-
We have a `differentiable `flag in the adam optimizer. This will not work as expected as we always detach the parameters.
Also, we should reconsider which of the optimizer flags we actually support…
-
In the substitutions batch of our LogicalPlanOptimizer, there's[ 4 rules](https://github.com/elastic/elasticsearch/blob/b5ec38e75ddafcf0584609c36afa87145a4ab0dc/x-pack/plugin/esql/src/main/java/org/el…
-
**Describe the bug**
The optimizer can be changed in dialog (either from the Preferences or Fit Algorithms tab) but it has no effect. It still runs the same optimizer as SasView started.
**To Rep…
-
hi, thanks for this excellent work. I have noticed that in the code of train-stage1.py line 106, the optimizer is AdamW
opt = torch.optim.AdamW(
swinir.parameters(), lr=cfg.train.learning_ra…
-
Currently every optimizer comes with a `config` specifically for that optimizer that manages the hyperparameters for the optimizer.
This is made because of the following reasons:
* A lot of hyp…
-
![飞书20240528-101519](https://github.com/Hujiazeng/Vach/assets/169432626/5ba72027-69e3-400a-9ad7-69bc9ef63811)
Failed to load optimizer.
loaded state dict has a different number of parameter groups
-
I'm trying to use your implementation to faster optimize a problem that I've already trated using different optimizers and libraries. During the first iteration of LFBGS_B, the losses are in the first…
-
Hello! Thank you for the clean + user friendly codebase!
I'm trying to finetune the VQ-VAE tokenizer and noticed some keys might be missing from the pretrained checkpoint listed on huggingface: `"o…
-
Split the `OptimizerRules` class and associated tests into individual top level classes and single-class test files.
Right now, the `OptimizerRules` class is over 1000 lines long, and has another 1…
-
Hi guys! I got the following error when using Unsloth patch 2024.7 to resume training from checkpoint.
```
RuntimeError: Expected all tensors to be on the same device, but found at least two devices…