fine_tuned_t5_small_model_sec_5_v7
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.9444
- Rouge1: 0.4164
- Rouge2: 0.1713
- Rougel: 0.2629
- Rougelsum: 0.263
- Gen Len: 97.6789
- Bert F1: 0.8782
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: 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 |
|---|---|---|---|---|---|---|---|---|---|
| 3.7935 | 0.8333 | 40 | 3.2861 | 0.4017 | 0.1617 | 0.2553 | 0.2555 | 85.1947 | 0.8757 |
| 3.4033 | 1.6667 | 80 | 3.0832 | 0.4134 | 0.1674 | 0.2577 | 0.258 | 96.5105 | 0.8765 |
| 3.2373 | 2.5 | 120 | 3.0022 | 0.4197 | 0.1746 | 0.2653 | 0.2655 | 100.2632 | 0.8777 |
| 3.1774 | 3.3333 | 160 | 2.9664 | 0.4146 | 0.1695 | 0.262 | 0.2619 | 98.3895 | 0.8773 |
| 3.1783 | 4.1667 | 200 | 2.9495 | 0.4151 | 0.1708 | 0.2633 | 0.2633 | 97.4684 | 0.878 |
| 3.1614 | 5.0 | 240 | 2.9444 | 0.4164 | 0.1713 | 0.2629 | 0.263 | 97.6789 | 0.8782 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.4.0
- Datasets 3.1.0
- Tokenizers 0.20.3