Training in progress, step 44, checkpoint
Browse files
last-checkpoint/adapter_config.json
CHANGED
|
@@ -20,13 +20,13 @@
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
-
"q_proj",
|
| 24 |
-
"k_proj",
|
| 25 |
-
"v_proj",
|
| 26 |
"up_proj",
|
|
|
|
| 27 |
"o_proj",
|
| 28 |
-
"
|
| 29 |
-
"gate_proj"
|
|
|
|
|
|
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
|
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
|
|
|
|
|
|
|
|
|
| 23 |
"up_proj",
|
| 24 |
+
"q_proj",
|
| 25 |
"o_proj",
|
| 26 |
+
"v_proj",
|
| 27 |
+
"gate_proj",
|
| 28 |
+
"k_proj",
|
| 29 |
+
"down_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 83945296
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:349c41609a51e6cfc6896a2a5d1a67153c68f9e2b7976427d560cec1ef2695d0
|
| 3 |
size 83945296
|
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 sha256:66a5843d74545eb236796350e0ece8c200e91256593c92b31b5d53bd3686a8f4
|
| 3 |
+
size 43706258
|
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 sha256:5f6daa0fed03c921127a64c255f462e66919bc76a6e6ba1e9093cf71d1068c6f
|
| 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": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -511,6 +511,294 @@
|
|
| 511 |
"rewards/margins": 0.019869212061166763,
|
| 512 |
"rewards/rejected": -0.09125552326440811,
|
| 513 |
"step": 28
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 514 |
}
|
| 515 |
],
|
| 516 |
"logging_steps": 1,
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.897100987575661,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 44,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 511 |
"rewards/margins": 0.019869212061166763,
|
| 512 |
"rewards/rejected": -0.09125552326440811,
|
| 513 |
"step": 28
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.5912711054475948,
|
| 517 |
+
"grad_norm": 1.6056082248687744,
|
| 518 |
+
"learning_rate": 5.128205128205128e-05,
|
| 519 |
+
"log_odds_chosen": 0.5487304925918579,
|
| 520 |
+
"log_odds_ratio": -0.478320449590683,
|
| 521 |
+
"logits/chosen": -2.2418763637542725,
|
| 522 |
+
"logits/rejected": -2.2638566493988037,
|
| 523 |
+
"logps/chosen": -0.7001346349716187,
|
| 524 |
+
"logps/rejected": -1.0050172805786133,
|
| 525 |
+
"loss": 0.9538,
|
| 526 |
+
"nll_loss": 0.9059388041496277,
|
| 527 |
+
"rewards/accuracies": 0.921875,
|
| 528 |
+
"rewards/chosen": -0.07001346349716187,
|
| 529 |
+
"rewards/margins": 0.030488261952996254,
|
| 530 |
+
"rewards/rejected": -0.10050173103809357,
|
| 531 |
+
"step": 29
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.6116597642561326,
|
| 535 |
+
"grad_norm": 2.707125663757324,
|
| 536 |
+
"learning_rate": 4.871794871794872e-05,
|
| 537 |
+
"log_odds_chosen": 0.433153361082077,
|
| 538 |
+
"log_odds_ratio": -0.5276967883110046,
|
| 539 |
+
"logits/chosen": -2.2189157009124756,
|
| 540 |
+
"logits/rejected": -2.228149890899658,
|
| 541 |
+
"logps/chosen": -0.6423375606536865,
|
| 542 |
+
"logps/rejected": -0.8684220910072327,
|
| 543 |
+
"loss": 0.943,
|
| 544 |
+
"nll_loss": 0.89023357629776,
|
| 545 |
+
"rewards/accuracies": 0.8125,
|
| 546 |
+
"rewards/chosen": -0.06423375755548477,
|
| 547 |
+
"rewards/margins": 0.022608455270528793,
|
| 548 |
+
"rewards/rejected": -0.08684220910072327,
|
| 549 |
+
"step": 30
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.6320484230646702,
|
| 553 |
+
"grad_norm": 3.1514434814453125,
|
| 554 |
+
"learning_rate": 4.615384615384616e-05,
|
| 555 |
+
"log_odds_chosen": 0.3669428527355194,
|
| 556 |
+
"log_odds_ratio": -0.5465207695960999,
|
| 557 |
+
"logits/chosen": -2.243276357650757,
