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: 0.6435
• Map: 0.6656
• Map 50: 0.8584
• Map 75: 0.8078
• Map Small: -1.0
• Map Medium: -1.0
• Map Large: 0.6662
• Mar 1: 0.5486
• Mar 10: 0.8152
• Mar 100: 0.8541
• Mar Small: -1.0
• Mar Medium: -1.0
• Mar Large: 0.8541
• Map Banana: 0.4776
• Mar 100 Banana: 0.8042
• Map Orange: 0.6854
• Mar 100 Orange: 0.8636
• Map Apple: 0.8338
• Mar 100 Apple: 0.8944

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	1.8431	0.0284	0.0658	0.0262	-1.0	-1.0	0.0298	0.0324	0.1882	0.4421	-1.0	-1.0	0.4421	0.0124	0.5542	0.024	0.35	0.0489	0.4222
No log	2.0	102	1.7374	0.0326	0.076	0.0255	-1.0	-1.0	0.0332	0.0694	0.2329	0.4395	-1.0	-1.0	0.4395	0.0661	0.5417	0.0125	0.3045	0.0191	0.4722
No log	3.0	153	1.6816	0.04	0.0948	0.028	-1.0	-1.0	0.0402	0.1349	0.2661	0.4966	-1.0	-1.0	0.4966	0.069	0.5667	0.0212	0.4455	0.0298	0.4778
No log	4.0	204	1.7031	0.0391	0.0858	0.0339	-1.0	-1.0	0.0392	0.116	0.2778	0.5347	-1.0	-1.0	0.5347	0.0658	0.5667	0.0239	0.4818	0.0276	0.5556
No log	5.0	255	1.5714	0.1005	0.2657	0.0606	-1.0	-1.0	0.1008	0.2056	0.3856	0.5269	-1.0	-1.0	0.5269	0.0763	0.55	0.1142	0.4864	0.1109	0.5444
No log	6.0	306	1.3019	0.1148	0.2774	0.0689	-1.0	-1.0	0.117	0.1945	0.4478	0.6452	-1.0	-1.0	0.6452	0.1209	0.6792	0.115	0.6455	0.1084	0.6111
No log	7.0	357	1.1840	0.1716	0.2911	0.1964	-1.0	-1.0	0.1802	0.3438	0.5866	0.7077	-1.0	-1.0	0.7077	0.118	0.6625	0.2324	0.7273	0.1646	0.7333
No log	8.0	408	1.1440	0.3462	0.5556	0.4163	-1.0	-1.0	0.3463	0.4018	0.6585	0.7264	-1.0	-1.0	0.7264	0.314	0.6792	0.4235	0.7	0.3011	0.8
No log	9.0	459	1.0075	0.4983	0.7346	0.5666	-1.0	-1.0	0.4988	0.4668	0.7413	0.7823	-1.0	-1.0	0.7823	0.3922	0.6833	0.5339	0.8136	0.5689	0.85
1.3814	10.0	510	0.8870	0.5764	0.8102	0.6616	-1.0	-1.0	0.577	0.491	0.7359	0.7897	-1.0	-1.0	0.7897	0.4599	0.7167	0.6132	0.8136	0.6561	0.8389
1.3814	11.0	561	0.8131	0.5733	0.8275	0.7065	-1.0	-1.0	0.5743	0.4693	0.7253	0.7918	-1.0	-1.0	0.7918	0.4448	0.775	0.5464	0.7727	0.7287	0.8278
1.3814	12.0	612	0.7591	0.6024	0.8316	0.6969	-1.0	-1.0	0.6032	0.4914	0.7539	0.8032	-1.0	-1.0	0.8032	0.4466	0.7875	0.6405	0.8	0.7201	0.8222
1.3814	13.0	663	0.8094	0.6017	0.8265	0.7062	-1.0	-1.0	0.6023	0.4996	0.7565	0.8044	-1.0	-1.0	0.8044	0.3917	0.7208	0.6315	0.8091	0.782	0.8833
1.3814	14.0	714	0.7015	0.627	0.8395	0.7252	-1.0	-1.0	0.6274	0.4969	0.7758	0.8039	-1.0	-1.0	0.8039	0.4684	0.7542	0.6133	0.7909	0.7993	0.8667
