<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
layoutlmv3-finetuned-cord_100
This model is a fine-tuned version of microsoft/layoutlmv3-base on the cord-layoutlmv3 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3992
- Precision: 0.8480
- Recall: 0.8937
- F1: 0.8703
- Accuracy: 0.9032
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: 1e-05
- train_batch_size: 5
- eval_batch_size: 5
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 2500
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.56 | 250 | 1.3625 | 0.5799 | 0.7006 | 0.6346 | 0.7148 |
| 1.4671 | 3.12 | 500 | 0.8263 | 0.7349 | 0.8114 | 0.7713 | 0.8192 |
| 1.4671 | 4.69 | 750 | 0.7066 | 0.7168 | 0.7957 | 0.7542 | 0.8315 |
| 0.4607 | 6.25 | 1000 | 0.5309 | 0.7899 | 0.8555 | 0.8214 | 0.8769 |
| 0.4607 | 7.81 | 1250 | 0.4772 | 0.8126 | 0.8668 | 0.8388 | 0.8841 |
| 0.2521 | 9.38 | 1500 | 0.4509 | 0.8270 | 0.8728 | 0.8492 | 0.8884 |
| 0.2521 | 10.94 | 1750 | 0.4169 | 0.8460 | 0.8885 | 0.8667 | 0.9011 |
| 0.169 | 12.5 | 2000 | 0.4078 | 0.8458 | 0.8907 | 0.8677 | 0.9028 |
| 0.169 | 14.06 | 2250 | 0.4024 | 0.8519 | 0.8952 | 0.8730 | 0.9024 |
| 0.1338 | 15.62 | 2500 | 0.3992 | 0.8480 | 0.8937 | 0.8703 | 0.9032 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.0
- Tokenizers 0.13.3
