t5-small-finetuned-xlsum-with-multi-news-test-5-epoch
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.2989
- Rouge1: 30.8254
- Rouge2: 9.2466
- Rougel: 24.0068
- Rougelsum: 24.0535
- Gen Len: 18.8143
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: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 2.7346 | 1.0 | 20543 | 2.3901 | 29.3586 | 8.2361 | 22.7798 | 22.8273 | 18.8201 |
| 2.6739 | 2.0 | 41086 | 2.3414 | 30.2258 | 8.77 | 23.496 | 23.5405 | 18.8384 |
| 2.6486 | 3.0 | 61629 | 2.3160 | 30.6221 | 9.1072 | 23.8114 | 23.8584 | 18.8194 |
| 2.648 | 4.0 | 82172 | 2.3033 | 30.8171 | 9.2146 | 23.9993 | 24.0424 | 18.8016 |
| 2.63 | 5.0 | 102715 | 2.2989 | 30.8254 | 9.2466 | 24.0068 | 24.0535 | 18.8143 |
Framework versions
- Transformers 4.13.0
- Pytorch 1.13.1+cpu
- Datasets 2.8.0
- Tokenizers 0.10.3