cdetr-mist1-brain-gt-tumors-8ah-6l

This model is a fine-tuned version of microsoft/conditional-detr-resnet-50 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.7389

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: 1e-05
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 100
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
5.4149	1.0	115	4.3974
3.9453	2.0	230	3.6520
3.7269	3.0	345	3.7602
3.5898	4.0	460	3.5671
3.486	5.0	575	3.4912
3.4073	6.0	690	3.4095
3.4181	7.0	805	3.3183
3.3603	8.0	920	3.1111
3.2777	9.0	1035	3.1992
3.2851	10.0	1150	3.3997
3.266	11.0	1265	3.2861
3.2803	12.0	1380	3.1813
3.1733	13.0	1495	2.9838
3.2094	14.0	1610	3.1175
3.1718	15.0	1725	3.0064
3.1303	16.0	1840	3.0869
3.0897	17.0	1955	3.0306
3.0233	18.0	2070	2.9479
3.0156	19.0	2185	2.9145
3.0277	20.0	2300	2.8919
3.0847	21.0	2415	2.9321
3.0333	22.0	2530	2.9128
3.0126	23.0	2645	2.8627
2.9968	24.0	2760	3.0186
3.0295	25.0	2875	3.0148
3.0294	26.0	2990	3.0341
3.0395	27.0	3105	2.9997
3.0445	28.0	3220	3.0575
2.9761	29.0	3335	2.9707
3.0075	30.0	3450	2.9392
3.0198	31.0	3565	2.9122
2.9782	32.0	3680	2.9471
2.9773	33.0	3795	3.0306
2.9528	34.0	3910	2.8513
2.9228	35.0	4025	2.8997
2.9221	36.0	4140	2.8646
2.8933	37.0	4255	2.8871
2.8925	38.0	4370	2.9407
2.9069	39.0	4485	2.9625
2.9246	40.0	4600	2.9946
2.9089	41.0	4715	2.8936
2.8573	42.0	4830	2.8272
2.8768	43.0	4945	2.9868
2.9666	44.0	5060	2.9200
2.958	45.0	5175	2.8755
2.8923	46.0	5290	2.8518
2.9204	47.0	5405	2.9000
2.9644	48.0	5520	2.8969
2.9011	49.0	5635	2.7918
2.9329	50.0	5750	2.9139
2.9031	51.0	5865	2.7796
2.9029	52.0	5980	2.8025
2.9555	53.0	6095	2.9121
2.9366	54.0	6210	2.9035
2.8871	55.0	6325	2.8759
2.863	56.0	6440	2.8540
2.8897	57.0	6555	2.8401
2.828	58.0	6670	2.8590
2.8221	59.0	6785	2.9255
2.835	60.0	6900	2.9809
2.886	61.0	7015	2.9907
2.8227	62.0	7130	2.8283
2.7864	63.0	7245	2.8258
2.8179	64.0	7360	2.9504
2.7944	65.0	7475	2.8042
2.7986	66.0	7590	2.8307
2.7567	67.0	7705	2.8060
2.7552	68.0	7820	2.7994
2.7933	69.0	7935	2.8493
2.7393	70.0	8050	2.8409
2.7357	71.0	8165	2.8086
2.7264	72.0	8280	2.7773
2.7614	73.0	8395	2.8937
2.7279	74.0	8510	2.8887
2.745	75.0	8625	2.8274
2.7225	76.0	8740	2.7971
2.7094	77.0	8855	2.8685
2.7306	78.0	8970	2.8482
2.6844	79.0	9085	2.7372
2.6949	80.0	9200	2.8149
2.7342	81.0	9315	2.7647
2.6813	82.0	9430	2.7666
2.7161	83.0	9545	2.8437
2.6953	84.0	9660	2.7895
2.6714	85.0	9775	2.7683
2.6611	86.0	9890	2.7004
2.6714	87.0	10005	2.7183
2.6655	88.0	10120	2.7043
2.6509	89.0	10235	2.7705
2.6266	90.0	10350	2.7152
2.6677	91.0	10465	2.7295
2.6438	92.0	10580	2.7018
2.6267	93.0	10695	2.7063
2.6286	94.0	10810	2.7798
2.6043	95.0	10925	2.7712
2.6188	96.0	11040	2.7614
2.6028	97.0	11155	2.7405
2.621	98.0	11270	2.7415
2.61	99.0	11385	2.7415
2.6164	100.0	11500	2.7389

Framework versions

• Transformers 4.35.0
• Pytorch 2.0.0
• Datasets 2.1.0
• Tokenizers 0.14.1