yolo_finetuned_fruits

This model is a fine-tuned version of hustvl/yolos-tiny on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.6777
Map: 0.6802
Map 50: 0.88
Map 75: 0.7868
Map Small: -1.0
Map Medium: -1.0
Map Large: 0.6832
Mar 1: 0.5387
Mar 10: 0.8
Mar 100: 0.8347
Mar Small: -1.0
Mar Medium: -1.0
Mar Large: 0.8347
Map Banana: 0.5085
Mar 100 Banana: 0.7667
Map Orange: 0.6831
Mar 100 Orange: 0.8318
Map Apple: 0.8488
Mar 100 Apple: 0.9056

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: 4
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Map	Map 50	Map 75	Map Small	Map Medium	Map Large	Mar 1	Mar 10	Mar 100	Mar Small	Mar Medium	Mar Large	Map Banana	Mar 100 Banana	Map Orange	Mar 100 Orange	Map Apple	Mar 100 Apple
No log	1.0	51	1.9322	0.0183	0.0525	0.0098	-1.0	-1.0	0.0191	0.0699	0.2055	0.3657	-1.0	-1.0	0.3657	0.0183	0.525	0.0302	0.3	0.0064	0.2722
No log	2.0	102	1.7795	0.0522	0.1331	0.0226	-1.0	-1.0	0.0541	0.1202	0.2662	0.4098	-1.0	-1.0	0.4098	0.0162	0.5	0.0849	0.4182	0.0556	0.3111
No log	3.0	153	1.7218	0.0398	0.121	0.0249	-1.0	-1.0	0.0399	0.1411	0.2769	0.4793	-1.0	-1.0	0.4793	0.0391	0.6042	0.029	0.3727	0.0515	0.4611
No log	4.0	204	1.2908	0.1028	0.2275	0.0915	-1.0	-1.0	0.1033	0.2292	0.4285	0.6486	-1.0	-1.0	0.6486	0.068	0.6125	0.1225	0.55	0.1178	0.7833
No log	5.0	255	1.0796	0.1227	0.1949	0.1361	-1.0	-1.0	0.1237	0.3035	0.5162	0.7395	-1.0	-1.0	0.7395	0.0868	0.7292	0.1109	0.6727	0.1706	0.8167
No log	6.0	306	0.9298	0.1907	0.2715	0.2129	-1.0	-1.0	0.1909	0.4271	0.6614	0.7968	-1.0	-1.0	0.7968	0.1298	0.7875	0.1988	0.7364	0.2437	0.8667
No log	7.0	357	0.9388	0.2024	0.3161	0.2115	-1.0	-1.0	0.2027	0.4484	0.6524	0.7677	-1.0	-1.0	0.7677	0.1796	0.7375	0.2431	0.7545	0.1844	0.8111
No log	8.0	408	0.8829	0.2141	0.3092	0.2352	-1.0	-1.0	0.2169	0.4653	0.6866	0.8	-1.0	-1.0	0.8	0.1622	0.7875	0.2351	0.7682	0.245	0.8444
No log	9.0	459	0.8358	0.2458	0.3717	0.2705	-1.0	-1.0	0.2493	0.4689	0.6981	0.7922	-1.0	-1.0	0.7922	0.2049	0.7458	0.1824	0.7864	0.3502	0.8444
1.3303	10.0	510	0.7960	0.3118	0.4631	0.3571	-1.0	-1.0	0.3162	0.4617	0.6993	0.8198	-1.0	-1.0	0.8198	0.3044	0.7958	0.2119	0.8136	0.4191	0.85
1.3303	11.0	561	0.8086	0.2704	0.416	0.3169	-1.0	-1.0	0.2739	0.4306	0.7161	0.8119	-1.0	-1.0	0.8119	0.2772	0.7792	0.2137	0.7955	0.3202	0.8611
1.3303	12.0	612	0.8034	0.427	0.6125	0.4752	-1.0	-1.0	0.4303	0.474	0.7386	0.7995	-1.0	-1.0	0.7995	0.3889	0.7667	0.424	0.7818	0.468	0.85
1.3303	13.0	663	0.7450	0.4523	0.6336	0.5023	-1.0	-1.0	0.4532	0.4821	0.773	0.8323	-1.0	-1.0	0.8323	0.3286	0.7833	0.4274	0.8136	0.6009	0.9
