<!-- 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. -->
greek_legal_bert_v2-finetuned-ner-V3
This model is a fine-tuned version of alexaapo/greek_legal_bert_v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0907
- Precision: 0.9023
- Recall: 0.9265
- F1: 0.9142
- Accuracy: 0.9828
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.19 | 25 | 0.0661 | 0.8895 | 0.9229 | 0.9059 | 0.9813 |
| No log | 2.38 | 50 | 0.0820 | 0.9091 | 0.9319 | 0.9204 | 0.9838 |
| No log | 3.57 | 75 | 0.0791 | 0.8924 | 0.9211 | 0.9065 | 0.9825 |
| No log | 4.76 | 100 | 0.0824 | 0.8950 | 0.9319 | 0.9131 | 0.9841 |
| No log | 5.95 | 125 | 0.0820 | 0.8830 | 0.9194 | 0.9008 | 0.9812 |
| No log | 7.14 | 150 | 0.0862 | 0.9059 | 0.9319 | 0.9187 | 0.9817 |
| No log | 8.33 | 175 | 0.0915 | 0.9021 | 0.9247 | 0.9133 | 0.9826 |
| No log | 9.52 | 200 | 0.0905 | 0.9023 | 0.9265 | 0.9142 | 0.9828 |
Framework versions
- Transformers 4.23.0
- Pytorch 1.12.1+cu113
- Datasets 2.5.2
- Tokenizers 0.13.1
