docintel-classifier

This model is a fine-tuned version of microsoft/layoutlmv3-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.6040
• Accuracy: 0.785
• F1: 0.7830
• Acc Letter: 0.6
• Acc Form: 0.6
• Acc Email: 0.96
• Acc Handwr: 0.96
• Acc Advert: 0.84
• Acc Scient: 0.76
• Acc Specif: 0.92
• Acc File f: 1.0
• Acc News a: 0.72
• Acc Budget: 0.6
• Acc Invoic: 0.84
• Acc Presen: 0.72
• Acc Questi: 0.68
• Acc Resume: 0.96
• Acc Memo: 0.8

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 0.1
• num_epochs: 8
• mixed_precision_training: Native AMP

Training results

Framework versions

• Transformers 5.0.0
• Pytorch 2.10.0+cu128
• Datasets 4.8.5
• Tokenizers 0.22.2