metadata
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: liar_binaryclassifier_roberta_base
results: []
liar_binaryclassifier_roberta_base
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6254
- Accuracy: 0.6768
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: 3e-06
- 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.689 | 1.0 | 461 | 0.6607 | 0.6269 |
| 0.6471 | 2.0 | 922 | 0.6379 | 0.6486 |
| 0.6125 | 3.0 | 1383 | 0.6207 | 0.6594 |
| 0.5813 | 4.0 | 1844 | 0.6269 | 0.6746 |
| 0.5634 | 5.0 | 2305 | 0.6254 | 0.6768 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1