<!-- 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-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: 1.7208
- Accuracy: 0.7674
- F1: 0.7661
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 |
---|---|---|---|---|---|
No log | 1.0 | 194 | 0.4802 | 0.7733 | 0.7809 |
No log | 2.0 | 388 | 0.5412 | 0.7616 | 0.7574 |
0.4228 | 3.0 | 582 | 0.7123 | 0.7529 | 0.7522 |
0.4228 | 4.0 | 776 | 0.9978 | 0.7762 | 0.7688 |
0.4228 | 5.0 | 970 | 1.3603 | 0.7645 | 0.7523 |
0.0917 | 6.0 | 1164 | 1.5289 | 0.7558 | 0.7342 |
0.0917 | 7.0 | 1358 | 1.6091 | 0.7645 | 0.7756 |
0.0172 | 8.0 | 1552 | 1.6438 | 0.7703 | 0.7762 |
0.0172 | 9.0 | 1746 | 1.7051 | 0.7587 | 0.7537 |
0.0172 | 10.0 | 1940 | 1.7208 | 0.7674 | 0.7661 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2