bertweet-base-SNS_BRANDS_100k
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: 0.0483
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0735 | 1.0 | 2928 | 0.0670 |
| 0.0574 | 2.0 | 5856 | 0.0529 |
| 0.0497 | 3.0 | 8784 | 0.0483 |
Framework versions
- Transformers 4.15.0
- Pytorch 1.10.0+cu111
- Datasets 1.17.0
- Tokenizers 0.10.3