senate_bills_summary_model
This model is a fine-tuned version of google-t5/t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.9099
- Rouge1: 0.2477
- Rouge2: 0.1963
- Rougel: 0.2407
- Rougelsum: 0.2406
- Gen Len: 18.9992
Model description
This model is a fine-tuned Google T5-Small model that is fine-tuned to summarize United States Senate Bills.
Intended uses & limitations
Summarize United States Federal Legislation.
Training and evaluation data
Trained on ~13.1k bills and summaries.
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 14
- eval_batch_size: 14
- 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 |
---|---|---|---|---|---|---|---|---|
2.2318 | 1.0 | 749 | 1.9710 | 0.2475 | 0.1952 | 0.2405 | 0.2402 | 18.9985 |
2.1782 | 2.0 | 1498 | 1.9331 | 0.2478 | 0.1959 | 0.2408 | 0.2406 | 18.9992 |
2.1355 | 3.0 | 2247 | 1.9141 | 0.2479 | 0.1961 | 0.2409 | 0.2407 | 18.9992 |
2.1079 | 4.0 | 2996 | 1.9099 | 0.2477 | 0.1963 | 0.2407 | 0.2406 | 18.9992 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 4
Model tree for MTSUFall2024SoftwareEngineering/UnitedStatesSenateBillsSummary
Base model
google-t5/t5-small