theblackcat102 commited on
Commit
882ad73
1 Parent(s): 6a85b57

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -92,10 +92,10 @@ print(output)
92
  ## Training Procedure
93
 
94
  ```
95
- deepspeed trainer_sft.py --configs defaults pythia-1b --deepspeed
96
  ```
97
 
98
- This model was trained for 1000 iterations.
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