Best model so far - eval_loss: 0.9088 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9150 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9178 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9190 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9273 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9301 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9381 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9502 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9661 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9811 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.0010 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.0192 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.0573 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.0932 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.1570 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.0971 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.1805 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.1817 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.1955 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.1133 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.1774 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.1141 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.1951 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.1716 -------------------------------------------------------- (Trained with Unsloth)

initial commit