<!-- 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-e6-w2-1-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: 0.4510
- Accuracy: 0.935
- F1: 0.9423
- Precision: 0.9432
- Recall: 0.9415
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: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 285 | 0.2599 | 0.871 | 0.8714 | 0.9954 | 0.7748 |
| 0.3039 | 2.0 | 570 | 0.2502 | 0.929 | 0.9371 | 0.9363 | 0.9379 |
| 0.3039 | 3.0 | 855 | 0.4228 | 0.923 | 0.9331 | 0.9148 | 0.9521 |
| 0.1246 | 4.0 | 1140 | 0.4102 | 0.934 | 0.9414 | 0.9431 | 0.9397 |
| 0.1246 | 5.0 | 1425 | 0.4532 | 0.933 | 0.9407 | 0.9398 | 0.9415 |
| 0.0379 | 6.0 | 1710 | 0.4510 | 0.935 | 0.9423 | 0.9432 | 0.9415 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
