Update README.md

README.md

@@ -52,7 +52,7 @@ datasets:
 ---
 # Granite-3.1-Earthen-v0.3-3B-A800M-QLoRA
 
-[`ibm-granite/granite-3.1-3b-a800m-instruct`](https://huggingface.co/ibm-granite/granite-3.1-3b-a800m-instruct) was trained at 8K with batch size 2 gradient accumulation 8, so each step was 131,072 tokens (including any padding tokens). It was trained for 400 steps, adding up to a total of 52,428,800 unique tokens seen.
+[`ibm-granite/granite-3.1-3b-a800m-instruct`](https://huggingface.co/ibm-granite/granite-3.1-3b-a800m-instruct) was trained at 8K with batch size 2 gradient accumulation 8, so each step was 131,072 tokens (including any padding tokens). It was trained for 500 steps, adding up to a total of 65,536,000 unique tokens seen.
 
 This is a small test run. A larger version is planned.