metadata
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
model-index:
- name: roberta-base_correlation
results: []
roberta-base_correlation
This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4129
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: 1e-05
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 5000
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6673 | 1.0 | 50 | 0.6690 |
| 0.6707 | 2.0 | 100 | 0.6668 |
| 0.6593 | 3.0 | 150 | 0.6631 |
| 0.6597 | 4.0 | 200 | 0.6583 |
| 0.6476 | 5.0 | 250 | 0.6536 |
| 0.6511 | 6.0 | 300 | 0.6487 |
| 0.6342 | 7.0 | 350 | 0.6459 |
| 0.6408 | 8.0 | 400 | 0.6427 |
| 0.6318 | 9.0 | 450 | 0.6405 |
| 0.6556 | 10.0 | 500 | 0.6372 |
| 0.6141 | 11.0 | 550 | 0.6289 |
| 0.59 | 12.0 | 600 | 0.6089 |
| 0.5781 | 13.0 | 650 | 0.5815 |
| 0.5529 | 14.0 | 700 | 0.5550 |
| 0.5367 | 15.0 | 750 | 0.5355 |
| 0.5107 | 16.0 | 800 | 0.5014 |
| 0.4441 | 17.0 | 850 | 0.4775 |
| 0.4206 | 18.0 | 900 | 0.4477 |
| 0.3608 | 19.0 | 950 | 0.4302 |
| 0.3241 | 20.0 | 1000 | 0.4129 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2