fusco_alzheimerMRI_model

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

• Loss: 0.0434
• Accuracy: 0.9902

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: 0.002
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• 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: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.8393	1.0	72	0.9099	0.5703
0.6828	2.0	144	0.7748	0.6914
0.5156	3.0	216	0.5721	0.7637
0.3141	4.0	288	0.2799	0.9082
0.2024	5.0	360	0.5322	0.8066
0.0934	6.0	432	0.6212	0.8555
0.0307	7.0	504	0.1234	0.9551
0.0383	8.0	576	0.1279	0.9570
0.0195	9.0	648	0.1022	0.9746
0.0102	10.0	720	0.1057	0.9629
0.0081	11.0	792	0.0785	0.9766
0.0009	12.0	864	0.0641	0.9805
0.0023	13.0	936	0.0612	0.9824
0.0089	14.0	1008	0.0571	0.9746
0.0008	15.0	1080	0.0437	0.9902
0.0014	16.0	1152	0.0375	0.9883
0.0002	17.0	1224	0.0485	0.9824
0.0002	18.0	1296	0.0450	0.9863
0.0002	19.0	1368	0.0451	0.9863
0.0002	20.0	1440	0.0434	0.9902

Framework versions

• Transformers 4.52.3
• Pytorch 2.7.0+cpu
• Datasets 3.6.0
• Tokenizers 0.21.1