Best model so far - eval_loss: 0.7820 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7823 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7839 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7877 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7941 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8028 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8138 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8270 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8415 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8585 -------------------------------------------------------- (Trained with Unsloth)

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

initial commit