Bugsec
/

fine_tuned_deberta

Text Classification

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Community

Bugsec commited on Apr 10

Commit

ec9aef6

•

1 Parent(s): 51865f0

End of training

Files changed (1) hide show

README.md +12 -11

README.md CHANGED Viewed

@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2193
-- Accuracy: 0.9437
-- F1: 0.9398
-- Precision: 0.9921
-- Recall: 0.8929
 ## Model description
@@ -52,18 +52,19 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 100
-- num_epochs: 5
 - mixed_precision_training: Native AMP
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
-| 0.7008        | 0.96  | 17   | 0.6755          | 0.5704   | 0.2375 | 0.95      | 0.1357 |
-| 0.578         | 1.97  | 35   | 0.5885          | 0.6866   | 0.5822 | 0.8493    | 0.4429 |
-| 0.4858        | 2.99  | 53   | 0.4109          | 0.8239   | 0.8344 | 0.7778    | 0.9    |
-| 0.2615        | 4.0   | 71   | 0.2202          | 0.9401   | 0.9373 | 0.9695    | 0.9071 |
-| 0.1685        | 4.79  | 85   | 0.2193          | 0.9437   | 0.9398 | 0.9921    | 0.8929 |
 ### Framework versions

 This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.2283
+- Accuracy: 0.9331
+- F1: 0.9272
+- Precision: 1.0
+- Recall: 0.8643
 ## Model description
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 100
+- num_epochs: 10
 - mixed_precision_training: Native AMP
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| 0.7017        | 0.96  | 17   | 0.6835          | 0.5352   | 0.1081 | 1.0       | 0.0571 |
+| 0.6085        | 1.97  | 35   | 0.5872          | 0.6866   | 0.5822 | 0.8493    | 0.4429 |
+| 0.518         | 2.99  | 53   | 0.4436          | 0.7958   | 0.8141 | 0.7384    | 0.9071 |
+| 0.2366        | 4.0   | 71   | 0.2283          | 0.9331   | 0.9272 | 1.0       | 0.8643 |
+| 0.1579        | 4.96  | 88   | 0.2696          | 0.9331   | 0.9294 | 0.9690    | 0.8929 |
+| 0.1626        | 5.97  | 106  | 0.2726          | 0.9225   | 0.9179 | 0.9609    | 0.8786 |
 ### Framework versions