vit-base-patch16-224-in21k-cards-june-07-cropping-filtered-preprocess-change-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: 1.4854
- eval_accuracy: 0.4582
- eval_runtime: 82.8936
- eval_samples_per_second: 120.637
- eval_steps_per_second: 0.483
- epoch: 12.9981
- step: 1682
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: 15
Framework versions
- Transformers 4.41.2
- Pytorch 2.0.1+cu117
- Datasets 2.19.1
- Tokenizers 0.19.1