T5-small_finetuned_billsum_subset_model_bs32_lr5e-05
This model is a fine-tuned version of t5-small on the billsum dataset. It achieves the following results on the evaluation set:
- Loss: 1.9708
- Rouge1: 0.1898
- Rouge2: 0.0974
- Rougel: 0.1666
- Rougelsum: 0.1663
- Gen Len: 19.0
- Bleu: 0.0007
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: 32
- eval_batch_size: 32
- 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 | Bleu |
---|---|---|---|---|---|---|---|---|---|
No log | 1.0 | 31 | 1.9796 | 0.1877 | 0.095 | 0.1648 | 0.1646 | 19.0 | 0.0007 |
No log | 2.0 | 62 | 1.9756 | 0.1875 | 0.0968 | 0.1657 | 0.1654 | 19.0 | 0.0007 |
No log | 3.0 | 93 | 1.9745 | 0.1867 | 0.0938 | 0.1638 | 0.1637 | 19.0 | 0.0007 |
No log | 4.0 | 124 | 1.9708 | 0.1898 | 0.0974 | 0.1666 | 0.1663 | 19.0 | 0.0007 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
- Downloads last month
- 2
Dataset used to train alaahussein/T5-small_finetuned_billsum_subset_model_bs32_lr5e-05
Evaluation results
- Rouge1 on billsumself-reported0.190
- Bleu on billsumself-reported0.001