lr0.0001_bs16_0617_1957

This model is a fine-tuned version of nvidia/mit-b0 on the greenkwd/upwellingdetection_SST dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0393
  • Mean Iou: 0.9563
  • Mean Accuracy: 0.9774
  • Overall Accuracy: 0.9834
  • Accuracy Land: 0.9933
  • Accuracy Upwelling: 0.9845
  • Accuracy Not Upwelling: 0.9543
  • Iou Land: 0.9886
  • Iou Upwelling: 0.9670
  • Iou Not Upwelling: 0.9131
  • Dice Macro: 0.9774
  • Dice Micro: 0.9834

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 0.0001
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 100

Training results

Training Loss Epoch Step Validation Loss Mean Iou Mean Accuracy Overall Accuracy Accuracy Land Accuracy Upwelling Accuracy Not Upwelling Iou Land Iou Upwelling Iou Not Upwelling Dice Macro Dice Micro
1.0016 0.4 20 1.0623 0.5156 0.6617 0.7019 0.7959 0.6728 0.5163 0.7752 0.5127 0.2588 0.6541 0.7019
0.8653 0.8 40 0.8709 0.6177 0.7313 0.8108 0.8640 0.9249 0.4048 0.8557 0.7121 0.2851 0.7326 0.8108
0.6586 1.2 60 0.5536 0.6537 0.7493 0.8497 0.9353 0.9699 0.3426 0.9233 0.7530 0.2848 0.7542 0.8497
0.6057 1.6 80 0.4194 0.7371 0.8179 0.8921 0.9709 0.9610 0.5217 0.9441 0.8097 0.4576 0.8313 0.8921
0.64 2.0 100 0.3555 0.7820 0.8571 0.9104 0.9709 0.9547 0.6456 0.9510 0.8371 0.5580 0.8675 0.9104
0.4969 2.4 120 0.3086 0.8131 0.8839 0.9231 0.9740 0.9472 0.7305 0.9541 0.8575 0.6277 0.8904 0.9231
0.4469 2.8 140 0.2876 0.8236 0.8909 0.9278 0.9732 0.9542 0.7453 0.9547 0.8667 0.6493 0.8976 0.9278
0.4722 3.2 160 0.2649 0.8151 0.8795 0.9257 0.9652 0.9810 0.6924 0.9566 0.8636 0.6251 0.8913 0.9257
0.4367 3.6 180 0.2657 0.8521 0.9202 0.9386 0.9781 0.9297 0.8530 0.9629 0.8803 0.7129 0.9166 0.9386
0.4458 4.0 200 0.2225 0.8594 0.9195 0.9429 0.9710 0.9604 0.8272 0.9637 0.8920 0.7224 0.9211 0.9429
0.3913 4.4 220 0.2168 0.8554 0.9077 0.9432 0.9853 0.9704 0.7674 0.9603 0.8974 0.7087 0.9184 0.9432
0.5363 4.8 240 0.2433 0.8690 0.9272 0.9470 0.9883 0.9388 0.8546 0.9602 0.9040 0.7429 0.9272 0.9470
0.3914 5.2 260 0.1801 0.8868 0.9414 0.9541 0.9659 0.9681 0.8901 0.9631 0.9187 0.7785 0.9381 0.9541
0.3516 5.6 280 0.1606 0.9023 0.9493 0.9609 0.9767 0.9673 0.9038 0.9697 0.9275 0.8097 0.9473 0.9609
0.3098 6.0 300 0.1323 0.8967 0.9389 0.9594 0.9812 0.9787 0.8567 0.9710 0.9234 0.7956 0.9439 0.9594
0.3887 6.4 320 0.1203 0.9022 0.9401 0.9620 0.9825 0.9860 0.8517 0.9729 0.9279 0.8056 0.9471 0.9620
0.4521 6.8 340 0.1191 0.9089 0.9534 0.9635 0.9708 0.9775 0.9118 0.9682 0.9356 0.8228 0.9511 0.9635
0.3816 7.2 360 0.1087 0.9139 0.9527 0.9661 0.9857 0.9714 0.9012 0.9743 0.9352 0.8321 0.9540 0.9661
0.3197 7.6 380 0.1081 0.9193 0.9583 0.9680 0.9813 0.9731 0.9205 0.9756 0.9383 0.8441 0.9571 0.9680
0.4084 8.0 400 0.1407 0.9036 0.9517 0.9611 0.9625 0.9806 0.9121 0.9618 0.9362 0.8126 0.9481 0.9611
0.4077 8.4 420 0.0923 0.9167 0.9544 0.9672 0.9777 0.9829 0.9027 0.9746 0.9378 0.8378 0.9556 0.9672
0.459 8.8 440 0.0942 0.9143 0.9514 0.9664 0.9775 0.9865 0.8902 0.9745 0.9364 0.8320 0.9542 0.9664
0.2765 9.2 460 0.0945 0.9086 0.9410 0.9650 0.9901 0.9879 0.8449 0.9755 0.9328 0.8176 0.9508 0.9650
0.3404 9.6 480 0.0822 0.9266 0.9614 0.9712 0.9868 0.9736 0.9238 0.9788 0.9437 0.8573 0.9612 0.9712
0.32 10.0 500 0.0823 0.9222 0.9521 0.9700 0.9879 0.9882 0.8803 0.9794 0.9406 0.8467 0.9587 0.9700
