roberta-base-university-writing2
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.5392
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.99) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.8142 | 0.99 | 82 | 1.6699 |
| 1.755 | 1.99 | 164 | 1.6330 |
| 1.7135 | 2.99 | 246 | 1.6195 |
| 1.6895 | 3.99 | 328 | 1.6024 |
| 1.6622 | 4.99 | 410 | 1.5921 |
| 1.644 | 5.99 | 492 | 1.5745 |
| 1.6321 | 6.99 | 574 | 1.5762 |
| 1.6194 | 7.99 | 656 | 1.5857 |
| 1.606 | 8.99 | 738 | 1.5607 |
| 1.5931 | 9.99 | 820 | 1.5649 |
| 1.5846 | 10.99 | 902 | 1.5547 |
| 1.5753 | 11.99 | 984 | 1.5451 |
| 1.5691 | 12.99 | 1066 | 1.5355 |
| 1.5645 | 13.99 | 1148 | 1.5409 |
| 1.5521 | 14.99 | 1230 | 1.5207 |
| 1.5471 | 15.99 | 1312 | 1.5367 |
| 1.5463 | 16.99 | 1394 | 1.5476 |
| 1.5412 | 17.99 | 1476 | 1.5065 |
| 1.5409 | 18.99 | 1558 | 1.5333 |
| 1.5331 | 19.99 | 1640 | 1.5123 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2
- Downloads last month
- 2