Hugging Face's logo

ethangclark
/
layoutlm-funsd

Token Classification
Transformers
TensorBoard
Safetensors
layoutlm
Generated from Trainer
Model card Files Metrics Community
ethangclark commited on
Commit
dcdaee4
·
verified ·
1 Parent(s): e100464

End of training

Browse files
Files changed (3) hide show
  1. README.md +23 -23
  2. logs/events.out.tfevents.1711210555.ethanmbp.lan.36282.0 +2 -2
  3. model.safetensors +1 -1
README.md CHANGED
@@ -15,13 +15,13 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [microsoft/layoutlm-base-uncased](https://huggingface.co/microsoft/layoutlm-base-uncased) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.5894
19
- - Answer: {'precision': 0.44274809160305345, 'recall': 0.6304347826086957, 'f1': 0.5201793721973095, 'number': 92}
20
- - Header: {'precision': 0.425, 'recall': 0.53125, 'f1': 0.47222222222222215, 'number': 32}
21
- - Overall Precision: 0.4386
22
  - Overall Recall: 0.6048
23
- - Overall F1: 0.5085
24
- - Overall Accuracy: 0.8707
25
 
26
  ## Model description
27
 
@@ -50,23 +50,23 @@ The following hyperparameters were used during training:
50
 
51
  ### Training results
52
 
53
- | Training Loss | Epoch | Step | Validation Loss | Answer | Header | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
54
- |:-------------:|:-----:|:----:|:---------------:|:---------------------------------------------------------------------------------------------------------:|:----------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
55
- | 1.2208 | 1.0 | 2 | 0.9951 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 92} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 32} | 0.0 | 0.0 | 0.0 | 0.8182 |
56
- | 0.6759 | 2.0 | 4 | 0.8725 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 92} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 32} | 0.0 | 0.0 | 0.0 | 0.8182 |
57
- | 0.5294 | 3.0 | 6 | 0.7928 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 92} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 32} | 0.0 | 0.0 | 0.0 | 0.8182 |
58
- | 0.4206 | 4.0 | 8 | 0.7208 | {'precision': 0.75, 'recall': 0.06521739130434782, 'f1': 0.12, 'number': 92} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 32} | 0.75 | 0.0484 | 0.0909 | 0.8233 |
59
- | 0.3048 | 5.0 | 10 | 0.6748 | {'precision': 0.5, 'recall': 0.3804347826086957, 'f1': 0.4320987654320988, 'number': 92} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 32} | 0.5 | 0.2823 | 0.3608 | 0.8476 |
60
- | 0.2901 | 6.0 | 12 | 0.6423 | {'precision': 0.4098360655737705, 'recall': 0.5434782608695652, 'f1': 0.4672897196261682, 'number': 92} | {'precision': 0.3333333333333333, 'recall': 0.03125, 'f1': 0.05714285714285714, 'number': 32} | 0.408 | 0.4113 | 0.4096 | 0.8515 |
61
- | 0.3439 | 7.0 | 14 | 0.6493 | {'precision': 0.3611111111111111, 'recall': 0.5652173913043478, 'f1': 0.44067796610169496, 'number': 92} | {'precision': 0.375, 'recall': 0.09375, 'f1': 0.15, 'number': 32} | 0.3618 | 0.4435 | 0.3986 | 0.8284 |
62
- | 0.3823 | 8.0 | 16 | 0.6242 | {'precision': 0.36054421768707484, 'recall': 0.5760869565217391, 'f1': 0.4435146443514644, 'number': 92} | {'precision': 0.42857142857142855, 'recall': 0.09375, 'f1': 0.15384615384615383, 'number': 32} | 0.3636 | 0.4516 | 0.4029 | 0.8387 |
63
- | 0.4495 | 9.0 | 18 | 0.6264 | {'precision': 0.3803680981595092, 'recall': 0.6739130434782609, 'f1': 0.4862745098039217, 'number': 92} | {'precision': 0.5, 'recall': 0.1875, 'f1': 0.2727272727272727, 'number': 32} | 0.3886 | 0.5484 | 0.4548 | 0.8528 |
64
- | 0.2476 | 10.0 | 20 | 0.6519 | {'precision': 0.3727810650887574, 'recall': 0.6847826086956522, 'f1': 0.4827586206896552, 'number': 92} | {'precision': 0.47368421052631576, 'recall': 0.28125, 'f1': 0.35294117647058826, 'number': 32} | 0.3830 | 0.5806 | 0.4615 | 0.8476 |
65
- | 0.2764 | 11.0 | 22 | 0.6478 | {'precision': 0.39473684210526316, 'recall': 0.6521739130434783, 'f1': 0.49180327868852464, 'number': 92} | {'precision': 0.53125, 'recall': 0.53125, 'f1': 0.53125, 'number': 32} | 0.4185 | 0.6210 | 0.5 | 0.8592 |
66
- | 0.2256 | 12.0 | 24 | 0.6271 | {'precision': 0.4027777777777778, 'recall': 0.6304347826086957, 'f1': 0.4915254237288136, 'number': 92} | {'precision': 0.46153846153846156, 'recall': 0.5625, 'f1': 0.5070422535211268, 'number': 32} | 0.4153 | 0.6129 | 0.4951 | 0.8579 |
67
- | 0.197 | 13.0 | 26 | 0.6084 | {'precision': 0.41843971631205673, 'recall': 0.6413043478260869, 'f1': 0.5064377682403434, 'number': 92} | {'precision': 0.4594594594594595, 'recall': 0.53125, 'f1': 0.4927536231884059, 'number': 32} | 0.4270 | 0.6129 | 0.5033 | 0.8630 |
68
- | 0.2038 | 14.0 | 28 | 0.5952 | {'precision': 0.4393939393939394, 'recall': 0.6304347826086957, 'f1': 0.5178571428571429, 'number': 92} | {'precision': 0.425, 'recall': 0.53125, 'f1': 0.47222222222222215, 'number': 32} | 0.4360 | 0.6048 | 0.5068 | 0.8694 |
69
- | 0.2755 | 15.0 | 30 | 0.5894 | {'precision': 0.44274809160305345, 'recall': 0.6304347826086957, 'f1': 0.5201793721973095, 'number': 92} | {'precision': 0.425, 'recall': 0.53125, 'f1': 0.47222222222222215, 'number': 32} | 0.4386 | 0.6048 | 0.5085 | 0.8707 |
70
 
