HansOMEL
/

QA-bert-base-chinese-Hw1

Question Answering

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Community

HansOMEL commited on Oct 20, 2023

Commit

a823171

•

1 Parent(s): c9a4d5a

End of training

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [bert-base-chinese](https://huggingface.co/bert-base-chinese) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3820
 ## Model description
@@ -47,9 +47,9 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step  | Validation Loss |
 |:-------------:|:-----:|:-----:|:---------------:|
-| 0.6399        | 1.0   | 13821 | 1.3820          |
-| 0.4027        | 2.0   | 27642 | 1.3894          |
-| 0.2129        | 3.0   | 41463 | 1.5486          |
 ### Framework versions

 This model is a fine-tuned version of [bert-base-chinese](https://huggingface.co/bert-base-chinese) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 1.2316
 ## Model description
 | Training Loss | Epoch | Step  | Validation Loss |
 |:-------------:|:-----:|:-----:|:---------------:|
+| 0.979         | 1.0   | 13821 | 0.9780          |
+| 0.4313        | 2.0   | 27642 | 1.0361          |
+| 0.3275        | 3.0   | 41463 | 1.2316          |
 ### Framework versions