13 lines · 378 BytesRaw
train.py | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/train.py b/train.py
index 1f2f7ed..5bc2a06 100644
--- a/train.py
+++ b/train.py
@@ -3,4 +3,4 @@ LORA_RANK = 64
LR = 1e-4 # 3e-4 and 2e-4 diverged (run-17, run-18)
WARMUP_STEPS = 500
GRAD_CLIP = 1.0
-EARLY_STOP_PATIENCE = None
+EARLY_STOP_PATIENCE = 3 # evals (every 200 steps) without a new best