layoutlmv3-funsd-finetuned
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: 0.6391
- Precision: 0.8943
- Recall: 0.9121
- F1: 0.9031
- Accuracy: 0.8540
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 | 1.3333 | 100 | 0.6387 | 0.7375 | 0.8306 | 0.7813 | 0.7786 |
No log | 2.6667 | 200 | 0.5473 | 0.8270 | 0.8718 | 0.8489 | 0.8184 |
No log | 4.0 | 300 | 0.5020 | 0.8514 | 0.8877 | 0.8692 | 0.8278 |
No log | 5.3333 | 400 | 0.5326 | 0.8610 | 0.9016 | 0.8809 | 0.8293 |
0.5379 | 6.6667 | 500 | 0.5600 | 0.8656 | 0.8987 | 0.8818 | 0.8451 |
0.5379 | 8.0 | 600 | 0.5903 | 0.8778 | 0.8917 | 0.8847 | 0.8357 |
0.5379 | 9.3333 | 700 | 0.6079 | 0.8859 | 0.9026 | 0.8942 | 0.8470 |
0.5379 | 10.6667 | 800 | 0.6449 | 0.8978 | 0.9076 | 0.9027 | 0.8458 |
0.5379 | 12.0 | 900 | 0.6410 | 0.8934 | 0.9116 | 0.9024 | 0.8582 |
0.1248 | 13.3333 | 1000 | 0.6391 | 0.8943 | 0.9121 | 0.9031 | 0.8540 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 1