-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathlog.txt
566 lines (554 loc) · 49.7 KB
/
log.txt
1
2
3
4
5
6
7
8
9
10
unsupervised_epochs=9 classifier_epochs=40 num_tra
Encoded feature size: 1024
Validation sanity check: 0it [00:00, ?it/s]Validation sanity check: 0%| | 0/2 [00:00<?, ?it/s]Validation sanity check: 50%|█████ | 1/2 [00:01<00:01, 1.61s/it] Training: 0it [00:00, ?it/s]Training: 0%| | 0/548 [00:00<?, ?it/s]Epoch 0: 0%| | 0/548 [00:00<?, ?it/s] Epoch 0: 0%| | 1/548 [00:00<04:17, 2.12it/s]Epoch 0: 0%| | 1/548 [00:00<04:17, 2.12it/s, loss=0.965, v_num=_tra]Epoch 0: 0%| | 2/548 [00:00<02:13, 4.08it/s, loss=0.894, v_num=_tra]Epoch 0: 1%| | 3/548 [00:00<01:31, 5.95it/s, loss=0.781, v_num=_tra]Epoch 0: 1%| | 4/548 [00:00<01:10, 7.69it/s, loss=0.687, v_num=_tra]Epoch 0: 1%| | 5/548 [00:00<00:58, 9.26it/s, loss=0.617, v_num=_tra]Epoch 0: 1%| | 6/548 [00:00<00:50, 10.82it/s, loss=0.565, v_num=_tra]Epoch 0: 1%|▏ | 7/548 [00:00<00:43, 12.32it/s, loss=0.522, v_num=_tra]Epoch 0: 1%|▏ | 8/548 [00:00<00:39, 13.73it/s, loss=0.522, v_num=_tra]Epoch 0: 1%|▏ | 8/548 [00:00<00:39, 13.73it/s, loss=0.483, v_num=_tra]Epoch 0: 2%|▏ | 9/548 [00:00<00:35, 14.99it/s, loss=0.452, v_num=_tra]Epoch 0: 2%|▏ | 10/548 [00:00<00:33, 16.26it/s, loss=0.427, v_num=_tra]Epoch 0: 2%|▏ | 11/548 [00:00<00:30, 17.46it/s, loss=0.405, v_num=_tra]Epoch 0: 2%|▏ | 12/548 [00:00<00:28, 18.60it/s, loss=0.386, v_num=_tra]Epoch 0: 2%|▏ | 13/548 [00:00<00:27, 19.65it/s, loss=0.369, v_num=_tra]Epoch 0: 3%|▎ | 14/548 [00:00<00:25, 20.69it/s, loss=0.354, v_num=_tra]Epoch 0: 3%|▎ | 15/548 [00:00<00:24, 21.69it/s, loss=0.354, v_num=_tra]Epoch 0: 3%|▎ | 15/548 [00:00<00:24, 21.69it/s, loss=0.34, v_num=_tra] Epoch 0: 3%|▎ | 16/548 [00:00<00:23, 22.63it/s, loss=0.328, v_num=_tra]Epoch 0: 3%|▎ | 17/548 [00:00<00:22, 23.45it/s, loss=0.317, v_num=_tra]Epoch 0: 3%|▎ | 18/548 [00:00<00:21, 24.32it/s, loss=0.307, v_num=_tra]Epoch 0: 3%|▎ | 19/548 [00:00<00:21, 25.17it/s, loss=0.298, v_num=_tra]Epoch 0: 4%|▎ | 20/548 [00:00<00:20, 25.99it/s, loss=0.29, v_num=_tra] Epoch 0: 4%|▍ | 21/548 [00:00<00:19, 26.77it/s, loss=0.248, v_num=_tra]Epoch 0: 4%|▍ | 22/548 [00:00<00:19, 27.53it/s, loss=0.248, v_num=_tra]Epoch 0: 4%|▍ | 22/548 [00:00<00:19, 27.52it/s, loss=0.213, v_num=_tra]Epoch 0: 4%|▍ | 23/548 [00:00<00:18, 28.26it/s, loss=0.192, v_num=_tra]Epoch 0: 4%|▍ | 24/548 [00:00<00:18, 28.96it/s, loss=0.178, v_num=_tra]Epoch 0: 5%|▍ | 25/548 [00:00<00:17, 29.54it/s, loss=0.167, v_num=_tra]Epoch 0: 5%|▍ | 26/548 [00:00<00:17, 30.20it/s, loss=0.157, v_num=_tra]Epoch 0: 5%|▍ | 27/548 [00:00<00:16, 30.84it/s, loss=0.15, v_num=_tra] Epoch 0: 5%|▌ | 28/548 [00:00<00:16, 31.46it/s, loss=0.145, v_num=_tra]Epoch 0: 5%|▌ | 29/548 [00:00<00:16, 32.05it/s, loss=0.145, v_num=_tra]Epoch 0: 5%|▌ | 29/548 [00:00<00:16, 32.04it/s, loss=0.14, v_num=_tra] Epoch 0: 5%|▌ | 30/548 [00:00<00:15, 32.50it/s, loss=0.136, v_num=_tra]Epoch 0: 6%|▌ | 31/548 [00:00<00:15, 32.99it/s, loss=0.132, v_num=_tra]Epoch 0: 6%|▌ | 32/548 [00:00<00:15, 33.49it/s, loss=0.128, v_num=_tra]Epoch 0: 6%|▌ | 33/548 [00:00<00:15, 33.94it/s, loss=0.125, v_num=_tra]Epoch 0: 6%|▌ | 34/548 [00:00<00:14, 34.45it/s, loss=0.123, v_num=_tra]Epoch 0: 6%|▋ | 35/548 [00:01<00:14, 34.94it/s, loss=0.12, v_num=_tra] Epoch 0: 7%|▋ | 36/548 [00:01<00:14, 35.43it/s, loss=0.12, v_num=_tra]Epoch 0: 7%|▋ | 36/548 [00:01<00:14, 35.42it/s, loss=0.118, v_num=_tra]Epoch 0: 7%|▋ | 37/548 [00:01<00:14, 35.88it/s, loss=0.116, v_num=_tra]Epoch 0: 7%|▋ | 38/548 [00:01<00:14, 36.34it/s, loss=0.114, v_num=_tra]Epoch 0: 7%|▋ | 39/548 [00:01<00:13, 36.78it/s, loss=0.112, v_num=_tra]Epoch 0: 7%|▋ | 40/548 [00:01<00:13, 37.14it/s, loss=0.109, v_num=_tra]Epoch 0: 7%|▋ | 41/548 [00:01<00:13, 37.51it/s, loss=0.108, v_num=_tra]Epoch 0: 8%|▊ | 42/548 [00:01<00:13, 37.91it/s, loss=0.106, v_num=_tra]Epoch 0: 8%|▊ | 43/548 [00:01<00:13, 38.27it/s, loss=0.106, v_num=_tra]Epoch 0: 8%|▊ | 43/548 [00:01<00:13, 38.26it/s, loss=0.105, v_num=_tra]Epoch 0: 8%|▊ | 44/548 [00:01<00:13, 38.65it/s, loss=0.103, v_num=_tra]Epoch 0: 8%|▊ | 45/548 [00:01<00:12, 38.98it/s, loss=0.102, v_num=_tra]Epoch 0: 8%|▊ | 46/548 [00:01<00:12, 39.40it/s, loss=0.101, v_num=_tra]Epoch 0: 9%|▊ | 47/548 [00:01<00:12, 39.83it/s, loss=0.0994, v_num=_tra]Epoch 0: 9%|▉ | 48/548 [00:01<00:12, 40.25it/s, loss=0.0978, v_num=_tra]Epoch 0: 9%|▉ | 49/548 [00:01<00:12, 40.65it/s, loss=0.0965, v_num=_tra]Epoch 0: 9%|▉ | 50/548 [00:01<00:12, 41.04it/s, loss=0.0953, v_num=_tra]Epoch 0: 9%|▉ | 51/548 [00:01<00:11, 41.43it/s, loss=0.0953, v_num=_tra]Epoch 0: 9%|▉ | 51/548 [00:01<00:11, 41.43it/s, loss=0.0943, v_num=_tra]Epoch 0: 9%|▉ | 52/548 [00:01<00:11, 41.81it/s, loss=0.0929, v_num=_tra]Epoch 0: 10%|▉ | 53/548 [00:01<00:11, 42.18it/s, loss=0.0918, v_num=_tra]Epoch 0: 10%|▉ | 54/548 [00:01<00:11, 42.54it/s, loss=0.0904, v_num=_tra]Epoch 0: 10%|█ | 55/548 [00:01<00:11, 42.85it/s, loss=0.0891, v_num=_tra]Epoch 0: 10%|█ | 56/548 [00:01<00:11, 43.13it/s, loss=0.088, v_num=_tra] Epoch 0: 10%|█ | 57/548 [00:01<00:11, 43.41it/s, loss=0.0868, v_num=_tra]Epoch 0: 11%|█ | 58/548 [00:01<00:11, 43.64it/s, loss=0.0857, v_num=_tra]Epoch 0: 11%|█ | 59/548 [00:01<00:11, 43.86it/s, loss=0.0857, v_num=_tra]Epoch 0: 11%|█ | 59/548 [00:01<00:11, 43.86it/s, loss=0.0846, v_num=_tra]Epoch 