metadata
library_name: transformers
license: apache-2.0
base_model: google-t5/t5-small
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: MTSUSpring2025SoftwareEngineering
results: []
MTSUSpring2025SoftwareEngineering
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: 1.2226
- Rouge1: 0.0823
- Rouge2: 0.0672
- Rougel: 0.0799
- Rougelsum: 0.0798
- Gen Len: 6.8086
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 8
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 1.6211 | 1.0 | 14778 | 1.4386 | 0.086 | 0.0686 | 0.0831 | 0.0831 | 7.0473 |
| 1.5116 | 2.0 | 29556 | 1.3540 | 0.0836 | 0.0677 | 0.0811 | 0.0811 | 6.9131 |
| 1.4459 | 3.0 | 44334 | 1.3019 | 0.0874 | 0.0708 | 0.0847 | 0.0846 | 7.1384 |
| 1.42 | 4.0 | 59112 | 1.2729 | 0.0843 | 0.0687 | 0.0818 | 0.0817 | 6.9433 |
| 1.3683 | 5.0 | 73890 | 1.2490 | 0.0838 | 0.0684 | 0.0814 | 0.0812 | 6.916 |
| 1.3589 | 6.0 | 88668 | 1.2357 | 0.0847 | 0.0692 | 0.0822 | 0.0821 | 6.995 |
| 1.353 | 7.0 | 103446 | 1.2245 | 0.0825 | 0.0673 | 0.08 | 0.0799 | 6.8302 |
| 1.3506 | 8.0 | 118224 | 1.2226 | 0.0823 | 0.0672 | 0.0799 | 0.0798 | 6.8086 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.6.0+cu124
- Datasets 3.4.1
- Tokenizers 0.21.1