Best model so far - eval_loss: 1.0254 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.0344 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.0355 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.0387 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.0397 -------------------------------------------------------- (Trained with Unsloth)

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

Best model so far - eval_loss: 1.6073 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.6388 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.7051 -------------------------------------------------------- (Trained with Unsloth)

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

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

initial commit