|
--- |
|
license: mit |
|
base_model: xlnet-large-cased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: xlnet-lg-cased-ms-ner-test |
|
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-lg-cased-ms-ner-test |
|
|
|
This model is a fine-tuned version of [xlnet-large-cased](https://huggingface.co/xlnet-large-cased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1308 |
|
- Precision: 0.8828 |
|
- Recall: 0.9077 |
|
- F1: 0.8951 |
|
- Accuracy: 0.9814 |
|
|
|
## 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: 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: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.137 | 1.0 | 3615 | 0.1313 | 0.7971 | 0.7986 | 0.7979 | 0.9663 | |
|
| 0.0761 | 2.0 | 7230 | 0.0894 | 0.8564 | 0.8773 | 0.8667 | 0.9781 | |
|
| 0.0459 | 3.0 | 10845 | 0.0946 | 0.8718 | 0.8918 | 0.8817 | 0.9803 | |
|
| 0.021 | 4.0 | 14460 | 0.1091 | 0.8795 | 0.9017 | 0.8905 | 0.9808 | |
|
| 0.013 | 5.0 | 18075 | 0.1308 | 0.8828 | 0.9077 | 0.8951 | 0.9814 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 1.12.0 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
