metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: finetuned_parsBERT_NER_fa
results: []
finetuned_parsBERT_NER_fa
This model is a fine-tuned version of HooshvareLab/bert-fa-zwnj-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0293
- Precision: 0.9435
- Recall: 0.9568
- F1: 0.9501
- Accuracy: 0.9941
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: 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1202 | 1.0 | 1821 | 0.0528 | 0.8209 | 0.8587 | 0.8394 | 0.9831 |
| 0.0383 | 2.0 | 3642 | 0.0348 | 0.9060 | 0.9189 | 0.9124 | 0.9899 |
| 0.0168 | 3.0 | 5463 | 0.0278 | 0.9249 | 0.9420 | 0.9334 | 0.9923 |
| 0.0077 | 4.0 | 7284 | 0.0274 | 0.9354 | 0.9517 | 0.9435 | 0.9936 |
| 0.0037 | 5.0 | 9105 | 0.0293 | 0.9435 | 0.9568 | 0.9501 | 0.9941 |
Framework versions
- Transformers 4.21.2
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1