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: 0.1966
- Precision: 0.6438
- Recall: 0.6483
- F1: 0.6460
- Accuracy: 0.9478
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 |
---|---|---|---|---|---|---|---|
0.4628 | 1.0 | 551 | 0.2481 | 0.5940 | 0.5448 | 0.5683 | 0.9326 |
0.2106 | 2.0 | 1102 | 0.1833 | 0.6486 | 0.6621 | 0.6553 | 0.9433 |
0.1434 | 3.0 | 1653 | 0.1966 | 0.6438 | 0.6483 | 0.6460 | 0.9478 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1