resnet-50-finetuned-brain-tumor

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

• Loss: 0.2757
• Accuracy: 0.9171

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: 5e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 256
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Accuracy	Validation Loss
1.3264	1.0	30	0.5035	1.3154
1.222	2.0	60	0.6473	1.2254
1.0584	3.0	90	1.0668	0.7510
0.8977	4.0	120	0.9205	0.8060
0.724	5.0	150	0.7740	0.8456
0.6025	6.0	180	0.6009	0.8720
0.4953	7.0	210	0.5039	0.8684
0.4252	8.0	240	0.4158	0.8904
0.3677	9.0	270	0.3705	0.9038
0.3305	10.0	300	0.3300	0.9049
0.3113	11.0	330	0.3053	0.9097
0.2835	12.0	360	0.2885	0.9116
0.2614	13.0	390	0.2606	0.9297
0.2735	14.0	420	0.2767	0.9187
0.2573	15.0	450	0.2757	0.9171

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1+cu117
• Datasets 2.10.0
• Tokenizers 0.13.2