0: 11%|█ | 60/548 [00:01<00:11, 44.13it/s, loss=0.0835, v_num=_tra]Epoch 0: 11%|█ | 61/548 [00:01<00:10, 44.38it/s, loss=0.0825, v_num=_tra]Epoch 0: 11%|█▏ | 62/548 [00:01<00:10, 44.63it/s, loss=0.0812, v_num=_tra]Epoch 0: 11%|█▏ | 63/548 [00:01<00:10, 44.81it/s, loss=0.0806, v_num=_tra]Epoch 0: 12%|█▏ | 64/548 [00:01<00:10, 44.99it/s, loss=0.0793, v_num=_tra]Epoch 0: 12%|█▏ | 65/548 [00:01<00:10, 45.22it/s, loss=0.0784, v_num=_tra]Epoch 0: 12%|█▏ | 66/548 [00:01<00:10, 45.42it/s, loss=0.0774, v_num=_tra]Epoch 0: 12%|█▏ | 67/548 [00:01<00:10, 45.63it/s, loss=0.0774, v_num=_tra]Epoch 0: 12%|█▏ | 67/548 [00:01<00:10, 45.62it/s, loss=0.0763, v_num=_tra]Epoch 0: 12%|█▏ | 68/548 [00:01<00:10, 45.79it/s, loss=0.0755, v_num=_tra]Epoch 0: 13%|█▎ | 69/548 [00:01<00:10, 45.88it/s, loss=0.0749, v_num=_tra]Epoch 0: 13%|█▎ | 70/548 [00:01<00:10, 46.04it/s, loss=0.074, v_num=_tra] Epoch 0: 13%|█▎ | 71/548 [00:01<00:10, 46.23it/s, loss=0.0732, v_num=_tra]Epoch 0: 13%|█▎ | 72/548 [00:01<00:10, 46.38it/s, loss=0.0725, v_num=_tra]Epoch 0: 13%|█▎ | 73/548 [00:01<00:10, 46.59it/s, loss=0.0716, v_num=_tra]Epoch 0: 14%|█▎ | 74/548 [00:01<00:10, 46.78it/s, loss=0.0709, v_num=_tra]Epoch 0: 14%|█▎ | 75/548 [00:01<00:10, 46.98it/s, loss=0.0709, v_num=_tra]Epoch 0: 14%|█▎ | 75/548 [00:01<00:10, 46.97it/s, loss=0.0703, v_num=_tra]Epoch 0: 14%|█▍ | 76/548 [00:01<00:09, 47.22it/s, loss=0.0698, v_num=_tra]Epoch 0: 14%|█▍ | 77/548 [00:01<00:09, 47.39it/s, loss=0.0692, v_num=_tra]Epoch 0: 14%|█▍ | 78/548 [00:01<00:09, 47.56it/s, loss=0.0685, v_num=_tra]Epoch 0: 14%|█▍ | 79/548 [00:01<00:09, 47.80it/s, loss=0.0676, v_num=_tra]Epoch 0: 15%|█▍ | 80/548 [00:01<00:09, 47.98it/s, loss=0.067, v_num=_tra] Epoch 0: 15%|█▍ | 81/548 [00:01<00:09, 48.16it/s, loss=0.0664, v_num=_tra]Epoch 0: 15%|█▍ | 82/548 [00:01<00:09, 48.33it/s, loss=0.0661, v_num=_tra]Epoch 0: 15%|█▌ | 83/548 [00:01<00:09, 48.44it/s, loss=0.0661, v_num=_tra]Epoch 0: 15%|█▌ | 83/548 [00:01<00:09, 48.44it/s, loss=0.0653, v_num=_tra]Epoch 0: 15%|█▌ | 84/548 [00:01<00:09, 48.59it/s, loss=0.0649, v_num=_tra]Epoch 0: 16%|█▌ | 85/548 [00:01<00:09, 48.65it/s, loss=0.0643, v_num=_tra]Epoch 0: 16%|█▌ | 86/548 [00:01<00:09, 48.66it/s, loss=0.0637, v_num=_tra]Epoch 0: 16%|█▌ | 87/548 [00:01<00:09, 48.75it/s, loss=0.0628, v_num=_tra]Epoch 0: 16%|█▌ | 88/548 [00:01<00:09, 48.95it/s, loss=0.0621, v_num=_tra]Epoch 0: 16%|█▌ | 89/548 [00:01<00:09, 49.11it/s, loss=0.0613, v_num=_tra]Epoch 0: 16%|█▋ | 90/548 [00:01<00:09, 49.30it/s, loss=0.0607, v_num=_tra]Epoch 0: 17%|█▋ | 91/548 [00:01<00:09, 49.46it/s, loss=0.0607, v_num=_tra]Epoch 0: 17%|█▋ | 91/548 [00:01<00:09, 49.45it/s, loss=0.0603, v_num=_tra]Epoch 0: 17%|█▋ | 92/548 [00:01<00:09, 49.56it/s, loss=0.0595, v_num=_tra]Epoch 0: 17%|█▋ | 93/548 [00:01<00:09, 49.69it/s, loss=0.0591, v_num=_tra]Epoch 0: 17%|█▋ | 94/548 [00:01<00:09, 49.76it/s, loss=0.0584, v_num=_tra]Epoch 0: 17%|█▋ | 95/548 [00:01<00:09, 49.89it/s, loss=0.058, v_num=_tra] Epoch 0: 18%|█▊ | 96/548 [00:01<00:09, 50.02it/s, loss=0.0576, v_num=_tra]Epoch 0: 18%|█▊ | 97/548 [00:01<00:08, 50.13it/s, loss=0.0572, v_num=_tra]Epoch 0: 18%|█▊ | 98/548 [00:01<00:08, 50.32it/s, loss=0.0567, v_num=_tra]Epoch 0: 18%|█▊ | 99/548 [00:01<00:08, 50.44it/s, loss=0.0567, v_num=_tra]Epoch 0: 18%|█▊ | 99/548 [00:01<00:08, 50.43it/s, loss=0.0562, v_num=_tra]Epoch 0: 18%|█▊ | 100/548 [00:01<00:08, 50.44it/s, loss=0.0556, v_num=_tra]Epoch 0: 18%|█▊ | 101/548 [00:01<00:08, 50.62it/s, loss=0.0551, v_num=_tra]Epoch 0: 19%|█▊ | 102/548 [00:02<00:08, 50.75it/s, loss=0.0545, v_num=_tra]Epoch 0: 19%|█▉ | 103/548 [00:02<00:08, 50.84it/s, loss=0.0542, v_num=_tra]Epoch 0: 19%|█▉ | 104/548 [00:02<00:08, 50.90it/s, loss=0.0536, v_num=_tra]Epoch 0: 19%|█▉ | 105/548 [00:02<00:08, 51.02it/s, loss=0.0533, v_num=_tra]Epoch 0: 19%|█▉ | 106/548 [00:02<00:08, 51.12it/s, loss=0.0531, v_num=_tra]Epoch 0: 20%|█▉ | 107/548 [00:02<00:08, 51.30it/s, loss=0.0531, v_num=_tra]Epoch 0: 20%|█▉ | 107/548 [00:02<00:08, 51.29it/s, loss=0.0527, v_num=_tra]Epoch 0: 20%|█▉ | 108/548 [00:02<00:08, 51.39it/s, loss=0.0522, v_num=_tra]Epoch 0: 20%|█▉ | 109/548 [00:02<00:08, 51.50it/s, loss=0.052, v_num=_tra] Epoch 0: 20%|██ | 110/548 [00:02<00:08, 51.66it/s, loss=0.0517, v_num=_tra]Epoch 0: 20%|██ | 111/548 [00:02<00:08, 51.76it/s, loss=0.0513, v_num=_tra]Epoch 0: 20%|██ | 112/548 [00:02<00:08, 51.92it/s, loss=0.0509, v_num=_tra]Epoch 0: 21%|██ | 113/548 [00:02<00:08, 52.01it/s, loss=0.0505, v_num=_tra]Epoch 0: 21%|██ | 114/548 [00:02<00:08, 52.02it/s, loss=0.0503, v_num=_tra]Epoch 0: 21%|██ | 115/548 [00:02<00:08, 52.04it/s, loss=0.0503, v_num=_tra]Epoch 0: 21%|██ | 115/548 [00:02<00:08, 52.03it/s, loss=0.0497, v_num=_tra]Epoch 0: 21%|██ | 116/548 [00:02<00:08, 52.18it/s, loss=0.049, v_num=_tra] Epoch 0: 21%|██▏ | 117/548 [00:02<00:08, 52.28it/s, loss=0.0486, v_num=_tra]Epoch 0: 22%|██▏ | 118/548 [00:02<00:08, 52.38it/s, loss=0.0485, v_num=_tra]Epoch 0: 22%|██▏ | 119/548 [00:02<00:08, 52.48it/s, loss=0.0483, v_num=_tra]Epoch 0: 22%|██▏ | 120/548 [00:02<00:08, 52.58it/s, loss=0.0479, v_num=_tra]Epoch 0: 22%|██▏ | 121/548 [00:02<00:08, 52.68it/s, loss=0.0474, v_num=_tra]Epoch 0: 22%|██▏ | 122/548 [00:02<00:08, 52.75it/s, loss=0.0472, v_num=_tra]Epoch 0: 22%|██▏ | 123/548 [00:02<00:08, 52.83it/s, loss=0.0472, v_num=_tra]Epoch 