business_license_clf-3

This model is a fine-tuned version of google/efficientnet-b0 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0424
• Accuracy: 0.9885

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
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	6	0.6705	0.6092
0.6906	2.0	12	0.6322	0.7126
0.6906	3.0	18	0.6103	0.7241
0.6406	4.0	24	0.5338	0.7931
0.5693	5.0	30	0.5135	0.8506
0.5693	6.0	36	0.4331	0.8966
0.4768	7.0	42	0.3827	0.8506
0.4768	8.0	48	0.3647	0.7931
0.3477	9.0	54	0.3326	0.8046
0.3268	10.0	60	0.2348	0.9080
0.3268	11.0	66	0.2387	0.8966
0.254	12.0	72	0.1859	0.9425
0.254	13.0	78	0.2038	0.9425
0.2075	14.0	84	0.4219	0.7586
0.1964	15.0	90	0.1517	0.9310
0.1964	16.0	96	0.1843	0.9195
0.1491	17.0	102	0.1788	0.9195
0.1491	18.0	108	0.1586	0.9080
0.1358	19.0	114	0.2322	0.8851
0.1444	20.0	120	0.0900	0.9770
0.1444	21.0	126	0.0988	0.9770
0.131	22.0	132	0.2102	0.8966
0.131	23.0	138	0.0960	0.9770
0.1083	24.0	144	0.0832	0.9655
0.1303	25.0	150	0.1087	0.9655
0.1303	26.0	156	0.1209	0.9540
0.1137	27.0	162	0.0638	0.9770
0.1137	28.0	168	0.0860	0.9770
0.1027	29.0	174	0.1754	0.9310
0.1019	30.0	180	0.0959	0.9655
0.1019	31.0	186	0.0782	0.9885
0.0833	32.0	192	0.0885	0.9655
0.0833	33.0	198	0.0977	0.9770
0.1076	34.0	204	0.1032	0.9540
0.1152	35.0	210	0.1446	0.9310
0.1152	36.0	216	0.0496	0.9885
0.0743	37.0	222	0.0652	0.9885
0.0743	38.0	228	0.0559	0.9885
0.0808	39.0	234	0.0654	0.9770
0.1056	40.0	240	0.0645	0.9770
0.1056	41.0	246	0.0677	0.9655
0.0838	42.0	252	0.0636	0.9770
0.0838	43.0	258	0.0746	0.9770
0.0707	44.0	264	0.0643	0.9885
0.0776	45.0	270	0.0688	0.9770
0.0776	46.0	276	0.0560	0.9885
0.0976	47.0	282	0.0765	0.9540
0.0976	48.0	288	0.0491	0.9885
0.0678	49.0	294	0.0704	0.9655
0.0892	50.0	300	0.0424	0.9885

Framework versions

• Transformers 4.56.1
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.0