StatsGary
/

questionanswering-distilbert-squad

Question Answering

Generated from Trainer

Model card Files Files and versions

StatsGary commited on Jan 26, 2023

Commit

b7aa010

·

1 Parent(s): 76f091f

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: 1.6157
 ## Model description
@@ -47,9 +47,9 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 250  | 2.0442          |
-| 2.5789        | 2.0   | 500  | 1.6466          |
-| 2.5789        | 3.0   | 750  | 1.6157          |
 ### 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: 1.6344
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 250  | 2.3866          |
+| 2.774         | 2.0   | 500  | 1.6956          |
+| 2.774         | 3.0   | 750  | 1.6344          |
 ### Framework versions