Cycle 2: New best model with eval_loss 0.607321 (Trained with Unsloth)

Cycle 1: New best model with eval_loss 0.608078 (Trained with Unsloth)

Cycle 1: New best model with eval_loss 0.611332 (Trained with Unsloth)

Cycle 1: New best model with eval_loss 0.617373 (Trained with Unsloth)

Cycle 1: New best model with eval_loss 0.625179 (Trained with Unsloth)

Cycle 1: New best model with eval_loss 0.630358 (Trained with Unsloth)

Cycle 0: New best model with eval_loss 0.634197 (Trained with Unsloth)

Cycle 0: New best model with eval_loss 0.649671 (Trained with Unsloth)

Cycle 0: New best model with eval_loss 0.666352 (Trained with Unsloth)

Best model so far - eval_loss: 0.9340 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9456 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9681 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9099 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9101 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9216 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9279 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9333 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9615 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9696 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8451 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8467 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8488 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8528 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8571 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8618 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8658 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8714 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8794 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8906 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8909 -------------------------------------------------------- (Trained with Unsloth)

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

Best model so far - eval_loss: 0.9052 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9375 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8952 -------------------------------------------------------- (Trained with Unsloth)

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

Best model so far - eval_loss: 1.0512 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9230 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9230 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.0407 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.1201 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.0913 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.1313 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.1765 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.1666 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9471 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9476 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9508 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9566 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9638 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9647 -------------------------------------------------------- (Trained with Unsloth)