vit-base-beans

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the fcakyon/pokemon-classification dataset. It achieves the following results on the evaluation set:

• Loss: 5.5730
• Accuracy: 0.0129

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: 0.0002
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
3.7644	0.3279	100	5.5730	0.0129
2.3105	0.6557	200	5.7311	0.0129
1.3142	0.9836	300	5.9778	0.0151
0.562	1.3115	400	6.3239	0.0446
0.3257	1.6393	500	6.4495	0.0813
0.1451	1.9672	600	6.6065	0.0791
0.0887	2.2951	700	6.7952	0.0813
0.0867	2.6230	800	6.9210	0.0770
0.0628	2.9508	900	6.9864	0.0849
0.047	3.2787	1000	7.0419	0.0827
0.0454	3.6066	1100	7.0862	0.0856
0.0408	3.9344	1200	7.1030	0.0856

Framework versions

• Transformers 4.42.0.dev0
• Pytorch 2.1.0+cu118
• Datasets 2.19.2
• Tokenizers 0.19.1