Best model so far - eval_loss: 1.8604 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.8608 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.8619 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.8638 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.8661 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.8709 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.8735 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.8776 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.8803 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.8886 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.8937 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.8978 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.9020 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.9036 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.9039 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.9051 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.9070 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.9110 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.9162 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.9239 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.9328 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.9406 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.9506 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.9664 -------------------------------------------------------- (Trained with Unsloth)

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

initial commit