ALL_mt5-base_15_spider_10_wikiSQL_sch

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

• Loss: 0.4214
• Rouge2 Precision: 0.5797
• Rouge2 Recall: 0.4033
• Rouge2 Fmeasure: 0.4501

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
0.498	1.0	912	0.3136	0.4916	0.3236	0.366
0.1561	2.0	1824	0.3188	0.541	0.3749	0.4171
0.1091	3.0	2736	0.3287	0.5457	0.3776	0.4213
0.0831	4.0	3648	0.3423	0.5544	0.3834	0.4277
0.0686	5.0	4560	0.3493	0.559	0.3831	0.4282
0.0616	6.0	5472	0.3660	0.5718	0.3992	0.4448
0.0524	7.0	6384	0.3725	0.555	0.3883	0.4322
0.0469	8.0	7296	0.3804	0.5867	0.4075	0.4551
0.0416	9.0	8208	0.3889	0.5725	0.3972	0.4432
0.0382	10.0	9120	0.4028	0.575	0.3991	0.4455
0.0352	11.0	10032	0.4027	0.5754	0.3992	0.4458
0.0337	12.0	10944	0.4161	0.5769	0.4015	0.4482
0.0322	13.0	11856	0.4168	0.5803	0.4021	0.4493
0.0304	14.0	12768	0.4203	0.5783	0.4018	0.4487
0.0298	15.0	13680	0.4214	0.5797	0.4033	0.4501

Framework versions

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