986d533cb08848aa75e297865af9e27f
This model is a fine-tuned version of FacebookAI/xlm-roberta-large-finetuned-conll02-dutch on the ccdv/patent-classification [abstract] dataset. It achieves the following results on the evaluation set:
- Loss: 1.9909
- Data Size: 0.25
- Epoch Runtime: 40.6864
- Accuracy: 0.2071
- F1 Macro: 0.0381
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 32
- total_eval_batch_size: 32
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Data Size | Epoch Runtime | Accuracy | F1 Macro |
|---|---|---|---|---|---|---|---|
| No log | 0 | 0 | 2.1965 | 0 | 7.7379 | 0.1270 | 0.0442 |
| No log | 1 | 781 | 2.0309 | 0.0078 | 9.0992 | 0.1689 | 0.0481 |
| No log | 2 | 1562 | 1.9483 | 0.0156 | 10.2724 | 0.2943 | 0.0965 |
| No log | 3 | 2343 | 2.0340 | 0.0312 | 12.8667 | 0.2071 | 0.0381 |
| 0.0459 | 4 | 3124 | 2.0041 | 0.0625 | 17.6166 | 0.2218 | 0.0403 |
| 2.0172 | 5 | 3905 | 1.9969 | 0.125 | 25.3419 | 0.2071 | 0.0381 |
| 2.0317 | 6 | 4686 | 1.9909 | 0.25 | 40.6864 | 0.2071 | 0.0381 |
Framework versions
- Transformers 4.57.0
- Pytorch 2.8.0+cu128
- Datasets 4.3.0
- Tokenizers 0.22.1
- Downloads last month
- 1