Skip to content

fix: pass missing gts argument to _dump_generations call #528

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.

Sign up for GitHub

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

Open
Alexi5000 wants to merge 1 commit into
base: main
Choose a base branch
from
+2 −2
Open

fix: pass missing gts argument to _dump_generations call #528

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion agentlightning/verl/trainer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -414,13 +414,13 @@ def _train_step(self, batch_dict: dict) -> dict:
rollout_data_dir = self.config.trainer.get("rollout_data_dir", None)
if rollout_data_dir:
with _timer("dump_rollout_generations", timing_raw):
print(batch.batch.keys())
inputs = self.tokenizer.batch_decode(batch.batch["prompts"], skip_special_tokens=True)
outputs = self.tokenizer.batch_decode(batch.batch["responses"], skip_special_tokens=True)
scores = batch.batch["token_level_scores"].sum(-1).cpu().tolist()
self._dump_generations(
inputs=inputs,
outputs=outputs,
gts=None,
scores=scores,
reward_extra_infos_dict=reward_extra_infos_dict,
dump_path=rollout_data_dir,
Comment on lines 420 to 426
Expand Down
2 changes: 1 addition & 1 deletion contrib/agentlightning/contrib/algorithm/env_verl/trainer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -514,13 +514,13 @@ def _train_step(self, batch_dict: dict) -> dict:
rollout_data_dir = self.config.trainer.get("rollout_data_dir", None)
if rollout_data_dir:
with _timer("dump_rollout_generations", timing_raw):
print(batch.batch.keys())
inputs = self.tokenizer.batch_decode(batch.batch["prompts"], skip_special_tokens=True)
outputs = self.tokenizer.batch_decode(batch.batch["responses"], skip_special_tokens=True)
scores = batch.batch["token_level_scores"].sum(-1).cpu().tolist()
self._dump_generations(
inputs=inputs,
outputs=outputs,
gts=None,
scores=scores,
reward_extra_infos_dict=reward_extra_infos_dict,
dump_path=rollout_data_dir,
Comment on lines 520 to 526
Expand Down