fix NaN loss not caught by fast-fail check

`train_loss_f > 100` silently passes on NaN because IEEE 754 NaN
comparisons always return False. When an agent experiment produces
NaN (e.g. from an aggressive LR change), the run wastes the full
5-minute budget instead of failing fast.

`not (x <= 100)` catches both >100 and NaN with no added complexity.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

train.py

@@ -565,8 +565,8 @@ while True:
 
     train_loss_f = train_loss.item()
 
-    # Fast fail: abort if loss is exploding
-    if train_loss_f > 100:
+    # Fast fail: abort if loss is exploding or NaN
+    if not train_loss_f <= 100:
         print("FAIL")
         exit(1)