metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: edos-2023-baseline-bert-base-multilingual-uncased-label_sexist
results: []
edos-2023-baseline-bert-base-multilingual-uncased-label_sexist
This model is a fine-tuned version of bert-base-multilingual-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3753
- F1: 0.7713
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: 64
- eval_batch_size: 64
- 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 |
|---|---|---|---|---|
| 0.4679 | 1.14 | 400 | 0.4074 | 0.7437 |
| 0.3421 | 2.29 | 800 | 0.3773 | 0.7755 |
| 0.3142 | 3.43 | 1200 | 0.3664 | 0.7747 |
| 0.2786 | 4.57 | 1600 | 0.3753 | 0.7713 |
| 0.275 | 5.71 | 2000 | 0.3753 | 0.7713 |
| 0.2785 | 6.86 | 2400 | 0.3753 | 0.7713 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2