metadata

license: apache-2.0
base_model: LazarusNLP/IndoNanoT5-base
tags:
  - generated_from_trainer
language:
  - ind
datasets:
  - GEM/indonlg
metrics:
  - rouge
model-index:
  - name: LazarusNLP/IndoNanoT5-base-IndoSum
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: indonlg
          type: indonlg
          config: indosum
          split: test
          args: indosum
        metrics:
          - name: Rouge1
            type: rouge
            value: 0.7529
          - name: Rouge2
            type: rouge
            value: 0.7123
          - name: RougeL
            type: rouge
            value: 0.733

LazarusNLP/IndoNanoT5-base-IndoSum

This model is a fine-tuned version of LazarusNLP/IndoNanoT5-base on the indonlg dataset. It achieves the following results on the evaluation set:

Loss: 0.1086
Rouge1: 0.7529
Rouge2: 0.7123
Rougel: 0.733
Rougelsum: 0.733
Gen Len: 110.0391

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: 8
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
0.3004	1.0	1761	0.1682	0.258	0.2277	0.2549	0.255	19.0
0.1463	2.0	3522	0.1318	0.2596	0.2305	0.2563	0.2565	19.0
0.095	3.0	5283	0.1272	0.2602	0.2314	0.2571	0.257	19.0
0.0705	4.0	7044	0.1186	0.2622	0.2338	0.2592	0.2592	19.0
0.0436	5.0	8805	0.1236	0.2625	0.2342	0.2594	0.2596	19.0

Framework versions

Transformers 4.36.2
Pytorch 2.2.0+cu118
Datasets 2.16.1
Tokenizers 0.15.1