Update README.md

README.md

@@ -1,11 +1,14 @@
 ---
 license: mit
-tags:
-- generated_from_keras_callback
 base_model: gpt2
 model-index:
 - name: gpt2-fantasy
   results: []
+language:
+- en
+metrics:
+- accuracy
+library_name: transformers
 ---
 
 <!-- This model card has been generated automatically according to the information Keras had access to. You should
@@ -13,29 +16,25 @@ probably proofread and complete it, then remove this comment. -->
 
 # gpt2-fantasy
 
-This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
-It achieves the following results on the evaluation set:
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on IMDB fantasy synopsis dataset.
 
 
 ## Model description
 
-More information needed
+This model was fine-tuned with intention of generating short fantasy stories based on given keywords. 
 
-## Intended uses & limitations
+## Training data
 
-More information needed
+Training data was parsed from IMDB website and consists of keywords-synopsis pairs. Method of encoding data was inspired from [this repo](https://github.com/minimaxir/gpt-2-keyword-generation)
 
-## Training and evaluation data
-
-More information needed
-
-## Training procedure
 
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: None
-- training_precision: float32
+- optimizer: Adam
+- dropout: 0.2
+- learning schedule: exponential decay 
+- epochs: 4
 
 ### Training results
 
@@ -45,4 +44,4 @@ The following hyperparameters were used during training:
 
 - Transformers 4.29.2
 - TensorFlow 2.12.0
-- Tokenizers 0.13.3
+- Tokenizers 0.13.3