mask2former-finetuned-ER-Mito-LD3

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: 39.9236
• 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: 0.0004
• train_batch_size: 4
• eval_batch_size: 4
• 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
57.794	1.0	129	47.5030	1.0
45.635	2.0	258	42.4622	1.0
43.6742	3.0	387	40.1383	1.0
37.5286	4.0	516	41.1964	1.0
33.7618	5.0	645	34.4374	1.0
31.5899	6.0	774	39.8242	1.0
29.0727	7.0	903	33.3223	1.0
27.8483	8.0	1032	30.9625	1.0
26.0904	9.0	1161	31.7084	1.0
26.1043	10.0	1290	31.8088	1.0
24.3038	11.0	1419	30.3361	1.0
23.6493	12.0	1548	30.2030	1.0
23.9146	13.0	1677	31.0806	1.0
21.9133	14.0	1806	31.3974	1.0
22.3071	15.0	1935	32.0925	1.0
21.0819	16.0	2064	29.9367	1.0
21.0089	17.0	2193	30.0420	1.0
20.9169	18.0	2322	29.2938	1.0
19.7935	19.0	2451	31.3945	1.0
19.8749	20.0	2580	29.8457	1.0
19.2973	21.0	2709	29.0713	1.0
18.5436	22.0	2838	29.0846	1.0
18.5996	23.0	2967	29.8810	1.0
19.1228	24.0	3096	29.3016	1.0
18.0519	25.0	3225	30.7155	1.0
17.7073	26.0	3354	28.7168	1.0
17.5055	27.0	3483	28.9899	1.0
17.4854	28.0	3612	30.1944	1.0
17.0048	29.0	3741	29.2829	1.0
16.8731	30.0	3870	30.1208	1.0
16.683	31.0	3999	30.7583	1.0
16.6109	32.0	4128	30.6232	1.0
15.8261	33.0	4257	29.4162	1.0
16.9002	34.0	4386	30.4388	1.0
16.3081	35.0	4515	29.9756	1.0
15.4745	36.0	4644	28.8214	1.0
15.938	37.0	4773	29.1001	1.0
15.9947	38.0	4902	31.0533	1.0
15.2328	39.0	5031	31.6211	1.0
15.202	40.0	5160	33.1383	1.0
15.0583	41.0	5289	31.4089	1.0
14.573	42.0	5418	31.5681	1.0
14.7401	43.0	5547	30.5548	1.0
14.6052	44.0	5676	31.3953	1.0
14.1299	45.0	5805	30.8153	1.0
13.6851	46.0	5934	30.9693	1.0
14.6677	47.0	6063	31.9361	1.0
13.6493	48.0	6192	34.3328	1.0
14.166	49.0	6321	32.6231	1.0
13.7388	50.0	6450	33.1736	1.0
13.0849	51.0	6579	34.9522	1.0
13.2502	52.0	6708	35.7990	1.0
13.5116	53.0	6837	31.5737	1.0
12.6993	54.0	6966	33.2650	1.0
13.3602	55.0	7095	34.8914	1.0
12.9585	56.0	7224	35.9862	1.0
12.7434	57.0	7353	34.9106	1.0
12.7299	58.0	7482	34.0106	1.0
12.717	59.0	7611	36.3588	1.0
12.0563	60.0	7740	35.0923	1.0
13.012	61.0	7869	38.7323	1.0
12.2878	62.0	7998	34.9967	1.0
12.2794	63.0	8127	37.5577	1.0
12.4147	64.0	8256	37.2733	1.0
12.0032	65.0	8385	35.3015	1.0
12.2793	66.0	8514	35.2806	1.0
12.2309	67.0	8643	36.2488	1.0
11.7082	68.0	8772	35.6687	1.0
11.8694	69.0	8901	36.0470	1.0
11.782	70.0	9030	35.4055	1.0
11.6254	71.0	9159	36.7066	1.0
11.5873	72.0	9288	36.1084	1.0
11.6251	73.0	9417	38.2932	1.0
11.4589	74.0	9546	36.5570	1.0
11.7378	75.0	9675	35.9887	1.0
11.4933	76.0	9804	36.4713	1.0
11.2566	77.0	9933	36.9622	1.0
11.25	78.0	10062	37.1016	1.0
11.2962	79.0	10191	37.8711	1.0
11.0868	80.0	10320	38.5714	1.0
11.2786	81.0	10449	38.1493	1.0
11.1528	82.0	10578	39.0100	1.0
11.089	83.0	10707	38.5474	1.0
10.954	84.0	10836	38.9405	1.0
11.0157	85.0	10965	39.3872	1.0
10.9849	86.0	11094	39.4875	1.0
10.5423	87.0	11223	39.1179	1.0
11.1968	88.0	11352	39.4084	1.0
10.6376	89.0	11481	39.8218	1.0
10.7131	90.0	11610	39.2553	1.0
10.8252	91.0	11739	39.1368	1.0
10.6456	92.0	11868	38.9194	1.0
10.8488	93.0	11997	39.5955	1.0
10.8675	94.0	12126	39.4760	1.0
10.4757	95.0	12255	40.4844	1.0
10.3191	96.0	12384	39.0673	1.0
10.6073	97.0	12513	39.3767	1.0
10.3038	98.0	12642	39.6969	1.0
11.0709	99.0	12771	39.9325	1.0
10.5951	100.0	12900	39.8755	1.0

Framework versions

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