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: 0.6086
• Map: 0.6954
• Map 50: 0.8733
• Map 75: 0.7818
• Map Small: -1.0
• Map Medium: -1.0
• Map Large: 0.6965
• Mar 1: 0.5586
• Mar 10: 0.8173
• Mar 100: 0.8624
• Mar Small: -1.0
• Mar Medium: -1.0
• Mar Large: 0.8624
• Map Banana: 0.5556
• Mar 100 Banana: 0.8083
• Map Orange: 0.7129
• Mar 100 Orange: 0.8455
• Map Apple: 0.8178
• Mar 100 Apple: 0.9333

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	1.9727	0.0036	0.0093	0.0026	-1.0	-1.0	0.0039	0.0509	0.1653	0.2986	-1.0	-1.0	0.2986	0.0065	0.4625	0.0	0.0	0.0042	0.4333
No log	2.0	102	1.2779	0.1052	0.1822	0.1277	-1.0	-1.0	0.1065	0.2761	0.4873	0.6523	-1.0	-1.0	0.6523	0.063	0.6917	0.2075	0.5318	0.0452	0.7333
No log	3.0	153	1.1161	0.1153	0.1798	0.1344	-1.0	-1.0	0.1168	0.2678	0.5101	0.6593	-1.0	-1.0	0.6593	0.0892	0.7417	0.2069	0.5364	0.0497	0.7
No log	4.0	204	0.9563	0.1555	0.2336	0.1899	-1.0	-1.0	0.1563	0.3937	0.6206	0.7789	-1.0	-1.0	0.7789	0.0725	0.7625	0.2411	0.7409	0.1529	0.8333
No log	5.0	255	0.9018	0.3152	0.5072	0.3052	-1.0	-1.0	0.3155	0.4161	0.6648	0.784	-1.0	-1.0	0.784	0.1813	0.7625	0.3717	0.7727	0.3926	0.8167
No log	6.0	306	0.8643	0.426	0.6408	0.4427	-1.0	-1.0	0.4285	0.4526	0.7179	0.7961	-1.0	-1.0	0.7961	0.2458	0.7667	0.3878	0.7773	0.6445	0.8444
No log	7.0	357	1.0006	0.4319	0.6614	0.5461	-1.0	-1.0	0.4325	0.4332	0.6923	0.7455	-1.0	-1.0	0.7455	0.3186	0.6917	0.3466	0.7227	0.6306	0.8222
No log	8.0	408	0.8097	0.5011	0.715	0.6133	-1.0	-1.0	0.5015	0.474	0.7499	0.7963	-1.0	-1.0	0.7963	0.3479	0.7875	0.4393	0.7682	0.7161	0.8333
No log	9.0	459	0.8407	0.5498	0.7716	0.6642	-1.0	-1.0	0.5505	0.482	0.7443	0.7981	-1.0	-1.0	0.7981	0.3953	0.7625	0.525	0.7818	0.7292	0.85
1.1272	10.0	510	0.8173	0.5445	0.7774	0.6648	-1.0	-1.0	0.545	0.4709	0.7544	0.8093	-1.0	-1.0	0.8093	0.392	0.7917	0.5143	0.7864	0.7271	0.85
1.1272	11.0	561	0.7884	0.5363	0.7619	0.6062	-1.0	-1.0	0.538	0.507	0.7425	0.7992	-1.0	-1.0	0.7992	0.3934	0.7542	0.5035	0.8045	0.7119	0.8389
1.1272	12.0	612	0.7833	0.5742	0.8005	0.6775	-1.0	-1.0	0.5814	0.5027	0.7626	0.8179	-1.0	-1.0	0.8179	0.4375	0.7542	0.5368	0.8273	0.7482	0.8722
1.1272	13.0	663	0.7102	0.6119	0.7814	0.6916	-1.0	-1.0	0.613	0.5239	0.7782	0.827	-1.0	-1.0	0.827	0.4338	0.775	0.6286	0.8227	0.7733	0.8833
1.1272	14.0	714	0.7197	0.6352	0.8276	0.7389	-1.0	-1.0	0.6379	0.533	0.7692	0.8144	-1.0	-1.0	0.8144	0.4824	0.7583	0.6861	0.8182	0.7371	0.8667
1.1272	15.0	765	0.7009	0.6253	0.8195	0.7296	-1.0	-1.0	0.6258	0.5375	0.7769	0.8353	-1.0	-1.0	0.8353	0.4377	0.7792	0.6785	0.8545	0.7597	0.8722
1.1272	16.0	816	0.6893	0.6301	0.8222	0.747	-1.0	-1.0	0.6306	0.5362	0.7767	0.835	-1.0	-1.0	0.835	0.4743	0.7833	0.6589	0.8273	0.757	0.8944
1.1272	17.0	867	0.6341	0.6753	0.8555	0.7759	-1.0	-1.0	0.6762	0.5662	0.7835	0.8442	-1.0	-1.0	0.8442	0.5202	0.7917	0.692	0.8409	0.8138	0.9
1.1272	18.0	918	0.6253	0.6725	0.8512	0.754	-1.0	-1.0	0.6736	0.5688	0.7894	0.8517	-1.0	-1.0	0.8517	0.5307	0.8333	0.6948	0.8273	0.7922	0.8944
1.1272	19.0	969	0.6525	0.6618	0.8636	0.7468	-1.0	-1.0	0.6654	0.5577	0.7826	0.8566	-1.0	-1.0	0.8566	0.5303	0.8208	0.6762	0.8545	0.7789	0.8944
0.6925	20.0	1020	0.6663	0.668	0.8639	0.7875	-1.0	-1.0	0.6686	0.5516	0.7866	0.857	-1.0	-1.0	0.857	0.5539	0.8125	0.6425	0.8364	0.8075	0.9222
0.6925	21.0	1071	0.6235	0.6855	0.8678	0.7723	-1.0	-1.0	0.6861	0.5543	0.8057	0.8624	-1.0	-1.0	0.8624	0.5456	0.8083	0.6906	0.8455	0.8204	0.9333
0.6925	22.0	1122	0.6298	0.6933	0.8776	0.7791	-1.0	-1.0	0.695	0.5605	0.809	0.8618	-1.0	-1.0	0.8618	0.5629	0.8167	0.6909	0.8409	0.8261	0.9278
0.6925	23.0	1173	0.6327	0.6893	0.8759	0.7788	-1.0	-1.0	0.6911	0.5574	0.8128	0.8582	-1.0	-1.0	0.8582	0.5469	0.8125	0.7014	0.8455	0.8197	0.9167
0.6925	24.0	1224	0.6120	0.7012	0.8708	0.78	-1.0	-1.0	0.7021	0.5577	0.8117	0.8632	-1.0	-1.0	0.8632	0.5573	0.8042	0.6954	0.8409	0.8507	0.9444
0.6925	25.0	1275	0.6105	0.6952	0.8776	0.7799	-1.0	-1.0	0.696	0.5571	0.8098	0.854	-1.0	-1.0	0.854	0.567	0.8125	0.6971	0.8273	0.8215	0.9222
0.6925	26.0	1326	0.6070	0.6958	0.8727	0.7786	-1.0	-1.0	0.6967	0.56	0.8158	0.8589	-1.0	-1.0	0.8589	0.5665	0.8125	0.7029	0.8364	0.8179	0.9278
0.6925	27.0	1377	0.6091	0.6931	0.8647	0.7758	-1.0	-1.0	0.6941	0.5619	0.8159	0.865	-1.0	-1.0	0.865	0.5482	0.8208	0.7087	0.8409	0.8223	0.9333
0.6925	28.0	1428	0.6082	0.6973	0.8736	0.7825	-1.0	-1.0	0.6983	0.56	0.8158	0.8641	-1.0	-1.0	0.8641	0.5635	0.8125	0.7109	0.8409	0.8175	0.9389
0.6925	29.0	1479	0.6085	0.6955	0.8735	0.7817	-1.0	-1.0	0.6965	0.5586	0.8173	0.8656	-1.0	-1.0	0.8656	0.5564	0.8125	0.7138	0.8455	0.8163	0.9389
0.5502	30.0	1530	0.6086	0.6954	0.8733	0.7818	-1.0	-1.0	0.6965	0.5586	0.8173	0.8624	-1.0	-1.0	0.8624	0.5556	0.8083	0.7129	0.8455	0.8178	0.9333

Framework versions

• Transformers 5.0.0
• Pytorch 2.10.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2