Best model so far - eval_loss: 0.5930 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.5998 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.6063 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.6101 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.6110 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.6145 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.6204 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.6297 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.6369 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.6472 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.6613 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.6736 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.6744 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.6796 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.6901 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7130 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7428 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7802 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8202 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8664 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9114 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9623 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.0393 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.1863 -------------------------------------------------------- (Trained with Unsloth)

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

initial commit