BARTBana_v4
This model is a fine-tuned version of IAmSkyDra/BARTBana_v3 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9365
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.1191 | 1.0 | 6519 | 1.1595 |
| 1.0149 | 2.0 | 13038 | 1.0606 |
| 0.9759 | 3.0 | 19557 | 1.0451 |
| 0.9603 | 4.0 | 26076 | 0.9603 |
| 1.0066 | 5.0 | 32595 | 0.9281 |
Framework versions
- Transformers 4.48.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 23
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.