xlm-roberta-base-finetuned-m_avoid_harm_seler
This model is a fine-tuned version of FacebookAI/xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5754
- Accuracy: 0.725
- F1: 0.8120
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: 2e-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
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
---|---|---|---|---|---|
0.7371 | 1.0 | 26 | 0.6372 | 0.965 | 0.9478 |
0.6778 | 2.0 | 52 | 0.6466 | 0.74 | 0.8221 |
0.655 | 3.0 | 78 | 0.6079 | 0.69 | 0.7871 |
0.5883 | 4.0 | 104 | 0.5863 | 0.77 | 0.8415 |
0.5832 | 5.0 | 130 | 0.5754 | 0.725 | 0.8120 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Tokenizers 0.19.1
- Downloads last month
- 3