1.3303	14.0	714	0.7498	0.5242	0.7422	0.5828	-1.0	-1.0	0.5302	0.5064	0.7702	0.8225	-1.0	-1.0	0.8225	0.4293	0.7625	0.5511	0.8273	0.5922	0.8778
1.3303	15.0	765	0.7764	0.5257	0.741	0.6315	-1.0	-1.0	0.5259	0.4645	0.7615	0.8014	-1.0	-1.0	0.8014	0.4175	0.775	0.5069	0.7682	0.6526	0.8611
1.3303	16.0	816	0.7647	0.5598	0.7727	0.6594	-1.0	-1.0	0.56	0.4905	0.762	0.8087	-1.0	-1.0	0.8087	0.4307	0.7583	0.5227	0.7955	0.7259	0.8722
1.3303	17.0	867	0.7531	0.5985	0.8217	0.6502	-1.0	-1.0	0.6022	0.5125	0.7739	0.821	-1.0	-1.0	0.821	0.4636	0.7833	0.5885	0.7909	0.7433	0.8889
1.3303	18.0	918	0.6944	0.628	0.8358	0.729	-1.0	-1.0	0.6285	0.5219	0.8027	0.8405	-1.0	-1.0	0.8405	0.5024	0.7917	0.6002	0.8409	0.7813	0.8889
1.3303	19.0	969	0.6648	0.648	0.8638	0.7594	-1.0	-1.0	0.6488	0.5193	0.813	0.8448	-1.0	-1.0	0.8448	0.4998	0.7875	0.6262	0.8636	0.8179	0.8833
0.7502	20.0	1020	0.6595	0.6553	0.8602	0.7563	-1.0	-1.0	0.6561	0.537	0.8089	0.8406	-1.0	-1.0	0.8406	0.4986	0.8	0.6161	0.8273	0.8513	0.8944
0.7502	21.0	1071	0.6764	0.6563	0.8624	0.7709	-1.0	-1.0	0.6572	0.5205	0.8052	0.8391	-1.0	-1.0	0.8391	0.4888	0.8	0.6515	0.8227	0.8286	0.8944
0.7502	22.0	1122	0.7066	0.6645	0.8815	0.7705	-1.0	-1.0	0.6698	0.524	0.7839	0.8265	-1.0	-1.0	0.8265	0.5059	0.7708	0.6758	0.8364	0.8118	0.8722
0.7502	23.0	1173	0.6886	0.6722	0.888	0.8079	-1.0	-1.0	0.6763	0.5362	0.7962	0.8354	-1.0	-1.0	0.8354	0.5127	0.7708	0.6763	0.8409	0.8277	0.8944
0.7502	24.0	1224	0.6894	0.6645	0.8777	0.7537	-1.0	-1.0	0.6671	0.5332	0.7875	0.828	-1.0	-1.0	0.828	0.4925	0.7542	0.6806	0.8409	0.8204	0.8889
0.7502	25.0	1275	0.6769	0.6711	0.8758	0.7848	-1.0	-1.0	0.6724	0.5394	0.7921	0.8313	-1.0	-1.0	0.8313	0.5014	0.7667	0.6734	0.8273	0.8385	0.9
0.7502	26.0	1326	0.6825	0.6723	0.8857	0.7815	-1.0	-1.0	0.6755	0.528	0.8026	0.8362	-1.0	-1.0	0.8362	0.5072	0.7667	0.6697	0.8364	0.8399	0.9056
0.7502	27.0	1377	0.6766	0.6812	0.8798	0.7845	-1.0	-1.0	0.6843	0.5378	0.8056	0.8343	-1.0	-1.0	0.8343	0.5093	0.7667	0.6849	0.8364	0.8495	0.9
0.7502	28.0	1428	0.6799	0.6789	0.8796	0.7834	-1.0	-1.0	0.682	0.5387	0.8042	0.8347	-1.0	-1.0	0.8347	0.5049	0.7667	0.683	0.8318	0.8489	0.9056
0.7502	29.0	1479	0.6772	0.6802	0.88	0.7869	-1.0	-1.0	0.6833	0.5387	0.8042	0.8347	-1.0	-1.0	0.8347	0.5087	0.7667	0.6831	0.8318	0.8488	0.9056
0.5715	30.0	1530	0.6777	0.6802	0.88	0.7868	-1.0	-1.0	0.6832	0.5387	0.8	0.8347	-1.0	-1.0	0.8347	0.5085	0.7667	0.6831	0.8318	0.8488	0.9056

Framework versions

Transformers 5.0.0
Pytorch 2.10.0+cu128
Datasets 4.0.0
Tokenizers 0.22.2

Loading…

yolo_finetuned_fruits

This model is a fine-tuned version of hustvl/yolos-tiny on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.6777