|
| 558 |
+
"logits/rejected": -2.231745719909668,
|
| 559 |
+
"logps/chosen": -0.7233006954193115,
|
| 560 |
+
"logps/rejected": -0.9113064408302307,
|
| 561 |
+
"loss": 1.0016,
|
| 562 |
+
"nll_loss": 0.9469515681266785,
|
| 563 |
+
"rewards/accuracies": 0.8125,
|
| 564 |
+
"rewards/chosen": -0.07233007252216339,
|
| 565 |
+
"rewards/margins": 0.018800577148795128,
|
| 566 |
+
"rewards/rejected": -0.09113065153360367,
|
| 567 |
+
"step": 31
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.652437081873208,
|
| 571 |
+
"grad_norm": 2.5206167697906494,
|
| 572 |
+
"learning_rate": 4.358974358974359e-05,
|
| 573 |
+
"log_odds_chosen": 0.5872430205345154,
|
| 574 |
+
"log_odds_ratio": -0.46654394268989563,
|
| 575 |
+
"logits/chosen": -2.2469942569732666,
|
| 576 |
+
"logits/rejected": -2.269362211227417,
|
| 577 |
+
"logps/chosen": -0.6239035725593567,
|
| 578 |
+
"logps/rejected": -0.9376953840255737,
|
| 579 |
+
"loss": 0.9061,
|
| 580 |
+
"nll_loss": 0.8594872951507568,
|
| 581 |
+
"rewards/accuracies": 0.875,
|
| 582 |
+
"rewards/chosen": -0.06239035725593567,
|
| 583 |
+
"rewards/margins": 0.03137918934226036,
|
| 584 |
+
"rewards/rejected": -0.09376954287290573,
|
| 585 |
+
"step": 32
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.6728257406817458,
|
| 589 |
+
"grad_norm": 1.3284610509872437,
|
| 590 |
+
"learning_rate": 4.1025641025641023e-05,
|
| 591 |
+
"log_odds_chosen": 0.5279171466827393,
|
| 592 |
+
"log_odds_ratio": -0.49398207664489746,
|
| 593 |
+
"logits/chosen": -2.263728618621826,
|
| 594 |
+
"logits/rejected": -2.288696050643921,
|
| 595 |
+
"logps/chosen": -0.6505022644996643,
|
| 596 |
+
"logps/rejected": -0.9282124042510986,
|
| 597 |
+
"loss": 0.9288,
|
| 598 |
+
"nll_loss": 0.8793907761573792,
|
| 599 |
+
"rewards/accuracies": 0.890625,
|
| 600 |
+
"rewards/chosen": -0.06505022943019867,
|
| 601 |
+
"rewards/margins": 0.027771014720201492,
|
| 602 |
+
"rewards/rejected": -0.09282123297452927,
|
| 603 |
+
"step": 33
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.6932143994902835,
|
| 607 |
+
"grad_norm": 1.2634799480438232,
|
| 608 |
+
"learning_rate": 3.846153846153846e-05,
|
| 609 |
+
"log_odds_chosen": 0.5196709036827087,
|
| 610 |
+
"log_odds_ratio": -0.5028817653656006,
|
| 611 |
+
"logits/chosen": -2.3093760013580322,
|
| 612 |
+
"logits/rejected": -2.3152754306793213,
|
| 613 |
+
"logps/chosen": -0.6717790365219116,
|
| 614 |
+
"logps/rejected": -0.9456109404563904,
|
| 615 |
+
"loss": 0.9413,
|
| 616 |
+
"nll_loss": 0.8909698724746704,
|
| 617 |
+
"rewards/accuracies": 0.796875,
|
| 618 |
+
"rewards/chosen": -0.0671778991818428,
|
| 619 |
+
"rewards/margins": 0.027383197098970413,
|
| 620 |
+
"rewards/rejected": -0.09456109255552292,
|
| 621 |
+
"step": 34
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.7136030582988213,
|
| 625 |
+
"grad_norm": 1.2822017669677734,
|
| 626 |
+
"learning_rate": 3.58974358974359e-05,
|
| 627 |
+
"log_odds_chosen": 0.44004446268081665,
|
| 628 |
+
"log_odds_ratio": -0.53327876329422,
|
| 629 |
+
"logits/chosen": -2.3234097957611084,
|
| 630 |
+
"logits/rejected": -2.319546937942505,
|
| 631 |
+
"logps/chosen": -0.7039386630058289,
|
| 632 |
+
"logps/rejected": -0.9365054965019226,
|
| 633 |
+
"loss": 0.9674,
|
| 634 |
+
"nll_loss": 0.9140487909317017,
|
| 635 |
+
"rewards/accuracies": 0.796875,
|
| 636 |
+
"rewards/chosen": -0.070393867790699,
|
| 637 |
+
"rewards/margins": 0.023256685584783554,
|
| 638 |
+
"rewards/rejected": -0.09365054965019226,
|
| 639 |
+
"step": 35
