Update README.md

README.md

@@ -52,7 +52,7 @@ datasets:
 ---
 # Gemma-3-Starshine-Earthen-v0.4-12B-QLoRA
 
-[`ToastyPigeon/Gemma-3-Starshine-12B`](https://huggingface.co/ToastyPigeon/Gemma-3-Starshine-12B) was trained at 8K with batch size 4 gradient accumulation 1, so each step was 32,768 tokens (including any padding tokens). It was trained for 40 steps, adding up to a total of 1,310,720 unique tokens seen.
+[`ToastyPigeon/Gemma-3-Starshine-12B`](https://huggingface.co/ToastyPigeon/Gemma-3-Starshine-12B) was trained at 8K with batch size 4 gradient accumulation 1, so each step was 32,768 tokens (including any padding tokens). It was trained for 100 steps, adding up to a total of 3,276,800 unique tokens seen.
 
 ## Quants