|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: CR_XLNet_5E |
|
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. --> |
|
|
|
# CR_XLNet_5E |
|
|
|
This model is a fine-tuned version of [xlnet-base-cased](https://huggingface.co/xlnet-base-cased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6034 |
|
- Accuracy: 0.9067 |
|
|
|
## 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: 3e-05 |
|
- train_batch_size: 16 |
|
- 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 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.5384 | 0.33 | 50 | 0.4165 | 0.8533 | |
|
| 0.3633 | 0.66 | 100 | 0.3059 | 0.8867 | |
|
| 0.2642 | 0.99 | 150 | 0.2582 | 0.9267 | |
|
| 0.2626 | 1.32 | 200 | 0.3324 | 0.9 | |
|
| 0.1859 | 1.66 | 250 | 0.4076 | 0.9067 | |
|
| 0.2631 | 1.99 | 300 | 0.4334 | 0.8867 | |
|
| 0.1449 | 2.32 | 350 | 0.4264 | 0.9 | |
|
| 0.1815 | 2.65 | 400 | 0.4334 | 0.8933 | |
|
| 0.1316 | 2.98 | 450 | 0.4436 | 0.9 | |
|
| 0.0725 | 3.31 | 500 | 0.6165 | 0.9 | |
|
| 0.0708 | 3.64 | 550 | 0.6737 | 0.8933 | |
|
| 0.0821 | 3.97 | 600 | 0.5777 | 0.9067 | |
|
| 0.0381 | 4.3 | 650 | 0.6052 | 0.9 | |
|
| 0.0441 | 4.64 | 700 | 0.5853 | 0.9133 | |
|
| 0.0237 | 4.97 | 750 | 0.6034 | 0.9067 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.24.0 |
|
- Pytorch 1.13.0 |
|
- Datasets 2.3.2 |
|
- Tokenizers 0.13.1 |
|
|