Map: 0.6802

Map 50: 0.88

Map 75: 0.7868

Map Small: -1.0

Map Medium: -1.0

Map Large: 0.6832

Mar 1: 0.5387

Mar 10: 0.8

Mar 100: 0.8347

Mar Small: -1.0

Mar Medium: -1.0

Mar Large: 0.8347

Map Banana: 0.5085

Mar 100 Banana: 0.7667

Map Orange: 0.6831

Mar 100 Orange: 0.8318

Map Apple: 0.8488

Mar 100 Apple: 0.9056

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05

train_batch_size: 4

eval_batch_size: 8

seed: 42

optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments

lr_scheduler_type: cosine

num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Map	Map 50	Map 75	Map Small	Map Medium	Map Large	Mar 1	Mar 10	Mar 100	Mar Small	Mar Medium	Mar Large	Map Banana	Mar 100 Banana	Map Orange	Mar 100 Orange	Map Apple	Mar 100 Apple
No log	1.0	51	1.9322	0.0183	0.0525	0.0098	-1.0	-1.0	0.0191	0.0699	0.2055	0.3657	-1.0	-1.0	0.3657	0.0183	0.525	0.0302	0.3	0.0064	0.2722
No log	2.0	102	1.7795	0.0522	0.1331	0.0226	-1.0	-1.0	0.0541	0.1202	0.2662	0.4098	-1.0	-1.0	0.4098	0.0162	0.5	0.0849	0.4182	0.0556	0.3111
No log	3.0	153	1.7218	0.0398	0.121	0.0249	-1.0	-1.0	0.0399	0.1411	0.2769	0.4793	-1.0	-1.0	0.4793	0.0391	0.6042	0.029	0.3727	0.0515	0.4611
No log	4.0	204	1.2908	0.1028	0.2275	0.0915	-1.0	-1.0	0.1033	0.2292	0.4285	0.6486	-1.0	-1.0	0.6486	0.068	0.6125	0.1225	0.55	0.1178	0.7833
No log	5.0	255	1.0796	0.1227	0.1949	0.1361	-1.0	-1.0	0.1237	0.3035	0.5162	0.7395	-1.0	-1.0	0.7395	0.0868	0.7292	0.1109	0.6727	0.1706	0.8167
No log	6.0	306	0.9298	0.1907	0.2715	0.2129	-1.0	-1.0	0.1909	0.4271	0.6614	0.7968	-1.0	-1.0	0.7968	0.1298	0.7875	0.1988	0.7364	0.2437	0.8667
No log	7.0	357	0.9388	0.2024	0.3161	0.2115	-1.0	-1.0	0.2027	0.4484	0.6524	0.7677	-1.0	-1.0	0.7677	0.1796	0.7375	0.2431	0.7545	0.1844	0.8111
No log	8.0	408	0.8829	0.2141	0.3092	0.2352	-1.0	-1.0	0.2169	0.4653	0.6866	0.8	-1.0	-1.0	0.8	0.1622	0.7875	0.2351	0.7682	0.245	0.8444
No log	9.0	459	0.8358	0.2458	0.3717	0.2705	-1.0	-1.0	0.2493	0.4689	0.6981	0.7922	-1.0	-1.0	0.7922	0.2049	0.7458	0.1824	0.7864	0.3502	0.8444
1.3303	10.0	510	0.7960	0.3118	0.4631	0.3571	-1.0	-1.0	0.3162	0.4617	0.6993	0.8198	-1.0	-1.0	0.8198	0.3044	0.7958	0.2119	0.8136	0.4191	0.85
1.3303	11.0	561	0.8086	0.2704	0.416	0.3169	-1.0	-1.0	0.2739	0.4306	0.7161	0.8119	-1.0	-1.0	0.8119	0.2772	0.7792	0.2137	0.7955	0.3202	0.8611
1.3303	12.0	612	0.8034	0.427	0.6125	0.4752	-1.0	-1.0	0.4303	0.474	0.7386	0.7995	-1.0	-1.0	0.7995	0.3889	0.7667	0.424	0.7818	0.468	0.85
1.3303	13.0	663	0.7450	0.4523	0.6336	0.5023	-1.0	-1.0	0.4532	0.4821	0.773	0.8323	-1.0	-1.0	0.8323	0.3286	0.7833	0.4274	0.8136	0.6009	0.9
