WeightsnWizardry
commited on
Commit
•
feb92bd
1
Parent(s):
e60fdf7
Update README.md
Browse files
README.md
CHANGED
@@ -125,7 +125,7 @@ Samples from each of the datasets have been programmatically formatted to chat,
|
|
125 |
| Clip Range Value | 0.2 |
|
126 |
| Whiten Advantages | `true` |
|
127 |
| Whiten Rewards | `false` |
|
128 |
-
|
|
129 |
| Max Steps | 200 |
|
130 |
| PPO steps/epoch | 1 |
|
131 |
| Value steps/epoch | 8 |
|
|
|
125 |
| Clip Range Value | 0.2 |
|
126 |
| Whiten Advantages | `true` |
|
127 |
| Whiten Rewards | `false` |
|
128 |
+
| Score on EOD | `true` |
|
129 |
| Max Steps | 200 |
|
130 |
| PPO steps/epoch | 1 |
|
131 |
| Value steps/epoch | 8 |
|