Update README.md

fixed a typo not leading to the training script.

README.md

@@ -38,7 +38,7 @@ After some tests with different tokenizers I decided to pick one of the oldest a
 * **99% performance:** Unexpectedly this model scored nearly 99% in comparison to [e5-base-sts-en-de](https://huggingface.co/danielheinz/e5-base-sts-en-de) during the [GermanGovServiceRetrieval](https://huggingface.co/datasets/mteb/GermanGovServiceRetrieval)-Task in MTEB by taking only a 80th of the time (40.3 seconds vs. 0.49).
 * **Matryoshka:** This model was trained with a [Matryoshka loss](https://huggingface.co/blog/matryoshka), allowing you to truncate the embeddings for faster retrieval at minimal performance costs.
 * **Evaluations:** See [Evaluations](#evaluation) for details on performance on German MTEB, special [GermanGovService retrieval](https://huggingface.co/datasets/mteb/GermanGovServiceRetrieval), embedding speed, and Matryoshka dimensionality truncation.
-* **Training Script:** See [base_train.py](base_train.py) for the training script used to train this model from scratch (be warned - it is wildly commented).
+* **Training Script:** See [train_base.py](train_base.py) for the training script used to train this model from scratch (be warned - it is wildly commented).
 
 ## Model Details