|
--- |
|
license: mit |
|
base_model: SCUT-DLVCLab/lilt-roberta-en-base |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: lilt-en-aadhaar-red |
|
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. --> |
|
|
|
# lilt-en-aadhaar-red |
|
|
|
This model is a fine-tuned version of [SCUT-DLVCLab/lilt-roberta-en-base](https://huggingface.co/SCUT-DLVCLab/lilt-roberta-en-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0287 |
|
- Adhaar Number: {'precision': 0.9743589743589743, 'recall': 0.9743589743589743, 'f1': 0.9743589743589743, 'number': 39} |
|
- Ame: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 23} |
|
- Ather Name: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 2} |
|
- Ather Name Back: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 19} |
|
- Ather Name Front Top: {'precision': 0.9166666666666666, 'recall': 1.0, 'f1': 0.9565217391304348, 'number': 11} |
|
- Ddress Back: {'precision': 0.9512195121951219, 'recall': 0.9629629629629629, 'f1': 0.9570552147239264, 'number': 81} |
|
- Ddress Front: {'precision': 0.9615384615384616, 'recall': 0.9615384615384616, 'f1': 0.9615384615384616, 'number': 52} |
|
- Ender: {'precision': 0.9523809523809523, 'recall': 0.9523809523809523, 'f1': 0.9523809523809523, 'number': 21} |
|
- Ob: {'precision': 0.9545454545454546, 'recall': 1.0, 'f1': 0.9767441860465117, 'number': 21} |
|
- Obile Number: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 10} |
|
- Ther: {'precision': 0.958974358974359, 'recall': 0.9689119170984456, 'f1': 0.9639175257731959, 'number': 193} |
|
- Overall Precision: 0.9623 |
|
- Overall Recall: 0.9725 |
|
- Overall F1: 0.9673 |
|
- Overall Accuracy: 0.9973 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- training_steps: 2500 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Adhaar Number | Ame | Ather Name | Ather Name Back | Ather Name Front Top | Ddress Back | Ddress Front | Ender | Ob | Obile Number | Ther | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------:|:------------------------------------------------------------------------:|:----------------------------------------------------------------------------------------:|:----------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------:|:----------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:| |
|
| 0.1651 | 10.0 | 200 | 0.0226 | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 39} | {'precision': 0.9130434782608695, 'recall': 0.9130434782608695, 'f1': 0.9130434782608695, 'number': 23} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 2} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 19} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 11} | {'precision': 0.926829268292683, 'recall': 0.9382716049382716, 'f1': 0.9325153374233128, 'number': 81} | {'precision': 0.9811320754716981, 'recall': 1.0, 'f1': 0.9904761904761905, 'number': 52} | {'precision': 0.9047619047619048, 'recall': 0.9047619047619048, 'f1': 0.9047619047619048, 'number': 21} | {'precision': 0.9545454545454546, 'recall': 1.0, 'f1': 0.9767441860465117, 'number': 21} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 10} | {'precision': 0.9384615384615385, 'recall': 0.9481865284974094, 'f1': 0.9432989690721649, 'number': 193} | 0.9497 | 0.9597 | 0.9547 | 0.9962 | |
|
| 0.004 | 20.0 | 400 | 0.0270 | {'precision': 0.9487179487179487, 'recall': 0.9487179487179487, 'f1': 0.9487179487179487, 'number': 39} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 23} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 2} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 19} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 11} | {'precision': 0.926829268292683, 'recall': 0.9382716049382716, 'f1': 0.9325153374233128, 'number': 81} | {'precision': 0.9615384615384616, 'recall': 0.9615384615384616, 'f1': 0.9615384615384616, 'number': 52} | {'precision': 0.9523809523809523, 'recall': 0.9523809523809523, 'f1': 0.9523809523809523, 'number': 21} | {'precision': 0.9090909090909091, 'recall': 0.9523809523809523, 'f1': 0.9302325581395349, 'number': 21} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 10} | {'precision': 0.9333333333333333, 'recall': 0.9430051813471503, 'f1': 0.9381443298969072, 'number': 193} | 0.9454 | 0.9534 | 0.9494 | 0.9964 | |
|
| 0.0016 | 30.0 | 600 | 0.0321 | {'precision': 0.925, 'recall': 0.9487179487179487, 'f1': 0.9367088607594937, 'number': 39} | {'precision': 0.9565217391304348, 'recall': 0.9565217391304348, 'f1': 0.9565217391304348, 'number': 23} | {'precision': 0.6666666666666666, 'recall': 1.0, 'f1': 0.8, 'number': 2} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 19} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 11} | {'precision': 0.9146341463414634, 'recall': 0.9259259259259259, 'f1': 0.9202453987730062, 'number': 81} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 52} | {'precision': 0.9523809523809523, 'recall': 0.9523809523809523, 'f1': 0.9523809523809523, 'number': 21} | {'precision': 0.9545454545454546, 'recall': 1.0, 'f1': 0.9767441860465117, 'number': 21} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 10} | {'precision': 0.9282051282051282, 'recall': 0.9378238341968912, 'f1': 0.9329896907216495, 'number': 193} | 0.9414 | 0.9534 | 0.9474 | 0.9959 | |
