metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: distilbart-cnn-12-6_1e-5
results: []
distilbart-cnn-12-6_1e-5
This model is a fine-tuned version of sshleifer/distilbart-cnn-12-6 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0778
- Rouge1: 51.4305
- Rouge2: 30.8023
- Rougel: 40.977
- Rougelsum: 45.5778
- Gen Len: 79.9607
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: 1e-05
- 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: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 1.2906 | 0.62 | 500 | 1.1144 | 49.7349 | 29.2413 | 39.062 | 43.9746 | 81.3764 |
| 1.0677 | 1.25 | 1000 | 1.0895 | 50.4239 | 30.3398 | 40.2029 | 44.8709 | 80.7528 |
| 0.9725 | 1.87 | 1500 | 1.0740 | 51.3474 | 31.1253 | 40.79 | 45.717 | 81.8455 |
| 0.8629 | 2.5 | 2000 | 1.0816 | 50.8972 | 30.6779 | 40.4662 | 45.3636 | 81.7191 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.10.0
- Tokenizers 0.13.2