metadata
license: mit
base_model: dslim/bert-large-NER
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-NER
results: []
bert-NER
This model is a fine-tuned version of dslim/bert-large-NER on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3706
- Precision: 0.5564
- Recall: 0.6510
- F1: 0.6
- Accuracy: 0.9117
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: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.4407 | 1.0 | 746 | 0.3447 | 0.4835 | 0.5572 | 0.5177 | 0.8881 |
0.245 | 2.0 | 1492 | 0.3399 | 0.5439 | 0.5630 | 0.5533 | 0.9014 |
0.0865 | 3.0 | 2238 | 0.3706 | 0.5564 | 0.6510 | 0.6 | 0.9117 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1