convnextv2-tiny-1k-224-finetuned-eurosat

This model is a fine-tuned version of facebook/convnextv2-tiny-1k-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.7923
Accuracy: 0.8288

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: 150

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
3.5919	0.992	31	3.5736	0.0315
3.5392	1.984	62	3.4990	0.0473
3.4591	2.976	93	3.3992	0.1104
3.3361	4.0	125	3.2526	0.2523
3.2066	4.992	156	3.0851	0.3761
3.0024	5.984	187	2.8376	0.4437
2.8094	6.976	218	2.6320	0.4910
2.509	8.0	250	2.3765	0.5360
2.2526	8.992	281	2.0400	0.5923
1.9442	9.984	312	1.7940	0.6396
1.7672	10.9760	343	1.5892	0.6824
1.5273	12.0	375	1.3500	0.7185
1.3854	12.992	406	1.2243	0.7162
1.197	13.984	437	1.1022	0.7387
1.1114	14.9760	468	1.0138	0.7613
0.9364	16.0	500	0.9164	0.7748
0.8755	16.992	531	0.9058	0.7523
0.7473	17.984	562	0.8045	0.7928
0.7189	18.976	593	0.7735	0.7883
0.6461	20.0	625	0.6876	0.8198
0.6041	20.992	656	0.7212	0.7973
0.5016	21.984	687	0.6611	0.8198
0.4996	22.976	718	0.6110	0.8153
0.4825	24.0	750	0.6476	0.8063
0.434	24.992	781	0.6793	0.8041
0.4296	25.984	812	0.6015	0.8018
0.36	26.976	843	0.6615	0.8063
0.3646	28.0	875	0.6059	0.8221
0.3542	28.992	906	0.6973	0.7928
0.3091	29.984	937	0.6400	0.8266
0.2774	30.976	968	0.5798	0.8266
0.3166	32.0	1000	0.6134	0.8333
0.2878	32.992	1031	0.6353	0.8063
0.2529	33.984	1062	0.6628	0.8243
0.2601	34.976	1093	0.6367	0.8041
0.2208	36.0	1125	0.6313	0.8288
0.2342	36.992	1156	0.5969	0.8378
0.2122	37.984	1187	0.6391	0.8198
0.1791	38.976	1218	0.6771	0.8108
0.2113	40.0	1250	0.7035	0.8086
0.1703	40.992	1281	0.7096	0.8153
0.1751	41.984	1312	0.5964	0.8446
0.1889	42.976	1343	0.6607	0.8446
0.1791	44.0	1375	0.7000	0.8243
0.1372	44.992	1406	0.6866	0.8243
0.1785	45.984	1437	0.6621	0.8266
0.1469	46.976	1468	0.6391	0.8266
0.1628	48.0	1500	0.6623	0.8356
0.1425	48.992	1531	0.6443	0.8288
0.1727	49.984	1562	0.6361	0.8446
0.1442	50.976	1593	0.6397	0.8491
0.1386	52.0	1625	0.6835	0.8423
0.1564	52.992	1656	0.7072	0.8266
0.1151	53.984	1687	0.6835	0.8311
0.1446	54.976	1718	0.7347	0.8198
0.1353	56.0	1750	0.6935	0.8401
0.13	56.992	1781	0.7337	0.8198
0.1312	57.984	1812	0.6625	0.8311
0.1201	58.976	1843	0.6956	0.8243
0.1411	60.0	1875	0.7290	0.8243
0.1116	60.992	1906	0.7052	0.8356
0.1251	61.984	1937	0.6915	0.8311
0.1101	62.976	1968	0.6457	0.8378
0.0883	64.0	2000	0.6553	0.8378
0.1225	64.992	2031	0.6454	0.8401
0.1135	65.984	2062	0.6616	0.8514
0.1009	66.976	2093	0.6375	0.8536
0.1027	68.0	2125	0.6754	0.8266
0.0925	68.992	2156	0.7497	0.8176
0.0878	69.984	2187	0.6573	0.8491
0.1093	70.976	2218	0.7015	0.8356
0.1024	72.0	2250	0.6907	0.8446
0.0934	72.992	2281	0.7059	0.8356
0.103	73.984	2312	0.7159	0.8356
0.0974	74.976	2343	0.7324	0.8266
