fine_tuned_t5_small_model_sec_5_v6
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.9223
- Rouge1: 0.3808
- Rouge2: 0.1521
- Rougel: 0.2479
- Rougelsum: 0.2488
- Gen Len: 76.8579
- Bert F1: 0.8757
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 |
|---|---|---|---|---|---|---|---|---|---|
| 3.7977 | 0.8333 | 40 | 3.2267 | 0.3522 | 0.1393 | 0.2331 | 0.2332 | 60.3579 | 0.8729 |
| 3.3838 | 1.6667 | 80 | 3.0432 | 0.3696 | 0.1498 | 0.2434 | 0.244 | 71.4526 | 0.8741 |
| 3.2314 | 2.5 | 120 | 2.9703 | 0.3727 | 0.1472 | 0.2436 | 0.2444 | 75.8737 | 0.8737 |
| 3.175 | 3.3333 | 160 | 2.9395 | 0.3801 | 0.1542 | 0.2476 | 0.2485 | 77.6211 | 0.8753 |
| 3.1805 | 4.1667 | 200 | 2.9266 | 0.3817 | 0.1541 | 0.2491 | 0.2498 | 76.7632 | 0.8756 |
| 3.1633 | 5.0 | 240 | 2.9223 | 0.3808 | 0.1521 | 0.2479 | 0.2488 | 76.8579 | 0.8757 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.4.0
- Datasets 3.1.0
- Tokenizers 0.20.3