<!-- 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. -->
generic_ner_model
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0992
- Precision: 0.8749
- Recall: 0.8980
- F1: 0.8863
- Accuracy: 0.9746
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: 16
- eval_batch_size: 16
- 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 |
---|---|---|---|---|---|---|---|
0.1084 | 1.0 | 1958 | 0.1001 | 0.8639 | 0.8822 | 0.8730 | 0.9722 |
0.0681 | 2.0 | 3916 | 0.0971 | 0.8699 | 0.8955 | 0.8825 | 0.9740 |
0.0471 | 3.0 | 5874 | 0.0992 | 0.8749 | 0.8980 | 0.8863 | 0.9746 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3