wandb: WARNING The get_url method is deprecated and will be removed in a future release. Please use `run.url` instead. [wandb] logging to https://wandb.ai/seungeun-goodgang-labs/animasync-v3-face/runs/2n5n3rfp epoch 0 train l1=0.2229 vel=0.0125 val l1=0.0784 vel=0.0025 lr=3.74e-04 4.1s → saved best (val l1=0.0784) epoch 1 train l1=0.0824 vel=0.0026 val l1=0.0782 vel=0.0026 lr=7.48e-04 3.4s → saved best (val l1=0.0782) epoch 2 train l1=0.0825 vel=0.0026 val l1=0.0786 vel=0.0025 lr=1.00e-03 3.4s epoch 3 train l1=0.0823 vel=0.0025 val l1=0.0785 vel=0.0025 lr=9.98e-04 3.5s epoch 4 train l1=0.0823 vel=0.0025 val l1=0.0782 vel=0.0025 lr=9.94e-04 3.5s → saved best (val l1=0.0782) epoch 5 train l1=0.0830 vel=0.0025 val l1=0.0780 vel=0.0026 lr=9.88e-04 3.4s → saved best (val l1=0.0780) epoch 6 train l1=0.0825 vel=0.0025 val l1=0.0784 vel=0.0025 lr=9.80e-04 3.5s epoch 7 train l1=0.0826 vel=0.0025 val l1=0.0785 vel=0.0025 lr=9.69e-04 3.5s epoch 8 train l1=0.0822 vel=0.0025 val l1=0.0784 vel=0.0025 lr=9.57e-04 3.5s epoch 9 train l1=0.0829 vel=0.0025 val l1=0.0782 vel=0.0025 lr=9.42e-04 3.4s epoch 10 train l1=0.0827 vel=0.0025 val l1=0.0786 vel=0.0025 lr=9.26e-04 3.5s epoch 11 train l1=0.0830 vel=0.0025 val l1=0.0784 vel=0.0025 lr=9.07e-04 3.4s epoch 12 train l1=0.0825 vel=0.0025 val l1=0.0783 vel=0.0025 lr=8.87e-04 3.5s epoch 13 train l1=0.0821 vel=0.0025 val l1=0.0783 vel=0.0025 lr=8.65e-04 3.6s epoch 14 train l1=0.0825 vel=0.0025 val l1=0.0783 vel=0.0025 lr=8.42e-04 3.5s epoch 15 train l1=0.0819 vel=0.0025 val l1=0.0783 vel=0.0025 lr=8.17e-04 3.4s epoch 16 train l1=0.0831 vel=0.0025 val l1=0.0781 vel=0.0025 lr=7.90e-04 3.4s epoch 17 train l1=0.0826 vel=0.0025 val l1=0.0785 vel=0.0025 lr=7.63e-04 3.4s epoch 18 train l1=0.0826 vel=0.0025 val l1=0.0781 vel=0.0025 lr=7.34e-04 3.4s epoch 19 train l1=0.0820 vel=0.0025 val l1=0.0784 vel=0.0025 lr=7.04e-04 3.5s epoch 20 train l1=0.0823 vel=0.0025 val l1=0.0783 vel=0.0025 lr=6.73e-04 3.4s epoch 21 train l1=0.0828 vel=0.0025 val l1=0.0785 vel=0.0025 lr=6.42e-04 3.4s epoch 22 train l1=0.0826 vel=0.0025 val l1=0.0783 vel=0.0025 lr=6.10e-04 3.5s epoch 23 train l1=0.0824 vel=0.0025 val l1=0.0783 vel=0.0025 lr=5.77e-04 3.5s epoch 24 train l1=0.0825 vel=0.0025 val l1=0.0785 vel=0.0025 lr=5.44e-04 3.5s epoch 25 train l1=0.0824 vel=0.0025 val l1=0.0785 vel=0.0025 lr=5.11e-04 3.5s epoch 26 train l1=0.0827 vel=0.0025 val l1=0.0784 vel=0.0025 lr=4.78e-04 3.5s epoch 27 train l1=0.0824 vel=0.0025 