vit5-base-vietnews-summarization-standardized-color

This model is a fine-tuned version of VietAI/vit5-base-vietnews-summarization on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.7799
• Rouge1: 74.6848
• Rouge2: 68.6336
• Rougel: 74.2192
• Rougelsum: 74.2071
• Gen Len: 7.0508

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	118	0.8194	69.6407	62.7891	69.2092	69.1422	8.786
No log	2.0	236	0.7301	72.6263	66.2139	72.2455	72.2856	7.1843
No log	3.0	354	0.7114	74.5668	68.1982	74.1184	74.1947	6.9979
No log	4.0	472	0.7141	74.484	68.3547	74.0625	74.0382	7.0636
0.7045	5.0	590	0.7091	74.661	68.4421	74.1176	74.1212	7.1398
0.7045	6.0	708	0.7452	75.1264	69.0871	74.5996	74.6391	7.4703
0.7045	7.0	826	0.7496	74.2754	68.0974	73.8278	73.8781	7.0424
0.7045	8.0	944	0.7693	74.1263	67.888	73.7264	73.7286	7.1314
0.2955	9.0	1062	0.7831	74.4148	68.2719	73.9605	73.9679	7.178
0.2955	10.0	1180	0.7799	74.6848	68.6336	74.2192	74.2071	7.0508

Framework versions

• Transformers 4.33.0
• Pytorch 2.0.0
• Datasets 2.1.0
• Tokenizers 0.13.3