learning_rate: 5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
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: linear
lr_scheduler_warmup_steps: 300
num_epochs: 80

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 Artemia	Mar 100 Artemia
No log	1.0	160	24.0289	0.0884	0.1741	0.0767	0.0821	0.1133	-1.0	0.2058	0.5072	0.6034	0.5213	0.7337	-1.0	0.0884	0.6034
No log	2.0	320	11.5203	0.1808	0.385	0.1454	0.1244	0.4417	-1.0	0.2391	0.558	0.613	0.5669	0.6862	-1.0	0.1808	0.613
No log	3.0	480	8.5257	0.3891	0.6711	0.4249	0.2988	0.5871	-1.0	0.3638	0.5976	0.6401	0.5874	0.7237	-1.0	0.3891	0.6401
158.8979	4.0	640	8.8219	0.3511	0.635	0.3479	0.2909	0.5292	-1.0	0.3246	0.5826	0.6222	0.5787	0.6913	-1.0	0.3511	0.6222
158.8979	5.0	800	8.6832	0.4606	0.8301	0.4341	0.3903	0.5839	-1.0	0.3729	0.5609	0.6116	0.5496	0.71	-1.0	0.4606	0.6116
158.8979	6.0	960	8.0822	0.4982	0.8625	0.5104	0.444	0.5998	-1.0	0.4	0.5821	0.599	0.5417	0.69	-1.0	0.4982	0.599
14.0017	7.0	1120	8.7836	0.4516	0.8016	0.4356	0.3825	0.5857	-1.0	0.3894	0.5763	0.5865	0.5386	0.6625	-1.0	0.4516	0.5865
14.0017	8.0	1280	8.3657	0.4543	0.8159	0.4521	0.3965	0.5685	-1.0	0.3845	0.5657	0.5696	0.5118	0.6612	-1.0	0.4543	0.5696
14.0017	9.0	1440	8.7325	0.4619	0.8152	0.4719	0.3938	0.5822	-1.0	0.3768	0.5575	0.5628	0.5031	0.6575	-1.0	0.4619	0.5628
12.0396	10.0	1600	8.6755	0.4745	0.8235	0.5199	0.4134	0.587	-1.0	0.3894	0.5667	0.585	0.5276	0.6762	-1.0	0.4745	0.585
12.0396	11.0	1760	8.6778	0.4514	0.8258	0.4078	0.3812	0.5718	-1.0	0.3821	0.5493	0.5594	0.4945	0.6625	-1.0	0.4514	0.5594
12.0396	12.0	1920	8.8920	0.4573	0.8242	0.4651	0.3822	0.5857	-1.0	0.3894	0.5633	0.5705	0.5165	0.6562	-1.0	0.4573	0.5705
10.6185	13.0	2080	8.7538	0.446	0.7948	0.4224	0.3749	0.5857	-1.0	0.371	0.558	0.5705	0.5008	0.6812	-1.0	0.446	0.5705
10.6185	14.0	2240	8.6437	0.4543	0.8154	0.4422	0.3893	0.5673	-1.0	0.3792	0.5502	0.5556	0.4898	0.66	-1.0	0.4543	0.5556
10.6185	15.0	2400	8.5215	0.4612	0.8334	0.4524	0.3996	0.5693	-1.0	0.385	0.5493	0.557	0.4945	0.6562	-1.0	0.4612	0.557
9.6088	16.0	2560	8.4067	0.4804	0.8435	0.502	0.4241	0.585	-1.0	0.3961	0.556	0.556	0.4961	0.6513	-1.0	0.4804	0.556
9.6088	17.0	2720	8.4700	0.471	0.8406	0.4689	0.4143	0.5697	-1.0	0.3884	0.5464	0.5464	0.4827	0.6475	-1.0	0.471	0.5464
9.6088	18.0	2880	8.9121	0.46	0.821	0.4205	0.3951	0.5738	-1.0	0.3783	0.5517	0.5517	0.4937	0.6438	-1.0	0.46	0.5517
8.8959	19.0	3040	8.9745	0.4683	0.8168	0.5016	0.3995	0.5984	-1.0	0.3845	0.5807	0.5865	0.5189	0.6938	-1.0	0.4683	0.5865
