bert-base-uncased-finetuned-cda2
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.6474
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
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.0558 | 1.0 | 407 | 1.8182 |
| 1.8924 | 2.0 | 814 | 1.7201 |
| 1.8353 | 3.0 | 1221 | 1.7211 |
| 1.7979 | 4.0 | 1628 | 1.6805 |
| 1.7721 | 5.0 | 2035 | 1.6345 |
| 1.7489 | 6.0 | 2442 | 1.6593 |
| 1.7305 | 7.0 | 2849 | 1.6600 |
| 1.7186 | 8.0 | 3256 | 1.6309 |
| 1.7053 | 9.0 | 3663 | 1.6647 |
| 1.6998 | 10.0 | 4070 | 1.6539 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- -
Model tree for zz990906/bert-base-uncased-finetuned-cda2
Base model
google-bert/bert-base-uncased