<!-- 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_manifesti_v3.6
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: 0.0893
- Precision: 0.9019
- Recall: 0.9223
- F1: 0.9120
- Accuracy: 0.9869
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 | 1.41 | 100 | 0.1184 | 0.8411 | 0.8920 | 0.8658 | 0.9817 |
No log | 2.82 | 200 | 0.0671 | 0.8821 | 0.9072 | 0.8945 | 0.9840 |
No log | 4.23 | 300 | 0.0739 | 0.8919 | 0.9223 | 0.9069 | 0.9863 |
No log | 5.63 | 400 | 0.0534 | 0.9270 | 0.9621 | 0.9442 | 0.9909 |
0.1242 | 7.04 | 500 | 0.0917 | 0.8947 | 0.9015 | 0.8981 | 0.9856 |
0.1242 | 8.45 | 600 | 0.0773 | 0.9065 | 0.9186 | 0.9125 | 0.9873 |
0.1242 | 9.86 | 700 | 0.0836 | 0.8950 | 0.9205 | 0.9076 | 0.9863 |
0.1242 | 11.27 | 800 | 0.0803 | 0.9112 | 0.9129 | 0.9120 | 0.9873 |
0.1242 | 12.68 | 900 | 0.0914 | 0.8953 | 0.9072 | 0.9012 | 0.9860 |
0.0099 | 14.08 | 1000 | 0.0687 | 0.9069 | 0.9223 | 0.9146 | 0.9873 |
0.0099 | 15.49 | 1100 | 0.0889 | 0.9035 | 0.9223 | 0.9128 | 0.9873 |
0.0099 | 16.9 | 1200 | 0.0924 | 0.8980 | 0.9167 | 0.9072 | 0.9866 |
0.0099 | 18.31 | 1300 | 0.0858 | 0.9052 | 0.9223 | 0.9137 | 0.9873 |
0.0099 | 19.72 | 1400 | 0.0893 | 0.9019 | 0.9223 | 0.9120 | 0.9869 |
0.0043 | 21.13 | 1500 | 0.0893 | 0.9019 | 0.9223 | 0.9120 | 0.9869 |
Framework versions
- Transformers 4.28.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.2.2
- Tokenizers 0.13.2