0: 22%|██▏ | 123/548 [00:02<00:08, 52.83it/s, loss=0.0467, v_num=_tra]Epoch 0: 23%|██▎ | 124/548 [00:02<00:08, 52.91it/s, loss=0.0464, v_num=_tra]Epoch 0: 23%|██▎ | 125/548 [00:02<00:07, 52.94it/s, loss=0.046, v_num=_tra] Epoch 0: 23%|██▎ | 126/548 [00:02<00:07, 53.03it/s, loss=0.0456, v_num=_tra]Epoch 0: 23%|██▎ | 127/548 [00:02<00:07, 53.17it/s, loss=0.0454, v_num=_tra]Epoch 0: 23%|██▎ | 128/548 [00:02<00:07, 53.26it/s, loss=0.0452, v_num=_tra]Epoch 0: 24%|██▎ | 129/548 [00:02<00:07, 53.28it/s, loss=0.045, v_num=_tra] Epoch 0: 24%|██▎ | 130/548 [00:02<00:07, 53.33it/s, loss=0.0446, v_num=_tra]Epoch 0: 24%|██▍ | 131/548 [00:02<00:07, 53.34it/s, loss=0.0446, v_num=_tra]Epoch 0: 24%|██▍ | 131/548 [00:02<00:07, 53.34it/s, loss=0.0443, v_num=_tra]Epoch 0: 24%|██▍ | 132/548 [00:02<00:07, 53.39it/s, loss=0.0442, v_num=_tra]Epoch 0: 24%|██▍ | 133/548 [00:02<00:07, 53.52it/s, loss=0.0438, v_num=_tra]Epoch 0: 24%|██▍ | 134/548 [00:02<00:07, 53.60it/s, loss=0.0435, v_num=_tra]Epoch 0: 25%|██▍ | 135/548 [00:02<00:07, 53.73it/s, loss=0.0434, v_num=_tra]Epoch 0: 25%|██▍ | 136/548 [00:02<00:07, 53.84it/s, loss=0.0434, v_num=_tra]Epoch 0: 25%|██▌ | 137/548 [00:02<00:07, 53.92it/s, loss=0.0434, v_num=_tra]Epoch 0: 25%|██▌ | 138/548 [00:02<00:07, 54.02it/s, loss=0.0431, v_num=_tra]Epoch 0: 25%|██▌ | 139/548 [00:02<00:07, 54.11it/s, loss=0.0431, v_num=_tra]Epoch 0: 25%|██▌ | 139/548 [00:02<00:07, 54.10it/s, loss=0.0429, v_num=_tra]Epoch 0: 26%|██▌ | 140/548 [00:02<00:07, 54.15it/s, loss=0.0429, v_num=_tra]Epoch 0: 26%|██▌ | 141/548 [00:02<00:07, 54.20it/s, loss=0.0427, v_num=_tra]Epoch 0: 26%|██▌ | 142/548 [00:02<00:07, 54.19it/s, loss=0.0425, v_num=_tra]Epoch 0: 26%|██▌ | 143/548 [00:02<00:07, 54.20it/s, loss=0.0423, v_num=_tra]Epoch 0: 26%|██▋ | 144/548 [00:02<00:07, 54.28it/s, loss=0.0421, v_num=_tra]Epoch 0: 26%|██▋ | 145/548 [00:02<00:07, 54.33it/s, loss=0.0419, v_num=_tra]Epoch 0: 27%|██▋ | 146/548 [00:02<00:07, 54.43it/s, loss=0.0417, v_num=_tra]Epoch 0: 27%|██▋ | 147/548 [00:02<00:07, 54.51it/s, loss=0.0417, v_num=_tra]Epoch 0: 27%|██▋ | 147/548 [00:02<00:07, 54.50it/s, loss=0.0417, v_num=_tra]Epoch 0: 27%|██▋ | 148/548 [00:02<00:07, 54.59it/s, loss=0.0414, v_num=_tra]Epoch 0: 27%|██▋ | 149/548 [00:02<00:07, 54.67it/s, loss=0.041, v_num=_tra] Epoch 0: 27%|██▋ | 150/548 [00:02<00:07, 54.76it/s, loss=0.0409, v_num=_tra]Epoch 0: 28%|██▊ | 151/548 [00:02<00:07, 54.83it/s, loss=0.0406, v_num=_tra]Epoch 0: 28%|██▊ | 152/548 [00:02<00:07, 54.90it/s, loss=0.0403, v_num=_tra]Epoch 0: 28%|██▊ | 153/548 [00:02<00:07, 54.90it/s, loss=0.0402, v_num=_tra]Epoch 0: 28%|██▊ | 154/548 [00:02<00:07, 54.93it/s, loss=0.0401, v_num=_tra]Epoch 0: 28%|██▊ | 155/548 [00:02<00:07, 54.95it/s, loss=0.0401, v_num=_tra]Epoch 0: 28%|██▊ | 155/548 [00:02<00:07, 54.95it/s, loss=0.0398, v_num=_tra]Epoch 0: 28%|██▊ | 156/548 [00:02<00:07, 55.06it/s, loss=0.0395, v_num=_tra]Epoch 0: 29%|██▊ | 157/548 [00:02<00:07, 55.11it/s, loss=0.0392, v_num=_tra]Epoch 0: 29%|██▉ | 158/548 [00:02<00:07, 55.22it/s, loss=0.039, v_num=_tra] Epoch 0: 29%|██▉ | 159/548 [00:02<00:07, 55.26it/s, loss=0.039, v_num=_tra]Epoch 0: 29%|██▉ | 160/548 [00:02<00:07, 55.30it/s, loss=0.0386, v_num=_tra]Epoch 0: 29%|██▉ | 161/548 [00:02<00:06, 55.39it/s, loss=0.0385, v_num=_tra]Epoch 0: 30%|██▉ | 162/548 [00:02<00:06, 55.45it/s, loss=0.0384, v_num=_tra]Epoch 0: 30%|██▉ | 163/548 [00:02<00:06, 55.53it/s, loss=0.0384, v_num=_tra]Epoch 0: 30%|██▉ | 163/548 [00:02<00:06, 55.52it/s, loss=0.0383, v_num=_tra]Epoch 0: 30%|██▉ | 164/548 [00:02<00:06, 55.57it/s, loss=0.038, v_num=_tra] Epoch 0: 30%|███ | 165/548 [00:02<00:06, 55.66it/s, loss=0.038, v_num=_tra]Epoch 0: 30%|███ | 166/548 [00:02<00:06, 55.60it/s, loss=0.0379, v_num=_tra]Epoch 0: 30%|███ | 167/548 [00:03<00:06, 55.62it/s, loss=0.0377, v_num=_tra]Epoch 0: 31%|███ | 168/548 [00:03<00:06, 55.69it/s, loss=0.0377, v_num=_tra]Epoch 0: 31%|███ | 169/548 [00:03<00:06, 55.68it/s, loss=0.0376, v_num=_tra]Epoch 0: 31%|███ | 170/548 [00:03<00:06, 55.73it/s, loss=0.0374, v_num=_tra]Epoch 0: 31%|███ | 171/548 [00:03<00:06, 55.79it/s, loss=0.0374, v_num=_tra]Epoch 0: 31%|███ | 171/548 [00:03<00:06, 55.78it/s, loss=0.0374, v_num=_tra]Epoch 0: 31%|███▏ | 172/548 [00:03<00:06, 55.84it/s, loss=0.0374, v_num=_tra]Epoch 0: 32%|███▏ | 173/548 [00:03<00:06, 55.84it/s, loss=0.0373, v_num=_tra]Epoch 0: 32%|███▏ | 174/548 [00:03<00:06, 55.90it/s, loss=0.0372, v_num=_tra]Epoch 0: 32%|███▏ | 175/548 [00:03<00:06, 55.96it/s, loss=0.0371, v_num=_tra]Epoch 0: 32%|███▏ | 176/548 [00:03<00:06, 56.02it/s, loss=0.037, v_num=_tra] Epoch 0: 32%|███▏ | 177/548 [00:03<00:06, 56.05it/s, loss=0.0368, v_num=_tra]Epoch 0: 32%|███▏ | 178/548 [00:03<00:06, 56.10it/s, loss=0.0366, v_num=_tra]Epoch 0: 33%|███▎ | 179/548 [00:03<00:06, 56.16it/s, loss=0.0366, v_num=_tra]Epoch 0: 33%|███▎ | 179/548 [00:03<00:06, 56.15it/s, loss=0.0363, v_num=_tra]Epoch 0: 33%|███▎ | 180/548 [00:03<00:06, 56.21it/s, loss=0.0362, v_num=_tra]Epoch 0: 33%|███▎ | 181/548 [00:03<00:06, 56.25it/s, loss=0.036, v_num=_tra] Epoch 0: 33%|███▎ | 182/548 [00:03<00:06, 56.34it/s, loss=0.0358, v_num=_tra]Epoch 0: 33%|███▎ | 183/548 [00:03<00:06, 56.39it/s, loss=0.0357, v_num=_tra]Epoch 0: 34%|███▎ | 184/548 [00:03<00:06, 56.40it/s, loss=0.0356, v_num=_tra]Epoch 0: 