Best model so far - eval_loss: 0.7344 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7507 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7758 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8030 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8093 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8445 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8516 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8541 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8878 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9044 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9649 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9883 -------------------------------------------------------- (Trained with Unsloth)

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

initial commit