vkmr
/

distilbert-base-uncased-finetuned-squad

Question Answering

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

vkmr commited on Mar 1, 2022

Commit

227ea01

•

1 Parent(s): 8d6e963

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: 1.4456
 ## Model description
@@ -47,9 +47,9 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step  | Validation Loss |
 |:-------------:|:-----:|:-----:|:---------------:|
-| 1.2251        | 1.0   | 8235  | 1.2660          |
-| 0.947         | 2.0   | 16470 | 1.2721          |
-| 0.7664        | 3.0   | 24705 | 1.4456          |
 ### 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: 1.3954
 ## Model description
 | Training Loss | Epoch | Step  | Validation Loss |
 |:-------------:|:-----:|:-----:|:---------------:|
+| 1.1994        | 1.0   | 8235  | 1.2608          |
+| 0.9271        | 2.0   | 16470 | 1.2250          |
+| 0.742         | 3.0   | 24705 | 1.3954          |
 ### Framework versions