<!-- 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_v3.0
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: 0.2426
- Precision: 0.8710
- Recall: 0.8710
- F1: 0.8710
- Accuracy: 0.9508
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 | 5.56 | 100 | 0.2242 | 0.7576 | 0.8065 | 0.7812 | 0.9180 |
| No log | 11.11 | 200 | 0.1528 | 0.9333 | 0.9032 | 0.9180 | 0.9672 |
| No log | 16.67 | 300 | 0.3891 | 0.8438 | 0.8710 | 0.8571 | 0.9016 |
| No log | 22.22 | 400 | 0.2012 | 0.9333 | 0.9032 | 0.9180 | 0.9672 |
| 0.109 | 27.78 | 500 | 0.2054 | 0.9333 | 0.9032 | 0.9180 | 0.9672 |
| 0.109 | 33.33 | 600 | 0.3423 | 0.8710 | 0.8710 | 0.8710 | 0.9508 |
| 0.109 | 38.89 | 700 | 0.2207 | 0.8710 | 0.8710 | 0.8710 | 0.9508 |
| 0.109 | 44.44 | 800 | 0.2205 | 0.9333 | 0.9032 | 0.9180 | 0.9672 |
| 0.109 | 50.0 | 900 | 0.2204 | 0.9333 | 0.9032 | 0.9180 | 0.9672 |
| 0.0056 | 55.56 | 1000 | 0.2426 | 0.8710 | 0.8710 | 0.8710 | 0.9508 |
Framework versions
- Transformers 4.28.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.2.2
- Tokenizers 0.13.2