34%|███▍ | 185/548 [00:03<00:06, 56.45it/s, loss=0.0354, v_num=_tra]Epoch 0: 34%|███▍ | 186/548 [00:03<00:06, 56.42it/s, loss=0.0351, v_num=_tra]Epoch 0: 34%|███▍ | 187/548 [00:03<00:06, 56.45it/s, loss=0.0351, v_num=_tra]Epoch 0: 34%|███▍ | 187/548 [00:03<00:06, 56.44it/s, loss=0.0349, v_num=_tra]Epoch 0: 34%|███▍ | 188/548 [00:03<00:06, 56.49it/s, loss=0.0348, v_num=_tra]Epoch 0: 34%|███▍ | 189/548 [00:03<00:06, 56.57it/s, loss=0.0347, v_num=_tra]Epoch 0: 35%|███▍ | 190/548 [00:03<00:06, 56.62it/s, loss=0.0347, v_num=_tra]Epoch 0: 35%|███▍ | 191/548 [00:03<00:06, 56.67it/s, loss=0.0345, v_num=_tra]Epoch 0: 35%|███▌ | 192/548 [00:03<00:06, 56.71it/s, loss=0.0343, v_num=_tra]Epoch 0: 35%|███▌ | 193/548 [00:03<00:06, 56.71it/s, loss=0.0341, v_num=_tra]Epoch 0: 35%|███▌ | 194/548 [00:03<00:06, 56.73it/s, loss=0.034, v_num=_tra] Epoch 0: 36%|███▌ | 195/548 [00:03<00:06, 56.78it/s, loss=0.034, v_num=_tra]Epoch 0: 36%|███▌ | 195/548 [00:03<00:06, 56.77it/s, loss=0.034, v_num=_tra]Epoch 0: 36%|███▌ | 196/548 [00:03<00:06, 56.78it/s, loss=0.0339, v_num=_tra]Epoch 0: 36%|███▌ | 197/548 [00:03<00:06, 56.78it/s, loss=0.0339, v_num=_tra]Epoch 0: 36%|███▌ | 198/548 [00:03<00:06, 56.77it/s, loss=0.0338, v_num=_tra]Epoch 0: 36%|███▋ | 199/548 [00:03<00:06, 56.81it/s, loss=0.0338, v_num=_tra]Epoch 0: 36%|███▋ | 200/548 [00:03<00:06, 56.83it/s, loss=0.0337, v_num=_tra]Epoch 0: 37%|███▋ | 201/548 [00:03<00:06, 56.75it/s, loss=0.0336, v_num=_tra]Epoch 0: 37%|███▋ | 202/548 [00:03<00:06, 56.77it/s, loss=0.0336, v_num=_tra]Epoch 0: 37%|███▋ | 203/548 [00:03<00:06, 56.81it/s, loss=0.0336, v_num=_tra]Epoch 0: 37%|███▋ | 203/548 [00:03<00:06, 56.81it/s, loss=0.0335, v_num=_tra]Epoch 0: 37%|███▋ | 204/548 [00:03<00:06, 56.78it/s, loss=0.0333, v_num=_tra]Epoch 0: 37%|███▋ | 205/548 [00:03<00:06, 56.80it/s, loss=0.0333, v_num=_tra]Epoch 0: 38%|███▊ | 206/548 [00:03<00:06, 56.84it/s, loss=0.0333, v_num=_tra]Epoch 0: 38%|███▊ | 207/548 [00:03<00:05, 56.87it/s, loss=0.0332, v_num=_tra]Epoch 0: 38%|███▊ | 208/548 [00:03<00:05, 56.91it/s, loss=0.0332, v_num=_tra]Epoch 0: 38%|███▊ | 209/548 [00:03<00:05, 56.97it/s, loss=0.0329, v_num=_tra]Epoch 0: 38%|███▊ | 210/548 [00:03<00:05, 57.01it/s, loss=0.0327, v_num=_tra]Epoch 0: 39%|███▊ | 211/548 [00:03<00:05, 57.06it/s, loss=0.0327, v_num=_tra]Epoch 0: 39%|███▊ | 211/548 [00:03<00:05, 57.06it/s, loss=0.0326, v_num=_tra]Epoch 0: 39%|███▊ | 212/548 [00:03<00:05, 57.10it/s, loss=0.0324, v_num=_tra]Epoch 0: 39%|███▉ | 213/548 [00:03<00:05, 57.05it/s, loss=0.0323, v_num=_tra]Epoch 0: 39%|███▉ | 214/548 [00:03<00:05, 57.08it/s, loss=0.032, v_num=_tra] Epoch 0: 39%|███▉ | 215/548 [00:03<00:05, 57.12it/s, loss=0.0319, v_num=_tra]Epoch 0: 39%|███▉ | 216/548 [00:03<00:05, 57.16it/s, loss=0.0319, v_num=_tra]Epoch 0: 40%|███▉ | 217/548 [00:03<00:05, 57.20it/s, loss=0.0319, v_num=_tra]Epoch 0: 40%|███▉ | 218/548 [00:03<00:05, 57.18it/s, loss=0.0318, v_num=_tra]Epoch 0: 40%|███▉ | 219/548 [00:03<00:05, 57.22it/s, loss=0.0318, v_num=_tra]Epoch 0: 40%|███▉ | 219/548 [00:03<00:05, 57.21it/s, loss=0.0316, v_num=_tra]Epoch 0: 40%|████ | 220/548 [00:03<00:05, 57.24it/s, loss=0.0315, v_num=_tra]Epoch 0: 40%|████ | 221/548 [00:03<00:05, 57.27it/s, loss=0.0315, v_num=_tra]Epoch 0: 41%|████ | 222/548 [00:03<00:05, 57.31it/s, loss=0.0314, v_num=_tra]Epoch 0: 41%|████ | 223/548 [00:03<00:05, 57.32it/s, loss=0.0313, v_num=_tra]Epoch 0: 41%|████ | 224/548 [00:03<00:05, 57.35it/s, loss=0.0313, v_num=_tra]Epoch 0: 41%|████ | 225/548 [00:03<00:05, 57.36it/s, loss=0.0312, v_num=_tra]Epoch 0: 41%|████ | 226/548 [00:03<00:05, 57.37it/s, loss=0.0311, v_num=_tra]Epoch 0: 41%|████▏ | 227/548 [00:03<00:05, 57.38it/s, loss=0.0311, v_num=_tra]Epoch 0: 41%|████▏ | 227/548 [00:03<00:05, 57.37it/s, loss=0.031, v_num=_tra] Epoch 0: 42%|████▏ | 228/548 [00:03<00:05, 57.36it/s, loss=0.0309, v_num=_tra]Epoch 0: 42%|████▏ | 229/548 [00:03<00:05, 57.36it/s, loss=0.0311, v_num=_tra]Epoch 0: 42%|████▏ | 230/548 [00:04<00:05, 57.39it/s, loss=0.0311, v_num=_tra]Epoch 0: 42%|████▏ | 231/548 [00:04<00:05, 57.42it/s, loss=0.031, v_num=_tra] Epoch 0: 42%|████▏ | 232/548 [00:04<00:05, 57.42it/s, loss=0.0311, v_num=_tra]Epoch 0: 43%|████▎ | 233/548 [00:04<00:05, 57.46it/s, loss=0.0313, v_num=_tra]Epoch 0: 43%|████▎ | 234/548 [00:04<00:05, 57.48it/s, loss=0.0312, v_num=_tra]Epoch 0: 43%|████▎ | 235/548 [00:04<00:05, 57.49it/s, loss=0.0312, v_num=_tra]Epoch 0: 43%|████▎ | 235/548 [00:04<00:05, 57.49it/s, loss=0.0311, v_num=_tra]Epoch 0: 43%|████▎ | 236/548 [00:04<00:05, 57.52it/s, loss=0.031, v_num=_tra] Epoch 0: 43%|████▎ | 237/548 [00:04<00:05, 57.55it/s, loss=0.031, v_num=_tra]Epoch 0: 43%|████▎ | 238/548 [00:04<00:05, 57.59it/s, loss=0.031, v_num=_tra]Epoch 0: 44%|████▎ | 239/548 [00:04<00:05, 57.59it/s, loss=0.031, v_num=_tra]Epoch 0: 44%|████▍ | 240/548 [00:04<00:05, 57.62it/s, loss=0.031, v_num=_tra]Epoch 0: 44%|████▍ | 241/548 [00:04<00:05, 57.65it/s, loss=0.031, v_num=_tra]Epoch 0: 44%|████▍ | 242/548 [00:04<00:05, 57.66it/s, loss=0.0309, v_num=_tra]Epoch 0: 44%|████▍ | 243/548 [00:04<00:05, 57.72it/s, loss=0.0309, v_num=_tra]Epoch 0: 44%|████▍ | 243/548 [00:04<00:05, 57.72it/s, loss=0.0308, v_num=_tra]Epoch 0: 45%|████▍ | 244/548 [00:04<00:05, 57.77it/s, loss=0.0308, v_num=_tra]Epoch 0: 45%|████▍ | 245/548 [00:04<00:05, 57.82it/s, loss=0.0307, v_num=_tra]Epoch 0: 45%|████▍ | 246/548 [00:04<00:05, 57.84it/s, loss=0.0307, v_num=_tra]Epoch 0: 45%|████▌ | 247/548 [00:04<00:05, 57.89it/s, loss=0.0307, v_num=_tra]Epoch 0: 45%|████▌ | 248/548 [00:04<00:05, 57.91it/s, loss=0.0307, v_num=_tra]Epoch 0: 45%|████▌ | 249/548 [00:04<00:05, 57.91it/s, loss=0.0305, v_num=_tra]Epoch 0: 46%|████▌ | 250/548 [00:04<00:05, 57.94it/s, loss=0.0304, v_num=_tra]Epoch 0: 46%|████▌ | 251/548 [00:04<00:05, 57.99it/s, loss=0.0304, v_num=_tra]Epoch 0: 46%|████▌ | 251/548 [00:04<00:05, 57.99it/s, loss=0.0304, v_num=_tra]Epoch 0: 46%|████▌ | 252/548 [00:04<00:05, 58.02it/s, loss=0.0302, v_num=_tra]Epoch 0: 46%|████▌ | 253/548 [00:04<00:05, 58.05it/s, loss=0.03, v_num=_tra] Epoch 0: 46%|████▋ | 254/548 [00:04<00:05, 58.07it/s, loss=0.03, v_num=_tra]Epoch 0: 47%|████▋ | 255/548 [00:04<00:05, 58.11it/s, loss=0.0299, v_num=_tra]Epoch 0: 47%|████▋ | 256/548 [00:04<00:05, 58.12it/s, loss=0.0298, v_num=_tra]Epoch 0: 47%|████▋ | 257/548 [00:04<00:05, 58.18it/s, loss=0.0297, v_num=_tra]Epoch 0: 47%|████▋ | 258/548 [00:04<00:04, 58.20it/s, loss=0.0294, v_num=_tra]Epoch 0: 47%|████▋ | 259/548 [00:04<00:04, 58.21it/s, loss=0.0294, v_num=_tra]Epoch 0: 47%|████▋ | 259/548 [00:04<00:04, 58.20it/s, loss=0.0293, v_num=_tra]Epoch 0: 47%|████▋ | 260/548 [00:04<00:04, 58.22it/s, loss=0.0292, v_num=_tra]Epoch 0: 48%|████▊ | 261/548 [00:04<00:04, 58.24it/s, loss=0.0291, v_num=_tra]Epoch 0: 48%|████▊ | 262/548 [00:04<00:04, 58.23it/s, loss=0.0291, v_num=_tra]Epoch 0: 48%|████▊ | 263/548 [00:04<00:04, 58.23it/s, loss=0.0291, v_num=_tra]Epoch 0: 48%|████▊ | 264/548 [00:04<00:04, 58.21it/s, loss=0.0289, v_num=_tra]Epoch 0: 48%|████▊ | 265/548 [00:04<00:04, 58.22it/s, loss=0.0288, v_num=_tra]Epoch 0: 49%|████▊ | 266/548 [00:04<00:04, 58.24it/s, loss=0.0286, v_num=_tra]Epoch 0: 49%|████▊ | 267/548 [00:04<00:04, 58.27it/s, loss=0.0286, v_num=_tra]Epoch 0: 49%|████▊ | 267/548 [00:04<00:04, 58.26it/s, loss=0.0285, v_num=_tra]Epoch 0: 49%|████▉ | 268/548 [00:04<00:04, 58.31it/s, loss=0.0283, v_num=_tra]Epoch 0: 49%|████▉ | 269/548 [00:04<00:04, 58.29it/s, loss=0.0283, v_num=_tra]Epoch 0: 49%|████▉ | 270/548 [00:04<00:04, 58.30it/s, loss=0.0282, v_num=_tra]Epoch 0: 49%|████▉ | 271/548 [00:04<00:04, 58.33it/s, loss=0.0281, v_num=_tra]Epoch 0: 50%|████▉ | 272/548 [00:04<00:04, 58.35it/s, loss=0.0282, v_num=_tra]Epoch 0: 50%|████▉ | 273/548 [00:04<00:04, 58.37it/s, loss=0.0281, v_num=_tra]Epoch 0: 50%|█████ | 274/548 [00:04<00:04, 58.42it/s, loss=0.028, v_num=_tra] Epoch 0: 50%|█████ | 275/548 [00:04<00:04, 58.44it/s, loss=0.028, v_num=_tra]Epoch 0: 50%|█████ | 275/548 [00:04<00:04, 58.44it/s, loss=0.0281, v_num=_tra]Epoch 0: 50%|█████ | 276/548 [00:04<00:04, 58.46it/s, loss=0.0281, v_num=_tra]Epoch 0: 51%|█████ | 277/548 [00:04<00:04, 58.48it/s, loss=0.0281, v_num=_tra]Epoch 0: 51%|█████ | 278/548 [00:04<00:04, 58.52it/s, loss=0.0282, v_num=_tra]Epoch 0: 51%|█████ | 279/548 [00:04<00:04, 58.54it/s, loss=0.0282, v_num=_tra]Epoch 0: 51%|█████ | 280/548 [00:04<00:04, 58.51it/s, loss=0.0281, v_num=_tra]Epoch 0: 51%|█████▏ | 281/548 [00:04<00:04, 58.54it/s, loss=0.028, v_num=_tra] Epoch 0: 51%|█████▏ | 282/548 [00:04<00:04, 58.56it/s, loss=0.0279, v_num=_tra]Epoch 0: 52%|█████▏ | 283/548 [00:04<00:04, 58.55it/s, loss=0.0279, v_num=_tra]Epoch 0: 52%|█████▏ | 283/548 [00:04<00:04, 58.54it/s, loss=0.0279, v_num=_tra]Epoch 0: 52%|█████▏ | 284/548 [00:04<00:04, 58.56it/s, loss=0.028, v_num=_tra] Epoch 0: 52%|█████▏ | 285/548 [00:04<00:04, 58.60it/s, loss=0.0279, v_num=_tra]Epoch 0: 52%|█████▏ | 286/548 [00:04<00:04, 58.61it/s, loss=0.0279, v_num=_tra]Epoch 0: 52%|█████▏ | 287/548 [00:04<00:04, 58.66it/s, loss=0.0279, v_num=_tra]Epoch 0: 53%|█████▎ | 288/548 [00:04<00:04, 58.62it/s, loss=0.028, v_num=_tra] Epoch 0: 53%|█████▎ | 289/548 [00:04<00:04, 58.63it/s, loss=0.0281, v_num=_tra]Epoch 0: 53%|█████▎ | 290/548 [00:04<00:04, 58.64it/s, loss=0.028, v_num=_tra] Epoch 0: 53%|█████▎ | 291/548 [00:04<00:04, 58.66it/s, loss=0.028, v_num=_tra]Epoch 0: 53%|█████▎ | 291/548 [00:04<00:04, 58.66it/s, loss=0.028, v_num=_tra]Epoch 0: 53%|█████▎ | 292/548 [00:04<00:04, 58.67it/s, loss=0.0279, v_num=_tra]Epoch 0: 53%|█████▎ | 293/548 [00:04<00:04, 58.65it/s, loss=0.0278, v_num=_tra]Epoch 0: 54%|█████▎ | 294/548 [00:05<00:04, 58.60it/s, loss=0.0278, v_num=_tra]Epoch 0: 54%|█████▍ | 295/548 [00:05<00:04, 58.59it/s, loss=0.0277, v_num=_tra]Epoch 0: 54%|█████▍ | 296/548 [00:05<00:04, 58.57it/s, loss=0.0276, v_num=_tra]Epoch 0: 54%|█████▍ | 297/548 [00:05<00:04, 58.58it/s, loss=0.0275, v_num=_tra]Epoch 0: 54%|█████▍ | 298/548 [00:05<00:04, 58.57it/s, loss=0.0275, v_num=_tra]Epoch 0: 55%|█████▍ | 299/548 [00:05<00:04, 58.59it/s, loss=0.0275, v_num=_tra]Epoch 0: 55%|█████▍ | 299/548 [00:05<00:04, 58.58it/s, loss=0.0274, v_num=_tra]Epoch 0: 55%|█████▍ | 300/548 [00:05<00:04, 58.57it/s, loss=0.0272, v_num=_tra]Epoch 0: 55%|█████▍ | 301/548 [00:05<00:04, 58.61it/s, loss=0.0272, v_num=_tra]Epoch 0: 55%|█████▌ | 302/548 [00:05<00:04, 58.63it/s, loss=0.0272, v_num=_tra]Epoch 0: 55%|█████▌ | 303/548 [00:05<00:04, 58.62it/s, loss=0.0271, v_num=_tra]Epoch 0: 55%|█████▌ | 304/548 [00:05<00:04, 58.64it/s, loss=0.0271, v_num=_tra]Epoch 0: 56%|█████▌ | 305/548 [00:05<00:04, 