layoutlmv3-final-v1-BIE
This model is a fine-tuned version of microsoft/layoutlmv3-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1338
- Precision: 0.9595
- Recall: 0.9730
- F1: 0.9662
- Accuracy: 0.9749
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: 8
- 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
- training_steps: 1000
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 2.56 | 100 | 2.1535 | 0.4538 | 0.5846 | 0.5109 | 0.5773 |
No log | 5.13 | 200 | 0.7537 | 0.7399 | 0.8398 | 0.7867 | 0.8664 |
No log | 7.69 | 300 | 0.4054 | 0.8173 | 0.8869 | 0.8507 | 0.9217 |
No log | 10.26 | 400 | 0.2619 | 0.9045 | 0.9389 | 0.9214 | 0.9570 |
1.1788 | 12.82 | 500 | 0.2051 | 0.9440 | 0.9610 | 0.9524 | 0.9683 |
1.1788 | 15.38 | 600 | 0.1780 | 0.9467 | 0.9610 | 0.9538 | 0.9688 |
1.1788 | 17.95 | 700 | 0.1569 | 0.9546 | 0.9690 | 0.9617 | 0.9729 |
1.1788 | 20.51 | 800 | 0.1417 | 0.9508 | 0.9670 | 0.9588 | 0.9724 |
1.1788 | 23.08 | 900 | 0.1339 | 0.9585 | 0.9720 | 0.9652 | 0.9759 |
0.1352 | 25.64 | 1000 | 0.1338 | 0.9595 | 0.9730 | 0.9662 | 0.9749 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 1.8.0+cu101
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 3
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.