blambert
/

test_wnut_model

Token Classification

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Community

blambert commited on Aug 2, 2023

Commit

6885e2c

•

1 Parent(s): cbd4400

update model card README.md

Files changed (1) hide show

README.md +14 -14

README.md CHANGED Viewed

@@ -25,16 +25,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.516566265060241
     - name: Recall
       type: recall
-      value: 0.3178869323447637
     - name: F1
       type: f1
-      value: 0.39357429718875503
     - name: Accuracy
       type: accuracy
-      value: 0.9431405241332136
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -44,11 +44,11 @@ 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 wnut_17 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2848
-- Precision: 0.5166
-- Recall: 0.3179
-- F1: 0.3936
-- Accuracy: 0.9431
 ## Model description
@@ -79,11 +79,11 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.376         | 1.0   | 566  | 0.3069          | 0.3829    | 0.1242 | 0.1875 | 0.9331   |
-| 0.1664        | 2.0   | 1132 | 0.2941          | 0.5151    | 0.2530 | 0.3393 | 0.9387   |
-| 0.1259        | 3.0   | 1698 | 0.3256          | 0.5982    | 0.2456 | 0.3482 | 0.9405   |
-| 0.1189        | 4.0   | 2264 | 0.2935          | 0.5420    | 0.3049 | 0.3903 | 0.9428   |
-| 0.0992        | 5.0   | 2830 | 0.2848          | 0.5166    | 0.3179 | 0.3936 | 0.9431   |
 ### Framework versions

     metrics:
     - name: Precision
       type: precision
+      value: 0.5218579234972678
     - name: Recall
       type: recall
+      value: 0.3540315106580167
     - name: F1
       type: f1
+      value: 0.4218663721700718
     - name: Accuracy
       type: accuracy
+      value: 0.9427130092770724
 ---
 <!-- 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 wnut_17 dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.2816
+- Precision: 0.5219
+- Recall: 0.3540
+- F1: 0.4219
+- Accuracy: 0.9427
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.3664        | 1.0   | 566  | 0.3082          | 0.4777    | 0.1687 | 0.2493 | 0.9354   |
+| 0.1672        | 2.0   | 1132 | 0.2867          | 0.5395    | 0.3105 | 0.3941 | 0.9407   |
+| 0.1265        | 3.0   | 1698 | 0.3171          | 0.5976    | 0.2753 | 0.3769 | 0.9413   |
+| 0.116         | 4.0   | 2264 | 0.2914          | 0.5712    | 0.3420 | 0.4278 | 0.9431   |
+| 0.0974        | 5.0   | 2830 | 0.2816          | 0.5219    | 0.3540 | 0.4219 | 0.9427   |
 ### Framework versions