ALL_mt5-base_15_spider_no_sch_15_wikiSQL_no_sch_128

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

• Loss: 0.0225
• Rouge2 Precision: 0.8419
• Rouge2 Recall: 0.5664
• Rouge2 Fmeasure: 0.6439

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: 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
0.2971	1.0	1293	0.1770	0.5043	0.3352	0.3788
0.1766	2.0	2586	0.1177	0.5844	0.3896	0.4412
0.1416	3.0	3879	0.0899	0.6329	0.4197	0.4773
0.1108	4.0	5172	0.0700	0.6794	0.4555	0.5171
0.0962	5.0	6465	0.0562	0.7204	0.4823	0.5478
0.0814	6.0	7758	0.0473	0.7503	0.5072	0.5746
0.0709	7.0	9051	0.0405	0.7655	0.5153	0.5845
0.0651	8.0	10344	0.0358	0.7863	0.5298	0.601
0.0589	9.0	11637	0.0312	0.7996	0.538	0.6108
0.0553	10.0	12930	0.0288	0.8123	0.5482	0.6218
0.0515	11.0	14223	0.0262	0.8229	0.553	0.6283
0.0487	12.0	15516	0.0246	0.8247	0.555	0.6304
0.0466	13.0	16809	0.0236	0.835	0.5611	0.6377
0.0445	14.0	18102	0.0227	0.8414	0.5662	0.6435
0.044	15.0	19395	0.0225	0.8419	0.5664	0.6439

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.0
• Datasets 2.16.1
• Tokenizers 0.15.1