Update README.md

README.md

@@ -55,7 +55,7 @@ The following hyperparameters were used during training:
 - num_epochs: 1
 ```
 
-Optimizer `paged_adamw_8bit` and Deepspeed ZeRO 3 was used at a LR of `1e-5` using the cosine scheduler for 1 epoch on 3x3090s taking 4h 12m 13s total.
+Optimizer `paged_adamw_8bit` and Deepspeed ZeRO 3 was used at a LR of `1e-5` using the cosine scheduler for 1 epoch on 3x3090s taking 2h 30m total.
 
 Sample packing and padding was disabled to reduce VRAM consumption significantly at the cost of speed.