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

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

Best model so far - eval_loss: 1.1386 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.1498 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.3523 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.2211 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.2024 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.4001 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.2869 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.2999 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.5065 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.4191 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.4400 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.6213 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.5790 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.6841 -------------------------------------------------------- (Trained with Unsloth)

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

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

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