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

Loss: 0.4114
F1: 0.7857

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: 1e-05
train_batch_size: 8
eval_batch_size: 8
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: linear
lr_scheduler_warmup_steps: 100
num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	F1
0.6912	0.2703	10	0.7520	0.125
0.6629	0.5405	20	0.7228	0.1333
0.6437	0.8108	30	0.6779	0.1429
0.6342	1.0811	40	0.6240	0.25
0.4349	1.3514	50	0.5809	0.4211
0.4226	1.6216	60	0.5349	0.5714
0.39	1.8919	70	0.4766	0.6957
0.2352	2.1622	80	0.4342	0.75
0.1292	2.4324	90	0.4085	0.6957
0.2239	2.7027	100	0.4385	0.7407
0.1512	2.9730	110	0.4366	0.7857
0.0491	3.2432	120	0.3861	0.75
0.018	3.5135	130	0.3774	0.8462
0.0151	3.7838	140	0.3935	0.8462

Framework versions

Transformers 4.48.3
Pytorch 2.5.1+cu124
Datasets 3.3.2
Tokenizers 0.21.0

olenabugaiova/vit-large-patch16-224-innmarksbeite

vit-large-patch16-224-innmarksbeite

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

olenabugaiova/
vit-large-patch16-224-innmarksbeite