fine_tuned_t5_small_model_sec_5_v12
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.7808
- Rouge1: 0.3922
- Rouge2: 0.1658
- Rougel: 0.2571
- Rougelsum: 0.2574
- Bertscore F1: 0.6415
- Gen Len: 95.9789
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 | Bertscore F1 | Gen Len |
|---|---|---|---|---|---|---|---|---|---|
| 3.5579 | 1.0526 | 100 | 2.9214 | 0.3898 | 0.1634 | 0.2562 | 0.2567 | 0.6375 | 98.7895 |
| 3.2216 | 2.1053 | 200 | 2.8219 | 0.392 | 0.1646 | 0.2559 | 0.2571 | 0.6372 | 97.8474 |
| 3.1439 | 3.1579 | 300 | 2.7919 | 0.3891 | 0.1625 | 0.2545 | 0.2547 | 0.638 | 95.6316 |
| 3.0991 | 4.2105 | 400 | 2.7808 | 0.3922 | 0.1658 | 0.2571 | 0.2574 | 0.6415 | 95.9789 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.4.0
- Datasets 3.1.0
- Tokenizers 0.20.3