<!-- 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. -->
SA-berttweet-large-e3-b16-w0.01
This model is a fine-tuned version of vinai/bertweet-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2822
- Accuracy: 0.926
- F1: 0.9333
- Precision: 0.9487
- Recall: 0.9184
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
---|---|---|---|---|---|---|---|
No log | 1.0 | 285 | 0.3723 | 0.839 | 0.8342 | 0.9951 | 0.7181 |
0.3662 | 2.0 | 570 | 0.2310 | 0.915 | 0.9242 | 0.9300 | 0.9184 |
0.3662 | 3.0 | 855 | 0.2822 | 0.926 | 0.9333 | 0.9487 | 0.9184 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3