<!-- 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 an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0894
- Overall Precision: 0.5187
- Overall Recall: 0.5814
- Overall F1: 0.5483
- Org Precision: 0.5127
- Org Recall: 0.5277
- Org F1: 0.5201
- Per Precision: 0.7294
- Per Recall: 0.8052
- Per F1: 0.7654
- Loc Precision: 0.4329
- Loc Recall: 0.7474
- Loc F1: 0.5483
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Overall Precision | Overall Recall | Overall F1 | Org Precision | Org Recall | Org F1 | Per Precision | Per Recall | Per F1 | Loc Precision | Loc Recall | Loc F1 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 53 | 0.1227 | 0.3066 | 0.3206 | 0.3134 | 0.3084 | 0.4104 | 0.3522 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| No log | 2.0 | 106 | 0.1055 | 0.3967 | 0.4224 | 0.4091 | 0.3829 | 0.3860 | 0.3844 | 0.6964 | 0.5065 | 0.5865 | 0.3457 | 0.5895 | 0.4358 |
| No log | 3.0 | 159 | 0.0897 | 0.4867 | 0.5598 | 0.5207 | 0.4883 | 0.5098 | 0.4988 | 0.7011 | 0.7922 | 0.7439 | 0.375 | 0.6947 | 0.4871 |
| No log | 4.0 | 212 | 0.0901 | 0.5179 | 0.5712 | 0.5433 | 0.5227 | 0.5261 | 0.5244 | 0.6988 | 0.7532 | 0.7250 | 0.4096 | 0.7158 | 0.5211 |
| No log | 5.0 | 265 | 0.0894 | 0.5187 | 0.5814 | 0.5483 | 0.5127 | 0.5277 | 0.5201 | 0.7294 | 0.8052 | 0.7654 | 0.4329 | 0.7474 | 0.5483 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
