Commit
·
17d9288
1
Parent(s):
1d94385
Training in progress, epoch 3, checkpoint
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +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/rng_state_4.pth +1 -1
- last-checkpoint/rng_state_5.pth +1 -1
- last-checkpoint/rng_state_6.pth +1 -1
- last-checkpoint/rng_state_7.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +313 -3
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 272138666
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c4862ebcdc8d2768d6132069a64ba7dfa94cdbf6455d4d4560f35f71fcc32dfb
|
| 3 |
size 272138666
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 136067312
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:094d5e98b1a3b1417249f16f63b4282afd3829ec4a31dbc2bc00df331ba5faf1
|
| 3 |
size 136067312
|
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 21687
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:67b5b6dd9206c42165f5188e8effb6be1e40ed13cd768d8b7a1b17575bf03d9e
|
| 3 |
size 21687
|
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 21687
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6828f225fa32178c33ef119d710f22e24b0bc0c656e9d474379f8495e0908384
|
| 3 |
size 21687
|
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 21687
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35c188ece0af9a1c1c070d68232ff9e3dc42d760df0f2e5e280f4c2013a3e538
|
| 3 |
size 21687
|
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 21687
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1f9da3ceb24bed58a42dc4e81d0a1e02d0fbd589dd70fb982262e3a3a271213
|
| 3 |
size 21687
|
last-checkpoint/rng_state_4.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 21687
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:05f3bf8804c8e87d47beaafc30681cc2d8abc53f079c3ec27b8405f27eafb62e
|
| 3 |
size 21687
|
last-checkpoint/rng_state_5.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 21687
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c4a3224faf90dcc36243bfcd086fe8dbeb1b17d0f25a5e2b7d1d315effde3250
|
| 3 |
size 21687
|
last-checkpoint/rng_state_6.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 21687
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4feb4ed70cfe7ab739f8d7012e2560e686d994777ba7aa8513abce68d4c42d9a
|
| 3 |
size 21687
|
last-checkpoint/rng_state_7.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 21687
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1934f6a0f7b05c9571484b9dbea2c6fb5ae573367912d95f0629f9b4ebdf3aa7
|
| 3 |
size 21687
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1d49d9630e070befda78ef6b64c8fdc0bb6b5103c4e1c8f4b6fa80c9bcbdbb4
|
| 3 |
size 627
|
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": 25,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -627,13 +627,323 @@
|
|
| 627 |
"learning_rate": 3.2871627610744385e-05,
|
| 628 |
"loss": 0.0255,
|
| 629 |
"step": 410
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 630 |
}
|
| 631 |
],
|
| 632 |
"logging_steps": 5,
|
| 633 |
"max_steps": 1030,
|
| 634 |
"num_train_epochs": 5,
|
| 635 |
"save_steps": 500,
|
| 636 |
-
"total_flos":
|
| 637 |
"trial_name": null,
|
| 638 |
"trial_params": null
|
| 639 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
"eval_steps": 25,
|
| 6 |
+
"global_step": 618,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 627 |
"learning_rate": 3.2871627610744385e-05,
|
| 628 |
"loss": 0.0255,
|
| 629 |
"step": 410
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 2.01,
|
| 633 |
+
"learning_rate": 3.250884674934208e-05,
|
| 634 |
+
"loss": 0.0377,
|
| 635 |
+
"step": 415
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 2.04,
|
| 639 |
+
"learning_rate": 3.214431944087437e-05,
|
| 640 |
+
"loss": 0.0309,
|
| 641 |
+
"step": 420
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.06,
|
| 645 |
+
"learning_rate": 3.17781304690197e-05,
|
| 646 |
+
"loss": 0.0667,
|
| 647 |
+
"step": 425
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 2.06,
|
| 651 |
+
"eval_loss": 0.07217594981193542,
|
| 652 |
+
"eval_runtime": 0.1187,
|
| 653 |
+
"eval_samples_per_second": 3462.503,
|
| 654 |
+
"eval_steps_per_second": 109.52,
|
| 655 |
+
"step": 425
