metadata
language:
- id
license: apache-2.0
base_model: LazarusNLP/IndoNanoT5-base
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: indosum-lora-4
results: []
indosum-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: 0.4741
- Rouge1: 73.4959
- Rouge2: 66.8131
- Rougel: 70.7936
- Rougelsum: 72.6487
- Gen Len: 102.2932
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 |
---|---|---|---|---|---|---|---|---|
0.8265 | 1.0 | 892 | 0.5175 | 68.9705 | 61.6703 | 66.1048 | 68.0943 | 94.2182 |
0.6279 | 2.0 | 1784 | 0.4892 | 71.4829 | 64.4236 | 68.7077 | 70.6264 | 99.7684 |
0.5857 | 3.0 | 2676 | 0.4836 | 72.3238 | 65.462 | 69.6316 | 71.4946 | 99.3775 |
0.561 | 4.0 | 3568 | 0.4794 | 72.2216 | 65.3919 | 69.5752 | 71.3864 | 100.2517 |
0.5438 | 5.0 | 4460 | 0.4741 | 72.7878 | 66.023 | 70.0879 | 71.9606 | 102.3829 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1