Update README.md

README.md

@@ -20,7 +20,14 @@ tags:
 Experimental RP Finetune with secret sauce dataset, rsLoRA, r = 64, on an Colab A100 instance. 30GB vRAM used, 2 epochs ~ 3hrs of training.
 
 ```
-         r = 64, 
+==((====))==  Unsloth - 2x faster free finetuning | Num GPUs = 1
+   \\   /|    Num examples = 8,160 | Num Epochs = 2
+O^O/ \_/ \    Batch size per device = 2 | Gradient Accumulation steps = 4
+\        /    Total batch size = 8 | Total steps = 2,040
+ "-____-"     Number of trainable parameters = 228,065,280
+
+
+        r = 64, 
         target_modules = ["q_proj", "k_proj", "v_proj", "o_proj",
                           "gate_proj", "up_proj", "down_proj",],
         lora_alpha = 64,