smids_3x_deit_base_sgd_001_fold5

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: 0.2858
• Accuracy: 0.8733

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: 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
0.9502	1.0	225	0.9617	0.575
0.7701	2.0	450	0.7420	0.7533
0.6098	3.0	675	0.5976	0.7833
0.477	4.0	900	0.5110	0.805
0.4263	5.0	1125	0.4583	0.82
0.414	6.0	1350	0.4227	0.8233
0.4045	7.0	1575	0.3990	0.8233
0.4145	8.0	1800	0.3808	0.8267
0.3701	9.0	2025	0.3676	0.8383
0.3094	10.0	2250	0.3582	0.845
0.3923	11.0	2475	0.3474	0.845
0.3461	12.0	2700	0.3427	0.8467
0.3684	13.0	2925	0.3332	0.8483
0.3232	14.0	3150	0.3290	0.8517
0.2418	15.0	3375	0.3249	0.855
0.2931	16.0	3600	0.3205	0.8517
0.2688	17.0	3825	0.3173	0.8533
0.3031	18.0	4050	0.3158	0.8567
0.2623	19.0	4275	0.3109	0.8517
0.298	20.0	4500	0.3083	0.8533
0.2399	21.0	4725	0.3072	0.8583
0.2519	22.0	4950	0.3035	0.8633
0.2394	23.0	5175	0.3028	0.86
0.254	24.0	5400	0.3011	0.8633
0.232	25.0	5625	0.3006	0.865
0.2794	26.0	5850	0.2984	0.865
0.2948	27.0	6075	0.2979	0.8633
0.2603	28.0	6300	0.2957	0.87
0.2519	29.0	6525	0.2949	0.8617
0.2151	30.0	6750	0.2933	0.8667
0.1937	31.0	6975	0.2918	0.8683
0.2408	32.0	7200	0.2919	0.87
0.2318	33.0	7425	0.2909	0.87
0.1908	34.0	7650	0.2902	0.8717
0.2103	35.0	7875	0.2898	0.87
0.2236	36.0	8100	0.2888	0.8717
0.2275	37.0	8325	0.2884	0.87
0.2349	38.0	8550	0.2885	0.87
0.1941	39.0	8775	0.2873	0.8683
0.2123	40.0	9000	0.2867	0.8667
0.2183	41.0	9225	0.2867	0.8683
0.2291	42.0	9450	0.2862	0.8667
0.2371	43.0	9675	0.2863	0.8717
0.2487	44.0	9900	0.2863	0.8717
0.2098	45.0	10125	0.2862	0.8717
0.2225	46.0	10350	0.2861	0.8733
0.2189	47.0	10575	0.2859	0.8733
0.2461	48.0	10800	0.2858	0.8733
0.2284	49.0	11025	0.2858	0.8733
0.236	50.0	11250	0.2858	0.8733

Framework versions

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