metadata
license: apache-2.0
base_model: facebook/bart-base
tags:
- generated_from_trainer
model-index:
- name: test-case-bart
results: []
test-case-bart
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: 0.3864
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: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7423 | 1.0 | 284 | 0.5396 |
| 0.4034 | 2.0 | 568 | 0.4471 |
| 0.3873 | 3.0 | 852 | 0.4062 |
| 0.3427 | 4.0 | 1136 | 0.3816 |
| 0.1896 | 5.0 | 1420 | 0.3715 |
| 0.2805 | 6.0 | 1704 | 0.3745 |
| 0.2514 | 7.0 | 1988 | 0.3745 |
| 0.2622 | 8.0 | 2272 | 0.3818 |
| 0.2816 | 9.0 | 2556 | 0.3817 |
| 0.1705 | 10.0 | 2840 | 0.3864 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Tokenizers 0.15.2