<!-- 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_2023-07-06_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: 1.0962
- Accuracy: 0.715
- Exit 0 Accuracy: 0.115
- Exit 1 Accuracy: 0.155
- Exit 2 Accuracy: 0.2125
- Exit 3 Accuracy: 0.2025
- 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: 12
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 24
- 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 | 0.72 | 2 | 2.7601 | 0.1125 | 0.08 | 0.0675 | 0.0875 | 0.0625 | 0.0625 |
No log | 1.72 | 4 | 2.7312 | 0.115 | 0.085 | 0.065 | 0.11 | 0.0625 | 0.0625 |
No log | 2.72 | 6 | 2.6976 | 0.1325 | 0.0825 | 0.06 | 0.1175 | 0.0625 | 0.0625 |
No log | 3.72 | 8 | 2.6619 | 0.1675 | 0.085 | 0.055 | 0.12 | 0.0625 | 0.0625 |
No log | 4.72 | 10 | 2.6175 | 0.2075 | 0.085 | 0.0575 | 0.125 | 0.0625 | 0.0625 |
No log | 5.72 | 12 | 2.5697 | 0.2225 | 0.0875 | 0.08 | 0.1275 | 0.0625 | 0.0625 |
No log | 6.72 | 14 | 2.5399 | 0.22 | 0.0925 | 0.08 | 0.1275 | 0.0625 | 0.0625 |
No log | 7.72 | 16 | 2.5148 | 0.2425 | 0.095 | 0.09 | 0.1275 | 0.0625 | 0.0625 |
No log | 8.72 | 18 | 2.4676 | 0.28 | 0.105 | 0.0975 | 0.1375 | 0.0625 | 0.0625 |
No log | 9.72 | 20 | 2.4278 | 0.2925 | 0.1075 | 0.1025 | 0.13 | 0.0625 | 0.0625 |
No log | 10.72 | 22 | 2.3857 | 0.29 | 0.1075 | 0.1175 | 0.1275 | 0.0625 | 0.0625 |
No log | 11.72 | 24 | 2.3281 | 0.325 | 0.105 | 0.1175 | 0.1225 | 0.0625 | 0.0625 |
No log | 12.72 | 26 | 2.2714 | 0.35 | 0.0975 | 0.115 | 0.1175 | 0.0625 | 0.0625 |
No log | 13.72 | 28 | 2.2242 | 0.37 | 0.0975 | 0.1225 | 0.1175 | 0.0625 | 0.0625 |
No log | 14.72 | 30 | 2.1879 | 0.365 | 0.0975 | 0.125 | 0.1275 | 0.0625 | 0.0625 |
No log | 15.72 | 32 | 2.1310 | 0.3925 | 0.0975 | 0.13 | 0.135 | 0.0625 | 0.0625 |
No log | 16.72 | 34 | 2.0772 | 0.395 | 0.1 | 0.1375 | 0.135 | 0.0625 | 0.0625 |
No log | 17.72 | 36 | 2.0417 | 0.4225 | 0.1025 | 0.1375 | 0.1375 | 0.0625 | 0.0625 |
No log | 18.72 | 38 | 1.9643 | 0.4675 | 0.1025 | 0.1375 | 0.145 | 0.0625 | 0.0625 |
No log | 19.72 | 40 | 1.9043 | 0.49 | 0.105 | 0.1425 | 0.15 | 0.0625 | 0.0625 |
No log | 20.72 | 42 | 1.8720 | 0.515 | 0.11 | 0.1425 | 0.1525 | 0.0625 | 0.0625 |
No log | 21.72 | 44 | 1.7821 | 0.5475 | 0.11 | 0.14 | 0.1525 | 0.0625 | 0.0625 |
No log | 22.72 | 46 | 1.7159 | 0.5575 | 0.1125 | 0.14 | 0.155 | 0.0625 | 0.0625 |
No log | 23.72 | 48 | 1.7110 | 0.5475 | 0.1125 | 0.14 | 0.16 | 0.0625 | 0.0625 |
No log | 24.72 | 50 | 1.6566 | 0.5675 | 0.1125 | 0.1425 | 0.16 | 0.065 | 0.0625 |
No log | 25.72 | 52 | 1.5870 | 0.5975 | 0.115 | 0.1475 | 0.1625 | 0.0675 | 0.0625 |
No log | 26.72 | 54 | 1.5599 | 0.595 | 0.115 | 0.1475 | 0.16 | 0.07 | 0.0625 |
No log | 27.72 | 56 | 1.5440 | 0.5975 | 0.115 | 0.1475 | 0.1625 | 0.0775 | 0.0625 |
