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: 0.0445
Accuracy: 0.9895

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: 64
eval_batch_size: 64
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 256
optimizer: Use 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_ratio: 0.1
num_epochs: 16

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6672	0.9950	100	0.4986	0.9233
0.3891	2.0	201	0.2037	0.9671
0.3164	2.9950	301	0.1414	0.9751
0.2884	4.0	402	0.1310	0.9699
0.2726	4.9950	502	0.1040	0.9748
0.2595	6.0	603	0.1150	0.9709
0.2662	6.9950	703	0.0842	0.9783
0.2195	8.0	804	0.0704	0.9842
0.2326	8.9950	904	0.0605	0.9842
0.2292	10.0	1005	0.0568	0.9846
0.2229	10.9950	1105	0.0445	0.9895
0.239	12.0	1206	0.0539	0.9839
0.2115	12.9950	1306	0.0464	0.9874
0.22	14.0	1407	0.0818	0.9734
0.2138	14.9950	1507	0.0599	0.9790
0.2003	15.9204	1600	0.0554	0.9821

Framework versions

Transformers 4.46.3
Pytorch 2.4.0
Datasets 3.1.0
Tokenizers 0.20.3

parasahuja23/vit-base-patch16-224-in21k-finetuned-final-2.0

vit-base-patch16-224-in21k-finetuned-final-2.0

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

parasahuja23/
vit-base-patch16-224-in21k-finetuned-final-2.0