Adrian
/

distilbert-base-uncased-finetuned-squad

Question Answering

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

Adrian commited on Apr 16, 2022

Commit

969ac09

•

1 Parent(s): 17609d8

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 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1562
 ## Model description
@@ -47,9 +47,9 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step  | Validation Loss |
 |:-------------:|:-----:|:-----:|:---------------:|
-| 1.2227        | 1.0   | 5533  | 1.1613          |
-| 0.9581        | 2.0   | 11066 | 1.1254          |
-| 0.7479        | 3.0   | 16599 | 1.1562          |
 ### Framework versions

 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the squad dataset.
 It achieves the following results on the evaluation set:
+- Loss: 1.1484
 ## Model description
 | Training Loss | Epoch | Step  | Validation Loss |
 |:-------------:|:-----:|:-----:|:---------------:|
+| 1.2114        | 1.0   | 5533  | 1.1509          |
+| 0.9537        | 2.0   | 11066 | 1.1229          |
+| 0.7459        | 3.0   | 16599 | 1.1484          |
 ### Framework versions