We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent c8a3eeb commit 95637f3Copy full SHA for 95637f3
test/test_cost.py
@@ -9642,7 +9642,7 @@ def test_ppo_value_clipping(
9642
KeyError,
9643
match=f"clip_value is set to {loss_fn.clip_value}, but the key "
9644
"state_value was not found in the input tensordict. "
9645
- "Make sure that the value_key passed to PPO exists in "
+ "Make sure that the.*passed to PPO exists in "
9646
"the input tensordict.",
9647
):
9648
loss = loss_fn(td)
torchrl/envs/llm/transforms/reason.py
@@ -153,7 +153,6 @@ def _step(
153
Returns:
154
The modified next_tensordict
155
"""
156
- print("Reward", next_tensordict["reward"])
157
# Handle batch dimensions
158
if next_tensordict.batch_dims >= 1:
159
ntds = []
0 commit comments