business_license_clf-4-scale-0.5-1.0

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: 0.0207
• Accuracy: 1.0

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	0.6505	0.6207
0.6483	2.0	12	0.5842	0.8046
0.6483	3.0	18	0.5401	0.8046
0.5986	4.0	24	0.4790	0.8506
0.4847	5.0	30	0.4355	0.9195
0.4847	6.0	36	0.3172	0.8851
0.3688	7.0	42	0.2810	0.9425
0.3688	8.0	48	0.2401	0.9425
0.2409	9.0	54	0.2387	0.9080
0.1902	10.0	60	0.1450	0.9770
0.1902	11.0	66	0.1108	0.9770
0.1332	12.0	72	0.1246	1.0
0.1332	13.0	78	0.0944	0.9885
0.1056	14.0	84	0.1437	0.9540
0.1005	15.0	90	0.0639	0.9885
0.1005	16.0	96	0.0822	0.9770
0.069	17.0	102	0.0613	0.9885
0.069	18.0	108	0.0448	1.0
0.0573	19.0	114	0.1275	0.9655
0.0603	20.0	120	0.0425	1.0
0.0603	21.0	126	0.0457	0.9885
0.0599	22.0	132	0.0636	0.9770
0.0599	23.0	138	0.0416	1.0
0.0409	24.0	144	0.0533	1.0
0.0611	25.0	150	0.1619	0.9655
0.0611	26.0	156	0.0533	0.9770
0.0454	27.0	162	0.0309	1.0
0.0454	28.0	168	0.0387	0.9885
0.0337	29.0	174	0.0949	0.9655
0.0556	30.0	180	0.0485	0.9655
0.0556	31.0	186	0.0285	1.0
0.0429	32.0	192	0.0283	1.0
0.0429	33.0	198	0.0385	1.0
0.0392	34.0	204	0.0355	0.9770
0.0466	35.0	210	0.0885	0.9655
0.0466	36.0	216	0.0196	1.0
0.0298	37.0	222	0.0258	1.0
0.0298	38.0	228	0.0269	1.0
0.0285	39.0	234	0.0254	1.0
0.0482	40.0	240	0.0290	0.9770
0.0482	41.0	246	0.0269	0.9885
0.0341	42.0	252	0.0297	0.9885
0.0341	43.0	258	0.1727	0.9655
0.0214	44.0	264	0.0211	1.0
0.0219	45.0	270	0.0332	0.9770
0.0219	46.0	276	0.0236	1.0
0.0315	47.0	282	0.0391	0.9770
0.0315	48.0	288	0.0201	1.0
0.0326	49.0	294	0.0229	1.0
0.0367	50.0	300	0.0207	1.0

Framework versions

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