metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: finetuned_distilbert_fa_zwnj_base_ner
results: []
finetuned_distilbert_fa_zwnj_base_ner
This model is a fine-tuned version of HooshvareLab/distilbert-fa-zwnj-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0655
- Precision: 0.7831
- Recall: 0.8436
- F1: 0.8122
- Accuracy: 0.9807
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 |
|---|---|---|---|---|---|---|---|
| 0.332 | 1.0 | 1821 | 0.1963 | 0.3958 | 0.5123 | 0.4466 | 0.9382 |
| 0.1716 | 2.0 | 3642 | 0.1287 | 0.5640 | 0.6490 | 0.6035 | 0.9579 |
| 0.1037 | 3.0 | 5463 | 0.0911 | 0.6542 | 0.7514 | 0.6995 | 0.9697 |
| 0.0644 | 4.0 | 7284 | 0.0736 | 0.7380 | 0.8155 | 0.7749 | 0.9768 |
| 0.0408 | 5.0 | 9105 | 0.0655 | 0.7831 | 0.8436 | 0.8122 | 0.9807 |
Framework versions
- Transformers 4.21.2
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1