ALL_manual_mt5-base_15_spider_no_sch_15

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: 0.0378
• Rouge2 Precision: 0.7495
• Rouge2 Recall: 0.5027
• Rouge2 Fmeasure: 0.5711

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
1.7943	1.0	1293	0.3227	0.2802	0.1766	0.1964
0.2825	2.0	2586	0.1790	0.4482	0.2731	0.318
0.2224	3.0	3879	0.1336	0.5122	0.3371	0.3817
0.1691	4.0	5172	0.1052	0.5597	0.3717	0.4211
0.1483	5.0	6465	0.0861	0.6096	0.4062	0.4603
0.1261	6.0	7758	0.0735	0.6317	0.4226	0.4787
0.1088	7.0	9051	0.0637	0.6726	0.4493	0.5099
0.1015	8.0	10344	0.0569	0.688	0.462	0.5237
0.0915	9.0	11637	0.0512	0.6945	0.4626	0.526
0.0865	10.0	12930	0.0469	0.7244	0.4879	0.5529
0.0799	11.0	14223	0.0439	0.7377	0.495	0.5615
0.0757	12.0	15516	0.0413	0.743	0.4983	0.5659
0.074	13.0	16809	0.0393	0.749	0.5028	0.5707
0.0718	14.0	18102	0.0382	0.7485	0.5018	0.5701
0.0708	15.0	19395	0.0378	0.7495	0.5027	0.5711

Framework versions

• Transformers 4.26.1
• Pytorch 2.1.2
• Datasets 2.16.1
• Tokenizers 0.13.3