Commit
•
a326a23
1
Parent(s):
5fbfc2c
Training in progress, step 19000, checkpoint
Browse files
last-checkpoint/adapter_config.json
CHANGED
|
@@ -20,13 +20,13 @@
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
-
"
|
| 24 |
-
"gate_proj",
|
| 25 |
"o_proj",
|
| 26 |
"k_proj",
|
|
|
|
|
|
|
| 27 |
"up_proj",
|
| 28 |
-
"v_proj"
|
| 29 |
-
"q_proj"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
|
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
+
"q_proj",
|
|
|
|
| 24 |
"o_proj",
|
| 25 |
"k_proj",
|
| 26 |
+
"gate_proj",
|
| 27 |
+
"down_proj",
|
| 28 |
"up_proj",
|
| 29 |
+
"v_proj"
|
|
|
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 167832240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30377e3553033d932e69daa7064c259e8a7335e5cc0b78f6a1f4f648bae4b97e
|
| 3 |
size 167832240
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:727033a6eb5dc35337334fe86877b4a8995db5404205b07aeda22261d1e1f288
|
| 3 |
+
size 85736914
|
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 sha256:6b7de94d4e3bf0d0cab47bcde24f41cd7eb97ed0885fd609023fab02c6a16228
|
| 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 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf318569a9b4769e81e4790eccd85435a6e6935dc6ee58b1ecc55958c1b71bd0
|
| 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": 0.
|
| 5 |
"eval_steps": 2000,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -413,14 +413,273 @@
|
|
| 413 |
"learning_rate": 1.9999853411898932e-05,
|
| 414 |
"loss": 1.5097,
|
| 415 |
"step": 11600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 416 |
}
|
| 417 |
],
|
| 418 |
"logging_steps": 200,
|
| 419 |
-
"max_steps":
|
| 420 |
"num_input_tokens_seen": 0,
|
| 421 |
"num_train_epochs": 5,
|
| 422 |
"save_steps": 200,
|
| 423 |
-
"total_flos":
|
| 424 |
"train_batch_size": 1,
|
| 425 |
"trial_name": null,
|
| 426 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.028259196323329825,
|
| 5 |
"eval_steps": 2000,
|
| 6 |
+
"global_step": 19000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 413 |
"learning_rate": 1.9999853411898932e-05,
|
| 414 |
"loss": 1.5097,
|
| 415 |
"step": 11600
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.02,
|
| 419 |
+
"grad_norm": 3.229198455810547,
|
| 420 |
+
"learning_rate": 1.999939333873553e-05,
|
| 421 |
+
"loss": 1.5721,
|
| 422 |
+
"step": 11800
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.02,
|
| 426 |
+
"grad_norm": 1.2855397462844849,
|
| 427 |
+
"learning_rate": 1.9999372576820398e-05,
|
| 428 |
+
"loss": 1.5382,
|
| 429 |
+
"step": 12000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.02,
|
| 433 |
+
"grad_norm": 1.536872148513794,
|
| 434 |
+
"learning_rate": 1.9999351465598642e-05,
|
| 435 |
+
"loss": 1.5964,
|
| 436 |
+
"step": 12200
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.02,
|
| 440 |
+
"grad_norm": 2.0981087684631348,
|
| 441 |
+
"learning_rate": 1.9999330005070992e-05,
|
| 442 |
+
"loss": 1.5269,
|
| 443 |
+
"step": 12400
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.02,
|
| 447 |
+
"grad_norm": 2.213561773300171,
|
| 448 |
+
"learning_rate": 1.99993081952382e-05,
|
| 449 |
+
"loss": 1.488,
|
| 450 |
+
"step": 12600
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.02,
|
| 454 |
+
"grad_norm": 2.3960020542144775,
|
| 455 |
+
"learning_rate": 1.999928603610103e-05,
|
| 456 |
+
"loss": 1.5714,
|
| 457 |
+
"step": 12800
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.02,
|
| 461 |
+