0.2849 10.4 520 0.0845 0.9287 0.9598 0.9724 0.9905 0.9780 0.9107 0.9802 0.9462 0.8597 0.9623 0.9724
0.2955 10.8 540 0.0794 0.9244 0.9534 0.9710 0.9889 0.9886 0.8826 0.9804 0.9429 0.8500 0.9599 0.9710
0.2918 11.2 560 0.0755 0.9278 0.9600 0.9721 0.9835 0.9850 0.9116 0.9794 0.9470 0.8570 0.9618 0.9721
0.3113 11.6 580 0.0735 0.9328 0.9611 0.9742 0.9909 0.9827 0.9098 0.9818 0.9496 0.8669 0.9646 0.9742
0.3019 12.0 600 0.0756 0.9304 0.9617 0.9732 0.9928 0.9741 0.9181 0.9812 0.9476 0.8624 0.9633 0.9732
0.315 12.4 620 0.0809 0.9294 0.9692 0.9721 0.9856 0.9615 0.9605 0.9812 0.9445 0.8625 0.9627 0.9721
0.3205 12.8 640 0.0703 0.9367 0.9642 0.9758 0.9911 0.9826 0.9190 0.9833 0.9526 0.8741 0.9667 0.9758
0.3359 13.2 660 0.0798 0.9323 0.9658 0.9736 0.9817 0.9811 0.9346 0.9791 0.9513 0.8665 0.9643 0.9736
0.2808 13.6 680 0.0685 0.9346 0.9688 0.9743 0.9818 0.9775 0.9470 0.9792 0.9523 0.8723 0.9656 0.9743
0.251 14.0 700 0.0686 0.9342 0.9645 0.9746 0.9854 0.9841 0.9240 0.9818 0.9511 0.8698 0.9654 0.9746
0.2585 14.4 720 0.0664 0.9311 0.9574 0.9739 0.9910 0.9899 0.8913 0.9833 0.9484 0.8616 0.9636 0.9739
0.3852 14.8 740 0.0664 0.9376 0.9656 0.9762 0.9888 0.9840 0.9242 0.9834 0.9539 0.8755 0.9672 0.9762
0.2465 15.2 760 0.0658 0.9384 0.9708 0.9761 0.9885 0.9723 0.9518 0.9835 0.9533 0.8783 0.9677 0.9761
0.2995 15.6 780 0.0664 0.9371 0.9639 0.9759 0.9895 0.9859 0.9164 0.9836 0.9523 0.8753 0.9669 0.9759
0.3256 16.0 800 0.0615 0.9395 0.9706 0.9766 0.9884 0.9752 0.9481 0.9835 0.9543 0.8809 0.9683 0.9766
0.3303 16.4 820 0.0675 0.9341 0.9692 0.9744 0.9922 0.9630 0.9524 0.9840 0.9478 0.8704 0.9653 0.9744
0.3632 16.8 840 0.0656 0.9379 0.9651 0.9762 0.9876 0.9870 0.9206 0.9832 0.9537 0.8768 0.9674 0.9762
0.2744 17.2 860 0.0700 0.9311 0.9712 0.9729 0.9890 0.9558 0.9688 0.9838 0.9443 0.8652 0.9636 0.9729
0.2301 17.6 880 0.0677 0.9296 0.9556 0.9734 0.9897 0.9931 0.8841 0.9835 0.9467 0.8587 0.9628 0.9734
0.4563 18.0 900 0.0580 0.9420 0.9697 0.9777 0.9902 0.9801 0.9389 0.9845 0.9562 0.8853 0.9697 0.9777
0.3108 18.4 920 0.0690 0.9284 0.9542 0.9732 0.9916 0.9930 0.8780 0.9847 0.9459 0.8545 0.9620 0.9732
0.3332 18.8 940 0.0601 0.9406 0.9651 0.9775 0.9940 0.9846 0.9168 0.9843 0.9565 0.8810 0.9689 0.9775
0.2756 19.2 960 0.0622 0.9346 0.9604 0.9753 0.9901 0.9904 0.9006 0.9848 0.9508 0.8681 0.9655 0.9753
0.2588 19.6 980 0.0622 0.9395 0.9728 0.9765 0.9896 0.9681 0.9605 0.9845 0.9531 0.8809 0.9683 0.9765
0.2404 20.0 1000 0.0610 0.9381 0.9636 0.9765 0.9895 0.9895 0.9118 0.9844 0.9538 0.8762 0.9675 0.9765
0.3353 20.4 1020 0.0685 0.9304 0.9632 0.9732 0.9920 0.9719 0.9256 0.9840 0.9455 0.8617 0.9632 0.9732
0.2617 20.8 1040 0.0579 0.9429 0.9693 0.9782 0.9927 0.9799 0.9353 0.9850 0.9571 0.8867 0.9701 0.9782
0.1977 21.2 1060 0.0593 0.9414 0.9670 0.9777 0.9895 0.9870 0.9246 0.9847 0.9565 0.8831 0.9693 0.9777
0.245 21.6 1080 0.0576 0.9419 0.9702 0.9777 0.9936 0.9745 0.9424 0.9842 0.9566 0.8850 0.9696 0.9777
0.2784 22.0 1100 0.0603 0.9371 0.9624 0.9762 0.9896 0.9906 0.9069 0.9848 0.9530 0.8734 0.9669 0.9762
0.2174 22.4 1120 0.0565 0.9431 0.9685 0.9783 0.9907 0.9847 0.9301 0.9847 0.9575 0.8873 0.9703 0.9783
0.1769 22.8 1140 0.0578 0.9413 0.9664 0.9777 0.9896 0.9883 0.9214 0.9849 0.9561 0.8829 0.9693 0.9777
0.2109 23.2 1160 0.0570 0.9437 0.9732 0.9783 0.9914 0.9731 0.9552 0.9855 0.9568 0.8889 0.9706 0.9783
