metadata
library_name: transformers
license: apache-2.0
base_model: facebook/bart-base
tags:
- generated_from_trainer
model-index:
- name: anlp_bart_level_aware
results: []
anlp_bart_level_aware
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: 0.8295
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: 3e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9928 | 1.0 | 282 | 0.8691 |
| 0.8659 | 2.0 | 564 | 0.8382 |
| 0.8021 | 3.0 | 846 | 0.8223 |
| 0.7573 | 4.0 | 1128 | 0.8222 |
| 0.7233 | 5.0 | 1410 | 0.8196 |
| 0.6797 | 6.0 | 1692 | 0.8185 |
| 0.663 | 7.0 | 1974 | 0.8195 |
| 0.6427 | 8.0 | 2256 | 0.8198 |
| 0.6308 | 9.0 | 2538 | 0.8273 |
| 0.6161 | 10.0 | 2820 | 0.8295 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.9.1+cu128
- Datasets 4.4.1
- Tokenizers 0.22.2