pensuke
/

distilbert-base-uncased-distilled-clinc

Text Classification

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Community

pensuke commited on Oct 14, 2023

Commit

9546eb5

•

1 Parent(s): b575e7d

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: 0.2126
-- Accuracy: 0.9490
 ## Model description
@@ -61,16 +61,16 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 318  | 1.6893          | 0.7597   |
-| 1.9981        | 2.0   | 636  | 0.8885          | 0.8761   |
-| 1.9981        | 3.0   | 954  | 0.5085          | 0.9213   |
-| 0.7907        | 4.0   | 1272 | 0.3452          | 0.9384   |
-| 0.3509        | 5.0   | 1590 | 0.2747          | 0.9445   |
-| 0.3509        | 6.0   | 1908 | 0.2428          | 0.9477   |
-| 0.2145        | 7.0   | 2226 | 0.2257          | 0.9487   |
-| 0.1664        | 8.0   | 2544 | 0.2181          | 0.9487   |
-| 0.1664        | 9.0   | 2862 | 0.2147          | 0.9490   |
-| 0.1498        | 10.0  | 3180 | 0.2126          | 0.9490   |
 ### Framework versions

     metrics:
     - name: Accuracy
       type: accuracy
+      value: 0.9470967741935484
 ---
 <!-- 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: 0.2992
+- Accuracy: 0.9471
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 318  | 3.0515          | 0.7435   |
+| 3.5618        | 2.0   | 636  | 1.5136          | 0.86     |
+| 3.5618        | 3.0   | 954  | 0.7620          | 0.9145   |
+| 1.2971        | 4.0   | 1272 | 0.4722          | 0.9348   |
+| 0.4453        | 5.0   | 1590 | 0.3635          | 0.9432   |
+| 0.4453        | 6.0   | 1908 | 0.3219          | 0.9442   |
+| 0.2135        | 7.0   | 2226 | 0.3061          | 0.9471   |
+| 0.1451        | 8.0   | 2544 | 0.3009          | 0.9481   |
+| 0.1451        | 9.0   | 2862 | 0.2990          | 0.9474   |
+| 0.125         | 10.0  | 3180 | 0.2992          | 0.9471   |
 ### Framework versions