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.733991717107359,
|
| 643 |
+
"grad_norm": 1.3868314027786255,
|
| 644 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 645 |
+
"log_odds_chosen": 0.40167126059532166,
|
| 646 |
+
"log_odds_ratio": -0.5467191338539124,
|
| 647 |
+
"logits/chosen": -2.3325843811035156,
|
| 648 |
+
"logits/rejected": -2.3239898681640625,
|
| 649 |
+
"logps/chosen": -0.7655161619186401,
|
| 650 |
+
"logps/rejected": -0.9702532291412354,
|
| 651 |
+
"loss": 0.9815,
|
| 652 |
+
"nll_loss": 0.9267975091934204,
|
| 653 |
+
"rewards/accuracies": 0.765625,
|
| 654 |
+
"rewards/chosen": -0.07655161619186401,
|
| 655 |
+
"rewards/margins": 0.02047371119260788,
|
| 656 |
+
"rewards/rejected": -0.0970253199338913,
|
| 657 |
+
"step": 36
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.7543803759158968,
|
| 661 |
+
"grad_norm": 1.338576078414917,
|
| 662 |
+
"learning_rate": 3.0769230769230774e-05,
|
| 663 |
+
"log_odds_chosen": 0.46663999557495117,
|
| 664 |
+
"log_odds_ratio": -0.5116292834281921,
|
| 665 |
+
"logits/chosen": -2.358604907989502,
|
| 666 |
+
"logits/rejected": -2.366859197616577,
|
| 667 |
+
"logps/chosen": -0.6805034875869751,
|
| 668 |
+
"logps/rejected": -0.9220788478851318,
|
| 669 |
+
"loss": 0.9614,
|
| 670 |
+
"nll_loss": 0.9102513790130615,
|
| 671 |
+
"rewards/accuracies": 0.84375,
|
| 672 |
+
"rewards/chosen": -0.06805035471916199,
|
| 673 |
+
"rewards/margins": 0.024157537147402763,
|
| 674 |
+
"rewards/rejected": -0.0922078862786293,
|
| 675 |
+
"step": 37
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.7747690347244345,
|
| 679 |
+
"grad_norm": 1.3231741189956665,
|
| 680 |
+
"learning_rate": 2.8205128205128207e-05,
|
| 681 |
+
"log_odds_chosen": 0.4579349756240845,
|
| 682 |
+
"log_odds_ratio": -0.5229912996292114,
|
| 683 |
+
"logits/chosen": -2.34989070892334,
|
| 684 |
+
"logits/rejected": -2.3443665504455566,
|
| 685 |
+
"logps/chosen": -0.7170583605766296,
|
| 686 |
+
"logps/rejected": -0.9584832191467285,
|
| 687 |
+
"loss": 0.9491,
|
| 688 |
+
"nll_loss": 0.8968215584754944,
|
| 689 |
+
"rewards/accuracies": 0.828125,
|
| 690 |
+
"rewards/chosen": -0.07170583307743073,
|
| 691 |
+
"rewards/margins": 0.024142492562532425,
|
| 692 |
+
"rewards/rejected": -0.09584832936525345,
|
| 693 |
+
"step": 38
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 0.7951576935329723,
|
| 697 |
+
"grad_norm": 1.5374537706375122,
|
| 698 |
+
"learning_rate": 2.564102564102564e-05,
|
| 699 |
+
"log_odds_chosen": 0.42807331681251526,
|
| 700 |
+
"log_odds_ratio": -0.5446363091468811,
|
| 701 |
+
"logits/chosen": -2.3315584659576416,
|
| 702 |
+
"logits/rejected": -2.3167564868927,
|
| 703 |
+
"logps/chosen": -0.7248810529708862,
|
| 704 |
+
"logps/rejected": -0.938808262348175,
|
| 705 |
+
"loss": 1.0008,
|
| 706 |
+
"nll_loss": 0.9463487863540649,
|
| 707 |
+
"rewards/accuracies": 0.765625,
|
| 708 |
+
"rewards/chosen": -0.07248809933662415,
|
| 709 |
+
"rewards/margins": 0.021392717957496643,
|
| 710 |
+
"rewards/rejected": -0.09388083219528198,
|
| 711 |
+
"step": 39
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.8155463523415101,
|
| 715 |
+
"grad_norm": 1.3374099731445312,
|
| 716 |
+
"learning_rate": 2.307692307692308e-05,
|
| 717 |
+
"log_odds_chosen": 0.5240917205810547,
|
| 718 |
+
"log_odds_ratio": -0.4976484477519989,
|
| 719 |
+
"logits/chosen": -2.366239547729492,
|
| 720 |
+
"logits/rejected": -2.3758716583251953,
|
| 721 |
+
"logps/chosen": -0.6952681541442871,
|
| 722 |
+
"logps/rejected": -0.9785600900650024,
|
| 723 |
+
"loss": 0.9671,
|
| 724 |
+
