metadata
license: apache-2.0
base_model: distilbert/distilbert-base-multilingual-cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: distilbert-base-multilingual-cased-finetuned-ner-harem
results: []
distilbert-base-multilingual-cased-finetuned-ner-harem
This model is a fine-tuned version of distilbert/distilbert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1929
- Precision: 0.7319
- Recall: 0.7531
- F1: 0.7423
- Accuracy: 0.9587
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 282 | 0.2132 | 0.5566 | 0.6224 | 0.5877 | 0.9403 |
| 0.28 | 2.0 | 564 | 0.1715 | 0.6793 | 0.7075 | 0.6931 | 0.9533 |
| 0.28 | 3.0 | 846 | 0.1507 | 0.7101 | 0.7469 | 0.7280 | 0.9586 |
| 0.0882 | 4.0 | 1128 | 0.1662 | 0.7368 | 0.7261 | 0.7315 | 0.9568 |
| 0.0882 | 5.0 | 1410 | 0.1718 | 0.7387 | 0.7448 | 0.7417 | 0.9579 |
| 0.0386 | 6.0 | 1692 | 0.1823 | 0.7078 | 0.7490 | 0.7278 | 0.9576 |
| 0.0386 | 7.0 | 1974 | 0.1969 | 0.7206 | 0.7490 | 0.7345 | 0.9574 |
| 0.0187 | 8.0 | 2256 | 0.1816 | 0.7349 | 0.7593 | 0.7469 | 0.9589 |
| 0.0101 | 9.0 | 2538 | 0.1928 | 0.7363 | 0.7531 | 0.7446 | 0.9584 |
| 0.0101 | 10.0 | 2820 | 0.1929 | 0.7319 | 0.7531 | 0.7423 | 0.9587 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.19.1