0.1049	76.0	2375	0.7397	0.8311
0.097	76.992	2406	0.7529	0.8176
0.0816	77.984	2437	0.7175	0.8423
0.0902	78.976	2468	0.7745	0.8288
0.0827	80.0	2500	0.7017	0.8423
0.0818	80.992	2531	0.7712	0.8243
0.076	81.984	2562	0.7341	0.8423
0.0837	82.976	2593	0.7242	0.8491
0.0743	84.0	2625	0.6999	0.8446
0.0552	84.992	2656	0.6875	0.8401
0.0762	85.984	2687	0.6743	0.8581
0.0742	86.976	2718	0.7027	0.8446
0.0708	88.0	2750	0.7367	0.8356
0.086	88.992	2781	0.6905	0.8401
0.0575	89.984	2812	0.7041	0.8423
0.0733	90.976	2843	0.6465	0.8423
0.0701	92.0	2875	0.7066	0.8401
0.0782	92.992	2906	0.6955	0.8243
0.0754	93.984	2937	0.6836	0.8468
0.0545	94.976	2968	0.7290	0.8288
0.0913	96.0	3000	0.7665	0.8266
0.0816	96.992	3031	0.7661	0.8311
0.0696	97.984	3062	0.6921	0.8356
0.0627	98.976	3093	0.7070	0.8446
0.0562	100.0	3125	0.7442	0.8401
0.0742	100.992	3156	0.7000	0.8423
0.0545	101.984	3187	0.7312	0.8401
0.0635	102.976	3218	0.7231	0.8491
0.0608	104.0	3250	0.7332	0.8333
0.0769	104.992	3281	0.7328	0.8356
0.057	105.984	3312	0.6954	0.8378
0.0447	106.976	3343	0.7006	0.8423
0.0629	108.0	3375	0.7149	0.8423
0.0394	108.992	3406	0.7469	0.8378
0.0602	109.984	3437	0.7274	0.8468
0.0635	110.976	3468	0.7495	0.8446
0.0565	112.0	3500	0.7885	0.8401
0.035	112.992	3531	0.7178	0.8468
0.0604	113.984	3562	0.7574	0.8356
0.0507	114.976	3593	0.7901	0.8266
0.05	116.0	3625	0.7730	0.8198
0.0465	116.992	3656	0.7967	0.8401
0.042	117.984	3687	0.7767	0.8423
0.0609	118.976	3718	0.7872	0.8378
0.0379	120.0	3750	0.7685	0.8514
0.0579	120.992	3781	0.7709	0.8423
0.0471	121.984	3812	0.7601	0.8423
0.0488	122.976	3843	0.8231	0.8356
0.0531	124.0	3875	0.8016	0.8378
0.0446	124.992	3906	0.7806	0.8423
0.0479	125.984	3937	0.7668	0.8378
0.0525	126.976	3968	0.7874	0.8288
0.0512	128.0	4000	0.7652	0.8311
0.0473	128.992	4031	0.7721	0.8356
0.0579	129.984	4062	0.7607	0.8356
0.0444	130.976	4093	0.7917	0.8356
0.0462	132.0	4125	0.7877	0.8333
0.0483	132.992	4156	0.8122	0.8401
0.042	133.984	4187	0.7956	0.8378
0.0439	134.976	4218	0.8281	0.8311
0.0458	136.0	4250	0.7723	0.8446
0.0307	136.992	4281	0.7686	0.8446
0.0481	137.984	4312	0.7834	0.8378
0.0503	138.976	4343	0.7987	0.8378
0.038	140.0	4375	0.8156	0.8311
0.0472	140.992	4406	0.8030	0.8356
0.0282	141.984	4437	0.7884	0.8378
0.0541	142.976	4468	0.7969	0.8311
0.0415	144.0	4500	0.7899	0.8333
0.0579	144.992	4531	0.7979	0.8266
0.048	145.984	4562	0.7935	0.8288
0.0353	146.976	4593	0.7933	0.8288
0.0438	148.0	4625	0.7916	0.8288
0.0487	148.8	4650	0.7923	0.8288

Framework versions

Transformers 4.44.0
Pytorch 2.4.0
Datasets 2.21.0
Tokenizers 0.19.1

vishalkatheriya18/convnextv2-tiny-1k-224-finetuned-all_wear

convnextv2-tiny-1k-224-finetuned-eurosat

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions