bart-finetuned-steel-news-general
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: 1.3448
- Bertscore Precision: 50.1636
- Bertscore Recall: 48.9044
- Bertscore F1: 49.5061
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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- 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
- lr_scheduler_warmup_steps: 500
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bertscore Precision | Bertscore Recall | Bertscore F1 |
|---|---|---|---|---|---|---|
| 2.681 | 1.0 | 152 | 1.6008 | 42.9429 | 43.7367 | 43.2784 |
| 1.6115 | 2.0 | 304 | 1.4576 | 48.3023 | 48.1847 | 48.1681 |
| 1.4817 | 3.0 | 456 | 1.4068 | 48.9183 | 46.4002 | 47.5919 |
| 1.2738 | 4.0 | 608 | 1.3563 | 47.6492 | 47.8798 | 47.7005 |
| 1.1491 | 5.0 | 760 | 1.3365 | 49.1544 | 48.0816 | 48.5460 |
Framework versions
- Transformers 4.57.6
- Pytorch 2.9.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.2