metadata
language:
- id
license: apache-2.0
base_model: LazarusNLP/IndoNanoT5-base
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: summarization-lora-4
results: []
summarization-lora-4
This model is a fine-tuned version of LazarusNLP/IndoNanoT5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5588
- Rouge1: 0.4494
- Rouge2: 0.0
- Rougel: 0.4489
- Rougelsum: 0.4499
- 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 |
|---|---|---|---|---|---|---|---|---|
| 1.3987 | 1.0 | 1784 | 0.6451 | 0.4474 | 0.0 | 0.4495 | 0.4472 | 1.0 |
| 0.8591 | 2.0 | 3568 | 0.5834 | 0.4222 | 0.0 | 0.4206 | 0.4228 | 1.0 |
| 0.7949 | 3.0 | 5352 | 0.5684 | 0.4462 | 0.0 | 0.4449 | 0.4456 | 1.0 |
| 0.7674 | 4.0 | 7136 | 0.5639 | 0.4564 | 0.0 | 0.4538 | 0.4545 | 1.0 |
| 0.7542 | 5.0 | 8920 | 0.5588 | 0.4494 | 0.0 | 0.4489 | 0.4499 | 1.0 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1