bart-base_ep_3_bz_32_dt_vnx_dev_1024_128_hydra_1751900347_
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: 5.6896
- Rouge1: 39.9687
- Rouge2: 12.7057
- Rougel: 25.5104
- Rougelsum: 27.3363
- Gen Len: 20.3056
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: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 83 | 5.9137 | 38.3219 | 11.9139 | 24.7194 | 26.4365 | 19.5802 |
| No log | 2.0 | 166 | 5.7649 | 40.1187 | 12.4322 | 25.705 | 27.5445 | 20.4506 |
| No log | 3.0 | 249 | 5.6896 | 39.9687 | 12.7057 | 25.5104 | 27.3363 | 20.3056 |
Framework versions
- Transformers 4.53.1
- Pytorch 2.7.1+cu128
- Datasets 3.6.0
- Tokenizers 0.21.2