Best model so far - eval_loss: 0.1937 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.1966 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.1985 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.2126 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.2343 -------------------------------------------------------- (Trained with Unsloth)

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

initial commit