bert_finetune_classification
This model is a fine-tuned version of bert-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1339
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
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 30
- num_epochs: 9
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0748 | 1.0 | 417 | 0.0957 |
| 0.0517 | 2.0 | 834 | 0.0880 |
| 0.0631 | 3.0 | 1251 | 0.0736 |
| 0.0048 | 4.0 | 1669 | 0.0795 |
| 0.0457 | 5.0 | 2086 | 0.0861 |
| 0.0016 | 6.0 | 2503 | 0.1086 |
| 0.0482 | 7.0 | 2920 | 0.1073 |
| 0.0483 | 8.0 | 3338 | 0.1224 |
| 0.0286 | 8.99 | 3753 | 0.1339 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.0.0+cu117
- Datasets 2.14.5
- Tokenizers 0.14.1