |
+
"learning_rate": 0.0001056294000096997,
|
| 743 |
+
"loss": 1.1205,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.5979899497487438,
|
| 748 |
+
"grad_norm": 0.377037912607193,
|
| 749 |
+
"learning_rate": 0.0001041743163463008,
|
| 750 |
+
"loss": 1.0803,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.6130653266331658,
|
| 755 |
+
"grad_norm": 0.35898640751838684,
|
| 756 |
+
"learning_rate": 0.00010272076036747365,
|
| 757 |
+
"loss": 1.0416,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.6281407035175879,
|
| 762 |
+
"grad_norm": 0.36311081051826477,
|
| 763 |
+
"learning_rate": 0.00010126911324308168,
|
| 764 |
+
"loss": 0.9846,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.6432160804020102,
|
| 769 |
+
"grad_norm": 0.3633027970790863,
|
| 770 |
+
"learning_rate": 9.981975564242443e-05,
|
| 771 |
+
"loss": 0.9981,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 1.658291457286432,
|
| 776 |
+
"grad_norm": 0.3827294409275055,
|
| 777 |
+
"learning_rate": 9.837306763441345e-05,
|
| 778 |
+
"loss": 0.9411,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.6733668341708543,
|
| 783 |
+
"grad_norm": 0.39575091004371643,
|
| 784 |
+
"learning_rate": 9.692942858790591e-05,
|
| 785 |
+
"loss": 0.9055,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.6884422110552764,
|
| 790 |
+
"grad_norm": 0.43744927644729614,
|
| 791 |
+
"learning_rate": 9.548921707222163e-05,
|
| 792 |
+
"loss": 0.8801,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.7035175879396984,
|
| 797 |
+
"grad_norm": 0.4338492453098297,
|
| 798 |
+
"learning_rate": 9.405281075786995e-05,
|
| 799 |
+
"loss": 0.8653,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 1.7185929648241207,
|
| 804 |
+
"grad_norm": 0.39823731780052185,
|
| 805 |
+
"learning_rate": 9.26205863175121e-05,
|
| 806 |
+
"loss": 0.8548,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.7336683417085426,
|
| 811 |
+
"grad_norm": 0.42383068799972534,
|
| 812 |
+
"learning_rate": 9.119291932718525e-05,
|
| 813 |
+
"loss": 0.7412,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 1.7487437185929648,
|
| 818 |
+
"grad_norm": 0.46130019426345825,
|
| 819 |
+
"learning_rate": 8.97701841678144e-05,
|
| 820 |
+
"loss": 0.6798,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 1.763819095477387,
|
| 825 |
+
"grad_norm": 0.3968804180622101,
|
| 826 |
+
"learning_rate": 8.835275392703721e-05,
|
| 827 |
+
"loss": 0.9816,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 1.778894472361809,
|
| 832 |
+
"grad_norm": 0.37212514877319336,
|
| 833 |
+
"learning_rate": 8.694100030136849e-05,
|
| 834 |
+
"loss": 1.0961,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 1.7939698492462313,
|
| 839 |
+
"grad_norm": 0.35753509402275085,
|
| 840 |
+
"learning_rate": 8.553529349872916e-05,
|
| 841 |
+
"loss": 1.0364,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 1.809045226130653,
|
| 846 |
+
"grad_norm": 0.3995687961578369,
|
| 847 |
+
"learning_rate": 8.413600214136548e-05,
|
| 848 |
+
"loss": 1.0853,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.8241206030150754,
|
| 853 |
+
"grad_norm": 0.35571298003196716,
|
| 854 |
+
"learning_rate": 8.274349316918446e-05,
|
| 855 |
+
"loss": 0.9598,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 1.8391959798994975,
|
| 860 |
+
"grad_norm": 0.36723199486732483,
|
| 861 |
+
"learning_rate": 8.135813174353008e-05,
|
| 862 |
+
"loss": 0.9179,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 1.8542713567839195,
|
| 867 |
+
"grad_norm": 0.3806018531322479,
|
| 868 |
+
"learning_rate": 7.998028115142617e-05,
|
| 869 |
+
"loss": 0.9019,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 1.8693467336683418,
|
| 874 |
+
"grad_norm": 0.413316547870636,
|
| 875 |
+
"learning_rate": 7.86103027103106e-05,
|
| 876 |
+
"loss": 0.8889,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 1.8844221105527639,
|
| 881 |
+
"grad_norm": 0.4195359945297241,
|
| 882 |
+
"learning_rate": 7.724855567328613e-05,
|
| 883 |
+
"loss": 0.8677,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 1.899497487437186,
|
| 888 |
+
"grad_norm": 0.42447102069854736,
|
| 889 |
+
"learning_rate": 7.58953971349124e-05,
|
| 890 |
+
"loss": 0.8344,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 1.914572864321608,
|
| 895 |
+
"grad_norm": 0.42873820662498474,
|
| 896 |
+
"learning_rate": 7.455118193756419e-05,
|
| 897 |
+
"loss": 0.8165,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 1.92964824120603,
|
| 902 |
+
"grad_norm": 0.43426066637039185,
|
| 903 |
+
"learning_rate": 7.321626257837996e-05,
|
| 904 |
+
"loss": 0.7341,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 1.9447236180904524,
|
| 909 |
+
"grad_norm": 0.4637242257595062,
|
| 910 |
+
"learning_rate": 7.189098911682592e-05,
|
| 911 |
+
"loss": 0.7844,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 1.9597989949748744,
|
| 916 |
+
"grad_norm": 0.3749074637889862,
|
| 917 |
+
"learning_rate": 7.05757090828986e-05,
|
| 918 |
+
"loss": 1.0112,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 1.9748743718592965,
|
| 923 |
+
"grad_norm": 0.3993157744407654,
|
| 924 |
+
"learning_rate": 6.927076738599152e-05,
|
| 925 |
+
"loss": 0.9289,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 1.9899497487437185,
|
| 930 |
+
"grad_norm": 0.44096246361732483,
|
| 931 |
+
"learning_rate": 6.797650622444836e-05,
|
| 932 |
+
"loss": 0.8243,
|
| 933 |
+
"step": 132
|
| 934 |
}
|
| 935 |
],
|
| 936 |
"logging_steps": 1,
|
|
|
|
| 950 |
"attributes": {}
|
| 951 |
}
|
| 952 |
},
|
| 953 |
+
"total_flos": 3.466382156266209e+17,
|
| 954 |
"train_batch_size": 18,
|
| 955 |
"trial_name": null,
|
| 956 |
"trial_params": null
|