Update README.md

fully custom dataset fine-tune

README.md

@@ -1,7 +1,5 @@
 ---
 license: cc-by-2.0
-datasets:
-- teknium/OpenHermes-2.5
 language:
 - en
 tags:
@@ -11,10 +9,10 @@ tags:
 - art
 ---
 
-Behold, one of the first fine-tunes of Mistral's 7B 0.2 Base model. SatoshiN is trained on 4 epochs of a diverse custom data-set, combined with a single sanitization round of teknium/OpenHermes2.5.
+Behold, one of the first fine-tunes of Mistral's 7B 0.2 Base model. SatoshiN is trained on 4 epochs 2e-4 learning rate (cosine) of a diverse custom data-set, combined with a polishing round of that same data-set at a 1e-4 linear learning rate.
 It's a nice assistant that isn't afraid to ask questions, and gather additional information before providing a response to user prompts.
 
-  I have found success using a variety of instruction-formats such as Alpaca, ChatML and Mistral. The custom training was performed on raw-text with the idea that it might acquire better generalization skills.
+  I have found varying success using instruction-formats such as Alpaca, ChatML and Mistral. The custom training was performed on raw-text with the idea that it might acquire better generalization skills.
 
   Total model-size has increased from 7.24B to 7.35B after merging a .5GB LoRa via PEFT.