Update README.md

README.md

@@ -20,18 +20,24 @@ base_model:
 
 # Newest: NLI head preliminary
 
-So the outcome is surprisingly good. Around 75% accuracy give or take for NLI with the prototype conv5d that I'm working with.
+So the outcome is surprisingly good. Around 75-76% accuracy give or take for NLI with the prototype conv5d that I'm working with.
 
 It's not a true conv5d, more an accumulator meant to encapsulate the necessary behavioral implications of every stretch that implicates the potential for a conv5d.
 This structure when paired with structural geometry defeats the MLP in terms of overfitting.
 
 MLP managed to overfit the model at around 71% or so, to nearly 95% training accuracy.
 
-Conv5d managed to preserve the bank's geometry instead of completely collapsing it into noise, allowing around 75% with 80% training accuracy.
+Conv5d managed to preserve the bank's geometry instead of completely collapsing it into noise, allowing around 75-76% with 80% training accuracy.
 
 So the problem is still present. Without the bank the model reached around 64% or so, with the anchor bank the model reaches around 75% with geometric solidity but it's not
 enough to say the NLI head works yet.
 
+As you can see either way, the model does eventually begin to overfit in it's current state. It's simply too small and predominantly distilled,
+which means it will have problems no matter which task I attempt to teach this model.
+
+
+![image](https://cdn-uploads.huggingface.co/production/uploads/630cf55b15433862cfc9556f/Yudr9ZF_bWx-8xAbSqGDr.png)
+
 HOWEVER, it's enough to say that it can with more training. This is enough to continue for me.
 
 If I were to say unlock the model's weights and train ALL FIVE EXPERTS, this would be an arbitrary task. The system would learn it instantly.