|
--- |
|
license: cc-by-nc-sa-4.0 |
|
base_model: microsoft/layoutlmv2-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: layoutlmv2-base-finetuned_docvqa |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# layoutlmv2-base-finetuned_docvqa |
|
|
|
This model is a fine-tuned version of [microsoft/layoutlmv2-base-uncased](https://huggingface.co/microsoft/layoutlmv2-base-uncased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 4.6228 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 20 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 5.2897 | 0.22 | 50 | 4.5700 | |
|
| 4.4152 | 0.44 | 100 | 4.4259 | |
|
| 4.1658 | 0.66 | 150 | 3.7699 | |
|
| 3.7752 | 0.88 | 200 | 3.5137 | |
|
| 3.4951 | 1.11 | 250 | 3.2858 | |
|
| 3.0566 | 1.33 | 300 | 3.1827 | |
|
| 2.9219 | 1.55 | 350 | 3.0013 | |
|
| 2.6689 | 1.77 | 400 | 2.8707 | |
|
| 2.5179 | 1.99 | 450 | 2.8395 | |
|
| 2.0212 | 2.21 | 500 | 2.5494 | |
|
| 1.9111 | 2.43 | 550 | 2.4910 | |
|
| 1.897 | 2.65 | 600 | 2.3390 | |
|
| 1.7719 | 2.88 | 650 | 2.0315 | |
|
| 1.3732 | 3.1 | 700 | 2.6837 | |
|
| 1.3554 | 3.32 | 750 | 2.7709 | |
|
| 1.2142 | 3.54 | 800 | 2.6627 | |
|
| 1.1214 | 3.76 | 850 | 2.6243 | |
|
| 1.1927 | 3.98 | 900 | 2.4302 | |
|
| 0.8986 | 4.2 | 950 | 2.5084 | |
|
| 0.8782 | 4.42 | 1000 | 2.6108 | |
|
| 0.9384 | 4.65 | 1050 | 2.5729 | |
|
| 0.9106 | 4.87 | 1100 | 2.8295 | |
|
| 0.7983 | 5.09 | 1150 | 3.3324 | |
|
| 0.7627 | 5.31 | 1200 | 3.0111 | |
|
| 0.8101 | 5.53 | 1250 | 3.0340 | |
|
| 0.8363 | 5.75 | 1300 | 2.6495 | |
|
| 0.8682 | 5.97 | 1350 | 3.0019 | |
|
| 0.636 | 6.19 | 1400 | 3.2153 | |
|
| 0.5614 | 6.42 | 1450 | 2.9601 | |
|
| 0.664 | 6.64 | 1500 | 3.1723 | |
|
| 0.6052 | 6.86 | 1550 | 3.8548 | |
|
| 0.5859 | 7.08 | 1600 | 3.2841 | |
|
| 0.5383 | 7.3 | 1650 | 3.2616 | |
|
| 0.3317 | 7.52 | 1700 | 3.6498 | |
|
| 0.5176 | 7.74 | 1750 | 3.1792 | |
|
| 0.323 | 7.96 | 1800 | 3.9586 | |
|
| 0.2828 | 8.19 | 1850 | 3.3414 | |
|
| 0.3408 | 8.41 | 1900 | 3.4490 | |
|
| 0.4341 | 8.63 | 1950 | 3.6120 | |
|
| 0.4256 | 8.85 | 2000 | 3.6485 | |
|
| 0.2488 | 9.07 | 2050 | 3.2907 | |
|
| 0.2399 | 9.29 | 2100 | 3.9223 | |
|
| 0.3902 | 9.51 | 2150 | 3.4605 | |
|
| 0.1764 | 9.73 | 2200 | 3.4834 | |
|
| 0.3641 | 9.96 | 2250 | 3.6385 | |
|
| 0.0802 | 10.18 | 2300 | 4.1041 | |
|
| 0.1922 | 10.4 | 2350 | 4.0973 | |
|
| 0.1943 | 10.62 | 2400 | 3.8264 | |
|
| 0.1944 | 10.84 | 2450 | 4.0448 | |
|
| 0.1396 | 11.06 | 2500 | 4.0736 | |
|
| 0.1399 | 11.28 | 2550 | 4.1645 | |
|
| 0.1739 | 11.5 | 2600 | 4.0905 | |
|
| 0.0859 | 11.73 | 2650 | 4.2965 | |
|
| 0.1819 | 11.95 | 2700 | 3.9382 | |
|
| 0.1614 | 12.17 | 2750 | 4.2804 | |
|
| 0.1406 | 12.39 | 2800 | 4.4033 | |
|
| 0.1474 | 12.61 | 2850 | 4.3500 | |
|
| 0.0857 | 12.83 | 2900 | 4.6170 | |
|
| 0.1197 | 13.05 | 2950 | 4.0885 | |
|
| 0.1087 | 13.27 | 3000 | 4.1931 | |
|
| 0.0654 | 13.5 | 3050 | 4.4273 | |
|
| 0.1081 | 13.72 | 3100 | 4.3433 | |
|
| 0.2075 | 13.94 | 3150 | 4.1598 | |
|
| 0.0807 | 14.16 | 3200 | 4.1951 | |
|
| 0.0338 | 14.38 | 3250 | 4.2540 | |
|
| 0.0918 | 14.6 | 3300 | 4.4138 | |
|
| 0.1703 | 14.82 | 3350 | 3.9894 | |
|
| 0.0176 | 15.04 | 3400 | 4.3193 | |
|
| 0.1292 | 15.27 | 3450 | 4.4866 | |
|
| 0.0484 | 15.49 | 3500 | 4.2460 | |
|
| 0.0703 | 15.71 | 3550 | 4.2828 | |
|
| 0.1076 | 15.93 | 3600 | 4.4895 | |
|
| 0.0245 | 16.15 | 3650 | 4.5421 | |
|
| 0.0779 | 16.37 | 3700 | 4.5335 | |
|
| 0.0553 | 16.59 | 3750 | 4.5308 | |
|
| 0.0626 | 16.81 | 3800 | 4.4731 | |
|
| 0.0175 | 17.04 | 3850 | 4.4889 | |
|
| 0.0038 | 17.26 | 3900 | 4.4956 | |
|
| 0.0074 | 17.48 | 3950 | 4.6014 | |
|
| 0.0761 | 17.7 | 4000 | 4.5396 | |
|
| 0.0095 | 17.92 | 4050 | 4.5511 | |
|
| 0.0634 | 18.14 | 4100 | 4.5970 | |
|
| 0.0043 | 18.36 | 4150 | 4.6040 | |
|
| 0.0863 | 18.58 | 4200 | 4.6277 | |
|
| 0.02 | 18.81 | 4250 | 4.5889 | |
|
| 0.0176 | 19.03 | 4300 | 4.6318 | |
|
| 0.0062 | 19.25 | 4350 | 4.6496 | |
|
| 0.008 | 19.47 | 4400 | 4.6139 | |
|
| 0.0035 | 19.69 | 4450 | 4.6159 | |
|
| 0.0137 | 19.91 | 4500 | 4.6228 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.32.1 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.13.3 |
|
|
