File size: 308 Bytes
aa4f91d 6ee341c |
1 2 3 4 5 6 7 8 9 |
---
license: llama2
---
Trained using TRL, it didn't fit properly on my 3090 without significantly dropping batch size and applying 4-bit quantization.
It didn't exactly converge.
![training_run.png](https://cdn-uploads.huggingface.co/production/uploads/64075c834dc5f2846c96bc98/b-Tn5IDcRubZp_AyfLNg7.png) |