ALL_mt5-base_15_spider_no_sch_15_wikiSQL_no_sch

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

• Loss: 0.0267
• Rouge2 Precision: 0.8214
• Rouge2 Recall: 0.551
• Rouge2 Fmeasure: 0.6267

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
0.3337	1.0	1293	0.1946	0.4739	0.3026	0.3469
0.1986	2.0	2586	0.1295	0.5591	0.3707	0.4203
0.1594	3.0	3879	0.0988	0.6081	0.4048	0.4587
0.1248	4.0	5172	0.0784	0.6641	0.446	0.5058
0.1085	5.0	6465	0.0639	0.6994	0.4687	0.5318
0.092	6.0	7758	0.0548	0.7211	0.4841	0.5496
0.0807	7.0	9051	0.0472	0.7398	0.4954	0.5633
0.0739	8.0	10344	0.0419	0.7611	0.5104	0.5801
0.0671	9.0	11637	0.0368	0.7779	0.5215	0.5926
0.0629	10.0	12930	0.0336	0.8019	0.5391	0.6123
0.0587	11.0	14223	0.0309	0.7974	0.5358	0.6087
0.0557	12.0	15516	0.0289	0.809	0.5446	0.6186
0.0532	13.0	16809	0.0278	0.8203	0.5502	0.6259
0.051	14.0	18102	0.0270	0.8202	0.5501	0.6258
0.0504	15.0	19395	0.0267	0.8214	0.551	0.6267

Framework versions

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