"grad_norm": 2.198500394821167,
|
| 462 |
+
"learning_rate": 1.9999263641071352e-05,
|
| 463 |
+
"loss": 1.5587,
|
| 464 |
+
"step": 13000
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.02,
|
| 468 |
+
"grad_norm": 2.4841859340667725,
|
| 469 |
+
"learning_rate": 1.9999240785074275e-05,
|
| 470 |
+
"loss": 1.5417,
|
| 471 |
+
"step": 13200
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.02,
|
| 475 |
+
"grad_norm": 2.9682819843292236,
|
| 476 |
+
"learning_rate": 1.999921757977517e-05,
|
| 477 |
+
"loss": 1.578,
|
| 478 |
+
"step": 13400
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.02,
|
| 482 |
+
"grad_norm": 2.8368330001831055,
|
| 483 |
+
"learning_rate": 1.999919402517485e-05,
|
| 484 |
+
"loss": 1.5703,
|
| 485 |
+
"step": 13600
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.02,
|
| 489 |
+
"grad_norm": 3.0925166606903076,
|
| 490 |
+
"learning_rate": 1.9999170121274143e-05,
|
| 491 |
+
"loss": 1.5163,
|
| 492 |
+
"step": 13800
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.02,
|
| 496 |
+
"grad_norm": 2.2362563610076904,
|
| 497 |
+
"learning_rate": 1.999914586807388e-05,
|
| 498 |
+
"loss": 1.6078,
|
| 499 |
+
"step": 14000
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.02,
|
| 503 |
+
"grad_norm": 3.019454002380371,
|
| 504 |
+
"learning_rate": 1.9999121265574902e-05,
|
| 505 |
+
"loss": 1.5317,
|
| 506 |
+
"step": 14200
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.02,
|
| 510 |
+
"grad_norm": 2.67069411277771,
|
| 511 |
+
"learning_rate": 1.9999096313778082e-05,
|
| 512 |
+
"loss": 1.529,
|
| 513 |
+
"step": 14400
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.02,
|
| 517 |
+
"grad_norm": 2.8095571994781494,
|
| 518 |
+
"learning_rate": 1.9999071012684285e-05,
|
| 519 |
+
"loss": 1.557,
|
| 520 |
+
"step": 14600
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.02,
|
| 524 |
+
"grad_norm": 2.3300442695617676,
|
| 525 |
+
"learning_rate": 1.9999045362294388e-05,
|
| 526 |
+
"loss": 1.5554,
|
| 527 |
+
"step": 14800
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.02,
|
| 531 |
+
"grad_norm": 2.160933256149292,
|
| 532 |
+
"learning_rate": 1.9999019362609297e-05,
|
| 533 |
+
"loss": 1.528,
|
| 534 |
+
"step": 15000
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.02,
|
| 538 |
+
"grad_norm": 1.6309542655944824,
|
| 539 |
+
"learning_rate": 1.999899301362992e-05,
|
| 540 |
+
"loss": 1.5344,
|
| 541 |
+
"step": 15200
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.02,
|
| 545 |
+
"grad_norm": 3.1774258613586426,
|
| 546 |
+
"learning_rate": 1.9998966315357173e-05,
|
| 547 |
+
"loss": 1.5661,
|
| 548 |
+
"step": 15400
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.02,
|
| 552 |
+
"grad_norm": 2.8362374305725098,
|
| 553 |
+
"learning_rate": 1.9998939267791986e-05,
|
| 554 |
+
"loss": 1.5404,
|
| 555 |
+
"step": 15600
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.02,
|
| 559 |
+
"grad_norm": 1.6643764972686768,
|
| 560 |
+
"learning_rate": 1.999891187093531e-05,
|
| 561 |
+
"loss": 1.562,
|
| 562 |
+
"step": 15800
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.02,
|
| 566 |
+
"grad_norm": 2.519455671310425,
|
| 567 |
+
"learning_rate": 1.99988841247881e-05,
|
| 568 |
+
"loss": 1.5468,
|
| 569 |
+
"step": 16000
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.02,
|
| 573 |
+
"grad_norm": 1.8681560754776,
|
| 574 |
+
"learning_rate": 1.9998856029351327e-05,
|
| 575 |
+
"loss": 1.501,
|
| 576 |
+
