model-v2-2024-05-07
This model is a fine-tuned version of microsoft/layoutlmv3-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8052
- Precision: 0.6764
- Recall: 0.6050
- F1: 0.6387
- Accuracy: 0.8195
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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 1000
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 0.9 | 100 | 1.3581 | 0.3509 | 0.0474 | 0.0836 | 0.6756 |
No log | 1.8 | 200 | 1.0434 | 0.5730 | 0.4235 | 0.4870 | 0.7685 |
No log | 2.7 | 300 | 0.8190 | 0.6662 | 0.5777 | 0.6188 | 0.8112 |
No log | 3.6 | 400 | 0.7884 | 0.6662 | 0.5753 | 0.6174 | 0.8108 |
0.962 | 4.5 | 500 | 0.7199 | 0.6835 | 0.6251 | 0.6530 | 0.8250 |
0.962 | 5.41 | 600 | 0.7505 | 0.6807 | 0.6145 | 0.6459 | 0.8235 |
0.962 | 6.31 | 700 | 0.7669 | 0.6641 | 0.6168 | 0.6396 | 0.8188 |
0.962 | 7.21 | 800 | 0.7707 | 0.6747 | 0.6002 | 0.6353 | 0.8188 |
0.962 | 8.11 | 900 | 0.7751 | 0.6765 | 0.6251 | 0.6498 | 0.8235 |
0.3828 | 9.01 | 1000 | 0.8052 | 0.6764 | 0.6050 | 0.6387 | 0.8195 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.13.3
- Downloads last month
- 2
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.