bart-base_ft_2_ep_bz_16_on_vnx_dev_by_hydra_1751818928_
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: 5.6581
- Rouge1: 39.6082
- Rouge2: 12.358
- Rougel: 25.4344
- Rougelsum: 27.1483
- Gen Len: 20.2469
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: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 166 | 5.7523 | 39.3729 | 12.3641 | 25.3123 | 27.1008 | 19.858 |
| No log | 2.0 | 332 | 5.6581 | 39.6082 | 12.358 | 25.4344 | 27.1483 | 20.2469 |
Framework versions
- Transformers 4.53.1
- Pytorch 2.7.1+cu128
- Datasets 3.6.0
- Tokenizers 0.21.2