metadata
library_name: transformers
license: apache-2.0
base_model: sshleifer/distilbart-cnn-12-6
tags:
- generated_from_trainer
datasets:
- samsum
metrics:
- rouge
model-index:
- name: distilbart-cnn-12-6-finetuned-samsum
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: samsum
type: samsum
config: samsum
split: validation
args: samsum
metrics:
- name: Rouge1
type: rouge
value: 41.0877
distilbart-cnn-12-6-finetuned-samsum
This model is a fine-tuned version of sshleifer/distilbart-cnn-12-6 on the samsum dataset. It achieves the following results on the evaluation set:
- Loss: 0.5352
- Rouge1: 41.0877
- Rouge2: 21.1031
- Rougel: 31.6773
- Rougelsum: 38.2167
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 0.3755 | 1.0 | 921 | 0.5071 | 40.4969 | 21.1036 | 31.4303 | 37.8602 |
| 0.3724 | 2.0 | 1842 | 0.5211 | 40.6622 | 20.7737 | 31.3884 | 37.7896 |
| 0.3157 | 3.0 | 2763 | 0.5352 | 41.0877 | 21.1031 | 31.6773 | 38.2167 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1