|
|
--- |
|
|
license: mit |
|
|
base_model: nielsr/lilt-xlm-roberta-base |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- precision |
|
|
- recall |
|
|
- f1 |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: LILT_DocLayNet_Large |
|
|
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. --> |
|
|
|
|
|
# LILT_DocLayNet_Large |
|
|
|
|
|
This model is a fine-tuned version of [nielsr/lilt-xlm-roberta-base](https://huggingface.co/nielsr/lilt-xlm-roberta-base) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.4755 |
|
|
- Precision: 0.8941 |
|
|
- Recall: 0.8941 |
|
|
- F1: 0.8941 |
|
|
- Accuracy: 0.8941 |
|
|
|
|
|
## 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: 2e-05 |
|
|
- train_batch_size: 16 |
|
|
- eval_batch_size: 32 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 1 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
|
| 0.427 | 0.05 | 1000 | 0.5688 | 0.8324 | 0.8324 | 0.8324 | 0.8324 | |
|
|
| 0.3433 | 0.11 | 2000 | 0.4321 | 0.8730 | 0.8730 | 0.8730 | 0.8730 | |
|
|
| 0.2772 | 0.16 | 3000 | 0.5145 | 0.8764 | 0.8764 | 0.8764 | 0.8764 | |
|
|
| 0.285 | 0.21 | 4000 | 0.4071 | 0.8843 | 0.8843 | 0.8843 | 0.8843 | |
|
|
| 0.2704 | 0.27 | 5000 | 0.4022 | 0.8747 | 0.8747 | 0.8747 | 0.8747 | |
|
|
| 0.2268 | 0.32 | 6000 | 0.4882 | 0.8732 | 0.8732 | 0.8732 | 0.8732 | |
|
|
| 0.2152 | 0.37 | 7000 | 0.5419 | 0.8844 | 0.8844 | 0.8844 | 0.8844 | |
|
|
| 0.2172 | 0.42 | 8000 | 0.5472 | 0.8793 | 0.8793 | 0.8793 | 0.8793 | |
|
|
| 0.2692 | 0.48 | 9000 | 0.6007 | 0.8790 | 0.8790 | 0.8790 | 0.8790 | |
|
|
| 0.2264 | 0.53 | 10000 | 0.7257 | 0.8793 | 0.8793 | 0.8793 | 0.8793 | |
|
|
| 0.2243 | 0.58 | 11000 | 0.5470 | 0.8882 | 0.8882 | 0.8882 | 0.8882 | |
|
|
| 0.1898 | 0.64 | 12000 | 0.6281 | 0.8850 | 0.8850 | 0.8850 | 0.8850 | |
|
|
| 0.2037 | 0.69 | 13000 | 0.5516 | 0.8913 | 0.8913 | 0.8913 | 0.8913 | |
|
|
| 0.1935 | 0.74 | 14000 | 0.5198 | 0.8859 | 0.8859 | 0.8859 | 0.8859 | |
|
|
| 0.2057 | 0.8 | 15000 | 0.5371 | 0.8915 | 0.8915 | 0.8915 | 0.8915 | |
|
|
| 0.2233 | 0.85 | 16000 | 0.5197 | 0.8835 | 0.8835 | 0.8835 | 0.8835 | |
|
|
| 0.1597 | 0.9 | 17000 | 0.4827 | 0.8934 | 0.8934 | 0.8934 | 0.8934 | |
|
|
| 0.2133 | 0.96 | 18000 | 0.4755 | 0.8941 | 0.8941 | 0.8941 | 0.8941 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.32.0 |
|
|
- Pytorch 2.0.1+cu117 |
|
|
- Datasets 2.13.1 |
|
|
- Tokenizers 0.13.3 |
|
|
|
