mt5_thaisum_finetune

This model is a fine-tuned version of google/mt5-base on the thaisum dataset. It achieves the following results on the evaluation set:

• Loss: 0.3039
• Rouge1: 0.2022
• Rouge2: 0.0808
• Rougel: 0.2023
• Rougelsum: 0.2019
• Gen Len: 18.9995

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: 0.0002
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
2.0742	1.0	5000	0.3272	0.1713	0.0551	0.1716	0.1714	18.9945
1.7874	2.0	10000	0.3073	0.1943	0.0747	0.195	0.1941	18.997
1.6341	3.0	15000	0.3035	0.2006	0.0807	0.2007	0.2002	19.0
1.4501	4.0	20000	0.3039	0.2022	0.0808	0.2023	0.2019	18.9995

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu118
• Datasets 2.13.1
• Tokenizers 0.13.3