<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
bart-large-cnn-finetuned-roundup-4
This model is a fine-tuned version of facebook/bart-large-cnn on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.2573
- Rouge1: 49.0193
- Rouge2: 28.6311
- Rougel: 31.3363
- Rougelsum: 46.1408
- Gen Len: 142.0
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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 132 | 1.3178 | 48.4526 | 28.6361 | 30.2875 | 45.4822 | 142.0 |
| No log | 2.0 | 264 | 1.2404 | 48.139 | 28.2459 | 29.3584 | 45.0785 | 142.0 |
| No log | 3.0 | 396 | 1.2389 | 49.74 | 29.7834 | 33.143 | 46.8147 | 142.0 |
| 0.9855 | 4.0 | 528 | 1.2573 | 49.0193 | 28.6311 | 31.3363 | 46.1408 | 142.0 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0+cu113
- Datasets 2.1.0
- Tokenizers 0.12.1
