urinary_carcinoma_classifier_g001

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.3828
• Accuracy: 0.8571

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: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	1	0.6854	0.7143
No log	2.0	2	0.6759	0.5714
No log	3.0	3	0.6738	0.5714
No log	4.0	4	0.6571	0.5714
No log	5.0	5	0.6342	0.5714
No log	6.0	6	0.6339	0.5714
No log	7.0	7	0.5402	0.5714
No log	8.0	8	0.5827	0.5714
No log	9.0	9	0.5439	0.7143
0.2718	10.0	10	0.5553	0.7143
0.2718	11.0	11	0.4241	1.0
0.2718	12.0	12	0.5177	0.8571
0.2718	13.0	13	0.4088	0.8571
0.2718	14.0	14	0.4763	0.7143
0.2718	15.0	15	0.3164	1.0
0.2718	16.0	16	0.3087	1.0
0.2718	17.0	17	0.3457	0.8571
0.2718	18.0	18	0.2585	1.0
0.2718	19.0	19	0.3642	0.8571
0.1299	20.0	20	0.4421	0.7143
0.1299	21.0	21	0.3558	0.8571
0.1299	22.0	22	0.3611	0.8571
0.1299	23.0	23	0.5796	0.7143
0.1299	24.0	24	0.4137	0.8571
0.1299	25.0	25	0.4281	0.8571
0.1299	26.0	26	0.2066	1.0
0.1299	27.0	27	0.2251	1.0
0.1299	28.0	28	0.2459	1.0
0.1299	29.0	29	0.4450	0.8571
0.0743	30.0	30	0.3828	0.8571

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1
• Datasets 2.20.0
• Tokenizers 0.19.1