Upload logs/9e507b57_sft_sftT1.log with huggingface_hub
Browse files- logs/9e507b57_sft_sftT1.log +98 -0
logs/9e507b57_sft_sftT1.log
CHANGED
|
@@ -640,3 +640,101 @@ Consider using tensor.detach() first. (Triggered internally at /pytorch/torch/cs
|
|
| 640 |
|
| 641 |
|
| 642 |
/tmp/sftT1.pt : 100%|ββββββββββ| 2.45GB / 2.45GB
|
| 643 |
14:04:51 SAVED sft/sftT1_latest.pt
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 644 |
/tmp/sftT1.pt : 3%|β | 64.0MB / 2.45GB [A[A
|
|
|
|
|
|
|
| 645 |
/tmp/sftT1.pt : 3%|β | 64.0MB / 2.45GB [A[A
|
|
|
|
|
|
|
| 646 |
/tmp/sftT1.pt : 5%|β | 120MB / 2.45GB [A[A
|
|
|
|
|
|
|
| 647 |
/tmp/sftT1.pt : 7%|β | 184MB / 2.45GB [A[A
|
|
|
|
|
|
|
| 648 |
/tmp/sftT1.pt : 10%|β | 248MB / 2.45GB [A[A
|
|
|
|
|
|
|
| 649 |
/tmp/sftT1.pt : 12%|ββ | 304MB / 2.45GB [A[A
|
|
|
|
|
|
|
| 650 |
/tmp/sftT1.pt : 15%|ββ | 368MB / 2.45GB [A[A
|
|
|
|
|
|
|
| 651 |
/tmp/sftT1.pt : 18%|ββ | 432MB / 2.45GB [A[A
|
|
|
|
|
|
|
| 652 |
/tmp/sftT1.pt : 20%|ββ | 488MB / 2.45GB [A[A
|
|
|
|
|
|
|
| 653 |
/tmp/sftT1.pt : 22%|βββ | 552MB / 2.45GB [A[A
|
|
|
|
|
|
|
| 654 |
/tmp/sftT1.pt : 25%|βββ | 616MB / 2.45GB [A[A
|
|
|
|
|
|
|
| 655 |
/tmp/sftT1.pt : 28%|βββ | 680MB / 2.45GB [A[A
|
|
|
|
|
|
|
| 656 |
/tmp/sftT1.pt : 30%|βββ | 736MB / 2.45GB [A[A
|
|
|
|
|
|
|
| 657 |
/tmp/sftT1.pt : 33%|ββββ | 800MB / 2.45GB [A[A
|
|
|
|
|
|
|
| 658 |
/tmp/sftT1.pt : 35%|ββββ | 864MB / 2.45GB [A[A
|
|
|
|
|
|
|
| 659 |
/tmp/sftT1.pt : 38%|ββββ | 928MB / 2.45GB [A[A
|
|
|
|
|
|
|
| 660 |
/tmp/sftT1.pt : 40%|ββββ | 984MB / 2.45GB [A[A
|
|
|
|
|
|
|
| 661 |
/tmp/sftT1.pt : 43%|βββββ | 1.05GB / 2.45GB [A[A
|
|
|
|
|
|
|
| 662 |
/tmp/sftT1.pt : 45%|βββββ | 1.10GB / 2.45GB [A[A
|
|
|
|
|
|
|
| 663 |
/tmp/sftT1.pt : 48%|βββββ | 1.17GB / 2.45GB [A[A
|
|
|
|
|
|
|
| 664 |
/tmp/sftT1.pt : 50%|βββββ | 1.22GB / 2.45GB [A[A
|
|
|
|
|
|
|
| 665 |
/tmp/sftT1.pt : 52%|ββββββ | 1.29GB / 2.45GB [A[A
|
|
|
|
|
|
|
| 666 |
/tmp/sftT1.pt : 55%|ββββββ | 1.35GB / 2.45GB [A[A
|
|
|
|
|
|
|
| 667 |
/tmp/sftT1.pt : 58%|ββββββ | 1.42GB / 2.45GB [A[A