1.3814	15.0	765	0.7873	0.6263	0.8671	0.7407	-1.0	-1.0	0.6268	0.4849	0.7629	0.8067	-1.0	-1.0	0.8067	0.4687	0.75	0.6192	0.8091	0.7911	0.8611
1.3814	16.0	816	0.7589	0.6119	0.8464	0.7386	-1.0	-1.0	0.6124	0.5114	0.761	0.8022	-1.0	-1.0	0.8022	0.4426	0.7208	0.6095	0.8136	0.7836	0.8722
1.3814	17.0	867	0.6998	0.6468	0.8509	0.7564	-1.0	-1.0	0.6476	0.5167	0.7749	0.8404	-1.0	-1.0	0.8404	0.4802	0.7667	0.6573	0.8545	0.803	0.9
1.3814	18.0	918	0.6883	0.6287	0.8471	0.7281	-1.0	-1.0	0.6297	0.5065	0.8012	0.8343	-1.0	-1.0	0.8343	0.4577	0.775	0.6415	0.85	0.7868	0.8778
1.3814	19.0	969	0.6679	0.6299	0.8304	0.7658	-1.0	-1.0	0.6312	0.5175	0.8003	0.8407	-1.0	-1.0	0.8407	0.4904	0.7958	0.6199	0.8318	0.7793	0.8944
0.7067	20.0	1020	0.6620	0.6307	0.832	0.7763	-1.0	-1.0	0.6315	0.5096	0.772	0.8312	-1.0	-1.0	0.8312	0.4779	0.8042	0.6464	0.8227	0.7679	0.8667
0.7067	21.0	1071	0.6664	0.6424	0.8445	0.7735	-1.0	-1.0	0.6432	0.5143	0.7631	0.8421	-1.0	-1.0	0.8421	0.4694	0.8042	0.6395	0.85	0.8182	0.8722
0.7067	22.0	1122	0.6489	0.6445	0.8523	0.7496	-1.0	-1.0	0.6451	0.5273	0.8027	0.8478	-1.0	-1.0	0.8478	0.479	0.8	0.6641	0.8545	0.7902	0.8889
0.7067	23.0	1173	0.6428	0.6603	0.8561	0.7906	-1.0	-1.0	0.661	0.5312	0.792	0.8512	-1.0	-1.0	0.8512	0.4974	0.8167	0.6671	0.8591	0.8163	0.8778
0.7067	24.0	1224	0.6540	0.6572	0.848	0.7817	-1.0	-1.0	0.6578	0.5426	0.7894	0.8504	-1.0	-1.0	0.8504	0.4965	0.8042	0.6599	0.8636	0.8151	0.8833
0.7067	25.0	1275	0.6384	0.6606	0.8493	0.7954	-1.0	-1.0	0.6611	0.5463	0.8005	0.846	-1.0	-1.0	0.846	0.4852	0.8	0.6779	0.8545	0.8186	0.8833
0.7067	26.0	1326	0.6450	0.6673	0.8494	0.7982	-1.0	-1.0	0.6679	0.5511	0.805	0.8464	-1.0	-1.0	0.8464	0.4835	0.7958	0.6839	0.8545	0.8347	0.8889
0.7067	27.0	1377	0.6478	0.6594	0.8543	0.7998	-1.0	-1.0	0.66	0.5465	0.8059	0.8461	-1.0	-1.0	0.8461	0.4701	0.7958	0.6873	0.8591	0.8207	0.8833
0.7067	28.0	1428	0.6457	0.6626	0.8557	0.8053	-1.0	-1.0	0.6633	0.5486	0.8123	0.8527	-1.0	-1.0	0.8527	0.4723	0.8	0.6827	0.8636	0.833	0.8944
0.7067	29.0	1479	0.6435	0.6647	0.8575	0.8068	-1.0	-1.0	0.6654	0.5486	0.8152	0.8541	-1.0	-1.0	0.8541	0.4757	0.8042	0.6854	0.8636	0.833	0.8944
0.5613	30.0	1530	0.6435	0.6656	0.8584	0.8078	-1.0	-1.0	0.6662	0.5486	0.8152	0.8541	-1.0	-1.0	0.8541	0.4776	0.8042	0.6854	0.8636	0.8338	0.8944

Framework versions

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