<!-- 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. -->
unsupervised-fine-tune-bert-exist
This model is a fine-tuned version of nouman-10/unsupervised-exist on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.6972
- Accuracy: 0.75
- F1: 0.7514
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 | 0.4714 | 0.7791 | 0.7901 |
No log | 2.0 | 388 | 0.5372 | 0.7587 | 0.7608 |
0.404 | 3.0 | 582 | 0.7204 | 0.7645 | 0.7652 |
0.404 | 4.0 | 776 | 1.1071 | 0.7645 | 0.7652 |
0.404 | 5.0 | 970 | 1.3216 | 0.7471 | 0.7387 |
0.0917 | 6.0 | 1164 | 1.4910 | 0.7529 | 0.7416 |
0.0917 | 7.0 | 1358 | 1.5978 | 0.7413 | 0.7295 |
0.0122 | 8.0 | 1552 | 1.6713 | 0.7471 | 0.7478 |
0.0122 | 9.0 | 1746 | 1.6915 | 0.7442 | 0.7427 |
0.0122 | 10.0 | 1940 | 1.6972 | 0.75 | 0.7514 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2