Upgrade lightning to 2.0 #3419
Upgrade lightning to 2.0 #3419
Conversation
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
zhiqiangdon
added
the
model list checked
zhiqiangdon
changed the title
|
Job PR-3419-05d0c20 is done. |
zhiqiangdon
requested review from
tonyhoo,
shchur,
suzhoum,
yinweisu and
FANGAreNotGnu
|
Job PR-3419-059fd91 is done. |
timeseries/setup.py
Outdated
| @@ -30,7 +30,7 @@ | |||
| "torch", # version range defined in `core/_setup_utils.py` | |||
| "statsmodels>=0.13.0,<0.15", | |||
| "gluonts>=0.13.1,<0.14", | |||
| "pytorch-lightning>=1.7.4,<1.10.0", | |||
| "pytorch-lightning>=2.0.0,<2.1", | |||
There was a problem hiding this comment.
Changes to timeseries look good to me, I validated that everything works as expected locally with pytorch-lightning v2.0.
Feel free to merge once the changes to multimodal are approved.
| @@ -5,6 +5,7 @@ | |||
| import torch | |||
| import torch.nn.functional as F | |||
| import torchmetrics | |||
| from pytorch_lightning.utilities import grad_norm | |||
There was a problem hiding this comment.
Should we at some point consider switching to the new API (as described here) or should we wait until the deprecation notice is released for the old API?
import lightning as LThere was a problem hiding this comment.
Good call. We can switch to the new namespace when it becomes more stable.
|
Job PR-3419-7acac86 is done. |
|
Job PR-3419-87c9101 is done. |
* 'master' of https://github.com/awslabs/autogluon: Upgrade lightning to 2.0 (autogluon#3419)
Issue #, if available:
Description of changes:
track_grad_norm. Refer to Remove Trainer'strack_grad_normargument Lightning-AI/pytorch-lightning#16745autoinstead of None, which is required by lightning 2.0.strategy_nameattribute since some strategies like DDPStrategy no longer has it.TODOs:
By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.