metadata
license: apache-2.0
tags:
- generated_from_trainer
base_model: facebook/bart-large
model-index:
- name: bart-finetuned-kwsylgen-64-simple_input_BARTlarge
results: []
bart-finetuned-kwsylgen-64-simple_input_BARTlarge
This model is a fine-tuned version of facebook/bart-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1785
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: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.0641 | 0.18 | 500 | 0.2451 |
| 0.2194 | 0.36 | 1000 | 0.2228 |
| 0.1989 | 0.54 | 1500 | 0.2086 |
| 0.1888 | 0.72 | 2000 | 0.2027 |
| 0.177 | 0.9 | 2500 | 0.1976 |
| 0.1703 | 1.08 | 3000 | 0.1933 |
| 0.1647 | 1.26 | 3500 | 0.1928 |
| 0.159 | 1.44 | 4000 | 0.1890 |
| 0.1538 | 1.61 | 4500 | 0.1864 |
| 0.151 | 1.79 | 5000 | 0.1857 |
| 0.1471 | 1.97 | 5500 | 0.1828 |
| 0.1436 | 2.15 | 6000 | 0.1814 |
| 0.1435 | 2.33 | 6500 | 0.1806 |
| 0.141 | 2.51 | 7000 | 0.1799 |
| 0.1393 | 2.69 | 7500 | 0.1790 |
| 0.1388 | 2.87 | 8000 | 0.1785 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2