2024-01-04_one_stage_subgraphs_weighted_txt_vision_enc_all_gate
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: 1.2459
- Accuracy: 0.78
- Exit 0 Accuracy: 0.06
- Exit 1 Accuracy: 0.07
- Exit 2 Accuracy: 0.0625
- Exit 3 Accuracy: 0.0625
- Exit 4 Accuracy: 0.0625
- Exit 5 Accuracy: 0.0625
- Exit 6 Accuracy: 0.05
- Exit 7 Accuracy: 0.0425
- Exit 8 Accuracy: 0.06
- Exit 9 Accuracy: 0.0625
- Exit 10 Accuracy: 0.0625
- Exit 11 Accuracy: 0.0625
- Exit 12 Accuracy: 0.1125
- Exit 13 Accuracy: 0.78
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: 2
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 24
- total_train_batch_size: 48
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 60
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Exit 0 Accuracy | Exit 1 Accuracy | Exit 2 Accuracy | Exit 3 Accuracy | Exit 4 Accuracy | Exit 5 Accuracy | Exit 6 Accuracy | Exit 7 Accuracy | Exit 8 Accuracy | Exit 9 Accuracy | Exit 10 Accuracy | Exit 11 Accuracy | Exit 12 Accuracy | Exit 13 Accuracy |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
No log | 0.96 | 16 | 2.6851 | 0.145 | 0.04 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.145 |
No log | 1.98 | 33 | 2.5373 | 0.2375 | 0.0425 | 0.0675 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.2375 |
No log | 3.0 | 50 | 2.3649 | 0.29 | 0.045 | 0.07 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.29 |
No log | 3.96 | 66 | 2.1518 | 0.3525 | 0.0475 | 0.07 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.3525 |
No log | 4.98 | 83 | 2.0040 | 0.425 | 0.045 | 0.07 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.425 |
No log | 6.0 | 100 | 1.8333 | 0.4475 | 0.0425 | 0.07 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.4475 |
No log | 6.96 | 116 | 1.6664 | 0.515 | 0.0475 | 0.07 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.515 |
No log | 7.98 | 133 | 1.4248 | 0.61 | 0.0525 | 0.07 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.61 |
No log | 9.0 | 150 | 1.2868 | 0.6225 | 0.0425 | 0.0675 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.6225 |
No log | 9.96 | 166 | 1.1599 | 0.6675 | 0.0625 | 0.0675 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.6675 |
No log | 10.98 | 183 | 1.0790 | 0.7075 | 0.045 | 0.0675 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.7075 |
No log | 12.0 | 200 | 1.0014 | 0.7125 | 0.0575 | 0.0675 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.7125 |
No log | 12.96 | 216 | 0.9468 | 0.72 | 0.0625 | 0.0675 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.72 |
No log | 13.98 | 233 | 0.9718 | 0.7375 | 0.0625 | 0.0675 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.7375 |
No log | 15.0 | 250 | 0.9015 | 0.7625 | 0.0625 | 0.0675 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.7625 |
No log | 15.96 | 266 | 0.9557 | 0.73 | 0.0575 | 0.0675 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.73 |
No log | 16.98 | 283 | 0.9545 | 0.7575 | 0.065 | 0.0675 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.7575 |
No log | 18.0 | 300 | 0.9979 | 0.765 | 0.0625 | 0.0675 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.765 |
No log | 18.96 | 316 | 0.9596 | 0.7575 | 0.065 | 0.0675 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.7575 |
No log | 19.98 | 333 | 1.0056 | 0.77 | 0.065 | 0.0675 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.77 |
No log | 21.0 | 350 | 1.0870 | 0.7475 | 0.0675 | 0.0675 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0675 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.7475 |
No log | 21.96 | 366 | 1.0650 | 0.7725 | 0.0625 | 0.0675 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0475 | 0.0525 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.7725 |
No log | 22.98 | 383 | 1.0799 | 0.745 | 0.06 | 0.0675 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0425 | 0.0525 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.745 |
No log | 24.0 | 400 | 1.1208 | 0.7575 | 0.065 | 0.0675 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0575 | 0.06 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.7575 |
No log | 24.96 | 416 | 1.0551 | 0.7825 | 0.065 | 0.0675 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0275 | 0.0525 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.7825 |
No log | 25.98 | 433 | 1.1037 | 0.7725 | 0.065 | 0.0675 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0275 | 0.05 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.7725 |
No log | 27.0 | 450 | 1.1324 | 0.77 | 0.065 | 0.0675 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.045 | 0.05 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.77 |
No log | 27.96 | 466 | 1.1191 | 0.7775 | 0.065 | 0.0675 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0325 | 0.05 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.7775 |
No log | 28.98 | 483 | 1.1116 | 0.7775 | 0.065 | 0.0675 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.03 | 0.05 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.7775 |
0.3877 | 30.0 | 500 | 1.1583 | 0.7725 | 0.065 | 0.0675 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0325 | 0.05 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.065 | 0.7725 |