8.8959	20.0	3200	8.5419	0.4761	0.8432	0.4552	0.4119	0.5892	-1.0	0.3913	0.57	0.571	0.4929	0.695	-1.0	0.4761	0.571
8.8959	21.0	3360	8.5784	0.4552	0.8021	0.4838	0.384	0.5926	-1.0	0.3734	0.572	0.5729	0.5087	0.675	-1.0	0.4552	0.5729
8.569	22.0	3520	9.0100	0.4558	0.823	0.4653	0.3939	0.5826	-1.0	0.372	0.5473	0.5473	0.4811	0.6525	-1.0	0.4558	0.5473
8.569	23.0	3680	8.6153	0.4556	0.809	0.4686	0.3881	0.5724	-1.0	0.3812	0.5676	0.5681	0.5118	0.6575	-1.0	0.4556	0.5681
8.569	24.0	3840	8.8562	0.4532	0.8166	0.4448	0.3879	0.5724	-1.0	0.3763	0.53	0.53	0.4528	0.6525	-1.0	0.4532	0.53
8.1209	25.0	4000	8.7479	0.4696	0.8342	0.4716	0.4071	0.5836	-1.0	0.3865	0.5551	0.5551	0.4898	0.6587	-1.0	0.4696	0.5551
8.1209	26.0	4160	9.0480	0.4472	0.8012	0.4555	0.3763	0.5778	-1.0	0.3705	0.5478	0.5478	0.4827	0.6513	-1.0	0.4472	0.5478
8.1209	27.0	4320	8.7353	0.4587	0.8271	0.4356	0.3921	0.5825	-1.0	0.3778	0.5556	0.5556	0.485	0.6675	-1.0	0.4587	0.5556
8.1209	28.0	4480	8.6736	0.4694	0.8389	0.4555	0.4074	0.5834	-1.0	0.3807	0.5478	0.5478	0.4811	0.6538	-1.0	0.4694	0.5478
7.6312	29.0	4640	8.8275	0.4638	0.8347	0.4486	0.4045	0.576	-1.0	0.3763	0.5594	0.5594	0.4992	0.655	-1.0	0.4638	0.5594
7.6312	30.0	4800	8.8725	0.4511	0.8354	0.4502	0.3906	0.5691	-1.0	0.37	0.5531	0.5531	0.4874	0.6575	-1.0	0.4511	0.5531
7.6312	31.0	4960	8.7811	0.4542	0.8147	0.461	0.3895	0.5802	-1.0	0.3715	0.556	0.556	0.4929	0.6562	-1.0	0.4542	0.556
7.2229	32.0	5120	8.8270	0.4624	0.8231	0.4457	0.3952	0.5872	-1.0	0.3831	0.5638	0.5638	0.4969	0.67	-1.0	0.4624	0.5638
7.2229	33.0	5280	8.9066	0.4618	0.826	0.4573	0.3916	0.5908	-1.0	0.3797	0.5614	0.5614	0.4976	0.6625	-1.0	0.4618	0.5614
7.2229	34.0	5440	9.1949	0.4522	0.8226	0.4265	0.3867	0.5709	-1.0	0.3787	0.5556	0.5556	0.4906	0.6587	-1.0	0.4522	0.5556
6.8428	35.0	5600	8.9804	0.4611	0.8146	0.4712	0.3972	0.5832	-1.0	0.3792	0.542	0.542	0.4724	0.6525	-1.0	0.4611	0.542
6.8428	36.0	5760	9.4163	0.4458	0.8021	0.463	0.3724	0.5832	-1.0	0.3686	0.5502	0.5502	0.4795	0.6625	-1.0	0.4458	0.5502
6.8428	37.0	5920	9.4936	0.4508	0.8011	0.4446	0.3831	0.5843	-1.0	0.3739	0.5604	0.5604	0.4992	0.6575	-1.0	0.4508	0.5604
6.5378	38.0	6080	9.5459	0.4615	0.819	0.4549	0.3982	0.5853	-1.0	0.3797	0.557	0.557	0.4906	0.6625	-1.0	0.4615	0.557
6.5378	39.0	6240	9.5361	0.4622	0.8229	0.4648	0.3964	0.5968	-1.0	0.3792	0.5454	0.5454	0.4693	0.6662	-1.0	0.4622	0.5454
6.5378	40.0	6400	9.2237	0.4643	0.8289	0.4787	0.4076	0.5803	-1.0	0.3807	0.5609	0.5609	0.5031	0.6525	-1.0	0.4643	0.5609
