<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
DanSumT5-small-finetuned-test
This model is a fine-tuned version of Danish-summarisation/DanSumT5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.8869
- Rouge1: 29.589
- Rouge2: 6.7042
- Rougel: 16.9991
- Rougelsum: 26.9941
- Gen Len: 127.0
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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 400 | 2.9481 | 29.8527 | 6.7842 | 16.8512 | 26.8767 | 127.0 |
| 3.2993 | 2.0 | 800 | 2.8938 | 30.3124 | 6.9557 | 17.3361 | 27.8521 | 126.64 |
| 3.1748 | 3.0 | 1200 | 2.8909 | 30.0801 | 6.7297 | 17.0973 | 27.4183 | 127.0 |
| 3.1709 | 4.0 | 1600 | 2.8869 | 29.5395 | 6.7387 | 17.0244 | 26.8949 | 127.0 |
| 3.1555 | 5.0 | 2000 | 2.8869 | 29.589 | 6.7042 | 16.9991 | 26.9941 | 127.0 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
