Skip to content
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

Geshen/async mcts #101

Draft
wants to merge 83 commits into
base: yi/search_benchmark
Choose a base branch
from
Draft

Geshen/async mcts #101

wants to merge 83 commits into from

Conversation

gshennvm
Copy link
Collaborator

@gshennvm gshennvm commented Feb 7, 2024

DRAFT tracking only

gshennvm and others added 30 commits January 28, 2024 21:34
Signed-off-by: Gerald Shen <geshen@nvidia.com>

fix

Signed-off-by: Gerald Shen <geshen@nvidia.com>
Signed-off-by: Gerald Shen <geshen@nvidia.com>
Signed-off-by: Gerald Shen <geshen@nvidia.com>
Signed-off-by: Gerald Shen <geshen@nvidia.com>
Signed-off-by: Gerald Shen <geshen@nvidia.com>
Signed-off-by: Gerald Shen <geshen@nvidia.com>
Signed-off-by: Gerald Shen <geshen@nvidia.com>
Signed-off-by: Gerald Shen <geshen@nvidia.com>
Signed-off-by: Gerald Shen <geshen@nvidia.com>
Signed-off-by: Gerald Shen <geshen@nvidia.com>
Signed-off-by: Gerald Shen <geshen@nvidia.com>
Signed-off-by: Gerald Shen <geshen@nvidia.com>
Signed-off-by: Gerald Shen <geshen@nvidia.com>
Signed-off-by: Gerald Shen <geshen@nvidia.com>
Signed-off-by: Gerald Shen <geshen@nvidia.com>
Signed-off-by: Gerald Shen <geshen@nvidia.com>
Signed-off-by: Gerald Shen <geshen@nvidia.com>
Signed-off-by: Gerald Shen <geshen@nvidia.com>
Signed-off-by: Gerald Shen <geshen@nvidia.com>
Signed-off-by: Gerald Shen <geshen@nvidia.com>
Signed-off-by: Yi Dong <yidong@nvidia.com>
gshennvm and others added 15 commits February 7, 2024 00:11
Signed-off-by: Gerald Shen <geshen@nvidia.com>
Signed-off-by: Gerald Shen <geshen@nvidia.com>
Signed-off-by: Gerald Shen <geshen@nvidia.com>
Signed-off-by: Gerald Shen <geshen@nvidia.com>
Signed-off-by: Gerald Shen <geshen@nvidia.com>
Signed-off-by: Gerald Shen <geshen@nvidia.com>
Signed-off-by: Gerald Shen <geshen@nvidia.com>
Signed-off-by: Gerald Shen <geshen@nvidia.com>
Signed-off-by: Gerald Shen <geshen@nvidia.com>
Signed-off-by: Gerald Shen <geshen@nvidia.com>
Signed-off-by: Gerald Shen <geshen@nvidia.com>
Signed-off-by: Gerald Shen <geshen@nvidia.com>
return_value_memory.append((list(spg.value_memory), spg.data_id, backup_root_states[i]))
del parallel_searches[i]
del backup_root_states[i]
if is_terminal:
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

indentation error?

Signed-off-by: Gerald Shen <geshen@nvidia.com>
Signed-off-by: Gerald Shen <geshen@nvidia.com>
cfg.model,
trainer,
strict=True,
load_base_model_only=True,
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

will it cause a problem that the second time we load the improved hybrid network, it won't load the value head weights?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

the second time we load the value head, PTL will overwrite this checkpoint that we loaded, so it should be pretty safe

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

okay. so you are loading from ckpt not nemo files

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

yeah, so when we have no checkpoint it loads from the .nemo file, when there is a checkpoint it loads this .nemo file but PTL will overwrite it

Signed-off-by: Gerald Shen <geshen@nvidia.com>
Signed-off-by: Gerald Shen <geshen@nvidia.com>
Signed-off-by: Gerald Shen <geshen@nvidia.com>
Signed-off-by: Gerald Shen <geshen@nvidia.com>
Signed-off-by: Gerald Shen <geshen@nvidia.com>
Signed-off-by: Gerald Shen <geshen@nvidia.com>
Signed-off-by: Gerald Shen <geshen@nvidia.com>
Signed-off-by: Gerald Shen <geshen@nvidia.com>
Signed-off-by: Gerald Shen <geshen@nvidia.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

2 participants