1.3303	14.0	714	0.7498	0.5242	0.7422	0.5828	-1.0	-1.0	0.5302	0.5064	0.7702	0.8225	-1.0	-1.0	0.8225	0.4293	0.7625	0.5511	0.8273	0.5922	0.8778
1.3303	15.0	765	0.7764	0.5257	0.741	0.6315	-1.0	-1.0	0.5259	0.4645	0.7615	0.8014	-1.0	-1.0	0.8014	0.4175	0.775	0.5069	0.7682	0.6526	0.8611
1.3303	16.0	816	0.7647	0.5598	0.7727	0.6594	-1.0	-1.0	0.56	0.4905	0.762	0.8087	-1.0	-1.0	0.8087	0.4307	0.7583	0.5227	0.7955	0.7259	0.8722
1.3303	17.0	867	0.7531	0.5985	0.8217	0.6502	-1.0	-1.0	0.6022	0.5125	0.7739	0.821	-1.0	-1.0	0.821	0.4636	0.7833	0.5885	0.7909	0.7433	0.8889
1.3303	18.0	918	0.6944	0.628	0.8358	0.729	-1.0	-1.0	0.6285	0.5219	0.8027	0.8405	-1.0	-1.0	0.8405	0.5024	0.7917	0.6002	0.8409	0.7813	0.8889
1.3303	19.0	969	0.6648	0.648	0.8638	0.7594	-1.0	-1.0	0.6488	0.5193	0.813	0.8448	-1.0	-1.0	0.8448	0.4998	0.7875	0.6262	0.8636	0.8179	0.8833
0.7502	20.0	1020	0.6595	0.6553	0.8602	0.7563	-1.0	-1.0	0.6561	0.537	0.8089	0.8406	-1.0	-1.0	0.8406	0.4986	0.8	0.6161	0.8273	0.8513	0.8944
0.7502	21.0	1071	0.6764	0.6563	0.8624	0.7709	-1.0	-1.0	0.6572	0.5205	0.8052	0.8391	-1.0	-1.0	0.8391	0.4888	0.8	0.6515	0.8227	0.8286	0.8944
0.7502	22.0	1122	0.7066	0.6645	0.8815	0.7705	-1.0	-1.0	0.6698	0.524	0.7839	0.8265	-1.0	-1.0	0.8265	0.5059	0.7708	0.6758	0.8364	0.8118	0.8722
0.7502	23.0	1173	0.6886	0.6722	0.888	0.8079	-1.0	-1.0	0.6763	0.5362	0.7962	0.8354	-1.0	-1.0	0.8354	0.5127	0.7708	0.6763	0.8409	0.8277	0.8944
0.7502	24.0	1224	0.6894	0.6645	0.8777	0.7537	-1.0	-1.0	0.6671	0.5332	0.7875	0.828	-1.0	-1.0	0.828	0.4925	0.7542	0.6806	0.8409	0.8204	0.8889
0.7502	25.0	1275	0.6769	0.6711	0.8758	0.7848	-1.0	-1.0	0.6724	0.5394	0.7921	0.8313	-1.0	-1.0	0.8313	0.5014	0.7667	0.6734	0.8273	0.8385	0.9
0.7502	26.0	1326	0.6825	0.6723	0.8857	0.7815	-1.0	-1.0	0.6755	0.528	0.8026	0.8362	-1.0	-1.0	0.8362	0.5072	0.7667	0.6697	0.8364	0.8399	0.9056
0.7502	27.0	1377	0.6766	0.6812	0.8798	0.7845	-1.0	-1.0	0.6843	0.5378	0.8056	0.8343	-1.0	-1.0	0.8343	0.5093	0.7667	0.6849	0.8364	0.8495	0.9
0.7502	28.0	1428	0.6799	0.6789	0.8796	0.7834	-1.0	-1.0	0.682	0.5387	0.8042	0.8347	-1.0	-1.0	0.8347	0.5049	0.7667	0.683	0.8318	0.8489	0.9056
0.7502	29.0	1479	0.6772	0.6802	0.88	0.7869	-1.0	-1.0	0.6833	0.5387	0.8042	0.8347	-1.0	-1.0	0.8347	0.5087	0.7667	0.6831	0.8318	0.8488	0.9056
0.5715	30.0	1530	0.6777	0.6802	0.88	0.7868	-1.0	-1.0	0.6832	0.5387	0.8	0.8347	-1.0	-1.0	0.8347	0.5085	0.7667	0.6831	0.8318	0.8488	0.9056

Framework versions

Transformers 5.0.0

Pytorch 2.10.0+cu128

Datasets 4.0.0

Tokenizers 0.22.2

humellad/yolo_finetuned_fruits

yolo_finetuned_fruits

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

yolo_finetuned_fruits

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions