vit-base-patch16-224-in21k-cards-june-06-cropping-filtered-test

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the None dataset. It achieves the following results on the evaluation set:

• eval_loss: 1.6758
• eval_accuracy: 0.3141
• eval_runtime: 71.2335
• eval_samples_per_second: 140.383
• eval_steps_per_second: 0.562
• epoch: 5.9981
• step: 779

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: 640
• eval_batch_size: 256
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 5120
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 10

Framework versions

• Transformers 4.41.2
• Pytorch 2.0.1+cu117
• Datasets 2.19.1
• Tokenizers 0.19.1