Open alexandersimoes opened 2 months ago
Fine-tuning results with both random sample and Ale's test set (in RAG only questions): | Model | Accuracy |
---|---|---|
TinyLlama 1epoch | 0% | |
TinyLlama 10 epoch | 0% | |
TinyLlama 50 epoch | 0% | |
Llama2 1epoch | 0% |
The main issue is the model learns the text around the numbers but it gets the numbers wrong. Actually, It changes the number every time is queried. Side effect, the tinyllama models lost their capabilities to answer other inputs.
Next steps:
Updates on my side: