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: 0.2177
Accuracy: 0.9194

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	0.9032	7	0.6456	0.7742
0.6684	1.9355	15	0.4995	0.8629
0.4818	2.9677	23	0.3788	0.8629
0.3026	4.0	31	0.2881	0.9113
0.3026	4.9032	38	0.2530	0.9032
0.1806	5.9355	46	0.2359	0.9194
0.1161	6.9677	54	0.2288	0.9194
0.0894	8.0	62	0.2043	0.9435
0.0894	8.9032	69	0.2042	0.9355
0.0723	9.0323	70	0.2177	0.9194

Framework versions

Transformers 4.44.2
Pytorch 2.5.0+cu121
Datasets 3.1.0
Tokenizers 0.19.1

soplac/stripes

stripes

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

soplac/
stripes