<!-- 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. -->
allways_pharma_v2.0
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: 0.2375
- Precision: 0.8776
- Recall: 0.86
- F1: 0.8687
- Accuracy: 0.9756
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: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 8.33 | 100 | 0.1635 | 0.8542 | 0.82 | 0.8367 | 0.9695 |
| No log | 16.67 | 200 | 0.1860 | 0.8776 | 0.86 | 0.8687 | 0.9756 |
| No log | 25.0 | 300 | 0.2545 | 0.86 | 0.86 | 0.8600 | 0.9695 |
| No log | 33.33 | 400 | 0.2707 | 0.8542 | 0.82 | 0.8367 | 0.9695 |
| 0.1 | 41.67 | 500 | 0.2618 | 0.8542 | 0.82 | 0.8367 | 0.9695 |
| 0.1 | 50.0 | 600 | 0.2784 | 0.8542 | 0.82 | 0.8367 | 0.9695 |
| 0.1 | 58.33 | 700 | 0.2679 | 0.8542 | 0.82 | 0.8367 | 0.9695 |
| 0.1 | 66.67 | 800 | 0.2405 | 0.8542 | 0.82 | 0.8367 | 0.9695 |
| 0.1 | 75.0 | 900 | 0.2372 | 0.8776 | 0.86 | 0.8687 | 0.9756 |
| 0.0012 | 83.33 | 1000 | 0.2375 | 0.8776 | 0.86 | 0.8687 | 0.9756 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.2.2
- Tokenizers 0.13.2
