| --- |
| tags: |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| - precision |
| - recall |
| model-index: |
| - name: roberta-base |
| 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. --> |
|
|
| # roberta-base |
|
|
| This model was trained from scratch on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 1.3682 |
| - Accuracy: 0.8280 |
| - Precision: 0.8277 |
| - Recall: 0.8280 |
| - Precision Macro: 0.7620 |
| - Recall Macro: 0.7780 |
| - Macro Fpr: 0.0163 |
| - Weighted Fpr: 0.0158 |
| - Weighted Specificity: 0.9771 |
| - Macro Specificity: 0.9862 |
| - Weighted Sensitivity: 0.8164 |
| - Macro Sensitivity: 0.7780 |
| - F1 Micro: 0.8164 |
| - F1 Macro: 0.7665 |
| - F1 Weighted: 0.8173 |
|
|
| ## 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: 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: 15 |
| - mixed_precision_training: Native AMP |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | Precision Macro | Recall Macro | Macro Fpr | Weighted Fpr | Weighted Specificity | Macro Specificity | Weighted Sensitivity | Macro Sensitivity | F1 Micro | F1 Macro | F1 Weighted | |
| |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:---------------:|:------------:|:---------:|:------------:|:--------------------:|:-----------------:|:--------------------:|:-----------------:|:--------:|:--------:|:-----------:| |
| | 1.4921 | 1.0 | 643 | 1.0307 | 0.6762 | 0.6362 | 0.6762 | 0.3746 | 0.4027 | 0.0351 | 0.0331 | 0.9438 | 0.9747 | 0.6762 | 0.4027 | 0.6762 | 0.3676 | 0.6382 | |
| | 0.9019 | 2.0 | 1286 | 0.8136 | 0.7374 | 0.7158 | 0.7374 | 0.4625 | 0.5149 | 0.0251 | 0.0248 | 0.9701 | 0.9805 | 0.7374 | 0.5149 | 0.7374 | 0.4767 | 0.7197 | |
| | 0.7714 | 3.0 | 1929 | 0.8494 | 0.7622 | 0.7386 | 0.7622 | 0.5056 | 0.5354 | 0.0224 | 0.0218 | 0.9713 | 0.9822 | 0.7622 | 0.5354 | 0.7622 | 0.5064 | 0.7441 | |
| | 0.5351 | 4.0 | 2572 | 0.9905 | 0.7645 | 0.7657 | 0.7645 | 0.5496 | 0.5653 | 0.0224 | 0.0215 | 0.9673 | 0.9821 | 0.7645 | 0.5653 | 0.7645 | 0.5444 | 0.7546 | |
| | 0.4521 | 5.0 | 3215 | 1.0260 | 0.7901 | 0.7882 | 0.7901 | 0.6421 | 0.6315 | 0.0190 | 0.0186 | 0.9745 | 0.9843 | 0.7901 | 0.6315 | 0.7901 | 0.6117 | 0.7794 | |
| | 0.3466 | 6.0 | 3858 | 1.0385 | 0.7870 | 0.8134 | 0.7870 | 0.6722 | 0.6335 | 0.0192 | 0.0190 | 0.9777 | 0.9843 | 0.7870 | 0.6335 | 0.7870 | 0.6119 | 0.7890 | |
| | 0.2333 | 7.0 | 4501 | 1.1465 | 0.8118 | 0.8064 | 0.8118 | 0.6795 | 0.6784 | 0.0169 | 0.0163 | 0.9746 | 0.9858 | 0.8118 | 0.6784 | 0.8118 | 0.6657 | 0.8058 | |
| | 0.1658 | 8.0 | 5144 | 1.2419 | 0.8149 | 0.8149 | 0.8149 | 0.7319 | 0.7440 | 0.0165 | 0.0160 | 0.9771 | 0.9861 | 0.8149 | 0.7440 | 0.8149 | 0.7329 | 0.8121 | |
| | 0.1597 | 9.0 | 5787 | 1.3441 | 0.8180 | 0.8259 | 0.8180 | 0.8314 | 0.7702 | 0.0160 | 0.0156 | 0.9768 | 0.9863 | 0.8180 | 0.7702 | 0.8180 | 0.7804 | 0.8190 | |
| | 0.11 | 10.0 | 6430 | 1.3505 | 0.8025 | 0.8152 | 0.8025 | 0.7520 | 0.7654 | 0.0178 | 0.0173 | 0.9761 | 0.9852 | 0.8025 | 0.7654 | 0.8025 | 0.7500 | 0.8065 | |
| | 0.0747 | 11.0 | 7073 | 1.3682 | 0.8280 | 0.8277 | 0.8280 | 0.8096 | 0.7820 | 0.0152 | 0.0146 | 0.9761 | 0.9869 | 0.8280 | 0.7820 | 0.8280 | 0.7850 | 0.8253 | |
| | 0.0519 | 12.0 | 7716 | 1.4437 | 0.8164 | 0.8188 | 0.8164 | 0.7731 | 0.7751 | 0.0164 | 0.0158 | 0.9755 | 0.9861 | 0.8164 | 0.7751 | 0.8164 | 0.7699 | 0.8170 | |
| | 0.0324 | 13.0 | 8359 | 1.4511 | 0.8087 | 0.8127 | 0.8087 | 0.7552 | 0.7802 | 0.0171 | 0.0166 | 0.9769 | 0.9857 | 0.8087 | 0.7802 | 0.8087 | 0.7638 | 0.8097 | |
| | 0.0184 | 14.0 | 9002 | 1.5005 | 0.8141 | 0.8196 | 0.8141 | 0.7613 | 0.7848 | 0.0165 | 0.0160 | 0.9776 | 0.9861 | 0.8141 | 0.7848 | 0.8141 | 0.7681 | 0.8159 | |
| | 0.0137 | 15.0 | 9645 | 1.4995 | 0.8164 | 0.8193 | 0.8164 | 0.7620 | 0.7780 | 0.0163 | 0.0158 | 0.9771 | 0.9862 | 0.8164 | 0.7780 | 0.8164 | 0.7665 | 0.8173 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.38.2 |
| - Pytorch 2.1.2 |
| - Datasets 2.1.0 |
| - Tokenizers 0.15.2 |
|
|
