finetune-newwiki-summarization-ver1

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

• Loss: 0.4720
• Rouge1: 48.6293
• Rouge2: 25.6053
• Rougel: 35.2967
• Rougelsum: 37.4842

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: 1e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.05
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
0.7106	1.0	1980	0.5006	46.5921	22.8276	33.1994	35.6330
0.621	2.0	3960	0.4774	47.4426	24.1508	34.1315	36.5692
0.5607	3.0	5940	0.4690	48.1503	24.7217	34.5071	36.7568
0.5241	4.0	7920	0.4673	48.2480	25.0604	34.4937	36.9301
0.499	5.0	9900	0.4678	48.1659	25.1857	34.9460	37.1931
0.4592	6.0	11880	0.4694	48.5839	25.5925	35.2301	37.5352
0.4535	7.0	13860	0.4720	48.6293	25.6053	35.2967	37.4842

Framework versions

• Transformers 4.17.0
• Pytorch 2.1.2
• Datasets 2.18.0
• Tokenizers 0.15.2