Raphaelg9
/

distilbert-base-uncased-finetuned-squad

Question Answering

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

Raphaelg9 commited on Nov 30, 2021

Commit

82797a3

•

1 Parent(s): 0751c18

update model card README.md

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -16,7 +16,7 @@ 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 squad_v2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.9378
 ## Model description
@@ -47,9 +47,9 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.7344        | 1.0   | 661  | 1.8938          |
-| 1.4805        | 2.0   | 1322 | 2.1169          |
-| 1.1922        | 3.0   | 1983 | 1.9378          |
 ### Framework versions

 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the squad_v2 dataset.
 It achieves the following results on the evaluation set:
+- Loss: 2.1323
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
+| 2.8535        | 1.0   | 661  | 2.0684          |
+| 1.5385        | 2.0   | 1322 | 2.0954          |
+| 1.2312        | 3.0   | 1983 | 2.1323          |
 ### Framework versions