business_license_clf-4-scale-0.3-1.0

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: 0.0289
• 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	0.7016	0.5287
0.7076	2.0	12	0.6588	0.6552
0.7076	3.0	18	0.6029	0.7471
0.6509	4.0	24	0.5343	0.8736
0.5587	5.0	30	0.5800	0.8966
0.5587	6.0	36	0.4146	0.9195
0.4375	7.0	42	0.3540	0.8966
0.4375	8.0	48	0.3075	0.9195
0.3052	9.0	54	0.3230	0.8276
0.2646	10.0	60	0.1999	0.9655
0.2646	11.0	66	0.1865	0.9540
0.1931	12.0	72	0.1569	0.9885
0.1931	13.0	78	0.1599	0.9770
0.1548	14.0	84	0.2853	0.8621
0.1362	15.0	90	0.1123	0.9770
0.1362	16.0	96	0.1597	0.9540
0.0963	17.0	102	0.1163	0.9770
0.0963	18.0	108	0.1016	0.9770
0.0842	19.0	114	0.2125	0.8851
0.0996	20.0	120	0.0720	0.9885
0.0996	21.0	126	0.0604	0.9885
0.0934	22.0	132	0.1087	0.9655
0.0934	23.0	138	0.0493	0.9885
0.08	24.0	144	0.0568	0.9885
0.0882	25.0	150	0.1093	0.9540
0.0882	26.0	156	0.0749	0.9770
0.0736	27.0	162	0.0463	0.9885
0.0736	28.0	168	0.0584	0.9770
0.0767	29.0	174	0.1708	0.9425
0.0646	30.0	180	0.0705	0.9770
0.0646	31.0	186	0.0576	0.9770
0.0561	32.0	192	0.0459	0.9885
0.0561	33.0	198	0.0788	0.9770
0.0608	34.0	204	0.0644	0.9770
0.0782	35.0	210	0.1063	0.9540
0.0782	36.0	216	0.0531	0.9770
0.0491	37.0	222	0.0339	0.9885
0.0491	38.0	228	0.0380	0.9885
0.0505	39.0	234	0.0486	0.9885
0.0621	40.0	240	0.0507	0.9770
0.0621	41.0	246	0.0437	0.9885
0.0549	42.0	252	0.0560	0.9770
0.0549	43.0	258	0.0772	0.9655
0.0343	44.0	264	0.0390	0.9885
0.0382	45.0	270	0.0609	0.9770
0.0382	46.0	276	0.0367	0.9885
0.0599	47.0	282	0.0825	0.9425
0.0599	48.0	288	0.0345	1.0
0.0594	49.0	294	0.0334	0.9885
0.0834	50.0	300	0.0289	0.9885

Framework versions

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