metadata
license: mit
base_model: facebook/bart-large-cnn
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: ATS-Bart-Large-CNN
results: []
ATS-Bart-Large-CNN
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: 1.1044
- Rouge1: 0.6648
- Rouge2: 0.4542
- Rougel: 0.5743
- Rougelsum: 0.5743
- Gen Len: 79.5693
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: 8
- eval_batch_size: 8
- 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 | 274 | 0.8020 | 0.6276 | 0.3994 | 0.5208 | 0.5212 | 77.3942 |
| 0.7545 | 2.0 | 548 | 0.8005 | 0.6469 | 0.4278 | 0.5488 | 0.5488 | 79.8577 |
| 0.7545 | 3.0 | 822 | 0.8290 | 0.6533 | 0.4371 | 0.56 | 0.56 | 78.7865 |
| 0.3296 | 4.0 | 1096 | 0.8996 | 0.6581 | 0.4439 | 0.5636 | 0.5637 | 78.8522 |
| 0.3296 | 5.0 | 1370 | 0.9740 | 0.6602 | 0.4486 | 0.5644 | 0.5645 | 78.8869 |
| 0.1575 | 6.0 | 1644 | 1.0374 | 0.6617 | 0.4493 | 0.5689 | 0.5687 | 78.7974 |
| 0.1575 | 7.0 | 1918 | 1.0972 | 0.6613 | 0.4513 | 0.5706 | 0.5706 | 79.9069 |
| 0.0868 | 8.0 | 2192 | 1.1044 | 0.6648 | 0.4542 | 0.5743 | 0.5743 | 79.5693 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1