<!-- 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-1000-lit-evalMA-NOpad
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: 1.9804
- Rouge1: 27.2698
- Rouge2: 11.8561
- Rougel: 20.5948
- Rougelsum: 23.5497
- Gen Len: 67.67
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: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 1.5372 | 1.0 | 1000 | 1.7499 | 27.7275 | 12.7894 | 21.1334 | 24.4929 | 66.31 |
| 0.7344 | 2.0 | 2000 | 1.9804 | 27.2698 | 11.8561 | 20.5948 | 23.5497 | 67.67 |
Framework versions
- Transformers 4.16.2
- Pytorch 1.10.2
- Datasets 1.18.3
- Tokenizers 0.11.0
