metadata
license: mit
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: bart-large-cnn-finetuned-roundup-4-8
results: []
bart-large-cnn-finetuned-roundup-4-8
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: 0.7790
- Rouge1: 54.3036
- Rouge2: 37.1443
- Rougel: 40.4762
- Rougelsum: 52.1796
- 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: 8
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
---|---|---|---|---|---|---|---|---|
No log | 1.0 | 398 | 0.9580 | 52.5184 | 33.0208 | 35.0634 | 49.9083 | 142.0 |
1.119 | 2.0 | 796 | 0.8356 | 53.0801 | 34.5549 | 36.9807 | 50.3394 | 141.2963 |
0.6814 | 3.0 | 1194 | 0.7968 | 53.9433 | 34.8086 | 36.7654 | 51.3384 | 142.0 |
0.4623 | 4.0 | 1592 | 0.7474 | 53.947 | 36.2662 | 39.332 | 51.7559 | 142.0 |
0.4623 | 5.0 | 1990 | 0.7563 | 54.5816 | 37.0675 | 40.3592 | 52.2391 | 142.0 |
0.3228 | 6.0 | 2388 | 0.7383 | 54.787 | 37.3647 | 40.521 | 52.3113 | 142.0 |
0.2183 | 7.0 | 2786 | 0.7606 | 54.1822 | 37.6748 | 40.7956 | 52.1102 | 141.7778 |
0.1759 | 8.0 | 3184 | 0.7790 | 54.3036 | 37.1443 | 40.4762 | 52.1796 | 142.0 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0+cu113
- Datasets 2.1.0
- Tokenizers 0.12.1