metadata
license: cc-by-nc-sa-4.0
base_model: microsoft/layoutlmv3-base
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: fine-tuned-rvl-cdip
results: []
fine-tuned-rvl-cdip
This model is a fine-tuned version of microsoft/layoutlmv3-base on the https://www.kaggle.com/datasets/hajdudavid/rvl-dcip-sample dataset. It achieves the following results on the evaluation set:
- Loss: 0.9012
- F1: 0.7708
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| No log | 1.0 | 96 | 2.0898 | 0.4661 |
| No log | 2.0 | 192 | 1.2981 | 0.6510 |
| No log | 3.0 | 288 | 1.0922 | 0.7161 |
| No log | 4.0 | 384 | 0.9723 | 0.7474 |
| No log | 5.0 | 480 | 0.9012 | 0.7708 |
Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.19.1