<!-- 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. -->
layoutlmv3-finetuned-cord_100
This model is a fine-tuned version of microsoft/layoutlmv3-base on the cord-layoutlmv3 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3467
- Precision: 0.9244
- Recall: 0.9334
- F1: 0.9289
- Accuracy: 0.9363
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: 5
- eval_batch_size: 5
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 2500
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 4.17 | 250 | 0.5174 | 0.8469 | 0.8735 | 0.8600 | 0.8790 |
| 0.5511 | 8.33 | 500 | 0.3975 | 0.8999 | 0.9147 | 0.9072 | 0.9194 |
| 0.5511 | 12.5 | 750 | 0.3872 | 0.9015 | 0.9184 | 0.9099 | 0.9189 |
| 0.1802 | 16.67 | 1000 | 0.3416 | 0.9180 | 0.9296 | 0.9238 | 0.9338 |
| 0.1802 | 20.83 | 1250 | 0.3311 | 0.9159 | 0.9289 | 0.9223 | 0.9359 |
| 0.0836 | 25.0 | 1500 | 0.3457 | 0.9192 | 0.9281 | 0.9236 | 0.9334 |
| 0.0836 | 29.17 | 1750 | 0.3347 | 0.9202 | 0.9319 | 0.9260 | 0.9291 |
| 0.0473 | 33.33 | 2000 | 0.3677 | 0.9194 | 0.9304 | 0.9249 | 0.9253 |
| 0.0473 | 37.5 | 2250 | 0.3433 | 0.9279 | 0.9341 | 0.9310 | 0.9376 |
| 0.0342 | 41.67 | 2500 | 0.3467 | 0.9244 | 0.9334 | 0.9289 | 0.9363 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
