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 May 16, 2023

Commit

3498879

•

1 Parent(s): 0863713

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: 3.3310
 ## Model description
@@ -35,7 +35,7 @@ More information needed
 ### Training hyperparameters
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
 - train_batch_size: 12
 - eval_batch_size: 12
 - seed: 42
@@ -47,9 +47,9 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 44   | 3.9979          |
-| No log        | 2.0   | 88   | 3.4500          |
-| No log        | 3.0   | 132  | 3.3310          |
 ### 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: 5.6633
 ## Model description
 ### Training hyperparameters
 The following hyperparameters were used during training:
+- learning_rate: 2e-06
 - train_batch_size: 12
 - eval_batch_size: 12
 - seed: 42
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 44   | 5.7861          |
+| No log        | 2.0   | 88   | 5.6961          |
+| No log        | 3.0   | 132  | 5.6633          |
 ### Framework versions