metadata
license: mit
base_model: roberta-large
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: FakeNews-roberta-large-grad
results: []
FakeNews-roberta-large-grad
This model is a fine-tuned version of roberta-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6921
- Accuracy: 0.5234
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- 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 |
|---|---|---|---|---|
| 0.3917 | 1.0 | 802 | 0.7031 | 0.5234 |
| 0.7167 | 2.0 | 1605 | 0.7046 | 0.5234 |
| 0.7011 | 3.0 | 2407 | 0.6921 | 0.5234 |
| 0.6973 | 4.0 | 3210 | 1.0022 | 0.4766 |
| 0.6865 | 5.0 | 4010 | 0.7125 | 0.4766 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1