mask2former-finetuned-ER-Mito-LD

This model is a fine-tuned version of facebook/mask2former-swin-base-IN21k-ade-semantic on the Dnq2025/Mask2former_Pretrain dataset. It achieves the following results on the evaluation set:

• Loss: 34.0481
• Dummy: 1.0

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: 6
• eval_batch_size: 6
• seed: 1337
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: polynomial
• training_steps: 12900

Training results

Training Loss	Epoch	Step	Validation Loss	Dummy
No log	1.0	86	34.1100	1.0
43.7572	2.0	172	30.1643	1.0
32.0025	3.0	258	28.1818	1.0
26.8817	4.0	344	27.1780	1.0
24.1857	5.0	430	26.5827	1.0
22.9335	6.0	516	25.7310	1.0
21.3521	7.0	602	25.2442	1.0
21.3521	8.0	688	25.0511	1.0
20.4144	9.0	774	25.3838	1.0
18.8722	10.0	860	25.7261	1.0
18.576	11.0	946	25.0048	1.0
18.1119	12.0	1032	25.3630	1.0
17.8769	13.0	1118	25.2566	1.0
17.0204	14.0	1204	25.6023	1.0
17.0204	15.0	1290	26.3285	1.0
16.3528	16.0	1376	26.3254	1.0
16.5548	17.0	1462	26.9244	1.0
16.6848	18.0	1548	27.6294	1.0
15.4544	19.0	1634	25.7570	1.0
15.7209	20.0	1720	25.7097	1.0
15.3127	21.0	1806	27.2604	1.0
15.3127	22.0	1892	26.4286	1.0
14.9528	23.0	1978	27.5768	1.0
15.1795	24.0	2064	26.4714	1.0
14.707	25.0	2150	28.0977	1.0
14.3456	26.0	2236	26.7914	1.0
14.4534	27.0	2322	27.4079	1.0
14.4448	28.0	2408	26.8291	1.0
14.4448	29.0	2494	27.1506	1.0
14.0327	30.0	2580	27.1973	1.0
13.8785	31.0	2666	27.5062	1.0
14.3373	32.0	2752	27.9510	1.0
13.3176	33.0	2838	27.1878	1.0
13.8154	34.0	2924	25.5759	1.0
13.8962	35.0	3010	27.7627	1.0
13.8962	36.0	3096	28.8061	1.0
13.3858	37.0	3182	28.4328	1.0
12.9659	38.0	3268	27.5515	1.0
13.6813	39.0	3354	27.8206	1.0
13.3049	40.0	3440	28.6062	1.0
13.1584	41.0	3526	28.5364	1.0
12.9234	42.0	3612	29.3165	1.0
12.9234	43.0	3698	28.5156	1.0
13.1375	44.0	3784	28.2476	1.0
12.7875	45.0	3870	29.9959	1.0
12.6507	46.0	3956	28.5480	1.0
13.0131	47.0	4042	29.1117	1.0
12.3806	48.0	4128	31.2153	1.0
12.9016	49.0	4214	28.9405	1.0
12.274	50.0	4300	28.7396	1.0
12.274	51.0	4386	30.3948	1.0
12.5767	52.0	4472	29.3863	1.0
12.5965	53.0	4558	29.4516	1.0
11.9685	54.0	4644	27.2974	1.0
12.3025	55.0	4730	27.0013	1.0
12.4256	56.0	4816	27.2713	1.0
12.2008	57.0	4902	27.4054	1.0
12.2008	58.0	4988	27.9546	1.0
12.1018	59.0	5074	28.9453	1.0
12.2156	60.0	5160	29.3121	1.0
11.9526	61.0	5246	30.1903	1.0
12.1103	62.0	5332	28.8276	1.0
11.8017	63.0	5418	28.7898	1.0
11.9907	64.0	5504	28.6167	1.0
11.9907	65.0	5590	29.2822	1.0
11.6683	66.0	5676	31.4695	1.0
12.1544	67.0	5762	27.7773	1.0
11.7442	68.0	5848	29.5376	1.0
11.1493	69.0	5934	27.8916	1.0
12.0781	70.0	6020	28.4096	1.0