"step": 16200
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.02,
|
| 580 |
+
"grad_norm": 1.5082764625549316,
|
| 581 |
+
"learning_rate": 1.999882758462597e-05,
|
| 582 |
+
"loss": 1.5632,
|
| 583 |
+
"step": 16400
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.02,
|
| 587 |
+
"grad_norm": 1.8632557392120361,
|
| 588 |
+
"learning_rate": 1.9998798790613018e-05,
|
| 589 |
+
"loss": 1.5509,
|
| 590 |
+
"step": 16600
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.02,
|
| 594 |
+
"grad_norm": 3.0881147384643555,
|
| 595 |
+
"learning_rate": 1.999876964731349e-05,
|
| 596 |
+
"loss": 1.5277,
|
| 597 |
+
"step": 16800
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.03,
|
| 601 |
+
"grad_norm": 1.9005630016326904,
|
| 602 |
+
"learning_rate": 1.9998740303060157e-05,
|
| 603 |
+
"loss": 1.5542,
|
| 604 |
+
"step": 17000
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.03,
|
| 608 |
+
"grad_norm": 1.4960647821426392,
|
| 609 |
+
"learning_rate": 1.9998710462936946e-05,
|
| 610 |
+
"loss": 1.5781,
|
| 611 |
+
"step": 17200
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.03,
|
| 615 |
+
"grad_norm": 2.5842814445495605,
|
| 616 |
+
"learning_rate": 1.9998680273530233e-05,
|
| 617 |
+
"loss": 1.5535,
|
| 618 |
+
"step": 17400
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.03,
|
| 622 |
+
"grad_norm": 2.9667937755584717,
|
| 623 |
+
"learning_rate": 1.9998649734841075e-05,
|
| 624 |
+
"loss": 1.5764,
|
| 625 |
+
"step": 17600
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.03,
|
| 629 |
+
"grad_norm": 2.2704834938049316,
|
| 630 |
+
"learning_rate": 1.9998618846870542e-05,
|
| 631 |
+
"loss": 1.55,
|
| 632 |
+
"step": 17800
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.03,
|
| 636 |
+
"grad_norm": 2.67142391204834,
|
| 637 |
+
"learning_rate": 1.9998587609619712e-05,
|
| 638 |
+
"loss": 1.5648,
|
| 639 |
+
"step": 18000
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.03,
|
| 643 |
+
"grad_norm": 2.281129837036133,
|
| 644 |
+
"learning_rate": 1.9998556023089672e-05,
|
| 645 |
+
"loss": 1.5405,
|
| 646 |
+
"step": 18200
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.03,
|
| 650 |
+
"grad_norm": 2.508354425430298,
|
| 651 |
+
"learning_rate": 1.999852408728153e-05,
|
| 652 |
+
"loss": 1.5574,
|
| 653 |
+
"step": 18400
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.03,
|
| 657 |
+
"grad_norm": 2.8000833988189697,
|
| 658 |
+
"learning_rate": 1.99984918021964e-05,
|
| 659 |
+
"loss": 1.5638,
|
| 660 |
+
"step": 18600
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.03,
|
| 664 |
+
"grad_norm": 3.3880839347839355,
|
| 665 |
+
"learning_rate": 1.999845916783541e-05,
|
| 666 |
+
"loss": 1.553,
|
| 667 |
+
"step": 18800
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.03,
|
| 671 |
+
"grad_norm": 2.8427979946136475,
|
| 672 |
+
"learning_rate": 1.9998426349986698e-05,
|
| 673 |
+
"loss": 1.5367,
|
| 674 |
+
"step": 19000
|
| 675 |
}
|
| 676 |
],
|
| 677 |
"logging_steps": 200,
|
| 678 |
+
"max_steps": 3361735,
|
| 679 |
"num_input_tokens_seen": 0,
|
| 680 |
"num_train_epochs": 5,
|
| 681 |
"save_steps": 200,
|
| 682 |
+
"total_flos": 3.4393054952298086e+17,
|
| 683 |
"train_batch_size": 1,
|
| 684 |
"trial_name": null,
|
| 685 |
"trial_params": null
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4920
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc9e75826f834526adf57daa4ee7a58f88bf2ec9679f7599af2037d01589eb4f
|
| 3 |
size 4920
|