cj-mills
/

distilbert-base-uncased-distilled-clinc

Text Classification

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Community

cj-mills commited on Apr 14, 2022

Commit

418e51c

·

1 Parent(s): e4cee3e

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: 0.94
 ---
 <!-- 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: 0.0734
-- Accuracy: 0.94
 ## Model description
@@ -62,16 +62,16 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.6673        | 1.0   | 318  | 0.4082          | 0.7090   |
-| 0.3283        | 2.0   | 636  | 0.2116          | 0.8774   |
-| 0.1988        | 3.0   | 954  | 0.1404          | 0.9194   |
-| 0.144         | 4.0   | 1272 | 0.1077          | 0.9281   |
-| 0.1175        | 5.0   | 1590 | 0.0922          | 0.9355   |
-| 0.1029        | 6.0   | 1908 | 0.0836          | 0.9365   |
-| 0.094         | 7.0   | 2226 | 0.0786          | 0.9371   |
-| 0.0883        | 8.0   | 2544 | 0.0756          | 0.9394   |
-| 0.0853        | 9.0   | 2862 | 0.0740          | 0.9394   |
-| 0.0835        | 10.0  | 3180 | 0.0734          | 0.94     |
 ### Framework versions

     metrics:
     - name: Accuracy
       type: accuracy
+      value: 0.9467741935483871
 ---
 <!-- 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: 0.2525
+- Accuracy: 0.9468
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 4.2246        | 1.0   | 318  | 3.1584          | 0.7545   |
+| 2.4033        | 2.0   | 636  | 1.5656          | 0.8652   |
+| 1.1684        | 3.0   | 954  | 0.7795          | 0.9161   |
+| 0.5693        | 4.0   | 1272 | 0.4653          | 0.9329   |
+| 0.3042        | 5.0   | 1590 | 0.3412          | 0.9406   |
+| 0.1794        | 6.0   | 1908 | 0.2912          | 0.9403   |
+| 0.1184        | 7.0   | 2226 | 0.2654          | 0.9461   |
+| 0.0873        | 8.0   | 2544 | 0.2557          | 0.9439   |
+| 0.0719        | 9.0   | 2862 | 0.2549          | 0.9465   |
+| 0.0646        | 10.0  | 3180 | 0.2525          | 0.9468   |
 ### Framework versions