0.2472 23.6 1180 0.0563 0.9433 0.9690 0.9783 0.9898 0.9848 0.9325 0.9848 0.9575 0.8877 0.9704 0.9783
0.1021 24.0 1200 0.0549 0.9452 0.9703 0.9791 0.9928 0.9816 0.9366 0.9856 0.9591 0.8908 0.9714 0.9791
0.2373 24.4 1220 0.0557 0.9434 0.9668 0.9786 0.9933 0.9865 0.9208 0.9853 0.9579 0.8868 0.9704 0.9786
0.2639 24.8 1240 0.0551 0.9445 0.9728 0.9787 0.9887 0.9791 0.9506 0.9847 0.9588 0.8901 0.9710 0.9787
0.2096 25.2 1260 0.0554 0.9444 0.9696 0.9788 0.9934 0.9810 0.9344 0.9855 0.9584 0.8893 0.9709 0.9788
0.2494 25.6 1280 0.0543 0.9445 0.9701 0.9789 0.9904 0.9842 0.9356 0.9855 0.9590 0.8890 0.9710 0.9789
0.26 26.0 1300 0.0571 0.9440 0.9730 0.9785 0.9909 0.9750 0.9530 0.9857 0.9569 0.8894 0.9708 0.9785
0.1706 26.4 1320 0.0534 0.9444 0.9676 0.9789 0.9934 0.9862 0.9234 0.9853 0.9589 0.8889 0.9709 0.9789
0.2623 26.8 1340 0.0524 0.9460 0.9724 0.9793 0.9915 0.9795 0.9461 0.9859 0.9592 0.8929 0.9718 0.9793
0.2358 27.2 1360 0.0560 0.9404 0.9641 0.9776 0.9915 0.9905 0.9101 0.9858 0.9553 0.8800 0.9687 0.9776
0.1839 27.6 1380 0.0541 0.9442 0.9692 0.9787 0.9891 0.9872 0.9314 0.9852 0.9586 0.8888 0.9708 0.9787
0.1351 28.0 1400 0.0530 0.9461 0.9715 0.9794 0.9893 0.9848 0.9404 0.9853 0.9605 0.8925 0.9719 0.9794
0.1897 28.4 1420 0.0529 0.9454 0.9704 0.9792 0.9896 0.9861 0.9355 0.9854 0.9597 0.8911 0.9715 0.9792
0.1737 28.8 1440 0.0538 0.9462 0.9735 0.9794 0.9912 0.9774 0.9520 0.9859 0.9593 0.8933 0.9719 0.9794
0.2112 29.2 1460 0.0557 0.9399 0.9634 0.9774 0.9909 0.9922 0.9070 0.9860 0.9549 0.8788 0.9684 0.9774
0.1971 29.6 1480 0.0538 0.9447 0.9749 0.9787 0.9923 0.9696 0.9630 0.9863 0.9569 0.8908 0.9711 0.9787
0.2033 30.0 1500 0.0519 0.9470 0.9728 0.9798 0.9934 0.9782 0.9469 0.9863 0.9601 0.8947 0.9724 0.9798
0.3146 30.4 1520 0.0504 0.9478 0.9713 0.9802 0.9915 0.9860 0.9365 0.9863 0.9613 0.8959 0.9728 0.9802
0.1865 30.8 1540 0.0537 0.9448 0.9713 0.9789 0.9945 0.9763 0.9431 0.9850 0.9590 0.8905 0.9712 0.9789
0.2039 31.2 1560 0.0502 0.9482 0.9743 0.9802 0.9915 0.9789 0.9525 0.9862 0.9611 0.8972 0.9730 0.9802
0.2195 31.6 1580 0.0506 0.9472 0.9729 0.9799 0.9934 0.9783 0.9470 0.9864 0.9602 0.8951 0.9725 0.9799
0.2176 32.0 1600 0.0502 0.9484 0.9727 0.9804 0.9936 0.9809 0.9435 0.9864 0.9614 0.8973 0.9731 0.9804
0.1906 32.4 1620 0.0519 0.9446 0.9681 0.9790 0.9902 0.9897 0.9244 0.9858 0.9588 0.8893 0.9711 0.9790
0.2276 32.8 1640 0.0539 0.9442 0.9757 0.9784 0.9913 0.9681 0.9676 0.9862 0.9565 0.8899 0.9708 0.9784
0.1454 33.2 1660 0.0506 0.9460 0.9690 0.9796 0.9920 0.9879 0.9270 0.9864 0.9599 0.8919 0.9718 0.9796
0.1789 33.6 1680 0.0493 0.9485 0.9731 0.9804 0.9919 0.9821 0.9454 0.9864 0.9615 0.8975 0.9732 0.9804
0.151 34.0 1700 0.0503 0.9467 0.9727 0.9796 0.9878 0.9849 0.9455 0.9846 0.9615 0.8940 0.9722 0.9796
0.1724 34.4 1720 0.0486 0.9486 0.9723 0.9805 0.9910 0.9856 0.9401 0.9863 0.9619 0.8976 0.9732 0.9805
0.1765 34.8 1740 0.0491 0.9487 0.9732 0.9805 0.9939 0.9797 0.9460 0.9864 0.9617 0.8980 0.9733 0.9805
0.1742 35.2 1760 0.0493 0.9486 0.9732 0.9804 0.9906 0.9837 0.9453 0.9860 0.9621 0.8975 0.9732 0.9804
0.162 35.6 1780 0.0489 0.9484 0.9717 0.9804 0.9919 0.9857 0.9374 0.9866 0.9614 0.8972 0.9731 0.9804
0.1057 36.0 1800 0.0495 0.9486 0.9748 0.9803 0.9913 0.9788 0.9544 0.9864 0.9614 0.8981 0.9733 0.9803
