KB13-t5-base-finetuned-en-to-regex

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

• Loss: 0.4785
• Semantic accuracy: 0.3902
• Syntactic accuracy: 0.3171
• Gen Len: 15.2927

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: 0.001
• 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
• training_steps: 1000

Training results

Training Loss	Epoch	Step	Validation Loss	Semantic accuracy	Syntactic accuracy	Gen Len
No log	2.13	100	0.7159	0.122	0.0976	15.2439
No log	4.26	200	0.4649	0.2683	0.2195	15.0488
No log	6.38	300	0.3749	0.4146	0.3415	15.3659
No log	8.51	400	0.4155	0.3902	0.2927	15.0976
0.5191	10.64	500	0.4148	0.3902	0.2927	15.7561
0.5191	12.77	600	0.4010	0.439	0.3415	15.3902
0.5191	14.89	700	0.4429	0.3902	0.3171	15.3659
0.5191	17.02	800	0.4607	0.3902	0.3415	15.561
0.5191	19.15	900	0.4629	0.3902	0.3171	15.122
0.0518	21.28	1000	0.4785	0.3902	0.3171	15.2927

Framework versions

• Transformers 4.25.1
• Pytorch 1.13.0+cu116
• Datasets 2.7.1
• Tokenizers 0.13.2