prashantloni
commited on
Commit
•
3b79026
1
Parent(s):
9311542
End of training
Browse files- README.md +84 -0
- logs/events.out.tfevents.1713964728.ed91e55b7eb3.647.0 +2 -2
- logs/events.out.tfevents.1713966176.ed91e55b7eb3.647.1 +3 -0
- merges.txt +0 -0
- model.safetensors +1 -1
- preprocessor_config.json +43 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +78 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: SCUT-DLVCLab/lilt-roberta-en-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: lilt-en-aadhaar-red
|
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 |
+
# lilt-en-aadhaar-red
|
15 |
+
|
16 |
+
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.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.0287
|
19 |
+
- Adhaar Number: {'precision': 0.9743589743589743, 'recall': 0.9743589743589743, 'f1': 0.9743589743589743, 'number': 39}
|
20 |
+
- Ame: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 23}
|
21 |
+
- Ather Name: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 2}
|
22 |
+
- Ather Name Back: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 19}
|
23 |
+
- Ather Name Front Top: {'precision': 0.9166666666666666, 'recall': 1.0, 'f1': 0.9565217391304348, 'number': 11}
|
24 |
+
- Ddress Back: {'precision': 0.9512195121951219, 'recall': 0.9629629629629629, 'f1': 0.9570552147239264, 'number': 81}
|
25 |
+
- Ddress Front: {'precision': 0.9615384615384616, 'recall': 0.9615384615384616, 'f1': 0.9615384615384616, 'number': 52}
|
26 |
+
- Ender: {'precision': 0.9523809523809523, 'recall': 0.9523809523809523, 'f1': 0.9523809523809523, 'number': 21}
|
27 |
+
- Ob: {'precision': 0.9545454545454546, 'recall': 1.0, 'f1': 0.9767441860465117, 'number': 21}
|
28 |
+
- Obile Number: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 10}
|
29 |
+
- Ther: {'precision': 0.958974358974359, 'recall': 0.9689119170984456, 'f1': 0.9639175257731959, 'number': 193}
|
30 |
+
- Overall Precision: 0.9623
|
31 |
+
- Overall Recall: 0.9725
|
32 |
+
- Overall F1: 0.9673
|
33 |
+
- Overall Accuracy: 0.9973
|
34 |
+
|
35 |
+
## Model description
|
36 |
+
|
37 |
+
More information needed
|
38 |
+
|
39 |
+
## Intended uses & limitations
|
40 |
+
|
41 |
+
More information needed
|
42 |
+
|
43 |
+
## Training and evaluation data
|
44 |
+
|
45 |
+
More information needed
|
46 |
+
|
47 |
+
## Training procedure
|
48 |
+
|
49 |
+
### Training hyperparameters
|
50 |
+
|
51 |
+
The following hyperparameters were used during training:
|
52 |
+
- learning_rate: 5e-05
|
53 |
+
- train_batch_size: 8
|
54 |
+
- eval_batch_size: 8
|
55 |
+
- seed: 42
|
56 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
57 |
+
- lr_scheduler_type: linear
|
58 |
+
- training_steps: 2500
|
59 |
+
- mixed_precision_training: Native AMP
|
60 |
+
|
61 |
+
### Training results
|
62 |
+
|
63 |
+
| 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 |
|
64 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------:|:------------------------------------------------------------------------:|:----------------------------------------------------------------------------------------:|:----------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------:|:----------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
|
65 |
+
| 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 |
|
66 |
+
| 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 |
|
67 |
+
| 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 |
|
68 |
+
| 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 |
|
69 |
+
| 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 |
|
70 |
+
| 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 |
|
71 |
+
| 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 |
|
72 |
+
| 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 |
|
73 |
+
| 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 |
|
74 |
+
| 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 |
|
75 |
+
| 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 |
|
76 |
+
| 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 |
|
77 |
+
|
78 |
+
|
79 |
+
### Framework versions
|
80 |
+
|
81 |
+
- Transformers 4.40.1
|
82 |
+
- Pytorch 2.2.1+cu121
|
83 |
+
- Datasets 2.19.0
|
84 |
+
- Tokenizers 0.19.1
|
logs/events.out.tfevents.1713964728.ed91e55b7eb3.647.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4cbc1b6edfdc05a59edb803f39bc3cea4948872317e0ea94e330b2a65f2e02d
|
3 |
+
size 14350
|
logs/events.out.tfevents.1713966176.ed91e55b7eb3.647.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ec2a30bc4e1230369cd0dc852e07457d3d85c0495f13c43a666da2e8b904496
|
3 |
+
size 592
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 520746020
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be4fb4aafbdc15b929d0a77f1d0f855ce4a6109369431197a39bbd7b5aa80785
|
3 |
size 520746020
|
preprocessor_config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_valid_processor_keys": [
|
3 |
+
"images",
|
4 |
+
"do_resize",
|
5 |
+
"size",
|
6 |
+
"resample",
|
7 |
+
"do_rescale",
|
8 |
+
"rescale_factor",
|
9 |
+
"do_normalize",
|
10 |
+
"image_mean",
|
11 |
+
"image_std",
|
12 |
+
"apply_ocr",
|
13 |
+
"ocr_lang",
|
14 |
+
"tesseract_config",
|
15 |
+
"return_tensors",
|
16 |
+
"data_format",
|
17 |
+
"input_data_format"
|
18 |
+
],
|
19 |
+
"apply_ocr": true,
|
20 |
+
"do_normalize": true,
|
21 |
+
"do_rescale": true,
|
22 |
+
"do_resize": true,
|
23 |
+
"image_mean": [
|
24 |
+
0.5,
|
25 |
+
0.5,
|
26 |
+
0.5
|
27 |
+
],
|
28 |
+
"image_processor_type": "LayoutLMv3FeatureExtractor",
|
29 |
+
"image_std": [
|
30 |
+
0.5,
|
31 |
+
0.5,
|
32 |
+
0.5
|
33 |
+
],
|
34 |
+
"ocr_lang": null,
|
35 |
+
"processor_class": "LayoutLMv3Processor",
|
36 |
+
"resample": 2,
|
37 |
+
"rescale_factor": 0.00392156862745098,
|
38 |
+
"size": {
|
39 |
+
"height": 224,
|
40 |
+
"width": 224
|
41 |
+
},
|
42 |
+
"tesseract_config": ""
|
43 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": true,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"50264": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": true,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"bos_token": "<s>",
|
46 |
+
"clean_up_tokenization_spaces": true,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"cls_token_box": [
|
49 |
+
0,
|
50 |
+
0,
|
51 |
+
0,
|
52 |
+
0
|
53 |
+
],
|
54 |
+
"eos_token": "</s>",
|
55 |
+
"errors": "replace",
|
56 |
+
"mask_token": "<mask>",
|
57 |
+
"model_max_length": 512,
|
58 |
+
"only_label_first_subword": true,
|
59 |
+
"pad_token": "<pad>",
|
60 |
+
"pad_token_box": [
|
61 |
+
0,
|
62 |
+
0,
|
63 |
+
0,
|
64 |
+
0
|
65 |
+
],
|
66 |
+
"pad_token_label": -100,
|
67 |
+
"processor_class": "LayoutLMv3Processor",
|
68 |
+
"sep_token": "</s>",
|
69 |
+
"sep_token_box": [
|
70 |
+
0,
|
71 |
+
0,
|
72 |
+
0,
|
73 |
+
0
|
74 |
+
],
|
75 |
+
"tokenizer_class": "LayoutLMv3Tokenizer",
|
76 |
+
"trim_offsets": true,
|
77 |
+
"unk_token": "<unk>"
|
78 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|