Bert-Chinese-Text-Classification-Pytorch
Bert-Chinese-Text-Classification-Pytorch copied to clipboard
649453932
大佬们，小白问一个简单的问题
你跑一遍就知道了，我跑完输出如下
Iter: 0, Train Loss: 2.4, Train Acc: 13.28%, Val Loss: 2.4, Val Acc: 9.08%, Time: 0:00:08 *
Iter: 100, Train Loss: 0.35, Train Acc: 88.28%, Val Loss: 0.38, Val Acc: 88.66%, Time: 0:00:52 *
Iter: 200, Train Loss: 0.37, Train Acc: 89.06%, Val Loss: 0.37, Val Acc: 88.97%, Time: 0:01:38 *
Iter: 300, Train Loss: 0.33, Train Acc: 90.62%, Val Loss: 0.3, Val Acc: 90.87%, Time: 0:02:25 *
Iter: 400, Train Loss: 0.5, Train Acc: 85.16%, Val Loss: 0.28, Val Acc: 91.54%, Time: 0:03:13 *
Iter: 500, Train Loss: 0.23, Train Acc: 93.75%, Val Loss: 0.25, Val Acc: 92.19%, Time: 0:04:01 *
Iter: 600, Train Loss: 0.31, Train Acc: 90.62%, Val Loss: 0.25, Val Acc: 91.99%, Time: 0:04:50 *
Iter: 700, Train Loss: 0.24, Train Acc: 92.19%, Val Loss: 0.24, Val Acc: 92.43%, Time: 0:05:39 *
Iter: 800, Train Loss: 0.18, Train Acc: 93.75%, Val Loss: 0.22, Val Acc: 92.98%, Time: 0:06:28 *
Iter: 900, Train Loss: 0.2, Train Acc: 93.75%, Val Loss: 0.21, Val Acc: 93.22%, Time: 0:07:18 *
Iter: 1000, Train Loss: 0.16, Train Acc: 93.75%, Val Loss: 0.22, Val Acc: 92.66%, Time: 0:08:04
Iter: 1100, Train Loss: 0.21, Train Acc: 93.75%, Val Loss: 0.2, Val Acc: 93.24%, Time: 0:08:55 *
Iter: 1200, Train Loss: 0.17, Train Acc: 93.75%, Val Loss: 0.21, Val Acc: 93.19%, Time: 0:09:41
Iter: 1300, Train Loss: 0.23, Train Acc: 89.84%, Val Loss: 0.2, Val Acc: 93.27%, Time: 0:10:33 *
Iter: 1400, Train Loss: 0.29, Train Acc: 92.97%, Val Loss: 0.2, Val Acc: 93.57%, Time: 0:11:24 *
Epoch [2/3]
Iter: 1500, Train Loss: 0.17, Train Acc: 94.53%, Val Loss: 0.19, Val Acc: 93.64%, Time: 0:12:15 *
Iter: 1600, Train Loss: 0.22, Train Acc: 91.41%, Val Loss: 0.2, Val Acc: 93.53%, Time: 0:13:02
Iter: 1700, Train Loss: 0.14, Train Acc: 96.09%, Val Loss: 0.19, Val Acc: 93.67%, Time: 0:13:55 *
Iter: 1800, Train Loss: 0.091, Train Acc: 96.88%, Val Loss: 0.19, Val Acc: 94.04%, Time: 0:14:46 *
Iter: 1900, Train Loss: 0.12, Train Acc: 96.09%, Val Loss: 0.18, Val Acc: 94.02%, Time: 0:15:38 *
Iter: 2000, Train Loss: 0.13, Train Acc: 96.09%, Val Loss: 0.2, Val Acc: 93.96%, Time: 0:16:26
Iter: 2100, Train Loss: 0.12, Train Acc: 96.09%, Val Loss: 0.2, Val Acc: 93.67%, Time: 0:17:15
Iter: 2200, Train Loss: 0.089, Train Acc: 96.88%, Val Loss: 0.19, Val Acc: 93.96%, Time: 0:18:04
Iter: 2300, Train Loss: 0.081, Train Acc: 96.09%, Val Loss: 0.19, Val Acc: 94.23%, Time: 0:18:54
Iter: 2400, Train Loss: 0.054, Train Acc: 96.88%, Val Loss: 0.19, Val Acc: 93.99%, Time: 0:19:44
Iter: 2500, Train Loss: 0.12, Train Acc: 96.88%, Val Loss: 0.19, Val Acc: 93.98%, Time: 0:20:33
Iter: 2600, Train Loss: 0.11, Train Acc: 94.53%, Val Loss: 0.19, Val Acc: 93.99%, Time: 0:21:24
Iter: 2700, Train Loss: 0.1, Train Acc: 96.09%, Val Loss: 0.18, Val Acc: 94.06%, Time: 0:22:14
Iter: 2800, Train Loss: 0.057, Train Acc: 97.66%, Val Loss: 0.18, Val Acc: 94.20%, Time: 0:23:09 *
Epoch [3/3]
Iter: 2900, Train Loss: 0.11, Train Acc: 97.66%, Val Loss: 0.19, Val Acc: 94.15%, Time: 0:23:57
Iter: 3000, Train Loss: 0.083, Train Acc: 98.44%, Val Loss: 0.19, Val Acc: 94.29%, Time: 0:24:47
Iter: 3100, Train Loss: 0.063, Train Acc: 96.88%, Val Loss: 0.19, Val Acc: 94.24%, Time: 0:25:37
Iter: 3200, Train Loss: 0.15, Train Acc: 96.09%, Val Loss: 0.19, Val Acc: 94.04%, Time: 0:26:28
Iter: 3300, Train Loss: 0.025, Train Acc: 100.00%, Val Loss: 0.19, Val Acc: 94.31%, Time: 0:27:18
Iter: 3400, Train Loss: 0.051, Train Acc: 98.44%, Val Loss: 0.19, Val Acc: 94.48%, Time: 0:28:09
Iter: 3500, Train Loss: 0.05, Train Acc: 97.66%, Val Loss: 0.19, Val Acc: 94.45%, Time: 0:28:59
Iter: 3600, Train Loss: 0.014, Train Acc: 100.00%, Val Loss: 0.19, Val Acc: 94.50%, Time: 0:29:50
Iter: 3700, Train Loss: 0.097, Train Acc: 96.88%, Val Loss: 0.19, Val Acc: 94.40%, Time: 0:30:41
Iter: 3800, Train Loss: 0.041, Train Acc: 98.44%, Val Loss: 0.19, Val Acc: 94.57%, Time: 0:31:32
No optimization for a long time, auto-stopping...
Test Loss: 0.17, Test Acc: 94.82%
