jhoonk
/

bert-base-uncased-finetuned-swag

Multiple Choice

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

jhoonk commited on May 3, 2022

Commit

d580cb5

•

1 Parent(s): 06151df

update model card README.md

Files changed (1) hide show

README.md +5 -5

README.md CHANGED Viewed

@@ -18,8 +18,8 @@ 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 swag dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0032
-- Accuracy: 0.7914
 ## Model description
@@ -50,9 +50,9 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step  | Validation Loss | Accuracy |
 |:-------------:|:-----:|:-----:|:---------------:|:--------:|
-| 0.7546        | 1.0   | 4597  | 0.5984          | 0.7654   |
-| 0.3706        | 2.0   | 9194  | 0.6242          | 0.7833   |
-| 0.1351        | 3.0   | 13791 | 1.0032          | 0.7914   |
 ### Framework versions

 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the swag dataset.
 It achieves the following results on the evaluation set:
+- Loss: 1.0456
+- Accuracy: 0.7888
 ## Model description
 | Training Loss | Epoch | Step  | Validation Loss | Accuracy |
 |:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.7475        | 1.0   | 4597  | 0.6037          | 0.7690   |
+| 0.373         | 2.0   | 9194  | 0.6472          | 0.7798   |
+| 0.1337        | 3.0   | 13791 | 1.0456          | 0.7888   |
 ### Framework versions