|
--- |
|
language: |
|
- id |
|
license: apache-2.0 |
|
base_model: LazarusNLP/IndoNanoT5-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: summarization-lora-2 |
|
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. --> |
|
|
|
# summarization-lora-2 |
|
|
|
This model is a fine-tuned version of [LazarusNLP/IndoNanoT5-base](https://huggingface.co/LazarusNLP/IndoNanoT5-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5351 |
|
- Rouge1: 0.3585 |
|
- Rouge2: 0.0 |
|
- Rougel: 0.3555 |
|
- Rougelsum: 0.357 |
|
- Gen Len: 1.0 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 8 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:| |
|
| 1.2329 | 1.0 | 1787 | 0.5976 | 0.3912 | 0.0 | 0.3916 | 0.392 | 1.0 | |
|
| 0.7952 | 2.0 | 3574 | 0.5580 | 0.3919 | 0.0 | 0.3921 | 0.3921 | 1.0 | |
|
| 0.7407 | 3.0 | 5361 | 0.5366 | 0.3893 | 0.0 | 0.3879 | 0.3866 | 1.0 | |
|
| 0.7152 | 4.0 | 7148 | 0.5402 | 0.354 | 0.0 | 0.3512 | 0.3523 | 1.0 | |
|
| 0.7029 | 5.0 | 8935 | 0.5351 | 0.3585 | 0.0 | 0.3555 | 0.357 | 1.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|