0.3877 | 30.96 | 516 | 1.1551 | 0.775 | 0.065 | 0.0675 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.03 | 0.0475 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.065 | 0.775 |
0.3877 | 31.98 | 533 | 1.1548 | 0.7775 | 0.065 | 0.0675 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.03 | 0.045 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.065 | 0.7775 |
0.3877 | 33.0 | 550 | 1.1548 | 0.7775 | 0.065 | 0.0675 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.03 | 0.0475 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0675 | 0.7775 |
0.3877 | 33.96 | 566 | 1.1517 | 0.7825 | 0.065 | 0.0675 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0325 | 0.045 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.065 | 0.7825 |
0.3877 | 34.98 | 583 | 1.1633 | 0.78 | 0.065 | 0.07 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0325 | 0.0425 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.065 | 0.78 |
0.3877 | 36.0 | 600 | 1.1747 | 0.78 | 0.065 | 0.07 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.035 | 0.0425 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.07 | 0.78 |
0.3877 | 36.96 | 616 | 1.1880 | 0.7775 | 0.065 | 0.07 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0325 | 0.0425 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0725 | 0.7775 |
0.3877 | 37.98 | 633 | 1.1981 | 0.78 | 0.065 | 0.07 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.035 | 0.045 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.075 | 0.78 |
0.3877 | 39.0 | 650 | 1.1997 | 0.7775 | 0.065 | 0.07 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.035 | 0.045 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.075 | 0.7775 |
0.3877 | 39.96 | 666 | 1.2021 | 0.78 | 0.065 | 0.07 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.035 | 0.045 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0775 | 0.78 |
0.3877 | 40.98 | 683 | 1.2079 | 0.7825 | 0.0625 | 0.07 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.035 | 0.045 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.08 | 0.7825 |
0.3877 | 42.0 | 700 | 1.2170 | 0.78 | 0.06 | 0.07 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0375 | 0.045 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.085 | 0.78 |
0.3877 | 42.96 | 716 | 1.2204 | 0.7775 | 0.06 | 0.07 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0375 | 0.0475 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.085 | 0.7775 |
0.3877 | 43.98 | 733 | 1.2252 | 0.7775 | 0.06 | 0.07 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0375 | 0.0475 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0875 | 0.7775 |
0.3877 | 45.0 | 750 | 1.2250 | 0.7775 | 0.06 | 0.07 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.04 | 0.05 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.09 | 0.7775 |
0.3877 | 45.96 | 766 | 1.2297 | 0.7775 | 0.06 | 0.07 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.045 | 0.0475 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.09 | 0.7775 |
0.3877 | 46.98 | 783 | 1.2338 | 0.7775 | 0.06 | 0.07 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0475 | 0.045 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0925 | 0.7775 |
0.3877 | 48.0 | 800 | 1.2344 | 0.78 | 0.06 | 0.07 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.05 | 0.045 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0975 | 0.78 |
0.3877 | 48.96 | 816 | 1.2349 | 0.7775 | 0.06 | 0.07 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.05 | 0.045 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.1 | 0.7775 |
0.3877 | 49.98 | 833 | 1.2382 | 0.7775 | 0.06 | 0.07 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.05 | 0.045 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.1025 | 0.7775 |
0.3877 | 51.0 | 850 | 1.2407 | 0.7775 | 0.06 | 0.07 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.05 | 0.045 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.1 | 0.7775 |
0.3877 | 51.96 | 866 | 1.2421 | 0.7775 | 0.06 | 0.07 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.05 | 0.045 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.1 | 0.7775 |
0.3877 | 52.98 | 883 | 1.2429 | 0.7775 | 0.06 | 0.07 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.05 | 0.045 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.1 | 0.7775 |
0.3877 | 54.0 | 900 | 1.2442 | 0.78 | 0.06 | 0.07 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.05 | 0.045 | 0.06 | 0.0625 | 0.0625 | 0.0625 | 0.1075 | 0.78 |
0.3877 | 54.96 | 916 | 1.2445 | 0.7825 | 0.06 | 0.07 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.05 | 0.045 | 0.06 | 0.0625 | 0.0625 | 0.0625 | 0.11 | 0.7825 |
0.3877 | 55.98 | 933 | 1.2457 | 0.78 | 0.06 | 0.07 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.05 | 0.045 | 0.06 | 0.0625 | 0.0625 | 0.0625 | 0.1125 | 0.78 |
0.3877 | 57.0 | 950 | 1.2459 | 0.78 | 0.06 | 0.07 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.05 | 0.0425 | 0.06 | 0.0625 | 0.0625 | 0.0625 | 0.1125 | 0.78 |
0.3877 | 57.6 | 960 | 1.2459 | 0.78 | 0.06 | 0.07 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.05 | 0.0425 | 0.06 | 0.0625 | 0.0625 | 0.0625 | 0.1125 | 0.78 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3
- Downloads last month
- 0