Spaces:
Runtime error
Runtime error
Update train.py
Browse files
train.py
CHANGED
|
@@ -44,10 +44,11 @@ except Exception as e:
|
|
| 44 |
print(f"Repo create: {e}")
|
| 45 |
|
| 46 |
MAX_SEQ_LEN = 1024
|
| 47 |
-
SFT_STEPS =
|
|
|
|
| 48 |
GRPO_STEPS = 250
|
| 49 |
GRPO_K = 2
|
| 50 |
-
GRPO_LR =
|
| 51 |
CURRICULUM_SWITCH = 0 # Start with Level 1, advance early
|
| 52 |
GRAD_CLIP = 1.0
|
| 53 |
SAVE_EVERY = 50
|
|
|
|
| 44 |
print(f"Repo create: {e}")
|
| 45 |
|
| 46 |
MAX_SEQ_LEN = 1024
|
| 47 |
+
SFT_STEPS = 80
|
| 48 |
+
# More warmup for JSON format
|
| 49 |
GRPO_STEPS = 250
|
| 50 |
GRPO_K = 2
|
| 51 |
+
GRPO_LR = 2e-5
|
| 52 |
CURRICULUM_SWITCH = 0 # Start with Level 1, advance early
|
| 53 |
GRAD_CLIP = 1.0
|
| 54 |
SAVE_EVERY = 50
|