11.8055	71.0	6106	29.2272	1.0
11.8055	72.0	6192	29.2769	1.0
11.4811	73.0	6278	29.2552	1.0
11.5947	74.0	6364	29.2611	1.0
11.7263	75.0	6450	30.7953	1.0
11.7399	76.0	6536	30.0692	1.0
11.0851	77.0	6622	29.6803	1.0
11.5118	78.0	6708	30.7345	1.0
11.5118	79.0	6794	31.5980	1.0
11.516	80.0	6880	30.5279	1.0
11.3797	81.0	6966	30.2265	1.0
11.3335	82.0	7052	30.3816	1.0
11.2303	83.0	7138	29.3238	1.0
11.1964	84.0	7224	30.3987	1.0
11.321	85.0	7310	30.1935	1.0
11.321	86.0	7396	29.1421	1.0
11.3891	87.0	7482	31.2074	1.0
11.1347	88.0	7568	30.6735	1.0
11.1945	89.0	7654	31.2053	1.0
10.9891	90.0	7740	31.4373	1.0
11.104	91.0	7826	31.3946	1.0
11.1408	92.0	7912	31.2186	1.0
11.1408	93.0	7998	29.5871	1.0
11.0779	94.0	8084	30.4671	1.0
11.0551	95.0	8170	32.0130	1.0
10.8809	96.0	8256	30.4459	1.0
11.1123	97.0	8342	30.8415	1.0
10.7116	98.0	8428	31.0445	1.0
11.0086	99.0	8514	31.0471	1.0
11.0542	100.0	8600	31.0217	1.0
11.0542	101.0	8686	31.7885	1.0
10.8332	102.0	8772	30.6191	1.0
10.8696	103.0	8858	31.2075	1.0
10.6959	104.0	8944	32.0795	1.0
11.0688	105.0	9030	33.7820	1.0
10.6762	106.0	9116	31.9403	1.0
10.8607	107.0	9202	33.1345	1.0
10.8607	108.0	9288	31.0811	1.0
10.7504	109.0	9374	31.0663	1.0
10.7841	110.0	9460	30.0841	1.0
10.5677	111.0	9546	30.8185	1.0
11.0266	112.0	9632	32.1549	1.0
10.5912	113.0	9718	32.2208	1.0
10.6698	114.0	9804	31.5337	1.0
10.6698	115.0	9890	32.2273	1.0
10.6857	116.0	9976	31.8648	1.0
10.5977	117.0	10062	31.8058	1.0
10.6883	118.0	10148	31.7254	1.0
10.3506	119.0	10234	33.0298	1.0
10.9217	120.0	10320	33.3403	1.0
10.5332	121.0	10406	32.5384	1.0
10.5332	122.0	10492	32.2192	1.0
10.4658	123.0	10578	32.8913	1.0
10.4877	124.0	10664	33.1068	1.0
10.7404	125.0	10750	34.1187	1.0
10.2195	126.0	10836	32.4418	1.0
10.7622	127.0	10922	32.2935	1.0
10.4301	128.0	11008	33.2411	1.0
10.4301	129.0	11094	32.3692	1.0
10.6464	130.0	11180	32.6297	1.0
10.4213	131.0	11266	33.7513	1.0
10.382	132.0	11352	32.6382	1.0
10.6049	133.0	11438	33.2621	1.0
10.3039	134.0	11524	32.9468	1.0
10.3088	135.0	11610	33.4821	1.0
10.3088	136.0	11696	33.4824	1.0
10.4832	137.0	11782	32.9320	1.0
10.4149	138.0	11868	33.8853	1.0
10.2473	139.0	11954	33.5977	1.0
10.7137	140.0	12040	34.1817	1.0
10.2686	141.0	12126	34.0892	1.0
10.2581	142.0	12212	34.1113	1.0
10.2581	143.0	12298	33.9106	1.0
10.447	144.0	12384	33.3470	1.0
10.3823	145.0	12470	33.3055	1.0
10.1283	146.0	12556	33.6762	1.0
10.5364	147.0	12642	33.9977	1.0
10.1257	148.0	12728	34.0327	1.0
10.3092	149.0	12814	34.1170	1.0
10.4947	150.0	12900	33.8776	1.0

Framework versions

• Transformers 4.50.0.dev0
• Pytorch 2.4.1
• Datasets 3.3.2
• Tokenizers 0.21.0