bart-base-summarization-medical-45
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: 2.1275
- Rouge1: 0.4196
- Rouge2: 0.2244
- Rougel: 0.3562
- Rougelsum: 0.3564
- Gen Len: 18.338
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: 3e-05
- train_batch_size: 4
- eval_batch_size: 1
- seed: 45
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 2.6973 | 1.0 | 1250 | 2.1978 | 0.4152 | 0.2215 | 0.3551 | 0.3555 | 17.896 |
| 2.6015 | 2.0 | 2500 | 2.1713 | 0.4141 | 0.2205 | 0.3511 | 0.3508 | 18.338 |
| 2.5775 | 3.0 | 3750 | 2.1466 | 0.4165 | 0.2208 | 0.3514 | 0.3515 | 18.41 |
| 2.5536 | 4.0 | 5000 | 2.1345 | 0.4214 | 0.2241 | 0.358 | 0.3579 | 18.38 |
| 2.5322 | 5.0 | 6250 | 2.1279 | 0.4226 | 0.2257 | 0.3587 | 0.3587 | 18.447 |
| 2.5289 | 6.0 | 7500 | 2.1275 | 0.4196 | 0.2244 | 0.3562 | 0.3564 | 18.338 |
Framework versions
- PEFT 0.12.0
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 2
Model tree for zbigi/bart-base-summarization-medical-45
Base model
facebook/bart-base