xrverse
/

distilbert-base-uncased-distilled-clinc

Text Classification

generated_from_trainer

Inference Endpoints

Model card Files Files and versions Community

xrverse commited on Oct 14, 2022

Commit

2726126

•

1 Parent(s): b1733f6

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: 0.9483870967741935
 ---
 <!-- 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: 0.2675
-- Accuracy: 0.9484
 ## Model description
@@ -61,16 +61,16 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.2332        | 1.0   | 318  | 1.5779          | 0.7303   |
-| 1.2209        | 2.0   | 636  | 0.7940          | 0.8603   |
-| 0.6485        | 3.0   | 954  | 0.4679          | 0.9135   |
-| 0.3987        | 4.0   | 1272 | 0.3480          | 0.9326   |
-| 0.2964        | 5.0   | 1590 | 0.3043          | 0.9442   |
-| 0.2522        | 6.0   | 1908 | 0.2863          | 0.9461   |
-| 0.2304        | 7.0   | 2226 | 0.2762          | 0.9468   |
-| 0.2193        | 8.0   | 2544 | 0.2708          | 0.9468   |
-| 0.2129        | 9.0   | 2862 | 0.2689          | 0.9477   |
-| 0.2097        | 10.0  | 3180 | 0.2675          | 0.9484   |
 ### Framework versions

     metrics:
     - name: Accuracy
       type: accuracy
+      value: 0.9303225806451613
 ---
 <!-- 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: 0.0332
+- Accuracy: 0.9303
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.4409        | 1.0   | 318  | 0.2288          | 0.6206   |
+| 0.1898        | 2.0   | 636  | 0.1106          | 0.8461   |
+| 0.116         | 3.0   | 954  | 0.0729          | 0.8994   |
+| 0.0861        | 4.0   | 1272 | 0.0548          | 0.9097   |
+| 0.0707        | 5.0   | 1590 | 0.0454          | 0.9184   |
+| 0.0613        | 6.0   | 1908 | 0.0399          | 0.9239   |
+| 0.0557        | 7.0   | 2226 | 0.0371          | 0.9294   |
+| 0.0522        | 8.0   | 2544 | 0.0348          | 0.93     |
+| 0.05          | 9.0   | 2862 | 0.0336          | 0.9297   |
+| 0.0487        | 10.0  | 3180 | 0.0332          | 0.9303   |
 ### Framework versions