Persian NLP
Collection
6 items
•
Updated
•
2
This model is a fine-tuned version of HooshvareLab/bert-base-parsbert-uncased on a custom dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1-score | Accuracy |
---|---|---|---|---|---|---|---|
0.3097 | 1.0 | 3491 | 0.3265 | 0.8727 | 0.8716 | 0.8715 | 0.8716 |
0.2686 | 2.0 | 6982 | 0.3602 | 0.8785 | 0.8758 | 0.8756 | 0.8758 |
0.2137 | 3.0 | 10473 | 0.3828 | 0.8759 | 0.8724 | 0.8721 | 0.8724 |
0.1823 | 4.0 | 13964 | 0.5545 | 0.8637 | 0.8636 | 0.8636 | 0.8636 |
0.1346 | 5.0 | 17455 | 0.6295 | 0.8572 | 0.8566 | 0.8566 | 0.8566 |
0.1001 | 6.0 | 20946 | 0.8501 | 0.8606 | 0.8604 | 0.8604 | 0.8604 |
0.071 | 7.0 | 24437 | 1.0192 | 0.8596 | 0.8594 | 0.8594 | 0.8594 |
0.0604 | 8.0 | 27928 | 1.0449 | 0.8553 | 0.8553 | 0.8553 | 0.8553 |
0.0312 | 9.0 | 31419 | 1.1677 | 0.8598 | 0.8598 | 0.8598 | 0.8598 |
0.022 | 10.0 | 34910 | 1.2128 | 0.8593 | 0.8591 | 0.8591 | 0.8591 |
Base model
HooshvareLab/bert-base-parsbert-uncased