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: 0.6339
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: 0.003
- 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: 500
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6338 | 1.0 | 50 | 0.6428 |
| 0.6921 | 2.0 | 100 | 0.6613 |
| 0.6453 | 3.0 | 150 | 0.6626 |
| 0.6368 | 4.0 | 200 | 0.6847 |
| 0.6039 | 5.0 | 250 | 0.6969 |
| 0.7043 | 6.0 | 300 | 0.6464 |
| 0.6971 | 7.0 | 350 | 0.6339 |
| 0.6376 | 8.0 | 400 | 0.6956 |
| 0.6976 | 9.0 | 450 | 0.6344 |
| 0.623 | 10.0 | 500 | 0.6493 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2