Upload train_hf.py with huggingface_hub
Browse files- train_hf.py +2 -2
train_hf.py
CHANGED
|
@@ -35,8 +35,8 @@ ACCUM_STEPS = 4
|
|
| 35 |
LR = 1e-6
|
| 36 |
PPO_EPOCHS = 4
|
| 37 |
PPO_EPS = 0.2
|
| 38 |
-
KL_COEFF = 0.
|
| 39 |
-
SL_COEFF = 0.
|
| 40 |
ENTROPY_COEFF = 0.0
|
| 41 |
NUM_STEPS = 1000
|
| 42 |
LOG_INTERVAL = 10
|
|
|
|
| 35 |
LR = 1e-6
|
| 36 |
PPO_EPOCHS = 4
|
| 37 |
PPO_EPS = 0.2
|
| 38 |
+
KL_COEFF = 0.5
|
| 39 |
+
SL_COEFF = 0.0
|
| 40 |
ENTROPY_COEFF = 0.0
|
| 41 |
NUM_STEPS = 1000
|
| 42 |
LOG_INTERVAL = 10
|