|
--- |
|
license: mit |
|
base_model: tangminhanh/ts_cate |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: ts_subcate |
|
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. --> |
|
|
|
# ts_subcate |
|
|
|
This model is a fine-tuned version of [tangminhanh/ts_cate](https://huggingface.co/tangminhanh/ts_cate) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0084 |
|
- Accuracy: 0.7013 |
|
- F1: 0.7812 |
|
- Precision: 0.8815 |
|
- Recall: 0.7014 |
|
|
|
## 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: 64 |
|
- 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 | Accuracy | F1 | Precision | Recall | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| No log | 1.0 | 403 | 0.0261 | 0.0 | 0.0 | 0.0 | 0.0 | |
|
| 0.0805 | 2.0 | 806 | 0.0174 | 0.3328 | 0.4904 | 0.9438 | 0.3313 | |
|
| 0.0203 | 3.0 | 1209 | 0.0131 | 0.4702 | 0.6217 | 0.9229 | 0.4687 | |
|
| 0.0138 | 4.0 | 1612 | 0.0111 | 0.5592 | 0.6939 | 0.9170 | 0.5581 | |
|
| 0.0104 | 5.0 | 2015 | 0.0100 | 0.6297 | 0.7417 | 0.8998 | 0.6308 | |
|
| 0.0104 | 6.0 | 2418 | 0.0091 | 0.6659 | 0.7628 | 0.8909 | 0.6669 | |
|
| 0.0084 | 7.0 | 2821 | 0.0088 | 0.6815 | 0.7712 | 0.8867 | 0.6823 | |
|
| 0.0072 | 8.0 | 3224 | 0.0086 | 0.6889 | 0.7764 | 0.8874 | 0.6900 | |
|
| 0.0063 | 9.0 | 3627 | 0.0084 | 0.6982 | 0.7803 | 0.8832 | 0.6989 | |
|
| 0.006 | 10.0 | 4030 | 0.0084 | 0.7013 | 0.7812 | 0.8815 | 0.7014 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.4 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
