vit5-query-rewriter

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: 0.0022
• Rouge1: 90.2916
• Rouge2: 89.9402
• Rougel: 90.2868
• Rougelsum: 90.2864

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: 0.0001
• train_batch_size: 128
• eval_batch_size: 128
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
0.6281	1.0	163	0.0032	90.2814	89.9197	90.2742	90.273
0.0049	2.0	326	0.0034	90.3052	89.9689	90.2983	90.2955
0.0027	3.0	489	0.0022	90.2916	89.9402	90.2868	90.2864

Framework versions

• Transformers 4.39.3
• Pytorch 2.10.0+cu128
• Datasets 5.0.0
• Tokenizers 0.15.2