EElayoutlmv3_jordyvl_rvl_cdip_100_examples_per_class_2023-12-04_txt_vis_concat_enc_3_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: 1.0305
- Accuracy: 0.725
- Exit 0 Accuracy: 0.06
- Exit 1 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: 8
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 24
- total_train_batch_size: 192
- 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 |
---|---|---|---|---|---|---|
No log | 0.96 | 4 | 2.7534 | 0.09 | 0.0475 | 0.0625 |
No log | 1.96 | 8 | 2.7060 | 0.1475 | 0.05 | 0.0625 |
No log | 2.96 | 12 | 2.6196 | 0.1825 | 0.0525 | 0.07 |
No log | 3.96 | 16 | 2.5436 | 0.1975 | 0.05 | 0.0525 |
No log | 4.96 | 20 | 2.4872 | 0.215 | 0.0525 | 0.085 |
No log | 5.96 | 24 | 2.3832 | 0.2825 | 0.055 | 0.065 |
No log | 6.96 | 28 | 2.3354 | 0.3125 | 0.0525 | 0.0625 |
No log | 7.96 | 32 | 2.2366 | 0.34 | 0.0525 | 0.0625 |
No log | 8.96 | 36 | 2.1689 | 0.3725 | 0.0525 | 0.0625 |
No log | 9.96 | 40 | 2.0622 | 0.4075 | 0.055 | 0.0625 |
No log | 10.96 | 44 | 1.9774 | 0.4575 | 0.0525 | 0.0625 |
No log | 11.96 | 48 | 1.8564 | 0.505 | 0.0525 | 0.0625 |
No log | 12.96 | 52 | 1.7648 | 0.52 | 0.0525 | 0.0625 |
No log | 13.96 | 56 | 1.6734 | 0.575 | 0.0525 | 0.0625 |
No log | 14.96 | 60 | 1.5849 | 0.5975 | 0.0525 | 0.0625 |
No log | 15.96 | 64 | 1.4981 | 0.605 | 0.0525 | 0.0625 |
No log | 16.96 | 68 | 1.4107 | 0.62 | 0.0575 | 0.0625 |
No log | 17.96 | 72 | 1.3647 | 0.635 | 0.06 | 0.0625 |
No log | 18.96 | 76 | 1.3250 | 0.645 | 0.0575 | 0.0625 |
No log | 19.96 | 80 | 1.2480 | 0.665 | 0.06 | 0.0625 |
No log | 20.96 | 84 | 1.2180 | 0.67 | 0.06 | 0.0625 |
No log | 21.96 | 88 | 1.1733 | 0.695 | 0.06 | 0.0625 |
No log | 22.96 | 92 | 1.1353 | 0.69 | 0.06 | 0.0625 |
No log | 23.96 | 96 | 1.1145 | 0.69 | 0.0625 | 0.0625 |
No log | 24.96 | 100 | 1.1087 | 0.7025 | 0.0625 | 0.0625 |
No log | 25.96 | 104 | 1.0682 | 0.6975 | 0.0625 | 0.0625 |
No log | 26.96 | 108 | 1.0841 | 0.71 | 0.0625 | 0.0625 |
No log | 27.96 | 112 | 1.0348 | 0.705 | 0.0625 | 0.0625 |
No log | 28.96 | 116 | 1.0339 | 0.7 | 0.0625 | 0.0625 |
No log | 29.96 | 120 | 1.0228 | 0.7075 | 0.0625 | 0.0625 |
No log | 30.96 | 124 | 1.0601 | 0.69 | 0.0625 | 0.0625 |
No log | 31.96 | 128 | 0.9958 | 0.7275 | 0.0625 | 0.0625 |
No log | 32.96 | 132 | 1.0300 | 0.7125 | 0.0625 | 0.0625 |
No log | 33.96 | 136 | 0.9698 | 0.7375 | 0.0625 | 0.0625 |
No log | 34.96 | 140 | 1.0067 | 0.715 | 0.0625 | 0.0625 |
No log | 35.96 | 144 | 0.9959 | 0.705 | 0.0625 | 0.0625 |
No log | 36.96 | 148 | 0.9956 | 0.7275 | 0.0625 | 0.0625 |
No log | 37.96 | 152 | 1.0076 | 0.71 | 0.0625 | 0.0625 |
No log | 38.96 | 156 | 0.9998 | 0.7275 | 0.0625 | 0.0625 |
No log | 39.96 | 160 | 0.9907 | 0.7225 | 0.0625 | 0.0625 |
No log | 40.96 | 164 | 0.9902 | 0.73 | 0.0625 | 0.0625 |
No log | 41.96 | 168 | 1.0063 | 0.72 | 0.06 | 0.0625 |
No log | 42.96 | 172 | 1.0144 | 0.72 | 0.06 | 0.0625 |
No log | 43.96 | 176 | 0.9945 | 0.7225 | 0.06 | 0.0625 |
No log | 44.96 | 180 | 0.9974 | 0.72 | 0.06 | 0.0625 |
No log | 45.96 | 184 | 1.0087 | 0.725 | 0.06 | 0.0625 |
No log | 46.96 | 188 | 1.0092 | 0.7125 | 0.06 | 0.0625 |
No log | 47.96 | 192 | 0.9966 | 0.7325 | 0.06 | 0.0625 |
No log | 48.96 | 196 | 1.0084 | 0.73 | 0.06 | 0.0625 |
No log | 49.96 | 200 | 1.0175 | 0.71 | 0.06 | 0.0625 |
No log | 50.96 | 204 | 1.0295 | 0.7175 | 0.06 | 0.0625 |
No log | 51.96 | 208 | 1.0233 | 0.7275 | 0.06 | 0.0625 |
No log | 52.96 | 212 | 1.0280 | 0.7175 | 0.06 | 0.0625 |
No log | 53.96 | 216 | 1.0254 | 0.725 | 0.06 | 0.0625 |
No log | 54.96 | 220 | 1.0211 | 0.73 | 0.06 | 0.0625 |
No log | 55.96 | 224 | 1.0193 | 0.73 | 0.06 | 0.0625 |
No log | 56.96 | 228 | 1.0233 | 0.725 | 0.06 | 0.0625 |
No log | 57.96 | 232 | 1.0284 | 0.725 | 0.06 | 0.0625 |
No log | 58.96 | 236 | 1.0304 | 0.725 | 0.06 | 0.0625 |
No log | 59.96 | 240 | 1.0305 | 0.725 | 0.06 | 0.0625 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1.post200
- Datasets 2.9.0
- Tokenizers 0.13.2
- Downloads last month
- 1