urinary_carcinoma_classifier_g004

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: 0.5556
• Accuracy: 0.7778

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: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.8	1	0.6989	0.6111
No log	1.6	2	0.6758	0.6111
No log	2.4	3	0.6409	0.6667
No log	4.0	5	0.6102	0.7222
No log	4.8	6	0.6065	0.7778
No log	5.6	7	0.6030	0.7778
No log	6.4	8	0.6254	0.5556
0.6126	8.0	10	0.5948	0.7222
0.6126	8.8	11	0.5967	0.6667
0.6126	9.6	12	0.5784	0.7778
0.6126	10.4	13	0.5751	0.6667
0.6126	12.0	15	0.5556	0.7778

Framework versions

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