58.65it/s, loss=0.027, v_num=_tra] Epoch 0: 56%|█████▌ | 306/548 [00:05<00:04, 58.67it/s, loss=0.0269, v_num=_tra]Epoch 0: 56%|█████▌ | 307/548 [00:05<00:04, 58.68it/s, loss=0.0269, v_num=_tra]Epoch 0: 56%|█████▌ | 307/548 [00:05<00:04, 58.68it/s, loss=0.0269, v_num=_tra]Epoch 0: 56%|█████▌ | 308/548 [00:05<00:04, 58.64it/s, loss=0.0268, v_num=_tra]Epoch 0: 56%|█████▋ | 309/548 [00:05<00:04, 58.59it/s, loss=0.0267, v_num=_tra]Epoch 0: 57%|█████▋ | 310/548 [00:05<00:04, 58.60it/s, loss=0.0266, v_num=_tra]Epoch 0: 57%|█████▋ | 311/548 [00:05<00:04, 58.62it/s, loss=0.0265, v_num=_tra]Epoch 0: 57%|█████▋ | 312/548 [00:05<00:04, 58.62it/s, loss=0.0265, v_num=_tra]Epoch 0: 57%|█████▋ | 313/548 [00:05<00:04, 58.66it/s, loss=0.0264, v_num=_tra]Epoch 0: 57%|█████▋ | 314/548 [00:05<00:03, 58.65it/s, loss=0.0263, v_num=_tra]Epoch 0: 57%|█████▋ | 315/548 [00:05<00:03, 58.70it/s, loss=0.0263, v_num=_tra]Epoch 0: 57%|█████▋ | 315/548 [00:05<00:03, 58.69it/s, loss=0.0262, v_num=_tra]Epoch 0: 58%|█████▊ | 316/548 [00:05<00:03, 58.70it/s, loss=0.0262, v_num=_tra]Epoch 0: 58%|█████▊ | 317/548 [00:05<00:03, 58.70it/s, loss=0.0262, v_num=_tra]Epoch 0: 58%|█████▊ | 318/548 [00:05<00:03, 58.71it/s, loss=0.0261, v_num=_tra]Epoch 0: 58%|█████▊ | 319/548 [00:05<00:03, 58.75it/s, loss=0.0262, v_num=_tra]Epoch 0: 58%|█████▊ | 320/548 [00:05<00:03, 58.73it/s, loss=0.0261, v_num=_tra]Epoch 0: 59%|█████▊ | 321/548 [00:05<00:03, 58.75it/s, loss=0.0261, v_num=_tra]Epoch 0: 59%|█████▉ | 322/548 [00:05<00:03, 58.76it/s, loss=0.0261, v_num=_tra]Epoch 0: 59%|█████▉ | 323/548 [00:05<00:03, 58.77it/s, loss=0.0261, v_num=_tra]Epoch 0: 59%|█████▉ | 323/548 [00:05<00:03, 58.77it/s, loss=0.0261, v_num=_tra]Epoch 0: 59%|█████▉ | 324/548 [00:05<00:03, 58.79it/s, loss=0.0259, v_num=_tra]Epoch 0: 59%|█████▉ | 325/548 [00:05<00:03, 58.76it/s, loss=0.0259, v_num=_tra]Epoch 0: 59%|█████▉ | 326/548 [00:05<00:03, 58.75it/s, loss=0.026, v_num=_tra] Epoch 0: 60%|█████▉ | 327/548 [00:05<00:03, 58.73it/s, loss=0.0259, v_num=_tra]Epoch 0: 60%|█████▉ | 328/548 [00:05<00:03, 58.75it/s, loss=0.0258, v_num=_tra]Epoch 0: 60%|██████ | 329/548 [00:05<00:03, 58.77it/s, loss=0.0258, v_num=_tra]Epoch 0: 60%|██████ | 330/548 [00:05<00:03, 58.79it/s, loss=0.0258, v_num=_tra]Epoch 0: 60%|██████ | 331/548 [00:05<00:03, 58.80it/s, loss=0.0258, v_num=_tra]Epoch 0: 60%|██████ | 331/548 [00:05<00:03, 58.80it/s, loss=0.0257, v_num=_tra]Epoch 0: 61%|██████ | 332/548 [00:05<00:03, 58.82it/s, loss=0.0257, v_num=_tra]Epoch 0: 61%|██████ | 333/548 [00:05<00:03, 58.83it/s, loss=0.0257, v_num=_tra]Epoch 0: 61%|██████ | 334/548 [00:05<00:03, 58.86it/s, loss=0.0258, v_num=_tra]Epoch 0: 61%|██████ | 335/548 [00:05<00:03, 58.87it/s, loss=0.0259, v_num=_tra]Epoch 0: 61%|██████▏ | 336/548 [00:05<00:03, 58.90it/s, loss=0.0259, v_num=_tra]Epoch 0: 61%|██████▏ | 337/548 [00:05<00:03, 58.91it/s, loss=0.0258, v_num=_tra]Epoch 0: 62%|██████▏ | 338/548 [00:05<00:03, 58.93it/s, loss=0.0259, v_num=_tra]Epoch 0: 62%|██████▏ | 339/548 [00:05<00:03, 58.94it/s, loss=0.0259, v_num=_tra]Epoch 0: 62%|██████▏ | 339/548 [00:05<00:03, 58.94it/s, loss=0.0258, v_num=_tra]Epoch 0: 62%|██████▏ | 340/548 [00:05<00:03, 58.91it/s, loss=0.0259, v_num=_tra]Epoch 0: 62%|██████▏ | 341/548 [00:05<00:03, 58.93it/s, loss=0.0259, v_num=_tra]Epoch 0: 62%|██████▏ | 342/548 [00:05<00:03, 58.97it/s, loss=0.0259, v_num=_tra]Epoch 0: 63%|██████▎ | 343/548 [00:05<00:03, 59.00it/s, loss=0.0257, v_num=_tra]Epoch 0: 63%|██████▎ | 344/548 [00:05<00:03, 58.98it/s, loss=0.0259, v_num=_tra]Epoch 0: 63%|██████▎ | 345/548 [00:05<00:03, 58.97it/s, loss=0.026, v_num=_tra] Epoch 0: 63%|██████▎ | 346/548 [00:05<00:03, 58.99it/s, loss=0.0258, v_num=_tra]Epoch 0: 63%|██████▎ | 347/548 [00:05<00:03, 59.03it/s, loss=0.0258, v_num=_tra]Epoch 0: 63%|██████▎ | 347/548 [00:05<00:03, 59.03it/s, loss=0.0258, v_num=_tra]Epoch 0: 64%|██████▎ | 348/548 [00:05<00:03, 59.07it/s, loss=0.0259, v_num=_tra]Epoch 0: 64%|██████▎ | 349/548 [00:05<00:03, 59.09it/s, loss=0.0257, v_num=_tra]Epoch 0: 64%|██████▍ | 350/548 [00:05<00:03, 59.10it/s, loss=0.0257, v_num=_tra]Epoch 0: 64%|██████▍ | 351/548 [00:05<00:03, 59.14it/s, loss=0.0257, v_num=_tra]Epoch 0: 64%|██████▍ | 352/548 [00:05<00:03, 59.17it/s, loss=0.0256, v_num=_tra]Epoch 0: 64%|██████▍ | 353/548 [00:05<00:03, 59.21it/s, loss=0.0257, v_num=_tra]Epoch 0: 65%|██████▍ | 354/548 [00:05<00:03, 59.24it/s, loss=0.0255, v_num=_tra]Epoch 0: 65%|██████▍ | 355/548 [00:05<00:03, 59.28it/s, loss=0.0255, v_num=_tra]Epoch 0: 65%|██████▍ | 355/548 [00:05<00:03, 59.28it/s, loss=0.0254, v_num=_tra]Epoch 0: 65%|██████▍ | 356/548 [00:06<00:03, 59.32it/s, loss=0.0253, v_num=_tra]Epoch 0: 65%|██████▌ | 357/548 [00:06<00:03, 59.36it/s, loss=0.0252, v_num=_tra]Epoch 0: 65%|██████▌ | 358/548 [00:06<00:03, 59.35it/s, loss=0.0251, v_num=_tra]Epoch 0: 66%|██████▌ | 359/548 [00:06<00:03, 59.36it/s, loss=0.0251, v_num=_tra]Epoch 0: 66%|██████▌ | 360/548 [00:06<00:03, 59.38it/s, loss=0.0249, v_num=_tra]Epoch 0: 66%|██████▌ | 361/548 [00:06<00:03, 59.42it/s, loss=0.0249, v_num=_tra]Epoch 0: 66%|██████▌ | 362/548 [00:06<00:03, 59.45it/s, loss=0.0248, v_num=_tra]Epoch 0: 66%|██████▌ | 363/548 [00:06<00:03, 59.49it/s, loss=0.0248, v_num=_tra]Epoch 0: 66%|██████▌ | 363/548 [00:06<00:03, 59.49it/s, loss=0.0249, v_num=_tra]Epoch 