metadata
library_name: transformers
license: apache-2.0
base_model: google-t5/t5-small
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: TennesseeLegislationBillSummarizer
results: []
TennesseeLegislationBillSummarizer
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: 0.9419
- Rouge1: 0.5247
- Rouge2: 0.4182
- Rougel: 0.4983
- Rougelsum: 0.4983
- Gen Len: 19.714
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 1.1552 | 1.0 | 15881 | 1.0253 | 0.5162 | 0.4064 | 0.4892 | 0.4892 | 19.7538 |
| 1.0885 | 2.0 | 31762 | 0.9789 | 0.5182 | 0.4099 | 0.4919 | 0.4918 | 19.7598 |
| 1.051 | 3.0 | 47643 | 0.9575 | 0.5211 | 0.4136 | 0.4948 | 0.4948 | 19.7535 |
| 1.0578 | 4.0 | 63524 | 0.9457 | 0.5237 | 0.4168 | 0.4973 | 0.4973 | 19.7212 |
| 1.0285 | 5.0 | 79405 | 0.9419 | 0.5247 | 0.4182 | 0.4983 | 0.4983 | 19.714 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1