Best model so far - eval_loss: 0.3902 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.3904 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.3912 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.3974 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.4046 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.4120 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.4189 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.4286 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.4361 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.4455 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.4574 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.4851 -------------------------------------------------------- (Trained with Unsloth)

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

initial commit