smids_10x_deit_small_rms_001_fold2

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

• Loss: 0.7042
• Accuracy: 0.8369

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
0.8864	1.0	750	0.8248	0.5474
0.7722	2.0	1500	0.8988	0.5092
0.7721	3.0	2250	0.7604	0.6456
0.7086	4.0	3000	0.6560	0.7371
0.6588	5.0	3750	0.6906	0.7088
0.5657	6.0	4500	0.5964	0.7654
0.5826	7.0	5250	0.5186	0.7854
0.5637	8.0	6000	0.5513	0.7737
0.5395	9.0	6750	0.5704	0.7537
0.5342	10.0	7500	0.4931	0.7987
0.5349	11.0	8250	0.5109	0.7937
0.596	12.0	9000	0.5425	0.7804
0.5878	13.0	9750	0.4766	0.8103
0.4609	14.0	10500	0.7520	0.7022
0.4491	15.0	11250	0.5442	0.7504
0.4637	16.0	12000	0.5054	0.8136
0.4699	17.0	12750	0.4927	0.8037
0.4528	18.0	13500	0.4576	0.8120
0.4797	19.0	14250	0.4748	0.7970
0.4704	20.0	15000	0.4438	0.8070
0.4406	21.0	15750	0.4383	0.8153
0.4289	22.0	16500	0.4522	0.8120
0.4219	23.0	17250	0.4457	0.8286
0.3979	24.0	18000	0.4791	0.8203
0.476	25.0	18750	0.4867	0.8136
0.4039	26.0	19500	0.4638	0.8319
0.4302	27.0	20250	0.4222	0.8303
0.4091	28.0	21000	0.4516	0.8270
0.3603	29.0	21750	0.5085	0.8170
0.4414	30.0	22500	0.4568	0.8353
0.3768	31.0	23250	0.4984	0.8253
0.3126	32.0	24000	0.4428	0.8436
0.3269	33.0	24750	0.4871	0.8236
0.3283	34.0	25500	0.4708	0.8253
0.3471	35.0	26250	0.4869	0.8353
0.3619	36.0	27000	0.5210	0.8153
0.4176	37.0	27750	0.4744	0.8353
0.3395	38.0	28500	0.5334	0.8386
0.2458	39.0	29250	0.5218	0.8286
0.3331	40.0	30000	0.5874	0.8186
0.3063	41.0	30750	0.5488	0.8236
0.2956	42.0	31500	0.5739	0.8220
0.3105	43.0	32250	0.5441	0.8369
0.2918	44.0	33000	0.6039	0.8303
0.2418	45.0	33750	0.6214	0.8303
0.2859	46.0	34500	0.6601	0.8286
0.2507	47.0	35250	0.6435	0.8369
0.2443	48.0	36000	0.6789	0.8336
0.2825	49.0	36750	0.6931	0.8336
0.1845	50.0	37500	0.7042	0.8369

Framework versions

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