ALL_mt5-base_15_spider_15_wikiSQL_new

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0160
• Rouge2 Precision: 0.9066
• Rouge2 Recall: 0.6077
• Rouge2 Fmeasure: 0.6916

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: 19
• eval_batch_size: 16
• 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
0.3243	1.0	1021	0.1423	0.6057	0.3898	0.4466
0.1428	2.0	2042	0.0864	0.7175	0.4822	0.5453
0.1071	3.0	3063	0.0644	0.7701	0.5183	0.5867
0.0845	4.0	4084	0.0517	0.798	0.5398	0.611
0.0723	5.0	5105	0.0417	0.8294	0.5584	0.6336
0.0612	6.0	6126	0.0349	0.8411	0.5623	0.6394
0.0528	7.0	7147	0.0302	0.853	0.5731	0.6514
0.0475	8.0	8168	0.0254	0.8734	0.5842	0.6649
0.0427	9.0	9189	0.0227	0.8855	0.5943	0.6757
0.0398	10.0	10210	0.0208	0.8901	0.5965	0.6787
0.0362	11.0	11231	0.0190	0.8943	0.5986	0.6815
0.0343	12.0	12252	0.0178	0.9024	0.6045	0.6882
0.0329	13.0	13273	0.0170	0.9075	0.6075	0.692
0.0316	14.0	14294	0.0162	0.9081	0.6092	0.6935
0.031	15.0	15315	0.0160	0.9066	0.6077	0.6916

Framework versions

• Transformers 4.26.1
• Pytorch 2.0.1+cu117
• Datasets 2.14.7.dev0
• Tokenizers 0.13.3