Best model so far - eval_loss: 0.7006 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7008 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7014 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7024 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7042 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7070 -------------------------------------------------------- (Trained with Unsloth)

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

Best model so far - eval_loss: 0.7149 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7186 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7226 -------------------------------------------------------- (Trained with Unsloth)

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

Best model so far - eval_loss: 0.7331 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7365 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7415 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7455 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7464 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7493 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7538 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7610 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7692 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7793 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7922 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8063 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8250 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8468 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.8867 -------------------------------------------------------- (Trained with Unsloth)

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

initial commit