bart-base-large-peft
This model is a fine-tuned version of facebook/bart-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.6188
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: 0.005
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.9432 | 1.0 | 843 | 3.7161 |
| 3.916 | 2.0 | 1686 | 3.6846 |
| 3.8955 | 3.0 | 2529 | 3.6695 |
| 3.8601 | 4.0 | 3372 | 3.6538 |
| 3.8141 | 5.0 | 4215 | 3.6188 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1
Model tree for alitolga/bart-base-large-peft
Base model
facebook/bart-base