Initial model upload

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
-license: apache-2.0
-base_model: bert-base-uncased
+license: mit
+base_model: xlm-roberta-base
 tags:
 - generated_from_trainer
 datasets:
@@ -10,7 +10,7 @@ metrics:
 - accuracy
 - f1
 model-index:
-- name: bert-multirc
+- name: xlmroberta-multirc
   results:
   - task:
       name: Text Classification
@@ -24,22 +24,22 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.574463696369637
+      value: 0.5719884488448845
     - name: F1
       type: f1
-      value: 0.5000357077611722
+      value: 0.4162508774824471
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# bert-multirc
+# xlmroberta-multirc
 
-This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the super_glue dataset.
+This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the super_glue dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6812
-- Accuracy: 0.5745
-- F1: 0.5000
+- Loss: 0.6823
+- Accuracy: 0.5720
+- F1: 0.4163
 
 ## Model description
 
@@ -71,7 +71,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 0.6862        | 1.0   | 1703 | 0.6812          | 0.5745   | 0.5000 |
+| 0.6873        | 1.0   | 1703 | 0.6823          | 0.5720   | 0.4163 |
 
 
 ### Framework versions