val l1=0.0785 vel=0.0025 lr=4.45e-04 3.5s epoch 28 train l1=0.0815 vel=0.0026 val l1=0.0780 vel=0.0025 lr=4.12e-04 3.5s → saved best (val l1=0.0780) epoch 29 train l1=0.0827 vel=0.0026 val l1=0.0769 vel=0.0028 lr=3.80e-04 3.6s → saved best (val l1=0.0769) epoch 30 train l1=0.0810 vel=0.0029 val l1=0.0765 vel=0.0026 lr=3.48e-04 3.4s → saved best (val l1=0.0765) epoch 31 train l1=0.0773 vel=0.0041 val l1=0.0717 vel=0.0039 lr=3.16e-04 3.5s → saved best (val l1=0.0717) epoch 32 train l1=0.0748 vel=0.0043 val l1=0.0709 vel=0.0031 lr=2.86e-04 3.5s → saved best (val l1=0.0709) epoch 33 train l1=0.0727 vel=0.0044 val l1=0.0688 vel=0.0038 lr=2.56e-04 3.6s → saved best (val l1=0.0688) epoch 34 train l1=0.0672 vel=0.0053 val l1=0.0604 vel=0.0044 lr=2.28e-04 3.6s → saved best (val l1=0.0604) epoch 35 train l1=0.0628 vel=0.0056 val l1=0.0582 vel=0.0046 lr=2.01e-04 3.7s → saved best (val l1=0.0582) epoch 36 train l1=0.0585 vel=0.0061 val l1=0.0532 vel=0.0051 lr=1.75e-04 3.7s → saved best (val l1=0.0532) epoch 37 train l1=0.0557 vel=0.0062 val l1=0.0504 vel=0.0051 lr=1.50e-04 3.8s → saved best (val l1=0.0504) epoch 38 train l1=0.0531 vel=0.0063 val l1=0.0477 vel=0.0052 lr=1.27e-04 3.6s → saved best (val l1=0.0477) epoch 39 train l1=0.0507 vel=0.0062 val l1=0.0459 vel=0.0050 lr=1.06e-04 3.8s → saved best (val l1=0.0459) epoch 40 train l1=0.0501 vel=0.0061 val l1=0.0449 vel=0.0049 lr=8.66e-05 3.6s → saved best (val l1=0.0449) epoch 41 train l1=0.0490 vel=0.0059 val l1=0.0442 vel=0.0050 lr=6.89e-05 3.6s → saved best (val l1=0.0442) epoch 42 train l1=0.0486 vel=0.0058 val l1=0.0442 vel=0.0048 lr=5.30e-05 3.4s epoch 43 train l1=0.0482 vel=0.0057 val l1=0.0437 vel=0.0047 lr=3.91e-05 3.5s → saved best (val l1=0.0437) epoch 44 train l1=0.0481 vel=0.0057 val l1=0.0436 vel=0.0047 lr=2.73e-05 3.5s → saved best (val l1=0.0436) epoch 45 train l1=0.0478 vel=0.0056 val l1=0.0432 vel=0.0046 lr=1.75e-05 3.6s → saved best (val l1=0.0432) epoch 46 train l1=0.0473 vel=0.0056 val l1=0.0430 vel=0.0046 lr=9.88e-06 3.5s → saved best (val l1=0.0430) epoch 47 train l1=0.0474 vel=0.0056 val l1=0.0429 vel=0.0046 lr=4.40e-06 3.5s → saved best (val l1=0.0429) epoch 48 train l1=0.0473 vel=0.0055 val l1=0.0430 vel=0.0045 lr=1.10e-06 3.5s epoch 49 train l1=0.0473 vel=0.0055 val l1=0.0428 vel=0.0045 lr=0.00e+00 3.4s → saved best (val l1=0.0428) Done. best val l1: 0.0428 checkpoints: /dataset/kemix-engine/package/face/animasync-face-v3/models/v3_face/checkpoints