Benedict-L commited on
Commit
1e633e3
·
verified ·
1 Parent(s): 4a88c3b

End of training

Browse files
README.md CHANGED
@@ -1,81 +1,81 @@
1
- ---
2
- license: mit
3
- base_model: microsoft/layoutlm-base-uncased
4
- tags:
5
- - generated_from_trainer
6
- datasets:
7
- - funsd
8
- model-index:
9
- - name: layoutlm-funsd
10
- results: []
11
- ---
12
-
13
- <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
- should probably proofread and complete it, then remove this comment. -->
15
-
16
- # layoutlm-funsd
17
-
18
- This model is a fine-tuned version of [microsoft/layoutlm-base-uncased](https://huggingface.co/microsoft/layoutlm-base-uncased) on the funsd dataset.
19
- It achieves the following results on the evaluation set:
20
- - Loss: 0.8707
21
- - Answer: {'precision': 0.731359649122807, 'recall': 0.8244746600741656, 'f1': 0.7751307379430563, 'number': 809}
22
- - Header: {'precision': 0.47101449275362317, 'recall': 0.5462184873949579, 'f1': 0.5058365758754864, 'number': 119}
23
- - Question: {'precision': 0.8043087971274686, 'recall': 0.8413145539906103, 'f1': 0.8223955943093162, 'number': 1065}
24
- - Overall Precision: 0.7523
25
- - Overall Recall: 0.8169
26
- - Overall F1: 0.7833
27
- - Overall Accuracy: 0.8120
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: 3e-05
47
- - train_batch_size: 16
48
- - eval_batch_size: 8
49
- - seed: 42
50
- - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
- - lr_scheduler_type: linear
52
- - num_epochs: 15
53
- - mixed_precision_training: Native AMP
54
-
55
- ### Training results
56
-
57
- | Training Loss | Epoch | Step | Validation Loss | Answer | Header | Question | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
58
- |:-------------:|:-----:|:----:|:---------------:|:---------------------------------------------------------------------------------------------------------:|:------------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
59
- | 1.6648 | 1.0 | 19 | 1.2802 | {'precision': 0.24287028518859247, 'recall': 0.3263288009888752, 'f1': 0.2784810126582279, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.3659942363112392, 'recall': 0.596244131455399, 'f1': 0.45357142857142857, 'number': 1065} | 0.3186 | 0.4511 | 0.3734 | 0.5834 |
60
- | 1.0035 | 2.0 | 38 | 0.7824 | {'precision': 0.5849056603773585, 'recall': 0.7280593325092707, 'f1': 0.6486784140969163, 'number': 809} | {'precision': 0.031746031746031744, 'recall': 0.01680672268907563, 'f1': 0.02197802197802198, 'number': 119} | {'precision': 0.6030042918454935, 'recall': 0.7915492957746478, 'f1': 0.684531059683313, 'number': 1065} | 0.5810 | 0.7195 | 0.6429 | 0.7645 |
61
- | 0.6425 | 3.0 | 57 | 0.6680 | {'precision': 0.6607515657620042, 'recall': 0.7824474660074165, 'f1': 0.7164685908319186, 'number': 809} | {'precision': 0.12037037037037036, 'recall': 0.1092436974789916, 'f1': 0.1145374449339207, 'number': 119} | {'precision': 0.7028753993610224, 'recall': 0.8262910798122066, 'f1': 0.7596029348295209, 'number': 1065} | 0.6583 | 0.7657 | 0.7080 | 0.7896 |
62
- | 0.4629 | 4.0 | 76 | 0.6420 | {'precision': 0.6653102746693794, 'recall': 0.8084054388133498, 'f1': 0.7299107142857143, 'number': 809} | {'precision': 0.29357798165137616, 'recall': 0.2689075630252101, 'f1': 0.28070175438596495, 'number': 119} | {'precision': 0.7648578811369509, 'recall': 0.8338028169014085, 'f1': 0.7978436657681941, 'number': 1065} | 0.6986 | 0.7898 | 0.7414 | 0.8070 |
