detr-resnet50-leuk

This model is a fine-tuned version of facebook/detr-resnet-50 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.6961

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 40

Training results

Training Loss	Epoch	Step	Validation Loss
3.1222	1.0	121	2.3225
2.7011	2.0	242	2.0470
2.7217	3.0	363	2.1209
2.5204	4.0	484	2.0189
2.4531	5.0	605	1.9293
2.5448	6.0	726	2.1573
2.5266	7.0	847	1.9387
2.385	8.0	968	1.9430
2.3655	9.0	1089	1.9070
2.384	10.0	1210	1.8772
2.4173	11.0	1331	1.9408
2.4512	12.0	1452	1.9038
2.4599	13.0	1573	2.0496
2.382	14.0	1694	1.9044
2.3739	15.0	1815	1.8649
2.3066	16.0	1936	1.8339
2.2597	17.0	2057	1.7873
2.2254	18.0	2178	1.8041
2.2674	19.0	2299	1.7946
2.2109	20.0	2420	1.7831
2.2812	21.0	2541	1.8024
2.2648	22.0	2662	1.7854
2.2161	23.0	2783	1.7622
2.209	24.0	2904	1.7544
2.1905	25.0	3025	1.7473
2.2166	26.0	3146	1.7674
2.2108	27.0	3267	1.7445
2.1813	28.0	3388	1.7329
2.1679	29.0	3509	1.7286
2.1481	30.0	3630	1.7254
2.1713	31.0	3751	1.7368
2.1471	32.0	3872	1.7362
2.1537	33.0	3993	1.7281
2.1347	34.0	4114	1.7205
2.129	35.0	4235	1.7109
2.1215	36.0	4356	1.7227
2.1425	37.0	4477	1.7109
2.1106	38.0	4598	1.6993
2.0987	39.0	4719	1.6982
2.1259	40.0	4840	1.6961

Framework versions

• Transformers 4.28.1
• Pytorch 2.0.0+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3