|
| 0.0013 | 40.0 | 800 | 0.0243 | {'precision': 0.9743589743589743, 'recall': 0.9743589743589743, 'f1': 0.9743589743589743, 'number': 39} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 23} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 2} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 19} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 11} | {'precision': 0.9390243902439024, 'recall': 0.9506172839506173, 'f1': 0.9447852760736196, 'number': 81} | {'precision': 0.9803921568627451, 'recall': 0.9615384615384616, 'f1': 0.970873786407767, 'number': 52} | {'precision': 0.9523809523809523, 'recall': 0.9523809523809523, 'f1': 0.9523809523809523, 'number': 21} | {'precision': 0.9545454545454546, 'recall': 1.0, 'f1': 0.9767441860465117, 'number': 21} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 10} | {'precision': 0.9487179487179487, 'recall': 0.9585492227979274, 'f1': 0.9536082474226804, 'number': 193} | 0.96 | 0.9661 | 0.9630 | 0.9973 | |
|
| 0.0006 | 50.0 | 1000 | 0.0400 | {'precision': 0.9743589743589743, 'recall': 0.9743589743589743, 'f1': 0.9743589743589743, 'number': 39} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 23} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 2} | {'precision': 1.0, 'recall': 0.8947368421052632, 'f1': 0.9444444444444444, 'number': 19} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 11} | {'precision': 0.8902439024390244, 'recall': 0.9012345679012346, 'f1': 0.8957055214723927, 'number': 81} | {'precision': 0.9803921568627451, 'recall': 0.9615384615384616, 'f1': 0.970873786407767, 'number': 52} | {'precision': 0.9523809523809523, 'recall': 0.9523809523809523, 'f1': 0.9523809523809523, 'number': 21} | {'precision': 0.9545454545454546, 'recall': 1.0, 'f1': 0.9767441860465117, 'number': 21} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 10} | {'precision': 0.9384615384615385, 'recall': 0.9481865284974094, 'f1': 0.9432989690721649, 'number': 193} | 0.9471 | 0.9492 | 0.9481 | 0.9951 | |
|
| 0.0003 | 60.0 | 1200 | 0.0323 | {'precision': 0.9743589743589743, 'recall': 0.9743589743589743, 'f1': 0.9743589743589743, 'number': 39} | {'precision': 0.9565217391304348, 'recall': 0.9565217391304348, 'f1': 0.9565217391304348, 'number': 23} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 2} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 19} | {'precision': 0.9166666666666666, 'recall': 1.0, 'f1': 0.9565217391304348, 'number': 11} | {'precision': 0.926829268292683, 'recall': 0.9382716049382716, 'f1': 0.9325153374233128, 'number': 81} | {'precision': 0.9423076923076923, 'recall': 0.9423076923076923, 'f1': 0.9423076923076923, 'number': 52} | {'precision': 0.9523809523809523, 'recall': 0.9523809523809523, 'f1': 0.9523809523809523, 'number': 21} | {'precision': 0.9545454545454546, 'recall': 1.0, 'f1': 0.9767441860465117, 'number': 21} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 10} | {'precision': 0.9384615384615385, 'recall': 0.9481865284974094, 'f1': 0.9432989690721649, 'number': 193} | 0.9455 | 0.9555 | 0.9505 | 0.9964 | |
|
| 0.0005 | 70.0 | 1400 | 0.0287 | {'precision': 0.9743589743589743, 'recall': 0.9743589743589743, 'f1': 0.9743589743589743, 'number': 39} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 23} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 2} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 19} | {'precision': 0.9166666666666666, 'recall': 1.0, 'f1': 0.9565217391304348, 'number': 11} | {'precision': 0.9512195121951219, 'recall': 0.9629629629629629, 'f1': 0.9570552147239264, 'number': 81} | {'precision': 0.9615384615384616, 'recall': 0.9615384615384616, 'f1': 0.9615384615384616, 'number': 52} | {'precision': 0.9523809523809523, 'recall': 0.9523809523809523, 'f1': 0.9523809523809523, 'number': 21} | {'precision': 0.9545454545454546, 'recall': 1.0, 'f1': 0.9767441860465117, 'number': 21} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 10} | {'precision': 0.958974358974359, 'recall': 0.9689119170984456, 'f1': 0.9639175257731959, 'number': 193} | 0.9623 | 0.9725 | 0.9673 | 0.9973 | |
|
