<!-- 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-V4
This model is a fine-tuned version of amichailidis/greek_legal_bert_v2-finetuned-ner on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0659
- Precision: 0.9033
- Recall: 0.9373
- F1: 0.9200
- Accuracy: 0.9845
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 | 0.1246 | 0.8264 | 0.8190 | 0.8227 | 0.9680 |
No log | 2.38 | 50 | 0.0729 | 0.8716 | 0.9247 | 0.8974 | 0.9809 |
No log | 3.57 | 75 | 0.0553 | 0.8978 | 0.9444 | 0.9205 | 0.9851 |
No log | 4.76 | 100 | 0.0591 | 0.8990 | 0.9409 | 0.9194 | 0.9852 |
No log | 5.95 | 125 | 0.0598 | 0.9017 | 0.9373 | 0.9192 | 0.9849 |
No log | 7.14 | 150 | 0.0628 | 0.9064 | 0.9373 | 0.9216 | 0.9842 |
No log | 8.33 | 175 | 0.0636 | 0.9031 | 0.9355 | 0.9190 | 0.9843 |
No log | 9.52 | 200 | 0.0659 | 0.9033 | 0.9373 | 0.9200 | 0.9845 |
Framework versions
- Transformers 4.23.0
- Pytorch 1.12.1+cu113
- Datasets 2.5.2
- Tokenizers 0.13.1