0.1874 36.4 1820 0.0495 0.9484 0.9747 0.9802 0.9924 0.9772 0.9547 0.9865 0.9608 0.8979 0.9731 0.9802
0.2005 36.8 1840 0.0482 0.9487 0.9708 0.9806 0.9936 0.9863 0.9325 0.9867 0.9619 0.8974 0.9733 0.9806
0.1634 37.2 1860 0.0495 0.9475 0.9728 0.9799 0.9880 0.9858 0.9445 0.9850 0.9620 0.8954 0.9726 0.9799
0.1518 37.6 1880 0.0504 0.9448 0.9670 0.9792 0.9919 0.9907 0.9184 0.9866 0.9585 0.8892 0.9711 0.9792
0.1764 38.0 1900 0.0473 0.9502 0.9742 0.9810 0.9916 0.9830 0.9479 0.9867 0.9629 0.9011 0.9741 0.9810
0.148 38.4 1920 0.0483 0.9480 0.9706 0.9803 0.9916 0.9882 0.9319 0.9868 0.9613 0.8959 0.9729 0.9803
0.1614 38.8 1940 0.0521 0.9448 0.9761 0.9787 0.9928 0.9663 0.9692 0.9869 0.9563 0.8913 0.9712 0.9787
0.1551 39.2 1960 0.0486 0.9482 0.9739 0.9801 0.9877 0.9846 0.9495 0.9849 0.9626 0.8970 0.9730 0.9801
0.1374 39.6 1980 0.0469 0.9503 0.9746 0.9811 0.9928 0.9806 0.9504 0.9868 0.9627 0.9015 0.9742 0.9811
0.1718 40.0 2000 0.0475 0.9496 0.9760 0.9807 0.9925 0.9761 0.9595 0.9869 0.9616 0.9003 0.9738 0.9807
0.1405 40.4 2020 0.0496 0.9456 0.9673 0.9795 0.9924 0.9911 0.9184 0.9869 0.9591 0.8908 0.9716 0.9795
0.1584 40.8 2040 0.0475 0.9499 0.9759 0.9808 0.9932 0.9761 0.9584 0.9870 0.9619 0.9007 0.9739 0.9808
0.1422 41.2 2060 0.0467 0.9503 0.9737 0.9811 0.9938 0.9814 0.9460 0.9869 0.9627 0.9011 0.9741 0.9811
0.1858 41.6 2080 0.0469 0.9502 0.9750 0.9810 0.9931 0.9791 0.9528 0.9869 0.9624 0.9013 0.9741 0.9810
0.1089 42.0 2100 0.0464 0.9502 0.9721 0.9812 0.9932 0.9864 0.9367 0.9872 0.9629 0.9006 0.9741 0.9812
0.1673 42.4 2120 0.0482 0.9476 0.9688 0.9803 0.9939 0.9890 0.9236 0.9869 0.9609 0.8949 0.9727 0.9803
0.1583 42.8 2140 0.0465 0.9502 0.9729 0.9811 0.9918 0.9861 0.9409 0.9869 0.9628 0.9009 0.9741 0.9811
0.1691 43.2 2160 0.0461 0.9506 0.9743 0.9812 0.9936 0.9809 0.9485 0.9869 0.9630 0.9020 0.9744 0.9812
0.1455 43.6 2180 0.0485 0.9464 0.9675 0.9799 0.9940 0.9902 0.9181 0.9871 0.9600 0.8921 0.9720 0.9799
0.1466 44.0 2200 0.0461 0.9508 0.9745 0.9813 0.9915 0.9836 0.9485 0.9869 0.9634 0.9023 0.9745 0.9813
0.155 44.4 2220 0.0458 0.9508 0.9742 0.9813 0.9941 0.9811 0.9473 0.9871 0.9630 0.9024 0.9744 0.9813
0.1192 44.8 2240 0.0458 0.9513 0.9747 0.9815 0.9942 0.9806 0.9492 0.9871 0.9635 0.9033 0.9747 0.9815
0.189 45.2 2260 0.0474 0.9490 0.9762 0.9804 0.9929 0.9741 0.9615 0.9871 0.9606 0.8993 0.9735 0.9804
0.1525 45.6 2280 0.0466 0.9490 0.9709 0.9808 0.9920 0.9890 0.9317 0.9871 0.9621 0.8979 0.9735 0.9808
0.1482 46.0 2300 0.0447 0.9514 0.9731 0.9816 0.9939 0.9850 0.9405 0.9872 0.9638 0.9031 0.9747 0.9816
0.1793 46.4 2320 0.0469 0.9500 0.9761 0.9809 0.9930 0.9760 0.9593 0.9873 0.9617 0.9010 0.9740 0.9809
0.1621 46.8 2340 0.0551 0.9380 0.9612 0.9768 0.9910 0.9944 0.8982 0.9869 0.9528 0.8742 0.9674 0.9768
0.1376 47.2 2360 0.0453 0.9514 0.9755 0.9815 0.9920 0.9816 0.9527 0.9871 0.9634 0.9037 0.9748 0.9815
0.2082 47.6 2380 0.0453 0.9508 0.9751 0.9812 0.9901 0.9839 0.9514 0.9864 0.9639 0.9022 0.9744 0.9812
0.1512 48.0 2400 0.0485 0.9458 0.9668 0.9797 0.9931 0.9918 0.9156 0.9873 0.9592 0.8908 0.9717 0.9797
0.1456 48.4 2420 0.0445 0.9516 0.9755 0.9815 0.9910 0.9831 0.9523 0.9869 0.9639 0.9040 0.9749 0.9815
0.1545 48.8 2440 0.0445 0.9515 0.9735 0.9816 0.9923 0.9864 0.9418 0.9873 0.9638 0.9034 0.9748 0.9816
0.1501 49.2 2460 0.0450 0.9512 0.9727 0.9815 0.9933 0.9866 0.9381 0.9874 0.9635 0.9026 0.9746 0.9815