No log | 28.72 | 58 | 1.4837 | 0.6175 | 0.115 | 0.1475 | 0.1625 | 0.09 | 0.0625 |
No log | 29.72 | 60 | 1.4401 | 0.625 | 0.1175 | 0.1475 | 0.1625 | 0.0925 | 0.0625 |
No log | 30.72 | 62 | 1.4396 | 0.63 | 0.1225 | 0.145 | 0.1675 | 0.095 | 0.0625 |
No log | 31.72 | 64 | 1.4129 | 0.6425 | 0.12 | 0.1475 | 0.17 | 0.0975 | 0.0625 |
No log | 32.72 | 66 | 1.3673 | 0.65 | 0.12 | 0.1475 | 0.1725 | 0.1025 | 0.0625 |
No log | 33.72 | 68 | 1.3507 | 0.6475 | 0.12 | 0.1475 | 0.175 | 0.1125 | 0.0625 |
No log | 34.72 | 70 | 1.3282 | 0.6675 | 0.1175 | 0.1475 | 0.18 | 0.11 | 0.0625 |
No log | 35.72 | 72 | 1.2985 | 0.675 | 0.1175 | 0.1475 | 0.1825 | 0.11 | 0.0625 |
No log | 36.72 | 74 | 1.2807 | 0.68 | 0.1175 | 0.1475 | 0.19 | 0.1125 | 0.0625 |
No log | 37.72 | 76 | 1.2576 | 0.6925 | 0.1175 | 0.15 | 0.195 | 0.1325 | 0.0625 |
No log | 38.72 | 78 | 1.2508 | 0.6925 | 0.1175 | 0.1525 | 0.1975 | 0.1325 | 0.0625 |
No log | 39.72 | 80 | 1.2297 | 0.7075 | 0.1175 | 0.1525 | 0.2 | 0.1425 | 0.0625 |
No log | 40.72 | 82 | 1.2162 | 0.7025 | 0.1175 | 0.1525 | 0.2025 | 0.16 | 0.0625 |
No log | 41.72 | 84 | 1.2092 | 0.7075 | 0.1175 | 0.1525 | 0.2025 | 0.1625 | 0.0625 |
No log | 42.72 | 86 | 1.1928 | 0.7025 | 0.1175 | 0.1525 | 0.21 | 0.165 | 0.0625 |
No log | 43.72 | 88 | 1.1688 | 0.715 | 0.115 | 0.1525 | 0.2125 | 0.1675 | 0.0625 |
No log | 44.72 | 90 | 1.1482 | 0.7125 | 0.1175 | 0.1525 | 0.2075 | 0.1725 | 0.0625 |
No log | 45.72 | 92 | 1.1488 | 0.715 | 0.1175 | 0.1525 | 0.2075 | 0.175 | 0.0625 |
No log | 46.72 | 94 | 1.1525 | 0.7075 | 0.1175 | 0.1525 | 0.205 | 0.1825 | 0.0625 |
No log | 47.72 | 96 | 1.1460 | 0.7075 | 0.1175 | 0.1525 | 0.2075 | 0.1825 | 0.0625 |
No log | 48.72 | 98 | 1.1344 | 0.7075 | 0.1175 | 0.1525 | 0.2125 | 0.1825 | 0.0625 |
No log | 49.72 | 100 | 1.1229 | 0.715 | 0.1175 | 0.155 | 0.2125 | 0.185 | 0.0625 |
No log | 50.72 | 102 | 1.1181 | 0.705 | 0.1175 | 0.155 | 0.2075 | 0.185 | 0.0625 |
No log | 51.72 | 104 | 1.1116 | 0.7175 | 0.115 | 0.155 | 0.21 | 0.1925 | 0.0625 |
No log | 52.72 | 106 | 1.1081 | 0.7175 | 0.1175 | 0.155 | 0.2075 | 0.195 | 0.0625 |
No log | 53.72 | 108 | 1.1082 | 0.7175 | 0.115 | 0.155 | 0.2075 | 0.1975 | 0.0625 |
No log | 54.72 | 110 | 1.1036 | 0.7175 | 0.115 | 0.155 | 0.21 | 0.1975 | 0.0625 |
No log | 55.72 | 112 | 1.0997 | 0.7175 | 0.115 | 0.155 | 0.2125 | 0.2 | 0.0625 |
No log | 56.72 | 114 | 1.0970 | 0.7175 | 0.115 | 0.155 | 0.2125 | 0.2 | 0.0625 |
No log | 57.72 | 116 | 1.0961 | 0.715 | 0.115 | 0.155 | 0.2125 | 0.2 | 0.0625 |
No log | 58.72 | 118 | 1.0963 | 0.715 | 0.115 | 0.155 | 0.2125 | 0.2025 | 0.0625 |
No log | 59.72 | 120 | 1.0962 | 0.715 | 0.115 | 0.155 | 0.2125 | 0.2025 | 0.0625 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1.post200
- Datasets 2.9.0
- Tokenizers 0.13.2