PaceKW/24PDInsight-TextSummarization

results

This model is a fine-tuned version of panggi/t5-base-indonesian-summarization-cased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5276

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	5	0.9031
No log	2.0	10	0.7196
No log	3.0	15	0.6421
No log	4.0	20	0.6057
No log	5.0	25	0.5856
No log	6.0	30	0.5718
No log	7.0	35	0.5608
No log	8.0	40	0.5524
No log	9.0	45	0.5443
No log	10.0	50	0.5381
No log	11.0	55	0.5335
No log	12.0	60	0.5307
No log	13.0	65	0.5290
No log	14.0	70	0.5279
No log	15.0	75	0.5276

Framework versions

• Transformers 4.41.1
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1