Update README.md

README.md

@@ -3,6 +3,8 @@ tags:
 - image-to-text
 - image-captioning
 license: apache-2.0
+metrics:
+- rouge
 widget:
 - src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/savanna.jpg
   example_title: Savanna
@@ -12,27 +14,43 @@ widget:
   example_title: Airport
 base_model: 
 - google/vit-base-patch16-224-in21k
+
+model-index:
+- name: mozilla/distilvit
+  results:
+  - task:
+      type: image-to-text
+      name: Image To Text
+    metrics:
+    - name: ROUGE-1
+      type: rouge
+      value: 43.006
+      verified: true
+    - name: ROUGE-2
+      type: rouge
+      value: 16.9939
+      verified: true
+    - name: ROUGE-L
+      type: rouge
+      value: 38.8923
+      verified: true
+    - name: ROUGE-LSUM
+      type: rouge
+      value: 38.8877
+      verified: true
+    - name: loss
+      type: loss
+      value: 0.19939416646957397
+    - name: gen_len
+      type: gen_len
+      value: 11.327256736227712
+      verified: true
 ---
 
 This model is a work in progress.  
 
 You can find the code used to create the model here: https://github.com/mozilla/distilvit
-
-Results after after 3 epochs (and ~45 hours of training)
-
-- eval_loss: 0.19939416646957397
-- eval_rouge1: 43.006
-- eval_rouge2: 16.9939
-- eval_rougeL: 38.8923
-- eval_rougeLsum: 38.8877
-- eval_gen_len: 11.327256736227712
-- eval_runtime: 1816.5255
-- eval_samples_per_second: 13.77
-- eval_steps_per_second': 1.721                                     
-- train_runtime: 46263.3695
-- train_samples_per_second: 38.373
-- train_steps_per_second: 4.797
-- train_loss: 0.05974134062104816
+