bert-multilingual-sdg-classification
This model is a fine-tuned version of google-bert/bert-base-multilingual-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7207
- F1: 0.7925
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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 600
- num_epochs: 5.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 2.1122 | 1.0 | 538 | 1.0625 | 0.6814 |
| 0.9564 | 2.0 | 1076 | 0.8073 | 0.7686 |
| 0.7652 | 3.0 | 1614 | 0.7433 | 0.7886 |
| 0.6619 | 4.0 | 2152 | 0.7261 | 0.7919 |
| 0.6038 | 5.0 | 2690 | 0.7207 | 0.7925 |
Framework versions
- Transformers 4.49.0.dev0
- Pytorch 2.1.2.post304
- Datasets 3.2.0
- Tokenizers 0.21.0