experiment-summarisation-2
This model is a fine-tuned version of google/mt5-small on the billsum dataset. It achieves the following results on the evaluation set:
- Loss: 2.6952
- Rouge1: 0.1384
- Rouge2: 0.0422
- Rougel: 0.1089
- Rougelsum: 0.109
- Gen Len: 19.0
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
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 248 | 3.1176 | 0.1349 | 0.0327 | 0.1088 | 0.109 | 19.0 |
| No log | 2.0 | 496 | 2.7865 | 0.1333 | 0.0377 | 0.1072 | 0.1074 | 19.0 |
| 7.2763 | 3.0 | 744 | 2.7115 | 0.1364 | 0.0406 | 0.1076 | 0.1078 | 19.0 |
| 7.2763 | 4.0 | 992 | 2.6952 | 0.1384 | 0.0422 | 0.1089 | 0.109 | 19.0 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3