mt5_base_EN_wiki

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

• Loss: nan
• Rouge2 Fmeasure: 0.0086

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: 5e-05
• train_batch_size: 53
• eval_batch_size: 16
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge2 Fmeasure
0.0	1.0	1223	nan	0.0086
0.0	2.0	2446	nan	0.0086
0.0	3.0	3669	nan	0.0086
0.0	4.0	4892	nan	0.0086
0.0	5.0	6115	nan	0.0086
0.0	6.0	7338	nan	0.0086
0.0	7.0	8561	nan	0.0086
0.0	8.0	9784	nan	0.0086
0.0	9.0	11007	nan	0.0086
0.0	10.0	12230	nan	0.0086
0.0	11.0	13453	nan	0.0086
0.0	12.0	14676	nan	0.0086
0.0	13.0	15899	nan	0.0086
0.0	14.0	17122	nan	0.0086
0.0	15.0	18345	nan	0.0086

Framework versions

• Transformers 4.46.1
• Pytorch 2.5.1
• Datasets 3.1.0
• Tokenizers 0.20.1