yolo_finetuned_racoon

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: 0.7860
Map: 0.5222
Map 50: 0.8485
Map 75: 0.6197
Map Small: -1.0
Map Medium: 0.0056
Map Large: 0.5532
Mar 1: 0.4235
Mar 10: 0.6618
Mar 100: 0.7265
Mar Small: -1.0
Mar Medium: 0.35
Mar Large: 0.75
Map Background: -1.0
Mar 100 Background: -1.0
Map Kangaroo: 0.5222
Mar 100 Kangaroo: 0.7265

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 Background	Mar 100 Background	Map Kangaroo	Mar 100 Kangaroo
No log	1.0	31	2.9940	0.0024	0.013	0.0001	-1.0	0.0	0.0032	0.0088	0.0588	0.1176	-1.0	0.0	0.125	-1.0	-1.0	0.0024	0.1176
No log	2.0	62	2.9258	0.0031	0.0176	0.0005	-1.0	0.0	0.0035	0.0088	0.0765	0.1088	-1.0	0.0	0.1156	-1.0	-1.0	0.0031	0.1088
No log	3.0	93	2.5915	0.009	0.0567	0.0006	-1.0	0.0005	0.0097	0.0265	0.0794	0.1824	-1.0	0.1	0.1875	0.009	0.1824
No log	4.0	124	2.5558	0.009	0.0478	0.0001	-1.0	0.0003	0.0096	0.0471	0.0853	0.1647	-1.0	0.1	0.1688	0.009	0.1647
No log	5.0	155	2.3728	0.0529	0.2289	0.0009	-1.0	0.0004	0.0577	0.0735	0.1265	0.1912	-1.0	0.1	0.1969	0.0529	0.1912
No log	6.0	186	2.2110	0.0425	0.1595	0.0092	-1.0	0.0	0.0476	0.0794	0.1382	0.1941	-1.0	0.0	0.2062	0.0425	0.1941
No log	7.0	217	2.0846	0.0745	0.3167	0.0112	-1.0	0.0	0.0813	0.0853	0.2176	0.2618	-1.0	0.0	0.2781	0.0745	0.2618
No log	8.0	248	1.6104	0.2083	0.6403	0.0745	-1.0	0.0007	0.2218	0.2	0.3471	0.4029	-1.0	0.05	0.425	0.2083	0.4029
No log	9.0	279	1.3185	0.3409	0.7858	0.2281	-1.0	0.0001	0.3633	0.2765	0.4735	0.5471	-1.0	0.05	0.5781	0.3409	0.5471
No log	10.0	310	1.1966	0.4245	0.8422	0.397	-1.0	0.0008	0.4525	0.3353	0.5529	0.6	-1.0	0.2	0.625	0.4245	0.6
No log	11.0	341	1.0366	0.4596	0.8161	0.4524	-1.0	0.0005	0.492	0.3676	0.5912	0.6353	-1.0	0.05	0.6719	-1.0	-1.0	0.4596	0.6353
No log	12.0	372	1.0827	0.4049	0.8489	0.3213	-1.0	0.0045	0.4318	0.3147	0.5647	0.6147	-1.0	0.25	0.6375	0.4049	0.6147
No log	13.0	403	1.0586	0.4227	0.7987	0.4476	-1.0	0.0035	0.4506	0.3294	0.5971	0.6647	-1.0	0.3	0.6875	0.4227	0.6647
No log	14.0	434	1.1212	0.4178	0.7742	0.3663	-1.0	0.0007	0.4471	0.3441	0.5706	0.6235	-1.0	0.1	0.6562	0.4178	0.6235
No log	15.0	465	0.9672	0.5019	0.8656	0.5506	-1.0	0.0	0.5336	0.3912	0.6382	0.6588	-1.0	0.0	0.7	0.5019	0.6588
No log	16.0	496	0.8672	0.4916	0.835	0.481	-1.0	0.0111	0.5209	0.4382	0.6706	0.7	-1.0	0.3	0.725	0.4916	0.7
1.0685	17.0	527	0.8415	0.5112	0.8593	0.4911	-1.0	0.0054	0.542	0.4294	0.6588	0.7059	-1.0	0.3	0.7312	0.5112	0.7059
1.0685	18.0	558	0.8310	0.5161	0.8606	0.6286	-1.0	0.0055	0.5469	0.4	0.6529	0.7	-1.0	0.35	0.7219	0.5161	0.7
1.0685	19.0	589	0.8094	0.5534	0.8509	0.6289	-1.0	0.006	0.5857	0.4294	0.6794	0.7294	-1.0	0.35	0.7531	0.5534	0.7294
1.0685	20.0	620	0.8320	0.5383	0.8635	0.6323	-1.0	0.0062	0.5705	0.4176	0.6735	0.7353	-1.0	0.35	0.7594	0.5383	0.7353
1.0685	21.0	651	0.8311	0.5444	0.8594	0.6468	-1.0	0.0044	0.5779	0.4118	0.6676	0.7441	-1.0	0.35	0.7688	0.5444	0.7441
1.0685	22.0	682	0.7858	0.5268	0.8471	0.6528	-1.0	0.0059	0.5596	0.4147	0.6588	0.7412	-1.0	0.4	0.7625	-1.0	-1.0	0.5268	0.7412
1.0685	23.0	713	0.7901	0.5331	0.8461	0.6214	-1.0	0.0058	0.5651	0.4265	0.6647	0.7382	-1.0	0.35	0.7625	-1.0	-1.0	0.5331	0.7382
1.0685	24.0	744	0.7845	0.522	0.8477	0.6225	-1.0	0.0056	0.5535	0.4235	0.6676	0.7382	-1.0	0.35	0.7625	-1.0	-1.0	0.522	0.7382
1.0685	25.0	775	0.7859	0.5278	0.8445	0.6197	-1.0	0.0054	0.5594	0.4353	0.6676	0.7265	-1.0	0.35	0.75	-1.0	-1.0	0.5278	0.7265
1.0685	26.0	806	0.7894	0.5267	0.8491	0.6199	-1.0	0.0058	0.5576	0.4294	0.6647	0.7265	-1.0	0.35	0.75	-1.0	-1.0	0.5267	0.7265
1.0685	27.0	837	0.7889	0.5279	0.85	0.6207	-1.0	0.0057	0.5589	0.4235	0.6647	0.7294	-1.0	0.35	0.7531	-1.0	-1.0	0.5279	0.7294
1.0685	28.0	868	0.7870	0.5158	0.8482	0.6183	-1.0	0.0055	0.5464	0.4176	0.6559	0.7235	-1.0	0.35	0.7469	-1.0	-1.0	0.5158	0.7235
1.0685	29.0	899	0.7862	0.5212	0.8471	0.6178	-1.0	0.0056	0.5521	0.4235	0.6618	0.7265	-1.0	0.35	0.75	-1.0	-1.0	0.5212	0.7265
1.0685	30.0	930	0.7860	0.5222	0.8485	0.6197	-1.0	0.0056	0.5532	0.4235	0.6618	0.7265	-1.0	0.35	0.75	-1.0	-1.0	0.5222	0.7265