0: 66%|██████▋ | 364/548 [00:06<00:03, 59.53it/s, loss=0.0246, v_num=_tra]Epoch 0: 67%|██████▋ | 365/548 [00:06<00:03, 59.55it/s, loss=0.0245, v_num=_tra]Epoch 0: 67%|██████▋ | 366/548 [00:06<00:03, 59.55it/s, loss=0.0245, v_num=_tra]Epoch 0: 67%|██████▋ | 367/548 [00:06<00:03, 59.58it/s, loss=0.0245, v_num=_tra]Epoch 0: 67%|██████▋ | 368/548 [00:06<00:03, 59.60it/s, loss=0.0243, v_num=_tra]Epoch 0: 67%|██████▋ | 369/548 [00:06<00:03, 59.63it/s, loss=0.0243, v_num=_tra]Epoch 0: 68%|██████▊ | 370/548 [00:06<00:02, 59.62it/s, loss=0.0242, v_num=_tra]Epoch 0: 68%|██████▊ | 371/548 [00:06<00:02, 59.62it/s, loss=0.0242, v_num=_tra]Epoch 0: 68%|██████▊ | 371/548 [00:06<00:02, 59.61it/s, loss=0.0241, v_num=_tra]Epoch 0: 68%|██████▊ | 372/548 [00:06<00:02, 59.64it/s, loss=0.0242, v_num=_tra]Epoch 0: 68%|██████▊ | 373/548 [00:06<00:02, 59.66it/s, loss=0.0241, v_num=_tra]Epoch 0: 68%|██████▊ | 374/548 [00:06<00:02, 59.68it/s, loss=0.0241, v_num=_tra]Epoch 0: 68%|██████▊ | 375/548 [00:06<00:02, 59.69it/s, loss=0.0241, v_num=_tra]Epoch 0: 69%|██████▊ | 376/548 [00:06<00:02, 59.70it/s, loss=0.024, v_num=_tra] Epoch 0: 69%|██████▉ | 377/548 [00:06<00:02, 59.73it/s, loss=0.0239, v_num=_tra]Epoch 0: 69%|██████▉ | 378/548 [00:06<00:02, 59.71it/s, loss=0.024, v_num=_tra] Epoch 0: 69%|██████▉ | 379/548 [00:06<00:02, 59.73it/s, loss=0.024, v_num=_tra]Epoch 0: 69%|██████▉ | 379/548 [00:06<00:02, 59.73it/s, loss=0.0239, v_num=_tra]Epoch 0: 69%|██████▉ | 380/548 [00:06<00:02, 59.74it/s, loss=0.0239, v_num=_tra]Epoch 0: 70%|██████▉ | 381/548 [00:06<00:02, 59.71it/s, loss=0.0238, v_num=_tra]Epoch 0: 70%|██████▉ | 382/548 [00:06<00:02, 59.69it/s, loss=0.0237, v_num=_tra]Epoch 0: 70%|██████▉ | 383/548 [00:06<00:02, 59.71it/s, loss=0.0238, v_num=_tra]Epoch 0: 70%|███████ | 384/548 [00:06<00:02, 59.72it/s, loss=0.0237, v_num=_tra]Epoch 0: 70%|███████ | 385/548 [00:06<00:02, 59.73it/s, loss=0.0237, v_num=_tra]Epoch 0: 70%|███████ | 386/548 [00:06<00:02, 59.70it/s, loss=0.0236, v_num=_tra]Epoch 0: 71%|███████ | 387/548 [00:06<00:02, 59.71it/s, loss=0.0236, v_num=_tra]Epoch 0: 71%|███████ | 387/548 [00:06<00:02, 59.70it/s, loss=0.0235, v_num=_tra]Epoch 0: 71%|███████ | 388/548 [00:06<00:02, 59.71it/s, loss=0.0235, v_num=_tra]Epoch 0: 71%|███████ | 389/548 [00:06<00:02, 59.70it/s, loss=0.0235, v_num=_tra]Epoch 0: 71%|███████ | 390/548 [00:06<00:02, 59.73it/s, loss=0.0234, v_num=_tra]Epoch 0: 71%|███████▏ | 391/548 [00:06<00:02, 59.74it/s, loss=0.0234, v_num=_tra]Epoch 0: 72%|███████▏ | 392/548 [00:06<00:02, 59.77it/s, loss=0.0233, v_num=_tra]Epoch 0: 72%|███████▏ | 393/548 [00:06<00:02, 59.76it/s, loss=0.0232, v_num=_tra]Epoch 0: 72%|███████▏ | 394/548 [00:06<00:02, 59.78it/s, loss=0.0233, v_num=_tra]Epoch 0: 72%|███████▏ | 395/548 [00:06<00:02, 59.80it/s, loss=0.0233, v_num=_tra]Epoch 0: 72%|███████▏ | 395/548 [00:06<00:02, 59.80it/s, loss=0.0232, v_num=_tra]Epoch 0: 72%|███████▏ | 396/548 [00:06<00:02, 59.81it/s, loss=0.0232, v_num=_tra]Epoch 0: 72%|███████▏ | 397/548 [00:06<00:02, 59.80it/s, loss=0.0232, v_num=_tra]Epoch 0: 73%|███████▎ | 398/548 [00:06<00:02, 59.81it/s, loss=0.0231, v_num=_tra]Epoch 0: 73%|███████▎ | 399/548 [00:06<00:02, 59.84it/s, loss=0.0231, v_num=_tra]Epoch 0: 73%|███████▎ | 400/548 [00:06<00:02, 59.85it/s, loss=0.0232, v_num=_tra]Epoch 0: 73%|███████▎ | 401/548 [00:06<00:02, 59.76it/s, loss=0.0231, v_num=_tra]Epoch 0: 73%|███████▎ | 402/548 [00:06<00:02, 59.75it/s, loss=0.0232, v_num=_tra]Epoch 0: 74%|███████▎ | 403/548 [00:06<00:02, 59.75it/s, loss=0.0232, v_num=_tra]Epoch 0: 74%|███████▎ | 403/548 [00:06<00:02, 59.75it/s, loss=0.0231, v_num=_tra]Epoch 0: 74%|███████▎ | 404/548 [00:06<00:02, 59.76it/s, loss=0.023, v_num=_tra] Epoch 0: 74%|███████▍ | 405/548 [00:06<00:02, 59.77it/s, loss=0.023, v_num=_tra]Epoch 0: 74%|███████▍ | 406/548 [00:06<00:02, 59.78it/s, loss=0.023, v_num=_tra]Epoch 0: 74%|███████▍ | 407/548 [00:06<00:02, 59.79it/s, loss=0.0231, v_num=_tra]Epoch 0: 74%|███████▍ | 408/548 [00:06<00:02, 59.81it/s, loss=0.023, v_num=_tra] Epoch 0: 75%|███████▍ | 409/548 [00:06<00:02, 59.83it/s, loss=0.023, v_num=_tra]Epoch 0: 75%|███████▍ | 410/548 [00:06<00:02, 59.85it/s, loss=0.023, v_num=_tra]Epoch 0: 75%|███████▌ | 411/548 [00:06<00:02, 59.87it/s, loss=0.023, v_num=_tra]Epoch 0: 75%|███████▌ | 411/548 [00:06<00:02, 59.87it/s, loss=0.0229, v_num=_tra]Epoch 0: 75%|███████▌ | 412/548 [00:06<00:02, 59.90it/s, loss=0.0229, v_num=_tra]Epoch 0: 75%|███████▌ | 413/548 [00:06<00:02, 59.90it/s, loss=0.023, v_num=_tra] Epoch 0: 76%|███████▌ | 414/548 [00:06<00:02, 59.89it/s, loss=0.0228, v_num=_tra]Epoch 0: 76%|███████▌ | 415/548 [00:06<00:02, 59.90it/s, loss=0.0228, v_num=_tra]Epoch 0: 76%|███████▌ | 416/548 [00:06<00:02, 59.89it/s, loss=0.0228, v_num=_tra]Epoch 0: 76%|███████▌ | 417/548 [00:06<00:02, 59.88it/s, loss=0.0228, v_num=_tra]Epoch 0: 76%|███████▋ | 418/548 [00:06<00:02, 59.87it/s, loss=0.0227, v_num=_tra]Epoch 0: 76%|███████▋ | 419/548 [00:06<00:02, 59.88it/s, loss=0.0227, v_num=_tra]Epoch 0: 76%|███████▋ | 419/548 [00:06<00:02, 59.88it/s, loss=0.0227, v_num=_tra]Epoch 0: 77%|███████▋ | 420/548 [00:07<00:02, 59.89it/s, loss=0.0227, v_num=_tra]Epoch 0: 77%|███████▋ | 421/548 [00:07<00:02, 59.90it/s, loss=0.0227, v_num=_tra]Epoch 0: 77%|███████▋ | 422/548 [00:07<00:02, 