led-base-16384-biolaysum-both-with_references
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: 2.1595
- Rouge1: 0.4548
- Rouge2: 0.1555
- Rougel: 0.2435
- Rougelsum: 0.2435
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 |
|---|---|---|---|---|---|---|---|
| 2.2751 | 0.69 | 5000 | 2.2219 | 0.4488 | 0.1496 | 0.2392 | 0.2392 |
| 2.0407 | 1.37 | 10000 | 2.1595 | 0.4548 | 0.1555 | 0.2435 | 0.2435 |
| 1.9246 | 2.06 | 15000 | 2.1263 | 0.4537 | 0.1522 | 0.2395 | 0.2396 |
| 1.9066 | 2.75 | 20000 | 2.1091 | 0.4562 | 0.1538 | 0.2409 | 0.2409 |
| 1.7802 | 3.43 | 25000 | 2.0998 | 0.4539 | 0.1523 | 0.2411 | 0.2411 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1
- Datasets 2.10.1
- Tokenizers 0.12.1