<!-- 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. -->
rhenus_v2.0_cleared
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: 0.2695
- Precision: 0.9566
- Recall: 0.9566
- F1: 0.9566
- Accuracy: 0.9556
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: 3000
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 0.91 | 100 | 2.3292 | 0.2072 | 0.1074 | 0.1415 | 0.3949 |
No log | 1.82 | 200 | 1.5407 | 0.6009 | 0.5475 | 0.5730 | 0.6939 |
No log | 2.73 | 300 | 0.9994 | 0.7174 | 0.6715 | 0.6937 | 0.8084 |
No log | 3.64 | 400 | 0.7563 | 0.7692 | 0.7645 | 0.7668 | 0.8435 |
1.6153 | 4.55 | 500 | 0.5786 | 0.8071 | 0.8037 | 0.8054 | 0.8692 |
1.6153 | 5.45 | 600 | 0.5156 | 0.7988 | 0.7955 | 0.7971 | 0.8680 |
1.6153 | 6.36 | 700 | 0.4419 | 0.8693 | 0.8657 | 0.8675 | 0.8984 |
1.6153 | 7.27 | 800 | 0.3940 | 0.8786 | 0.8822 | 0.8804 | 0.9077 |
1.6153 | 8.18 | 900 | 0.3359 | 0.9156 | 0.9194 | 0.9175 | 0.9252 |
0.4054 | 9.09 | 1000 | 0.3066 | 0.9262 | 0.9339 | 0.9300 | 0.9381 |
0.4054 | 10.0 | 1100 | 0.2570 | 0.9270 | 0.9442 | 0.9355 | 0.9568 |
0.4054 | 10.91 | 1200 | 0.2439 | 0.9406 | 0.9483 | 0.9444 | 0.9603 |
0.4054 | 11.82 | 1300 | 0.2378 | 0.9446 | 0.9504 | 0.9475 | 0.9614 |
0.4054 | 12.73 | 1400 | 0.2502 | 0.9388 | 0.9504 | 0.9446 | 0.9521 |
0.1461 | 13.64 | 1500 | 0.2008 | 0.9569 | 0.9628 | 0.9598 | 0.9696 |
0.1461 | 14.55 | 1600 | 0.2454 | 0.9446 | 0.9504 | 0.9475 | 0.9544 |
0.1461 | 15.45 | 1700 | 0.2234 | 0.9609 | 0.9649 | 0.9629 | 0.9673 |
0.1461 | 16.36 | 1800 | 0.2408 | 0.9526 | 0.9545 | 0.9536 | 0.9544 |
0.1461 | 17.27 | 1900 | 0.2620 | 0.9545 | 0.9545 | 0.9545 | 0.9544 |
0.0693 | 18.18 | 2000 | 0.2170 | 0.9588 | 0.9628 | 0.9608 | 0.9673 |
0.0693 | 19.09 | 2100 | 0.2408 | 0.9588 | 0.9607 | 0.9598 | 0.9603 |
0.0693 | 20.0 | 2200 | 0.2450 | 0.9506 | 0.9545 | 0.9526 | 0.9556 |
0.0693 | 20.91 | 2300 | 0.2437 | 0.9545 | 0.9545 | 0.9545 | 0.9544 |
0.0693 | 21.82 | 2400 | 0.2173 | 0.9548 | 0.9607 | 0.9578 | 0.9685 |
0.0472 | 22.73 | 2500 | 0.2428 | 0.9485 | 0.9504 | 0.9494 | 0.9626 |
0.0472 | 23.64 | 2600 | 0.2659 | 0.9525 | 0.9525 | 0.9525 | 0.9533 |
0.0472 | 24.55 | 2700 | 0.2713 | 0.9566 | 0.9566 | 0.9566 | 0.9556 |
0.0472 | 25.45 | 2800 | 0.2803 | 0.9545 | 0.9545 | 0.9545 | 0.9544 |
0.0472 | 26.36 | 2900 | 0.2779 | 0.9566 | 0.9566 | 0.9566 | 0.9556 |
0.0356 | 27.27 | 3000 | 0.2695 | 0.9566 | 0.9566 | 0.9566 | 0.9556 |
Framework versions
- Transformers 4.28.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.2.2
- Tokenizers 0.13.2