xrverse
/

distilbert-base-uncased-distilled-clinc

Text Classification

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Community

xrverse commited on Oct 13, 2022

Commit

5a099ad

·

1 Parent(s): 009b24a

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: 0.9419354838709677
 ---
 <!-- 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: 0.1662
-- Accuracy: 0.9419
 ## Model description
@@ -61,16 +61,16 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.4626        | 1.0   | 318  | 0.9384          | 0.7232   |
-| 0.7233        | 2.0   | 636  | 0.4417          | 0.8648   |
-| 0.375         | 3.0   | 954  | 0.2598          | 0.9181   |
-| 0.2407        | 4.0   | 1272 | 0.2047          | 0.9323   |
-| 0.1932        | 5.0   | 1590 | 0.1859          | 0.9394   |
-| 0.1732        | 6.0   | 1908 | 0.1769          | 0.9377   |
-| 0.162         | 7.0   | 2226 | 0.1718          | 0.9410   |
-| 0.156         | 8.0   | 2544 | 0.1684          | 0.9410   |
-| 0.1523        | 9.0   | 2862 | 0.1669          | 0.9416   |
-| 0.1502        | 10.0  | 3180 | 0.1662          | 0.9419   |
 ### 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: 0.2573
+- Accuracy: 0.9487
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 2.4269        | 1.0   | 318  | 1.7650          | 0.7465   |
+| 1.3713        | 2.0   | 636  | 0.9151          | 0.8645   |
+| 0.7375        | 3.0   | 954  | 0.5308          | 0.9161   |
+| 0.4403        | 4.0   | 1272 | 0.3740          | 0.9332   |
+| 0.3071        | 5.0   | 1590 | 0.3101          | 0.9445   |
+| 0.2442        | 6.0   | 1908 | 0.2835          | 0.9471   |
+| 0.2133        | 7.0   | 2226 | 0.2690          | 0.9465   |
+| 0.1972        | 8.0   | 2544 | 0.2616          | 0.9487   |
+| 0.1884        | 9.0   | 2862 | 0.2592          | 0.9487   |
+| 0.184         | 10.0  | 3180 | 0.2573          | 0.9487   |
 ### Framework versions