|
--- |
|
language: |
|
- id |
|
license: apache-2.0 |
|
base_model: LazarusNLP/IndoNanoT5-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: indosum-lora-0 |
|
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. --> |
|
|
|
# indosum-lora-0 |
|
|
|
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: 0.4997 |
|
- Rouge1: 73.7275 |
|
- Rouge2: 66.7471 |
|
- Rougel: 70.8087 |
|
- Rougelsum: 72.8058 |
|
- Gen Len: 103.516 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:--------:| |
|
| 0.8234 | 1.0 | 892 | 0.5383 | 70.3236 | 62.968 | 67.3562 | 69.3577 | 100.7253 | |
|
| 0.6236 | 2.0 | 1784 | 0.5276 | 70.7232 | 63.3489 | 67.5777 | 69.7735 | 106.88 | |
|
| 0.5819 | 3.0 | 2676 | 0.5015 | 72.5246 | 65.3573 | 69.5275 | 71.631 | 103.876 | |
|
| 0.5563 | 4.0 | 3568 | 0.5032 | 72.7472 | 65.6552 | 69.7436 | 71.8704 | 104.6533 | |
|
| 0.5381 | 5.0 | 4460 | 0.4997 | 73.3085 | 66.3297 | 70.3711 | 72.4621 | 103.344 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.2 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|