Initial release

README.md

@@ -14,8 +14,8 @@ model-index:
 - name: banking77-deBERTa-v3-base
   results:
   - task:
-      type: text-classification
       name: Text Classification
+      type: text-classification
     dataset:
       name: banking77
       type: banking77
@@ -23,9 +23,9 @@ model-index:
       split: train
       args: default
     metrics:
-    - type: accuracy
-      value: 0.9225387306346826
-      name: Accuracy
+    - name: Accuracy
+      type: accuracy
+      value: 0.9195402298850575
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -35,14 +35,14 @@ 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 the banking77 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3388
-- Accuracy: 0.9225
-- F1 Macro: 0.9207
-- Precision Macro: 0.9261
-- Recall Macro: 0.9193
-- F1 Weighted: 0.9221
-- Precision Weighted: 0.9252
-- Recall Weighted: 0.9225
+- Loss: 0.3281
+- Accuracy: 0.9195
+- F1 Macro: 0.9170
+- Precision Macro: 0.9222
+- Recall Macro: 0.9159
+- F1 Weighted: 0.9194
+- Precision Weighted: 0.9229
+- Recall Weighted: 0.9195
 
 ## Model description
 
@@ -68,15 +68,17 @@ The following hyperparameters were used during training:
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- num_epochs: 3
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | Precision Macro | Recall Macro | F1 Weighted | Precision Weighted | Recall Weighted |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:---------------:|:------------:|:-----------:|:------------------:|:---------------:|
-| 0.9407        | 1.0   | 501  | 0.8110          | 0.8351   | 0.8093   | 0.8304          | 0.8144       | 0.8263      | 0.8412             | 0.8351          |
-| 0.4485        | 2.0   | 1002 | 0.4066          | 0.9055   | 0.8958   | 0.9069          | 0.8941       | 0.9041      | 0.9093             | 0.9055          |
-| 0.2692        | 3.0   | 1503 | 0.3388          | 0.9225   | 0.9207   | 0.9261          | 0.9193       | 0.9221      | 0.9252             | 0.9225          |
+| 3.4666        | 1.0   | 501  | 3.1762          | 0.3548   | 0.2479   | 0.3016          | 0.3195       | 0.2774      | 0.3421             | 0.3548          |
+| 1.2538        | 2.0   | 1002 | 1.0122          | 0.8141   | 0.7625   | 0.8091          | 0.7795       | 0.7946      | 0.8291             | 0.8141          |
+| 0.5576        | 3.0   | 1503 | 0.4823          | 0.8941   | 0.8797   | 0.9012          | 0.8786       | 0.8915      | 0.9021             | 0.8941          |
+| 0.3544        | 4.0   | 2004 | 0.3625          | 0.9110   | 0.9090   | 0.9170          | 0.9084       | 0.9108      | 0.9172             | 0.9110          |
+| 0.2603        | 5.0   | 2505 | 0.3281          | 0.9195   | 0.9170   | 0.9222          | 0.9159       | 0.9194      | 0.9229             | 0.9195          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:497584b4f9c857dffca420184d39d6d5799a83b107eb9360749392c71f94aedc
+oid sha256:17435a19f85b188ff17b784f1f203e711ca2d5d2f8b3ddd8da6f1ee881c5071c
 size 737949988

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5fc97f368e1905e2351297a1c44a84a50e3a1e033694e4c9b1cc4e22191d7ac
+oid sha256:42182bc423f5c98b3410e3dc5143cd47594da824a48eee325f672f64016ced02
 size 5240