smids_5x_deit_base_rms_00001_fold3

This model is a fine-tuned version of facebook/deit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.8646
• Accuracy: 0.9133

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: 1e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.1923	1.0	375	0.2761	0.89
0.0794	2.0	750	0.2797	0.92
0.0089	3.0	1125	0.3862	0.9083
0.0263	4.0	1500	0.4507	0.915
0.0241	5.0	1875	0.5940	0.9033
0.0093	6.0	2250	0.5438	0.915
0.0074	7.0	2625	0.6908	0.9
0.003	8.0	3000	0.6531	0.905
0.038	9.0	3375	0.6121	0.9133
0.0021	10.0	3750	0.6007	0.9167
0.0	11.0	4125	0.7290	0.9017
0.0	12.0	4500	0.6566	0.905
0.0057	13.0	4875	0.7475	0.905
0.0	14.0	5250	0.7562	0.915
0.0001	15.0	5625	0.7103	0.9117
0.0	16.0	6000	0.7619	0.9133
0.023	17.0	6375	0.8515	0.9017
0.0	18.0	6750	0.7788	0.9167
0.0668	19.0	7125	0.9370	0.8917
0.0002	20.0	7500	0.9448	0.8933
0.0	21.0	7875	0.8080	0.9117
0.0	22.0	8250	0.8600	0.9017
0.0029	23.0	8625	0.9399	0.9017
0.0	24.0	9000	0.8645	0.9067
0.0	25.0	9375	0.8436	0.9117
0.0	26.0	9750	0.8337	0.905
0.0	27.0	10125	0.8133	0.9117
0.0	28.0	10500	0.8299	0.9217
0.0	29.0	10875	0.8115	0.9117
0.0038	30.0	11250	0.8569	0.9183
0.0	31.0	11625	0.7968	0.9133
0.0	32.0	12000	0.8353	0.9133
0.0	33.0	12375	0.8387	0.9117
0.0	34.0	12750	0.8604	0.9117
0.0	35.0	13125	0.8144	0.9133
0.0	36.0	13500	0.8218	0.9033
0.0	37.0	13875	0.8203	0.9133
0.0	38.0	14250	0.8248	0.9133
0.0	39.0	14625	0.8352	0.9133
0.0031	40.0	15000	0.8391	0.9233
0.0	41.0	15375	0.8462	0.9167
0.0	42.0	15750	0.8442	0.9217
0.0	43.0	16125	0.8498	0.9133
0.0	44.0	16500	0.8546	0.9117
0.0	45.0	16875	0.8578	0.9117
0.0	46.0	17250	0.8603	0.9117
0.0	47.0	17625	0.8622	0.9117
0.0	48.0	18000	0.8633	0.9117
0.0	49.0	18375	0.8638	0.9133
0.0	50.0	18750	0.8646	0.9133

Framework versions

• Transformers 4.32.1
• Pytorch 2.1.0+cu121
• Datasets 2.12.0
• Tokenizers 0.13.2