Commit
•
1a4b93f
1
Parent(s):
b39f302
layoutlmv3-finetuned-cord_100
Browse files
README.md
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-nc-sa-4.0
|
| 3 |
+
base_model: microsoft/layoutlmv3-base
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- precision
|
| 8 |
+
- recall
|
| 9 |
+
- f1
|
| 10 |
+
- accuracy
|
| 11 |
+
model-index:
|
| 12 |
+
- name: layoutlmv3-finetuned-cord_100
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# layoutlmv3-finetuned-cord_100
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on an unknown dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.1687
|
| 24 |
+
- Precision: 0.9382
|
| 25 |
+
- Recall: 0.9574
|
| 26 |
+
- F1: 0.9477
|
| 27 |
+
- Accuracy: 0.9597
|
| 28 |
+
|
| 29 |
+
## Model description
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Intended uses & limitations
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training and evaluation data
|
| 38 |
+
|
| 39 |
+
More information needed
|
| 40 |
+
|
| 41 |
+
## Training procedure
|
| 42 |
+
|
| 43 |
+
### Training hyperparameters
|
| 44 |
+
|
| 45 |
+
The following hyperparameters were used during training:
|
| 46 |
+
- learning_rate: 1e-05
|
| 47 |
+
- train_batch_size: 5
|
| 48 |
+
- eval_batch_size: 5
|
| 49 |
+
- seed: 42
|
| 50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
+
- lr_scheduler_type: linear
|
| 52 |
+
- training_steps: 2500
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
| 57 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
| 58 |
+
| No log | 1.56 | 250 | 0.3730 | 0.8662 | 0.8708 | 0.8685 | 0.9042 |
|
| 59 |
+
| 0.3943 | 3.12 | 500 | 0.2683 | 0.8939 | 0.9027 | 0.8983 | 0.9279 |
|
| 60 |
+
| 0.3943 | 4.69 | 750 | 0.2232 | 0.9248 | 0.9339 | 0.9293 | 0.9474 |
|
| 61 |
+
| 0.1559 | 6.25 | 1000 | 0.2129 | 0.9301 | 0.9407 | 0.9354 | 0.9504 |
|
| 62 |
+
| 0.1559 | 7.81 | 1250 | 0.1782 | 0.9289 | 0.9529 | 0.9407 | 0.9563 |
|
| 63 |
+
| 0.082 | 9.38 | 1500 | 0.1876 | 0.9327 | 0.9483 | 0.9405 | 0.9555 |
|
| 64 |
+
| 0.082 | 10.94 | 1750 | 0.1746 | 0.9416 | 0.9559 | 0.9487 | 0.9606 |
|
| 65 |
+
| 0.0486 | 12.5 | 2000 | 0.1848 | 0.9349 | 0.9498 | 0.9423 | 0.9550 |
|
| 66 |
+
| 0.0486 | 14.06 | 2250 | 0.1739 | 0.9439 | 0.9590 | 0.9514 | 0.9623 |
|
| 67 |
+
| 0.0351 | 15.62 | 2500 | 0.1687 | 0.9382 | 0.9574 | 0.9477 | 0.9597 |
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
### Framework versions
|
| 71 |
+
|
| 72 |
+
- Transformers 4.39.3
|
| 73 |
+
- Pytorch 2.1.2
|
| 74 |
+
- Datasets 2.18.0
|
| 75 |
+
- Tokenizers 0.15.2
|