timopixel
/

distilbert-base-uncased-finetuned-squad

Question Answering

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

timopixel commited on Jun 7, 2023

Commit

134c801

•

1 Parent(s): 2f219b5

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: 2.6484
 ## Model description
@@ -47,9 +47,9 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 86   | 2.7033          |
-| No log        | 2.0   | 172  | 2.4321          |
-| No log        | 3.0   | 258  | 2.6484          |
 ### 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: 3.7286
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 21   | 3.7602          |
+| No log        | 2.0   | 42   | 3.7330          |
+| No log        | 3.0   | 63   | 3.7286          |
 ### Framework versions