metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: DanSumT5-baseV_13284V_36974V_40973
results: []
DanSumT5-baseV_13284V_36974V_40973
This model is a fine-tuned version of emilstabil/DanSumT5-baseV_13284V_36974 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.0844
- Rouge1: 34.7659
- Rouge2: 12.0539
- Rougel: 21.7003
- Rougelsum: 32.4346
- Gen Len: 125.7257
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: 1e-05
- train_batch_size: 6
- eval_batch_size: 6
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 24
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 11
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 79 | 2.0942 | 34.8616 | 12.1787 | 21.938 | 32.7257 | 125.2743 |
| No log | 1.99 | 158 | 2.0948 | 35.2673 | 12.4538 | 22.1361 | 33.0224 | 125.4852 |
| No log | 2.99 | 237 | 2.0952 | 34.9658 | 12.3838 | 21.8458 | 32.7172 | 125.4684 |
| No log | 4.0 | 317 | 2.0912 | 35.0599 | 12.2917 | 22.056 | 32.8679 | 125.789 |
| No log | 5.0 | 396 | 2.0928 | 34.8244 | 12.177 | 21.7107 | 32.5448 | 125.7342 |
| No log | 5.99 | 475 | 2.0921 | 34.9628 | 12.0905 | 21.9328 | 32.6944 | 125.7384 |
| 1.9703 | 6.99 | 554 | 2.0894 | 35.2438 | 12.2584 | 22.0919 | 32.8896 | 125.6118 |
| 1.9703 | 8.0 | 634 | 2.0880 | 35.0228 | 12.0681 | 21.9121 | 32.6604 | 125.7848 |
| 1.9703 | 9.0 | 713 | 2.0864 | 34.9607 | 12.0556 | 21.8096 | 32.5884 | 125.6751 |
| 1.9703 | 9.99 | 792 | 2.0849 | 34.7755 | 12.0721 | 21.7294 | 32.4555 | 125.7215 |
| 1.9703 | 10.97 | 869 | 2.0844 | 34.7659 | 12.0539 | 21.7003 | 32.4346 | 125.7257 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.12.1+git7548e2f
- Datasets 2.13.2
- Tokenizers 0.13.3