bert-base-uncased-finetuned-cda
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: 1.6567
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 |
|---|---|---|---|
| 2.0518 | 1.0 | 391 | 1.8074 |
| 1.8971 | 2.0 | 782 | 1.7770 |
| 1.8422 | 3.0 | 1173 | 1.7504 |
| 1.7984 | 4.0 | 1564 | 1.7272 |
| 1.777 | 5.0 | 1955 | 1.6912 |
| 1.7532 | 6.0 | 2346 | 1.6920 |
| 1.7323 | 7.0 | 2737 | 1.6826 |
| 1.7251 | 8.0 | 3128 | 1.6687 |
| 1.7108 | 9.0 | 3519 | 1.6553 |
| 1.7076 | 10.0 | 3910 | 1.6702 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
- Downloads last month
- 125
Model tree for zz990906/bert-base-uncased-finetuned-cda
Base model
google-bert/bert-base-uncased