This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 1.0369
Accuracy: 0.5816

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: 5e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 100

Training results

Training Loss	Epoch	Step	Accuracy	Validation Loss
1.2196	1.0	1240	0.5816	1.0369
1.2491	2.0	2481	0.5752	1.0638
1.2016	3.0	3721	0.5792	1.0546
1.2234	4.0	4962	0.5810	1.0560
1.2298	5.0	6202	0.5725	1.0795
1.287	6.0	7443	0.5731	1.0763
1.2472	7.0	8683	0.5635	1.1067
1.2171	8.0	9924	0.5775	1.0671
1.3164	9.0	11164	0.5701	1.0681
1.3019	10.0	12405	0.5698	1.0824
1.2977	11.0	13645	0.5694	1.0721
1.2587	12.0	14886	0.5704	1.0833
1.2704	13.0	16126	0.5675	1.0934
1.2604	14.0	17367	0.5730	1.0739
1.2834	15.0	18607	0.5524	1.1210
1.2082	16.0	19848	0.5611	1.1271
1.2307	17.0	21088	0.5720	1.1013
1.2136	18.0	22329	0.5753	1.1036
1.2133	19.0	23569	0.5610	1.1350
1.2478	20.0	24810	0.5676	1.1256
1.2006	21.0	26050	0.5682	1.1288
1.1934	22.0	27291	0.5619	1.1472
1.2136	23.0	28531	0.5713	1.1304
1.2449	24.0	29772	0.5581	1.1893
1.1968	25.0	31012	0.5633	1.1754
1.1582	26.0	32253	0.5651	1.1735
1.1404	27.0	33493	0.5642	1.1752
1.2011	28.0	34734	0.5538	1.2227
1.1223	29.0	35974	0.5578	1.2200
1.1427	30.0	37215	0.5608	1.2028
1.1751	31.0	38455	0.5635	1.2253
1.1012	32.0	39696	0.5543	1.2473
1.0912	33.0	40936	0.5673	1.2370
1.1085	34.0	42177	0.5534	1.2838
1.099	35.0	43417	0.5526	1.2760
1.1092	36.0	44658	0.5547	1.2769
1.0655	37.0	45898	0.5534	1.3178
1.0861	38.0	47139	0.5585	1.2943
1.0917	39.0	48379	0.5518	1.3659
1.0791	40.0	49620	0.5541	1.3413
1.0356	41.0	50860	0.5495	1.3567
1.0394	42.0	52101	0.5491	1.3648
1.0096	43.0	53341	0.5574	1.3671
1.0736	44.0	54582	0.5468	1.4142
1.0145	45.0	55822	0.5462	1.4340
1.0437	46.0	57063	0.5442	1.4734
0.9771	47.0	58303	0.5446	1.4496
0.9758	48.0	59544	0.5397	1.5071
1.0199	49.0	60784	0.5437	1.5119
0.9898	50.0	62025	0.5428	1.5066
1.0139	51.0	63265	0.5375	1.5314
1.0035	52.0	64506	0.5427	1.5604
0.9786	53.0	65746	0.5396	1.5899
0.9768	54.0	66987	0.5449	1.5642
0.968	55.0	68227	0.5394	1.6056
0.9254	56.0	69468	0.5380	1.6091
0.9764	57.0	70680	0.5340	1.6646
0.8998	58.0	71921	0.5323	1.6692
0.9592	59.0	73161	0.5353	1.6395
0.8722	60.0	74402	0.5393	1.6702
0.888	61.0	75642	0.5336	1.6771
0.872	62.0	76883	0.5331	1.6873
0.9133	63.0	78123	0.5325	1.7182
0.8815	64.0	79364	0.5310	1.7375
0.9144	65.0	80604	0.5337	1.7263
0.8712	66.0	81845	0.5284	1.7628
0.8576	67.0	83080	1.7786	0.5322
0.8677	68.0	84321	1.7947	0.5327
0.8448	69.0	85561	1.8100	0.5314
0.8102	70.0	86802	1.8256	0.5313
0.8438	71.0	88042	1.8325	0.5273
0.8015	72.0	89283	1.8564	0.5311
0.8025	73.0	90523	1.8451	0.5342
0.8295	74.0	91764	1.8748	0.5305
0.8101	75.0	93004	1.8884	0.5297
0.7883	76.0	94245	1.8777	0.5297
0.7989	77.0	95485	1.9185	0.5262
0.7791	78.0	96726	1.9436	0.5246
0.7197	79.0	97966	1.9615	0.5222
0.7639	80.0	99207	1.9567	0.5213
0.7922	81.0	100447	1.9746	0.5248
0.7874	82.0	101688	1.9960	0.5206
0.8155	83.0	102928	2.0131	0.5211
0.7791	84.0	104169	2.0559	0.5196
0.7731	85.0	105409	2.0255	0.5192
0.8018	86.0	106650	2.0784	0.5216
0.777	87.0	107890	2.0482	0.5224
0.7637	88.0	109131	2.0889	0.5201
0.7783	89.0	110371	2.0663	0.5222
0.7156	90.0	111612	2.0884	0.5200
0.702	91.0	112852	2.1034	0.5215
0.7136	92.0	114093	2.1380	0.5164
0.6889	93.0	115333	2.1321	0.5198
0.7117	94.0	116574	2.1175	0.5186
0.6903	95.0	117814	2.1155	0.5187
0.7334	96.0	119055	2.1197	0.5200
0.6684	97.0	120295	2.1435	0.5192
0.7471	98.0	121536	2.1403	0.5196
0.7197	99.0	122776	2.1465	0.5182
0.7026	99.99	124000	2.1492	0.5186

Framework versions

Transformers 4.37.2
Pytorch 2.0.1+cu117
Datasets 2.17.0
Tokenizers 0.15.2

sai17/cards-top_left_swin-tiny-patch4-window7-224-finetuned-dough_100_epoch

cards-top_left_swin-tiny-patch4-window7-224-finetuned-dough_100_epoch

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

sai17/
cards-top_left_swin-tiny-patch4-window7-224-finetuned-dough_100_epoch