0.1467 49.6 2480 0.0441 0.9516 0.9732 0.9817 0.9932 0.9864 0.9399 0.9874 0.9638 0.9037 0.9749 0.9817
0.1531 50.0 2500 0.0466 0.9490 0.9731 0.9806 0.9934 0.9811 0.9449 0.9873 0.9610 0.8986 0.9734 0.9806
0.1468 50.4 2520 0.0445 0.9516 0.9740 0.9816 0.9941 0.9830 0.9448 0.9875 0.9636 0.9037 0.9749 0.9816
0.1571 50.8 2540 0.0478 0.9481 0.9767 0.9800 0.9936 0.9702 0.9662 0.9875 0.9592 0.8976 0.9730 0.9800
0.1161 51.2 2560 0.0470 0.9477 0.9687 0.9803 0.9929 0.9909 0.9222 0.9875 0.9607 0.8948 0.9727 0.9803
0.1212 51.6 2580 0.0450 0.9504 0.9729 0.9812 0.9905 0.9882 0.9400 0.9867 0.9635 0.9010 0.9742 0.9812
0.1131 52.0 2600 0.0433 0.9526 0.9745 0.9820 0.9928 0.9853 0.9454 0.9875 0.9645 0.9058 0.9754 0.9820
0.1951 52.4 2620 0.0440 0.9520 0.9731 0.9818 0.9936 0.9869 0.9387 0.9877 0.9641 0.9042 0.9751 0.9818
0.1582 52.8 2640 0.0443 0.9521 0.9770 0.9817 0.9932 0.9775 0.9603 0.9877 0.9634 0.9054 0.9752 0.9817
0.1483 53.2 2660 0.0474 0.9471 0.9689 0.9801 0.9916 0.9911 0.9239 0.9872 0.9604 0.8938 0.9724 0.9801
0.1671 53.6 2680 0.0453 0.9509 0.9767 0.9812 0.9940 0.9750 0.9611 0.9876 0.9621 0.9029 0.9745 0.9812
0.1397 54.0 2700 0.0451 0.9503 0.9709 0.9813 0.9933 0.9895 0.9300 0.9876 0.9627 0.9004 0.9741 0.9813
0.1616 54.4 2720 0.0444 0.9517 0.9765 0.9816 0.9930 0.9784 0.9582 0.9876 0.9632 0.9045 0.9749 0.9816
0.1681 54.8 2740 0.0446 0.9512 0.9753 0.9814 0.9933 0.9800 0.9528 0.9876 0.9628 0.9033 0.9747 0.9814
0.112 55.2 2760 0.0460 0.9500 0.9749 0.9809 0.9956 0.9757 0.9534 0.9868 0.9623 0.9007 0.9740 0.9809
0.1436 55.6 2780 0.0431 0.9528 0.9750 0.9821 0.9938 0.9834 0.9477 0.9877 0.9645 0.9063 0.9755 0.9821
0.08 56.0 2800 0.0432 0.9527 0.9759 0.9820 0.9941 0.9804 0.9533 0.9876 0.9643 0.9063 0.9755 0.9820
0.1322 56.4 2820 0.0433 0.9525 0.9744 0.9820 0.9920 0.9864 0.9448 0.9875 0.9645 0.9054 0.9753 0.9820
0.1266 56.8 2840 0.0433 0.9528 0.9767 0.9820 0.9915 0.9818 0.9569 0.9872 0.9648 0.9063 0.9755 0.9820
0.1589 57.2 2860 0.0444 0.9508 0.9744 0.9813 0.9897 0.9862 0.9471 0.9865 0.9639 0.9021 0.9744 0.9813
0.161 57.6 2880 0.0435 0.9526 0.9768 0.9819 0.9932 0.9791 0.9580 0.9878 0.9639 0.9061 0.9754 0.9819
0.1559 58.0 2900 0.0444 0.9504 0.9707 0.9814 0.9936 0.9900 0.9285 0.9879 0.9628 0.9006 0.9742 0.9814
0.1452 58.4 2920 0.0424 0.9534 0.9749 0.9823 0.9937 0.9848 0.9461 0.9879 0.9649 0.9073 0.9758 0.9823
0.1368 58.8 2940 0.0425 0.9534 0.9758 0.9823 0.9926 0.9839 0.9509 0.9877 0.9651 0.9073 0.9758 0.9823
0.126 59.2 2960 0.0426 0.9536 0.9772 0.9823 0.9928 0.9803 0.9586 0.9878 0.9648 0.9081 0.9759 0.9823
0.1371 59.6 2980 0.0424 0.9538 0.9768 0.9824 0.9935 0.9808 0.9562 0.9879 0.9650 0.9084 0.9760 0.9824
0.1057 60.0 3000 0.0440 0.9511 0.9715 0.9816 0.9932 0.9896 0.9317 0.9878 0.9633 0.9021 0.9746 0.9816
0.1193 60.4 3020 0.0437 0.9512 0.9719 0.9816 0.9927 0.9895 0.9334 0.9878 0.9634 0.9025 0.9747 0.9816
0.1517 60.8 3040 0.0426 0.9534 0.9771 0.9822 0.9930 0.9799 0.9585 0.9879 0.9646 0.9077 0.9758 0.9822
0.1668 61.2 3060 0.0423 0.9535 0.9747 0.9824 0.9930 0.9862 0.9450 0.9879 0.9650 0.9075 0.9759 0.9824
0.1537 61.6 3080 0.0427 0.9532 0.9758 0.9822 0.9952 0.9800 0.9523 0.9877 0.9647 0.9073 0.9757 0.9822
0.1837 62.0 3100 0.0425 0.9526 0.9731 0.9821 0.9935 0.9882 0.9377 0.9880 0.9645 0.9054 0.9754 0.9821
