zlxi
/

bert-base-uncased-finetuned-swag

Multiple Choice

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

zlxi commited on Mar 4, 2023

Commit

1db7818

•

1 Parent(s): d805afb

update model card README.md

Files changed (1) hide show

README.md +5 -5

README.md CHANGED Viewed

@@ -16,8 +16,8 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6931
-- Accuracy: 0.4600
 ## Model description
@@ -48,9 +48,9 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 25   | 0.6931          | 0.4600   |
-| No log        | 2.0   | 50   | 0.6931          | 0.4600   |
-| No log        | 3.0   | 75   | 0.6931          | 0.4600   |
 ### Framework versions

 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.6935
+- Accuracy: 0.4100
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 25   | 0.6945          | 0.3800   |
+| No log        | 2.0   | 50   | 0.6936          | 0.3600   |
+| No log        | 3.0   | 75   | 0.6935          | 0.4100   |
 ### Framework versions