metadata
license: apache-2.0
base_model: bert-base-cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert_finetuned_ner_a
results: []
bert_finetuned_ner_a
This model is a fine-tuned version of bert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0827
- Precision: 0.9363
- Recall: 0.9541
- F1: 0.9451
- Accuracy: 0.9843
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: 8
- 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 |
|---|---|---|---|---|---|---|---|
| 0.0371 | 1.0 | 32820 | 0.0475 | 0.9322 | 0.9416 | 0.9369 | 0.9836 |
| 0.016 | 2.0 | 65640 | 0.0666 | 0.9414 | 0.9458 | 0.9436 | 0.9841 |
| 0.0051 | 3.0 | 98460 | 0.0827 | 0.9363 | 0.9541 | 0.9451 | 0.9843 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0