End of training
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: test
|
| 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 |
+
# test
|
| 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: 0.5892
|
| 24 |
+
- Precision: 0.9073
|
| 25 |
+
- Recall: 0.9240
|
| 26 |
+
- F1: 0.9156
|
| 27 |
+
- Accuracy: 0.8690
|
| 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: 2
|
| 48 |
+
- eval_batch_size: 2
|
| 49 |
+
- seed: 42
|
| 50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
+
- lr_scheduler_type: linear
|
| 52 |
+
- training_steps: 1000
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
| 57 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
| 58 |
+
| No log | 1.33 | 100 | 0.5784 | 0.7726 | 0.8455 | 0.8074 | 0.8067 |
|
| 59 |
+
| No log | 2.67 | 200 | 0.4754 | 0.8436 | 0.8818 | 0.8623 | 0.8483 |
|
| 60 |
+
| No log | 4.0 | 300 | 0.4297 | 0.8572 | 0.9036 | 0.8798 | 0.8574 |
|
| 61 |
+
| No log | 5.33 | 400 | 0.5095 | 0.8676 | 0.9016 | 0.8843 | 0.8370 |
|
| 62 |
+
| 0.526 | 6.67 | 500 | 0.5301 | 0.8785 | 0.9051 | 0.8916 | 0.8533 |
|
| 63 |
+
| 0.526 | 8.0 | 600 | 0.5517 | 0.8849 | 0.8937 | 0.8893 | 0.8431 |
|
| 64 |
+
| 0.526 | 9.33 | 700 | 0.6011 | 0.8853 | 0.9086 | 0.8968 | 0.8556 |
|
| 65 |
+
| 0.526 | 10.67 | 800 | 0.5435 | 0.8989 | 0.9230 | 0.9108 | 0.8682 |
|
| 66 |
+
| 0.526 | 12.0 | 900 | 0.5980 | 0.9078 | 0.9240 | 0.9158 | 0.8676 |
|
| 67 |
+
| 0.1221 | 13.33 | 1000 | 0.5892 | 0.9073 | 0.9240 | 0.9156 | 0.8690 |
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
### Framework versions
|
| 71 |
+
|
| 72 |
+
- Transformers 4.38.0.dev0
|
| 73 |
+
- Pytorch 2.1.0+cu121
|
| 74 |
+
- Datasets 2.17.1
|
| 75 |
+
- Tokenizers 0.15.2
|