63
- | 0.3456 | 5.0 | 95 | 0.6765 | {'precision': 0.6901709401709402, 'recall': 0.7985166872682324, 'f1': 0.7404011461318052, 'number': 809} | {'precision': 0.3007518796992481, 'recall': 0.33613445378151263, 'f1': 0.31746031746031744, 'number': 119} | {'precision': 0.7731685789938217, 'recall': 0.8225352112676056, 'f1': 0.7970882620564149, 'number': 1065} | 0.7094 | 0.7837 | 0.7447 | 0.8024 |
64
- | 0.2667 | 6.0 | 114 | 0.6940 | {'precision': 0.6908315565031983, 'recall': 0.8009888751545118, 'f1': 0.7418431597023468, 'number': 809} | {'precision': 0.35294117647058826, 'recall': 0.35294117647058826, 'f1': 0.35294117647058826, 'number': 119} | {'precision': 0.7787610619469026, 'recall': 0.8262910798122066, 'f1': 0.8018223234624146, 'number': 1065} | 0.7179 | 0.7878 | 0.7512 | 0.8054 |
65
- | 0.2131 | 7.0 | 133 | 0.7425 | {'precision': 0.696652719665272, 'recall': 0.823238566131026, 'f1': 0.7546742209631728, 'number': 809} | {'precision': 0.40310077519379844, 'recall': 0.4369747899159664, 'f1': 0.4193548387096774, 'number': 119} | {'precision': 0.8073394495412844, 'recall': 0.8262910798122066, 'f1': 0.8167053364269143, 'number': 1065} | 0.7347 | 0.8018 | 0.7668 | 0.8062 |
66
- | 0.1712 | 8.0 | 152 | 0.7707 | {'precision': 0.7065101387406617, 'recall': 0.8182941903584673, 'f1': 0.7583046964490264, 'number': 809} | {'precision': 0.39215686274509803, 'recall': 0.5042016806722689, 'f1': 0.4411764705882353, 'number': 119} | {'precision': 0.8030713640469738, 'recall': 0.8347417840375587, 'f1': 0.8186003683241252, 'number': 1065} | 0.7333 | 0.8083 | 0.7690 | 0.8080 |
67
- | 0.1426 | 9.0 | 171 | 0.7811 | {'precision': 0.717391304347826, 'recall': 0.8158220024721878, 'f1': 0.7634470792365529, 'number': 809} | {'precision': 0.4274193548387097, 'recall': 0.44537815126050423, 'f1': 0.43621399176954734, 'number': 119} | {'precision': 0.7968056787932565, 'recall': 0.8431924882629108, 'f1': 0.8193430656934306, 'number': 1065} | 0.7421 | 0.8083 | 0.7738 | 0.8127 |
68
- | 0.1229 | 10.0 | 190 | 0.8075 | {'precision': 0.7242524916943521, 'recall': 0.8084054388133498, 'f1': 0.764018691588785, 'number': 809} | {'precision': 0.4722222222222222, 'recall': 0.5714285714285714, 'f1': 0.5171102661596959, 'number': 119} | {'precision': 0.8030438675022381, 'recall': 0.8422535211267606, 'f1': 0.8221814848762603, 'number': 1065} | 0.7482 | 0.8123 | 0.7789 | 0.8139 |
69
- | 0.1023 | 11.0 | 209 | 0.8426 | {'precision': 0.7358490566037735, 'recall': 0.8195302843016069, 'f1': 0.775438596491228, 'number': 809} | {'precision': 0.45774647887323944, 'recall': 0.5462184873949579, 'f1': 0.49808429118773945, 'number': 119} | {'precision': 0.7978339350180506, 'recall': 0.8300469483568075, 'f1': 0.8136217211228716, 'number': 1065} | 0.7494 | 0.8088 | 0.7780 | 0.8106 |
70
- | 0.0935 | 12.0 | 228 | 0.8502 | {'precision': 0.7300546448087432, 'recall': 0.8257107540173053, 'f1': 0.7749419953596288, 'number': 809} | {'precision': 0.4520547945205479, 'recall': 0.5546218487394958, 'f1': 0.4981132075471698, 'number': 119} | {'precision': 0.7978339350180506, 'recall': 0.8300469483568075, 'f1': 0.8136217211228716, 'number': 1065} | 0.7460 | 0.8118 | 0.7775 | 0.8110 |
71
