mt5_base_EN_sch_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 Precision: 0.0165
• Rouge2 Recall: 0.0087
• Rouge2 Fmeasure: 0.0111

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: 14
• 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 Precision	Rouge2 Recall	Rouge2 Fmeasure
0.0	1.0	4627	nan	0.0165	0.0087	0.0111
0.0	2.0	9254	nan	0.0165	0.0087	0.0111
0.0	3.0	13881	nan	0.0165	0.0087	0.0111
0.0	4.0	18508	nan	0.0165	0.0087	0.0111
0.0	5.0	23135	nan	0.0165	0.0087	0.0111
0.0	6.0	27762	nan	0.0165	0.0087	0.0111
0.0	7.0	32389	nan	0.0165	0.0087	0.0111
0.0	8.0	37016	nan	0.0165	0.0087	0.0111
0.0	9.0	41643	nan	0.0165	0.0087	0.0111
0.0	10.0	46270	nan	0.0165	0.0087	0.0111
0.0	11.0	50897	nan	0.0165	0.0087	0.0111
0.0	12.0	55524	nan	0.0165	0.0087	0.0111
0.0	13.0	60151	nan	0.0165	0.0087	0.0111
0.0	14.0	64778	nan	0.0165	0.0087	0.0111
0.0	15.0	69405	nan	0.0165	0.0087	0.0111

Framework versions

• Transformers 4.46.2
• Pytorch 2.2.2
• Datasets 2.16.1
• Tokenizers 0.20.3