Best model so far - eval_loss: 2.2126 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 2.2317 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 2.2369 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 2.2570 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 2.2703 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 2.2814 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 2.3035 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 2.3340 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 2.3626 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 2.3903 -------------------------------------------------------- (Trained with Unsloth)

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

initial commit