muril-ner-multilingual-v2
This model is a fine-tuned version of google/muril-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2213
- Precision: 0.7501
- Recall: 0.7872
- F1: 0.7682
- Accuracy: 0.9383
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: 3e-05
- train_batch_size: 16
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2128 | 1.0 | 6250 | 0.2208 | 0.7484 | 0.7707 | 0.7594 | 0.9361 |
| 0.1840 | 2.0 | 12500 | 0.2173 | 0.7375 | 0.7950 | 0.7652 | 0.9366 |
| 0.1435 | 3.0 | 18750 | 0.2213 | 0.7501 | 0.7872 | 0.7682 | 0.9383 |
Framework versions
- Transformers 5.14.1
- Pytorch 2.11.0+cu128
- Datasets 2.21.0
- Tokenizers 0.22.2