V3RX2000
/

distilbert-base-uncased-finetuned-squad

Question Answering

generated_from_trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

V3RX2000 commited on Oct 12, 2021

Commit

599d7a4

•

1 Parent(s): e978d23

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: 1.1600
 ## Model description
@@ -47,9 +47,9 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step  | Validation Loss |
 |:-------------:|:-----:|:-----:|:---------------:|
-| 1.2269        | 1.0   | 5533  | 1.1558          |
-| 0.9533        | 2.0   | 11066 | 1.1166          |
-| 0.7673        | 3.0   | 16599 | 1.1600          |
 ### 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: 1.1580
 ## Model description
 | Training Loss | Epoch | Step  | Validation Loss |
 |:-------------:|:-----:|:-----:|:---------------:|
+| 1.2246        | 1.0   | 5533  | 1.1484          |
+| 0.9433        | 2.0   | 11066 | 1.1294          |
+| 0.7625        | 3.0   | 16599 | 1.1580          |
 ### Framework versions