metadata
library_name: transformers
license: mit
base_model: akdeniz27/bert-base-turkish-cased-ner
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-base-turkish-cased-ner-finetuned-ner
results: []
bert-base-turkish-cased-ner-finetuned-ner
This model is a fine-tuned version of akdeniz27/bert-base-turkish-cased-ner on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1768
- Precision: 0.9689
- Recall: 0.9688
- F1: 0.9688
- Accuracy: 0.9711
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: 1e-05
- train_batch_size: 6
- eval_batch_size: 6
- 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 | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1616 | 1.0 | 3334 | 0.1414 | 0.9622 | 0.9624 | 0.9623 | 0.9651 |
| 0.1143 | 2.0 | 6668 | 0.1483 | 0.9667 | 0.9672 | 0.9670 | 0.9694 |
| 0.0957 | 3.0 | 10002 | 0.1531 | 0.9680 | 0.9682 | 0.9681 | 0.9705 |
| 0.0488 | 4.0 | 13336 | 0.1720 | 0.9690 | 0.9688 | 0.9689 | 0.9713 |
| 0.03 | 5.0 | 16670 | 0.1768 | 0.9689 | 0.9688 | 0.9688 | 0.9711 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1