urinary_carcinoma_classifier_g002

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: 0.3544
• Accuracy: 0.9231

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	0.6814	0.5385
No log	2.0	2	0.6743	0.6923
No log	3.0	3	0.6449	0.7692
No log	4.0	4	0.6149	0.7692
No log	5.0	5	0.5980	0.7692
No log	6.0	6	0.5855	0.7692
No log	7.0	7	0.5663	0.7692
No log	8.0	8	0.5675	0.7692
No log	9.0	9	0.5530	0.7692
0.637	10.0	10	0.5246	0.8462
0.637	11.0	11	0.5135	0.7692
0.637	12.0	12	0.5296	0.8462
0.637	13.0	13	0.5340	0.8462
0.637	14.0	14	0.4781	0.9231
0.637	15.0	15	0.4870	0.8462
0.637	16.0	16	0.4701	0.8462
0.637	17.0	17	0.4521	1.0
0.637	18.0	18	0.4266	0.9231
0.637	19.0	19	0.4220	0.9231
0.4474	20.0	20	0.3837	0.9231
0.4474	21.0	21	0.4257	0.8462
0.4474	22.0	22	0.4093	0.9231
0.4474	23.0	23	0.4019	1.0
0.4474	24.0	24	0.4578	0.8462
0.4474	25.0	25	0.3932	1.0
0.4474	26.0	26	0.3838	1.0
0.4474	27.0	27	0.3627	1.0
0.4474	28.0	28	0.3862	0.9231
0.4474	29.0	29	0.3624	0.9231
0.3102	30.0	30	0.3544	0.9231

Framework versions

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