0.1151 62.4 3120 0.0423 0.9531 0.9743 0.9823 0.9928 0.9869 0.9434 0.9879 0.9648 0.9067 0.9757 0.9823
0.1217 62.8 3140 0.0418 0.9543 0.9770 0.9826 0.9936 0.9813 0.9560 0.9881 0.9653 0.9094 0.9763 0.9826
0.1214 63.2 3160 0.0423 0.9535 0.9764 0.9823 0.9942 0.9804 0.9544 0.9879 0.9647 0.9078 0.9759 0.9823
0.153 63.6 3180 0.0424 0.9536 0.9776 0.9823 0.9937 0.9784 0.9605 0.9881 0.9646 0.9083 0.9760 0.9823
0.1196 64.0 3200 0.0420 0.9537 0.9744 0.9825 0.9935 0.9869 0.9428 0.9880 0.9652 0.9079 0.9760 0.9825
0.1371 64.4 3220 0.0423 0.9532 0.9739 0.9823 0.9929 0.9879 0.9410 0.9880 0.9649 0.9067 0.9757 0.9823
0.126 64.8 3240 0.0419 0.9538 0.9754 0.9825 0.9950 0.9826 0.9487 0.9878 0.9655 0.9083 0.9761 0.9825
0.1284 65.2 3260 0.0417 0.9544 0.9771 0.9826 0.9932 0.9815 0.9566 0.9880 0.9655 0.9096 0.9764 0.9826
0.1115 65.6 3280 0.0418 0.9536 0.9740 0.9825 0.9943 0.9868 0.9408 0.9879 0.9654 0.9076 0.9760 0.9825
0.0778 66.0 3300 0.0414 0.9544 0.9758 0.9827 0.9933 0.9848 0.9493 0.9881 0.9657 0.9094 0.9764 0.9827
0.1513 66.4 3320 0.0421 0.9531 0.9743 0.9823 0.9921 0.9879 0.9428 0.9878 0.9650 0.9066 0.9757 0.9823
0.1127 66.8 3340 0.0428 0.9523 0.9723 0.9820 0.9937 0.9893 0.9338 0.9881 0.9641 0.9045 0.9752 0.9820
0.1303 67.2 3360 0.0411 0.9547 0.9764 0.9828 0.9931 0.9841 0.9520 0.9881 0.9659 0.9100 0.9765 0.9828
0.1128 67.6 3380 0.0411 0.9545 0.9760 0.9828 0.9942 0.9835 0.9504 0.9881 0.9658 0.9097 0.9764 0.9828
0.1319 68.0 3400 0.0412 0.9547 0.9772 0.9828 0.9936 0.9815 0.9566 0.9882 0.9657 0.9103 0.9765 0.9828
0.1358 68.4 3420 0.0413 0.9542 0.9746 0.9827 0.9940 0.9865 0.9434 0.9882 0.9656 0.9088 0.9762 0.9827
0.1297 68.8 3440 0.0411 0.9544 0.9749 0.9827 0.9944 0.9855 0.9448 0.9881 0.9659 0.9092 0.9764 0.9827
0.1594 69.2 3460 0.0417 0.9535 0.9734 0.9825 0.9942 0.9882 0.9378 0.9882 0.9652 0.9073 0.9759 0.9825
0.1164 69.6 3480 0.0410 0.9547 0.9757 0.9829 0.9949 0.9837 0.9484 0.9881 0.9660 0.9100 0.9766 0.9829
0.1154 70.0 3500 0.0408 0.9549 0.9770 0.9828 0.9932 0.9827 0.9551 0.9882 0.9659 0.9106 0.9766 0.9828
0.0991 70.4 3520 0.0408 0.9550 0.9767 0.9829 0.9936 0.9833 0.9532 0.9883 0.9660 0.9107 0.9767 0.9829
0.1175 70.8 3540 0.0421 0.9528 0.9730 0.9822 0.9932 0.9893 0.9364 0.9883 0.9645 0.9057 0.9755 0.9822
0.1397 71.2 3560 0.0410 0.9546 0.9759 0.9828 0.9925 0.9859 0.9494 0.9881 0.9659 0.9098 0.9765 0.9828
0.1217 71.6 3580 0.0415 0.9538 0.9742 0.9826 0.9937 0.9874 0.9415 0.9882 0.9654 0.9079 0.9761 0.9826
0.116 72.0 3600 0.0407 0.9548 0.9756 0.9829 0.9938 0.9855 0.9476 0.9883 0.9660 0.9102 0.9766 0.9829
0.1383 72.4 3620 0.0407 0.9550 0.9771 0.9829 0.9931 0.9829 0.9554 0.9882 0.9660 0.9108 0.9767 0.9829
0.1034 72.8 3640 0.0412 0.9540 0.9745 0.9826 0.9930 0.9880 0.9424 0.9882 0.9655 0.9083 0.9762 0.9826
0.1148 73.2 3660 0.0413 0.9540 0.9741 0.9826 0.9939 0.9878 0.9405 0.9883 0.9655 0.9082 0.9761 0.9826
0.0963 73.6 3680 0.0407 0.9550 0.9768 0.9829 0.9928 0.9842 0.9532 0.9882 0.9661 0.9107 0.9767 0.9829
0.1363 74.0 3700 0.0405 0.9552 0.9770 0.9830 0.9926 0.9842 0.9542 0.9882 0.9664 0.9110 0.9768 0.9830
0.1434 74.4 3720 0.0404 0.9552 0.9762 0.9830 0.9940 0.9846 0.9501 0.9884 0.9663 0.9111 0.9768 0.9830
0.1595 74.8 3740 0.0409 0.9543 0.9745 0.9827 0.9934 0.9879 0.9422 0.9883 0.9657 0.9088 0.9763 0.9827
0.1251 75.2 3760 0.0404 0.9552 0.9763 0.9830 0.9933 0.9852 0.9502 0.9883 0.9663 0.9109 0.9768 0.9830
