metadata
license: apache-2.0
base_model: t5-small
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: t5-small-finetuned-xsum
results: []
t5-small-finetuned-xsum
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4626
- Rouge1: 10.9564
- Rouge2: 4.685
- Rougel: 10.3752
- Rougelsum: 10.39
- Gen Len: 15.9259
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
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 3 | 2.0757 | 5.4388 | 1.552 | 5.2972 | 5.3409 | 16.6667 |
| No log | 2.0 | 6 | 1.9515 | 7.8036 | 3.5979 | 7.7847 | 7.8498 | 16.6667 |
| No log | 3.0 | 9 | 1.8397 | 7.8036 | 3.5979 | 7.7847 | 7.8498 | 16.8148 |
| No log | 4.0 | 12 | 1.7541 | 9.1266 | 4.3563 | 9.1926 | 9.2266 | 16.8148 |
| No log | 5.0 | 15 | 1.6738 | 9.2104 | 4.3563 | 9.3105 | 9.3533 | 16.5556 |
| No log | 6.0 | 18 | 1.5897 | 9.6908 | 4.3563 | 9.8162 | 9.8658 | 16.5185 |
| No log | 7.0 | 21 | 1.5435 | 9.5442 | 3.8683 | 9.6336 | 9.5258 | 16.7037 |
| No log | 8.0 | 24 | 1.5038 | 10.7654 | 4.4381 | 10.1637 | 10.1979 | 16.7037 |
| No log | 9.0 | 27 | 1.4776 | 10.7654 | 4.4381 | 10.1637 | 10.1979 | 16.1481 |
| No log | 10.0 | 30 | 1.4626 | 10.9564 | 4.685 | 10.3752 | 10.39 | 15.9259 |
Framework versions
- Transformers 4.32.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3