sofa566
/

my_awesome_qa_model

Question Answering

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

sofa566 commited on May 29, 2023

Commit

141e4ac

•

1 Parent(s): f1a7a82

update model card README.md

Files changed (1) hide show

README.md +5 -5

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: 1.5592
 ## Model description
@@ -47,14 +47,14 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 250  | 2.3395          |
-| 2.74          | 2.0   | 500  | 1.6269          |
-| 2.74          | 3.0   | 750  | 1.5592          |
 ### Framework versions
-- Transformers 4.29.1
 - Pytorch 1.12.1
 - Datasets 2.11.0
 - Tokenizers 0.11.0

 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: 1.6306
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 250  | 2.0567          |
+| 2.5851        | 2.0   | 500  | 1.6653          |
+| 2.5851        | 3.0   | 750  | 1.6306          |
 ### Framework versions
+- Transformers 4.29.2
 - Pytorch 1.12.1
 - Datasets 2.11.0
 - Tokenizers 0.11.0