Framework versions

Transformers 5.0.0
Pytorch 2.10.0+cu128
Datasets 4.0.0
Tokenizers 0.22.2

Loading…

yolo_finetuned_racoon

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: 0.7860

Map: 0.5222

Map 50: 0.8485

Map 75: 0.6197

Map Small: -1.0

Map Medium: 0.0056

Map Large: 0.5532

Mar 1: 0.4235

Mar 10: 0.6618

Mar 100: 0.7265

Mar Small: -1.0

Mar Medium: 0.35

Mar Large: 0.75

Map Background: -1.0

Mar 100 Background: -1.0

Map Kangaroo: 0.5222

Mar 100 Kangaroo: 0.7265

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 Background	Mar 100 Background	Map Kangaroo	Mar 100 Kangaroo
No log	1.0	31	2.9940	0.0024	0.013	0.0001	-1.0	0.0	0.0032	0.0088	0.0588	0.1176	-1.0	0.0	0.125	-1.0	-1.0	0.0024	0.1176
No log	2.0	62	2.9258	0.0031	0.0176	0.0005	-1.0	0.0	0.0035	0.0088	0.0765	0.1088	-1.0	0.0	0.1156	-1.0	-1.0	0.0031	0.1088
No log	3.0	93	2.5915	0.009	0.0567	0.0006	-1.0	0.0005	0.0097	0.0265	0.0794	0.1824	-1.0	0.1	0.1875	0.009	0.1824
No log	4.0	124	2.5558	0.009	0.0478	0.0001	-1.0	0.0003	0.0096	0.0471	0.0853	0.1647	-1.0	0.1	0.1688	0.009	0.1647
No log	5.0	155	2.3728	0.0529	0.2289	0.0009	-1.0	0.0004	0.0577	0.0735	0.1265	0.1912	-1.0	0.1	0.1969	0.0529	0.1912
No log	6.0	186	2.2110	0.0425	0.1595	0.0092	-1.0	0.0	0.0476	0.0794	0.1382	0.1941	-1.0	0.0	0.2062	0.0425	0.1941
No log	7.0	217	2.0846	0.0745	0.3167	0.0112	-1.0	0.0	0.0813	0.0853	0.2176	0.2618	-1.0	0.0	0.2781	0.0745	0.2618
No log	8.0	248	1.6104	0.2083	0.6403	0.0745	-1.0	0.0007	0.2218	0.2	0.3471	0.4029	-1.0	0.05	0.425	0.2083	0.4029
No log	9.0	279	1.3185	0.3409	0.7858	0.2281	-1.0	0.0001	0.3633	0.2765	0.4735	0.5471	-1.0	0.05	0.5781	0.3409	0.5471
No log	10.0	310	1.1966	0.4245	0.8422	0.397	-1.0	0.0008	0.4525	0.3353	0.5529	0.6	-1.0	0.2	0.625	0.4245	0.6
No log	11.0	341	1.0366	0.4596	0.8161	0.4524	-1.0	0.0005	0.492	0.3676	0.5912	0.6353	-1.0	0.05	0.6719	-1.0	-1.0	0.4596	0.6353
No log	12.0	372	1.0827	0.4049	0.8489	0.3213	-1.0	0.0045	0.4318	0.3147	0.5647	0.6147	-1.0	0.25	0.6375	0.4049	0.6147
No log	13.0	403	1.0586	0.4227	0.7987	0.4476	-1.0	0.0035	0.4506	0.3294	0.5971	0.6647	-1.0	0.3	0.6875	0.4227	0.6647
No log	14.0	434	1.1212	0.4178	0.7742	0.3663	-1.0	0.0007	0.4471	0.3441	0.5706	0.6235	-1.0	0.1	0.6562	0.4178	0.6235
