ALL_mt5-base_15_wikiSQL_sch

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

• Loss: 0.0585
• Rouge2 Precision: 0.8836
• Rouge2 Recall: 0.8038
• Rouge2 Fmeasure: 0.8358

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: 15
• eval_batch_size: 15
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge2 Precision	Rouge2 Recall	Rouge2 Fmeasure
0.0796	1.0	8637	0.0675	0.8604	0.78	0.8122
0.0683	2.0	17274	0.0617	0.8681	0.7878	0.8199
0.0587	3.0	25911	0.0593	0.8733	0.7924	0.8248
0.0527	4.0	34548	0.0579	0.8776	0.795	0.8282
0.0478	5.0	43185	0.0573	0.8788	0.7981	0.8305
0.0453	6.0	51822	0.0571	0.8806	0.7999	0.8323
0.043	7.0	60459	0.0571	0.8816	0.8008	0.8333
0.0399	8.0	69096	0.0570	0.881	0.8006	0.8329
0.0389	9.0	77733	0.0573	0.8823	0.8019	0.8343
0.0363	10.0	86370	0.0573	0.8828	0.8025	0.8347
0.0366	11.0	95007	0.0580	0.8835	0.8028	0.8352
0.0333	12.0	103644	0.0579	0.8836	0.8032	0.8355
0.0325	13.0	112281	0.0581	0.8833	0.8036	0.8356
0.0327	14.0	120918	0.0585	0.8839	0.8039	0.836
0.0306	15.0	129555	0.0585	0.8836	0.8038	0.8358

Framework versions

• Transformers 4.37.2
• Pytorch 2.2.0
• Datasets 2.16.1
• Tokenizers 0.15.1