lwdetr-tiny-tray-cart-transfer-20260303-221609

This model is a fine-tuned version of AnnaZhang/lwdetr_tiny_60e_coco on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 3.0021
• Map: 0.0021
• Map 50: 0.0099
• Map 75: 0.0004
• Map Small: 0.0006
• Map Medium: 0.0021
• Map Large: 0.0065
• Mar 1: 0.0001
• Mar 10: 0.0037
• Mar 100: 0.0326
• Mar Small: 0.0095
• Mar Medium: 0.025
• Mar Large: 0.103
• Map Tray: 0.0041
• Mar 100 Tray: 0.0571
• Map Cart: 0.0001
• Mar 100 Cart: 0.0081

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: 0.0001
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 3
• num_epochs: 50

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 Tray	Mar 100 Tray	Map Cart	Mar 100 Cart
No log	1.0	7	5.0852	0.0004	0.0022	0.0	0.0	0.0023	0.0001	0.0008	0.0009	0.0178	0.0	0.0197	0.0121	0.0001	0.005	0.0007	0.0306
No log	2.0	14	4.9075	0.0002	0.0008	0.0	0.0	0.0007	0.0002	0.0	0.0046	0.0123	0.0	0.0124	0.0174	0.0003	0.0117	0.0001	0.0129
No log	3.0	21	4.8383	0.0004	0.0011	0.0	0.0	0.0003	0.0009	0.0004	0.0015	0.006	0.0	0.0046	0.0197	0.0007	0.0104	0.0	0.0016
No log	4.0	28	4.5661	0.0002	0.0008	0.0001	0.0001	0.0002	0.0004	0.0	0.0008	0.0058	0.0024	0.0039	0.022	0.0003	0.0116	0.0	0.0
No log	5.0	35	4.4083	0.0001	0.0006	0.0	0.0	0.0002	0.0002	0.0	0.0004	0.005	0.0	0.0034	0.0197	0.0002	0.01	0.0	0.0
No log	6.0	42	4.2050	0.0002	0.0009	0.0001	0.0	0.0002	0.0006	0.0	0.0011	0.0063	0.0	0.0052	0.0167	0.0004	0.0125	0.0	0.0
No log	7.0	49	4.1096	0.0002	0.0012	0.0	0.0	0.0002	0.0008	0.0002	0.0005	0.0084	0.0	0.0071	0.022	0.0003	0.0103	0.0001	0.0065
No log	8.0	56	4.0172	0.0002	0.0008	0.0	0.0	0.0002	0.0003	0.0001	0.0011	0.006	0.0	0.0049	0.0167	0.0004	0.012	0.0	0.0
No log	9.0	63	3.8443	0.0005	0.0022	0.0	0.0	0.0009	0.0012	0.0	0.0019	0.0138	0.0	0.0129	0.0273	0.0007	0.0164	0.0002	0.0113
No log	10.0	70	3.8083	0.0003	0.0016	0.0	0.0	0.0003	0.0011	0.0001	0.0009	0.0115	0.0	0.0097	0.0311	0.0005	0.0149	0.0001	0.0081
No log	11.0	77	3.6705	0.0005	0.0024	0.0	0.0	0.0008	0.0012	0.0001	0.0014	0.0168	0.0	0.0151	0.0379	0.0008	0.0207	0.0001	0.0129
No log	12.0	84	3.6117	0.0003	0.0015	0.0	0.0	0.0005	0.0005	0.0	0.001	0.0098	0.0	0.0085	0.0235	0.0007	0.0196	0.0	0.0
No log	13.0	91	3.6202	0.0006	0.0029	0.0	0.0	0.0008	0.0011	0.0002	0.0009	0.0136	0.0	0.0113	0.0364	0.0012	0.0271	0.0	0.0
No log	14.0	98	3.4994	0.0007	0.0037	0.0	0.0	0.0009	0.0012	0.0	0.0012	0.0145	0.0	0.0123	0.0364	0.0013	0.0273	0.0	0.0016
No log	15.0	105	3.4583	0.0006	0.0029	0.0	0.0	0.0007	0.0012	0.0	0.0008	0.0136	0.0	0.0109	0.0394	0.0011	0.0271	0.0	0.0
No log	16.0	112	3.4286	0.0007	0.0035	0.0001	0.0004	0.0008	0.0017	0.0008	0.0012	0.0167	0.0071	0.0126	0.0538	0.0013	0.0302	0.0001	0.0032
No log	17.0	119	3.3848	0.0013	0.0057	0.0002	0.0	0.0016	0.0025	0.0001	0.0052	0.0254	0.0	0.0214	0.0667	0.0023	0.0427	0.0002	0.0081
No log	18.0	126	3.3248	0.0008	0.0036	0.0001	0.0	0.0009	0.0016	0.0	0.0014	0.0185	0.0	0.0147	0.0549	0.0015	0.0337	0.0	0.0032
