Update README.md

README.md

@@ -37,7 +37,7 @@ Refer to the base model for info on the patching process.
 
 Besides language modeling, another aim of this experiment was to test the accelerate library by offloading certain workloads to CPU as well as finding the optimal training iterations.
 
-The perplexity of this model is 17.17 after 160,000 steps. Comparing to the previous [attempt](https://huggingface.co/jed351/gpt2_tiny_zh-hk-shikoto) 27.02 after 400,000 steps. 
+The perplexity of this model is 16.12 after 400,000 steps. Comparing to the previous [attempt](https://huggingface.co/jed351/gpt2_tiny_zh-hk-shikoto) 27.02 after 400,000 steps. 
 It took around the same time duration to train this model but I only used 1 GPU here.
 
 
@@ -47,7 +47,7 @@ Please refer to the [script](https://github.com/huggingface/transformers/tree/ma
 provided by Huggingface. 
 
 
-The model was trained for 160,000 steps on 1 NVIDIA Quadro RTX6000 for around 15 hours at the Research Computing Services of Imperial College London. 
+The model was trained for 400,000 steps on 1 NVIDIA Quadro RTX6000 for around 30 hours at the Research Computing Services of Imperial College London.