ryan_model314_3

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

• Loss: 0.2750
• Na Accuracy: 0.931
• Ordinal Accuracy: 0.6271
• Ordinal Mae: 0.5319

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: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Na Accuracy	Ordinal Accuracy	Ordinal Mae
0.4423	0.08	50	0.3386	0.904	0.4629	0.6578
0.3088	0.16	100	0.3269	0.928	0.5371	0.5969
0.316	0.24	150	0.3396	0.902	0.5143	0.6323
0.2821	0.32	200	0.3234	0.927	0.5131	0.6293
0.2731	0.4	250	0.3314	0.925	0.5086	0.5856
0.2975	0.48	300	0.3037	0.927	0.5964	0.5690
0.2609	0.56	350	0.3209	0.928	0.5450	0.5765
0.287	0.64	400	0.2908	0.931	0.5827	0.5458
0.2905	0.72	450	0.3007	0.919	0.5986	0.5484
0.2574	0.8	500	0.2834	0.929	0.6032	0.5363
0.2855	0.88	550	0.2750	0.931	0.6271	0.5319

Framework versions

• Transformers 4.39.1
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2