100%|██████████| 114/114 [00:16<00:00, 6.90 batches/s, epoch=1, train loss= 4.9292, val loss= 4.8979]
100%|██████████| 114/114 [00:16<00:00, 6.83 batches/s, epoch=2, train loss= 4.3143, val loss= 4.5898]
100%|██████████| 114/114 [00:16<00:00, 6.81 batches/s, epoch=3, train loss= 3.9902, val loss= 4.3482]
100%|██████████| 114/114 [00:16<00:00, 6.76 batches/s, epoch=4, train loss= 3.6813, val loss= 4.1082]
100%|██████████| 114/114 [00:16<00:00, 6.78 batches/s, epoch=5, train loss= 3.4669, val loss= 4.0274]
100%|██████████| 114/114 [00:16<00:00, 6.72 batches/s, epoch=6, train loss= 3.3279, val loss= 3.8433]
100%|██████████| 114/114 [00:16<00:00, 6.72 batches/s, epoch=7, train loss= 3.156, val loss= 3.863]
100%|██████████| 114/114 [00:17<00:00, 6.70 batches/s, epoch=8, train loss= 3.039, val loss= 3.8006]
100%|██████████| 114/114 [00:16<00:00, 6.73 batches/s, epoch=9, train loss= 2.9121, val loss= 3.7312]
100%|██████████| 114/114 [00:17<00:00, 6.71 batches/s, epoch=10, train loss= 2.8272, val loss= 3.7297]
100%|██████████| 114/114 [00:17<00:00, 6.69 batches/s, epoch=11, train loss= 2.697, val loss= 3.6217]
100%|██████████| 114/114 [00:17<00:00, 6.69 batches/s, epoch=12, train loss= 2.6489, val loss= 3.5662]
100%|██████████| 114/114 [00:17<00:00, 6.70 batches/s, epoch=13, train loss= 2.5568, val loss= 3.6312]
100%|██████████| 114/114 [00:16<00:00, 6.71 batches/s, epoch=14, train loss= 2.4507, val loss= 3.6511]
100%|██████████| 114/114 [00:16<00:00, 6.72 batches/s, epoch=15, train loss= 2.3717, val loss= 3.6543]
100%|██████████| 114/114 [00:17<00:00, 6.69 batches/s, epoch=16, train loss= 2.3243, val loss= 3.5326]
100%|██████████| 114/114 [00:16<00:00, 6.72 batches/s, epoch=17, train loss= 2.2451, val loss= 3.6471]
100%|██████████| 114/114 [00:17<00:00, 6.69 batches/s, epoch=18, train loss= 2.1703, val loss= 3.65]
100%|██████████| 114/114 [00:17<00:00, 6.70 batches/s, epoch=19, train loss= 2.0889, val loss= 3.6411]
100%|██████████| 114/114 [00:17<00:00, 6.68 batches/s, epoch=20, train loss= 2.0468, val loss= 3.6686]