|
--- |
|
license: apache-2.0 |
|
base_model: facebook/bart-base |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: pubmed-mixed-noise-v3-0.5 |
|
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-mixed-noise-v3-0.5 |
|
|
|
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: 0.8977 |
|
|
|
## 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 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
| 1.6463 | 0.11 | 500 | 1.4928 | |
|
| 1.4367 | 0.21 | 1000 | 1.3112 | |
|
| 1.3415 | 0.32 | 1500 | 1.2125 | |
|
| 1.2466 | 0.43 | 2000 | 1.1661 | |
|
| 1.1417 | 0.54 | 2500 | 1.1133 | |
|
| 1.1749 | 0.64 | 3000 | 1.0694 | |
|
| 1.1272 | 0.75 | 3500 | 1.0524 | |
|
| 1.1683 | 0.86 | 4000 | 1.0289 | |
|
| 1.0353 | 0.96 | 4500 | 1.0149 | |
|
| 0.9557 | 1.07 | 5000 | 1.0026 | |
|
| 0.9627 | 1.18 | 5500 | 0.9882 | |
|
| 0.9371 | 1.28 | 6000 | 0.9813 | |
|
| 0.9498 | 1.39 | 6500 | 0.9642 | |
|
| 0.9903 | 1.5 | 7000 | 0.9578 | |
|
| 0.9031 | 1.61 | 7500 | 0.9493 | |
|
| 0.8613 | 1.71 | 8000 | 0.9403 | |
|
| 0.8746 | 1.82 | 8500 | 0.9345 | |
|
| 0.8455 | 1.93 | 9000 | 0.9277 | |
|
| 0.7622 | 2.03 | 9500 | 0.9284 | |
|
| 0.7276 | 2.14 | 10000 | 0.9206 | |
|
| 0.7861 | 2.25 | 10500 | 0.9218 | |
|
| 0.8205 | 2.35 | 11000 | 0.9181 | |
|
| 0.7348 | 2.46 | 11500 | 0.9092 | |
|
| 0.792 | 2.57 | 12000 | 0.9061 | |
|
| 0.7531 | 2.68 | 12500 | 0.9034 | |
|
| 0.7652 | 2.78 | 13000 | 0.9013 | |
|
| 0.7635 | 2.89 | 13500 | 0.8974 | |
|
| 0.7748 | 3.0 | 14000 | 0.8977 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.1 |
|
- Pytorch 2.0.1 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.0 |
|
|
