layoutlm-FUNSD-only-5fold
This model is a fine-tuned version of microsoft/layoutlm-base-uncased on the funsd dataset. It achieves the following results on the evaluation set:
- Loss: 0.0018
- Eader: {'precision': 0.9850746268656716, 'recall': 0.9850746268656716, 'f1': 0.9850746268656716, 'number': 67}
- Nswer: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 176}
- Uestion: {'precision': 0.9951456310679612, 'recall': 1.0, 'f1': 0.9975669099756691, 'number': 205}
- Overall Precision: 0.9955
- Overall Recall: 0.9978
- Overall F1: 0.9967
- Overall Accuracy: 0.9998
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: 3e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Eader | Nswer | Uestion | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
|---|---|---|---|---|---|---|---|---|---|---|
| 0.0276 | 1.0 | 8 | 0.0029 | {'precision': 0.9850746268656716, 'recall': 0.9850746268656716, 'f1': 0.9850746268656716, 'number': 67} | {'precision': 0.9943181818181818, 'recall': 0.9943181818181818, 'f1': 0.9943181818181818, 'number': 176} | {'precision': 0.9951456310679612, 'recall': 1.0, 'f1': 0.9975669099756691, 'number': 205} | 0.9933 | 0.9955 | 0.9944 | 0.9995 |
| 0.0298 | 2.0 | 16 | 0.0053 | {'precision': 0.9558823529411765, 'recall': 0.9701492537313433, 'f1': 0.962962962962963, 'number': 67} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 176} | {'precision': 0.9806763285024155, 'recall': 0.9902439024390244, 'f1': 0.9854368932038836, 'number': 205} | 0.9845 | 0.9911 | 0.9878 | 0.9993 |
| 0.0256 | 3.0 | 24 | 0.0027 | {'precision': 0.9850746268656716, 'recall': 0.9850746268656716, 'f1': 0.9850746268656716, 'number': 67} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 176} | {'precision': 0.9951456310679612, 'recall': 1.0, 'f1': 0.9975669099756691, 'number': 205} | 0.9955 | 0.9978 | 0.9967 | 0.9998 |
| 0.0177 | 4.0 | 32 | 0.0024 | {'precision': 0.9850746268656716, 'recall': 0.9850746268656716, 'f1': 0.9850746268656716, 'number': 67} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 176} | {'precision': 0.9951456310679612, 'recall': 1.0, 'f1': 0.9975669099756691, 'number': 205} | 0.9955 | 0.9978 | 0.9967 | 0.9998 |
| 0.0129 | 5.0 | 40 | 0.0022 | {'precision': 0.9850746268656716, 'recall': 0.9850746268656716, 'f1': 0.9850746268656716, 'number': 67} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 176} | {'precision': 0.9951456310679612, 'recall': 1.0, 'f1': 0.9975669099756691, 'number': 205} | 0.9955 | 0.9978 | 0.9967 | 0.9998 |
| 0.012 | 6.0 | 48 | 0.0021 | {'precision': 0.9850746268656716, 'recall': 0.9850746268656716, 'f1': 0.9850746268656716, 'number': 67} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 176} | {'precision': 0.9951456310679612, 'recall': 1.0, 'f1': 0.9975669099756691, 'number': 205} | 0.9955 | 0.9978 | 0.9967 | 0.9998 |
| 0.0092 | 7.0 | 56 | 0.0019 | {'precision': 0.9850746268656716, 'recall': 0.9850746268656716, 'f1': 0.9850746268656716, 'number': 67} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 176} | {'precision': 0.9951456310679612, 'recall': 1.0, 'f1': 0.9975669099756691, 'number': 205} | 0.9955 | 0.9978 | 0.9967 | 0.9998 |
| 0.0079 | 8.0 | 64 | 0.0018 | {'precision': 0.9850746268656716, 'recall': 0.9850746268656716, 'f1': 0.9850746268656716, 'number': 67} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 176} | {'precision': 0.9951456310679612, 'recall': 1.0, 'f1': 0.9975669099756691, 'number': 205} | 0.9955 | 0.9978 | 0.9967 | 0.9998 |
| 0.0075 | 9.0 | 72 | 0.0018 | {'precision': 0.9850746268656716, 'recall': 0.9850746268656716, 'f1': 0.9850746268656716, 'number': 67} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 176} | {'precision': 0.9951456310679612, 'recall': 1.0, 'f1': 0.9975669099756691, 'number': 205} | 0.9955 | 0.9978 | 0.9967 | 0.9998 |
| 0.0078 | 10.0 | 80 | 0.0019 | {'precision': 0.9850746268656716, 'recall': 0.9850746268656716, 'f1': 0.9850746268656716, 'number': 67} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 176} | {'precision': 0.9951456310679612, 'recall': 1.0, 'f1': 0.9975669099756691, 'number': 205} | 0.9955 | 0.9978 | 0.9967 | 0.9998 |
| 0.0073 | 11.0 | 88 | 0.0020 | {'precision': 0.9850746268656716, 'recall': 0.9850746268656716, 'f1': 0.9850746268656716, 'number': 67} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 176} | {'precision': 0.9951456310679612, 'recall': 1.0, 'f1': 0.9975669099756691, 'number': 205} | 0.9955 | 0.9978 | 0.9967 | 0.9998 |
| 0.0063 | 12.0 | 96 | 0.0021 | {'precision': 0.9705882352941176, 'recall': 0.9850746268656716, 'f1': 0.9777777777777777, 'number': 67} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 176} | {'precision': 0.9855072463768116, 'recall': 0.9951219512195122, 'f1': 0.9902912621359223, 'number': 205} | 0.9889 | 0.9955 | 0.9922 | 0.9995 |
| 0.0054 | 13.0 | 104 | 0.0018 | {'precision': 0.9850746268656716, 'recall': 0.9850746268656716, 'f1': 0.9850746268656716, 'number': 67} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 176} | {'precision': 0.9951456310679612, 'recall': 1.0, 'f1': 0.9975669099756691, 'number': 205} | 0.9955 | 0.9978 | 0.9967 | 0.9998 |
| 0.0046 | 14.0 | 112 | 0.0018 | {'precision': 0.9850746268656716, 'recall': 0.9850746268656716, 'f1': 0.9850746268656716, 'number': 67} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 176} | {'precision': 0.9951456310679612, 'recall': 1.0, 'f1': 0.9975669099756691, 'number': 205} | 0.9955 | 0.9978 | 0.9967 | 0.9998 |
| 0.0052 | 15.0 | 120 | 0.0018 | {'precision': 0.9850746268656716, 'recall': 0.9850746268656716, 'f1': 0.9850746268656716, 'number': 67} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 176} | {'precision': 0.9951456310679612, 'recall': 1.0, 'f1': 0.9975669099756691, 'number': 205} | 0.9955 | 0.9978 | 0.9967 | 0.9998 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.6.0+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0
- Downloads last month
- 31
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for pabloma09/layoutlm-FUNSD-only-5fold
Base model
microsoft/layoutlm-base-uncased