fine_tuned_t5_small_model_sec_5_v8
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.0291
- Rouge1: 0.4097
- Rouge2: 0.1755
- Rougel: 0.265
- Rougelsum: 0.265
- Gen Len: 91.6842
- Bert F1: 0.8773
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use 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: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | Bert F1 |
|---|---|---|---|---|---|---|---|---|---|
| 4.0511 | 0.8333 | 40 | 3.4679 | 0.3889 | 0.1606 | 0.2546 | 0.2544 | 76.5053 | 0.8751 |
| 3.5797 | 1.6667 | 80 | 3.2230 | 0.3977 | 0.1652 | 0.2577 | 0.2572 | 83.4368 | 0.8754 |
| 3.412 | 2.5 | 120 | 3.1147 | 0.4011 | 0.1665 | 0.2601 | 0.2595 | 86.7526 | 0.8758 |
| 3.4241 | 3.3333 | 160 | 3.0614 | 0.4082 | 0.1739 | 0.2624 | 0.2622 | 89.2895 | 0.877 |
| 3.3084 | 4.1667 | 200 | 3.0368 | 0.4066 | 0.1733 | 0.2633 | 0.2639 | 89.6579 | 0.8769 |
| 3.3262 | 5.0 | 240 | 3.0291 | 0.4097 | 0.1755 | 0.265 | 0.265 | 91.6842 | 0.8773 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.4.0
- Datasets 3.1.0
- Tokenizers 0.20.3