Best model so far - eval_loss: 0.8506 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8654 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8816 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8978 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9129 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9332 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9499 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9640 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9899 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9926 -------------------------------------------------------- (Trained with Unsloth)

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

initial commit