anirudh21
/

distilbert-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 12, 2022

Commit

677e73d

•

1 Parent(s): 9d689b2

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: 0.5546789239242798
 ---
 <!-- 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 [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the glue dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8421
-- Matthews Correlation: 0.5547
 ## Model description
@@ -61,11 +61,11 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
 |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
-| 0.5243        | 1.0   | 535  | 0.5428          | 0.4201               |
-| 0.3497        | 2.0   | 1070 | 0.5010          | 0.5239               |
-| 0.2388        | 3.0   | 1605 | 0.6261          | 0.5259               |
-| 0.1714        | 4.0   | 2140 | 0.7664          | 0.5461               |
-| 0.1269        | 5.0   | 2675 | 0.8421          | 0.5547               |
 ### Framework versions

     metrics:
     - name: Matthews Correlation
       type: matthews_correlation
+      value: 0.5224154837835395
 ---
 <!-- 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 [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the glue dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.8623
+- Matthews Correlation: 0.5224
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
 |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
+| 0.5278        | 1.0   | 535  | 0.5223          | 0.4007               |
+| 0.3515        | 2.0   | 1070 | 0.5150          | 0.4993               |
+| 0.2391        | 3.0   | 1605 | 0.6471          | 0.5103               |
+| 0.1841        | 4.0   | 2140 | 0.7640          | 0.5153               |
+| 0.1312        | 5.0   | 2675 | 0.8623          | 0.5224               |
 ### Framework versions