Update README.md

README.md

@@ -16,18 +16,25 @@ widget:
 
 # t5-base-dutch-demo
 
-> This is part of the
-[Flax/Jax Community Week](https://discuss.huggingface.co/t/pretrain-t5-from-scratch-in-dutch/8109), organized by [HuggingFace](https://huggingface.co/) and TPU usage sponsored by Google.
-Want to give it a try? Then head over to the Hugging Face Spaces for the [Netherformer](https://huggingface.co/spaces/flax-community/netherformer) example application.
+
+Created by [Yeb Havinga](https://www.linkedin.com/in/yeb-havinga-86530825/) & [Dat Nguyen](https://www.linkedin.com/in/dat-nguyen-49a641138/) during the [Hugging Face community week](https://discuss.huggingface.co/t/open-to-the-community-community-week-using-jax-flax-for-nlp-cv/7104)
 
 This model is based on [t5-base-dutch](https://huggingface.co/flax-community/t5-base-dutch) 
 and fine-tuned to create summaries of news articles.
 
+For a demo of the model, head over to the Hugging Face Spaces for the [Netherformer](https://huggingface.co/spaces/flax-community/netherformer) example application!
+
 ## Dataset
 
 `t5-base-dutch-demo` is fine-tuned on three mixed news sources:
 
- 1. CNN DM translated to Dutch with MarianMT.
- 2. XSUM translated to Dutch with MarianMt.
+ 1. **CNN DailyMail** translated to Dutch with MarianMT.
+ 2. **XSUM** translated to Dutch with MarianMt.
  3. News article summaries distilled from the nu.nl website.
 
+## Training
+
+The pre-trained model [t5-base-dutch](https://huggingface.co/flax-community/t5-base-dutch) was fine-tuned with a constant learning rate of 0.0005, a batch size of 64, for 10.000 steps. 
+The performance of this model can be improved with longer training. Unfortunately due to a bug, an earlier training script would not save intermediate checkpoints, and had been started for 6 epochs, and would finish past the availability of the TPU-VM. Since there was limited time left, the fine-tuning was restarted without evaluation and for only half an epoch (10.000 steps).
+
+