You can deploy this model and start earning money today!

mluger/
LinearHeadDropout

transformers

safetensors

generated_from_trainer

imagefolder

google/vit-base-patch16-224-in21k

finetune

apache-2.0

endpoints_compatible

Views

No views yet

LinearHeadDropout

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: 0.8840
Accuracy: 0.6780

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: 3e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
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: cosine
lr_scheduler_warmup_steps: 200
num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.529	0.2972	200	1.5736	0.4703
1.263	0.5944	400	1.3058	0.5407
1.1958	0.8915	600	1.1821	0.5917
1.0997	1.1887	800	1.0876	0.6154
1.098	1.4859	1000	1.0784	0.6172
1.0514	1.7831	1200	1.0475	0.6177
0.9697	2.0802	1400	1.0143	0.6376
0.9485	2.3774	1600	0.9993	0.6395
0.9591	2.6746	1800	0.9805	0.6410
0.9263	2.9718	2000	0.9533	0.6507
0.8639	3.2689	2200	0.9659	0.6467
0.8583	3.5661	2400	0.9330	0.6577
0.8396	3.8633	2600	0.9164	0.6661
0.8212	4.1605	2800	0.9262	0.6580
0.8013	4.4577	3000	0.9154	0.6598
0.7974	4.7548	3200	0.9053	0.6687
0.7712	5.0520	3400	0.9110	0.6638
0.732	5.3492	3600	0.9021	0.6707
0.7642	5.6464	3800	0.8897	0.6715
0.7447	5.9435	4000	0.8902	0.6723
0.7446	6.2407	4200	0.8892	0.6754
0.7337	6.5379	4400	0.8886	0.6736
0.7277	6.8351	4600	0.8850	0.6746
0.6591	7.1322	4800	0.8845	0.6767
0.6763	7.4294	5000	0.8841	0.6758
0.7166	7.7266	5200	0.8840	0.6780

Framework versions

Transformers 4.51.1
Pytorch 2.6.0+cu124
Datasets 3.5.0
Tokenizers 0.21.1

mluger/LinearHeadDropout

LinearHeadDropout

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

mluger/
LinearHeadDropout