<!-- 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-cased-combined
This model is a fine-tuned version of nouman-10/unsupervised-comb-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.4579
- Accuracy: 0.7384
- F1: 0.7384
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 |
---|---|---|---|---|---|
0.4463 | 1.0 | 1819 | 0.7093 | 0.6483 | 0.6483 |
0.3304 | 2.0 | 3638 | 0.5988 | 0.7471 | 0.7471 |
0.211 | 3.0 | 5457 | 0.8888 | 0.75 | 0.75 |
0.1237 | 4.0 | 7276 | 1.4573 | 0.7355 | 0.7355 |
0.0959 | 5.0 | 9095 | 1.7000 | 0.7355 | 0.7355 |
0.062 | 6.0 | 10914 | 2.0796 | 0.7064 | 0.7064 |
0.0347 | 7.0 | 12733 | 1.7562 | 0.7558 | 0.7558 |
0.0259 | 8.0 | 14552 | 2.3160 | 0.7267 | 0.7267 |
0.0166 | 9.0 | 16371 | 2.3301 | 0.7471 | 0.7471 |
0.0091 | 10.0 | 18190 | 2.4579 | 0.7384 | 0.7384 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2