End of training
Browse files- README.md +101 -0
- pytorch_model.bin +1 -1
README.md
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-nc-sa-4.0
|
| 3 |
+
base_model: microsoft/layoutlmv2-base-uncased
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: layoutlmv2-base-uncased_finetuned_docvqa
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# layoutlmv2-base-uncased_finetuned_docvqa
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [microsoft/layoutlmv2-base-uncased](https://huggingface.co/microsoft/layoutlmv2-base-uncased) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 3.8273
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 5e-05
|
| 38 |
+
- train_batch_size: 8
|
| 39 |
+
- eval_batch_size: 8
|
| 40 |
+
- seed: 42
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: linear
|
| 43 |
+
- num_epochs: 20
|
| 44 |
+
|
| 45 |
+
### Training results
|
| 46 |
+
|
| 47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 49 |
+
| 2.0156 | 0.44 | 50 | 2.4679 |
|
| 50 |
+
| 1.8368 | 0.88 | 100 | 2.2079 |
|
| 51 |
+
| 1.5567 | 1.33 | 150 | 2.3312 |
|
| 52 |
+
| 1.3487 | 1.77 | 200 | 2.8410 |
|
| 53 |
+
| 1.2254 | 2.21 | 250 | 2.6996 |
|
| 54 |
+
| 1.1201 | 2.65 | 300 | 2.2915 |
|
| 55 |
+
| 0.8816 | 3.1 | 350 | 2.3419 |
|
| 56 |
+
| 0.7885 | 3.54 | 400 | 2.6410 |
|
| 57 |
+
| 0.7532 | 3.98 | 450 | 2.7539 |
|
| 58 |
+
| 0.5822 | 4.42 | 500 | 2.7213 |
|
| 59 |
+
| 0.5801 | 4.87 | 550 | 2.7429 |
|
| 60 |
+
| 0.5043 | 5.31 | 600 | 2.8523 |
|
| 61 |
+
| 0.4545 | 5.75 | 650 | 2.8666 |
|
| 62 |
+
| 0.4029 | 6.19 | 700 | 3.4559 |
|
| 63 |
+
| 0.3568 | 6.64 | 750 | 3.1760 |
|
| 64 |
+
| 0.3962 | 7.08 | 800 | 3.0625 |
|
| 65 |
+
| 0.2381 | 7.52 | 850 | 3.3868 |
|
| 66 |
+
| 0.2492 | 7.96 | 900 | 3.7453 |
|
| 67 |
+
| 0.3813 | 8.41 | 950 | 3.2516 |
|
| 68 |
+
| 0.2477 | 8.85 | 1000 | 3.4677 |
|
| 69 |
+
| 0.1834 | 9.29 | 1050 | 3.2748 |
|
| 70 |
+
| 0.2067 | 9.73 | 1100 | 3.7590 |
|
| 71 |
+
| 0.2062 | 10.18 | 1150 | 3.5956 |
|
| 72 |
+
| 0.1337 | 10.62 | 1200 | 3.8232 |
|
| 73 |
+
| 0.1785 | 11.06 | 1250 | 3.5264 |
|
| 74 |
+
| 0.0906 | 11.5 | 1300 | 3.6157 |
|
| 75 |
+
| 0.1649 | 11.95 | 1350 | 3.4667 |
|
| 76 |
+
| 0.1306 | 12.39 | 1400 | 3.7029 |
|
| 77 |
+
| 0.0529 | 12.83 | 1450 | 3.6307 |
|
| 78 |
+
| 0.0628 | 13.27 | 1500 | 3.5905 |
|
| 79 |
+
| 0.1015 | 13.72 | 1550 | 3.4659 |
|
| 80 |
+
| 0.0693 | 14.16 | 1600 | 3.7713 |
|
| 81 |
+
| 0.1111 | 14.6 | 1650 | 3.7680 |
|
| 82 |
+
| 0.0414 | 15.04 | 1700 | 3.8956 |
|
| 83 |
+
| 0.0256 | 15.49 | 1750 | 3.9021 |
|
| 84 |
+
| 0.0737 | 15.93 | 1800 | 3.9392 |
|
| 85 |
+
| 0.0577 | 16.37 | 1850 | 3.8129 |
|
| 86 |
+
| 0.0744 | 16.81 | 1900 | 3.8356 |
|
| 87 |
+
| 0.0698 | 17.26 | 1950 | 3.8406 |
|
| 88 |
+
| 0.0173 | 17.7 | 2000 | 3.8611 |
|
| 89 |
+
| 0.0667 | 18.14 | 2050 | 3.7995 |
|
| 90 |
+
| 0.0482 | 18.58 | 2100 | 3.8132 |
|
| 91 |
+
| 0.0458 | 19.03 | 2150 | 3.8335 |
|
| 92 |
+
| 0.0415 | 19.47 | 2200 | 3.8475 |
|
| 93 |
+
| 0.0236 | 19.91 | 2250 | 3.8273 |
|
| 94 |
+
|
| 95 |
+
|
| 96 |
+
### Framework versions
|
| 97 |
+
|
| 98 |
+
- Transformers 4.34.1
|
| 99 |
+
- Pytorch 2.1.0+cu118
|
| 100 |
+
- Datasets 2.14.6
|
| 101 |
+
- Tokenizers 0.14.1
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 802214446
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab22aed2b13b53aa842b548f6118a02b9edb355863ce73eaed1dd82cafe29a4e
|
| 3 |
size 802214446
|