<!-- 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_exitlosses
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: 2.4148
- Accuracy: 0.69
- Exit 0 Accuracy: 0.0625
- 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: 18
- eval_batch_size: 3
- seed: 42
- gradient_accumulation_steps: 12
- total_train_batch_size: 216
- 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 | 0.8 | 3 | 5.9533 | 0.1025 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 1.8 | 6 | 5.6136 | 0.1375 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 2.8 | 9 | 5.3608 | 0.195 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 3.8 | 12 | 5.0940 | 0.2075 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 4.8 | 15 | 4.8476 | 0.2325 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 5.8 | 18 | 4.5730 | 0.18 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 6.8 | 21 | 4.3736 | 0.2 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 7.8 | 24 | 4.1419 | 0.24 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 8.8 | 27 | 4.0632 | 0.2575 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 9.8 | 30 | 3.8993 | 0.2725 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 10.8 | 33 | 3.7832 | 0.2725 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 11.8 | 36 | 3.6698 | 0.3175 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 12.8 | 39 | 3.5906 | 0.3375 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 13.8 | 42 | 3.5428 | 0.3825 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 14.8 | 45 | 3.4243 | 0.4075 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 15.8 | 48 | 3.3143 | 0.4475 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 16.8 | 51 | 3.2227 | 0.465 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 17.8 | 54 | 3.1765 | 0.4775 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 18.8 | 57 | 3.0634 | 0.51 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 19.8 | 60 | 3.0335 | 0.5125 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 20.8 | 63 | 2.9393 | 0.5625 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 21.8 | 66 | 2.9017 | 0.58 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 22.8 | 69 | 2.8951 | 0.565 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 23.8 | 72 | 2.8495 | 0.6 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 24.8 | 75 | 2.7970 | 0.6075 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 25.8 | 78 | 2.7476 | 0.615 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 26.8 | 81 | 2.7269 | 0.625 | 0.065 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 27.8 | 84 | 2.7068 | 0.615 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 28.8 | 87 | 2.7034 | 0.6375 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 29.8 | 90 | 2.6356 | 0.66 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 30.8 | 93 | 2.6201 | 0.6525 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 31.8 | 96 | 2.5855 | 0.66 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 32.8 | 99 | 2.5871 | 0.6575 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 33.8 | 102 | 2.5959 | 0.665 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 34.8 | 105 | 2.5538 | 0.6625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 35.8 | 108 | 2.5488 | 0.65 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 36.8 | 111 | 2.5309 | 0.675 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 37.8 | 114 | 2.5034 | 0.6825 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 38.8 | 117 | 2.5297 | 0.6625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 39.8 | 120 | 2.4822 | 0.6725 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 40.8 | 123 | 2.5056 | 0.66 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 41.8 | 126 | 2.4856 | 0.68 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 42.8 | 129 | 2.4918 | 0.67 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 43.8 | 132 | 2.4635 | 0.69 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 44.8 | 135 | 2.4477 | 0.68 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 45.8 | 138 | 2.4668 | 0.68 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 46.8 | 141 | 2.4412 | 0.685 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 47.8 | 144 | 2.4477 | 0.6825 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 48.8 | 147 | 2.4581 | 0.68 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 49.8 | 150 | 2.4446 | 0.6875 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 50.8 | 153 | 2.4598 | 0.685 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 51.8 | 156 | 2.4323 | 0.69 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 52.8 | 159 | 2.4148 | 0.69 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 53.8 | 162 | 2.4228 | 0.6925 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 54.8 | 165 | 2.4136 | 0.695 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 55.8 | 168 | 2.4112 | 0.69 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 56.8 | 171 | 2.4135 | 0.69 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 57.8 | 174 | 2.4219 | 0.69 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 58.8 | 177 | 2.4158 | 0.69 | 0.0625 | 0.0625 | 0.0625 | 0.0625 | 0.0625 |
No log | 59.8 | 180 | 2.4148 | 0.69 | 0.0625 | 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