Initial model upload

README.md

@@ -1,22 +1,45 @@
 ---
 library_name: transformers
-license: mit
-base_model: roberta-base
+license: apache-2.0
+base_model: bert-base-multilingual-uncased
 tags:
 - generated_from_trainer
+datasets:
+- super_glue
+metrics:
+- accuracy
+- f1
 model-index:
-- name: roberta-sst2
-  results: []
+- name: mbert-multirc
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: super_glue
+      type: super_glue
+      config: multirc
+      split: validation
+      args: multirc
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.5759075907590759
+    - name: F1
+      type: f1
+      value: 0.5048127206005825
 ---
 
 <!-- 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. -->
 
-# roberta-sst2
+# mbert-multirc
 
-This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
+This model is a fine-tuned version of [bert-base-multilingual-uncased](https://huggingface.co/bert-base-multilingual-uncased) on the super_glue dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2146
+- Loss: 0.6812
+- Accuracy: 0.5759
+- F1: 0.5048
 
 ## Model description
 
@@ -46,9 +69,9 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 0.1975        | 1.0   | 4210 | 0.2146          |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
+| 0.6862        | 1.0   | 1703 | 0.6812          | 0.5759   | 0.5048 |
 
 
 ### Framework versions