No log	19.0	133	3.2500	0.0009	0.0036	0.0001	0.0	0.001	0.0019	0.0	0.0018	0.0181	0.0	0.0148	0.0508	0.0017	0.0363	0.0	0.0
No log	20.0	140	3.2823	0.0012	0.0055	0.0002	0.0005	0.0014	0.0019	0.0	0.0022	0.0217	0.0048	0.0178	0.0583	0.0024	0.0433	0.0	0.0
No log	21.0	147	3.1991	0.0011	0.0049	0.0002	0.0005	0.0013	0.0022	0.0002	0.002	0.0212	0.0048	0.017	0.0606	0.0023	0.0424	0.0	0.0
No log	22.0	154	3.2038	0.001	0.0046	0.0001	0.0	0.001	0.0026	0.0001	0.0014	0.0189	0.0	0.0139	0.0652	0.002	0.0377	0.0	0.0
No log	23.0	161	3.1729	0.0011	0.0048	0.0005	0.0027	0.0012	0.0026	0.0006	0.0024	0.0207	0.0071	0.0158	0.0652	0.0023	0.0414	0.0	0.0
No log	24.0	168	3.1440	0.0011	0.0048	0.0002	0.0001	0.0013	0.0027	0.0002	0.0022	0.0202	0.0024	0.0153	0.0659	0.0023	0.0404	0.0	0.0
No log	25.0	175	3.0750	0.0013	0.0064	0.0001	0.0008	0.0014	0.0032	0.0	0.001	0.0217	0.0024	0.0169	0.0674	0.0026	0.0435	0.0	0.0
No log	26.0	182	3.0577	0.0017	0.0081	0.0001	0.0011	0.0016	0.0045	0.0008	0.0029	0.0254	0.0238	0.0188	0.0803	0.0032	0.0493	0.0001	0.0016
No log	27.0	189	3.1072	0.0014	0.0062	0.0002	0.0019	0.0014	0.003	0.0	0.0019	0.0243	0.0071	0.0191	0.0727	0.0027	0.047	0.0	0.0016
No log	28.0	196	3.0196	0.0015	0.0069	0.0004	0.0001	0.0014	0.0046	0.0006	0.0024	0.0247	0.0024	0.0176	0.0894	0.0029	0.0494	0.0	0.0
No log	29.0	203	3.0774	0.0017	0.007	0.0006	0.0	0.0014	0.005	0.0	0.0015	0.0242	0.0	0.0174	0.0871	0.0034	0.0483	0.0	0.0
No log	30.0	210	3.0737	0.0021	0.0098	0.0003	0.0031	0.0024	0.0046	0.0002	0.0059	0.0329	0.0143	0.0269	0.0894	0.004	0.0546	0.0002	0.0113
No log	31.0	217	3.0752	0.0017	0.0083	0.0002	0.001	0.0016	0.0046	0.0002	0.0024	0.0286	0.0119	0.0218	0.0894	0.0033	0.0507	0.0001	0.0065
No log	32.0	224	3.1023	0.0016	0.0061	0.0004	0.0	0.0014	0.006	0.0	0.0024	0.0264	0.0	0.018	0.103	0.0032	0.0528	0.0	0.0
No log	33.0	231	2.9882	0.0019	0.0081	0.0004	0.0105	0.0018	0.0057	0.0001	0.0073	0.0345	0.0833	0.0228	0.1041	0.0036	0.0546	0.0002	0.0145
No log	34.0	238	3.0337	0.002	0.0081	0.0004	0.0003	0.0022	0.0052	0.0003	0.0033	0.0291	0.0071	0.0212	0.1	0.004	0.0581	0.0	0.0
No log	35.0	245	3.0331	0.0016	0.0063	0.0004	0.0006	0.0016	0.0052	0.0005	0.0024	0.0292	0.0024	0.0219	0.0977	0.0032	0.0536	0.0	0.0048
No log	36.0	252	2.9962	0.0018	0.0069	0.0004	0.0	0.0019	0.0064	0.0002	0.0073	0.0302	0.0024	0.0227	0.1008	0.0035	0.0555	0.0001	0.0048
No log	37.0	259	3.0349	0.002	0.0077	0.0004	0.0	0.002	0.006	0.0003	0.0043	0.0286	0.0	0.0215	0.0955	0.0039	0.0571	0.0	0.0
No log	38.0	266	3.0621	0.002	0.0084	0.0003	0.0005	0.002	0.0055	0.0002	0.003	0.0291	0.0024	0.0215	0.0992	0.004	0.0581	0.0	0.0
No log	39.0	273	2.9924	0.002	0.0084	0.0005	0.0001	0.0024	0.0049	0.0004	0.0035	0.0295	0.0024	0.0231	0.0909	0.004	0.0559	0.0001	0.0032
No log	40.0	280	3.0021	0.0021	0.0099	0.0004	0.0006	0.0021	0.0065	0.0001	0.0037	0.0326	0.0095	0.025	0.103	0.0041	0.0571	0.0001	0.0081

Framework versions

• Transformers 5.2.0
• Pytorch 2.10.0+cu128
• Datasets 4.6.1
• Tokenizers 0.22.2