Hugging Face's logo

Benedict-L
/
layoutlm-funsd

Token Classification
Transformers
TensorBoard
Safetensors
layoutlm
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Benedict-L commited on
Commit
3467d6d
·
verified ·
1 Parent(s): 37bcc1c

End of training

Browse files
Files changed (3) hide show
  1. README.md +21 -26
  2. logs/events.out.tfevents.1719554732.HCIDC-SV-DMZ-ORC-NODE02.2957937.0 +2 -2
  3. model.safetensors +1 -1
README.md CHANGED
@@ -17,14 +17,14 @@ should probably proofread and complete it, then remove this comment. -->
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: 0.6771
21
- - Answer: {'precision': 0.7181719260065288, 'recall': 0.8158220024721878, 'f1': 0.7638888888888888, 'number': 809}
22
- - Header: {'precision': 0.2867647058823529, 'recall': 0.3277310924369748, 'f1': 0.30588235294117644, 'number': 119}
23
- - Question: {'precision': 0.7996406109613656, 'recall': 0.8356807511737089, 'f1': 0.8172635445362718, 'number': 1065}
24
- - Overall Precision: 0.7329
25
- - Overall Recall: 0.7973
26
- - Overall F1: 0.7638
27
- - Overall Accuracy: 0.8074
28
 
