metadata
license: apache-2.0
base_model: facebook/bart-base
tags:
- generated_from_trainer
model-index:
- name: pubmed-abs-ins-con-05
results: []
pubmed-abs-ins-con-05
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: 0.0628
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 |
|---|---|---|---|
| 0.2037 | 0.11 | 500 | 0.1196 |
| 0.1558 | 0.21 | 1000 | 0.1121 |
| 0.1542 | 0.32 | 1500 | 0.0949 |
| 0.2147 | 0.43 | 2000 | 0.0913 |
| 0.0961 | 0.54 | 2500 | 0.0884 |
| 0.108 | 0.64 | 3000 | 0.0817 |
| 0.1098 | 0.75 | 3500 | 0.0798 |
| 0.1288 | 0.86 | 4000 | 0.0771 |
| 0.0962 | 0.96 | 4500 | 0.0757 |
| 0.0858 | 1.07 | 5000 | 0.0751 |
| 0.0759 | 1.18 | 5500 | 0.0749 |
| 0.0668 | 1.28 | 6000 | 0.0755 |
| 0.0792 | 1.39 | 6500 | 0.0711 |
| 0.0906 | 1.5 | 7000 | 0.0702 |
| 0.0564 | 1.61 | 7500 | 0.0703 |
| 0.0616 | 1.71 | 8000 | 0.0682 |
| 0.12 | 1.82 | 8500 | 0.0669 |
| 0.066 | 1.93 | 9000 | 0.0651 |
| 0.0569 | 2.03 | 9500 | 0.0665 |
| 0.0576 | 2.14 | 10000 | 0.0658 |
| 0.0584 | 2.25 | 10500 | 0.0662 |
| 0.044 | 2.35 | 11000 | 0.0680 |
| 0.0598 | 2.46 | 11500 | 0.0644 |
| 0.052 | 2.57 | 12000 | 0.0641 |
| 0.0589 | 2.68 | 12500 | 0.0625 |
| 0.039 | 2.78 | 13000 | 0.0638 |
| 0.0388 | 2.89 | 13500 | 0.0637 |
| 0.0598 | 3.0 | 14000 | 0.0628 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0
- Datasets 2.14.7
- Tokenizers 0.14.1