N_roberta_imdb_padding60model
This model is a fine-tuned version of roberta-base on the imdb dataset. It achieves the following results on the evaluation set:
- Loss: 0.4811
- Accuracy: 0.9500
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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.2157 | 1.0 | 1563 | 0.2020 | 0.9366 |
| 0.1716 | 2.0 | 3126 | 0.1757 | 0.9467 |
| 0.1135 | 3.0 | 4689 | 0.2601 | 0.9442 |
| 0.0834 | 4.0 | 6252 | 0.2498 | 0.9485 |
| 0.0533 | 5.0 | 7815 | 0.3480 | 0.9452 |
| 0.0441 | 6.0 | 9378 | 0.3548 | 0.9371 |
| 0.0319 | 7.0 | 10941 | 0.3257 | 0.9474 |
| 0.0264 | 8.0 | 12504 | 0.3932 | 0.9457 |
| 0.0239 | 9.0 | 14067 | 0.3367 | 0.9469 |
| 0.0185 | 10.0 | 15630 | 0.4500 | 0.94 |
| 0.018 | 11.0 | 17193 | 0.3871 | 0.9470 |
| 0.0153 | 12.0 | 18756 | 0.4206 | 0.9456 |
| 0.0101 | 13.0 | 20319 | 0.4027 | 0.9492 |
| 0.005 | 14.0 | 21882 | 0.4701 | 0.9477 |
| 0.0051 | 15.0 | 23445 | 0.4454 | 0.9484 |
| 0.0013 | 16.0 | 25008 | 0.5015 | 0.9493 |
| 0.007 | 17.0 | 26571 | 0.5011 | 0.9476 |
| 0.0022 | 18.0 | 28134 | 0.4798 | 0.95 |
| 0.0047 | 19.0 | 29697 | 0.4794 | 0.9498 |
| 0.0014 | 20.0 | 31260 | 0.4811 | 0.9500 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3