metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: distilbart-cnn-12-6-summarization_final_labeled_data
results: []
distilbart-cnn-12-6-summarization_final_labeled_data
This model is a fine-tuned version of sshleifer/distilbart-cnn-12-6 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1308
- Rouge1: 71.046
- Rouge2: 59.5936
- Rougel: 66.5089
- Rougelsum: 69.5863
- Gen Len: 120.08
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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 99 | 0.4590 | 49.5947 | 32.0274 | 39.973 | 47.0858 | 124.54 |
| No log | 2.0 | 198 | 0.2493 | 53.1348 | 36.2418 | 43.9192 | 50.68 | 120.1 |
| No log | 3.0 | 297 | 0.1645 | 63.4779 | 49.8803 | 57.8773 | 62.0455 | 116.12 |
| No log | 4.0 | 396 | 0.1344 | 68.4348 | 55.6375 | 63.3955 | 66.2623 | 124.84 |
| No log | 5.0 | 495 | 0.1308 | 71.046 | 59.5936 | 66.5089 | 69.5863 | 120.08 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1