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 2.09,
|
| 659 |
+
"learning_rate": 3.14103650039349e-05,
|
| 660 |
+
"loss": 0.0339,
|
| 661 |
+
"step": 430
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 2.11,
|
| 665 |
+
"learning_rate": 3.104110858244588e-05,
|
| 666 |
+
"loss": 0.0068,
|
| 667 |
+
"step": 435
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 2.14,
|
| 671 |
+
"learning_rate": 3.0670447088153055e-05,
|
| 672 |
+
"loss": 0.0522,
|
| 673 |
+
"step": 440
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 2.16,
|
| 677 |
+
"learning_rate": 3.029846673145604e-05,
|
| 678 |
+
"loss": 0.0068,
|
| 679 |
+
"step": 445
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 2.18,
|
| 683 |
+
"learning_rate": 2.99252540295024e-05,
|
| 684 |
+
"loss": 0.0514,
|
| 685 |
+
"step": 450
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 2.18,
|
| 689 |
+
"eval_loss": 0.05946213752031326,
|
| 690 |
+
"eval_runtime": 0.1357,
|
| 691 |
+
"eval_samples_per_second": 3027.628,
|
| 692 |
+
"eval_steps_per_second": 95.764,
|
| 693 |
+
"step": 450
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 2.21,
|
| 697 |
+
"learning_rate": 2.955089578606506e-05,
|
| 698 |
+
"loss": 0.022,
|
| 699 |
+
"step": 455
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 2.23,
|
| 703 |
+
"learning_rate": 2.9175479071352996e-05,
|
| 704 |
+
"loss": 0.058,
|
| 705 |
+
"step": 460
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 2.26,
|
| 709 |
+
"learning_rate": 2.8799091201760008e-05,
|
| 710 |
+
"loss": 0.0262,
|
| 711 |
+
"step": 465
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 2.28,
|
| 715 |
+
"learning_rate": 2.8421819719556205e-05,
|
| 716 |
+
"loss": 0.0108,
|
| 717 |
+
"step": 470
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 2.31,
|
| 721 |
+
"learning_rate": 2.804375237252694e-05,
|
| 722 |
+
"loss": 0.0286,
|
| 723 |
+
"step": 475
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 2.31,
|
| 727 |
+
"eval_loss": 0.04657759144902229,
|
| 728 |
+
"eval_runtime": 0.1207,
|
| 729 |
+
"eval_samples_per_second": 3405.261,
|
| 730 |
+
"eval_steps_per_second": 107.709,
|
| 731 |
+
"step": 475
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 2.33,
|
| 735 |
+
"learning_rate": 2.7664977093564022e-05,
|
| 736 |
+
"loss": 0.0122,
|
| 737 |
+
"step": 480
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 2.35,
|
| 741 |
+
"learning_rate": 2.728558198021378e-05,
|
| 742 |
+
"loss": 0.0286,
|
| 743 |
+
"step": 485
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 2.38,
|
| 747 |
+
"learning_rate": 2.6905655274186892e-05,
|
| 748 |
+
"loss": 0.0284,
|
| 749 |
+
"step": 490
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 2.4,
|
| 753 |
+
"learning_rate": 2.6525285340834644e-05,
|
| 754 |
+
"loss": 0.0223,
|
| 755 |
+
"step": 495
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 2.43,
|
| 759 |
+
"learning_rate": 2.6144560648596466e-05,
|
| 760 |
+
"loss": 0.0349,
|
| 761 |
+
"step": 500
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 2.43,
|
| 765 |
+
"eval_loss": 0.05097094178199768,
|
| 766 |
+
"eval_runtime": 0.1152,
|
| 767 |
+
"eval_samples_per_second": 3566.29,
|
| 768 |
+
"eval_steps_per_second": 112.802,
|
| 769 |
+
"step": 500
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 2.45,
|
| 773 |
+
"learning_rate": 2.576356974842349e-05,
|
| 774 |
+
"loss": 0.031,
|
| 775 |
+
"step": 505
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 2.48,
|
| 779 |
+
"learning_rate": 2.538240125318287e-05,
|
| 780 |
+
"loss": 0.0534,
|
| 781 |
+
"step": 510
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 2.5,
|
| 785 |
+
"learning_rate": 2.5001143817047762e-05,
|
| 786 |
+
"loss": 0.04,
|
| 787 |
+
"step": 515
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 2.52,
|
| 791 |
+
"learning_rate": 2.4619886114877678e-05,
|
| 792 |
+
"loss": 0.0463,
|
| 793 |
+
"step": 520
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 2.55,
|
| 797 |
+
"learning_rate": 2.4238716821593986e-05,
|
| 798 |
+
"loss": 0.0231,
|
| 799 |
+
"step": 525
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 2.55,
|
| 803 |
+
"eval_loss": 0.04907093197107315,