- | 0.0829 | 13.0 | 247 | 0.8513 | {'precision': 0.7335562987736901, 'recall': 0.8133498145859085, 'f1': 0.7713950762016414, 'number': 809} | {'precision': 0.4589041095890411, 'recall': 0.5630252100840336, 'f1': 0.5056603773584906, 'number': 119} | {'precision': 0.8018018018018018, 'recall': 0.8356807511737089, 'f1': 0.8183908045977012, 'number': 1065} | 0.7501 | 0.8103 | 0.7791 | 0.8124 |
72
- | 0.0801 | 14.0 | 266 | 0.8655 | {'precision': 0.729490022172949, 'recall': 0.8133498145859085, 'f1': 0.7691408533021624, 'number': 809} | {'precision': 0.4507042253521127, 'recall': 0.5378151260504201, 'f1': 0.4904214559386973, 'number': 119} | {'precision': 0.8057553956834532, 'recall': 0.8413145539906103, 'f1': 0.8231511254019293, 'number': 1065} | 0.7505 | 0.8118 | 0.7799 | 0.8110 |
73
- | 0.0751 | 15.0 | 285 | 0.8707 | {'precision': 0.731359649122807, 'recall': 0.8244746600741656, 'f1': 0.7751307379430563, 'number': 809} | {'precision': 0.47101449275362317, 'recall': 0.5462184873949579, 'f1': 0.5058365758754864, 'number': 119} | {'precision': 0.8043087971274686, 'recall': 0.8413145539906103, 'f1': 0.8223955943093162, 'number': 1065} | 0.7523 | 0.8169 | 0.7833 | 0.8120 |
74
-
75
-
76
- ### Framework versions
77
-
78
- - Transformers 4.41.2
79
- - Pytorch 2.3.1+cu118
80
- - Datasets 2.19.2
81
- - Tokenizers 0.19.1
 
1
+ ---
2
+ license: mit
3
+ base_model: microsoft/layoutlm-base-uncased
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - funsd
8
+ model-index:
9
+ - name: layoutlm-funsd
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # layoutlm-funsd
17
+
18
+ This model is a fine-tuned version of [microsoft/layoutlm-base-uncased](https://huggingface.co/microsoft/layoutlm-base-uncased) on the funsd dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.7113
21
+ - Answer: {'precision': 0.7158962795941376, 'recall': 0.7849196538936959, 'f1': 0.7488207547169812, 'number': 809}
22
+ - Header: {'precision': 0.3418803418803419, 'recall': 0.33613445378151263, 'f1': 0.3389830508474576, 'number': 119}
23
+ - Question: {'precision': 0.7726480836236934, 'recall': 0.8328638497652582, 'f1': 0.8016267510167194, 'number': 1065}
24
+ - Overall Precision: 0.7258
25
+ - Overall Recall: 0.7837
26
+ - Overall F1: 0.7537
27
+ - Overall Accuracy: 0.8028
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: 3e-05
47
+ - train_batch_size: 16
48
+ - eval_batch_size: 8
49
+ - seed: 42
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: linear
52
+ - num_epochs: 15
53
+ - mixed_precision_training: Native AMP
54
+
55
+ ### Training results
56
+
57
+ | Training Loss | Epoch | Step | Validation Loss | Answer | Header | Question | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
58
+ |:-------------:|:-----:|:----:|:---------------:|:-------------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------:|:----------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
59
+ | 1.7452 | 1.0 | 10 | 1.5534 | {'precision': 0.03913894324853229, 'recall': 0.049443757725587144, 'f1': 0.043691971600218454, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.26121794871794873, 'recall': 0.3061032863849765, 'f1': 0.2818849978383052, 'number': 1065} | 0.1612 | 0.1836 | 0.1717 | 0.4436 |
60