0.1277 75.6 3780 0.0417 0.9540 0.9786 0.9824 0.9932 0.9773 0.9653 0.9883 0.9647 0.9091 0.9762 0.9824
0.1045 76.0 3800 0.0404 0.9552 0.9764 0.9830 0.9941 0.9839 0.9511 0.9884 0.9662 0.9111 0.9768 0.9830
0.1569 76.4 3820 0.0409 0.9543 0.9744 0.9828 0.9936 0.9881 0.9414 0.9884 0.9656 0.9089 0.9763 0.9828
0.1106 76.8 3840 0.0406 0.9549 0.9759 0.9829 0.9928 0.9863 0.9484 0.9883 0.9661 0.9103 0.9766 0.9829
0.144 77.2 3860 0.0402 0.9554 0.9766 0.9831 0.9934 0.9845 0.9518 0.9884 0.9663 0.9114 0.9769 0.9831
0.1274 77.6 3880 0.0405 0.9553 0.9773 0.9830 0.9945 0.9812 0.9561 0.9884 0.9660 0.9113 0.9768 0.9830
0.1251 78.0 3900 0.0403 0.9551 0.9757 0.9830 0.9934 0.9865 0.9472 0.9884 0.9663 0.9107 0.9768 0.9830
0.1315 78.4 3920 0.0422 0.9525 0.9719 0.9821 0.9937 0.9906 0.9315 0.9884 0.9642 0.9048 0.9753 0.9821
0.1386 78.8 3940 0.0444 0.9498 0.9707 0.9811 0.9915 0.9917 0.9288 0.9878 0.9624 0.8992 0.9739 0.9811
0.1256 79.2 3960 0.0426 0.9521 0.9723 0.9820 0.9927 0.9903 0.9340 0.9882 0.9640 0.9041 0.9751 0.9820
0.16 79.6 3980 0.0407 0.9545 0.9746 0.9828 0.9941 0.9870 0.9427 0.9884 0.9658 0.9093 0.9764 0.9828
0.1227 80.0 4000 0.0399 0.9557 0.9769 0.9832 0.9942 0.9836 0.9529 0.9884 0.9666 0.9122 0.9771 0.9832
0.1308 80.4 4020 0.0403 0.9552 0.9761 0.9830 0.9930 0.9861 0.9492 0.9884 0.9663 0.9110 0.9768 0.9830
0.1643 80.8 4040 0.0407 0.9545 0.9752 0.9828 0.9924 0.9878 0.9455 0.9882 0.9660 0.9093 0.9764 0.9828
0.1349 81.2 4060 0.0400 0.9555 0.9758 0.9832 0.9942 0.9859 0.9472 0.9885 0.9665 0.9114 0.9770 0.9832
0.1093 81.6 4080 0.0406 0.9546 0.9747 0.9829 0.9933 0.9881 0.9429 0.9884 0.9659 0.9095 0.9765 0.9829
0.1028 82.0 4100 0.0402 0.9555 0.9781 0.9830 0.9930 0.9816 0.9597 0.9884 0.9662 0.9118 0.9770 0.9830
0.1353 82.4 4120 0.0406 0.9552 0.9775 0.9829 0.9949 0.9801 0.9574 0.9884 0.9660 0.9111 0.9768 0.9829
0.0916 82.8 4140 0.0403 0.9555 0.9783 0.9830 0.9936 0.9804 0.9608 0.9885 0.9660 0.9119 0.9770 0.9830
0.1316 83.2 4160 0.0399 0.9558 0.9774 0.9832 0.9933 0.9836 0.9554 0.9885 0.9667 0.9124 0.9771 0.9832
0.1502 83.6 4180 0.0401 0.9551 0.9751 0.9831 0.9938 0.9875 0.9439 0.9886 0.9662 0.9106 0.9768 0.9831
0.1012 84.0 4200 0.0401 0.9553 0.9759 0.9831 0.9932 0.9865 0.9481 0.9885 0.9664 0.9111 0.9769 0.9831
0.1199 84.4 4220 0.0399 0.9555 0.9755 0.9832 0.9944 0.9863 0.9459 0.9886 0.9666 0.9114 0.9770 0.9832
0.1112 84.8 4240 0.0399 0.9557 0.9773 0.9832 0.9930 0.9840 0.9548 0.9884 0.9666 0.9121 0.9771 0.9832
0.131 85.2 4260 0.0398 0.9558 0.9771 0.9832 0.9945 0.9827 0.9541 0.9885 0.9666 0.9122 0.9771 0.9832
0.0996 85.6 4280 0.0401 0.9551 0.9749 0.9830 0.9939 0.9877 0.9430 0.9886 0.9662 0.9105 0.9767 0.9830
0.1242 86.0 4300 0.0398 0.9556 0.9765 0.9832 0.9930 0.9859 0.9507 0.9885 0.9666 0.9117 0.9770 0.9832
0.1496 86.4 4320 0.0398 0.9557 0.9770 0.9832 0.9929 0.9850 0.9531 0.9884 0.9667 0.9121 0.9771 0.9832
0.1189 86.8 4340 0.0402 0.9550 0.9755 0.9830 0.9927 0.9876 0.9463 0.9884 0.9662 0.9105 0.9767 0.9830
0.1288 87.2 4360 0.0402 0.9549 0.9748 0.9830 0.9936 0.9881 0.9427 0.9886 0.9660 0.9100 0.9766 0.9830
0.1462 87.6 4380 0.0397 0.9557 0.9765 0.9832 0.9935 0.9855 0.9504 0.9886 0.9666 0.9121 0.9771 0.9832
0.1011 88.0 4400 0.0396 0.9560 0.9775 0.9833 0.9933 0.9838 0.9554 0.9885 0.9668 0.9127 0.9772 0.9833
0.1252 88.4 4420 0.0399 0.9555 0.9756 0.9832 0.9936 0.9871 0.9461 0.9886 0.9665 0.9114 0.9770 0.9832
