metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: DanSumT5-smallV_45767V_52355V_7660
results: []
DanSumT5-smallV_45767V_52355V_7660
This model is a fine-tuned version of emilstabil/DanSumT5-smallV_45767V_52355 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.3932
- Rouge1: 34.5352
- Rouge2: 11.9341
- Rougel: 21.4899
- Rougelsum: 32.0084
- Gen Len: 126.2447
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: 10
- eval_batch_size: 10
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 40
- 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 | 0.99 | 47 | 2.4069 | 34.5802 | 11.8249 | 21.4672 | 32.0387 | 125.9072 |
| No log | 2.0 | 95 | 2.4024 | 34.3627 | 11.7441 | 21.2184 | 31.8869 | 126.0042 |
| No log | 2.99 | 142 | 2.4040 | 34.2328 | 11.5022 | 21.2019 | 31.7474 | 125.9958 |
| No log | 4.0 | 190 | 2.4002 | 34.3259 | 11.5709 | 21.2498 | 31.8805 | 126.2068 |
| No log | 4.99 | 237 | 2.3988 | 34.3771 | 11.5555 | 21.3218 | 31.8772 | 125.9367 |
| No log | 6.0 | 285 | 2.3983 | 34.4098 | 11.6914 | 21.3358 | 31.9277 | 126.3333 |
| No log | 6.99 | 332 | 2.3960 | 34.5531 | 11.8207 | 21.4971 | 32.0056 | 126.616 |
| No log | 8.0 | 380 | 2.3952 | 34.3497 | 11.7249 | 21.3948 | 31.8378 | 126.789 |
| No log | 8.99 | 427 | 2.3935 | 34.4175 | 11.9061 | 21.4974 | 31.9233 | 126.6329 |
| No log | 10.0 | 475 | 2.3935 | 34.5727 | 11.9325 | 21.5313 | 32.0453 | 126.2447 |
| 2.5639 | 10.88 | 517 | 2.3932 | 34.5352 | 11.9341 | 21.4899 | 32.0084 | 126.2447 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.12.1+git7548e2f
- Datasets 2.13.2
- Tokenizers 0.13.3