-
Notifications
You must be signed in to change notification settings - Fork 168
Open
Description
First of all, thank you for your excellent work!
I have not modified any other parameters, but my losses are still high after 25 rounds of training. Do I still need to continue training? Is this normal?
Look forward to your reply!
Here is the specific situation:
23100.7s | 1674 | Mon Mar 27 23:05:44 2023 Epoch: 24 Sample 7120/7200 Loss: 0.4667869508266449 |
---|---|---|
23104.6s | 1675 | Mon Mar 27 23:05:48 2023 Epoch: 24 Sample 7130/7200 Loss: 0.5839558243751526 |
23108.4s | 1676 | Mon Mar 27 23:05:52 2023 Epoch: 24 Sample 7140/7200 Loss: 0.4183468520641327 |
23112.2s | 1677 | Mon Mar 27 23:05:55 2023 Epoch: 24 Sample 7150/7200 Loss: 0.6217041611671448 |
23116.2s | 1678 | Mon Mar 27 23:05:59 2023 Epoch: 24 Sample 7160/7200 Loss: 0.5632153153419495 |
23120.8s | 1679 | Mon Mar 27 23:06:03 2023 Epoch: 24 Sample 7170/7200 Loss: 0.47710853815078735 |
23123.9s | 1680 | Mon Mar 27 23:06:07 2023 Epoch: 24 Sample 7180/7200 Loss: 0.6275425553321838 |
23127.7s | 1681 | Mon Mar 27 23:06:11 2023 Epoch: 24 Sample 7190/7200 Loss: 0.42571431398391724 |
23143.9s | 1682 | Current learning rate> 0.0001 |
23143.9s | 1683 | ------------------------------------------------------- |
23143.9s | 1684 | DexiNed, # of Parameters: |
23143.9s | 1685 | 35215245 |
Metadata
Metadata
Assignees
Labels
No labels