renjithks
/

layoutlmv2-er-ner

Token Classification

Generated from Trainer

Model card Files Files and versions

Metrics Training metrics Community

renjithks commited on Jun 5, 2022

Commit

ac373ba

·

1 Parent(s): c29b203

update model card README.md

Files changed (1) hide show

README.md +15 -15

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 [renjithks/layoutlmv2-cord-ner](https://huggingface.co/renjithks/layoutlmv2-cord-ner) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2940
-- Precision: 0.4454
-- Recall: 0.3512
-- F1: 0.3927
-- Accuracy: 0.9270
 ## Model description
@@ -54,16 +54,16 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 22   | 0.5444          | 0.0       | 0.0    | 0.0    | 0.8801   |
-| No log        | 2.0   | 44   | 0.5413          | 0.0       | 0.0    | 0.0    | 0.8801   |
-| No log        | 3.0   | 66   | 0.5373          | 0.0       | 0.0    | 0.0    | 0.8801   |
-| No log        | 4.0   | 88   | 0.5359          | 0.0       | 0.0    | 0.0    | 0.8801   |
-| No log        | 5.0   | 110  | 0.5311          | 0.0       | 0.0    | 0.0    | 0.8801   |
-| No log        | 6.0   | 132  | 0.4794          | 0.0       | 0.0    | 0.0    | 0.8801   |
-| No log        | 7.0   | 154  | 0.4198          | 0.0       | 0.0    | 0.0    | 0.8801   |
-| No log        | 8.0   | 176  | 0.3509          | 0.3643    | 0.2271 | 0.2798 | 0.9108   |
-| No log        | 9.0   | 198  | 0.3045          | 0.4324    | 0.3427 | 0.3824 | 0.9225   |
-| No log        | 10.0  | 220  | 0.2940          | 0.4454    | 0.3512 | 0.3927 | 0.9270   |
 ### Framework versions

 This model is a fine-tuned version of [renjithks/layoutlmv2-cord-ner](https://huggingface.co/renjithks/layoutlmv2-cord-ner) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.1710
+- Precision: 0.6987
+- Recall: 0.6968
+- F1: 0.6977
+- Accuracy: 0.9622
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 22   | 0.2635          | 0.4513    | 0.3724 | 0.4080 | 0.9282   |
+| No log        | 2.0   | 44   | 0.2537          | 0.4459    | 0.4824 | 0.4634 | 0.9327   |
+| No log        | 3.0   | 66   | 0.2027          | 0.6367    | 0.5487 | 0.5894 | 0.9486   |
+| No log        | 4.0   | 88   | 0.1943          | 0.6126    | 0.6446 | 0.6282 | 0.9547   |
+| No log        | 5.0   | 110  | 0.1840          | 0.6644    | 0.6756 | 0.6699 | 0.9559   |
+| No log        | 6.0   | 132  | 0.1719          | 0.6819    | 0.6319 | 0.6559 | 0.9610   |
+| No log        | 7.0   | 154  | 0.1698          | 0.6471    | 0.6827 | 0.6644 | 0.9598   |
+| No log        | 8.0   | 176  | 0.1767          | 0.7022    | 0.6685 | 0.6850 | 0.9604   |
+| No log        | 9.0   | 198  | 0.1661          | 0.6973    | 0.6953 | 0.6963 | 0.9630   |
+| No log        | 10.0  | 220  | 0.1710          | 0.6987    | 0.6968 | 0.6977 | 0.9622   |
 ### Framework versions