metadata
license: apache-2.0
base_model: facebook/bart-base
tags:
- generated_from_trainer
model-index:
- name: pubmed-mixed-noise-v3-0.1
results: []
pubmed-mixed-noise-v3-0.1
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: 0.2607
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 |
|---|---|---|---|
| 0.5222 | 0.11 | 500 | 0.4206 |
| 0.3862 | 0.21 | 1000 | 0.3907 |
| 0.4108 | 0.32 | 1500 | 0.3568 |
| 0.3871 | 0.43 | 2000 | 0.3415 |
| 0.3846 | 0.54 | 2500 | 0.3240 |
| 0.3313 | 0.64 | 3000 | 0.3124 |
| 0.3317 | 0.75 | 3500 | 0.3066 |
| 0.3136 | 0.86 | 4000 | 0.3049 |
| 0.3267 | 0.96 | 4500 | 0.2925 |
| 0.2816 | 1.07 | 5000 | 0.2929 |
| 0.2421 | 1.18 | 5500 | 0.2882 |
| 0.2643 | 1.28 | 6000 | 0.2872 |
| 0.2776 | 1.39 | 6500 | 0.2824 |
| 0.2854 | 1.5 | 7000 | 0.2751 |
| 0.2301 | 1.61 | 7500 | 0.2756 |
| 0.2118 | 1.71 | 8000 | 0.2770 |
| 0.2079 | 1.82 | 8500 | 0.2732 |
| 0.2474 | 1.93 | 9000 | 0.2631 |
| 0.1482 | 2.03 | 9500 | 0.2693 |
| 0.1908 | 2.14 | 10000 | 0.2656 |
| 0.2017 | 2.25 | 10500 | 0.2647 |
| 0.1687 | 2.35 | 11000 | 0.2680 |
| 0.191 | 2.46 | 11500 | 0.2630 |
| 0.1821 | 2.57 | 12000 | 0.2618 |
| 0.2301 | 2.68 | 12500 | 0.2605 |
| 0.2106 | 2.78 | 13000 | 0.2601 |
| 0.1637 | 2.89 | 13500 | 0.2617 |
| 0.1902 | 3.0 | 14000 | 0.2607 |
Framework versions
- Transformers 4.36.1
- Pytorch 2.0.1
- Datasets 2.16.1
- Tokenizers 0.15.0