swin-tiny-patch4-window7-224-finetuned-woody_130epochs

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: 0.4550
Accuracy: 0.8921

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: 130

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6694	1.0	58	0.6370	0.6594
0.6072	2.0	116	0.5813	0.7030
0.6048	3.0	174	0.5646	0.7030
0.5849	4.0	232	0.5778	0.6970
0.5671	5.0	290	0.5394	0.7236
0.5575	6.0	348	0.5212	0.7382
0.568	7.0	406	0.5218	0.7358
0.5607	8.0	464	0.5183	0.7527
0.5351	9.0	522	0.5138	0.7467
0.5459	10.0	580	0.5290	0.7394
0.5454	11.0	638	0.5212	0.7345
0.5291	12.0	696	0.5130	0.7576
0.5378	13.0	754	0.5372	0.7503
0.5264	14.0	812	0.6089	0.6861
0.4909	15.0	870	0.4852	0.7636
0.5591	16.0	928	0.4817	0.76
0.4966	17.0	986	0.5673	0.6933
0.4988	18.0	1044	0.5131	0.7418
0.5339	19.0	1102	0.4998	0.7394
0.4804	20.0	1160	0.4655	0.7733
0.503	21.0	1218	0.4554	0.7685
0.4859	22.0	1276	0.4713	0.7770
0.504	23.0	1334	0.4545	0.7721
0.478	24.0	1392	0.4658	0.7830
0.4759	25.0	1450	0.4365	0.8012
0.4686	26.0	1508	0.4452	0.7855
0.4668	27.0	1566	0.4427	0.7879
0.4615	28.0	1624	0.4439	0.7685
0.4588	29.0	1682	0.4378	0.7830
0.4588	30.0	1740	0.4229	0.7988
0.4296	31.0	1798	0.4188	0.7976
0.4208	32.0	1856	0.4316	0.7891
0.4481	33.0	1914	0.4331	0.7891
0.4253	34.0	1972	0.4524	0.7879
0.4117	35.0	2030	0.4570	0.7952
0.4405	36.0	2088	0.4307	0.7927
0.4154	37.0	2146	0.4257	0.8024
0.3962	38.0	2204	0.5077	0.7818
0.414	39.0	2262	0.4602	0.8012
0.3937	40.0	2320	0.4741	0.7770
0.4186	41.0	2378	0.4250	0.8
0.4076	42.0	2436	0.4353	0.7988
0.3777	43.0	2494	0.4442	0.7879
0.3968	44.0	2552	0.4525	0.7879
0.377	45.0	2610	0.4198	0.7988
0.378	46.0	2668	0.4297	0.8097
0.3675	47.0	2726	0.4435	0.8085
0.3562	48.0	2784	0.4477	0.7952
0.381	49.0	2842	0.4206	0.8255
0.3603	50.0	2900	0.4136	0.8109
0.3331	51.0	2958	0.4141	0.8230
0.3471	52.0	3016	0.4253	0.8109
0.346	53.0	3074	0.5203	0.8048
0.3481	54.0	3132	0.4288	0.8242
0.3411	55.0	3190	0.4416	0.8194
0.3275	56.0	3248	0.4149	0.8291
0.3067	57.0	3306	0.4623	0.8218
0.3166	58.0	3364	0.4432	0.8255
0.3294	59.0	3422	0.4599	0.8267
0.3146	60.0	3480	0.4266	0.8291
0.3091	61.0	3538	0.4318	0.8315
0.3277	62.0	3596	0.4252	0.8242
0.296	63.0	3654	0.4332	0.8436
0.3241	64.0	3712	0.4729	0.8194
0.3104	65.0	3770	0.4228	0.8448
0.2878	66.0	3828	0.4173	0.8388
0.265	67.0	3886	0.4210	0.8497
0.3011	68.0	3944	0.4276	0.8436
0.2861	69.0	4002	0.4923	0.8315
0.2994	70.0	4060	0.4472	0.8182
0.276	71.0	4118	0.4541	0.8315
0.2796	72.0	4176	0.4218	0.8521
0.2727	73.0	4234	0.4053	0.8448
0.255	74.0	4292	0.4356	0.8376
0.276	75.0	4350	0.4193	0.8436
0.261	76.0	4408	0.4484	0.8533
0.2416	77.0	4466	0.4722	0.8194
0.2602	78.0	4524	0.4431	0.8533
0.2591	79.0	4582	0.4269	0.8606
0.2613	80.0	4640	0.4335	0.8485
0.2555	81.0	4698	0.4269	0.8594
0.2832	82.0	4756	0.3968	0.8715
0.264	83.0	4814	0.4173	0.8703
0.2462	84.0	4872	0.4150	0.8606
0.2424	85.0	4930	0.4377	0.8630
0.2574	86.0	4988	0.4120	0.8679
0.2273	87.0	5046	0.4393	0.8533
0.2334	88.0	5104	0.4366	0.8630
0.2258	89.0	5162	0.4189	0.8630
0.2153	90.0	5220	0.4474	0.8630
0.2462	91.0	5278	0.4362	0.8642
0.2356	92.0	5336	0.4454	0.8715
0.2019	93.0	5394	0.4413	0.88
0.209	94.0	5452	0.4410	0.8703
0.2201	95.0	5510	0.4323	0.8691
0.2245	96.0	5568	0.4999	0.8618
0.2178	97.0	5626	0.4612	0.8655
0.2163	98.0	5684	0.4340	0.8703
0.2228	99.0	5742	0.4504	0.8788
0.2151	100.0	5800	0.4602	0.8703
0.1988	101.0	5858	0.4414	0.8812
0.2227	102.0	5916	0.4392	0.8824
0.1772	103.0	5974	0.5069	0.8630
0.2199	104.0	6032	0.4648	0.8667
0.1936	105.0	6090	0.4806	0.8691
0.199	106.0	6148	0.4569	0.8764
0.2149	107.0	6206	0.4445	0.8739
0.1917	108.0	6264	0.4444	0.8727
0.201	109.0	6322	0.4594	0.8727
0.1938	110.0	6380	0.4564	0.8764
0.1977	111.0	6438	0.4398	0.8739
0.1776	112.0	6496	0.4356	0.88
0.1939	113.0	6554	0.4412	0.8848
0.178	114.0	6612	0.4373	0.88
0.1926	115.0	6670	0.4508	0.8812
0.1979	116.0	6728	0.4477	0.8848
0.1958	117.0	6786	0.4488	0.8897
0.189	118.0	6844	0.4553	0.8836
0.1838	119.0	6902	0.4605	0.8848
0.1755	120.0	6960	0.4463	0.8836
0.1958	121.0	7018	0.4474	0.8861
0.1857	122.0	7076	0.4550	0.8921
0.1466	123.0	7134	0.4494	0.8885
0.1751	124.0	7192	0.4560	0.8873
0.175	125.0	7250	0.4383	0.8897
0.207	126.0	7308	0.4601	0.8873
0.1756	127.0	7366	0.4425	0.8897
0.1695	128.0	7424	0.4533	0.8909
0.1873	129.0	7482	0.4510	0.8897
0.1726	130.0	7540	0.4463	0.8909

Framework versions

Transformers 4.23.1
Pytorch 1.12.1+cu113
Datasets 2.6.1
Tokenizers 0.13.1

Alex-VisTas/swin-tiny-patch4-window7-224-finetuned-woody_130epochs

swin-tiny-patch4-window7-224-finetuned-woody_130epochs

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions