EElayoutlmv3_jordyvl_rvl_cdip_easyocr_2023-07-09_weighted
This model is a fine-tuned version of microsoft/layoutlmv3-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2223
- Accuracy: 0.9400
- Exit 0 Accuracy: 0.2580
- Exit 1 Accuracy: 0.5214
- Exit 2 Accuracy: 0.7781
- Exit 3 Accuracy: 0.8564
- Exit 4 Accuracy: 0.9330
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: 2e-05
- train_batch_size: 6
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 24
- total_train_batch_size: 144
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Exit 0 Accuracy | Exit 1 Accuracy | Exit 2 Accuracy | Exit 3 Accuracy | Exit 4 Accuracy |
|---|---|---|---|---|---|---|---|---|---|
| 2.4115 | 1.0 | 2222 | 0.2907 | 0.9172 | 0.209 | 0.3731 | 0.645 | 0.7651 | 0.9109 |
| 2.0272 | 2.0 | 4444 | 0.2444 | 0.9310 | 0.2243 | 0.4579 | 0.7297 | 0.8172 | 0.9234 |
| 1.8196 | 3.0 | 6666 | 0.2268 | 0.9350 | 0.2383 | 0.4979 | 0.7589 | 0.8439 | 0.9285 |
| 1.7287 | 4.0 | 8888 | 0.2216 | 0.9387 | 0.2438 | 0.5163 | 0.7728 | 0.8533 | 0.9315 |
| 1.6664 | 5.0 | 11110 | 0.2223 | 0.9400 | 0.2580 | 0.5214 | 0.7781 | 0.8564 | 0.9330 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1.post200
- Datasets 2.9.0
- Tokenizers 0.13.2