metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: fine-tuned-bert-base-multilingual-uncased-NED_latest
results: []
fine-tuned-bert-base-multilingual-uncased-NED_latest
This model is a fine-tuned version of bert-base-multilingual-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1376
- Accuracy: 0.9687
- Precision: 0.9761
- Recall: 0.9764
- F1: 0.9762
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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.157 | 1.0 | 56232 | 0.1271 | 0.9658 | 0.9740 | 0.9741 | 0.9740 |
| 0.144 | 2.0 | 112464 | 0.1549 | 0.9665 | 0.9693 | 0.9802 | 0.9747 |
| 0.1439 | 3.0 | 168696 | 0.1600 | 0.9660 | 0.9701 | 0.9786 | 0.9743 |
| 0.1267 | 4.0 | 224928 | 0.1376 | 0.9687 | 0.9761 | 0.9764 | 0.9762 |
Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1