metadata
license: apache-2.0
base_model: stevhliu/my_awesome_billsum_model
tags:
- generated_from_trainer
datasets:
- multi_news
metrics:
- rouge
model-index:
- name: my_awesome_multinews_model
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: multi_news
type: multi_news
config: default
split: validation
args: default
metrics:
- name: Rouge1
type: rouge
value: 0.1416
my_awesome_multinews_model
This model is a fine-tuned version of stevhliu/my_awesome_billsum_model on the multi_news dataset. It achieves the following results on the evaluation set:
- Loss: 2.8031
- Rouge1: 0.1416
- Rouge2: 0.0452
- Rougel: 0.1098
- Rougelsum: 0.1099
- Gen Len: 19.0
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: 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: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 282 | 2.8803 | 0.1378 | 0.0427 | 0.1067 | 0.1067 | 19.0 |
| 3.1546 | 2.0 | 564 | 2.8260 | 0.1393 | 0.043 | 0.1077 | 0.1077 | 19.0 |
| 3.1546 | 3.0 | 846 | 2.8089 | 0.1418 | 0.0452 | 0.1096 | 0.1096 | 19.0 |
| 3.0357 | 4.0 | 1128 | 2.8031 | 0.1416 | 0.0452 | 0.1098 | 0.1099 | 19.0 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1