<!-- 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. -->
EElayoutlmv3_jordyvl_rvl_cdip_100_examples_per_class_2023-09-19_baseline_gates
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: 2.8358
- Accuracy: 0.6925
- Exit 0 Accuracy: 0.065
- Exit 1 Accuracy: 0.0625
- Exit 2 Accuracy: 0.0625
- Exit 3 Accuracy: 0.0625
- Exit 4 Accuracy: 0.0625
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: 24
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 12
- total_train_batch_size: 288
- 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 |
---|---|---|---|---|---|---|---|---|---|
No log | 0.71 | 2 | 6.0791 | 0.0675 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 1.71 | 4 | 5.8341 | 0.1125 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 2.71 | 6 | 5.6298 | 0.1425 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 3.71 | 8 | 5.4519 | 0.1875 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 4.71 | 10 | 5.2664 | 0.1925 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 5.71 | 12 | 5.0830 | 0.2075 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 6.71 | 14 | 4.8990 | 0.215 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 7.71 | 16 | 4.7073 | 0.215 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 8.71 | 18 | 4.5002 | 0.1925 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 9.71 | 20 | 4.4009 | 0.2225 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 10.71 | 22 | 4.2853 | 0.23 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 11.71 | 24 | 4.0933 | 0.27 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 12.71 | 26 | 3.9761 | 0.27 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 13.71 | 28 | 3.9351 | 0.3025 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 14.71 | 30 | 3.8232 | 0.32 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 15.71 | 32 | 3.7217 | 0.345 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 16.71 | 34 | 3.6380 | 0.39 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 17.71 | 36 | 3.6336 | 0.3925 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 18.71 | 38 | 3.5816 | 0.415 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 19.71 | 40 | 3.4517 | 0.445 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 20.71 | 42 | 3.4066 | 0.475 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 21.71 | 44 | 3.3252 | 0.4825 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 22.71 | 46 | 3.3034 | 0.5075 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 23.71 | 48 | 3.2461 | 0.5275 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 24.71 | 50 | 3.2623 | 0.54 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 25.71 | 52 | 3.1701 | 0.545 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 26.71 | 54 | 3.2183 | 0.545 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 27.71 | 56 | 3.1410 | 0.5625 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 28.71 | 58 | 3.1476 | 0.56 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 29.71 | 60 | 3.0950 | 0.585 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 30.71 | 62 | 3.0338 | 0.605 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 31.71 | 64 | 3.0406 | 0.6 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 32.71 | 66 | 3.0577 | 0.615 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 33.71 | 68 | 3.0389 | 0.6125 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 34.71 | 70 | 3.0199 | 0.62 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 35.71 | 72 | 3.0103 | 0.645 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 36.71 | 74 | 2.9517 | 0.645 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 37.71 | 76 | 2.9726 | 0.645 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 38.71 | 78 | 2.9587 | 0.66 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 39.71 | 80 | 2.9024 | 0.6725 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 40.71 | 82 | 2.9354 | 0.655 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 41.71 | 84 | 2.8976 | 0.6775 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 42.71 | 86 | 2.8988 | 0.6875 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 43.71 | 88 | 2.8944 | 0.6825 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 44.71 | 90 | 2.8853 | 0.6825 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 45.71 | 92 | 2.8685 | 0.6825 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 46.71 | 94 | 2.8623 | 0.665 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 47.71 | 96 | 2.8534 | 0.675 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 48.71 | 98 | 2.8601 | 0.685 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 49.71 | 100 | 2.8378 | 0.6875 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 50.71 | 102 | 2.8203 | 0.6875 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 51.71 | 104 | 2.8153 | 0.69 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 52.71 | 106 | 2.8077 | 0.6925 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 53.71 | 108 | 2.8061 | 0.69 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 54.71 | 110 | 2.8099 | 0.69 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 55.71 | 112 | 2.8061 | 0.6875 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 56.71 | 114 | 2.8268 | 0.69 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 57.71 | 116 | 2.8331 | 0.69 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 58.71 | 118 | 2.8371 | 0.69 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 59.71 | 120 | 2.8358 | 0.6925 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1.post200
- Datasets 2.9.0
- Tokenizers 0.13.2