<!-- 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. -->
klue-roberta-large-klue-2016klp-crime1-ner
This model is a fine-tuned version of soddokayo/klue-roberta-large-klue-2016klp-ner on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2425
- Precision: 0.9392
- Recall: 0.9444
- F1: 0.9418
- Accuracy: 0.9517
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 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 23 | 0.9424 | 0.6486 | 0.6667 | 0.6575 | 0.7183 |
| No log | 2.0 | 46 | 0.6026 | 0.7098 | 0.7611 | 0.7346 | 0.8410 |
| No log | 3.0 | 69 | 0.4010 | 0.8703 | 0.8944 | 0.8822 | 0.9235 |
| No log | 4.0 | 92 | 0.2797 | 0.9066 | 0.9167 | 0.9116 | 0.9416 |
| No log | 5.0 | 115 | 0.2845 | 0.9227 | 0.9278 | 0.9252 | 0.9457 |
| No log | 6.0 | 138 | 0.2425 | 0.9392 | 0.9444 | 0.9418 | 0.9517 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cpu
- Datasets 2.12.0
- Tokenizers 0.11.0
