<!-- 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-roberta-exist
This model is a fine-tuned version of nouman-10/unsupervised-exist-rb on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.9911
- Accuracy: 0.7238
- F1: 0.7262
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 | 0.5147 | 0.7471 | 0.7434 |
| No log | 2.0 | 388 | 0.5395 | 0.7384 | 0.7458 |
| 0.4616 | 3.0 | 582 | 0.6484 | 0.75 | 0.7440 |
| 0.4616 | 4.0 | 776 | 0.9610 | 0.7355 | 0.7407 |
| 0.4616 | 5.0 | 970 | 1.2414 | 0.7326 | 0.7262 |
| 0.1786 | 6.0 | 1164 | 1.7050 | 0.7209 | 0.7209 |
| 0.1786 | 7.0 | 1358 | 1.7930 | 0.7384 | 0.7273 |
| 0.0557 | 8.0 | 1552 | 1.8999 | 0.7355 | 0.7378 |
| 0.0557 | 9.0 | 1746 | 1.9886 | 0.7209 | 0.7225 |
| 0.0557 | 10.0 | 1940 | 1.9911 | 0.7238 | 0.7262 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2