|
|
|
|
|
|
|
| 668 |
/tmp/sftT1.pt : 60%|ββββββ | 1.47GB / 2.45GB [A[A
|
|
|
|
|
|
|
| 669 |
/tmp/sftT1.pt : 63%|βββββββ | 1.54GB / 2.45GB [A[A
|
|
|
|
|
|
|
| 670 |
/tmp/sftT1.pt : 65%|βββββββ | 1.60GB / 2.45GB [A[A
|
|
|
|
|
|
|
| 671 |
/tmp/sftT1.pt : 67%|βββββββ | 1.66GB / 2.45GB [A[A
|
|
|
|
|
|
|
| 672 |
/tmp/sftT1.pt : 70%|βββββββ | 1.72GB / 2.45GB [A[A
|
|
|
|
|
|
|
| 673 |
/tmp/sftT1.pt : 73%|ββββββββ | 1.78GB / 2.45GB [A[A
|
|
|
|
|
|
|
| 674 |
/tmp/sftT1.pt : 75%|ββββββββ | 1.85GB / 2.45GB [A[A
|
|
|
|
|
|
|
| 675 |
/tmp/sftT1.pt : 78%|ββββββββ | 1.90GB / 2.45GB [A[A
|
|
|
|
|
|
|
| 676 |
/tmp/sftT1.pt : 80%|ββββββββ | 1.97GB / 2.45GB [A[A
|
|
|
|
|
|
|
| 677 |
/tmp/sftT1.pt : 83%|βββββββββ | 2.03GB / 2.45GB [A[A
|
|
|
|
|
|
|
| 678 |
/tmp/sftT1.pt : 85%|βββββββββ | 2.09GB / 2.45GB [A[A
|
|
|
|
|
|
|
| 679 |
/tmp/sftT1.pt : 88%|βββββββββ | 2.15GB / 2.45GB [A[A
|
|
|
|
|
|
|
| 680 |
/tmp/sftT1.pt : 90%|βββββββββ | 2.21GB / 2.45GB [A[A
|
|
|
|
|
|
|
| 681 |
/tmp/sftT1.pt : 93%|ββββββββββ| 2.27GB / 2.45GB [A[A
|
|
|
|
|
|
|
| 682 |
/tmp/sftT1.pt : 95%|ββββββββββ| 2.34GB / 2.45GB [A[A
|
|
|
|
|
|
|
| 683 |
/tmp/sftT1.pt : 98%|ββββββββββ| 2.40GB / 2.45GB [A[A
|
|
|
|
|
|
|
| 684 |
/tmp/sftT1.pt : 100%|ββββββββββ| 2.45GB / 2.45GB [A[A
|
|
|
|
|
|
|
| 685 |
/tmp/sftT1.pt : 100%|ββββββββββ| 2.45GB / 2.45GB [A[A
|
|
|
|
|
|
|
| 686 |
/tmp/sftT1.pt : 100%|ββββββββββ| 2.45GB / 2.45GB [A[A
|
|
|
|
|
|
|
| 687 |
/tmp/sftT1.pt : 100%|ββββββββββ| 2.45GB / 2.45GB [A[A
|
|
|
|
|
|
|
| 688 |
/tmp/sftT1.pt : 100%|ββββββββββ| 2.45GB / 2.45GB [A[A
|
|
|
|
|
|
|
| 689 |
/tmp/sftT1.pt : 100%|ββββββββββ| 2.45GB / 2.45GB
|
|
|
|
|
|
|
|
|
| 640 |
|
| 641 |
|
| 642 |
/tmp/sftT1.pt : 100%|ββββββββββ| 2.45GB / 2.45GB
|
| 643 |
14:04:51 SAVED sft/sftT1_latest.pt
|
| 644 |
+
14:09:20 EVAL step 500 gsm8k 0.000 svamp 0.000 heldout_nll 0.4896 reached_####: 0/200 (269s)
|
| 645 |
+
