-
Notifications
You must be signed in to change notification settings - Fork 31
Issues: NVIDIA/NeMo-Aligner
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
Some code related to Something isn't working
train_valid_test_num_samples
may be wrong / unused
bug
#176
opened May 17, 2024 by
odelalleau
Amend SPIN to be able to handle the cast of rollout_MBS < DP_size
#171
opened May 3, 2024 by
trias702
Docker build failing. Also, is there a .nemo reward model file available?
bug
Something isn't working
#167
opened May 1, 2024 by
rundiffusion
cannot load reward model from SFT model because of missing keys
bug
Something isn't working
#137
opened Apr 1, 2024 by
DZ9
SFT is broken with container 24.01.01
bug
Something isn't working
#131
opened Mar 22, 2024 by
odelalleau
SFT may crash if input data exceeds the context length
bug
Something isn't working
#127
opened Mar 15, 2024 by
odelalleau
Changing Something isn't working
num_rollout_samples
modifies the validation set in PPO
bug
#90
opened Jan 23, 2024 by
odelalleau
Padding impacts parallel_logits computation, affecting PPO logprobs
bug
Something isn't working
#68
opened Dec 28, 2023 by
shengyangs
The learning rate schedule is generally incorrect when Something isn't working
max_steps
is not set
bug
#65
opened Dec 19, 2023 by
odelalleau
More helpful error message when failing to connect to critic server
#58
opened Dec 14, 2023 by
odelalleau
GPTSFTChatDataset loss_mask becomes all False when prompt length > max_seq_length
bug
Something isn't working
#57
opened Dec 13, 2023 by
shengyangs
Previous Next
ProTip!
no:milestone will show everything without a milestone.