metadata
base_model: mor40/BulBERT-chitanka-model
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: BulBERT-ner-wikiann
results: []
BulBERT-ner-wikiann
This model is a fine-tuned version of mor40/BulBERT-chitanka-model on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2787
- Precision: 0.8050
- Recall: 0.8556
- F1: 0.8296
- Accuracy: 0.9446
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2436 | 1.0 | 2030 | 0.2391 | 0.7289 | 0.8071 | 0.7660 | 0.9284 |
| 0.1601 | 2.0 | 4060 | 0.2230 | 0.7698 | 0.8328 | 0.8001 | 0.9380 |
| 0.102 | 3.0 | 6090 | 0.2441 | 0.7962 | 0.8444 | 0.8196 | 0.9431 |
| 0.0707 | 4.0 | 8120 | 0.2643 | 0.7998 | 0.8533 | 0.8257 | 0.9444 |
| 0.0542 | 5.0 | 10150 | 0.2787 | 0.8050 | 0.8556 | 0.8296 | 0.9446 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1