Best model so far - eval_loss: 0.0005 (Trained with Unsloth)

Best model so far - eval_loss: 0.0008 (Trained with Unsloth)

Best model so far - eval_loss: 0.0020 (Trained with Unsloth)

Best model so far - eval_loss: 0.0026 (Trained with Unsloth)

Initial model state (Trained with Unsloth)

initial commit