<!-- 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_2023-10-28_two_text_visual_1_4_8_enc
This model is a fine-tuned version of jordyvl/LayoutLMv3_RVL-CDIP_NK100 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.2233
- Accuracy: 0.7975
- Exit 0 Accuracy: 0.07
- Exit 1 Accuracy: 0.07
- Exit 2 Accuracy: 0.06
- 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: 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 |
|---|---|---|---|---|---|---|---|---|---|
| No log | 0.96 | 16 | 0.9783 | 0.7975 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| No log | 1.98 | 33 | 0.9981 | 0.795 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| No log | 3.0 | 50 | 1.0156 | 0.7975 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| No log | 3.96 | 66 | 1.0306 | 0.8 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| No log | 4.98 | 83 | 1.0420 | 0.8 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| No log | 6.0 | 100 | 1.0522 | 0.8 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| No log | 6.96 | 116 | 1.0613 | 0.8 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| No log | 7.98 | 133 | 1.0719 | 0.8 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| No log | 9.0 | 150 | 1.0820 | 0.7975 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| No log | 9.96 | 166 | 1.0894 | 0.7975 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| No log | 10.98 | 183 | 1.0976 | 0.7975 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| No log | 12.0 | 200 | 1.1053 | 0.7975 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| No log | 12.96 | 216 | 1.1104 | 0.795 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| No log | 13.98 | 233 | 1.1160 | 0.795 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| No log | 15.0 | 250 | 1.1213 | 0.795 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| No log | 15.96 | 266 | 1.1276 | 0.795 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| No log | 16.98 | 283 | 1.1342 | 0.795 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| No log | 18.0 | 300 | 1.1405 | 0.795 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| No log | 18.96 | 316 | 1.1454 | 0.795 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| No log | 19.98 | 333 | 1.1499 | 0.795 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| No log | 21.0 | 350 | 1.1547 | 0.795 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| No log | 21.96 | 366 | 1.1594 | 0.795 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| No log | 22.98 | 383 | 1.1638 | 0.795 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| No log | 24.0 | 400 | 1.1678 | 0.795 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| No log | 24.96 | 416 | 1.1710 | 0.795 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| No log | 25.98 | 433 | 1.1745 | 0.795 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| No log | 27.0 | 450 | 1.1772 | 0.795 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| No log | 27.96 | 466 | 1.1794 | 0.795 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| No log | 28.98 | 483 | 1.1823 | 0.795 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| 2.1017 | 30.0 | 500 | 1.1853 | 0.7975 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| 2.1017 | 30.96 | 516 | 1.1883 | 0.7975 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| 2.1017 | 31.98 | 533 | 1.1912 | 0.7975 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| 2.1017 | 33.0 | 550 | 1.1938 | 0.7975 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| 2.1017 | 33.96 | 566 | 1.1961 | 0.7975 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| 2.1017 | 34.98 | 583 | 1.1985 | 0.7975 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| 2.1017 | 36.0 | 600 | 1.2006 | 0.7975 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| 2.1017 | 36.96 | 616 | 1.2028 | 0.7975 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| 2.1017 | 37.98 | 633 | 1.2049 | 0.7975 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| 2.1017 | 39.0 | 650 | 1.2066 | 0.7975 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| 2.1017 | 39.96 | 666 | 1.2083 | 0.7975 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| 2.1017 | 40.98 | 683 | 1.2094 | 0.7975 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| 2.1017 | 42.0 | 700 | 1.2106 | 0.7975 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| 2.1017 | 42.96 | 716 | 1.2122 | 0.7975 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| 2.1017 | 43.98 | 733 | 1.2136 | 0.7975 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| 2.1017 | 45.0 | 750 | 1.2151 | 0.7975 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| 2.1017 | 45.96 | 766 | 1.2164 | 0.7975 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| 2.1017 | 46.98 | 783 | 1.2177 | 0.7975 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| 2.1017 | 48.0 | 800 | 1.2186 | 0.7975 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| 2.1017 | 48.96 | 816 | 1.2194 | 0.7975 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| 2.1017 | 49.98 | 833 | 1.2202 | 0.7975 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| 2.1017 | 51.0 | 850 | 1.2208 | 0.7975 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| 2.1017 | 51.96 | 866 | 1.2214 | 0.7975 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| 2.1017 | 52.98 | 883 | 1.2220 | 0.7975 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| 2.1017 | 54.0 | 900 | 1.2226 | 0.7975 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| 2.1017 | 54.96 | 916 | 1.2230 | 0.7975 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| 2.1017 | 55.98 | 933 | 1.2232 | 0.7975 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| 2.1017 | 57.0 | 950 | 1.2233 | 0.7975 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
| 2.1017 | 57.6 | 960 | 1.2233 | 0.7975 | 0.07 | 0.07 | 0.06 | 0.0625 | 0.0625 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3
