metadata
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: bart-base-finetuned-cnn_dailymail
results: []
bart-base-finetuned-cnn_dailymail
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0513
- Rouge1: 24.267
- Rouge2: 11.7305
- Rougel: 20.2444
- Rougelsum: 22.6768
- Bleu 1: 4.2724
- Bleu 2: 2.7858
- Bleu 3: 2.0352
- Meteor: 12.0395
- Compression rate: 4.0329
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: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Bleu 1 | Bleu 2 | Bleu 3 | Meteor | Compression rate |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1.1979 | 1.0 | 625 | 1.0653 | 23.882 | 11.5236 | 19.9616 | 22.36 | 4.1676 | 2.7136 | 1.9845 | 11.8215 | 4.0625 |
| 1.0449 | 2.0 | 1250 | 1.0513 | 24.267 | 11.7305 | 20.2444 | 22.6768 | 4.2724 | 2.7858 | 2.0352 | 12.0395 | 4.0329 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.2.2+cu118
- Datasets 2.19.0
- Tokenizers 0.19.1