<!-- 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. -->
roberta-base-bne-finetuned_personality_multi_4
This model is a fine-tuned version of BSC-TeMU/roberta-base-bne on the None dataset. It achieves the following results on the evaluation set:
- Loss: 4.1709
- Accuracy: 0.3470
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: 0.0001
- 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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.1759 | 1.0 | 125 | 2.1873 | 0.2548 |
| 1.8651 | 2.0 | 250 | 2.2285 | 0.2680 |
| 1.8619 | 3.0 | 375 | 2.1732 | 0.2951 |
| 1.7224 | 4.0 | 500 | 2.0688 | 0.3925 |
| 1.6432 | 5.0 | 625 | 2.1094 | 0.3735 |
| 1.3599 | 6.0 | 750 | 2.1732 | 0.3631 |
| 1.0623 | 7.0 | 875 | 2.4785 | 0.3579 |
| 1.0504 | 8.0 | 1000 | 2.4598 | 0.3844 |
| 0.7662 | 9.0 | 1125 | 2.8081 | 0.3573 |
| 0.9167 | 10.0 | 1250 | 2.9385 | 0.3452 |
| 0.6391 | 11.0 | 1375 | 2.9933 | 0.3320 |
| 0.3893 | 12.0 | 1500 | 3.1037 | 0.3579 |
| 0.673 | 13.0 | 1625 | 3.4369 | 0.3631 |
| 0.3498 | 14.0 | 1750 | 3.6396 | 0.3383 |
| 0.3891 | 15.0 | 1875 | 3.8332 | 0.3556 |
| 0.0818 | 16.0 | 2000 | 3.9451 | 0.3401 |
| 0.1438 | 17.0 | 2125 | 3.9271 | 0.3458 |
| 0.0634 | 18.0 | 2250 | 4.1564 | 0.3481 |
| 0.0121 | 19.0 | 2375 | 4.1405 | 0.3499 |
| 0.0071 | 20.0 | 2500 | 4.1709 | 0.3470 |
Framework versions
- Transformers 4.19.4
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1
