t5-small-transcript-summarizer
This model is a fine-tuned version of t5-small on the samsum dataset. It achieves the following results on the evaluation set:
- Loss: 1.7347
- Rouge1: 41.4993
- Rouge2: 18.6768
- Rougel: 34.8901
- Rougelsum: 38.434
- Gen Len: 16.533
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 1.9691 | 1.0 | 3683 | 1.7864 | 40.9391 | 18.2339 | 34.4773 | 38.0777 | 16.7017 |
| 1.9213 | 2.0 | 7366 | 1.7533 | 41.4658 | 18.8086 | 34.8947 | 38.3528 | 16.5208 |
| 1.8757 | 3.0 | 11049 | 1.7367 | 41.641 | 18.7355 | 35.0432 | 38.5403 | 16.544 |
| 1.8484 | 4.0 | 14732 | 1.7347 | 41.4993 | 18.6768 | 34.8901 | 38.434 | 16.533 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1