End of training

README.md

@@ -18,7 +18,7 @@ model-index:
     metrics:
     - name: Matthews Correlation
       type: matthews_correlation
-      value: 0.5912435391119252
+      value: 0.0
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -28,8 +28,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [allenai/longformer-base-4096](https://huggingface.co/allenai/longformer-base-4096) on the glue dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5643
-- Matthews Correlation: 0.5912
+- Loss: 0.7005
+- Matthews Correlation: 0.0
 
 ## Model description
 
@@ -60,11 +60,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
 |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
-| No log        | 1.0   | 268  | 0.4890          | 0.5080               |
-| 0.4099        | 2.0   | 536  | 0.4874          | 0.5312               |
-| 0.4099        | 3.0   | 804  | 0.5917          | 0.5733               |
-| 0.197         | 4.0   | 1072 | 0.5643          | 0.5912               |
-| 0.197         | 5.0   | 1340 | 0.6762          | 0.5863               |
+| No log        | 1.0   | 268  | 0.7005          | 0.0                  |
+| 0.6995        | 2.0   | 536  | 0.6960          | -0.0043              |
+| 0.6995        | 3.0   | 804  | 0.6976          | -0.0057              |
+| 0.6962        | 4.0   | 1072 | 0.6983          | -0.0123              |
+| 0.6962        | 5.0   | 1340 | 0.6977          | -0.0529              |
 
 
 ### Framework versions