End of training

README.md

@@ -16,9 +16,9 @@ model-index:
     dataset:
       name: glue
       type: glue
-      config: rte
+      config: cola
       split: validation
-      args: rte
+      args: cola
     metrics:
     - name: Accuracy
       type: accuracy
@@ -32,7 +32,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the glue dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.7574
+- Loss: 4.3499
 - Accuracy: 0.0
 
 ## Model description
@@ -65,14 +65,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.535         | 0.32  | 25   | 0.5791          | 0.7076   |
-| 0.5089        | 0.64  | 50   | 0.5602          | 0.7401   |
-| 0.4866        | 0.96  | 75   | 0.5481          | 0.7545   |
-| 0.4275        | 1.28  | 100  | 0.6181          | 0.7690   |
-| 0.4487        | 1.6   | 125  | 0.5974          | 0.7726   |
-| 0.477         | 1.92  | 150  | 0.6099          | 0.7509   |
-| 0.3414        | 2.24  | 175  | 0.6009          | 0.7798   |
-| 0.2874        | 2.56  | 200  | 0.6210          | 0.7906   |
+| 0.387         | 0.09  | 25   | 0.5450          | 0.8293   |
+| 0.2475        | 0.19  | 50   | 0.5868          | 0.8188   |
+| 0.3632        | 0.28  | 75   | 0.4910          | 0.8178   |
+| 0.3274        | 0.37  | 100  | 0.4657          | 0.8169   |
+| 0.3411        | 0.47  | 125  | 0.5840          | 0.8188   |
+| 0.3016        | 0.56  | 150  | 0.5476          | 0.8169   |
+| 0.2658        | 0.65  | 175  | 0.5822          | 0.8130   |
+| 0.3412        | 0.75  | 200  | 0.5156          | 0.8188   |
+| 0.2783        | 0.84  | 225  | 0.4850          | 0.8245   |
+| 0.3596        | 0.93  | 250  | 0.5406          | 0.8284   |
 
 
 ### Framework versions