You can deploy this model and start earning money today!

selmamalak/
deit-base-patch16-224-bloodmnist-fold-8

Name: deit-base-patch16-224-bloodmnist-fold-8
Availability: InStock

peft

safetensors

generated_from_trainer

medmnist-v2

facebook/deit-base-patch16-224

adapter

apache-2.0

Views

No views yet

deit-base-patch16-224-bloodmnist-fold-8

This model is a fine-tuned version of facebook/deit-base-patch16-224 on the medmnist-v2 dataset. It achieves the following results on the evaluation set:

Loss: 0.0881
Accuracy: 0.9710
Precision: 0.9698
Recall: 0.9699
F1: 0.9696

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: 0.005
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 64
optimizer: Use OptimizerNames.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: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.5665	1.0	196	0.3301	0.8824	0.8975	0.8670	0.8714
0.4673	2.0	392	0.1627	0.9543	0.9481	0.9526	0.9503
0.3211	3.0	588	0.1627	0.9421	0.9345	0.9362	0.9347
0.3377	4.0	784	0.2708	0.9096	0.9312	0.8939	0.9044
0.3133	5.0	980	0.2002	0.9377	0.9347	0.9398	0.9360
0.2457	6.0	1176	0.1659	0.9464	0.9426	0.9415	0.9403
0.2564	7.0	1372	0.1354	0.9570	0.9599	0.9478	0.9520
0.1807	8.0	1568	0.1057	0.9579	0.9543	0.9559	0.9545
0.1779	9.0	1764	0.0983	0.9693	0.9680	0.9694	0.9687
0.136	10.0	1960	0.0881	0.9710	0.9698	0.9699	0.9696

Framework versions

PEFT 0.15.2
Transformers 4.52.4
Pytorch 2.6.0+cu124
Datasets 3.6.0
Tokenizers 0.21.2

selmamalak/deit-base-patch16-224-bloodmnist-fold-8

deit-base-patch16-224-bloodmnist-fold-8

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

selmamalak/
deit-base-patch16-224-bloodmnist-fold-8