fine_tuned_t5_small_model_sec_5_v11
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.9050
- Rouge1: 0.4126
- Rouge2: 0.1679
- Rougel: 0.2637
- Rougelsum: 0.2633
- Gen Len: 95.1211
- Bert F1: 0.8787
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: 8
- eval_batch_size: 8
- 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 |
|---|---|---|---|---|---|---|---|---|---|
| 3.5538 | 1.0526 | 100 | 3.0575 | 0.4092 | 0.1599 | 0.2556 | 0.2549 | 97.1789 | 0.8759 |
| 3.1873 | 2.1053 | 200 | 2.9535 | 0.41 | 0.1605 | 0.2557 | 0.2552 | 97.3474 | 0.8769 |
| 3.1181 | 3.1579 | 300 | 2.9187 | 0.4102 | 0.1651 | 0.2626 | 0.262 | 95.5947 | 0.878 |
| 3.0864 | 4.2105 | 400 | 2.9050 | 0.4126 | 0.1679 | 0.2637 | 0.2633 | 95.1211 | 0.8787 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.4.0
- Datasets 3.1.0
- Tokenizers 0.20.3