metadata
license: apache-2.0
tags:
- summarization
- generated_from_trainer
metrics:
- rouge
model-index:
- name: t5-small-medical_transcription
results: []
t5-small-medical_transcription
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.7744
- Rouge1: 0.3722
- Rouge2: 0.2709
- Rougel: 0.3628
- Rougelsum: 0.3619
- Gen Len: 17.0877
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 | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 2.4475 | 1.0 | 27 | 2.0647 | 0.3288 | 0.2503 | 0.3252 | 0.3212 | 17.2281 |
| 2.0319 | 2.0 | 54 | 1.9089 | 0.3456 | 0.2527 | 0.3407 | 0.3377 | 16.3684 |
| 1.8772 | 3.0 | 81 | 1.8572 | 0.3528 | 0.2615 | 0.3478 | 0.3457 | 16.1579 |
| 1.796 | 4.0 | 108 | 1.8211 | 0.3274 | 0.2479 | 0.324 | 0.3216 | 15.7719 |
| 1.7107 | 5.0 | 135 | 1.7972 | 0.3689 | 0.277 | 0.3614 | 0.3586 | 16.3509 |
| 1.711 | 6.0 | 162 | 1.7852 | 0.359 | 0.2599 | 0.3505 | 0.348 | 16.2105 |
| 1.7581 | 7.0 | 189 | 1.7773 | 0.3659 | 0.2646 | 0.3566 | 0.3559 | 16.9298 |
| 1.704 | 8.0 | 216 | 1.7744 | 0.3722 | 0.2709 | 0.3628 | 0.3619 | 17.0877 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2