<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
bert-finetuned-ner-a1-a2-a3-a4-tok-1k-10k-e6-v1
This model is a fine-tuned version of dslim/bert-large-NER on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0073
- Precision: 0.8372
- Recall: 0.9506
- F1: 0.8903
- Accuracy: 0.9976
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: 6
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.008 | 1.0 | 1125 | 0.0076 | 0.8349 | 0.9253 | 0.8778 | 0.9973 |
0.0052 | 2.0 | 2250 | 0.0069 | 0.8300 | 0.9292 | 0.8768 | 0.9973 |
0.0038 | 3.0 | 3375 | 0.0071 | 0.8267 | 0.9397 | 0.8796 | 0.9973 |
0.0033 | 4.0 | 4500 | 0.0068 | 0.8322 | 0.9498 | 0.8871 | 0.9976 |
0.0023 | 5.0 | 5625 | 0.0066 | 0.8362 | 0.9478 | 0.8885 | 0.9976 |
0.002 | 6.0 | 6750 | 0.0073 | 0.8372 | 0.9506 | 0.8903 | 0.9976 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3