metadata
license: apache-2.0
base_model: t5-small
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: t5-small-finetuned-new-gettitle
results: []
t5-small-finetuned-new-gettitle
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.1342
- Rouge1: 41.0072
- Rouge2: 21.829
- Rougel: 36.7872
- Rougelsum: 36.7623
- Gen Len: 13.7485
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
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
---|---|---|---|---|---|---|---|---|
2.5176 | 1.0 | 2050 | 2.2543 | 39.227 | 21.0282 | 35.4225 | 35.4136 | 13.2759 |
2.4304 | 2.0 | 4100 | 2.1874 | 40.0497 | 21.2453 | 36.0247 | 36.0363 | 13.6354 |
2.3839 | 3.0 | 6150 | 2.1550 | 40.579 | 21.5834 | 36.4843 | 36.4847 | 13.6754 |
2.3506 | 4.0 | 8200 | 2.1392 | 41.0029 | 21.8114 | 36.757 | 36.7411 | 13.8856 |
2.328 | 5.0 | 10250 | 2.1342 | 41.0072 | 21.829 | 36.7872 | 36.7623 | 13.7485 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1