metadata
license: apache-2.0
base_model: google-bert/bert-base-multilingual-uncased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-base-multilingual-uncased-finetuned-ner-harem
results: []
bert-base-multilingual-uncased-finetuned-ner-harem
This model is a fine-tuned version of google-bert/bert-base-multilingual-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1861
- Precision: 0.7833
- Recall: 0.7589
- F1: 0.7709
- Accuracy: 0.9634
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: 100
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 282 | 0.2275 | 0.5847 | 0.6014 | 0.5929 | 0.9378 |
0.2687 | 2.0 | 564 | 0.1620 | 0.7389 | 0.6754 | 0.7057 | 0.9583 |
0.2687 | 3.0 | 846 | 0.1395 | 0.7820 | 0.7446 | 0.7628 | 0.9659 |
0.0845 | 4.0 | 1128 | 0.1694 | 0.7458 | 0.7351 | 0.7404 | 0.9586 |
0.0845 | 5.0 | 1410 | 0.1861 | 0.7833 | 0.7589 | 0.7709 | 0.9634 |
0.0398 | 6.0 | 1692 | 0.1821 | 0.7583 | 0.7637 | 0.7610 | 0.9639 |
0.0398 | 7.0 | 1974 | 0.2303 | 0.7789 | 0.7064 | 0.7409 | 0.9595 |
0.0203 | 8.0 | 2256 | 0.1912 | 0.7350 | 0.7876 | 0.7604 | 0.9629 |
0.0109 | 9.0 | 2538 | 0.2304 | 0.7524 | 0.7613 | 0.7568 | 0.9595 |
0.0109 | 10.0 | 2820 | 0.2457 | 0.7617 | 0.7399 | 0.7506 | 0.9622 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.19.1