| | --- |
| | license: apache-2.0 |
| | base_model: sshleifer/distilbart-xsum-12-6 |
| | tags: |
| | - generated_from_trainer |
| | model-index: |
| | - name: trained-distilbart-abs-0807 |
| | 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. --> |
| |
|
| | # trained-distilbart-abs-0807 |
| |
|
| | This model is a fine-tuned version of [sshleifer/distilbart-xsum-12-6](https://huggingface.co/sshleifer/distilbart-xsum-12-6) on the None dataset. |
| | It achieves the following results on the evaluation set: |
| | - Loss: 2.4184 |
| | - Rouge/rouge1: 0.0185 |
| | - Rouge/rouge2: 0.0088 |
| | - Rouge/rougel: 0.0152 |
| | - Rouge/rougelsum: 0.016 |
| | - Bertscore/bertscore-precision: 0.0404 |
| | - Bertscore/bertscore-recall: 0.04 |
| | - Bertscore/bertscore-f1: 0.0402 |
| | - Meteor: 0.0163 |
| | - Gen Len: 80.0 |
| |
|
| | ## 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: 3e-05 |
| | - train_batch_size: 4 |
| | - eval_batch_size: 4 |
| | - seed: 42 |
| | - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| | - lr_scheduler_type: linear |
| | - num_epochs: 6 |
| | - mixed_precision_training: Native AMP |
| |
|
| | ### Training results |
| |
|
| | | Training Loss | Epoch | Step | Validation Loss | Rouge/rouge1 | Rouge/rouge2 | Rouge/rougel | Rouge/rougelsum | Bertscore/bertscore-precision | Bertscore/bertscore-recall | Bertscore/bertscore-f1 | Meteor | Gen Len | |
| | |:-------------:|:-----:|:----:|:---------------:|:------------:|:------------:|:------------:|:---------------:|:-----------------------------:|:--------------------------:|:----------------------:|:------:|:-------:| |
| | | 2.105 | 1.0 | 220 | 2.0884 | 0.4545 | 0.2049 | 0.3881 | 0.3905 | 0.8969 | 0.88 | 0.8882 | 0.3923 | 80.0 | |
| | | 1.8823 | 2.0 | 440 | 2.0066 | 0.3453 | 0.1575 | 0.2965 | 0.2984 | 0.6632 | 0.6547 | 0.6587 | 0.2949 | 80.0 | |
| | | 1.4089 | 3.0 | 660 | 2.0717 | 0.0768 | 0.0337 | 0.0637 | 0.0639 | 0.1559 | 0.1535 | 0.1547 | 0.0667 | 80.0 | |
| | | 1.0687 | 4.0 | 880 | 2.1627 | 0.0125 | 0.0048 | 0.0104 | 0.0114 | 0.0322 | 0.0317 | 0.0319 | 0.0118 | 80.0 | |
| | | 0.7445 | 5.0 | 1100 | 2.2927 | 0.0402 | 0.0177 | 0.0332 | 0.0332 | 0.0815 | 0.0809 | 0.0812 | 0.0374 | 80.0 | |
| | | 0.7619 | 6.0 | 1320 | 2.4184 | 0.0185 | 0.0088 | 0.0152 | 0.016 | 0.0404 | 0.04 | 0.0402 | 0.0163 | 80.0 | |
| |
|
| |
|
| | ### Framework versions |
| |
|
| | - Transformers 4.41.2 |
| | - Pytorch 2.1.2 |
| | - Datasets 2.19.2 |
| | - Tokenizers 0.19.1 |
| |
|
