metadata
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
model-index:
- name: fire_or_not
results: []
fire_or_not
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5768
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
- 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 |
|---|---|---|---|
| 0.4667 | 1.0 | 343 | 0.5833 |
| 0.7134 | 2.0 | 686 | 0.5768 |
| 0.3713 | 3.0 | 1029 | 0.6627 |
| 0.2676 | 4.0 | 1372 | 0.5839 |
| 0.5337 | 5.0 | 1715 | 0.9343 |
| 0.2096 | 6.0 | 2058 | 0.8992 |
| 0.0586 | 7.0 | 2401 | 0.9487 |
| 0.0483 | 8.0 | 2744 | 1.0178 |
| 0.0565 | 9.0 | 3087 | 1.0771 |
| 0.1489 | 10.0 | 3430 | 1.0715 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2