|
| 804 |
+
"eval_runtime": 0.1367,
|
| 805 |
+
"eval_samples_per_second": 3007.163,
|
| 806 |
+
"eval_steps_per_second": 95.117,
|
| 807 |
+
"step": 525
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 2.57,
|
| 811 |
+
"learning_rate": 2.3857724591555443e-05,
|
| 812 |
+
"loss": 0.0292,
|
| 813 |
+
"step": 530
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 2.6,
|
| 817 |
+
"learning_rate": 2.347699803793854e-05,
|
| 818 |
+
"loss": 0.0527,
|
| 819 |
+
"step": 535
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 2.62,
|
| 823 |
+
"learning_rate": 2.309662571212731e-05,
|
| 824 |
+
"loss": 0.0424,
|
| 825 |
+
"step": 540
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 2.65,
|
| 829 |
+
"learning_rate": 2.2716696083117664e-05,
|
| 830 |
+
"loss": 0.0363,
|
| 831 |
+
"step": 545
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 2.67,
|
| 835 |
+
"learning_rate": 2.233729751694071e-05,
|
| 836 |
+
"loss": 0.0301,
|
| 837 |
+
"step": 550
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 2.67,
|
| 841 |
+
"eval_loss": 0.04202725738286972,
|
| 842 |
+
"eval_runtime": 0.1194,
|
| 843 |
+
"eval_samples_per_second": 3441.042,
|
| 844 |
+
"eval_steps_per_second": 108.841,
|
| 845 |
+
"step": 550
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 2.69,
|
| 849 |
+
"learning_rate": 2.1958518256110213e-05,
|
| 850 |
+
"loss": 0.0638,
|
| 851 |
+
"step": 555
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 2.72,
|
| 855 |
+
"learning_rate": 2.1580446399098604e-05,
|
| 856 |
+
"loss": 0.0684,
|
| 857 |
+
"step": 560
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 2.74,
|
| 861 |
+
"learning_rate": 2.1203169879846667e-05,
|
| 862 |
+
"loss": 0.0249,
|
| 863 |
+
"step": 565
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 2.77,
|
| 867 |
+
"learning_rate": 2.0826776447311296e-05,
|
| 868 |
+
"loss": 0.0454,
|
| 869 |
+
"step": 570
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 2.79,
|
| 873 |
+
"learning_rate": 2.0451353645056464e-05,
|
| 874 |
+
"loss": 0.0617,
|
| 875 |
+
"step": 575
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 2.79,
|
| 879 |
+
"eval_loss": 0.03725917637348175,
|
| 880 |
+
"eval_runtime": 0.1154,
|
| 881 |
+
"eval_samples_per_second": 3562.318,
|
| 882 |
+
"eval_steps_per_second": 112.677,
|
| 883 |
+
"step": 575
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 2.82,
|
| 887 |
+
"learning_rate": 2.0076988790891832e-05,
|
| 888 |
+
"loss": 0.0323,
|
| 889 |
+
"step": 580
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 2.84,
|
| 893 |
+
"learning_rate": 1.970376895656394e-05,
|
| 894 |
+
"loss": 0.0442,
|
| 895 |
+
"step": 585
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 2.86,
|
| 899 |
+
"learning_rate": 1.9331780947504582e-05,
|
| 900 |
+
"loss": 0.0052,
|
| 901 |
+
"step": 590
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 2.89,
|
| 905 |
+
"learning_rate": 1.8961111282641173e-05,
|
| 906 |
+
"loss": 0.0171,
|
| 907 |
+
"step": 595
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 2.91,
|
| 911 |
+
"learning_rate": 1.859184617427367e-05,
|
| 912 |
+
"loss": 0.0305,
|
| 913 |
+
"step": 600
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 2.91,
|
| 917 |
+
"eval_loss": 0.054718561470508575,
|
| 918 |
+
"eval_runtime": 0.144,
|
| 919 |
+
"eval_samples_per_second": 2853.575,
|
| 920 |
+
"eval_steps_per_second": 90.259,
|
| 921 |
+
"step": 600
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 2.94,
|
| 925 |
+
"learning_rate": 1.822407150802294e-05,
|
| 926 |
+
"loss": 0.0405,
|
| 927 |
+
"step": 605
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 2.96,
|
| 931 |
+
"learning_rate": 1.7857872822854935e-05,
|
| 932 |
+
"loss": 0.0273,
|
| 933 |
+
"step": 610
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 2.99,
|
| 937 |
+
"learning_rate": 1.7493335291185675e-05,
|
| 938 |
+
"loss": 0.0324,
|
| 939 |
+
"step": 615
|
| 940 |
}
|
| 941 |
],
|
| 942 |
"logging_steps": 5,
|
| 943 |
"max_steps": 1030,
|
| 944 |
"num_train_epochs": 5,
|
| 945 |
"save_steps": 500,
|
| 946 |
+
"total_flos": 275559470923776.0,
|
| 947 |
"trial_name": null,
|
| 948 |
"trial_params": null
|
| 949 |
}
|