metadata
license: mit
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: bart-large-cnn-10k-pad-early-lit
results: []
bart-large-cnn-10k-pad-early-lit
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: 0.3758
- Rouge1: 27.7351
- Rouge2: 13.1664
- Rougel: 21.6559
- Rougelsum: 24.648
- Gen Len: 69.343
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: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 0.2516 | 1.0 | 9998 | 0.3540 | 28.1151 | 13.3875 | 22.1496 | 25.1745 | 66.578 |
| 0.1747 | 2.0 | 19996 | 0.3758 | 27.7351 | 13.1664 | 21.6559 | 24.648 | 69.343 |
Framework versions
- Transformers 4.16.2
- Pytorch 1.10.2
- Datasets 1.18.3
- Tokenizers 0.11.0