|
|
--- |
|
|
library_name: transformers |
|
|
license: gpl-3.0 |
|
|
base_model: ckiplab/albert-tiny-chinese |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
- precision |
|
|
- recall |
|
|
- f1 |
|
|
model-index: |
|
|
- name: tuned-albert-tiny |
|
|
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. --> |
|
|
|
|
|
# tuned-albert-tiny |
|
|
|
|
|
This model is a fine-tuned version of [ckiplab/albert-tiny-chinese](https://huggingface.co/ckiplab/albert-tiny-chinese) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.6326 |
|
|
- Accuracy: 1.0 |
|
|
- Precision: 1.0 |
|
|
- Recall: 1.0 |
|
|
- F1: 1.0 |
|
|
|
|
|
## 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: 32 |
|
|
- eval_batch_size: 32 |
|
|
- seed: 42 |
|
|
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 3 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:| |
|
|
| 0.6878 | 0.2 | 1 | 0.6827 | 0.625 | 0.75 | 0.7 | 0.6190 | |
|
|
| 0.6849 | 0.4 | 2 | 0.6786 | 0.625 | 0.75 | 0.7 | 0.6190 | |
|
|
| 0.6747 | 0.6 | 3 | 0.6729 | 0.875 | 0.875 | 0.9 | 0.8730 | |
|
|
| 0.6763 | 0.8 | 4 | 0.6672 | 0.9375 | 0.9286 | 0.95 | 0.9352 | |
|
|
| 0.6634 | 1.0 | 5 | 0.6628 | 0.9375 | 0.9286 | 0.95 | 0.9352 | |
|
|
| 0.6562 | 1.2 | 6 | 0.6589 | 0.9375 | 0.9286 | 0.95 | 0.9352 | |
|
|
| 0.6516 | 1.4 | 7 | 0.6553 | 0.9375 | 0.9286 | 0.95 | 0.9352 | |
|
|
| 0.6525 | 1.6 | 8 | 0.6517 | 0.9375 | 0.9286 | 0.95 | 0.9352 | |
|
|
| 0.6497 | 1.8 | 9 | 0.6477 | 0.9375 | 0.9286 | 0.95 | 0.9352 | |
|
|
| 0.6432 | 2.0 | 10 | 0.6439 | 0.9375 | 0.9286 | 0.95 | 0.9352 | |
|
|
| 0.6488 | 2.2 | 11 | 0.6403 | 0.9375 | 0.9286 | 0.95 | 0.9352 | |
|
|
| 0.6384 | 2.4 | 12 | 0.6373 | 0.9375 | 0.9286 | 0.95 | 0.9352 | |
|
|
| 0.6236 | 2.6 | 13 | 0.6349 | 1.0 | 1.0 | 1.0 | 1.0 | |
|
|
| 0.6254 | 2.8 | 14 | 0.6334 | 1.0 | 1.0 | 1.0 | 1.0 | |
|
|
| 0.6346 | 3.0 | 15 | 0.6326 | 1.0 | 1.0 | 1.0 | 1.0 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.49.0 |
|
|
- Pytorch 2.5.1+cu124 |
|
|
- Datasets 3.5.0 |
|
|
- Tokenizers 0.21.0 |
|
|
|
