metadata
license: mit
tags:
- generated_from_trainer
metrics:
- f1
base_model: roberta-base
model-index:
- name: edos-2023-baseline-roberta-base-label_sexist
results: []
edos-2023-baseline-roberta-base-label_sexist
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4729
- F1: 0.8048
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: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 5
- num_epochs: 8
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.4114 | 1.14 | 400 | 0.3516 | 0.7954 |
| 0.2725 | 2.29 | 800 | 0.4086 | 0.7925 |
| 0.2134 | 3.43 | 1200 | 0.4404 | 0.8062 |
| 0.1632 | 4.57 | 1600 | 0.4729 | 0.8048 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2