metadata
license: apache-2.0
base_model: facebook/bart-base
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: bart-base-finetuned-cnn_dailymail
results: []
bart-base-finetuned-cnn_dailymail
This model is a fine-tuned version of facebook/bart-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0624
- Rouge1: 24.4564
- Rouge2: 11.9696
- Rougel: 20.5207
- Rougelsum: 23.0078
- Bleu 1: 4.1113
- Bleu 2: 2.692
- Bleu 3: 1.9585
- Meteor: 12.0483
- Compression rate: 4.07
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: 5.6e-05
- train_batch_size: 16
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Bleu 1 | Bleu 2 | Bleu 3 | Meteor | Compression rate |
---|---|---|---|---|---|---|---|---|---|---|---|---|
1.3117 | 1.0 | 1875 | 1.0873 | 24.4119 | 11.8902 | 20.5092 | 22.8997 | 4.1432 | 2.7081 | 1.9647 | 12.0394 | 4.0945 |
1.0667 | 2.0 | 3750 | 1.0588 | 24.364 | 11.9692 | 20.3498 | 22.8133 | 4.0425 | 2.6521 | 1.9328 | 11.9475 | 4.1164 |
0.9644 | 3.0 | 5625 | 1.0564 | 24.2853 | 11.9445 | 20.4585 | 22.8519 | 4.0533 | 2.6698 | 1.9457 | 11.9912 | 4.1173 |
0.8876 | 4.0 | 7500 | 1.0519 | 24.2696 | 11.8337 | 20.3562 | 22.8098 | 4.1164 | 2.698 | 1.9479 | 11.9819 | 4.0777 |
0.8301 | 5.0 | 9375 | 1.0556 | 24.393 | 11.9329 | 20.4502 | 22.9487 | 4.116 | 2.693 | 1.9458 | 11.9937 | 4.0738 |
0.7897 | 6.0 | 11250 | 1.0624 | 24.4564 | 11.9696 | 20.5207 | 23.0078 | 4.1113 | 2.692 | 1.9585 | 12.0483 | 4.07 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.2.2+cu118
- Datasets 2.19.0
- Tokenizers 0.19.1