0.1338 88.8 4440 0.0396 0.9560 0.9768 0.9833 0.9941 0.9844 0.9519 0.9886 0.9668 0.9126 0.9772 0.9833
0.122 89.2 4460 0.0396 0.9561 0.9774 0.9833 0.9941 0.9831 0.9550 0.9887 0.9667 0.9129 0.9773 0.9833
0.0999 89.6 4480 0.0399 0.9557 0.9765 0.9832 0.9932 0.9857 0.9504 0.9885 0.9666 0.9119 0.9771 0.9832
0.1092 90.0 4500 0.0395 0.9561 0.9768 0.9834 0.9941 0.9847 0.9515 0.9887 0.9669 0.9128 0.9773 0.9834
0.0858 90.4 4520 0.0399 0.9555 0.9756 0.9832 0.9937 0.9871 0.9460 0.9887 0.9665 0.9113 0.9770 0.9832
0.1322 90.8 4540 0.0396 0.9561 0.9776 0.9833 0.9932 0.9839 0.9556 0.9886 0.9668 0.9129 0.9773 0.9833
0.134 91.2 4560 0.0396 0.9561 0.9773 0.9833 0.9941 0.9834 0.9544 0.9887 0.9668 0.9129 0.9773 0.9833
0.0948 91.6 4580 0.0396 0.9561 0.9768 0.9833 0.9935 0.9851 0.9519 0.9886 0.9668 0.9127 0.9773 0.9833
0.0818 92.0 4600 0.0396 0.9560 0.9766 0.9833 0.9936 0.9855 0.9505 0.9887 0.9668 0.9125 0.9772 0.9833
0.1144 92.4 4620 0.0398 0.9561 0.9781 0.9833 0.9942 0.9812 0.9588 0.9887 0.9665 0.9129 0.9773 0.9833
0.116 92.8 4640 0.0395 0.9561 0.9766 0.9834 0.9936 0.9856 0.9506 0.9887 0.9669 0.9127 0.9773 0.9834
0.0954 93.2 4660 0.0394 0.9562 0.9772 0.9834 0.9936 0.9845 0.9536 0.9887 0.9669 0.9131 0.9774 0.9834
0.1232 93.6 4680 0.0395 0.9560 0.9769 0.9833 0.9931 0.9854 0.9523 0.9885 0.9669 0.9126 0.9772 0.9833
0.1176 94.0 4700 0.0396 0.9559 0.9761 0.9833 0.9943 0.9857 0.9484 0.9887 0.9668 0.9124 0.9772 0.9833
0.1237 94.4 4720 0.0394 0.9562 0.9774 0.9834 0.9935 0.9842 0.9544 0.9886 0.9669 0.9131 0.9773 0.9834
0.0952 94.8 4740 0.0394 0.9561 0.9767 0.9834 0.9940 0.9850 0.9511 0.9887 0.9669 0.9128 0.9773 0.9834
0.1022 95.2 4760 0.0394 0.9562 0.9769 0.9834 0.9938 0.9848 0.9520 0.9887 0.9669 0.9129 0.9773 0.9834
0.0975 95.6 4780 0.0395 0.9560 0.9766 0.9833 0.9935 0.9857 0.9506 0.9887 0.9668 0.9126 0.9772 0.9833
0.1356 96.0 4800 0.0394 0.9562 0.9769 0.9834 0.9939 0.9847 0.9522 0.9887 0.9669 0.9130 0.9773 0.9834
0.1112 96.4 4820 0.0394 0.9561 0.9770 0.9834 0.9933 0.9852 0.9524 0.9886 0.9669 0.9128 0.9773 0.9834
0.1293 96.8 4840 0.0394 0.9561 0.9769 0.9834 0.9935 0.9851 0.9519 0.9887 0.9669 0.9128 0.9773 0.9834
0.1046 97.2 4860 0.0394 0.9561 0.9765 0.9834 0.9942 0.9851 0.9503 0.9887 0.9669 0.9128 0.9773 0.9834
0.0884 97.6 4880 0.0394 0.9561 0.9768 0.9834 0.9937 0.9851 0.9515 0.9887 0.9669 0.9128 0.9773 0.9834
0.1165 98.0 4900 0.0395 0.9561 0.9769 0.9833 0.9933 0.9854 0.9521 0.9886 0.9668 0.9128 0.9773 0.9833
0.1203 98.4 4920 0.0395 0.9559 0.9763 0.9833 0.9935 0.9863 0.9491 0.9887 0.9668 0.9124 0.9772 0.9833
0.101 98.8 4940 0.0394 0.9561 0.9766 0.9834 0.9937 0.9855 0.9507 0.9887 0.9669 0.9127 0.9773 0.9834
0.0945 99.2 4960 0.0394 0.9563 0.9775 0.9834 0.9934 0.9840 0.9553 0.9887 0.9669 0.9132 0.9774 0.9834
0.115 99.6 4980 0.0394 0.9561 0.9765 0.9834 0.9939 0.9855 0.9501 0.9887 0.9669 0.9128 0.9773 0.9834
0.1029 100.0 5000 0.0393 0.9563 0.9774 0.9834 0.9933 0.9845 0.9543 0.9886 0.9670 0.9131 0.9774 0.9834

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.6.0+cu124
  • Datasets 3.2.0
  • Tokenizers 0.19.1
Downloads last month
12
Safetensors
Model size
3.72M params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for greenkwd/lr0.0001_bs16_0617_1957

Base model

nvidia/mit-b0
Finetuned
(456)
this model