pokemon-vit

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

• Loss: 1.3224
• Accuracy: 0.4737

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: 0.0003
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	10	1.7717	0.3684
No log	2.0	20	1.5295	0.4211
No log	3.0	30	1.3983	0.4211
No log	4.0	40	1.3240	0.5263
No log	5.0	50	1.2977	0.6316

Framework versions

• Transformers 5.5.3
• Pytorch 2.10.0+cpu
• Datasets 4.8.4
• Tokenizers 0.22.2