71
 
72
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [microsoft/layoutlm-base-uncased](https://huggingface.co/microsoft/layoutlm-base-uncased) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.6103
19
+ - Answer: {'precision': 0.46564885496183206, 'recall': 0.6630434782608695, 'f1': 0.547085201793722, 'number': 92}
20
+ - Header: {'precision': 0.34146341463414637, 'recall': 0.4375, 'f1': 0.3835616438356165, 'number': 32}
21
+ - Overall Precision: 0.4360
22
  - Overall Recall: 0.6048
23
+ - Overall F1: 0.5068
24
+ - Overall Accuracy: 0.8784
25
 
26
  ## Model description
27
 
 
50
 
51
  ### Training results
52
 
53
+ | Training Loss | Epoch | Step | Validation Loss | Answer | Header | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
54
+ |:-------------:|:-----:|:----:|:---------------:|:----------------------------------------------------------------------------------------------------------:|:----------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
55
+ | 1.1168 | 1.0 | 2 | 0.9441 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 92} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 32} | 0.0 | 0.0 | 0.0 | 0.8182 |
56
+ | 0.6159 | 2.0 | 4 | 0.8352 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 92} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 32} | 0.0 | 0.0 | 0.0 | 0.8182 |
57
+ | 0.495 | 3.0 | 6 | 0.7209 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 92} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 32} | 0.0 | 0.0 | 0.0 | 0.8182 |
58
+ | 0.4034 | 4.0 | 8 | 0.6673 | {'precision': 0.45454545454545453, 'recall': 0.21739130434782608, 'f1': 0.29411764705882354, 'number': 92} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 32} | 0.4545 | 0.1613 | 0.2381 | 0.8412 |
59
+ | 0.2859 | 5.0 | 10 | 0.6247 | {'precision': 0.4536082474226804, 'recall': 0.4782608695652174, 'f1': 0.4656084656084656, 'number': 92} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 32} | 0.4536 | 0.3548 | 0.3982 | 0.8617 |
60
+ | 0.2644 | 6.0 | 12 | 0.6132 | {'precision': 0.4027777777777778, 'recall': 0.6304347826086957, 'f1': 0.4915254237288136, 'number': 92} | {'precision': 0.3333333333333333, 'recall': 0.03125, 'f1': 0.05714285714285714, 'number': 32} | 0.4014 | 0.4758 | 0.4354 | 0.8668 |
61
+ | 0.3123 | 7.0 | 14 | 0.6367 | {'precision': 0.3954802259887006, 'recall': 0.7608695652173914, 'f1': 0.5204460966542751, 'number': 92} | {'precision': 0.25, 'recall': 0.03125, 'f1': 0.05555555555555555, 'number': 32} | 0.3923 | 0.5726 | 0.4656 | 0.8592 |
62
