Best model so far - eval_loss: 0.9577 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9580 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9582 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9584 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9591 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9599 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9625 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9635 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9659 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9681 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9708 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9722 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9744 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9751 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9755 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9756 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9760 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9784 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9835 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9885 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9952 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.0020 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.0050 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.0089 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.0160 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.0190 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.0298 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.0314 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.0356 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.0429 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.0472 -------------------------------------------------------- (Trained with Unsloth)

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

Best model so far - eval_loss: 0.9756 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9768 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9793 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9807 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9819 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9833 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9841 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9850 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9897 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9952 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.0018 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.0057 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.0089 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.0165 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.0177 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.0223 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.0254 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.0344 -------------------------------------------------------- (Trained with Unsloth)