29
  ## Model description
30
 
@@ -49,28 +49,23 @@ The following hyperparameters were used during training:
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
- | 1.8162 | 1.0 | 10 | 1.6077 | {'precision': 0.02144469525959368, 'recall': 0.023485784919653894, 'f1': 0.0224188790560472, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.21670702179176757, 'recall': 0.168075117370892, 'f1': 0.18931782125859334, 'number': 1065} | 0.1156 | 0.0993 | 0.1069 | 0.3690 |
60
- | 1.456 | 2.0 | 20 | 1.2533 | {'precision': 0.16709844559585493, 'recall': 0.15945611866501855, 'f1': 0.1631878557874763, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.4537037037037037, 'recall': 0.5521126760563381, 'f1': 0.4980940279542566, 'number': 1065} | 0.3467 | 0.3598 | 0.3531 | 0.5841 |
61
- | 1.1159 | 3.0 | 30 | 0.9750 | {'precision': 0.46204620462046203, 'recall': 0.519159456118665, 'f1': 0.48894062863795107, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.5617378048780488, 'recall': 0.692018779342723, 'f1': 0.6201093815734119, 'number': 1065} | 0.5170 | 0.5805 | 0.5469 | 0.6980 |
62
- | 0.8586 | 4.0 | 40 | 0.8007 | {'precision': 0.5894941634241245, 'recall': 0.7490729295426453, 'f1': 0.6597713663581928, 'number': 809} | {'precision': 0.07017543859649122, 'recall': 0.03361344537815126, 'f1': 0.04545454545454545, 'number': 119} | {'precision': 0.658994032395567, 'recall': 0.7258215962441315, 'f1': 0.6907953529937445, 'number': 1065} | 0.6125 | 0.6939 | 0.6507 | 0.7498 |
63
- | 0.6732 | 5.0 | 50 | 0.7143 | {'precision': 0.6391213389121339, 'recall': 0.7552533992583437, 'f1': 0.6923512747875353, 'number': 809} | {'precision': 0.11827956989247312, 'recall': 0.09243697478991597, 'f1': 0.10377358490566038, 'number': 119} | {'precision': 0.6695379796397808, 'recall': 0.8028169014084507, 'f1': 0.730145175064048, 'number': 1065} | 0.6350 | 0.7411 | 0.6840 | 0.7808 |
64
- | 0.5697 | 6.0 | 60 | 0.6923 | {'precision': 0.6557711950970377, 'recall': 0.7935723114956736, 'f1': 0.7181208053691274, 'number': 809} | {'precision': 0.21052631578947367, 'recall': 0.16806722689075632, 'f1': 0.1869158878504673, 'number': 119} | {'precision': 0.7318777292576419, 'recall': 0.7868544600938967, 'f1': 0.758371040723982, 'number': 1065} | 0.6760 | 0.7526 | 0.7123 | 0.7869 |
65
- | 0.4947 | 7.0 | 70 | 0.6645 | {'precision': 0.6886291179596175, 'recall': 0.8009888751545118, 'f1': 0.7405714285714285, 'number': 809} | {'precision': 0.2459016393442623, 'recall': 0.25210084033613445, 'f1': 0.24896265560165975, 'number': 119} | {'precision': 0.7497805092186128, 'recall': 0.8018779342723005, 'f1': 0.7749546279491834, 'number': 1065} | 0.6957 | 0.7687 | 0.7304 | 0.7950 |
66
- | 0.4371 | 8.0 | 80 | 0.6554 | {'precision': 0.6950959488272921, 'recall': 0.8059332509270705, 'f1': 0.7464224384659416, 'number': 809} | {'precision': 0.22580645161290322, 'recall': 0.23529411764705882, 'f1': 0.23045267489711935, 'number': 119} | {'precision': 0.7470288624787776, 'recall': 0.8262910798122066, 'f1': 0.7846633972358449, 'number': 1065} | 0.6964 | 0.7827 | 0.7371 | 0.7999 |
