format

Acellera · Apr 23, 2024 · 160dd89 · 160dd89
1 parent 5eed34e
commit 160dd89
Show file tree

Hide file tree

Showing 2 changed files with 1 addition and 2 deletions.
diff --git a/scripts/reinforce/config_scaffold.yaml b/scripts/reinforce/config_scaffold.yaml
@@ -29,4 +29,3 @@ model: gru # gru, lstm, or gpt2
 lr: 0.0001
 eps: 1.0e-08
 weight_decay: 0.0
-
diff --git a/scripts/reinforce/reinforce.py b/scripts/reinforce/reinforce.py
@@ -290,7 +290,7 @@ def compute_loss(data, model):
     agent_log_prob = get_log_prob(data, model)
     agent_likelihood = (agent_log_prob * mask).sum(-1)
     reward = data.get(("next", "reward")).squeeze(-1).sum(-1)
-    loss = - agent_likelihood * reward
+    loss = -agent_likelihood * reward
 
     return data, loss
Original file line number	Diff line number	Diff line change
Expand Up		@@ -29,4 +29,3 @@ model: gru # gru, lstm, or gpt2
		lr: 0.0001
		eps: 1.0e-08
		weight_decay: 0.0