| license: apache-2.0 | |
| library_name: peft | |
| tags: | |
| - generated_from_trainer | |
| metrics: | |
| - rouge | |
| base_model: google/bigbird-pegasus-large-bigpatent | |
| model-index: | |
| - name: bigbird_lora_multi_lexsum | |
| 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. --> | |
| # bigbird_lora_multi_lexsum | |
| This model is a fine-tuned version of [google/bigbird-pegasus-large-bigpatent](https://huggingface.co/google/bigbird-pegasus-large-bigpatent) on an unknown dataset. | |
| It achieves the following results on the evaluation set: | |
| - Loss: 9.1007 | |
| - Rouge1: 0.197 | |
| - Rouge2: 0.0165 | |
| - Rougel: 0.1446 | |
| - Rougelsum: 0.1445 | |
| - Gen Len: 235.208 | |
| ## 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: 1 | |
| - eval_batch_size: 1 | |
| - seed: 42 | |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 | |
| - lr_scheduler_type: linear | |
| - lr_scheduler_warmup_ratio: 0.03 | |
| - num_epochs: 2 | |
| ### Training results | |
| | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | | |
| |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:| | |
| | 9.2003 | 1.0 | 850 | 9.1012 | 0.1982 | 0.0162 | 0.1439 | 0.1441 | 234.016 | | |
| | 9.151 | 2.0 | 1700 | 9.1007 | 0.197 | 0.0165 | 0.1446 | 0.1445 | 235.208 | | |
| ### Framework versions | |
| - PEFT 0.10.0 | |
| - Transformers 4.38.2 | |
| - Pytorch 2.2.1+cu121 | |
| - Datasets 2.18.0 | |
| - Tokenizers 0.15.2 |