Update README.md

README.md

@@ -13,15 +13,15 @@ should probably proofread and complete it, then remove this comment. -->
 
 # sentiment-guesser
 
-This model is a fine-tuned version of [microsoft/MiniLM-L12-H384-uncased](https://huggingface.co/microsoft/MiniLM-L12-H384-uncased) on an unknown dataset.
+This model is a fine-tuned version of [microsoft/MiniLM-L12-H384-uncased](https://huggingface.co/microsoft/MiniLM-L12-H384-uncased) on the [imdb dataset](https://huggingface.co/datasets/imdb).
 
-## Model description
+See the [colab here](https://huggingface.co/eddyjin/sentiment-guesser/blob/main/Train_a_simple_sentiment_classifier_on_Hugging_Face.ipynb).
 
-More information needed
+This is part of [www.huggingfacetutorial.com](https://www.huggingfacetutorial.com), where you can find easy to follow tutorials on AI modeling on Hugging Face.
 
 ## Intended uses & limitations
 
-More information needed
+This model is not very good. It is only intended to be a simple example of how to fine-tune.
 
 ## Training and evaluation data
 
@@ -29,6 +29,8 @@ More information needed
 
 ## Training procedure
 
+Training was done on a sampled set of 1,000 examples. The eval set is also 1,000 examples. Only 1 epoch was completed to make this example easy to run on a CPU powered colab.
+
 ### Training hyperparameters
 
 The following hyperparameters were used during training: