|
--- |
|
base_model: vinai/bertweet-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
- recall |
|
model-index: |
|
- name: bertweet-base |
|
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. --> |
|
|
|
# bertweet-base |
|
|
|
This model is a fine-tuned version of [vinai/bertweet-base](https://huggingface.co/vinai/bertweet-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5645 |
|
- F1 Macro: 0.8513 |
|
- F1: 0.9041 |
|
- F1 Neg: 0.7984 |
|
- Acc: 0.87 |
|
- Prec: 0.8974 |
|
- Recall: 0.9108 |
|
- Mcc: 0.7027 |
|
|
|
## 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 |
|
- distributed_type: multi-GPU |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 5 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 | F1 Neg | Acc | Prec | Recall | Mcc | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:------:|:------:|:------:|:------:| |
|
| 0.6718 | 1.0 | 614 | 0.6382 | 0.6919 | 0.8136 | 0.5702 | 0.74 | 0.7517 | 0.8867 | 0.4083 | |
|
| 0.5134 | 2.0 | 1228 | 0.5523 | 0.7460 | 0.7657 | 0.7263 | 0.7475 | 0.9429 | 0.6445 | 0.5564 | |
|
| 0.4637 | 3.0 | 1842 | 0.5460 | 0.8362 | 0.8837 | 0.7887 | 0.85 | 0.8769 | 0.8906 | 0.6726 | |
|
| 0.4004 | 4.0 | 2456 | 0.6145 | 0.8160 | 0.8505 | 0.7815 | 0.8225 | 0.9224 | 0.7891 | 0.6471 | |
|
| 0.3192 | 5.0 | 3070 | 0.5929 | 0.8476 | 0.8911 | 0.8042 | 0.86 | 0.8876 | 0.8945 | 0.6953 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