67
- | 0.3844 | 9.0 | 90 | 0.6466 | {'precision': 0.6878980891719745, 'recall': 0.8009888751545118, 'f1': 0.7401484865790977, 'number': 809} | {'precision': 0.24806201550387597, 'recall': 0.2689075630252101, 'f1': 0.25806451612903225, 'number': 119} | {'precision': 0.7504258943781942, 'recall': 0.8272300469483568, 'f1': 0.7869584635998212, 'number': 1065} | 0.6953 | 0.7832 | 0.7367 | 0.8057 |
68
- | 0.3688 | 10.0 | 100 | 0.6478 | {'precision': 0.7040598290598291, 'recall': 0.8145859085290482, 'f1': 0.755300859598854, 'number': 809} | {'precision': 0.29365079365079366, 'recall': 0.31092436974789917, 'f1': 0.30204081632653057, 'number': 119} | {'precision': 0.7722513089005235, 'recall': 0.8309859154929577, 'f1': 0.8005427408412483, 'number': 1065} | 0.7160 | 0.7933 | 0.7527 | 0.8120 |
69
- | 0.3157 | 11.0 | 110 | 0.6550 | {'precision': 0.7084673097534834, 'recall': 0.8170580964153276, 'f1': 0.758897818599311, 'number': 809} | {'precision': 0.2846153846153846, 'recall': 0.31092436974789917, 'f1': 0.29718875502008035, 'number': 119} | {'precision': 0.7736013986013986, 'recall': 0.8309859154929577, 'f1': 0.8012675418741513, 'number': 1065} | 0.7173 | 0.7943 | 0.7538 | 0.8059 |
70
- | 0.2999 | 12.0 | 120 | 0.6654 | {'precision': 0.7153762268266085, 'recall': 0.8108776266996292, 'f1': 0.7601390498261876, 'number': 809} | {'precision': 0.2962962962962963, 'recall': 0.33613445378151263, 'f1': 0.31496062992125984, 'number': 119} | {'precision': 0.7864768683274022, 'recall': 0.8300469483568075, 'f1': 0.8076747373229787, 'number': 1065} | 0.7261 | 0.7928 | 0.7580 | 0.8108 |
71
- | 0.2827 | 13.0 | 130 | 0.6687 | {'precision': 0.7092274678111588, 'recall': 0.8170580964153276, 'f1': 0.7593337162550259, 'number': 809} | {'precision': 0.31746031746031744, 'recall': 0.33613445378151263, 'f1': 0.32653061224489793, 'number': 119} | {'precision': 0.7857142857142857, 'recall': 0.8366197183098592, 'f1': 0.8103683492496588, 'number': 1065} | 0.7263 | 0.7988 | 0.7608 | 0.8104 |
72
- | 0.2652 | 14.0 | 140 | 0.6735 | {'precision': 0.7138193688792165, 'recall': 0.8108776266996292, 'f1': 0.7592592592592592, 'number': 809} | {'precision': 0.28888888888888886, 'recall': 0.3277310924369748, 'f1': 0.3070866141732283, 'number': 119} | {'precision': 0.7883082373782108, 'recall': 0.8356807511737089, 'f1': 0.8113035551504102, 'number': 1065} | 0.7261 | 0.7953 | 0.7591 | 0.8063 |
73
- | 0.2599 | 15.0 | 150 | 0.6771 | {'precision': 0.7181719260065288, 'recall': 0.8158220024721878, 'f1': 0.7638888888888888, 'number': 809} | {'precision': 0.2867647058823529, 'recall': 0.3277310924369748, 'f1': 0.30588235294117644, 'number': 119} | {'precision': 0.7996406109613656, 'recall': 0.8356807511737089, 'f1': 0.8172635445362718, 'number': 1065} | 0.7329 | 0.7973 | 0.7638 | 0.8074 |
74
 
