Output_LayoutLMv3_v7
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: 0.1075
- Precision: 0.7928
- Recall: 0.8
- F1: 0.7964
- Accuracy: 0.9723
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-06
- train_batch_size: 12
- eval_batch_size: 12
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 2600
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 9.09 | 100 | 0.4138 | 0.0 | 0.0 | 0.0 | 0.8962 |
No log | 18.18 | 200 | 0.2709 | 0.1667 | 0.0273 | 0.0469 | 0.9014 |
No log | 27.27 | 300 | 0.2003 | 0.6234 | 0.4364 | 0.5134 | 0.9360 |
No log | 36.36 | 400 | 0.1711 | 0.6496 | 0.6909 | 0.6696 | 0.9481 |
0.3384 | 45.45 | 500 | 0.1624 | 0.6667 | 0.7273 | 0.6957 | 0.9498 |
0.3384 | 54.55 | 600 | 0.1502 | 0.6803 | 0.7545 | 0.7155 | 0.9550 |
0.3384 | 63.64 | 700 | 0.1428 | 0.7227 | 0.7818 | 0.7511 | 0.9602 |
0.3384 | 72.73 | 800 | 0.1452 | 0.7049 | 0.7818 | 0.7414 | 0.9550 |
0.3384 | 81.82 | 900 | 0.1260 | 0.7544 | 0.7818 | 0.7679 | 0.9671 |
0.0995 | 90.91 | 1000 | 0.1254 | 0.7544 | 0.7818 | 0.7679 | 0.9671 |
0.0995 | 100.0 | 1100 | 0.1211 | 0.7863 | 0.8364 | 0.8106 | 0.9706 |
0.0995 | 109.09 | 1200 | 0.1093 | 0.7739 | 0.8091 | 0.7911 | 0.9706 |
0.0995 | 118.18 | 1300 | 0.1081 | 0.7946 | 0.8091 | 0.8018 | 0.9723 |
0.0995 | 127.27 | 1400 | 0.1108 | 0.7778 | 0.8273 | 0.8018 | 0.9723 |
0.0608 | 136.36 | 1500 | 0.1115 | 0.7627 | 0.8182 | 0.7895 | 0.9706 |
0.0608 | 145.45 | 1600 | 0.1034 | 0.8053 | 0.8273 | 0.8161 | 0.9740 |
0.0608 | 154.55 | 1700 | 0.1050 | 0.7895 | 0.8182 | 0.8036 | 0.9723 |
0.0608 | 163.64 | 1800 | 0.1093 | 0.7739 | 0.8091 | 0.7911 | 0.9706 |
0.0608 | 172.73 | 1900 | 0.1043 | 0.7965 | 0.8182 | 0.8072 | 0.9723 |
0.0443 | 181.82 | 2000 | 0.1048 | 0.8036 | 0.8182 | 0.8108 | 0.9758 |
0.0443 | 190.91 | 2100 | 0.1067 | 0.8036 | 0.8182 | 0.8108 | 0.9758 |
0.0443 | 200.0 | 2200 | 0.1069 | 0.8036 | 0.8182 | 0.8108 | 0.9740 |
0.0443 | 209.09 | 2300 | 0.1083 | 0.7928 | 0.8 | 0.7964 | 0.9723 |
0.0443 | 218.18 | 2400 | 0.1079 | 0.7928 | 0.8 | 0.7964 | 0.9723 |
0.0381 | 227.27 | 2500 | 0.1076 | 0.7928 | 0.8 | 0.7964 | 0.9723 |
0.0381 | 236.36 | 2600 | 0.1075 | 0.7928 | 0.8 | 0.7964 | 0.9723 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.13.3
- Downloads last month
- 17
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.