+ | 1.3859 | 2.0 | 20 | 1.1959 | {'precision': 0.3140161725067385, 'recall': 0.2880098887515451, 'f1': 0.30045132172791744, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.5303030303030303, 'recall': 0.5915492957746479, 'f1': 0.559254327563249, 'number': 1065} | 0.4467 | 0.4330 | 0.4397 | 0.6150 |
61
+ | 1.037 | 3.0 | 30 | 0.8960 | {'precision': 0.5337078651685393, 'recall': 0.5871446229913473, 'f1': 0.559152442613302, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.616597510373444, 'recall': 0.6976525821596244, 'f1': 0.654625550660793, 'number': 1065} | 0.5724 | 0.6111 | 0.5911 | 0.7266 |
62
+ | 0.7743 | 4.0 | 40 | 0.7486 | {'precision': 0.6307363927427961, 'recall': 0.73053152039555, 'f1': 0.6769759450171822, 'number': 809} | {'precision': 0.1044776119402985, 'recall': 0.058823529411764705, 'f1': 0.07526881720430108, 'number': 119} | {'precision': 0.6512013256006628, 'recall': 0.7380281690140845, 'f1': 0.6919014084507042, 'number': 1065} | 0.6260 | 0.6944 | 0.6584 | 0.7694 |
63
+ | 0.6151 | 5.0 | 50 | 0.7067 | {'precision': 0.6449511400651465, 'recall': 0.7342398022249691, 'f1': 0.6867052023121387, 'number': 809} | {'precision': 0.21686746987951808, 'recall': 0.15126050420168066, 'f1': 0.1782178217821782, 'number': 119} | {'precision': 0.6762589928057554, 'recall': 0.7943661971830986, 'f1': 0.7305699481865285, 'number': 1065} | 0.6466 | 0.7316 | 0.6864 | 0.7804 |
64
+ | 0.5319 | 6.0 | 60 | 0.6947 | {'precision': 0.6685022026431718, 'recall': 0.7503090234857849, 'f1': 0.707047175305766, 'number': 809} | {'precision': 0.24096385542168675, 'recall': 0.16806722689075632, 'f1': 0.19801980198019803, 'number': 119} | {'precision': 0.7186700767263428, 'recall': 0.7915492957746478, 'f1': 0.7533512064343162, 'number': 1065} | 0.6793 | 0.7376 | 0.7072 | 0.7920 |
65
+ | 0.4602 | 7.0 | 70 | 0.6794 | {'precision': 0.6762430939226519, 'recall': 0.7564894932014833, 'f1': 0.7141190198366394, 'number': 809} | {'precision': 0.28225806451612906, 'recall': 0.29411764705882354, 'f1': 0.2880658436213992, 'number': 119} | {'precision': 0.7359307359307359, 'recall': 0.7981220657276995, 'f1': 0.7657657657657657, 'number': 1065} | 0.6854 | 0.7511 | 0.7168 | 0.7980 |
66
+ | 0.4119 | 8.0 | 80 | 0.6743 | {'precision': 0.6659619450317125, 'recall': 0.7787391841779975, 'f1': 0.7179487179487181, 'number': 809} | {'precision': 0.32, 'recall': 0.2689075630252101, 'f1': 0.2922374429223744, 'number': 119} | {'precision': 0.7383820998278829, 'recall': 0.8056338028169014, 'f1': 0.7705433318365513, 'number': 1065} | 0.6884 | 0.7627 | 0.7236 | 0.7996 |
67
+ | 0.3663 | 9.0 | 90 | 0.6797 | {'precision': 0.6924803591470258, 'recall': 0.7626699629171817, 'f1': 0.7258823529411764, 'number': 809} | {'precision': 0.3017241379310345, 'recall': 0.29411764705882354, 'f1': 0.29787234042553185, 'number': 119} | {'precision': 0.7450812660393499, 'recall': 0.8178403755868544, 'f1': 0.7797672336615935, 'number': 1065} | 0.6999 | 0.7642 | 0.7306 | 0.7968 |
68
+ | 0.3556 | 10.0 | 100 | 0.6809 | {'precision': 0.699666295884316, 'recall': 0.7775030902348579, 'f1': 0.7365339578454333, 'number': 809} | {'precision': 0.34615384615384615, 'recall': 0.3025210084033613, 'f1': 0.32286995515695066, 'number': 119} | {'precision': 0.7615720524017467, 'recall': 0.8187793427230047, 'f1': 0.7891402714932126, 'number': 1065} | 0.7155 | 0.7712 | 0.7423 | 0.8013 |
69
