theblackcat102
commited on
Commit
•
882ad73
1
Parent(s):
6a85b57
Update README.md
Browse files
README.md
CHANGED
@@ -92,10 +92,10 @@ print(output)
|
|
92 |
## Training Procedure
|
93 |
|
94 |
```
|
95 |
-
deepspeed trainer_sft.py --configs defaults pythia-
|
96 |
```
|
97 |
|
98 |
-
This model was trained for
|
99 |
|
100 |
### Training Hyperparameters
|
101 |
|
|
|
92 |
## Training Procedure
|
93 |
|
94 |
```
|
95 |
+
deepspeed trainer_sft.py --configs defaults pythia-1-4b-ost --deepspeed
|
96 |
```
|
97 |
|
98 |
+
This model was trained for 200 iterations. After 200 iterations the accuracy started to drop and loss increasing which is a sign of overfitting.
|
99 |
|
100 |
### Training Hyperparameters
|
101 |
|