itoh5588
/

distilbert-base-uncased-distilled-clinc

Text Classification

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Community

itoh5588 commited on Aug 4, 2023

Commit

fd8ac2a

•

1 Parent(s): d34ff28

update model card README.md

Files changed (1) hide show

README.md +13 -13

README.md CHANGED Viewed

@@ -19,7 +19,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.9490322580645161
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,8 +29,8 @@ 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 clinc_oos dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2396
-- Accuracy: 0.9490
 ## Model description
@@ -61,16 +61,16 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.4105        | 1.0   | 318  | 1.7674          | 0.7568   |
-| 1.3717        | 2.0   | 636  | 0.9207          | 0.8716   |
-| 0.7351        | 3.0   | 954  | 0.5276          | 0.9197   |
-| 0.4354        | 4.0   | 1272 | 0.3646          | 0.9377   |
-| 0.2955        | 5.0   | 1590 | 0.2968          | 0.9439   |
-| 0.231         | 6.0   | 1908 | 0.2671          | 0.9477   |
-| 0.198         | 7.0   | 2226 | 0.2513          | 0.9490   |
-| 0.1802        | 8.0   | 2544 | 0.2446          | 0.9484   |
-| 0.1707        | 9.0   | 2862 | 0.2416          | 0.9490   |
-| 0.1671        | 10.0  | 3180 | 0.2396          | 0.9490   |
 ### Framework versions

     metrics:
     - name: Accuracy
       type: accuracy
+      value: 0.9364516129032258
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the clinc_oos dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.0661
+- Accuracy: 0.9365
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.7476        | 1.0   | 318  | 0.4241          | 0.6858   |
+| 0.33          | 2.0   | 636  | 0.1883          | 0.8665   |
+| 0.1795        | 3.0   | 954  | 0.1159          | 0.9110   |
+| 0.1267        | 4.0   | 1272 | 0.0902          | 0.9232   |
+| 0.1032        | 5.0   | 1590 | 0.0793          | 0.9284   |
+| 0.0918        | 6.0   | 1908 | 0.0732          | 0.9339   |
+| 0.0847        | 7.0   | 2226 | 0.0699          | 0.9358   |
+| 0.0804        | 8.0   | 2544 | 0.0678          | 0.9371   |
+| 0.0778        | 9.0   | 2862 | 0.0665          | 0.9371   |
+| 0.0767        | 10.0  | 3180 | 0.0661          | 0.9365   |
 ### Framework versions