openalex-topic-classification-title-abstract
This model is a fine-tuned version of google-bert/bert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.1286
- Accuracy: 0.5287
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: 128
- eval_batch_size: 128
- 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: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 4.7089 | 1.0 | 26376 | 4.6094 | 0.1920 |
| 2.9397 | 2.0 | 52752 | 2.8504 | 0.4195 |
| 2.444 | 3.0 | 79128 | 2.4296 | 0.4763 |
| 2.1399 | 4.0 | 105504 | 2.2586 | 0.5015 |
| 1.9042 | 5.0 | 131880 | 2.1800 | 0.5144 |
| 1.7293 | 6.0 | 158256 | 2.1372 | 0.5227 |
| 1.5672 | 7.0 | 184632 | 2.1298 | 0.5260 |
| 1.4574 | 8.0 | 211008 | 2.1245 | 0.5281 |
| 1.3737 | 9.0 | 237384 | 2.1277 | 0.5285 |
| 1.3748 | 10.0 | 263760 | 2.1286 | 0.5287 |
Framework versions
- Transformers 4.49.0.dev0
- Pytorch 2.6.0+cu118
- Datasets 2.19.2
- Tokenizers 0.21.0