+ | 0.3486 | 8.0 | 16 | 0.6209 | {'precision': 0.4166666666666667, 'recall': 0.7608695652173914, 'f1': 0.5384615384615384, 'number': 92} | {'precision': 0.125, 'recall': 0.03125, 'f1': 0.05, 'number': 32} | 0.4034 | 0.5726 | 0.4733 | 0.8656 |
63
+ | 0.3703 | 9.0 | 18 | 0.5961 | {'precision': 0.4339622641509434, 'recall': 0.75, 'f1': 0.549800796812749, 'number': 92} | {'precision': 0.5, 'recall': 0.15625, 'f1': 0.23809523809523808, 'number': 32} | 0.4379 | 0.5968 | 0.5051 | 0.8771 |
64
+ | 0.2037 | 10.0 | 20 | 0.5895 | {'precision': 0.423841059602649, 'recall': 0.6956521739130435, 'f1': 0.5267489711934157, 'number': 92} | {'precision': 0.42857142857142855, 'recall': 0.1875, 'f1': 0.26086956521739124, 'number': 32} | 0.4242 | 0.5645 | 0.4844 | 0.8796 |
65
+ | 0.1851 | 11.0 | 22 | 0.5810 | {'precision': 0.4461538461538462, 'recall': 0.6304347826086957, 'f1': 0.5225225225225225, 'number': 92} | {'precision': 0.38235294117647056, 'recall': 0.40625, 'f1': 0.393939393939394, 'number': 32} | 0.4329 | 0.5726 | 0.4931 | 0.8809 |
66
+ | 0.1832 | 12.0 | 24 | 0.5900 | {'precision': 0.46153846153846156, 'recall': 0.6521739130434783, 'f1': 0.5405405405405406, 'number': 92} | {'precision': 0.35135135135135137, 'recall': 0.40625, 'f1': 0.37681159420289856, 'number': 32} | 0.4371 | 0.5887 | 0.5017 | 0.8809 |
67
+ | 0.1588 | 13.0 | 26 | 0.6012 | {'precision': 0.46153846153846156, 'recall': 0.6521739130434783, 'f1': 0.5405405405405406, 'number': 92} | {'precision': 0.35, 'recall': 0.4375, 'f1': 0.38888888888888884, 'number': 32} | 0.4353 | 0.5968 | 0.5034 | 0.8796 |
68
+ | 0.1622 | 14.0 | 28 | 0.6075 | {'precision': 0.46564885496183206, 'recall': 0.6630434782608695, 'f1': 0.547085201793722, 'number': 92} | {'precision': 0.34146341463414637, 'recall': 0.4375, 'f1': 0.3835616438356165, 'number': 32} | 0.4360 | 0.6048 | 0.5068 | 0.8784 |
69
+ | 0.2028 | 15.0 | 30 | 0.6103 | {'precision': 0.46564885496183206, 'recall': 0.6630434782608695, 'f1': 0.547085201793722, 'number': 92} | {'precision': 0.34146341463414637, 'recall': 0.4375, 'f1': 0.3835616438356165, 'number': 32} | 0.4360 | 0.6048 | 0.5068 | 0.8784 |
70
 
71
 
72
  ### Framework versions
logs/events.out.tfevents.1711210555.ethanmbp.lan.36282.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2f60f1a56b9eb66711c408f5b4b83e8f95ae5c1169045235fc8dd8aaad1f1a9
3
- size 5462
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccf288c537886b0f4b516641618aa26b5e27237e5ab1d87d79d920c57b6ef057
3
+ size 15638
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ce44aa3ae60074ce9aa5ef29bd6d3442f71538c208f38a71d11a099d30140df
3
  size 450552060
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c975014e58f2e9e86844261792bc5dd5542db1ac9efc50fb24f9e597bf94d718
3
  size 450552060