metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: roberta-base-culinary
results: []
roberta-base-culinary
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1108
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 16
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.5688 | 1.0 | 39865 | 1.4449 |
| 1.4332 | 2.0 | 79730 | 1.3822 |
| 1.277 | 3.0 | 119595 | 1.3387 |
| 1.3483 | 4.0 | 159460 | 1.2833 |
| 1.2675 | 5.0 | 199325 | nan |
| 1.2381 | 6.0 | 239190 | 1.2546 |
| 1.1841 | 7.0 | 279055 | 1.2204 |
| 1.1608 | 8.0 | 318920 | 1.2095 |
| 1.2045 | 9.0 | 358785 | 1.1817 |
| 1.1401 | 10.0 | 398650 | 1.1810 |
| 1.0748 | 11.0 | 438515 | 1.1499 |
| 1.0857 | 12.0 | 478380 | 1.1345 |
| 1.0561 | 13.0 | 518245 | 1.1332 |
| 1.0431 | 14.0 | 558110 | 1.1127 |
| 1.0273 | 15.0 | 597975 | 1.1091 |
| 1.0275 | 16.0 | 637840 | 1.1108 |
Framework versions
- Transformers 4.22.1
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1