my_awesome_ects_model
This model is a fine-tuned version of google-t5/t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.2922
- Rouge1: 0.2697
- Rouge2: 0.1698
- Rougel: 0.2563
- Rougelsum: 0.2565
- Gen Len: 19.0
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
---|---|---|---|---|---|---|---|---|
No log | 1.0 | 106 | 3.0113 | 0.1325 | 0.0481 | 0.1134 | 0.1132 | 19.0 |
No log | 2.0 | 212 | 2.6834 | 0.2312 | 0.1285 | 0.2126 | 0.2131 | 19.0 |
No log | 3.0 | 318 | 2.5284 | 0.2593 | 0.1507 | 0.2419 | 0.2415 | 19.0 |
No log | 4.0 | 424 | 2.4443 | 0.263 | 0.1583 | 0.2465 | 0.2466 | 19.0 |
3.0639 | 5.0 | 530 | 2.3860 | 0.2679 | 0.1643 | 0.2541 | 0.254 | 19.0 |
3.0639 | 6.0 | 636 | 2.3454 | 0.2677 | 0.1658 | 0.2535 | 0.2534 | 19.0 |
3.0639 | 7.0 | 742 | 2.3214 | 0.2656 | 0.1651 | 0.2526 | 0.2526 | 19.0 |
3.0639 | 8.0 | 848 | 2.3054 | 0.2693 | 0.1699 | 0.2562 | 0.2564 | 19.0 |
3.0639 | 9.0 | 954 | 2.2950 | 0.2721 | 0.1717 | 0.2579 | 0.258 | 19.0 |
2.5574 | 10.0 | 1060 | 2.2922 | 0.2697 | 0.1698 | 0.2563 | 0.2565 | 19.0 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 22