6.365	41.0	6560	9.4217	0.4643	0.8318	0.4671	0.4059	0.5825	-1.0	0.3758	0.5599	0.5599	0.5	0.655	-1.0	0.4643	0.5599
6.365	42.0	6720	9.6089	0.4615	0.8168	0.4559	0.402	0.5797	-1.0	0.3739	0.5498	0.5498	0.489	0.6463	-1.0	0.4615	0.5498
6.365	43.0	6880	9.3128	0.4545	0.8148	0.4471	0.3916	0.5918	-1.0	0.3768	0.5556	0.5556	0.4866	0.665	-1.0	0.4545	0.5556
6.0415	44.0	7040	9.3568	0.4642	0.8289	0.4748	0.3997	0.5868	-1.0	0.3792	0.5473	0.5473	0.4764	0.66	-1.0	0.4642	0.5473
6.0415	45.0	7200	9.2827	0.4595	0.8195	0.439	0.4027	0.5809	-1.0	0.3845	0.558	0.558	0.4969	0.655	-1.0	0.4595	0.558
6.0415	46.0	7360	9.7081	0.4513	0.8116	0.4576	0.3852	0.5887	-1.0	0.3749	0.5522	0.5522	0.4858	0.6575	-1.0	0.4513	0.5522
5.8918	47.0	7520	10.0808	0.4437	0.791	0.4551	0.3803	0.5903	-1.0	0.3754	0.5614	0.5614	0.4992	0.66	-1.0	0.4437	0.5614
5.8918	48.0	7680	9.2187	0.4646	0.8256	0.4751	0.409	0.5804	-1.0	0.3831	0.556	0.556	0.4953	0.6525	-1.0	0.4646	0.556
5.8918	49.0	7840	9.4209	0.4473	0.8144	0.4194	0.3838	0.5809	-1.0	0.3739	0.5512	0.5512	0.4866	0.6538	-1.0	0.4473	0.5512
5.7175	50.0	8000	10.0629	0.4317	0.7705	0.4339	0.3547	0.5875	-1.0	0.3715	0.5604	0.5604	0.4984	0.6587	-1.0	0.4317	0.5604
5.7175	51.0	8160	9.7275	0.449	0.7957	0.4498	0.3833	0.5923	-1.0	0.3715	0.5599	0.5599	0.4937	0.665	-1.0	0.449	0.5599
5.7175	52.0	8320	9.6675	0.4261	0.7757	0.4011	0.3549	0.5866	-1.0	0.3667	0.5633	0.5633	0.4984	0.6662	-1.0	0.4261	0.5633
5.7175	53.0	8480	9.5460	0.4379	0.7975	0.4473	0.3717	0.588	-1.0	0.3807	0.5531	0.5531	0.485	0.6612	-1.0	0.4379	0.5531
5.4851	54.0	8640	9.7311	0.463	0.816	0.4599	0.4008	0.5935	-1.0	0.3812	0.5541	0.5541	0.4843	0.665	-1.0	0.463	0.5541
5.4851	55.0	8800	9.9874	0.4318	0.7785	0.4247	0.3687	0.5873	-1.0	0.3725	0.5589	0.5589	0.4953	0.66	-1.0	0.4318	0.5589
5.4851	56.0	8960	9.8335	0.4296	0.7752	0.426	0.364	0.5852	-1.0	0.37	0.5589	0.5589	0.4961	0.6587	-1.0	0.4296	0.5589
5.3402	57.0	9120	10.0254	0.4395	0.7916	0.4461	0.3711	0.5959	-1.0	0.3797	0.5618	0.5618	0.4937	0.67	-1.0	0.4395	0.5618
5.3402	58.0	9280	9.7425	0.4519	0.8065	0.46	0.3893	0.5854	-1.0	0.3845	0.558	0.558	0.4937	0.66	-1.0	0.4519	0.558
5.3402	59.0	9440	9.6929	0.4553	0.8097	0.4552	0.3892	0.5944	-1.0	0.3845	0.558	0.558	0.4898	0.6662	-1.0	0.4553	0.558
5.1557	60.0	9600	9.9021	0.4566	0.8121	0.4904	0.3898	0.5975	-1.0	0.3889	0.5589	0.5589	0.4906	0.6675	-1.0	0.4566	0.5589
5.1557	61.0	9760	9.8478	0.4578	0.8128	0.4765	0.393	0.5975	-1.0	0.3812	0.5614	0.5614	0.4953	0.6662	-1.0	0.4578	0.5614
