| --- |
| library_name: transformers |
| license: agpl-3.0 |
| base_model: vinai/phobert-base-v2 |
| tags: |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| - f1 |
| model-index: |
| - name: model_segment_content_DEFI |
| results: [] |
| --- |
| |
| <!-- This model card has been generated automatically according to the information the Trainer had access to. You |
| should probably proofread and complete it, then remove this comment. --> |
|
|
| # model_segment_content_DEFI |
| |
| This model is a fine-tuned version of [vinai/phobert-base-v2](https://huggingface.co/vinai/phobert-base-v2) on the None dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.1130 |
| - Accuracy: 0.9707 |
| - F1: 0.9659 |
| |
| ## 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: 64 |
| - eval_batch_size: 64 |
| - seed: 42 |
| - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
| - lr_scheduler_type: linear |
| - num_epochs: 10 |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |
| |:-------------:|:------:|:----:|:---------------:|:--------:|:------:| |
| | No log | 0.1419 | 150 | 0.1087 | 0.9636 | 0.9580 | |
| | No log | 0.2838 | 300 | 0.0979 | 0.9671 | 0.9620 | |
| | No log | 0.4257 | 450 | 0.0967 | 0.9614 | 0.9559 | |
| | No log | 0.5676 | 600 | 0.0894 | 0.9688 | 0.9639 | |
| | No log | 0.7096 | 750 | 0.0917 | 0.9693 | 0.9644 | |
| | No log | 0.8515 | 900 | 0.0967 | 0.9672 | 0.9617 | |
| | No log | 0.9934 | 1050 | 0.0939 | 0.9693 | 0.9643 | |
| | 0.1071 | 1.1353 | 1200 | 0.0852 | 0.9697 | 0.9651 | |
| | 0.1071 | 1.2772 | 1350 | 0.0914 | 0.9705 | 0.9659 | |
| | 0.1071 | 1.4191 | 1500 | 0.0870 | 0.9706 | 0.9658 | |
| | 0.1071 | 1.5610 | 1650 | 0.0908 | 0.9707 | 0.9659 | |
| | 0.1071 | 1.7029 | 1800 | 0.0873 | 0.9707 | 0.9662 | |
| | 0.1071 | 1.8448 | 1950 | 0.1037 | 0.9699 | 0.9654 | |
| | 0.1071 | 1.9868 | 2100 | 0.0829 | 0.9716 | 0.9673 | |
| | 0.0675 | 2.1287 | 2250 | 0.1106 | 0.9686 | 0.9640 | |
| | 0.0675 | 2.2706 | 2400 | 0.0950 | 0.9716 | 0.9672 | |
| | 0.0675 | 2.4125 | 2550 | 0.0900 | 0.9712 | 0.9666 | |
| | 0.0675 | 2.5544 | 2700 | 0.0904 | 0.9723 | 0.9678 | |
| | 0.0675 | 2.6963 | 2850 | 0.1167 | 0.9669 | 0.9621 | |
| | 0.0675 | 2.8382 | 3000 | 0.0909 | 0.9694 | 0.9649 | |
| | 0.0675 | 2.9801 | 3150 | 0.1014 | 0.9687 | 0.9640 | |
| | 0.0506 | 3.1220 | 3300 | 0.1003 | 0.9720 | 0.9675 | |
| | 0.0506 | 3.2640 | 3450 | 0.1130 | 0.9707 | 0.9659 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 5.12.1 |
| - Pytorch 2.7.1+cu118 |
| - Datasets 5.0.0 |
| - Tokenizers 0.22.2 |
| |
