results
This model is a fine-tuned version of bert-base-uncased on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.8481
- Accuracy: 0.425
- F1: 0.4068
- Precision: 0.4371
- Recall: 0.425
- Mse: 5.314
- Mae: 1.37
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss |
Epoch |
Step |
Validation Loss |
Accuracy |
F1 |
Precision |
Recall |
Mse |
Mae |
| 1.9914 |
1.0 |
157 |
1.7086 |
0.404 |
0.2561 |
0.3800 |
0.404 |
10.332 |
1.95 |
| 1.5651 |
2.0 |
314 |
1.6295 |
0.419 |
0.3343 |
0.4048 |
0.419 |
7.397 |
1.591 |
| 1.3878 |
3.0 |
471 |
1.6456 |
0.421 |
0.3666 |
0.4605 |
0.421 |
6.147 |
1.473 |
| 1.1967 |
4.0 |
628 |
1.7054 |
0.42 |
0.3790 |
0.3598 |
0.42 |
5.874 |
1.44 |
| 1.1002 |
5.0 |
785 |
1.7713 |
0.414 |
0.3896 |
0.3701 |
0.414 |
5.647 |
1.419 |
| 0.9412 |
6.0 |
942 |
1.8481 |
0.425 |
0.4068 |
0.4371 |
0.425 |
5.314 |
1.37 |
| 0.8737 |
7.0 |
1099 |
1.9534 |
0.407 |
0.4007 |
0.4025 |
0.407 |
5.141 |
1.375 |
| 0.757 |
8.0 |
1256 |
2.0153 |
0.401 |
0.3932 |
0.3918 |
0.401 |
5.227 |
1.385 |
| 0.6973 |
9.0 |
1413 |
2.0556 |
0.404 |
0.3979 |
0.4004 |
0.404 |
5.176 |
1.376 |
| 0.6573 |
10.0 |
1570 |
2.0672 |
0.408 |
0.4008 |
0.4003 |
0.408 |
5.179 |
1.373 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.20.3
