|
--- |
|
license: cc-by-nc-sa-4.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: layoutlmv2-cord-ner |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# layoutlmv2-cord-ner |
|
|
|
This model is a fine-tuned version of [microsoft/layoutlmv2-base-uncased](https://huggingface.co/microsoft/layoutlmv2-base-uncased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0952 |
|
- Precision: 0.9639 |
|
- Recall: 0.9741 |
|
- F1: 0.9690 |
|
- Accuracy: 0.9911 |
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 5e-05 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 1.0 | 113 | 0.5962 | 0.8714 | 0.8973 | 0.8842 | 0.9405 | |
|
| No log | 2.0 | 226 | 0.4064 | 0.8713 | 0.9098 | 0.8901 | 0.9511 | |
|
| No log | 3.0 | 339 | 0.2687 | 0.9314 | 0.9386 | 0.9350 | 0.9754 | |
|
| No log | 4.0 | 452 | 0.2007 | 0.9355 | 0.9472 | 0.9413 | 0.9792 | |
|
| 0.4677 | 5.0 | 565 | 0.1625 | 0.9497 | 0.9597 | 0.9547 | 0.9834 | |
|
| 0.4677 | 6.0 | 678 | 0.1326 | 0.9526 | 0.9645 | 0.9585 | 0.9868 | |
|
| 0.4677 | 7.0 | 791 | 0.1212 | 0.9508 | 0.9645 | 0.9576 | 0.9851 | |
|
| 0.4677 | 8.0 | 904 | 0.1019 | 0.9675 | 0.9712 | 0.9693 | 0.9911 | |
|
| 0.1131 | 9.0 | 1017 | 0.1029 | 0.9545 | 0.9664 | 0.9604 | 0.9881 | |
|
| 0.1131 | 10.0 | 1130 | 0.0952 | 0.9639 | 0.9741 | 0.9690 | 0.9911 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.16.2 |
|
- Pytorch 1.9.0+cu111 |
|
- Datasets 1.18.4 |
|
- Tokenizers 0.11.6 |
|
|
