<!-- 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-base-cased-ner
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: 0.3793
- Job Title precision: 0.8079
- Job Title recall: 0.8248
- Job Title f1: 0.8163
- Loc precision: 0.8911
- Loc recall: 0.9081
- Loc f1: 0.8995
- Org precision: 0.6484
- Org recall: 0.7620
- Org f1: 0.7006
- Misc precision: 0.6134
- Misc recall: 0.7201
- Misc f1: 0.6625
- Precision: 0.7800
- Recall: 0.8265
- F1: 0.8025
- Accuracy: 0.8606
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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Job Title precision | Job Title recall | Job Title f1 | Loc precision | Loc recall | Loc f1 | Org precision | Org recall | Org f1 | Misc precision | Misc recall | Misc f1 | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
No log | 1.0 | 308 | 0.3793 | 0.8079 | 0.8248 | 0.8163 | 0.8911 | 0.9081 | 0.8995 | 0.6484 | 0.7620 | 0.7006 | 0.6134 | 0.7201 | 0.6625 | 0.7800 | 0.8265 | 0.8025 | 0.8606 |
0.4249 | 2.0 | 616 | 0.3866 | 0.7911 | 0.8728 | 0.8299 | 0.8676 | 0.9541 | 0.9088 | 0.6551 | 0.7886 | 0.7157 | 0.6623 | 0.6962 | 0.6789 | 0.7719 | 0.8669 | 0.8167 | 0.8685 |
Framework versions
- Transformers 4.28.1
- Pytorch 1.7.1+cu110
- Datasets 2.12.0
- Tokenizers 0.13.2