my_awesome_arxiv_model
This model is a fine-tuned version of t5-small on the scientific_papers dataset. It achieves the following results on the evaluation set:
- Loss: 2.5995
- Rouge1: 0.1783
- Rouge2: 0.0671
- Rougel: 0.1433
- Rougelsum: 0.1433
- Gen Len: 19.0
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
---|---|---|---|---|---|---|---|---|
2.8985 | 1.0 | 1269 | 2.6663 | 0.1735 | 0.0651 | 0.1393 | 0.1393 | 19.0 |
2.7954 | 2.0 | 2538 | 2.6231 | 0.1759 | 0.0675 | 0.1417 | 0.1417 | 19.0 |
2.7799 | 3.0 | 3807 | 2.6054 | 0.1779 | 0.0674 | 0.1434 | 0.1435 | 19.0 |
2.7715 | 4.0 | 5076 | 2.5995 | 0.1783 | 0.0671 | 0.1433 | 0.1433 | 19.0 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 2
Finetuned from
Dataset used to train David-Xu/my_awesome_arxiv_model
Evaluation results
- Rouge1 on scientific_paperstest set self-reported0.178