summarizer
This model is a fine-tuned version of facebook/bart-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.5029
- Rouge1: 48.685
- Rouge2: 22.7386
- Rougel: 43.8124
- Rougelsum: 43.8396
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: 5.6e-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: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 2.3383 | 1.0 | 460 | 1.8745 | 49.3535 | 25.1806 | 45.1706 | 45.1579 |
| 1.5714 | 2.0 | 920 | 1.9525 | 48.5102 | 23.7917 | 43.5276 | 43.5289 |
| 1.0907 | 3.0 | 1380 | 2.0340 | 47.3071 | 22.9257 | 42.9624 | 43.0095 |
| 0.7586 | 4.0 | 1840 | 2.2207 | 49.078 | 24.4061 | 44.8266 | 44.7489 |
| 0.507 | 5.0 | 2300 | 2.3542 | 49.1445 | 23.918 | 44.4869 | 44.4544 |
| 0.3503 | 6.0 | 2760 | 2.4352 | 47.8282 | 22.9394 | 43.2666 | 43.2609 |
| 0.2434 | 7.0 | 3220 | 2.4867 | 48.8996 | 23.6147 | 44.4024 | 44.3788 |
| 0.1769 | 8.0 | 3680 | 2.5029 | 48.685 | 22.7386 | 43.8124 | 43.8396 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
- Downloads last month
- 0
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support