<!-- 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-3-4
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: 1.1949
- Rouge1: 49.6216
- Rouge2: 29.1874
- Rougel: 32.042
- Rougelsum: 46.3679
- Gen Len: 140.9688
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 | 258 | 1.2708 | 48.8914 | 29.2868 | 30.6203 | 46.2886 | 142.0 |
1.1751 | 2.0 | 516 | 1.1869 | 49.3567 | 28.4751 | 31.3075 | 46.3408 | 141.75 |
1.1751 | 3.0 | 774 | 1.1869 | 48.8335 | 28.4976 | 30.5434 | 46.2584 | 141.625 |
0.7391 | 4.0 | 1032 | 1.1949 | 49.6216 | 29.1874 | 32.042 | 46.3679 | 140.9688 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0+cu113
- Datasets 2.1.0
- Tokenizers 0.12.1