metadata
license: mit
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: bart-large-cnn-finetuned-p7_V2
results: []
bart-large-cnn-finetuned-p7_V2
This model is a fine-tuned version of facebook/bart-large-cnn on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0742
- Rouge1: 54.2238
- Rouge2: 44.1502
- Rougel: 49.9702
- Rougelsum: 51.9939
- Gen Len: 65.3454
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: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 0.6948 | 1.0 | 910 | 0.8121 | 51.6637 | 41.9437 | 48.1988 | 49.7012 | 68.7993 |
| 0.3042 | 2.0 | 1820 | 0.9086 | 52.4291 | 42.1856 | 48.6079 | 50.2419 | 66.2829 |
| 0.1471 | 3.0 | 2730 | 1.0742 | 54.2238 | 44.1502 | 49.9702 | 51.9939 | 65.3454 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3