indobart-silver-standard-lora

This model is a fine-tuned version of indobenchmark/indobart-v2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.8453
• Rouge1: 21.8211
• Rouge2: 11.2186
• Rougel: 21.525
• Rougelsum: 21.5204

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: 0.0003
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
17.9151	1.0	149	3.2758	14.5283	5.046	14.0207	14.1012
12.8416	2.0	298	2.9058	20.9816	10.7915	20.6061	20.6493
12.2039	3.0	447	2.8453	21.8211	11.2186	21.525	21.5204

Framework versions

• PEFT 0.18.1
• Transformers 5.0.0
• Pytorch 2.10.0+cu128
• Datasets 4.8.3
• Tokenizers 0.22.2