+ | 0.3051 | 11.0 | 110 | 0.6935 | {'precision': 0.6933187294633077, 'recall': 0.7824474660074165, 'f1': 0.7351916376306621, 'number': 809} | {'precision': 0.3217391304347826, 'recall': 0.31092436974789917, 'f1': 0.3162393162393162, 'number': 119} | {'precision': 0.764102564102564, 'recall': 0.8394366197183099, 'f1': 0.7999999999999999, 'number': 1065} | 0.7116 | 0.7847 | 0.7464 | 0.8018 |
70
+ | 0.2905 | 12.0 | 120 | 0.7059 | {'precision': 0.7200929152148664, 'recall': 0.7663782447466008, 'f1': 0.7425149700598803, 'number': 809} | {'precision': 0.35185185185185186, 'recall': 0.31932773109243695, 'f1': 0.33480176211453744, 'number': 119} | {'precision': 0.7692307692307693, 'recall': 0.8262910798122066, 'f1': 0.7967406066093254, 'number': 1065} | 0.7279 | 0.7717 | 0.7491 | 0.7986 |
71
+ | 0.2804 | 13.0 | 130 | 0.7065 | {'precision': 0.709211986681465, 'recall': 0.7898640296662547, 'f1': 0.7473684210526316, 'number': 809} | {'precision': 0.35135135135135137, 'recall': 0.3277310924369748, 'f1': 0.3391304347826087, 'number': 119} | {'precision': 0.7648068669527897, 'recall': 0.8366197183098592, 'f1': 0.7991031390134529, 'number': 1065} | 0.7207 | 0.7873 | 0.7525 | 0.8008 |
72
+ | 0.261 | 14.0 | 140 | 0.7096 | {'precision': 0.713963963963964, 'recall': 0.7836835599505563, 'f1': 0.7472009428403065, 'number': 809} | {'precision': 0.3448275862068966, 'recall': 0.33613445378151263, 'f1': 0.3404255319148936, 'number': 119} | {'precision': 0.7722943722943723, 'recall': 0.8375586854460094, 'f1': 0.8036036036036036, 'number': 1065} | 0.7253 | 0.7858 | 0.7543 | 0.8028 |
73
+ | 0.2537 | 15.0 | 150 | 0.7113 | {'precision': 0.7158962795941376, 'recall': 0.7849196538936959, 'f1': 0.7488207547169812, 'number': 809} | {'precision': 0.3418803418803419, 'recall': 0.33613445378151263, 'f1': 0.3389830508474576, 'number': 119} | {'precision': 0.7726480836236934, 'recall': 0.8328638497652582, 'f1': 0.8016267510167194, 'number': 1065} | 0.7258 | 0.7837 | 0.7537 | 0.8028 |
74
+
75
+
76
+ ### Framework versions
77
+
78
+ - Transformers 4.41.2
79
+ - Pytorch 2.3.1+cu121
80
+ - Datasets 2.19.2
81
+ - Tokenizers 0.19.1
logs/events.out.tfevents.1718614849.HCIDC-SV-DMZ-ORC-NODE02.723418.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd2eef41147b5246c5716934593d569f23a38847cc0d6a6639c7eed2afa1f3ce
3
- size 14200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42807c0d7e155fa6df6479b25038476baeab8f9b430b7f5d66f7e10dc54b2d0e
3
+ size 15984
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e18615f2adeaa7f9e9079452973a96cc6003e71ee2288210d3cadf60dae81ae3
3
  size 450558212
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2977241eaa7494fb71f9189f8ac69810c1671655349ae108799b508ae9ffb89b
3
  size 450558212
preprocessor_config.json CHANGED
@@ -1,25 +1,25 @@
1
- {
2
- "_valid_processor_keys": [
3
- "images",
4
- "do_resize",
5
- "size",
6
- "resample",
7
- "apply_ocr",
8
- "ocr_lang",
9
- "tesseract_config",
10
- "return_tensors",
11
- "data_format",
12
- "input_data_format"
13
- ],
14
- "apply_ocr": true,
15
- "do_resize": true,
16
- "image_processor_type": "LayoutLMv2ImageProcessor",
17
- "ocr_lang": null,
18
- "processor_class": "LayoutLMv2Processor",
19
- "resample": 2,
20
- "size": {
21
- "height": 224,
22
- "width": 224
23
- },
24
- "tesseract_config": ""
25
- }
 
1
+ {
2
+ "_valid_processor_keys": [
3
