|
--- |
|
license: apache-2.0 |
|
base_model: LazarusNLP/IndoNanoT5-base |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- id_liputan6 |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: liputan6-unipelt |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# liputan6-unipelt |
|
|
|
This model is a fine-tuned version of [LazarusNLP/IndoNanoT5-base](https://huggingface.co/LazarusNLP/IndoNanoT5-base) on the id_liputan6 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 3.6316 |
|
- Rouge1: 1.8166 |
|
- Rouge2: 0.0438 |
|
- Rougel: 1.7867 |
|
- Rougelsum: 1.8115 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:| |
|
| 4.4282 | 1.0 | 63 | 3.9181 | 6.5087 | 1.1507 | 5.6509 | 5.8646 | 127.0 | |
|
| 3.5887 | 2.0 | 126 | 3.7178 | 2.446 | 0.2311 | 2.2699 | 2.3165 | 127.0 | |
|
| 3.2648 | 3.0 | 189 | 3.6481 | 2.5164 | 0.1545 | 2.3984 | 2.4483 | 127.0 | |
|
| 3.0219 | 4.0 | 252 | 3.6384 | 1.8155 | 0.0676 | 1.7586 | 1.7921 | 127.0 | |
|
| 2.8422 | 5.0 | 315 | 3.6316 | 1.8166 | 0.0438 | 1.7867 | 1.8115 | 127.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.2 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
