Fixed model card

README.md

@@ -1,25 +1,27 @@
 ---
+language:
+  - el
 tags:
-- generated_from_trainer
+  - text
+  - language-modeling
 datasets:
-- dataset/wiki_oscar_combined_normalized_uncased
+  - dataset/wiki_oscar_combined_normalized_uncased
 metrics:
-- accuracy
+  - accuracy
 model-index:
-- name: greek-longformer-base-4096-uncased
-  results:
-  - task:
-      name: Masked Language Modeling
-      type: fill-mask
-    dataset:
-      name: dataset/wiki_oscar_combined_normalized_uncased
-      type: dataset/wiki_oscar_combined_normalized_uncased
-      config: null
-      split: None
-    metrics:
-    - name: Accuracy
-      type: accuracy
-      value: 0.7765486725663717
+  - name: greek-longformer-base-4096-uncased
+    results:
+      - task:
+          name: Masked Language Modeling
+          type: fill-mask
+        dataset:
+          name: dataset/wiki_oscar_combined_normalized_uncased
+          type: dataset/wiki_oscar_combined_normalized_uncased
+          split: None
+        metrics:
+          - name: Accuracy
+            type: accuracy
+            value: 0.7765486725663717
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -27,8 +29,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # greek-longformer-base-4096-uncased
 
-This model is a fine-tuned version of [](https://huggingface.co/) on the dataset/wiki_oscar_combined_normalized_uncased dataset.
+This model is a Longformer model version based on [allenai/longformer-base-4096](https://huggingface.co/allenai/longformer-base-4096) trained on the dataset/wiki_oscar_combined_normalized_uncased dataset from scratch.
 It achieves the following results on the evaluation set:
+
 - Loss: 1.1080
 - Accuracy: 0.7765
 
@@ -49,6 +52,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
+
 - learning_rate: 5e-05
 - train_batch_size: 8
 - eval_batch_size: 8
@@ -62,8 +66,6 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-
-
 ### Framework versions
 
 - Transformers 4.28.0.dev0