amyeroberts/vit-base-beans

THIS IS A TEST REPO FOR DEBUGGING!

This repo is here as a result of playing with and debugging training scripts and push to hub features. As such, the TesnorFlow and PyTorch models will be out of sync and different weights may be push at any time, including pushing models with very low performance.

vit-base-beans

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: 0.0630
• Accuracy: 0.9850

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: 2e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 1337
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3038	1.0	130	0.2396	0.9624
0.1609	2.0	260	0.1130	0.9774
0.2313	3.0	390	0.0809	0.9850
0.1436	4.0	520	0.0738	0.9850
0.1086	5.0	650	0.0630	0.9850

Framework versions

• Transformers 4.27.0.dev0
• Pytorch 1.14.0.dev20221118
• Datasets 2.9.1.dev0
• Tokenizers 0.13.2