princebansal42
/

distilbert-base-uncased-finetuned-squad

Question Answering

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

princebansal42 commited on Dec 19, 2021

Commit

f256390

•

1 Parent(s): a3344e6

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_v2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.9209
 ## Model description
@@ -47,9 +47,9 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.705         | 1.0   | 824  | 1.8465          |
-| 1.269         | 2.0   | 1648 | 1.8994          |
-| 1.0972        | 3.0   | 2472 | 1.9209          |
 ### Framework versions

 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the squad_v2 dataset.
 It achieves the following results on the evaluation set:
+- Loss: 2.6623
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
+| 1.3993        | 1.0   | 2051 | 1.8058          |
+| 1.0467        | 2.0   | 4102 | 1.9564          |
+| 0.8304        | 3.0   | 6153 | 2.6623          |
 ### Framework versions