------------------EAT MY SHORTS -------------------------------------------------------- (Trained with Unsloth)

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

Best model so far - eval_loss: 4.9478 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 4.9490 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 4.9555 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 4.9634 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 4.9729 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 4.9842 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 5.0146 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 5.0447 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 5.0772 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 5.1489 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 5.2867 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 5.5162 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 5.7217 -------------------------------------------------------- (Trained with Unsloth)

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

Best model so far - eval_loss: 4.9288 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 4.9289 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 4.9305 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 4.9335 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 4.9381 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 4.9391 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 4.9413 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 4.9519 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 4.9565 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 4.9697 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 4.9848 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 5.0063 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 5.0445 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 5.0939 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 5.1621 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 5.3188 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 5.5779 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 5.8124 -------------------------------------------------------- (Trained with Unsloth)

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

Best model so far - eval_loss: 1.5604 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.7283 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.9866 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 2.3438 -------------------------------------------------------- (Trained with Unsloth)

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

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

Best model so far - eval_loss: 1.2825 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.2937 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.3059 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.3304 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.3611 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.4119 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.4783 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.5817 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.7317 -------------------------------------------------------- (Trained with Unsloth)