metadata
license: mit
base_model: khalidrajan/roberta-base_legal_ner_finetuned
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: roberta_crf_ner_finetuned
results: []
roberta_crf_ner_finetuned
This model is a fine-tuned version of khalidrajan/roberta-base_legal_ner_finetuned on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 45.0197
- Precision: 0.7445
- Recall: 0.7491
- F1: 0.7458
- Accuracy: 0.9569
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: 5e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 35.5086 | 1.0 | 340 | 47.8493 | 0.5897 | 0.6128 | 0.5997 | 0.9460 |
| 29.9206 | 2.0 | 680 | 44.2660 | 0.6897 | 0.7258 | 0.7067 | 0.9548 |
| 26.0727 | 3.0 | 1020 | 45.0197 | 0.7445 | 0.7491 | 0.7458 | 0.9569 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1