dayvidwang
/

bert-finetuned-ner

Token Classification

Generated from Trainer

Model card Files Files and versions Community

dayvidwang commited on Jun 13, 2023

Commit

0585be7

·

1 Parent(s): c6470ce

update model card README.md

Files changed (1) hide show

README.md +13 -13

README.md CHANGED Viewed

@@ -19,11 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1592
-- Precision: 0.7852
-- Recall: 0.8012
-- F1: 0.7931
-- Accuracy: 0.9701
 ## Model description
@@ -54,14 +54,14 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 131  | 0.1607          | 0.6254    | 0.6801 | 0.6516 | 0.9538   |
-| No log        | 2.0   | 262  | 0.1188          | 0.7437    | 0.7695 | 0.7564 | 0.9670   |
-| No log        | 3.0   | 393  | 0.1264          | 0.7556    | 0.7750 | 0.7652 | 0.9675   |
-| 0.0923        | 4.0   | 524  | 0.1344          | 0.7622    | 0.7858 | 0.7738 | 0.9680   |
-| 0.0923        | 5.0   | 655  | 0.1442          | 0.7741    | 0.7835 | 0.7788 | 0.9694   |
-| 0.0923        | 6.0   | 786  | 0.1501          | 0.7892    | 0.8104 | 0.7997 | 0.9703   |
-| 0.0923        | 7.0   | 917  | 0.1584          | 0.7750    | 0.7964 | 0.7856 | 0.9694   |
-| 0.0133        | 8.0   | 1048 | 0.1592          | 0.7852    | 0.8012 | 0.7931 | 0.9701   |
 ### Framework versions

 This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.1622
+- Precision: 0.7774
+- Recall: 0.7937
+- F1: 0.7854
+- Accuracy: 0.9707
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 131  | 0.1355          | 0.6880    | 0.7298 | 0.7083 | 0.9604   |
+| No log        | 2.0   | 262  | 0.1194          | 0.7564    | 0.7727 | 0.7645 | 0.9684   |
+| No log        | 3.0   | 393  | 0.1277          | 0.7731    | 0.7868 | 0.7799 | 0.9691   |
+| 0.0433        | 4.0   | 524  | 0.1433          | 0.7553    | 0.7829 | 0.7688 | 0.9685   |
+| 0.0433        | 5.0   | 655  | 0.1515          | 0.7734    | 0.7946 | 0.7839 | 0.9700   |
+| 0.0433        | 6.0   | 786  | 0.1518          | 0.7819    | 0.8008 | 0.7912 | 0.9708   |
+| 0.0433        | 7.0   | 917  | 0.1602          | 0.7752    | 0.7914 | 0.7832 | 0.9704   |
+| 0.0094        | 8.0   | 1048 | 0.1622          | 0.7774    | 0.7937 | 0.7854 | 0.9707   |
 ### Framework versions