--- language: - vi base_model: vinai/phobert-base-v2 tags: - generated_from_trainer model-index: - name: phobert-base-v2_baseline_syllables results: [] --- # phobert-base-v2_baseline_syllables This model is a fine-tuned version of [vinai/phobert-base-v2](https://huggingface.co/vinai/phobert-base-v2) on the covid19_ner dataset. It achieves the following results on the evaluation set: - Loss: 0.0934 - Patient Id: 0.9852 - Name: 0.9337 - Gender: 0.9489 - Age: 0.9644 - Job: 0.7601 - Location: 0.9449 - Organization: 0.8970 - Date: 0.9892 - Symptom And Disease: 0.8754 - Transportation: 1.0 - F1 Macro: 0.9299 - F1 Micro: 0.9455 ## 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 | Patient Id | Name | Gender | Age | Job | Location | Organization | Date | Symptom And Disease | Transportation | F1 Macro | F1 Micro | |:-------------:|:-----:|:----:|:---------------:|:----------:|:------:|:------:|:------:|:------:|:--------:|:------------:|:------:|:-------------------:|:--------------:|:--------:|:--------:| | 0.4655 | 1.0 | 629 | 0.2020 | 0.9690 | 0.9276 | 0.8866 | 0.8962 | 0.0 | 0.9159 | 0.8135 | 0.9860 | 0.8368 | 0.9486 | 0.8180 | 0.9093 | | 0.1235 | 2.0 | 1258 | 0.1219 | 0.9761 | 0.9125 | 0.9529 | 0.9642 | 0.0 | 0.9419 | 0.8810 | 0.9883 | 0.8545 | 0.9943 | 0.8466 | 0.9336 | | 0.0713 | 3.0 | 1887 | 0.1015 | 0.9789 | 0.9355 | 0.9541 | 0.9699 | 0.7077 | 0.9428 | 0.8891 | 0.9878 | 0.8667 | 1.0 | 0.9232 | 0.9418 | | 0.0502 | 4.0 | 2516 | 0.0950 | 0.9824 | 0.9291 | 0.9485 | 0.9657 | 0.7442 | 0.9455 | 0.8899 | 0.9865 | 0.8698 | 1.0 | 0.9262 | 0.9435 | | 0.0405 | 5.0 | 3145 | 0.0934 | 0.9852 | 0.9337 | 0.9489 | 0.9644 | 0.7601 | 0.9449 | 0.8970 | 0.9892 | 0.8754 | 1.0 | 0.9299 | 0.9455 | ### Framework versions - Transformers 4.41.2 - Pytorch 2.1.2 - Datasets 2.19.2 - Tokenizers 0.19.1