75
 
76
  ### Framework versions
 
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: 0.6244
21
+ - Answer: {'precision': 0.6850886339937435, 'recall': 0.8121137206427689, 'f1': 0.743212669683258, 'number': 809}
22
+ - Header: {'precision': 0.3118279569892473, 'recall': 0.24369747899159663, 'f1': 0.27358490566037735, 'number': 119}
23
+ - Question: {'precision': 0.7454228421970357, 'recall': 0.8028169014084507, 'f1': 0.7730560578661845, 'number': 1065}
24
+ - Overall Precision: 0.7008
25
+ - Overall Recall: 0.7732
26
+ - Overall F1: 0.7352
27
+ - Overall Accuracy: 0.8082
28
 
29
  ## Model description
30
 
 
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
+ - num_epochs: 10
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
+ | 1.815 | 1.0 | 10 | 1.5977 | {'precision': 0.01854714064914992, 'recall': 0.014833127317676144, 'f1': 0.01648351648351648, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.28852459016393445, 'recall': 0.1652582159624413, 'f1': 0.21014925373134327, 'number': 1065} | 0.1496 | 0.0943 | 0.1157 | 0.3533 |
60
+ | 1.4806 | 2.0 | 20 | 1.2889 | {'precision': 0.15517241379310345, 'recall': 0.20024721878862795, 'f1': 0.174851592012952, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.42313218390804597, 'recall': 0.5530516431924882, 'f1': 0.47944647944647945, 'number': 1065} | 0.3083 | 0.3768 | 0.3391 | 0.5762 |
61
+ | 1.1569 | 3.0 | 30 | 0.9771 | {'precision': 0.40138751238850345, 'recall': 0.5006180469715699, 'f1': 0.44554455445544555, 'number': 809} | {'precision': 0.038461538461538464, 'recall': 0.008403361344537815, 'f1': 0.013793103448275862, 'number': 119} | {'precision': 0.5620767494356659, 'recall': 0.7014084507042253, 'f1': 0.6240601503759399, 'number': 1065} | 0.4877 | 0.5785 | 0.5293 | 0.6555 |
62
+ | 0.891 | 4.0 | 40 | 0.8126 | {'precision': 0.5368516833484986, 'recall': 0.7292954264524104, 'f1': 0.618448637316562, 'number': 809} | {'precision': 0.16279069767441862, 'recall': 0.058823529411764705, 'f1': 0.08641975308641975, 'number': 119} | {'precision': 0.6547202797202797, 'recall': 0.7032863849765258, 'f1': 0.6781349026708917, 'number': 1065} | 0.5888 | 0.6754 | 0.6291 | 0.7338 |
63
+ | 0.7304 | 5.0 | 50 | 0.7076 | {'precision': 0.6277836691410392, 'recall': 0.7317676143386898, 'f1': 0.6757990867579908, 'number': 809} | {'precision': 0.22535211267605634, 'recall': 0.13445378151260504, 'f1': 0.16842105263157894, 'number': 119} | {'precision': 0.6539360872954014, 'recall': 0.787793427230047, 'f1': 0.7146507666098807, 'number': 1065} | 0.6300 | 0.7260 | 0.6746 | 0.7781 |
64
+ | 0.6363 | 6.0 | 60 | 0.6767 | {'precision': 0.6412825651302605, 'recall': 0.7911001236093943, 'f1': 0.7083563918096293, 'number': 809} | {'precision': 0.3235294117647059, 'recall': 0.18487394957983194, 'f1': 0.23529411764705885, 'number': 119} | {'precision': 0.7082969432314411, 'recall': 0.7615023474178404, 'f1': 0.7339366515837105, 'number': 1065} | 0.6662 | 0.7391 | 0.7008 | 0.7846 |
65
+ | 0.5714 | 7.0 | 70 | 0.6386 | {'precision': 0.6797040169133193, 'recall': 0.7948084054388134, 'f1': 0.7327635327635328, 'number': 809} | {'precision': 0.313953488372093, 'recall': 0.226890756302521, 'f1': 0.2634146341463415, 'number': 119} | {'precision': 0.726962457337884, 'recall': 0.8, 'f1': 0.7617344658024139, 'number': 1065} | 0.6906 | 0.7637 | 0.7253 | 0.8048 |
66
+ | 0.5241 | 8.0 | 80 | 0.6398 | {'precision': 0.6753112033195021, 'recall': 0.8046971569839307, 'f1': 0.7343485617597293, 'number': 809} | {'precision': 0.29213483146067415, 'recall': 0.2184873949579832, 'f1': 0.25, 'number': 119} | {'precision': 0.7306015693112468, 'recall': 0.7868544600938967, 'f1': 0.7576853526220616, 'number': 1065} | 0.6886 | 0.7602 | 0.7226 | 0.8005 |
67
+ | 0.4861 | 9.0 | 90 | 0.6272 | {'precision': 0.6785340314136126, 'recall': 0.8009888751545118, 'f1': 0.7346938775510204, 'number': 809} | {'precision': 0.3010752688172043, 'recall': 0.23529411764705882, 'f1': 0.2641509433962264, 'number': 119} | {'precision': 0.7407407407407407, 'recall': 0.8075117370892019, 'f1': 0.7726864330637916, 'number': 1065} | 0.6953 | 0.7707 | 0.7311 | 0.8087 |
68
+ | 0.5004 | 10.0 | 100 | 0.6244 | {'precision': 0.6850886339937435, 'recall': 0.8121137206427689, 'f1': 0.743212669683258, 'number': 809} | {'precision': 0.3118279569892473, 'recall': 0.24369747899159663, 'f1': 0.27358490566037735, 'number': 119} | {'precision': 0.7454228421970357, 'recall': 0.8028169014084507, 'f1': 0.7730560578661845, 'number': 1065} | 0.7008 | 0.7732 | 0.7352 | 0.8082 |
 
 
 
 
 
69
 
70
 
71
  ### Framework versions
logs/events.out.tfevents.1719554732.HCIDC-SV-DMZ-ORC-NODE02.2957937.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c260e9cf19584fc1ac227ca7ee27be82c7ef403ea99038b0e5173da5b6dbec1
3
- size 9975
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dd5824c549ef16bcd65a7ec9b2e06b1c0e4fc9726b4b09e74ed44add7f4c926
3
+ size 12429
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dcdcdfaecd532099b065655ac27e8f849529cd26a4e61c285c95d112f1d59552
3
  size 450558212
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:febbaddce7b38e42dcd79290daa00870e0e8f9245d4620ef0cac1831ffe918d3
3
  size 450558212