| --- |
| tags: |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| - f1 |
| - precision |
| - recall |
| model-index: |
| - name: Research_paper_MLM_Final_Label |
| 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. --> |
|
|
| # Research_paper_MLM_Final_Label |
|
|
| This model was trained from scratch on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 1.9925 |
| - Accuracy: 0.8591 |
| - F1: 0.8575 |
| - Precision: 0.8712 |
| - Recall: 0.8591 |
|
|
| ## 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: 64 |
| - seed: 42 |
| - gradient_accumulation_steps: 2 |
| - total_train_batch_size: 32 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: linear |
| - lr_scheduler_warmup_steps: 50 |
| - num_epochs: 2 |
| - mixed_precision_training: Native AMP |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | |
| |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:| |
| | 0.1091 | 0.04 | 500 | 0.9687 | 0.8633 | 0.8614 | 0.8791 | 0.8633 | |
| | 0.1186 | 0.08 | 1000 | 1.2620 | 0.8629 | 0.8612 | 0.8769 | 0.8629 | |
| | 0.2068 | 0.12 | 1500 | 2.0443 | 0.8527 | 0.8509 | 0.8659 | 0.8527 | |
| | 0.42 | 0.16 | 2000 | 2.1931 | 0.8595 | 0.8574 | 0.8764 | 0.8595 | |
| | 0.1435 | 0.2 | 2500 | 2.0973 | 0.8644 | 0.8625 | 0.8805 | 0.8644 | |
| | 0.4373 | 0.24 | 3000 | 2.0976 | 0.8603 | 0.8580 | 0.8785 | 0.8603 | |
| | 0.1527 | 0.28 | 3500 | 2.2136 | 0.8550 | 0.8532 | 0.8679 | 0.8550 | |
| | 0.459 | 0.32 | 4000 | 2.0543 | 0.8610 | 0.8590 | 0.8775 | 0.8610 | |
| | 0.2396 | 0.36 | 4500 | 2.1373 | 0.8565 | 0.8548 | 0.8690 | 0.8565 | |
| | 0.1641 | 0.4 | 5000 | 2.2913 | 0.8557 | 0.8539 | 0.8695 | 0.8557 | |
| | 0.1841 | 0.44 | 5500 | 2.1315 | 0.8539 | 0.8520 | 0.8672 | 0.8539 | |
| | 0.133 | 0.48 | 6000 | 2.2268 | 0.8580 | 0.8564 | 0.8695 | 0.8580 | |
| | 0.1659 | 0.52 | 6500 | 2.1685 | 0.8573 | 0.8557 | 0.8689 | 0.8573 | |
| | 0.1677 | 0.56 | 7000 | 2.1515 | 0.8576 | 0.8558 | 0.8712 | 0.8576 | |
| | 0.3713 | 0.6 | 7500 | 2.2057 | 0.8606 | 0.8584 | 0.8785 | 0.8606 | |
| | 0.1469 | 0.64 | 8000 | 1.8279 | 0.8606 | 0.8594 | 0.8698 | 0.8606 | |
| | 0.3673 | 0.68 | 8500 | 1.9808 | 0.8625 | 0.8603 | 0.8812 | 0.8625 | |
| | 0.1395 | 0.72 | 9000 | 2.0565 | 0.8603 | 0.8585 | 0.8741 | 0.8603 | |
| | 0.1052 | 0.76 | 9500 | 2.0813 | 0.8606 | 0.8591 | 0.8724 | 0.8606 | |
| | 0.3925 | 0.8 | 10000 | 2.0700 | 0.8569 | 0.8553 | 0.8687 | 0.8569 | |
| | 0.1886 | 0.84 | 10500 | 1.9925 | 0.8591 | 0.8575 | 0.8712 | 0.8591 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.37.0 |
| - Pytorch 2.1.0+cu121 |
| - Datasets 2.16.1 |
| - Tokenizers 0.15.1 |
|
|
