vietnamese_t5_summary_model_falcon

This model is a fine-tuned version of Falconsai/text_summarization on the None dataset. It achieves the following results on the evaluation set:

• Loss: 4.9637
• Rouge1: 5.3259
• Rouge2: 1.0432
• Rougel: 4.3589
• Rougelsum: 4.4312

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 3000
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
5.5256	1.0	13	5.0138	5.1301	1.1104	4.3454	4.4618
5.3866	2.0	26	5.0124	5.2801	1.1592	4.4856	4.6096
5.5331	3.0	39	5.0101	5.2801	1.1592	4.4856	4.6096
5.3745	4.0	52	5.0061	5.2233	1.1592	4.4309	4.5483
5.5461	5.0	65	5.0023	4.9462	1.0051	4.1778	4.3127
5.326	6.0	78	4.9966	4.9914	1.0075	4.1731	4.309
5.5432	7.0	91	4.9909	5.1529	1.1614	4.2869	4.3977
5.4482	8.0	104	4.9828	5.0223	0.9709	4.1513	4.2346
5.4006	9.0	117	4.9732	5.2199	1.0146	4.291	4.3823
5.4558	10.0	130	4.9637	5.3259	1.0432	4.3589	4.4312

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.1+cu121
• Datasets 2.19.2
• Tokenizers 0.19.1