|
--- |
|
library_name: transformers |
|
license: agpl-3.0 |
|
base_model: vinai/phobert-base-v2 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: Phobert_CITA_15k |
|
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. --> |
|
|
|
# Phobert_CITA_15k |
|
|
|
This model is a fine-tuned version of [vinai/phobert-base-v2](https://huggingface.co/vinai/phobert-base-v2) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6995 |
|
- Accuracy: 0.8057 |
|
- F1: 0.8034 |
|
|
|
## 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: cosine_with_restarts |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| |
|
| 0.4825 | 1.0 | 375 | 0.4345 | 0.8047 | 0.7947 | |
|
| 0.3984 | 2.0 | 750 | 0.4341 | 0.8033 | 0.8030 | |
|
| 0.3466 | 3.0 | 1125 | 0.4692 | 0.8213 | 0.8158 | |
|
| 0.3012 | 4.0 | 1500 | 0.5128 | 0.8147 | 0.8051 | |
|
| 0.256 | 5.0 | 1875 | 0.5427 | 0.806 | 0.8061 | |
|
| 0.213 | 6.0 | 2250 | 0.5851 | 0.8087 | 0.8022 | |
|
| 0.1805 | 7.0 | 2625 | 0.6466 | 0.8083 | 0.8060 | |
|
| 0.1568 | 8.0 | 3000 | 0.6883 | 0.81 | 0.8053 | |
|
| 0.1453 | 9.0 | 3375 | 0.6956 | 0.8083 | 0.8056 | |
|
| 0.1467 | 10.0 | 3750 | 0.6995 | 0.8057 | 0.8034 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.48.0 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.21.0 |
|
|
