EElayoutlmv3_jordyvl_rvl_cdip_100_examples_per_class_2023-07-03_test

• Loss: 2.6984
• Accuracy: 0.13
• Exit 0 Accuracy: 0.0675
• Exit 1 Accuracy: 0.0725
• Exit 2 Accuracy: 0.1125
• Exit 3 Accuracy: 0.0625
• Exit 4 Accuracy: 0.0625

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

• learning_rate: 2e-05
• train_batch_size: 3
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 24
• total_train_batch_size: 72
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2

Training results

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1.post200
• Datasets 2.9.0
• Tokenizers 0.13.2