"nll_loss": 0.9173198342323303,
|
| 725 |
+
"rewards/accuracies": 0.8125,
|
| 726 |
+
"rewards/chosen": -0.06952681392431259,
|
| 727 |
+
"rewards/margins": 0.028329193592071533,
|
| 728 |
+
"rewards/rejected": -0.09785601496696472,
|
| 729 |
+
"step": 40
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.8359350111500478,
|
| 733 |
+
"grad_norm": 1.3435301780700684,
|
| 734 |
+
"learning_rate": 2.0512820512820512e-05,
|
| 735 |
+
"log_odds_chosen": 0.5015857219696045,
|
| 736 |
+
"log_odds_ratio": -0.5036069750785828,
|
| 737 |
+
"logits/chosen": -2.3854644298553467,
|
| 738 |
+
"logits/rejected": -2.3718245029449463,
|
| 739 |
+
"logps/chosen": -0.6270416975021362,
|
| 740 |
+
"logps/rejected": -0.8865860104560852,
|
| 741 |
+
"loss": 0.8826,
|
| 742 |
+
"nll_loss": 0.8322214484214783,
|
| 743 |
+
"rewards/accuracies": 0.859375,
|
| 744 |
+
"rewards/chosen": -0.0627041757106781,
|
| 745 |
+
"rewards/margins": 0.025954432785511017,
|
| 746 |
+
"rewards/rejected": -0.08865861594676971,
|
| 747 |
+
"step": 41
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.8563236699585856,
|
| 751 |
+
"grad_norm": 1.317194938659668,
|
| 752 |
+
"learning_rate": 1.794871794871795e-05,
|
| 753 |
+
"log_odds_chosen": 0.47509485483169556,
|
| 754 |
+
"log_odds_ratio": -0.5203093886375427,
|
| 755 |
+
"logits/chosen": -2.3959298133850098,
|
| 756 |
+
"logits/rejected": -2.3753604888916016,
|
| 757 |
+
"logps/chosen": -0.6470075845718384,
|
| 758 |
+
"logps/rejected": -0.8970209360122681,
|
| 759 |
+
"loss": 0.9053,
|
| 760 |
+
"nll_loss": 0.8532766103744507,
|
| 761 |
+
"rewards/accuracies": 0.828125,
|
| 762 |
+
"rewards/chosen": -0.06470076739788055,
|
| 763 |
+
"rewards/margins": 0.025001339614391327,
|
| 764 |
+
"rewards/rejected": -0.08970209211111069,
|
| 765 |
+
"step": 42
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.8767123287671232,
|
| 769 |
+
"grad_norm": 1.3642792701721191,
|
| 770 |
+
"learning_rate": 1.5384615384615387e-05,
|
| 771 |
+
"log_odds_chosen": 0.49100199341773987,
|
| 772 |
+
"log_odds_ratio": -0.5025806427001953,
|
| 773 |
+
"logits/chosen": -2.3995158672332764,
|
| 774 |
+
"logits/rejected": -2.3859848976135254,
|
| 775 |
+
"logps/chosen": -0.6976916790008545,
|
| 776 |
+
"logps/rejected": -0.9635840058326721,
|
| 777 |
+
"loss": 0.9203,
|
| 778 |
+
"nll_loss": 0.8700023889541626,
|
| 779 |
+
"rewards/accuracies": 0.84375,
|
| 780 |
+
"rewards/chosen": -0.06976917386054993,
|
| 781 |
+
"rewards/margins": 0.026589233428239822,
|
| 782 |
+
"rewards/rejected": -0.09635840356349945,
|
| 783 |
+
"step": 43
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.897100987575661,
|
| 787 |
+
"grad_norm": 1.382372260093689,
|
| 788 |
+
"learning_rate": 1.282051282051282e-05,
|
| 789 |
+
"log_odds_chosen": 0.4726504683494568,
|
| 790 |
+
"log_odds_ratio": -0.5079113841056824,
|
| 791 |
+
"logits/chosen": -2.3786683082580566,
|
| 792 |
+
"logits/rejected": -2.394200325012207,
|
| 793 |
+
"logps/chosen": -0.6358219981193542,
|
| 794 |
+
"logps/rejected": -0.8916367888450623,
|
| 795 |
+
"loss": 0.9158,
|
| 796 |
+
"nll_loss": 0.8650074005126953,
|
| 797 |
+
"rewards/accuracies": 0.859375,
|
| 798 |
+
"rewards/chosen": -0.06358219683170319,
|
| 799 |
+
"rewards/margins": 0.0255814790725708,
|
| 800 |
+
"rewards/rejected": -0.08916367590427399,
|
| 801 |
+
"step": 44
|
| 802 |
}
|
| 803 |
],
|
| 804 |
"logging_steps": 1,
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5560
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6bcc3f11131b07d173fb79ad8c31d1a50ed3843eadae9ec2e4213021d99bed1
|
| 3 |
size 5560
|