ALL_mt5-base_15_spider_new2

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: 0.3806
• Rouge2 Precision: 0.6339
• Rouge2 Recall: 0.4352
• Rouge2 Fmeasure: 0.487

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: 4
• 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
0.1807	1.0	4847	0.2361	0.546	0.3648	0.4103
0.1003	2.0	9694	0.2335	0.5674	0.3804	0.4267
0.0695	3.0	14541	0.2456	0.5959	0.4034	0.4521
0.0565	4.0	19388	0.2553	0.6119	0.4163	0.466
0.0421	5.0	24235	0.2739	0.62	0.4241	0.4745
0.0354	6.0	29082	0.2824	0.6257	0.4252	0.4769
0.0317	7.0	33929	0.2992	0.6321	0.4299	0.4822
0.0257	8.0	38776	0.3090	0.6191	0.4201	0.4715
0.0229	9.0	43623	0.3216	0.6336	0.4322	0.4848
0.0205	10.0	48470	0.3331	0.6339	0.4347	0.4865
0.0171	11.0	53317	0.3484	0.6281	0.4305	0.482
0.0141	12.0	58164	0.3614	0.6364	0.4359	0.4882
0.0135	13.0	63011	0.3634	0.6324	0.4345	0.486
0.0131	14.0	67858	0.3744	0.6334	0.4349	0.4867
0.0116	15.0	72705	0.3806	0.6339	0.4352	0.487

Framework versions

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