Best model so far - eval_loss: 0.9455 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9514 -------------------------------------------------------- (Trained with Unsloth)

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

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

Best model so far - eval_loss: 0.9703 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9752 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9837 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9915 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9915 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9932 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9977 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.0055 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.0179 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.0325 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.0517 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.0747 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.0952 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.1228 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.1597 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.2142 -------------------------------------------------------- (Trained with Unsloth)

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

initial commit