metadata
language:
- id
license: apache-2.0
base_model: LazarusNLP/IndoNanoT5-base
tags:
- generated_from_trainer
datasets:
- id_liputan6
metrics:
- rouge
model-index:
- name: liputan6-unipelt
results:
- task:
name: Summarization
type: summarization
dataset:
name: id_liputan6 canonical
type: id_liputan6
config: canonical
split: validation
args: canonical
metrics:
- name: Rouge1
type: rouge
value: 1.8031
liputan6-unipelt
This model is a fine-tuned version of LazarusNLP/IndoNanoT5-base on the id_liputan6 canonical dataset. It achieves the following results on the evaluation set:
- Loss: 2.5645
- Rouge1: 1.8031
- Rouge2: 0.4028
- Rougel: 1.5585
- Rougelsum: 1.6132
- Gen Len: 127.0
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: 0.001
- train_batch_size: 16
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 3.9747 | 1.0 | 63 | 3.1043 | 3.9543 | 1.0191 | 3.7375 | 3.7922 | 127.0 |
| 3.0262 | 2.0 | 126 | 2.7314 | 5.0276 | 1.3105 | 4.1292 | 4.3574 | 127.0 |
| 2.6214 | 3.0 | 189 | 2.5645 | 5.2587 | 1.2673 | 3.8487 | 4.3728 | 127.0 |
| 2.3496 | 4.0 | 252 | 2.4158 | 4.4309 | 0.9142 | 3.2152 | 3.5296 | 127.0 |
| 2.1749 | 5.0 | 315 | 2.3672 | 5.0669 | 1.0704 | 3.6335 | 4.1011 | 127.0 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1