<!-- 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. -->
LOC1.0
This model is a fine-tuned version of microsoft/layoutlmv3-base on the sroie dataset. It achieves the following results on the evaluation set:
- Loss: 0.3003
- Precision: 0.6609
- Recall: 0.7170
- F1: 0.6878
- Accuracy: 0.9565
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: 2000
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 3.7 | 100 | 0.3041 | 0.7009 | 0.7075 | 0.7042 | 0.9585 |
No log | 7.41 | 200 | 0.3411 | 0.5682 | 0.7075 | 0.6303 | 0.9406 |
No log | 11.11 | 300 | 0.1978 | 0.664 | 0.7830 | 0.7186 | 0.9606 |
No log | 14.81 | 400 | 0.2985 | 0.6667 | 0.7170 | 0.6909 | 0.9585 |
0.0194 | 18.52 | 500 | 0.2931 | 0.6239 | 0.6415 | 0.6326 | 0.9575 |
0.0194 | 22.22 | 600 | 0.2981 | 0.6697 | 0.6887 | 0.6791 | 0.9544 |
0.0194 | 25.93 | 700 | 0.3242 | 0.6757 | 0.7075 | 0.6912 | 0.9565 |
0.0194 | 29.63 | 800 | 0.2913 | 0.7255 | 0.6981 | 0.7115 | 0.9565 |
0.0194 | 33.33 | 900 | 0.2944 | 0.592 | 0.6981 | 0.6407 | 0.9503 |
0.012 | 37.04 | 1000 | 0.2923 | 0.7404 | 0.7264 | 0.7333 | 0.9549 |
0.012 | 40.74 | 1100 | 0.3083 | 0.7451 | 0.7170 | 0.7308 | 0.9539 |
0.012 | 44.44 | 1200 | 0.3142 | 0.6667 | 0.7170 | 0.6909 | 0.9513 |
0.012 | 48.15 | 1300 | 0.2950 | 0.6909 | 0.7170 | 0.7037 | 0.9539 |
0.012 | 51.85 | 1400 | 0.2958 | 0.6852 | 0.6981 | 0.6916 | 0.9534 |
0.0105 | 55.56 | 1500 | 0.2882 | 0.7 | 0.7264 | 0.7130 | 0.9590 |
0.0105 | 59.26 | 1600 | 0.2954 | 0.7476 | 0.7264 | 0.7368 | 0.9600 |
0.0105 | 62.96 | 1700 | 0.2975 | 0.6696 | 0.7264 | 0.6968 | 0.9580 |
0.0105 | 66.67 | 1800 | 0.2986 | 0.6522 | 0.7075 | 0.6787 | 0.9565 |
0.0105 | 70.37 | 1900 | 0.3011 | 0.6609 | 0.7170 | 0.6878 | 0.9565 |
0.0081 | 74.07 | 2000 | 0.3003 | 0.6609 | 0.7170 | 0.6878 | 0.9565 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.2.2
- Tokenizers 0.13.3