smids_5x_deit_base_rms_0001_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: 1.0537
• Accuracy: 0.9033

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: 0.0001
• 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
0.2482	1.0	375	0.3175	0.8933
0.1437	2.0	750	0.2994	0.91
0.0829	3.0	1125	0.4831	0.8717
0.0657	4.0	1500	0.4645	0.87
0.0415	5.0	1875	0.5452	0.895
0.0518	6.0	2250	0.4649	0.89
0.0246	7.0	2625	0.4579	0.8933
0.0124	8.0	3000	0.5092	0.8933
0.0196	9.0	3375	0.6123	0.885
0.0528	10.0	3750	0.5846	0.89
0.0162	11.0	4125	0.6461	0.89
0.0269	12.0	4500	0.6644	0.89
0.0189	13.0	4875	0.6691	0.8867
0.013	14.0	5250	0.5509	0.895
0.0125	15.0	5625	0.6239	0.8867
0.042	16.0	6000	0.5644	0.8967
0.0002	17.0	6375	0.7253	0.8967
0.0067	18.0	6750	0.7652	0.8983
0.0166	19.0	7125	0.7033	0.8983
0.0136	20.0	7500	0.7542	0.8867
0.0035	21.0	7875	0.8364	0.8883
0.0092	22.0	8250	0.7788	0.89
0.0366	23.0	8625	0.7487	0.8933
0.0057	24.0	9000	0.8195	0.8933
0.0002	25.0	9375	0.6186	0.9
0.0001	26.0	9750	0.7244	0.9017
0.0002	27.0	10125	0.8368	0.8883
0.0004	28.0	10500	0.8205	0.895
0.0421	29.0	10875	0.8404	0.89
0.0033	30.0	11250	0.8091	0.8967
0.0	31.0	11625	0.7929	0.8967
0.0109	32.0	12000	0.8783	0.8883
0.0	33.0	12375	0.8591	0.8917
0.0	34.0	12750	0.9822	0.89
0.0	35.0	13125	0.9216	0.8933
0.0	36.0	13500	0.9855	0.895
0.0	37.0	13875	0.8868	0.9017
0.0	38.0	14250	0.9047	0.9017
0.0	39.0	14625	0.9416	0.9017
0.0033	40.0	15000	0.8937	0.91
0.0117	41.0	15375	1.0141	0.8967
0.0	42.0	15750	1.0456	0.9
0.0	43.0	16125	1.0341	0.9017
0.0	44.0	16500	1.0394	0.9033
0.0	45.0	16875	1.0421	0.905
0.0	46.0	17250	1.0425	0.9017
0.0	47.0	17625	1.0481	0.905
0.0	48.0	18000	1.0506	0.9033
0.0	49.0	18375	1.0518	0.905
0.0	50.0	18750	1.0537	0.9033

Framework versions

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