resnet-pretrained-brain-mri

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

• Loss: 1.1450
• Accuracy: 0.5228

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: 0.0003
• train_batch_size: 32
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Accuracy	Validation Loss
No log	1.0	72	0.4704	1.2440
1.2771	2.0	144	0.5575	1.1610
1.1543	3.0	216	0.6446	1.0949
1.1543	4.0	288	0.6812	1.0361
1.0664	5.0	360	0.6742	1.0100
0.9998	6.0	432	0.7003	0.9687
0.9537	7.0	504	0.6986	0.9484
0.9537	8.0	576	0.6934	0.9285
0.9239	9.0	648	0.7108	0.8992
0.893	10.0	720	0.7369	0.8723
0.893	11.0	792	0.7334	0.8635
0.8726	12.0	864	0.7474	0.8589
0.8482	13.0	936	0.7160	0.8423
0.8461	14.0	1008	0.7300	0.8481
0.8461	15.0	1080	0.7352	0.8312
0.8267	16.0	1152	0.7247	0.8319
0.8163	17.0	1224	0.7456	0.8136
0.8163	18.0	1296	0.7474	0.8151
0.8126	19.0	1368	0.7596	0.8071
0.8022	20.0	1440	0.7491	0.8210

Framework versions

• Transformers 4.44.2
• Pytorch 2.3.0+cu121
• Tokenizers 0.19.1