EElayoutlmv3_rvl-cdip_single_10_2023-05-16_withoutdoublesavecheck
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: 2.4923
- Accuracy: 0.2812
- Exit 0 Accuracy: 0.0938
- Exit 1 Accuracy: 0.1187
- Exit 2 Accuracy: 0.225
- Exit 3 Accuracy: 0.0938
- Exit 4 Accuracy: 0.075
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: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Exit 0 Accuracy | Exit 1 Accuracy | Exit 2 Accuracy | Exit 3 Accuracy | Exit 4 Accuracy |
|---|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 160 | 2.7258 | 0.1187 | 0.0625 | 0.0813 | 0.1062 | 0.0625 | 0.0625 |
| No log | 2.0 | 320 | 2.5812 | 0.2062 | 0.0875 | 0.1313 | 0.2062 | 0.125 | 0.0688 |
| No log | 3.0 | 480 | 2.4923 | 0.2812 | 0.0938 | 0.1187 | 0.225 | 0.0938 | 0.075 |
Framework versions
- Transformers 4.28.0.dev0
- Pytorch 1.12.1+cu113
- Datasets 2.12.0
- Tokenizers 0.12.1