led-base-16384-biolaysum-plos-baseline
This model is a fine-tuned version of allenai/led-base-16384 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.1835
- Rouge1: 0.4580
- Rouge2: 0.1614
- Rougel: 0.2502
- Rougelsum: 0.2502
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: 5e-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: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 2.4366 | 0.16 | 1000 | 2.3373 | 0.4497 | 0.1584 | 0.2476 | 0.2476 |
| 2.3531 | 0.32 | 2000 | 2.3002 | 0.4468 | 0.1523 | 0.2439 | 0.2438 |
| 2.3102 | 0.48 | 3000 | 2.2368 | 0.4531 | 0.1549 | 0.2436 | 0.2437 |
| 2.2755 | 0.65 | 4000 | 2.2092 | 0.4568 | 0.1585 | 0.2478 | 0.2477 |
| 2.244 | 0.81 | 5000 | 2.1835 | 0.4580 | 0.1614 | 0.2502 | 0.2502 |
| 2.2353 | 0.97 | 6000 | 2.1693 | 0.4565 | 0.1586 | 0.2478 | 0.2477 |
| 2.0477 | 1.13 | 7000 | 2.1620 | 0.4561 | 0.1585 | 0.2478 | 0.2478 |
| 2.0493 | 1.29 | 8000 | 2.1438 | 0.4515 | 0.1530 | 0.2426 | 0.2426 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1
- Datasets 2.10.1
- Tokenizers 0.12.1