metadata
license: apache-2.0
base_model: facebook/bart-base
tags:
- generated_from_trainer
model-index:
- name: results
results: []
results
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: 0.2933
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 |
|---|---|---|---|
| 2.5922 | 1.0 | 176 | 1.6306 |
| 0.5199 | 2.0 | 352 | 0.3777 |
| 0.4592 | 3.0 | 528 | 0.3371 |
| 0.3187 | 4.0 | 704 | 0.3111 |
| 0.3016 | 5.0 | 880 | 0.2977 |
| 0.2335 | 6.0 | 1056 | 0.2938 |
| 0.1684 | 7.0 | 1232 | 0.2874 |
| 0.1294 | 8.0 | 1408 | 0.2960 |
| 0.1348 | 9.0 | 1584 | 0.2924 |
| 0.137 | 10.0 | 1760 | 0.2933 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Tokenizers 0.15.2