+ "images",
4
+ "do_resize",
5
+ "size",
6
+ "resample",
7
+ "apply_ocr",
8
+ "ocr_lang",
9
+ "tesseract_config",
10
+ "return_tensors",
11
+ "data_format",
12
+ "input_data_format"
13
+ ],
14
+ "apply_ocr": true,
15
+ "do_resize": true,
16
+ "image_processor_type": "LayoutLMv2ImageProcessor",
17
+ "ocr_lang": null,
18
+ "processor_class": "LayoutLMv2Processor",
19
+ "resample": 2,
20
+ "size": {
21
+ "height": 224,
22
+ "width": 224
23
+ },
24
+ "tesseract_config": ""
25
+ }
special_tokens_map.json CHANGED
@@ -1,37 +1,37 @@
1
- {
2
- "cls_token": {
3
- "content": "[CLS]",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "mask_token": {
10
- "content": "[MASK]",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": {
17
- "content": "[PAD]",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
- "sep_token": {
24
- "content": "[SEP]",
25
- "lstrip": false,
26
- "normalized": false,
27
- "rstrip": false,
28
- "single_word": false
29
- },
30
- "unk_token": {
31
- "content": "[UNK]",
32
- "lstrip": false,
33
- "normalized": false,
34
- "rstrip": false,
35
- "single_word": false
36
- }
37
- }
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer_config.json CHANGED
@@ -1,80 +1,80 @@
1
- {
2
- "added_tokens_decoder": {
3
- "0": {
4
- "content": "[PAD]",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "100": {
12
- "content": "[UNK]",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "101": {
20
- "content": "[CLS]",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "102": {
28
- "content": "[SEP]",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "103": {
36
- "content": "[MASK]",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- }
43
- },
44
- "additional_special_tokens": [],
45
- "apply_ocr": false,
46
- "clean_up_tokenization_spaces": true,
47
- "cls_token": "[CLS]",
48
- "cls_token_box": [
49
- 0,
50
- 0,
51
- 0,
52
- 0
53
- ],
54
- "do_basic_tokenize": true,
55
- "do_lower_case": true,
56
- "mask_token": "[MASK]",
57
- "model_max_length": 512,
58
- "never_split": null,
59
- "only_label_first_subword": true,
60
- "pad_token": "[PAD]",
61
- "pad_token_box": [
62
- 0,
63
- 0,
64
- 0,
65
- 0
66
- ],
67
- "pad_token_label": -100,
68
- "processor_class": "LayoutLMv2Processor",
69
- "sep_token": "[SEP]",
70
- "sep_token_box": [
71
- 1000,
72
- 1000,
73
- 1000,
74
- 1000
75
- ],
76
- "strip_accents": null,
77
- "tokenize_chinese_chars": true,
78
- "tokenizer_class": "LayoutLMv2Tokenizer",
79
- "unk_token": "[UNK]"
80
- }
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "additional_special_tokens": [],
45
+ "apply_ocr": false,
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "[CLS]",
48
+ "cls_token_box": [
49
+ 0,
50
+ 0,
51
+ 0,
52
+ 0
53
+ ],
54
+ "do_basic_tokenize": true,
55
+ "do_lower_case": true,
56
+ "mask_token": "[MASK]",
57
+ "model_max_length": 512,
58
+ "never_split": null,
59
+ "only_label_first_subword": true,
60
+ "pad_token": "[PAD]",
61
+ "pad_token_box": [
62
+ 0,
63
+ 0,
64
+ 0,
65
+ 0
66
+ ],
67
+ "pad_token_label": -100,
68
+ "processor_class": "LayoutLMv2Processor",
69
+ "sep_token": "[SEP]",
70
+ "sep_token_box": [
71
+ 1000,
72
+ 1000,
73
+ 1000,
74
+ 1000
75
+ ],
76
+ "strip_accents": null,
77
+ "tokenize_chinese_chars": true,
78
+ "tokenizer_class": "LayoutLMv2Tokenizer",
79
+ "unk_token": "[UNK]"
80
+ }