Update README.md

README.md

@@ -14,9 +14,17 @@ license: apache-2.0
 # t5-v1.1-base-dutch-uncased
 
 A [T5](https://ai.googleblog.com/2020/02/exploring-transfer-learning-with-t5.html) sequence to sequence model
-pre-trained from scratch on [cleaned Dutch 🇳🇱🇧🇪 mC4 ](https://huggingface.co/datasets/yhavinga/mc4_nl_cleaned).
+pre-trained from scratch on [cleaned Dutch 🇳🇱🇧🇪 mC4](https://huggingface.co/datasets/yhavinga/mc4_nl_cleaned).
 
 
+This **t5-v1.1** model has **247M** parameters.
+It was pre-trained on the dataset
+`mc4_nl_cleaned` config `full` for **2** epoch(s) and a duration of **5d5h**,
+with a sequence length of **1024**, batch size **64** and **1014525** total steps. 
+Pre-training evaluation loss and accuracy are **1,20** and **0,73**.
+After fine-tuning on 25K samples of Dutch CNN summarization, the Rouge1 score is **33.8**
+(note: this evaluation model was not saved).
+
 * Pre-trained T5 models need to be finetuned before they can be used for downstream tasks, therefore the inference widget on the right has been turned off.
 * For a demo of the Dutch CNN summarization models, head over to the Hugging Face Spaces for
 the **[Netherformer 📰](https://huggingface.co/spaces/flax-community/netherformer)** example application!
@@ -30,14 +38,6 @@ and configs, though it must be noted that this model (t5-v1.1-base-dutch-uncased
 ![model image](https://camo.githubusercontent.com/623b4dea0b653f2ad3f36c71ebfe749a677ac0a1/68747470733a2f2f6d69726f2e6d656469756d2e636f6d2f6d61782f343030362f312a44304a31674e51663876727255704b657944387750412e706e67)
 
 
-This **t5-v1.1** model has **247M** parameters.
-It was pre-trained on the dataset
-`mc4_nl_cleaned` config `full` for **2** epoch(s) and a duration of **5d5h**,
-with a sequence length of **1024**, batch size **64** and **1014525** total steps. 
-Pre-training evaluation loss and accuracy are **1,20** and **0,73**.
-After fine-tuning on 25K samples of Dutch CNN summarization, the Rouge1 score is **33.8**
-(note: this evaluation model was not saved).
-
 ## Tokenizer
 
 The model uses an uncased SentencePiece tokenizer configured with the `Nmt, NFKC, Replace multi-space to single-space, Lowercase` normalizers