EN_t5-small_15_spider

This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4888
• Rouge2 Precision: 0.5237
• Rouge2 Recall: 0.3349
• Rouge2 Fmeasure: 0.3832

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: 16
• 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
No log	1.0	438	0.4960	0.3036	0.2109	0.2216
1.0347	2.0	876	0.4496	0.3801	0.2453	0.2721
0.3664	3.0	1314	0.4839	0.4223	0.2627	0.2999
0.2966	4.0	1752	0.4671	0.457	0.2786	0.3218
0.2486	5.0	2190	0.4586	0.4628	0.2872	0.3302
0.2254	6.0	2628	0.4475	0.4873	0.3071	0.3521
0.2061	7.0	3066	0.4932	0.5017	0.3147	0.3622
0.1915	8.0	3504	0.4904	0.52	0.3331	0.3812
0.1915	9.0	3942	0.4924	0.5069	0.3189	0.3668
0.179	10.0	4380	0.4941	0.5094	0.3253	0.3721
0.1714	11.0	4818	0.4865	0.5064	0.3201	0.3672
0.1655	12.0	5256	0.4825	0.5147	0.3289	0.3762
0.1604	13.0	5694	0.4730	0.5155	0.3306	0.3776
0.1584	14.0	6132	0.4873	0.5239	0.336	0.384
0.1563	15.0	6570	0.4888	0.5237	0.3349	0.3832

Framework versions

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