59.93it/s, loss=0.0225, v_num=_tra]Epoch 0: 77%|███████▋ | 423/548 [00:07<00:02, 59.94it/s, loss=0.0226, v_num=_tra]Epoch 0: 77%|███████▋ | 424/548 [00:07<00:02, 59.97it/s, loss=0.0225, v_num=_tra]Epoch 0: 78%|███████▊ | 425/548 [00:07<00:02, 59.97it/s, loss=0.0226, v_num=_tra]Epoch 0: 78%|███████▊ | 426/548 [00:07<00:02, 59.98it/s, loss=0.0226, v_num=_tra]Epoch 0: 78%|███████▊ | 427/548 [00:07<00:02, 60.01it/s, loss=0.0226, v_num=_tra]Epoch 0: 78%|███████▊ | 427/548 [00:07<00:02, 60.00it/s, loss=0.0226, v_num=_tra]Epoch 0: 78%|███████▊ | 428/548 [00:07<00:01, 60.03it/s, loss=0.0226, v_num=_tra]Epoch 0: 78%|███████▊ | 429/548 [00:07<00:01, 60.06it/s, loss=0.0225, v_num=_tra]Epoch 0: 78%|███████▊ | 430/548 [00:07<00:01, 60.09it/s, loss=0.0226, v_num=_tra]Epoch 0: 79%|███████▊ | 431/548 [00:07<00:01, 60.12it/s, loss=0.0226, v_num=_tra]Epoch 0: 79%|███████▉ | 432/548 [00:07<00:01, 60.15it/s, loss=0.0225, v_num=_tra]Epoch 0: 79%|███████▉ | 433/548 [00:07<00:01, 60.18it/s, loss=0.0226, v_num=_tra]Epoch 0: 79%|███████▉ | 434/548 [00:07<00:01, 60.21it/s, loss=0.0225, v_num=_tra]Epoch 0: 79%|███████▉ | 435/548 [00:07<00:01, 60.24it/s, loss=0.0225, v_num=_tra]Epoch 0: 79%|███████▉ | 435/548 [00:07<00:01, 60.24it/s, loss=0.0225, v_num=_tra]Epoch 0: 80%|███████▉ | 436/548 [00:07<00:01, 60.27it/s, loss=0.0225, v_num=_tra]Epoch 0: 80%|███████▉ | 437/548 [00:07<00:01, 60.26it/s, loss=0.0225, v_num=_tra]Epoch 0: 80%|███████▉ | 438/548 [00:07<00:01, 60.27it/s, loss=0.0225, v_num=_tra]Epoch 0: 80%|████████ | 439/548 [00:07<00:01, 60.29it/s, loss=0.0225, v_num=_tra]Epoch 0: 80%|████████ | 440/548 [00:07<00:01, 60.31it/s, loss=0.0225, v_num=_tra]Epoch 0: 80%|████████ | 441/548 [00:07<00:01, 60.32it/s, loss=0.0226, v_num=_tra]Epoch 0: 81%|████████ | 442/548 [00:07<00:01, 60.33it/s, loss=0.0226, v_num=_tra]Epoch 0: 81%|████████ | 443/548 [00:07<00:01, 60.35it/s, loss=0.0226, v_num=_tra]Epoch 0: 81%|████████ | 443/548 [00:07<00:01, 60.35it/s, loss=0.0226, v_num=_tra]Epoch 0: 81%|████████ | 444/548 [00:07<00:01, 60.34it/s, loss=0.0226, v_num=_tra]Epoch 0: 81%|████████ | 445/548 [00:07<00:01, 60.35it/s, loss=0.0226, v_num=_tra]Epoch 0: 81%|████████▏ | 446/548 [00:07<00:01, 60.35it/s, loss=0.0226, v_num=_tra]Epoch 0: 82%|████████▏ | 447/548 [00:07<00:01, 60.35it/s, loss=0.0227, v_num=_tra]Epoch 0: 82%|████████▏ | 448/548 [00:07<00:01, 60.37it/s, loss=0.0226, v_num=_tra]Epoch 0: 82%|████████▏ | 449/548 [00:07<00:01, 60.38it/s, loss=0.0226, v_num=_tra]Epoch 0: 82%|████████▏ | 450/548 [00:07<00:01, 60.37it/s, loss=0.0227, v_num=_tra]Epoch 0: 82%|████████▏ | 451/548 [00:07<00:01, 60.37it/s, loss=0.0227, v_num=_tra]Epoch 0: 82%|████████▏ | 451/548 [00:07<00:01, 60.36it/s, loss=0.0227, v_num=_tra]Epoch 0: 82%|████████▏ | 452/548 [00:07<00:01, 60.36it/s, loss=0.0228, v_num=_tra]Epoch 0: 83%|████████▎ | 453/548 [00:07<00:01, 60.36it/s, loss=0.0227, v_num=_tra]Epoch 0: 83%|████████▎ | 454/548 [00:07<00:01, 60.37it/s, loss=0.0229, v_num=_tra]Epoch 0: 83%|████████▎ | 455/548 [00:07<00:01, 60.38it/s, loss=0.0229, v_num=_tra]Epoch 0: 83%|████████▎ | 456/548 [00:07<00:01, 60.40it/s, loss=0.023, v_num=_tra] Epoch 0: 83%|████████▎ | 457/548 [00:07<00:01, 60.41it/s, loss=0.0229, v_num=_tra]Epoch 0: 84%|████████▎ | 458/548 [00:07<00:01, 60.40it/s, loss=0.0229, v_num=_tra]Epoch 0: 84%|████████▍ | 459/548 [00:07<00:01, 60.36it/s, loss=0.0229, v_num=_tra]Epoch 0: 84%|████████▍ | 459/548 [00:07<00:01, 60.36it/s, loss=0.0229, v_num=_tra]Epoch 0: 84%|████████▍ | 460/548 [00:07<00:01, 60.34it/s, loss=0.0228, v_num=_tra]Epoch 0: 84%|████████▍ | 461/548 [00:07<00:01, 60.29it/s, loss=0.0227, v_num=_tra]Epoch 0: 84%|████████▍ | 462/548 [00:07<00:01, 60.30it/s, loss=0.0226, v_num=_tra]Epoch 0: 84%|████████▍ | 463/548 [00:07<00:01, 60.29it/s, loss=0.0227, v_num=_tra]Epoch 0: 85%|████████▍ | 464/548 [00:07<00:01, 60.29it/s, loss=0.0226, v_num=_tra]Epoch 0: 85%|████████▍ | 465/548 [00:07<00:01, 60.28it/s, loss=0.0226, v_num=_tra]Epoch 0: 85%|████████▌ | 466/548 [00:07<00:01, 60.27it/s, loss=0.0226, v_num=_tra]Epoch 0: 85%|████████▌ | 467/548 [00:07<00:01, 60.26it/s, loss=0.0226, v_num=_tra]Epoch 0: 85%|████████▌ | 467/548 [00:07<00:01, 60.26it/s, loss=0.0225, v_num=_tra]Epoch 0: 85%|████████▌ | 468/548 [00:07<00:01, 60.26it/s, loss=0.0225, v_num=_tra]Epoch 0: 86%|████████▌ | 469/548 [00:07<00:01, 59.70it/s, loss=0.0225, v_num=_tra]
Validating: 0it [00:00, ?it/s][A
Validating: 0%| | 0/79 [00:00<?, ?it/s][A
Validating: 1%|▏ | 1/79 [00:00<00:21, 3.71it/s][AEpoch 0: 87%|████████▋ | 475/548 [00:08<00:01, 58.29it/s, loss=0.0225, v_num=_tra]
Validating: 32%|███▏ | 25/79 [00:00<00:00, 85.39it/s][AEpoch 0: 91%|█████████▏| 501/548 [00:08<00:00, 60.72it/s, loss=0.0225, v_num=_tra]
Validating: 67%|██████▋ | 53/79 [00:00<00:00, 148.28it/s][AEpoch 0: 96%|█████████▌| 527/548 [00:08<00:00, 63.11it/s, loss=0.0225, v_num=_tra]
Validating: 100%|██████████| 79/79 [00:00<00:00, 150.31it/s][AEpoch 0: 100%|██████████| 548/548 [00:10<00:00, 50.52it/s, loss=0.0225, v_num=_tra]
[AEpoch 0: 100%|██████████| 548/548 [00:10<00:00, 50.51it/s, loss=0.0225, v_num=_tra]Validation sanity check: 0it [00:00, ?it/s]Validation sanity check: 0%| | 0/2 [00:00<?, ?it/s]Validating: 0it [00:00, ?it/s] Validating: 0%| | 0/79 [00:00<?, ?it/s]Validating: 0%| | 0/79 [00:00<?, ?it/s]