Update README.md

README.md

@@ -55,10 +55,10 @@ print(tok.decode(out[0], skip_special_tokens=True))
 ## Training procedure
 
 * ~512 warm-start steps (Alpaca-style data)
-* 256 SFT steps on `O1-OPEN/OpenO1-SFT`
-* +100 top-up SFT steps for reasoning behaviors
+* 256 Additional pretraining steps on (O1-OPEN/OpenO1-SFT)
+* 128  SFT steps with  (Jackrong/gpt-oss-120b-reasoning-STEM-5K)
+* 256 SFT steps with (O1-OPEN/OpenO1-SFT)
 
-This model was trained with SFT.
 
 ### Framework versions