5.1557	62.0	9920	10.1368	0.439	0.7829	0.4474	0.3672	0.5992	-1.0	0.3802	0.5609	0.5609	0.4929	0.6687	-1.0	0.439	0.5609
4.9831	63.0	10080	10.1771	0.4413	0.7802	0.4568	0.3746	0.5858	-1.0	0.3826	0.5647	0.5647	0.4984	0.67	-1.0	0.4413	0.5647
4.9831	64.0	10240	10.3118	0.4242	0.7605	0.44	0.3424	0.5908	-1.0	0.372	0.5643	0.5643	0.5016	0.6637	-1.0	0.4242	0.5643
4.9831	65.0	10400	10.2648	0.4393	0.7868	0.4403	0.3684	0.5912	-1.0	0.3884	0.5609	0.5609	0.4945	0.6662	-1.0	0.4393	0.5609
4.7725	66.0	10560	10.2136	0.4429	0.7883	0.4459	0.3716	0.594	-1.0	0.386	0.5589	0.5589	0.4906	0.6675	-1.0	0.4429	0.5589
4.7725	67.0	10720	10.4523	0.4304	0.7617	0.4316	0.3497	0.5963	-1.0	0.3744	0.5652	0.5652	0.4984	0.6712	-1.0	0.4304	0.5652
4.7725	68.0	10880	10.3906	0.4292	0.7678	0.427	0.3567	0.5817	-1.0	0.3783	0.5609	0.5609	0.4945	0.6662	-1.0	0.4292	0.5609
4.5934	69.0	11040	10.4266	0.4224	0.759	0.4355	0.3484	0.5915	-1.0	0.3773	0.5662	0.5662	0.5016	0.6687	-1.0	0.4224	0.5662
4.5934	70.0	11200	10.4166	0.4441	0.7779	0.4613	0.3699	0.602	-1.0	0.3836	0.5676	0.5676	0.5016	0.6725	-1.0	0.4441	0.5676
4.5934	71.0	11360	10.4787	0.4429	0.7849	0.4625	0.3713	0.5963	-1.0	0.3884	0.5618	0.5618	0.4937	0.67	-1.0	0.4429	0.5618
4.374	72.0	11520	10.6351	0.4288	0.7628	0.4484	0.3466	0.5928	-1.0	0.3768	0.5623	0.5623	0.4953	0.6687	-1.0	0.4288	0.5623
4.374	73.0	11680	10.6730	0.4408	0.7852	0.4572	0.3618	0.5957	-1.0	0.3816	0.5604	0.5604	0.4898	0.6725	-1.0	0.4408	0.5604
4.374	74.0	11840	10.6846	0.4326	0.7664	0.4459	0.3544	0.5941	-1.0	0.3749	0.5618	0.5618	0.4969	0.665	-1.0	0.4326	0.5618
4.2986	75.0	12000	10.7497	0.4315	0.7747	0.4467	0.3548	0.5879	-1.0	0.3768	0.5565	0.5565	0.4882	0.665	-1.0	0.4315	0.5565
4.2986	76.0	12160	10.7465	0.4284	0.7639	0.4401	0.3574	0.587	-1.0	0.3783	0.5614	0.5614	0.4945	0.6675	-1.0	0.4284	0.5614
4.2986	77.0	12320	10.9365	0.4245	0.7622	0.4477	0.3477	0.5919	-1.0	0.3797	0.5594	0.5594	0.4921	0.6662	-1.0	0.4245	0.5594
4.2986	78.0	12480	10.8859	0.4289	0.7624	0.4376	0.3524	0.5959	-1.0	0.3792	0.5628	0.5628	0.4969	0.6675	-1.0	0.4289	0.5628
4.1529	79.0	12640	10.8838	0.4281	0.7636	0.4425	0.3531	0.5884	-1.0	0.3768	0.5594	0.5594	0.4937	0.6637	-1.0	0.4281	0.5594
4.1529	80.0	12800	10.8640	0.4293	0.7679	0.4426	0.3554	0.5925	-1.0	0.3778	0.5609	0.5609	0.4937	0.6675	-1.0	0.4293	0.5609

Framework versions

Transformers 4.57.1
Pytorch 2.8.0+cu128
Datasets 4.2.0
Tokenizers 0.22.1

dariacuna/rtdetr-v2-r50-finetune-11

rtdetr-v2-r50-finetune-11

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

dariacuna/
rtdetr-v2-r50-finetune-11