pubmed-abs-noise-03
This model is a fine-tuned version of facebook/bart-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4432
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7656 | 0.11 | 500 | 0.6197 |
| 0.648 | 0.21 | 1000 | 0.5950 |
| 0.6307 | 0.32 | 1500 | 0.5712 |
| 0.6847 | 0.43 | 2000 | 0.5361 |
| 0.5841 | 0.54 | 2500 | 0.5333 |
| 0.5418 | 0.64 | 3000 | 0.5195 |
| 0.5303 | 0.75 | 3500 | 0.5068 |
| 0.5555 | 0.86 | 4000 | 0.4948 |
| 0.5109 | 0.96 | 4500 | 0.4851 |
| 0.4823 | 1.07 | 5000 | 0.4866 |
| 0.491 | 1.18 | 5500 | 0.4793 |
| 0.441 | 1.28 | 6000 | 0.4825 |
| 0.4939 | 1.39 | 6500 | 0.4730 |
| 0.4425 | 1.5 | 7000 | 0.4715 |
| 0.4942 | 1.61 | 7500 | 0.4676 |
| 0.4256 | 1.71 | 8000 | 0.4593 |
| 0.5072 | 1.82 | 8500 | 0.4587 |
| 0.4215 | 1.93 | 9000 | 0.4561 |
| 0.3497 | 2.03 | 9500 | 0.4589 |
| 0.3899 | 2.14 | 10000 | 0.4575 |
| 0.3759 | 2.25 | 10500 | 0.4545 |
| 0.3637 | 2.35 | 11000 | 0.4535 |
| 0.3997 | 2.46 | 11500 | 0.4456 |
| 0.3496 | 2.57 | 12000 | 0.4466 |
| 0.3409 | 2.68 | 12500 | 0.4460 |
| 0.3575 | 2.78 | 13000 | 0.4440 |
| 0.3925 | 2.89 | 13500 | 0.4427 |
| 0.3228 | 3.0 | 14000 | 0.4432 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0
- Datasets 2.14.7
- Tokenizers 0.14.1