smids_5x_beit_base_rms_001_fold2

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

• Loss: 0.5865
• Accuracy: 0.7953

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
1.0449	1.0	375	0.9946	0.4576
0.9062	2.0	750	0.8678	0.5341
0.8013	3.0	1125	1.1322	0.4709
0.7159	4.0	1500	0.7319	0.6373
0.717	5.0	1875	0.7090	0.6672
0.6942	6.0	2250	0.6958	0.6356
0.7767	7.0	2625	0.6812	0.7022
0.7025	8.0	3000	0.6844	0.6406
0.731	9.0	3375	0.6703	0.6872
0.712	10.0	3750	0.7094	0.6789
0.6865	11.0	4125	0.6498	0.6972
0.7524	12.0	4500	0.6865	0.6955
0.6624	13.0	4875	0.6872	0.6772
0.6979	14.0	5250	0.6496	0.6972
0.6174	15.0	5625	0.6736	0.6805
0.6379	16.0	6000	0.6464	0.6889
0.6532	17.0	6375	0.6449	0.7271
0.6218	18.0	6750	0.6026	0.7421
0.6018	19.0	7125	0.6684	0.6988
0.6058	20.0	7500	0.6198	0.7205
0.6269	21.0	7875	0.6185	0.7338
0.586	22.0	8250	0.5945	0.7571
0.6047	23.0	8625	0.5838	0.7404
0.5645	24.0	9000	0.5895	0.7304
0.5266	25.0	9375	0.6076	0.7554
0.5433	26.0	9750	0.6078	0.7205
0.6677	27.0	10125	0.5591	0.7837
0.5463	28.0	10500	0.6091	0.7488
0.5494	29.0	10875	0.5955	0.7471
0.4887	30.0	11250	0.5393	0.7987
0.5572	31.0	11625	0.5935	0.7537
0.5382	32.0	12000	0.6529	0.7288
0.5356	33.0	12375	0.5723	0.7787
0.5102	34.0	12750	0.5659	0.7720
0.5047	35.0	13125	0.5433	0.7887
0.4869	36.0	13500	0.5564	0.7687
0.4821	37.0	13875	0.5581	0.7754
0.455	38.0	14250	0.5595	0.7837
0.4345	39.0	14625	0.5481	0.7854
0.4695	40.0	15000	0.5459	0.8003
0.4129	41.0	15375	0.5458	0.8020
0.4369	42.0	15750	0.5508	0.7953
0.4043	43.0	16125	0.5495	0.7854
0.4715	44.0	16500	0.5470	0.7987
0.4036	45.0	16875	0.5777	0.7887
0.3786	46.0	17250	0.5867	0.8003
0.4177	47.0	17625	0.5806	0.7770
0.3538	48.0	18000	0.5857	0.7937
0.3987	49.0	18375	0.5813	0.8020
0.3452	50.0	18750	0.5865	0.7953

Framework versions

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