text-to-sparql-Version-Test

This model is a fine-tuned version of yazdipour/text-to-sparql-t5-small-qald9 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.9612
• Gen Len: 19.0
• Bleu-score: 0.2838
• Bleu-precisions: [72.02432667245873, 38.11833171677983, 15.038419319429199, 4.424778761061947]
• Bleu-bp: 0.0137

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: 3e-05
• train_batch_size: 12
• eval_batch_size: 12
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Gen Len	Bleu-score	Bleu-precisions	Bleu-bp
No log	1.0	24	2.5035	19.0	0.0169	[30.0, 3.8016528925619837, 0.045871559633027525, 0.02577319587628866]	0.0280
No log	2.0	48	2.0260	19.0	0.0402	[34.44976076555024, 6.790123456790123, 0.9861932938856016, 0.05592841163310962]	0.0212
No log	3.0	72	1.6870	19.0	0.0709	[45.14866979655712, 15.284974093264248, 2.3121387283236996, 0.054466230936819175]	0.0232
No log	4.0	96	1.4481	19.0	0.0822	[50.08130081300813, 19.63963963963964, 2.9292929292929295, 0.11494252873563218]	0.0193
No log	5.0	120	1.2693	19.0	0.1507	[67.11711711711712, 32.92929292929293, 8.275862068965518, 1.7333333333333334]	0.0113
No log	6.0	144	1.1483	19.0	0.2096	[70.38703870387039, 37.134207870837535, 12.85878300803674, 3.4620505992010653]	0.0113
No log	7.0	168	1.0610	19.0	0.2489	[70.16769638128861, 38.104639684106616, 14.109742441209406, 4.010349288486417]	0.0126
No log	8.0	192	1.0048	19.0	0.2615	[70.53182214472537, 37.098344693281405, 14.22271223814774, 3.8119440914866582]	0.0135
No log	9.0	216	0.9719	19.0	0.2838	[72.02432667245873, 38.11833171677983, 15.038419319429199, 4.424778761061947]	0.0137
No log	10.0	240	0.9612	19.0	0.2838	[72.02432667245873, 38.11833171677983, 15.038419319429199, 4.424778761061947]	0.0137

Framework versions

• Transformers 4.41.1
• Pytorch 2.1.0+cpu
• Datasets 2.14.0
• Tokenizers 0.19.1