| tags: | |
| - generated_from_trainer | |
| datasets: | |
| - id_liputan6 | |
| model-index: | |
| - name: bert2bert-dropout-0.3-lr-5e-05-ds-canonical | |
| 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. --> | |
| # bert2bert-dropout-0.3-lr-5e-05-ds-canonical | |
| This model was trained from scratch on the id_liputan6 dataset. | |
| It achieves the following results on the evaluation set: | |
| - Loss: 2.2037 | |
| - Rouge2 Precision: 0.1783 | |
| - Rouge2 Recall: 0.1901 | |
| - Rouge2 Fmeasure: 0.1818 | |
| ## 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: 48 | |
| - eval_batch_size: 48 | |
| - seed: 42 | |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 | |
| - lr_scheduler_type: linear | |
| - num_epochs: 3 | |
| - mixed_precision_training: Native AMP | |
| ### Training results | |
| | Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure | | |
| |:-------------:|:-----:|:-----:|:---------------:|:----------------:|:-------------:|:---------------:| | |
| | 1.7398 | 1.0 | 4040 | 2.2892 | 0.1789 | 0.1933 | 0.1835 | | |
| | 1.5953 | 2.0 | 8080 | 2.2380 | 0.1789 | 0.1917 | 0.1829 | | |
| | 1.5771 | 3.0 | 12120 | 2.2037 | 0.1783 | 0.1901 | 0.1818 | | |
| ### Framework versions | |
| - Transformers 4.37.0 | |
| - Pytorch 2.1.2 | |
| - Datasets 2.16.1 | |
| - Tokenizers 0.15.1 | |