metadata
license: cc-by-nc-sa-4.0
base_model: microsoft/layoutlmv2-large-uncased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: layoutlmv2-finetuned-cord
results: []
layoutlmv2-finetuned-cord
This model is a fine-tuned version of microsoft/layoutlmv2-large-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4287
- Precision: 0.5421
- Recall: 0.4754
- F1: 0.5066
- Accuracy: 0.9272
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: 2
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 135 | 0.3706 | 0.4855 | 0.4816 | 0.4835 | 0.9190 |
| No log | 2.0 | 270 | 0.3198 | 0.5887 | 0.5102 | 0.5467 | 0.9308 |
| No log | 3.0 | 405 | 0.3602 | 0.5237 | 0.4529 | 0.4857 | 0.9238 |
| 0.323 | 4.0 | 540 | 0.3866 | 0.5251 | 0.4508 | 0.4851 | 0.9250 |
| 0.323 | 5.0 | 675 | 0.4287 | 0.5421 | 0.4754 | 0.5066 | 0.9272 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1