<!-- 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. -->
perioli_vgm_v4.4
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: 0.0314
- Precision: 0.9085
- Recall: 0.9021
- F1: 0.9053
- Accuracy: 0.9968
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: 1200
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 0.81 | 100 | 0.0901 | 0.5385 | 0.2937 | 0.3801 | 0.9800 |
No log | 1.63 | 200 | 0.0517 | 0.6879 | 0.6783 | 0.6831 | 0.9896 |
No log | 2.44 | 300 | 0.0479 | 0.8169 | 0.8112 | 0.8140 | 0.9938 |
No log | 3.25 | 400 | 0.0354 | 0.8219 | 0.8392 | 0.8304 | 0.9951 |
0.0712 | 4.07 | 500 | 0.0278 | 0.84 | 0.8811 | 0.8601 | 0.9951 |
0.0712 | 4.88 | 600 | 0.0326 | 0.8299 | 0.8531 | 0.8414 | 0.9953 |
0.0712 | 5.69 | 700 | 0.0323 | 0.8493 | 0.8671 | 0.8581 | 0.9955 |
0.0712 | 6.5 | 800 | 0.0264 | 0.8819 | 0.8881 | 0.8850 | 0.9960 |
0.0712 | 7.32 | 900 | 0.0297 | 0.9085 | 0.9021 | 0.9053 | 0.9968 |
0.0085 | 8.13 | 1000 | 0.0335 | 0.8873 | 0.8811 | 0.8842 | 0.9965 |
0.0085 | 8.94 | 1100 | 0.0319 | 0.9014 | 0.8951 | 0.8982 | 0.9965 |
0.0085 | 9.76 | 1200 | 0.0314 | 0.9085 | 0.9021 | 0.9053 | 0.9968 |
Framework versions
- Transformers 4.28.0.dev0
- Pytorch 2.0.0+cu118
- Datasets 2.2.2
- Tokenizers 0.13.3