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: 0.6495
• Map: 0.6577
• Map 50: 0.8888
• Map 75: 0.7196
• Map Small: -1.0
• Map Medium: 0.4565
• Map Large: 0.696
• Mar 1: 0.7167
• Mar 10: 0.8238
• Mar 100: 0.8571
• Mar Small: -1.0
• Mar Medium: 0.7
• Mar Large: 0.8833
• Map Raccoon: 0.0
• Mar 100 Raccoon: 0.0

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 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 Raccoon	Mar 100 Raccoon
No log	1.0	40	1.7327	0.0125	0.0323	0.0087	-1.0	0.0009	0.0269	0.1643	0.3119	0.5643	-1.0	0.1333	0.6361	0.0	0.0
No log	2.0	80	1.5556	0.0334	0.0889	0.0197	-1.0	0.0013	0.0512	0.1619	0.4143	0.6024	-1.0	0.15	0.6778	0.0	0.0
No log	3.0	120	1.3242	0.0751	0.1717	0.0527	-1.0	0.0321	0.086	0.2381	0.5	0.6619	-1.0	0.1833	0.7417	0.0	0.0
No log	4.0	160	1.3937	0.0627	0.1689	0.0273	-1.0	0.018	0.0749	0.2024	0.4	0.6571	-1.0	0.3667	0.7056	0.0	0.0
No log	5.0	200	1.4487	0.0691	0.186	0.0318	-1.0	0.0136	0.0819	0.1976	0.381	0.6619	-1.0	0.3833	0.7083	0.0	0.0
No log	6.0	240	1.6055	0.072	0.1773	0.0367	-1.0	0.0166	0.0826	0.2738	0.3976	0.6	-1.0	0.1167	0.6806	0.0	0.0
No log	7.0	280	1.2369	0.0891	0.1749	0.0764	-1.0	0.0147	0.1052	0.3286	0.5643	0.6762	-1.0	0.3	0.7389	0.0	0.0
No log	8.0	320	1.1697	0.1039	0.2156	0.0769	-1.0	0.0276	0.1226	0.35	0.5929	0.7071	-1.0	0.35	0.7667	0.0	0.0
No log	9.0	360	1.3522	0.0799	0.1892	0.043	-1.0	0.0075	0.0965	0.3333	0.531	0.6667	-1.0	0.2167	0.7417	0.0	0.0
No log	10.0	400	1.1073	0.1661	0.3327	0.1245	-1.0	0.0721	0.1853	0.4	0.6333	0.7333	-1.0	0.45	0.7806	0.0	0.0
No log	11.0	440	1.2113	0.1826	0.2611	0.1954	-1.0	0.0132	0.2154	0.5452	0.6667	0.7143	-1.0	0.1833	0.8028	0.0	0.0
No log	12.0	480	0.7511	0.181	0.2856	0.1872	-1.0	0.0802	0.2093	0.5429	0.7429	0.8214	-1.0	0.6167	0.8556	0.0	0.0
1.1152	13.0	520	0.7134	0.2717	0.3694	0.3298	-1.0	0.3034	0.2829	0.6524	0.7976	0.8429	-1.0	0.7	0.8667	0.0	0.0
1.1152	14.0	560	0.7378	0.2944	0.4283	0.3525	-1.0	0.3236	0.3003	0.631	0.7857	0.8405	-1.0	0.65	0.8722	0.0	0.0
1.1152	15.0	600	0.6910	0.3206	0.4532	0.3833	-1.0	0.2139	0.3496	0.6595	0.8095	0.8571	-1.0	0.7	0.8833	0.0	0.0
1.1152	16.0	640	0.7127	0.3638	0.5373	0.3835	-1.0	0.207	0.399	0.6214	0.7905	0.8571	-1.0	0.6833	0.8861	0.0	0.0
1.1152	17.0	680	0.7322	0.423	0.6133	0.487	-1.0	0.303	0.4664	0.6667	0.7952	0.85	-1.0	0.6833	0.8778	0.0	0.0
1.1152	18.0	720	0.6799	0.4933	0.6995	0.5327	-1.0	0.4098	0.5267	0.7167	0.8381	0.8667	-1.0	0.7333	0.8889	0.0	0.0
1.1152	19.0	760	0.7052	0.5861	0.806	0.6607	-1.0	0.4365	0.6174	0.6857	0.8286	0.8595	-1.0	0.6667	0.8917	0.0	0.0
1.1152	20.0	800	0.6941	0.5829	0.8159	0.6512	-1.0	0.4048	0.6189	0.6881	0.819	0.8571	-1.0	0.6833	0.8861	0.0	0.0
1.1152	21.0	840	0.7119	0.6005	0.8281	0.6929	-1.0	0.3645	0.6466	0.7024	0.7905	0.8429	-1.0	0.6833	0.8694	0.0	0.0
1.1152	22.0	880	0.6753	0.6023	0.8291	0.6487	-1.0	0.4107	0.6406	0.7214	0.819	0.8619	-1.0	0.7167	0.8861	0.0	0.0
1.1152	23.0	920	0.6418	0.6598	0.8868	0.7259	-1.0	0.4322	0.703	0.7262	0.8167	0.8643	-1.0	0.7	0.8917	0.0	0.0
1.1152	24.0	960	0.6646	0.6521	0.8725	0.7208	-1.0	0.4154	0.6961	0.7095	0.8262	0.869	-1.0	0.7	0.8972	0.0	0.0
0.661	25.0	1000	0.6629	0.6552	0.8923	0.7389	-1.0	0.4398	0.6956	0.7262	0.8167	0.8548	-1.0	0.6667	0.8861	0.0	0.0
0.661	26.0	1040	0.6507	0.6501	0.8893	0.7147	-1.0	0.4404	0.6893	0.7167	0.8119	0.8524	-1.0	0.6833	0.8806	0.0	0.0
0.661	27.0	1080	0.6527	0.6502	0.8883	0.7192	-1.0	0.4258	0.6913	0.7167	0.831	0.8548	-1.0	0.6833	0.8833	0.0	0.0
0.661	28.0	1120	0.6488	0.6592	0.8861	0.7451	-1.0	0.447	0.697	0.719	0.8262	0.8571	-1.0	0.7	0.8833	0.0	0.0
0.661	29.0	1160	0.6496	0.6578	0.8885	0.7198	-1.0	0.4565	0.6961	0.7167	0.8238	0.8571	-1.0	0.7	0.8833	0.0	0.0
0.661	30.0	1200	0.6495	0.6577	0.8888	0.7196	-1.0	0.4565	0.696	0.7167	0.8238	0.8571	-1.0	0.7	0.8833	0.0	0.0

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1