fine_tuned_bart_on_vnx_1751603301_
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: 5.0216
- Rouge1: 0.4213
- Rouge2: 0.1226
- Rougel: 0.268
- Rougelsum: 0.2677
- Gen Len: 20.6728
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: 16
- eval_batch_size: 16
- 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: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 166 | 5.4541 | 0.3779 | 0.1069 | 0.2435 | 0.2432 | 19.0802 |
| No log | 2.0 | 332 | 5.2755 | 0.4048 | 0.1146 | 0.2575 | 0.2573 | 20.287 |
| No log | 3.0 | 498 | 5.1766 | 0.4135 | 0.1233 | 0.2658 | 0.2656 | 20.4167 |
| 5.7087 | 4.0 | 664 | 5.1612 | 0.4084 | 0.1214 | 0.2631 | 0.2631 | 20.4691 |
| 5.7087 | 5.0 | 830 | 5.0639 | 0.4054 | 0.1157 | 0.2594 | 0.2593 | 20.5309 |
| 5.7087 | 6.0 | 996 | 5.0617 | 0.4176 | 0.1235 | 0.2665 | 0.2662 | 20.4321 |
| 5.0805 | 7.0 | 1162 | 5.0810 | 0.4139 | 0.1259 | 0.2664 | 0.2655 | 20.5617 |
| 5.0805 | 8.0 | 1328 | 5.0307 | 0.4181 | 0.1241 | 0.2666 | 0.2664 | 20.4691 |
| 5.0805 | 9.0 | 1494 | 5.0209 | 0.4256 | 0.1285 | 0.2711 | 0.2709 | 20.5895 |
| 4.8766 | 10.0 | 1660 | 5.0216 | 0.4213 | 0.1226 | 0.268 | 0.2677 | 20.6728 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.7.0+cu126
- Datasets 3.5.1
- Tokenizers 0.21.1