metadata
library_name: transformers
license: apache-2.0
base_model: sshleifer/distilbart-xsum-12-6
tags:
- generated_from_trainer
model-index:
- name: bart-abs-2409-1947-lr-3e-06-bs-4-maxep-6
results: []
bart-abs-2409-1947-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: 7.3666
- Rouge/rouge1: 0.2722
- Rouge/rouge2: 0.0714
- Rouge/rougel: 0.2029
- Rouge/rougelsum: 0.2031
- Bertscore/bertscore-precision: 0.8612
- Bertscore/bertscore-recall: 0.8618
- Bertscore/bertscore-f1: 0.8615
- Meteor: 0.2582
- Gen Len: 44.0
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.2442 | 1.0 | 217 | 7.1796 | 0.2722 | 0.0714 | 0.2029 | 0.2031 | 0.8612 | 0.8618 | 0.8615 | 0.2582 | 44.0 |
| 0.2514 | 2.0 | 434 | 7.2470 | 0.2722 | 0.0714 | 0.2029 | 0.2031 | 0.8612 | 0.8618 | 0.8615 | 0.2582 | 44.0 |
| 0.2226 | 3.0 | 651 | 7.2953 | 0.2722 | 0.0714 | 0.2029 | 0.2031 | 0.8612 | 0.8618 | 0.8615 | 0.2582 | 44.0 |
| 0.2207 | 4.0 | 868 | 7.3342 | 0.2722 | 0.0714 | 0.2029 | 0.2031 | 0.8612 | 0.8618 | 0.8615 | 0.2582 | 44.0 |
| 0.2177 | 5.0 | 1085 | 7.3588 | 0.2722 | 0.0714 | 0.2029 | 0.2031 | 0.8612 | 0.8618 | 0.8615 | 0.2582 | 44.0 |
| 0.2176 | 6.0 | 1302 | 7.3666 | 0.2722 | 0.0714 | 0.2029 | 0.2031 | 0.8612 | 0.8618 | 0.8615 | 0.2582 | 44.0 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0
- Datasets 3.0.0
- Tokenizers 0.19.1