No log	15.0	465	0.9672	0.5019	0.8656	0.5506	-1.0	0.0	0.5336	0.3912	0.6382	0.6588	-1.0	0.0	0.7	0.5019	0.6588
No log	16.0	496	0.8672	0.4916	0.835	0.481	-1.0	0.0111	0.5209	0.4382	0.6706	0.7	-1.0	0.3	0.725	0.4916	0.7
1.0685	17.0	527	0.8415	0.5112	0.8593	0.4911	-1.0	0.0054	0.542	0.4294	0.6588	0.7059	-1.0	0.3	0.7312	0.5112	0.7059
1.0685	18.0	558	0.8310	0.5161	0.8606	0.6286	-1.0	0.0055	0.5469	0.4	0.6529	0.7	-1.0	0.35	0.7219	0.5161	0.7
1.0685	19.0	589	0.8094	0.5534	0.8509	0.6289	-1.0	0.006	0.5857	0.4294	0.6794	0.7294	-1.0	0.35	0.7531	0.5534	0.7294
1.0685	20.0	620	0.8320	0.5383	0.8635	0.6323	-1.0	0.0062	0.5705	0.4176	0.6735	0.7353	-1.0	0.35	0.7594	0.5383	0.7353
1.0685	21.0	651	0.8311	0.5444	0.8594	0.6468	-1.0	0.0044	0.5779	0.4118	0.6676	0.7441	-1.0	0.35	0.7688	0.5444	0.7441
1.0685	22.0	682	0.7858	0.5268	0.8471	0.6528	-1.0	0.0059	0.5596	0.4147	0.6588	0.7412	-1.0	0.4	0.7625	-1.0	-1.0	0.5268	0.7412
1.0685	23.0	713	0.7901	0.5331	0.8461	0.6214	-1.0	0.0058	0.5651	0.4265	0.6647	0.7382	-1.0	0.35	0.7625	-1.0	-1.0	0.5331	0.7382
1.0685	24.0	744	0.7845	0.522	0.8477	0.6225	-1.0	0.0056	0.5535	0.4235	0.6676	0.7382	-1.0	0.35	0.7625	-1.0	-1.0	0.522	0.7382
1.0685	25.0	775	0.7859	0.5278	0.8445	0.6197	-1.0	0.0054	0.5594	0.4353	0.6676	0.7265	-1.0	0.35	0.75	-1.0	-1.0	0.5278	0.7265
1.0685	26.0	806	0.7894	0.5267	0.8491	0.6199	-1.0	0.0058	0.5576	0.4294	0.6647	0.7265	-1.0	0.35	0.75	-1.0	-1.0	0.5267	0.7265
1.0685	27.0	837	0.7889	0.5279	0.85	0.6207	-1.0	0.0057	0.5589	0.4235	0.6647	0.7294	-1.0	0.35	0.7531	-1.0	-1.0	0.5279	0.7294
1.0685	28.0	868	0.7870	0.5158	0.8482	0.6183	-1.0	0.0055	0.5464	0.4176	0.6559	0.7235	-1.0	0.35	0.7469	-1.0	-1.0	0.5158	0.7235
1.0685	29.0	899	0.7862	0.5212	0.8471	0.6178	-1.0	0.0056	0.5521	0.4235	0.6618	0.7265	-1.0	0.35	0.75	-1.0	-1.0	0.5212	0.7265
1.0685	30.0	930	0.7860	0.5222	0.8485	0.6197	-1.0	0.0056	0.5532	0.4235	0.6618	0.7265	-1.0	0.35	0.75	-1.0	-1.0	0.5222	0.7265

Framework versions

Transformers 5.0.0

Pytorch 2.10.0+cu128

Datasets 4.0.0

Tokenizers 0.22.2

joarnaiz/yolo_finetuned_racoon

yolo_finetuned_racoon

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

yolo_finetuned_racoon

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions