bart-base_ep_2_bz_32_dt_vnx_dev_hydra_1751819165_
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: 5.8717
- Rouge1: 40.1343
- Rouge2: 12.4163
- Rougel: 25.7421
- Rougelsum: 27.5582
- Gen Len: 20.3241
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: 32
- eval_batch_size: 32
- 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 | 83 | 5.9402 | 38.6233 | 11.9291 | 24.8259 | 26.5956 | 19.8302 |
| No log | 2.0 | 166 | 5.8717 | 40.1343 | 12.4163 | 25.7421 | 27.5582 | 20.3241 |
Framework versions
- Transformers 4.53.1
- Pytorch 2.7.1+cu128
- Datasets 3.6.0
- Tokenizers 0.21.2