update model card README.md

README.md

@@ -3,10 +3,25 @@ license: mit
 tags:
 - generated_from_trainer
 datasets:
-- short-jokes
+- Fraser/short-jokes
+metrics:
+- accuracy
 model-index:
 - name: gpt2-jokes
-  results: []
+  results:
+  - task:
+      name: Causal Language Modeling
+      type: text-generation
+    dataset:
+      name: Fraser/short-jokes
+      type: Fraser/short-jokes
+      config: default
+      split: train[:5%]
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8760281609284458
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -14,7 +29,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # gpt2-jokes
 
-This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the short-jokes dataset.
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the Fraser/short-jokes dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6851
+- Accuracy: 0.8760
 
 ## Model description