wangzixiang
/
lerobot
mirror of https://github.com/huggingface/lerobot.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

remove redundant comments

This commit is contained in:
jayLEE0301 2024-06-08 18:28:53 -04:00
parent 32fa5d22b9
commit 2a6af3a6ad
1 changed files with 0 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
lerobot/common/policies/vqbet/modeling_vqbet.py
View File

@ -2321,7 +2321,6 @@ class GPT(nn.Module):
This long function is unfortunately doing something very simple and is being very defensive:
We are separating out all parameters of the model into two buckets: those that will experience
weight decay for regularization and those that won't (biases, and layernorm/embedding weights).
We are then returning the PyTorch optimizer object.
"""
# separate out all parameters to those that will and won't experience regularizing weight decay
@ -2355,24 +2354,6 @@ class GPT(nn.Module):
str(param_dict.keys() - union_params),
)
# create the pytorch optimizer object
# optim_groups = [
# {
# "params": [param_dict[pn] for pn in sorted(list(decay))],
# "weight_decay": weight_decay,
# },
# {
# "params": [param_dict[pn] for pn in sorted(list(no_decay))],
# "weight_decay": 0.0,
# },
# ]
decay = [param_dict[pn] for pn in sorted(list(decay))]
no_decay = [param_dict[pn] for pn in sorted(list(no_decay))]
return decay, no_decay
# if optimizer=="Adamw":
# optimizer = torch.optim.AdamW(optim_groups, lr=learning_rate, betas=betas)
# elif optimizer=="Adam":
# optimizer = torch.optim.Adam(optim_groups, lr=learning_rate, betas=betas, eps=eps)
# else:
# raise NotImplementedError
# return optimizer