metadata
license: mit
base_model: dslim/bert-base-NER
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-finetuned-ner
results: []
bert-finetuned-ner
This model is a fine-tuned version of dslim/bert-base-NER on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1297
- Precision: 0.8328
- Recall: 0.3864
- F1: 0.3321
- Accuracy: 0.8676
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 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 51 | 0.1687 | 0.6907 | 0.2347 | 0.2279 | 0.8456 |
| No log | 2.0 | 102 | 0.1344 | 0.8467 | 0.3308 | 0.2812 | 0.8603 |
| No log | 3.0 | 153 | 0.1297 | 0.8328 | 0.3864 | 0.3321 | 0.8676 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1