anirudh21
/

bert-base-uncased-finetuned-cola

Text Classification

generated_from_trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

anirudh21 commited on Jan 24, 2022

Commit

27dd929

•

1 Parent(s): db27d27

update model card README.md

Files changed (1) hide show

README.md +8 -8

README.md CHANGED Viewed

@@ -19,7 +19,7 @@ model-index:
     metrics:
     - name: Matthews Correlation
       type: matthews_correlation
-      value: 0.5859983483284835
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,8 +29,8 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the glue dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7877
-- Matthews Correlation: 0.5860
 ## Model description
@@ -61,11 +61,11 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
 |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
-| 0.4985        | 1.0   | 535  | 0.5282          | 0.5116               |
-| 0.2975        | 2.0   | 1070 | 0.5192          | 0.5575               |
-| 0.1953        | 3.0   | 1605 | 0.6840          | 0.5756               |
-| 0.1304        | 4.0   | 2140 | 0.7877          | 0.5860               |
-| 0.1048        | 5.0   | 2675 | 0.8585          | 0.5786               |
 ### Framework versions

     metrics:
     - name: Matthews Correlation
       type: matthews_correlation
+      value: 0.5796941781913538
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the glue dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.9664
+- Matthews Correlation: 0.5797
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
 |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
+| 0.5017        | 1.0   | 535  | 0.5252          | 0.4841               |
+| 0.2903        | 2.0   | 1070 | 0.5550          | 0.4967               |
+| 0.1839        | 3.0   | 1605 | 0.7295          | 0.5634               |
+| 0.1132        | 4.0   | 2140 | 0.7762          | 0.5702               |
+| 0.08          | 5.0   | 2675 | 0.9664          | 0.5797               |
 ### Framework versions