bisoye
/

token_classification

Token Classification

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

bisoye commited on Sep 9, 2024

Commit

7dfdb58

·

verified ·

1 Parent(s): 277deb9

End of training

Files changed (1) hide show

README.md +4 -4

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 [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2154
-- Wer: 0.0522
 ## Model description
@@ -50,8 +50,8 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 0.2071        | 1.0   | 76   | 0.2230          | 0.0566 |
-| 0.0539        | 2.0   | 152  | 0.2154          | 0.0522 |
 ### Framework versions

 This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.2064
+- Wer: 0.0558
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
+| 0.2169        | 1.0   | 76   | 0.2291          | 0.0531 |
+| 0.0588        | 2.0   | 152  | 0.2064          | 0.0558 |
 ### Framework versions