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

Loss: 0.8384
Accuracy: 0.75

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	1	1.1029	0.125
No log	2.0	2	1.0384	0.625
No log	3.0	3	0.9989	0.75
No log	4.0	4	0.9557	0.75
No log	5.0	5	0.8941	0.75
No log	6.0	6	0.8952	0.75
No log	7.0	7	0.8669	0.75
No log	8.0	8	0.8705	0.75
No log	9.0	9	0.8357	0.75
0.4538	10.0	10	0.8384	0.75

Framework versions

Transformers 4.44.2
Pytorch 2.5.0+cu121
Datasets 3.1.0
Tokenizers 0.19.1

soplac/test2

test2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

soplac/
test2