<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
fine-tune-bert-sem-exist
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: 2.5349
- Accuracy: 0.7180
- F1: 0.6799
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 | F1 |
---|---|---|---|---|---|
0.3891 | 1.0 | 1194 | 0.5836 | 0.75 | 0.7410 |
0.2899 | 2.0 | 2388 | 0.7013 | 0.7297 | 0.7010 |
0.1772 | 3.0 | 3582 | 1.1096 | 0.7006 | 0.6508 |
0.1075 | 4.0 | 4776 | 1.2577 | 0.7326 | 0.6974 |
0.0609 | 5.0 | 5970 | 1.7651 | 0.7093 | 0.6575 |
0.0372 | 6.0 | 7164 | 2.0735 | 0.7180 | 0.6820 |
0.0221 | 7.0 | 8358 | 2.3200 | 0.7238 | 0.6926 |
0.0187 | 8.0 | 9552 | 2.3803 | 0.7209 | 0.6821 |
0.0115 | 9.0 | 10746 | 2.4671 | 0.7122 | 0.6711 |
0.0061 | 10.0 | 11940 | 2.5349 | 0.7180 | 0.6799 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2