metadata
license: apache-2.0
tags:
- summarization
- generated_from_trainer
metrics:
- rouge
model-index:
- name: t5-small-train
results: []
t5-small-train
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.2589
- Rouge1: 43.1462
- Rouge2: 20.2003
- Rougel: 37.2256
- Rougelsum: 37.7491
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: 5.6e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 3.1738 | 1.0 | 45 | 2.6267 | 34.8542 | 14.7593 | 29.9782 | 30.6298 |
| 2.6398 | 2.0 | 90 | 2.4201 | 38.2276 | 16.8995 | 33.8005 | 34.1779 |
| 2.4631 | 3.0 | 135 | 2.3275 | 40.3451 | 18.0124 | 35.2156 | 35.7063 |
| 2.3377 | 4.0 | 180 | 2.2937 | 41.8988 | 18.8153 | 36.0159 | 36.5891 |
| 2.2943 | 5.0 | 225 | 2.2786 | 43.2743 | 20.1419 | 37.261 | 37.8233 |
| 2.2183 | 6.0 | 270 | 2.2653 | 42.6978 | 19.3844 | 36.512 | 37.0261 |
| 2.2127 | 7.0 | 315 | 2.2600 | 43.2684 | 20.0259 | 37.1756 | 37.6875 |
| 2.1962 | 8.0 | 360 | 2.2589 | 43.1462 | 20.2003 | 37.2256 | 37.7491 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.1.0
- Tokenizers 0.12.1