metadata
license: apache-2.0
base_model: t5-small
tags:
- generated_from_trainer
datasets:
- indosum
metrics:
- rouge
model-index:
- name: my_awesome_billsum_model
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: indosum
type: indosum
config: indosum_fold0_source
split: test
args: indosum_fold0_source
metrics:
- name: Rouge1
type: rouge
value: 0.2065
my_awesome_billsum_model
This model is a fine-tuned version of t5-small on the indosum dataset. It achieves the following results on the evaluation set:
- Loss: 0.4806
- Rouge1: 0.2065
- Rouge2: 0.1639
- Rougel: 0.2038
- Rougelsum: 0.2038
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 0.7495 | 1.0 | 892 | 0.5226 | 0.2061 | 0.1635 | 0.2033 | 0.2033 | 19.0 |
| 0.5326 | 2.0 | 1784 | 0.4929 | 0.2063 | 0.1639 | 0.2037 | 0.2037 | 19.0 |
| 0.4982 | 3.0 | 2676 | 0.4840 | 0.2065 | 0.1639 | 0.2038 | 0.2037 | 19.0 |
| 0.4958 | 4.0 | 3568 | 0.4806 | 0.2065 | 0.1639 | 0.2038 | 0.2038 | 19.0 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1