|
--- |
|
base_model: vinai/phobert-base-v2 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: phobert-base-v2-ed |
|
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-base-v2-ed |
|
|
|
This model is a fine-tuned version of [vinai/phobert-base-v2](https://huggingface.co/vinai/phobert-base-v2) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0455 |
|
- F1 Micro: 0.7302 |
|
- F1 Macro: 0.0774 |
|
- Recall Micro: 0.6299 |
|
- Precision Micro: 0.8683 |
|
- Recall Macro: 0.0745 |
|
- Precision Macro: 0.0806 |
|
|
|
## 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 | F1 Micro | F1 Macro | Recall Micro | Precision Micro | Recall Macro | Precision Macro | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:------------:|:---------------:|:------------:|:---------------:| |
|
| 0.0638 | 1.0 | 1526 | 0.0622 | 0.7114 | 0.0257 | 0.6218 | 0.8312 | 0.0271 | 0.0244 | |
|
| 0.046 | 2.0 | 3052 | 0.0543 | 0.7112 | 0.0259 | 0.6021 | 0.8684 | 0.0263 | 0.0255 | |
|
| 0.0462 | 3.0 | 4578 | 0.0494 | 0.7049 | 0.0716 | 0.5895 | 0.8764 | 0.0685 | 0.0803 | |
|
| 0.0472 | 4.0 | 6104 | 0.0461 | 0.7326 | 0.0762 | 0.6402 | 0.8562 | 0.0724 | 0.0812 | |
|
| 0.0228 | 5.0 | 7630 | 0.0455 | 0.7302 | 0.0774 | 0.6299 | 0.8683 | 0.0745 | 0.0806 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
