nttwt1597/ViT_Blood_test_ckpt_3582

test-cifar-10

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.9675
• Accuracy: 0.1471

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: 2e-05
• train_batch_size: 10
• eval_batch_size: 4
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 12

Training results

Training Loss	Epoch	Step	Accuracy	Validation Loss
No log	1.0	398	0.1078	2.4878
2.6367	2.0	796	0.1225	2.2750
2.0748	3.0	1194	0.1471	2.1435
1.9035	4.0	1592	0.1225	2.0770
1.9035	5.0	1990	0.1422	2.0976
1.8217	6.0	2388	0.1618	1.9768
1.7998	7.0	2786	2.0803	0.1275
1.7268	8.0	3184	1.9141	0.1569
1.6826	9.0	3582	1.7059	0.2010
1.6826	10.0	3980	2.0650	0.1127
1.6642	11.0	4378	1.9643	0.1520
1.6267	12.0	4776	1.9675	0.1471

Framework versions

• Transformers 4.46.3
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3