metadata
base_model: vinai/bertweet-base
tags:
- generated_from_trainer
metrics:
- f1
- recall
model-index:
- name: bertweet-base
results: []
bertweet-base
This model is a fine-tuned version of vinai/bertweet-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6138
- F1 Macro: 0.8316
- F1: 0.8834
- F1 Neg: 0.7798
- Acc: 0.8475
- Prec: 0.8652
- Recall: 0.9023
- Mcc: 0.6647
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: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 | F1 Neg | Acc | Prec | Recall | Mcc |
|---|---|---|---|---|---|---|---|---|---|---|
| 0.646 | 1.0 | 614 | 0.4778 | 0.7714 | 0.8366 | 0.7063 | 0.79 | 0.8333 | 0.8398 | 0.5429 |
| 0.4482 | 2.0 | 1228 | 0.4859 | 0.7700 | 0.8597 | 0.6803 | 0.805 | 0.7967 | 0.9336 | 0.5653 |
| 0.3669 | 3.0 | 1842 | 0.6138 | 0.8316 | 0.8834 | 0.7798 | 0.8475 | 0.8652 | 0.9023 | 0.6647 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2