metadata
library_name: transformers
license: afl-3.0
base_model: Davlan/distilbert-base-multilingual-cased-ner-hrl
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: exp1
results: []
exp1
This model is a fine-tuned version of Davlan/distilbert-base-multilingual-cased-ner-hrl on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0695
- Precision: 0.9266
- Recall: 0.9478
- F1: 0.9371
- Accuracy: 0.9838
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0981 | 1.0 | 11771 | 0.0893 | 0.8784 | 0.9084 | 0.8932 | 0.9656 |
| 0.0752 | 2.0 | 23542 | 0.0737 | 0.8950 | 0.9317 | 0.9129 | 0.9740 |
| 0.0587 | 3.0 | 35313 | 0.0671 | 0.9067 | 0.9383 | 0.9222 | 0.9780 |
| 0.0444 | 4.0 | 47084 | 0.0684 | 0.9099 | 0.9462 | 0.9277 | 0.9802 |
| 0.0336 | 5.0 | 58855 | 0.0675 | 0.9257 | 0.9428 | 0.9342 | 0.9828 |
| 0.023 | 6.0 | 70626 | 0.0683 | 0.9218 | 0.9471 | 0.9343 | 0.9833 |
| 0.0216 | 7.0 | 82397 | 0.0695 | 0.9266 | 0.9478 | 0.9371 | 0.9838 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1