|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
base_model: facebook/bart-large |
|
model-index: |
|
- name: bart-finetuned-kwsylgen-64-simple_input_BARTlarge |
|
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. --> |
|
|
|
# bart-finetuned-kwsylgen-64-simple_input_BARTlarge |
|
|
|
This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/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 |
|
|
