bert-base-cased-finetuned
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: 0.2396
- Accuracy: 0.9575
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: 10
Training results
| Training Loss |
Epoch |
Step |
Validation Loss |
Accuracy |
| 0.2096 |
1.0 |
100 |
0.2535 |
0.9375 |
| 0.0835 |
2.0 |
200 |
0.2931 |
0.9425 |
| 0.0358 |
3.0 |
300 |
0.2112 |
0.9525 |
| 0.0124 |
4.0 |
400 |
0.2400 |
0.9475 |
| 0.0071 |
5.0 |
500 |
0.2241 |
0.955 |
| 0.0024 |
6.0 |
600 |
0.2342 |
0.9575 |
| 0.0035 |
7.0 |
700 |
0.2345 |
0.96 |
| 0.0005 |
8.0 |
800 |
0.2278 |
0.9575 |
| 0.0059 |
9.0 |
900 |
0.2243 |
0.96 |
| 0.0003 |
10.0 |
1000 |
0.2396 |
0.9575 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.15.0
