shmuhammad
/

distilbert-base-uncased-distilled-clinc

Text Classification

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Community

shmuhammad commited on Sep 25, 2022

Commit

4a0ea0c

•

1 Parent(s): dae2241

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: 0.9409677419354838
 ---
 <!-- 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: 0.1348
-- Accuracy: 0.9410
 ## Model description
@@ -61,16 +61,16 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.2777        | 1.0   | 318  | 0.7817          | 0.7155   |
-| 0.6021        | 2.0   | 636  | 0.3564          | 0.8613   |
-| 0.3068        | 3.0   | 954  | 0.2092          | 0.9181   |
-| 0.2015        | 4.0   | 1272 | 0.1677          | 0.9306   |
-| 0.1639        | 5.0   | 1590 | 0.1517          | 0.9368   |
-| 0.148         | 6.0   | 1908 | 0.1435          | 0.9397   |
-| 0.1386        | 7.0   | 2226 | 0.1392          | 0.9394   |
-| 0.1334        | 8.0   | 2544 | 0.1366          | 0.9416   |
-| 0.1303        | 9.0   | 2862 | 0.1351          | 0.9410   |
-| 0.1283        | 10.0  | 3180 | 0.1348          | 0.9410   |
 ### Framework versions

     metrics:
     - name: Accuracy
       type: accuracy
+      value: 0.9487096774193549
 ---
 <!-- 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: 0.3060
+- Accuracy: 0.9487
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 2.643         | 1.0   | 318  | 1.9110          | 0.7452   |
+| 1.4751        | 2.0   | 636  | 0.9678          | 0.8606   |
+| 0.7736        | 3.0   | 954  | 0.5578          | 0.9168   |
+| 0.4652        | 4.0   | 1272 | 0.4081          | 0.9352   |
+| 0.3364        | 5.0   | 1590 | 0.3538          | 0.9442   |
+| 0.2801        | 6.0   | 1908 | 0.3294          | 0.9465   |
+| 0.2515        | 7.0   | 2226 | 0.3165          | 0.9471   |
+| 0.2366        | 8.0   | 2544 | 0.3107          | 0.9487   |
+| 0.2292        | 9.0   | 2862 | 0.3069          | 0.9490   |
+| 0.2247        | 10.0  | 3180 | 0.3060          | 0.9487   |
 ### Framework versions