<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
distilbart-cnn-12-6-finetuned-roundup-4-8
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: 0.8447
- Rouge1: 54.3326
- Rouge2: 36.1031
- Rougel: 38.842
- Rougelsum: 51.7632
- Gen Len: 142.0
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: 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: 8
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
---|---|---|---|---|---|---|---|---|
No log | 1.0 | 398 | 1.1572 | 51.6618 | 32.7542 | 34.8631 | 49.2691 | 141.3333 |
1.405 | 2.0 | 796 | 1.0039 | 52.2029 | 32.6704 | 34.4948 | 50.1141 | 142.0 |
0.9039 | 3.0 | 1194 | 0.9300 | 53.2839 | 34.3928 | 36.8971 | 51.1148 | 142.0 |
0.6705 | 4.0 | 1592 | 0.8708 | 52.5229 | 33.8116 | 36.9664 | 50.0067 | 142.0 |
0.6705 | 5.0 | 1990 | 0.8508 | 53.4468 | 35.1394 | 38.4144 | 50.794 | 142.0 |
0.5205 | 6.0 | 2388 | 0.8347 | 53.8859 | 35.1182 | 38.1126 | 51.3089 | 142.0 |
0.3898 | 7.0 | 2786 | 0.8406 | 54.2293 | 36.1189 | 38.7127 | 51.6878 | 142.0 |
0.3468 | 8.0 | 3184 | 0.8447 | 54.3326 | 36.1031 | 38.842 | 51.7632 | 142.0 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0+cu113
- Datasets 2.1.0
- Tokenizers 0.12.1