-
-
I try to add weight_decay and momentum in the update_params() function in the model.py but I cannot figure it out yet. Could anybody give me some advice? Thank you in advance.
-
## Describe the bug
In the current implementation, all subclasses of `MPCPlannerBase` do not consider `done` thrown by env during the planning process, which means that MPC is invalid in a large cl…
-
Just noticed your package. Looks promising. Just two suggestions
1. drop Optim.jl since its a heavy dependency. I believe a simple golden section search should be enough (like 20 lines of code). See …
-
### Issue Description
Standard errors derived from hessian matrices of `optim` function output could be used to assess confidence in that output.
Hessian matrices could be included in final output…
-
Hi,
I have pasted code below of error when running ichor_CNA snakemake:
Error in optim(n_prev, fn = completeLikelihoodFun, pType = rep("n", S), :
2 L-BFGS-B needs finite values of 'fn'
…
-
### Motivation and description
A common practice in machine learning is to take a pre-trained model and fine-tune it on a particular dataset. This typically involves freezing the weights in some la…
-
I'm training XLM model with MLM+TLM for english and spanish, however I got the oom error. The log is as followed:
INFO - 03/05/20 16:22:31 - 0:02:34 - Number of parameters (model): 3834768422
INFO -…
-
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…
-
### 🐛 Describe the bug
After an optimizer step, the weights become NaN.
Testcase: [train_distributed.txt](https://github.com/pytorch/pytorch/files/15344575/train_distributed.txt) (actually .py)
…
ad8e updated
3 months ago