14:09:20 SAMPLE Daily consumption = 16 eggs / Daily consumption = 3 eggs / Daily consumption = 4 eggs / Daily consumption = 16 - 3 = 9 eggs / Daily consumption = 4 eggs / Daily consumption = 4 eggs / Daily consumption = 4 * 4 = 28 eggs / Daily consumption = 16 - 9 = 15 eggs / Daily consumption = 15 * 15 = 30 eggs / Daily consumption
|
| 646 |
+
|
| 647 |
+
|
| 648 |
+
|
| 649 |
+
|
| 650 |
/tmp/sftT1.pt : 3%|β | 64.0MB / 2.45GB [A[A
|
| 651 |
+
|
| 652 |
+
|
| 653 |
/tmp/sftT1.pt : 3%|β | 64.0MB / 2.45GB [A[A
|
| 654 |
+
|
| 655 |
+
|
| 656 |
/tmp/sftT1.pt : 5%|β | 120MB / 2.45GB [A[A
|
| 657 |
+
|
| 658 |
+
|
| 659 |
/tmp/sftT1.pt : 7%|β | 184MB / 2.45GB [A[A
|
| 660 |
+
|
| 661 |
+
|
| 662 |
/tmp/sftT1.pt : 10%|β | 248MB / 2.45GB [A[A
|
| 663 |
+
|
| 664 |
+
|
| 665 |
/tmp/sftT1.pt : 12%|ββ | 304MB / 2.45GB [A[A
|
| 666 |
+
|
| 667 |
+
|
| 668 |
/tmp/sftT1.pt : 15%|ββ | 368MB / 2.45GB [A[A
|
| 669 |
+
|
| 670 |
+
|
| 671 |
/tmp/sftT1.pt : 18%|ββ | 432MB / 2.45GB [A[A
|
| 672 |
+
|
| 673 |
+
|
| 674 |
/tmp/sftT1.pt : 20%|ββ | 488MB / 2.45GB [A[A
|
| 675 |
+
|
| 676 |
+
|
| 677 |
/tmp/sftT1.pt : 22%|βββ | 552MB / 2.45GB [A[A
|
| 678 |
+
|
| 679 |
+
|
| 680 |
/tmp/sftT1.pt : 25%|βββ | 616MB / 2.45GB [A[A
|
| 681 |
+
|
| 682 |
+
|
| 683 |
/tmp/sftT1.pt : 28%|βββ | 680MB / 2.45GB [A[A
|
| 684 |
+
|
| 685 |
+
|
| 686 |
/tmp/sftT1.pt : 30%|βββ | 736MB / 2.45GB [A[A
|
| 687 |
+
|
| 688 |
+
|
| 689 |
/tmp/sftT1.pt : 33%|ββββ | 800MB / 2.45GB [A[A
|
| 690 |
+
|
| 691 |
+
|
| 692 |
/tmp/sftT1.pt : 35%|ββββ | 864MB / 2.45GB [A[A
|
| 693 |
+
|
| 694 |
+
|
| 695 |
/tmp/sftT1.pt : 38%|ββββ | 928MB / 2.45GB [A[A
|
| 696 |
+
|
| 697 |
+
|
| 698 |
/tmp/sftT1.pt : 40%|ββββ | 984MB / 2.45GB [A[A
|
| 699 |
+
|
| 700 |
+
|
| 701 |
/tmp/sftT1.pt : 43%|βββββ | 1.05GB / 2.45GB [A[A
|
| 702 |
+
|
| 703 |
+
|
| 704 |
/tmp/sftT1.pt : 45%|βββββ | 1.10GB / 2.45GB [A[A
|
| 705 |
+
|
| 706 |
+
|
| 707 |
/tmp/sftT1.pt : 48%|βββββ | 1.17GB / 2.45GB [A[A
|
| 708 |
+
|
| 709 |
+
|
| 710 |
/tmp/sftT1.pt : 50%|βββββ | 1.22GB / 2.45GB [A[A
|
| 711 |
+
|
| 712 |
+
|
| 713 |
/tmp/sftT1.pt : 52%|ββββββ | 1.29GB / 2.45GB [A[A
|
| 714 |
+
|
| 715 |
+
|
| 716 |
/tmp/sftT1.pt : 55%|ββββββ | 1.35GB / 2.45GB [A[A
|
| 717 |
