yolo_finetuned_raccoon

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: 0.7439
Map: 0.6716
Map 50: 0.9673
Map 75: 0.8837
Map Small: -1.0
Map Medium: 0.471
Map Large: 0.6864
Mar 1: 0.7048
Mar 10: 0.7952
Mar 100: 0.8167
Mar Small: -1.0
Mar Medium: 0.7333
Mar Large: 0.8231
Map Raccoon: 0.6716
Mar 100 Raccoon: 0.8167

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 Raccoon	Mar 100 Raccoon
No log	1.0	40	1.6984	0.0561	0.1537	0.0201	-1.0	0.0	0.061	0.2071	0.3667	0.5571	-1.0	0.0	0.6	0.0561	0.5571
No log	2.0	80	1.4034	0.0917	0.2337	0.0339	-1.0	0.0151	0.1004	0.2286	0.481	0.6286	-1.0	0.3667	0.6487	0.0917	0.6286
No log	3.0	120	1.5315	0.0705	0.201	0.0288	-1.0	0.0034	0.0805	0.2381	0.4333	0.5833	-1.0	0.0667	0.6231	0.0705	0.5833
No log	4.0	160	1.6040	0.0987	0.2656	0.0525	-1.0	0.006	0.1081	0.2357	0.4286	0.5619	-1.0	0.1	0.5974	0.0987	0.5619
No log	5.0	200	1.6814	0.0893	0.234	0.0397	-1.0	0.0049	0.1104	0.2048	0.4762	0.5619	-1.0	0.3	0.5821	0.0893	0.5619
No log	6.0	240	1.6518	0.1028	0.2622	0.0691	-1.0	0.0071	0.1105	0.2762	0.4595	0.5762	-1.0	0.2	0.6051	0.1028	0.5762
No log	7.0	280	1.0601	0.2085	0.3918	0.1889	-1.0	0.0151	0.23	0.4214	0.6429	0.7333	-1.0	0.3333	0.7641	0.2085	0.7333
No log	8.0	320	0.9967	0.2295	0.4045	0.2266	-1.0	0.0413	0.26	0.4524	0.6905	0.7595	-1.0	0.5	0.7795	0.2295	0.7595
No log	9.0	360	0.8575	0.293	0.4967	0.3194	-1.0	0.1463	0.3182	0.5548	0.7262	0.7833	-1.0	0.5	0.8051	0.293	0.7833
No log	10.0	400	0.8759	0.4284	0.7017	0.4938	-1.0	0.1147	0.4565	0.5738	0.7214	0.7762	-1.0	0.6333	0.7872	0.4284	0.7762
No log	11.0	440	0.8862	0.4082	0.7148	0.4267	-1.0	0.2385	0.4265	0.4929	0.7214	0.7905	-1.0	0.6333	0.8026	0.4082	0.7905
No log	12.0	480	0.7574	0.607	0.9075	0.7345	-1.0	0.5011	0.6209	0.6357	0.8048	0.8286	-1.0	0.7333	0.8359	0.607	0.8286
1.0352	13.0	520	0.9198	0.5812	0.9155	0.6406	-1.0	0.3316	0.6038	0.6167	0.7548	0.7738	-1.0	0.5	0.7949	0.5812	0.7738
1.0352	14.0	560	0.7823	0.6139	0.9281	0.6987	-1.0	0.5608	0.6245	0.6643	0.7833	0.7952	-1.0	0.7	0.8026	0.6139	0.7952
1.0352	15.0	600	0.8266	0.6255	0.9595	0.6683	-1.0	0.3716	0.6476	0.6667	0.7619	0.781	-1.0	0.5333	0.8	0.6255	0.781
1.0352	16.0	640	0.8258	0.6212	0.9628	0.6952	-1.0	0.3745	0.6425	0.6429	0.7833	0.8024	-1.0	0.6333	0.8154	0.6212	0.8024
1.0352	17.0	680	0.7867	0.6509	0.9513	0.7863	-1.0	0.3649	0.6761	0.6667	0.8	0.8238	-1.0	0.6667	0.8359	0.6509	0.8238
1.0352	18.0	720	0.7573	0.6644	0.9581	0.8481	-1.0	0.3902	0.6865	0.6738	0.7905	0.819	-1.0	0.7	0.8282	0.6644	0.819
1.0352	19.0	760	0.7638	0.6683	0.9571	0.8439	-1.0	0.4196	0.6885	0.6929	0.8	0.8071	-1.0	0.6333	0.8205	0.6683	0.8071
1.0352	20.0	800	0.8193	0.6368	0.954	0.7606	-1.0	0.4206	0.6558	0.6643	0.7786	0.8048	-1.0	0.6667	0.8154	0.6368	0.8048
1.0352	21.0	840	0.7233	0.671	0.9577	0.7859	-1.0	0.4118	0.6915	0.6619	0.8119	0.8333	-1.0	0.6667	0.8462	0.671	0.8333
1.0352	22.0	880	0.7698	0.6536	0.9566	0.841	-1.0	0.4658	0.6711	0.6857	0.7857	0.8071	-1.0	0.6667	0.8179	0.6536	0.8071
1.0352	23.0	920	0.7467	0.673	0.9621	0.87	-1.0	0.471	0.6891	0.6881	0.8	0.8238	-1.0	0.6667	0.8359	0.673	0.8238
1.0352	24.0	960	0.7547	0.665	0.9662	0.8293	-1.0	0.4788	0.6792	0.6905	0.7976	0.8167	-1.0	0.7	0.8256	0.665	0.8167
0.572	25.0	1000	0.7396	0.67	0.9669	0.8844	-1.0	0.4755	0.6843	0.7	0.7905	0.8214	-1.0	0.7667	0.8256	0.67	0.8214
0.572	26.0	1040	0.7605	0.663	0.9661	0.8869	-1.0	0.4738	0.6768	0.6952	0.7905	0.8167	-1.0	0.8	0.8179	0.663	0.8167
0.572	27.0	1080	0.7458	0.6782	0.9667	0.8855	-1.0	0.4771	0.6928	0.7048	0.8	0.8262	-1.0	0.8	0.8282	0.6782	0.8262
0.572	28.0	1120	0.7458	0.6712	0.9666	0.8846	-1.0	0.4722	0.6857	0.7048	0.7952	0.8238	-1.0	0.7667	0.8282	0.6712	0.8238
0.572	29.0	1160	0.7439	0.6718	0.9673	0.8845	-1.0	0.471	0.6866	0.7048	0.7952	0.8167	-1.0	0.7333	0.8231	0.6718	0.8167
0.572	30.0	1200	0.7439	0.6716	0.9673	0.8837	-1.0	0.471	0.6864	0.7048	0.7952	0.8167	-1.0	0.7333	0.8231	0.6716	0.8167

Framework versions

Transformers 4.57.6
Pytorch 2.9.0+cu128
Datasets 4.0.0
Tokenizers 0.22.2

adcelis/yolo_finetuned_raccoon

yolo_finetuned_raccoon

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Seed this model