t5-small-keyphrase-id
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4733
- Rouge1: 41.0259
- Rouge2: 21.517
- Rougel: 35.32
- Bleu: 19.1166
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 0.1
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Bleu |
|---|---|---|---|---|---|---|---|
| 2.1428 | 1.0 | 793 | 1.6842 | 31.5776 | 15.7424 | 27.8274 | 12.4053 |
| 1.7467 | 2.0 | 1586 | 1.5864 | 36.525 | 18.5667 | 31.9128 | 16.0299 |
| 1.6433 | 3.0 | 2379 | 1.5418 | 37.975 | 19.416 | 32.9918 | 16.8339 |
| 1.5858 | 4.0 | 3172 | 1.5158 | 39.0333 | 20.2533 | 34.1644 | 18.0909 |
| 1.5455 | 5.0 | 3965 | 1.5008 | 39.8088 | 20.6915 | 34.6625 | 18.6534 |
| 1.5084 | 6.0 | 4758 | 1.4849 | 40.5524 | 21.3479 | 35.1159 | 19.0572 |
| 1.4859 | 7.0 | 5551 | 1.4772 | 40.2129 | 21.1254 | 35.0268 | 19.0809 |
| 1.4630 | 8.0 | 6344 | 1.4819 | 40.5756 | 21.468 | 35.3439 | 19.3096 |
| 1.4475 | 9.0 | 7137 | 1.4736 | 40.8466 | 21.4684 | 35.4963 | 19.359 |
| 1.4434 | 10.0 | 7930 | 1.4733 | 41.0259 | 21.517 | 35.32 | 19.1166 |
Framework versions
- Transformers 5.10.2
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2