+
|
| 718 |
+
|
| 719 |
/tmp/sftT1.pt : 58%|ββββββ | 1.42GB / 2.45GB [A[A
|
| 720 |
+
|
| 721 |
+
|
| 722 |
/tmp/sftT1.pt : 60%|ββββββ | 1.47GB / 2.45GB [A[A
|
| 723 |
+
|
| 724 |
+
|
| 725 |
/tmp/sftT1.pt : 63%|βββββββ | 1.54GB / 2.45GB [A[A
|
| 726 |
+
|
| 727 |
+
|
| 728 |
/tmp/sftT1.pt : 65%|βββββββ | 1.60GB / 2.45GB [A[A
|
| 729 |
+
|
| 730 |
+
|
| 731 |
/tmp/sftT1.pt : 67%|βββββββ | 1.66GB / 2.45GB [A[A
|
| 732 |
+
|
| 733 |
+
|
| 734 |
/tmp/sftT1.pt : 70%|βββββββ | 1.72GB / 2.45GB [A[A
|
| 735 |
+
|
| 736 |
+
|
| 737 |
/tmp/sftT1.pt : 73%|ββββββββ | 1.78GB / 2.45GB [A[A
|
| 738 |
+
|
| 739 |
+
|
| 740 |
/tmp/sftT1.pt : 75%|ββββββββ | 1.85GB / 2.45GB [A[A
|
| 741 |
+
|
| 742 |
+
|
| 743 |
/tmp/sftT1.pt : 78%|ββββββββ | 1.90GB / 2.45GB [A[A
|
| 744 |
+
|
| 745 |
+
|
| 746 |
/tmp/sftT1.pt : 80%|ββββββββ | 1.97GB / 2.45GB [A[A
|
| 747 |
+
|
| 748 |
+
|
| 749 |
/tmp/sftT1.pt : 83%|βββββββββ | 2.03GB / 2.45GB [A[A
|
| 750 |
+
|
| 751 |
+
|
| 752 |
/tmp/sftT1.pt : 85%|βββββββββ | 2.09GB / 2.45GB [A[A
|
| 753 |
+
|
| 754 |
+
|
| 755 |
/tmp/sftT1.pt : 88%|βββββββββ | 2.15GB / 2.45GB [A[A
|
| 756 |
+
|
| 757 |
+
|
| 758 |
/tmp/sftT1.pt : 90%|βββββββββ | 2.21GB / 2.45GB [A[A
|
| 759 |
+
|
| 760 |
+
|
| 761 |
/tmp/sftT1.pt : 93%|ββββββββββ| 2.27GB / 2.45GB [A[A
|
| 762 |
+
|
| 763 |
+
|
| 764 |
/tmp/sftT1.pt : 95%|ββββββββββ| 2.34GB / 2.45GB [A[A
|
| 765 |
+
|
| 766 |
+
|
| 767 |
/tmp/sftT1.pt : 98%|ββββββββββ| 2.40GB / 2.45GB [A[A
|
| 768 |
+
|
| 769 |
+
|
| 770 |
/tmp/sftT1.pt : 100%|ββββββββββ| 2.45GB / 2.45GB [A[A
|
| 771 |
+
|
| 772 |
+
|
| 773 |
/tmp/sftT1.pt : 100%|ββββββββββ| 2.45GB / 2.45GB [A[A
|
| 774 |
+
|
| 775 |
+
|
| 776 |
/tmp/sftT1.pt : 100%|ββββββββββ| 2.45GB / 2.45GB [A[A
|
| 777 |
+
|
| 778 |
+
|
| 779 |
/tmp/sftT1.pt : 100%|ββββββββββ| 2.45GB / 2.45GB [A[A
|
| 780 |
+
|
| 781 |
+
|
| 782 |
/tmp/sftT1.pt : 100%|ββββββββββ| 2.45GB / 2.45GB [A[A
|
| 783 |
+
|
| 784 |
+
|
| 785 |
/tmp/sftT1.pt : 100%|ββββββββββ| 2.45GB / 2.45GB
|
| 786 |
+
14:09:28 SAVED sft/sftT1_final.pt
|
| 787 |
+
14:09:28 SFT DONE
|