metadata
license: apache-2.0
base_model: sshleifer/distilbart-xsum-12-6
tags:
- generated_from_trainer
model-index:
- name: bart-abs-1509-0313-lr-3e-06-bs-4-maxep-6
results: []
bart-abs-1509-0313-lr-3e-06-bs-4-maxep-6
This model is a fine-tuned version of sshleifer/distilbart-xsum-12-6 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 6.1788
- Rouge/rouge1: 0.3111
- Rouge/rouge2: 0.0793
- Rouge/rougel: 0.2212
- Rouge/rougelsum: 0.2213
- Bertscore/bertscore-precision: 0.8659
- Bertscore/bertscore-recall: 0.864
- Bertscore/bertscore-f1: 0.8649
- Meteor: 0.228
- Gen Len: 36.0
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: 3e-06
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge/rouge1 | Rouge/rouge2 | Rouge/rougel | Rouge/rougelsum | Bertscore/bertscore-precision | Bertscore/bertscore-recall | Bertscore/bertscore-f1 | Meteor | Gen Len |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.5854 | 1.0 | 217 | 5.7937 | 0.2578 | 0.0526 | 0.1861 | 0.1862 | 0.8466 | 0.8559 | 0.8512 | 0.265 | 55.0 |
| 0.5363 | 2.0 | 434 | 5.9473 | 0.2723 | 0.0677 | 0.226 | 0.2265 | 0.8613 | 0.855 | 0.8581 | 0.2229 | 30.0 |
| 0.4911 | 3.0 | 651 | 6.0403 | 0.3064 | 0.0749 | 0.2182 | 0.2185 | 0.865 | 0.8652 | 0.8651 | 0.2255 | 37.0 |
| 0.4651 | 4.0 | 868 | 6.1046 | 0.3064 | 0.0749 | 0.2182 | 0.2185 | 0.865 | 0.8652 | 0.8651 | 0.2255 | 37.0 |
| 0.4476 | 5.0 | 1085 | 6.1659 | 0.3111 | 0.0793 | 0.2212 | 0.2213 | 0.8659 | 0.864 | 0.8649 | 0.228 | 36.0 |
| 0.4415 | 6.0 | 1302 | 6.1788 | 0.3111 | 0.0793 | 0.2212 | 0.2213 | 0.8659 | 0.864 | 0.8649 | 0.228 | 36.0 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1