| 0.0004 | 80.0 | 1600 | 0.0417 | {'precision': 0.9487179487179487, 'recall': 0.9487179487179487, 'f1': 0.9487179487179487, 'number': 39} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 23} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 2} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 19} | {'precision': 0.9166666666666666, 'recall': 1.0, 'f1': 0.9565217391304348, 'number': 11} | {'precision': 0.9036144578313253, 'recall': 0.9259259259259259, 'f1': 0.9146341463414634, 'number': 81} | {'precision': 0.9607843137254902, 'recall': 0.9423076923076923, 'f1': 0.9514563106796117, 'number': 52} | {'precision': 0.9523809523809523, 'recall': 0.9523809523809523, 'f1': 0.9523809523809523, 'number': 21} | {'precision': 0.9545454545454546, 'recall': 1.0, 'f1': 0.9767441860465117, 'number': 21} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 10} | {'precision': 0.9285714285714286, 'recall': 0.9430051813471503, 'f1': 0.9357326478149101, 'number': 193} | 0.9393 | 0.9513 | 0.9453 | 0.9951 | |
|
| 0.0001 | 90.0 | 1800 | 0.0362 | {'precision': 0.9743589743589743, 'recall': 0.9743589743589743, 'f1': 0.9743589743589743, 'number': 39} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 23} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 2} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 19} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 11} | {'precision': 0.9146341463414634, 'recall': 0.9259259259259259, 'f1': 0.9202453987730062, 'number': 81} | {'precision': 0.9803921568627451, 'recall': 0.9615384615384616, 'f1': 0.970873786407767, 'number': 52} | {'precision': 0.9523809523809523, 'recall': 0.9523809523809523, 'f1': 0.9523809523809523, 'number': 21} | {'precision': 0.9545454545454546, 'recall': 1.0, 'f1': 0.9767441860465117, 'number': 21} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 10} | {'precision': 0.9384615384615385, 'recall': 0.9481865284974094, 'f1': 0.9432989690721649, 'number': 193} | 0.9516 | 0.9576 | 0.9546 | 0.9964 | |
|
| 0.0001 | 100.0 | 2000 | 0.0378 | {'precision': 0.9743589743589743, 'recall': 0.9743589743589743, 'f1': 0.9743589743589743, 'number': 39} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 23} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 2} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 19} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 11} | {'precision': 0.9146341463414634, 'recall': 0.9259259259259259, 'f1': 0.9202453987730062, 'number': 81} | {'precision': 0.9615384615384616, 'recall': 0.9615384615384616, 'f1': 0.9615384615384616, 'number': 52} | {'precision': 0.9523809523809523, 'recall': 0.9523809523809523, 'f1': 0.9523809523809523, 'number': 21} | {'precision': 0.9545454545454546, 'recall': 1.0, 'f1': 0.9767441860465117, 'number': 21} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 10} | {'precision': 0.9336734693877551, 'recall': 0.9481865284974094, 'f1': 0.9408740359897172, 'number': 193} | 0.9476 | 0.9576 | 0.9526 | 0.9962 | |
|
| 0.0001 | 110.0 | 2200 | 0.0379 | {'precision': 0.9743589743589743, 'recall': 0.9743589743589743, 'f1': 0.9743589743589743, 'number': 39} | {'precision': 0.9565217391304348, 'recall': 0.9565217391304348, 'f1': 0.9565217391304348, 'number': 23} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 2} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 19} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 11} | {'precision': 0.9146341463414634, 'recall': 0.9259259259259259, 'f1': 0.9202453987730062, 'number': 81} | {'precision': 0.9615384615384616, 'recall': 0.9615384615384616, 'f1': 0.9615384615384616, 'number': 52} | {'precision': 0.9523809523809523, 'recall': 0.9523809523809523, 'f1': 0.9523809523809523, 'number': 21} | {'precision': 0.9545454545454546, 'recall': 1.0, 'f1': 0.9767441860465117, 'number': 21} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 10} | {'precision': 0.9285714285714286, 'recall': 0.9430051813471503, 'f1': 0.9357326478149101, 'number': 193} | 0.9434 | 0.9534 | 0.9484 | 0.9959 | |
|
| 0.0001 | 120.0 | 2400 | 0.0361 | {'precision': 0.9743589743589743, 'recall': 0.9743589743589743, 'f1': 0.9743589743589743, 'number': 39} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 23} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 2} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 19} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 11} | {'precision': 0.9146341463414634, 'recall': 0.9259259259259259, 'f1': 0.9202453987730062, 'number': 81} | {'precision': 0.9615384615384616, 'recall': 0.9615384615384616, 'f1': 0.9615384615384616, 'number': 52} | {'precision': 0.9523809523809523, 'recall': 0.9523809523809523, 'f1': 0.9523809523809523, 'number': 21} | {'precision': 0.9545454545454546, 'recall': 1.0, 'f1': 0.9767441860465117, 'number': 21} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 10} | {'precision': 0.9336734693877551, 'recall': 0.9481865284974094, 'f1': 0.9408740359897172, 'number': 193} | 0.9476 | 0.9576 | 0.9526 | 0.9962 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.1 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.19.0 |
|
- Tokenizers 0.19.1 |
|
|
