|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: xlnet-large-cased-ner-food-combined-v2 |
|
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. --> |
|
|
|
# xlnet-large-cased-ner-food-combined-v2 |
|
|
|
This model is a fine-tuned version of [xlnet-large-cased](https://huggingface.co/xlnet-large-cased) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0681 |
|
- Precision: 0.8554 |
|
- Recall: 0.8743 |
|
- F1: 0.8647 |
|
- Accuracy: 0.9769 |
|
|
|
## 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-06 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 24 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.2606 | 1.12 | 500 | 0.0822 | 0.7976 | 0.8664 | 0.8306 | 0.9712 | |
|
| 0.0837 | 2.25 | 1000 | 0.0955 | 0.7657 | 0.8764 | 0.8173 | 0.9683 | |
|
| 0.0706 | 3.37 | 1500 | 0.0732 | 0.8322 | 0.8714 | 0.8513 | 0.9750 | |
|
| 0.0631 | 4.49 | 2000 | 0.0681 | 0.8554 | 0.8743 | 0.8647 | 0.9769 | |
|
| 0.0549 | 5.62 | 2500 | 0.0713 | 0.8356 | 0.8868 | 0.8604 | 0.9754 | |
|
| 0.0521 | 6.74 | 3000 | 0.0700 | 0.8425 | 0.8863 | 0.8639 | 0.9759 | |
|
| 0.0493 | 7.87 | 3500 | 0.0721 | 0.8444 | 0.8859 | 0.8647 | 0.9763 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.27.4 |
|
- Pytorch 2.0.0+cu118 |
|
- Datasets 2.11.0 |
|
- Tokenizers 0.13.3 |
|
|
