metadata
license: apache-2.0
base_model: facebook/bart-base
tags:
- generated_from_trainer
model-index:
- name: pubmed-abs-sub-04
results: []
pubmed-abs-sub-04
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: 0.1828
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: 32
- eval_batch_size: 32
- 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 |
|---|---|---|---|
| 0.4621 | 0.21 | 500 | 0.3522 |
| 0.3527 | 0.43 | 1000 | 0.2873 |
| 0.298 | 0.64 | 1500 | 0.2523 |
| 0.2818 | 0.86 | 2000 | 0.2292 |
| 0.2317 | 1.07 | 2500 | 0.2204 |
| 0.2232 | 1.28 | 3000 | 0.2125 |
| 0.2191 | 1.5 | 3500 | 0.2045 |
| 0.1944 | 1.71 | 4000 | 0.1971 |
| 0.1707 | 1.93 | 4500 | 0.1931 |
| 0.1446 | 2.14 | 5000 | 0.1914 |
| 0.139 | 2.35 | 5500 | 0.1882 |
| 0.1345 | 2.57 | 6000 | 0.1844 |
| 0.1416 | 2.78 | 6500 | 0.1843 |
| 0.1635 | 3.0 | 7000 | 0.1828 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3