|
--- |
|
license: apache-2.0 |
|
base_model: facebook/bart-base |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: pubmed-abs-ins-con-04 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# pubmed-abs-ins-con-04 |
|
|
|
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co./facebook/bart-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0614 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
| 0.1838 | 0.11 | 500 | 0.1188 | |
|
| 0.1451 | 0.21 | 1000 | 0.1138 | |
|
| 0.1363 | 0.32 | 1500 | 0.0935 | |
|
| 0.2084 | 0.43 | 2000 | 0.0868 | |
|
| 0.1054 | 0.54 | 2500 | 0.0866 | |
|
| 0.1228 | 0.64 | 3000 | 0.0789 | |
|
| 0.0911 | 0.75 | 3500 | 0.0771 | |
|
| 0.1134 | 0.86 | 4000 | 0.0733 | |
|
| 0.0853 | 0.96 | 4500 | 0.0727 | |
|
| 0.0822 | 1.07 | 5000 | 0.0734 | |
|
| 0.0699 | 1.18 | 5500 | 0.0716 | |
|
| 0.0767 | 1.28 | 6000 | 0.0741 | |
|
| 0.0675 | 1.39 | 6500 | 0.0713 | |
|
| 0.0724 | 1.5 | 7000 | 0.0693 | |
|
| 0.0643 | 1.61 | 7500 | 0.0674 | |
|
| 0.0614 | 1.71 | 8000 | 0.0668 | |
|
| 0.1225 | 1.82 | 8500 | 0.0633 | |
|
| 0.0704 | 1.93 | 9000 | 0.0623 | |
|
| 0.055 | 2.03 | 9500 | 0.0660 | |
|
| 0.0567 | 2.14 | 10000 | 0.0633 | |
|
| 0.052 | 2.25 | 10500 | 0.0658 | |
|
| 0.0459 | 2.35 | 11000 | 0.0644 | |
|
| 0.0572 | 2.46 | 11500 | 0.0628 | |
|
| 0.0604 | 2.57 | 12000 | 0.0615 | |
|
| 0.0516 | 2.68 | 12500 | 0.0611 | |
|
| 0.0424 | 2.78 | 13000 | 0.0616 | |
|
| 0.0385 | 2.89 | 13500 | 0.0615 | |
|
| 0.0448 | 3.0 | 14000 | 0.0614 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.1 |
|
- Pytorch 2.1.0 |
|
- Datasets 2.14.7 |
|
- Tokenizers 0.14.1 |
|
|