t5-small-finetuned-xsum
This model is a fine-tuned version of t5-small on the xsum dataset. It achieves the following results on the evaluation set:
- Loss: 2.5941
- Rouge1: 26.5386
- Rouge2: 6.559
- Rougel: 20.6697
- Rougelsum: 20.6761
- Gen Len: 18.8162
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: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 2.851 | 1.0 | 3125 | 2.5941 | 26.5386 | 6.559 | 20.6697 | 20.6761 | 18.8162 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 2
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for gbv/t5-small-finetuned-xsum
Base model
google-t5/t5-smallDataset used to train gbv/t5-small-finetuned-xsum
Evaluation results
- Rouge1 on xsumvalidation set self-reported26.539