Cosine Decay Not Properly Enforced
Open
bug
i-nvpr
- Dominant language
- Python
- Stars
- 2k
- Forks
- 561
- Avg merge
- 4d 5h
- Merged PRs (30d)
- 145
Description
When passing the following hyper-parameters , one expects to see a cosine decay profile:
```
scheduler:
start_weight_decay: ${policy.megatron_cfg.optimizer.weight_decay}
end_weight_decay: ${policy.megatron_cfg.optimizer.weight_decay}
weight_decay_incr_style: "cosine"
lr_decay_style: "cosine"
lr_warmup_iters: 25
lr_warmup_init: 1e-7
```
However, although warmup is properly enforced, learning rate seems to remain constant. Please see the figure below.
We appreciate if there is a solution for actual enforcement of a cosine decay profile.
Contributor guide
Assessment
This issue has not been assessed yet.