<!-- 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-80percent
This model is a fine-tuned version of bert-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5462
- Precision: 0.8116
- Recall: 0.8408
- F1: 0.8260
- Accuracy: 0.9238
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: 2022
- 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 | 60 | 0.5514 | 0.7966 | 0.8348 | 0.8152 | 0.9170 |
No log | 2.0 | 120 | 0.5718 | 0.8020 | 0.8333 | 0.8174 | 0.9184 |
No log | 3.0 | 180 | 0.5462 | 0.8116 | 0.8408 | 0.8260 | 0.9238 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.2