metadata
license: mit
tags:
- generated_from_trainer
model-index:
- name: roberta-base-academic
results: []
roberta-base-academic
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4621
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: 32
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.99) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.668 | 1.0 | 169 | 1.5412 |
| 1.6261 | 2.0 | 338 | 1.5138 |
| 1.5967 | 3.0 | 507 | 1.4943 |
| 1.5745 | 4.0 | 676 | 1.4913 |
| 1.5549 | 5.0 | 845 | 1.4738 |
| 1.5445 | 6.0 | 1014 | 1.4671 |
| 1.536 | 7.0 | 1183 | 1.4689 |
| 1.5254 | 8.0 | 1352 | 1.4612 |
| 1.5244 | 9.0 | 1521 | 1.4560 |
| 1.5263 | 10.0 | 1690 | 1.4580 |
| 1.5249 | 11.0 | 1859 | 1.4482 |
| 1.5238 | 12.0 | 2028 | 1.4565 |
| 1.526 | 13.0 | 2197 | 1.4568 |
| 1.5232 | 14.0 | 2366 | 1.4547 |
| 1.5232 | 15.0 | 2535 | 1.4558 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2