Update README.md

README.md

@@ -45,26 +45,36 @@ library_name: transformers
 
 # distilgpt2-HC3
 
+
+> what happens if you train a smaller model on a dataset of chatGPT responses?
+
+This happens.
+
+## Model description
+
 This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the "chatgpt answers" column of the `Hello-SimpleAI/HC3` dataset.
 
 It achieves the following results on the evaluation set:
 - Loss: 1.9983
 - Accuracy: 0.5441
 
-## Model description
-
-More information needed
 
 ## Intended uses & limitations
 
-More information needed
+Despite how it sounds, this model only has 80m parameters and will likely not be factually accurate most of the time.
 
 ## Training and evaluation data
 
-More information needed
+Modifications made w.r.t. original dataset:
 
+- drop all rows that did not have a chatGPT answer 
+- if a row (_i.e. ELI5 question, etc_) had more than one response (_from chatGPT_), randomly choose one of the responses as the answer to the question
+- the "question" and chatGPT answer were combined into a single string for that row as follows: `QUESTION_TEXT <answer> CHATGPT_ANSWER_TEXT <end_answer>`
+  - `<answer>` and `<end_answer>` serve as added tokens to help the model learn "turns" in the conversation
+ 
 ## Training procedure
 
+
 ### Training hyperparameters
 
 The following hyperparameters were used during training: