<!-- 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_v4.2
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: 0.0247
- Precision: 0.8814
- Recall: 0.8595
- F1: 0.8703
- Accuracy: 0.9956
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: 1500
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 0.84 | 100 | 0.1047 | 0.4194 | 0.2149 | 0.2842 | 0.9764 |
No log | 1.68 | 200 | 0.0555 | 0.5441 | 0.6116 | 0.5759 | 0.9843 |
No log | 2.52 | 300 | 0.0445 | 0.5899 | 0.6777 | 0.6308 | 0.9879 |
No log | 3.36 | 400 | 0.0288 | 0.7402 | 0.7769 | 0.7581 | 0.9929 |
0.0777 | 4.2 | 500 | 0.0292 | 0.8033 | 0.8099 | 0.8066 | 0.9938 |
0.0777 | 5.04 | 600 | 0.0172 | 0.8321 | 0.9008 | 0.8651 | 0.9962 |
0.0777 | 5.88 | 700 | 0.0321 | 0.8067 | 0.7934 | 0.8 | 0.9932 |
0.0777 | 6.72 | 800 | 0.0165 | 0.8862 | 0.9008 | 0.8934 | 0.9967 |
0.0777 | 7.56 | 900 | 0.0318 | 0.8644 | 0.8430 | 0.8536 | 0.9953 |
0.0093 | 8.4 | 1000 | 0.0247 | 0.8814 | 0.8595 | 0.8703 | 0.9956 |
0.0093 | 9.24 | 1100 | 0.0220 | 0.8678 | 0.8678 | 0.8678 | 0.9962 |
0.0093 | 10.08 | 1200 | 0.0183 | 0.8607 | 0.8678 | 0.8642 | 0.9965 |
0.0093 | 10.92 | 1300 | 0.0269 | 0.8739 | 0.8595 | 0.8667 | 0.9959 |
0.0093 | 11.76 | 1400 | 0.0171 | 0.8387 | 0.8595 | 0.8490 | 0.9965 |
0.0035 | 12.61 | 1500 | 0.0201 | 0.8607 | 0.8678 | 0.8642 | 0.9965 |
Framework versions
- Transformers 4.28.0.dev0
- Pytorch 2.0.0+cu118
- Datasets 2.2.2
- Tokenizers 0.13.3