Best model so far - eval_loss: 0.7109 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7110 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7112 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7117 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7121 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7152 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7159 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7181 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7253 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7276 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7339 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7379 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7469 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7527 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7568 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7656 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7763 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7845 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7917 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7955 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8019 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8101 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8113 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8147 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8216 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8244 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8360 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8519 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8609 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8690 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8887 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9102 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9255 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9390 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9766 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9969 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.0012 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.0135 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.0382 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.0670 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.1021 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.1494 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.2063 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.2920 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.3625 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.4483 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.6098 -------------------------------------------------------- (Trained with Unsloth)

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

initial commit