Best model so far - eval_loss: 0.9692 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9746 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9799 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9813 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9275 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9278 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9324 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9412 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9432 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9479 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9499 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9521 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9535 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9184 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9202 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9257 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9354 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9411 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.9475 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7342 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7371 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7432 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7474 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7617 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.7707 -------------------------------------------------------- (Trained with Unsloth)

initial commit