<!-- 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. -->
timi-domain-classification-undersampling-class-weight-v3
This model is a fine-tuned version of vinai/phobert-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1075
- Precision: 0.8918
- F1: 0.8716
- Accuracy: 0.9362
- Recall: 0.8523
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | F1 | Accuracy | Recall |
---|---|---|---|---|---|---|---|
0.0559 | 1.0 | 460 | 0.0597 | 0.8121 | 0.8426 | 0.9169 | 0.8755 |
0.023 | 2.0 | 920 | 0.0580 | 0.8634 | 0.8653 | 0.9314 | 0.8671 |
0.011 | 3.0 | 1380 | 0.1114 | 0.9501 | 0.8468 | 0.9298 | 0.7637 |
0.0042 | 4.0 | 1840 | 0.0870 | 0.8511 | 0.8713 | 0.9330 | 0.8924 |
0.0021 | 5.0 | 2300 | 0.1075 | 0.8918 | 0.8716 | 0.9362 | 0.8523 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3