Best model so far - eval_loss: 7.3754 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 7.4787 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 7.7704 -------------------------------------------------------- (Trained with Unsloth)

Initial model state ------------------------------------------------------------------------ (Trained with Unsloth)

initial commit