metadata
license: cc-by-nc-sa-4.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: EElayoutlmv3_jordyvl_rvl_cdip_easyocr_2023-07-23_g025
results: []
EElayoutlmv3_jordyvl_rvl_cdip_easyocr_2023-07-23_g025
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: 0.2244
- Accuracy: 0.9394
- Exit 0 Accuracy: 0.2721
- Exit 1 Accuracy: 0.4875
- Exit 2 Accuracy: 0.8051
- Exit 3 Accuracy: 0.8840
- Exit 4 Accuracy: 0.9339
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.5909 | 1.0 | 2222 | 0.2945 | 0.9158 | 0.2021 | 0.3569 | 0.7091 | 0.8143 | 0.9092 |
| 0.4951 | 2.0 | 4444 | 0.2469 | 0.9292 | 0.2262 | 0.4336 | 0.7677 | 0.8614 | 0.9258 |
| 0.4279 | 3.0 | 6666 | 0.2281 | 0.9336 | 0.2530 | 0.4682 | 0.7898 | 0.8768 | 0.9302 |
| 0.39 | 4.0 | 8888 | 0.2241 | 0.9385 | 0.2600 | 0.483 | 0.8008 | 0.8827 | 0.9328 |
| 0.3602 | 5.0 | 11110 | 0.2244 | 0.9394 | 0.2721 | 0.4875 | 0.8051 | 0.8840 | 0.9339 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1.post200
- Datasets 2.9.0
- Tokenizers 0.13.2