Hugging Face's logo

tkazusa
/
lilt-en-funsd

Token Classification
Transformers
PyTorch
TensorBoard
lilt
Generated from Trainer
Model card Files
xet
 Metrics Community
1
tkazusa commited on
Commit
4dc042b
·
1 Parent(s): 634f29d

End of training

Browse files
Files changed (3) hide show
  1. README.md +13 -23
  2. logs/events.out.tfevents.1670920837.ip-172-31-89-140.197324.0 +2 -2
  3. logs/events.out.tfevents.1670921146.ip-172-31-89-140.197324.2 +3 -0
README.md CHANGED
@@ -16,14 +16,14 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  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 funsd-layoutlmv3 dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 1.3685
20
- - Answer: {'precision': 0.8654073199527745, 'recall': 0.8971848225214198, 'f1': 0.8810096153846154, 'number': 817}
21
- - Header: {'precision': 0.6041666666666666, 'recall': 0.48739495798319327, 'f1': 0.5395348837209302, 'number': 119}
22
- - Question: {'precision': 0.8660245183887916, 'recall': 0.9182915506035283, 'f1': 0.8913925191527715, 'number': 1077}
23
- - Overall Precision: 0.8537
24
- - Overall Recall: 0.8843
25
- - Overall F1: 0.8687
26
- - Overall Accuracy: 0.8073
27
 
28
  ## Model description
29
 
@@ -48,25 +48,15 @@ The following hyperparameters were used during training:
48
  - seed: 42
49
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
  - lr_scheduler_type: linear
51
- - training_steps: 2500
52
  - mixed_precision_training: Native AMP
53
 
54
  ### Training results
55
 
56
- | Training Loss | Epoch | Step | Validation Loss | Answer | Header | Question | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
57
- |:-------------:|:------:|:----:|:---------------:|:--------------------------------------------------------------------------------------------------------:|:----------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
58
- | 0.4208 | 10.53 | 200 | 0.9422 | {'precision': 0.8501742160278746, 'recall': 0.8959608323133414, 'f1': 0.872467222884386, 'number': 817} | {'precision': 0.47580645161290325, 'recall': 0.4957983193277311, 'f1': 0.48559670781893005, 'number': 119} | {'precision': 0.8847884788478848, 'recall': 0.9127205199628597, 'f1': 0.8985374771480805, 'number': 1077} | 0.8464 | 0.8813 | 0.8635 | 0.8109 |
59
- | 0.043 | 21.05 | 400 | 1.3865 | {'precision': 0.8387096774193549, 'recall': 0.9228886168910648, 'f1': 0.8787878787878787, 'number': 817} | {'precision': 0.5423728813559322, 'recall': 0.5378151260504201, 'f1': 0.540084388185654, 'number': 119} | {'precision': 0.8985507246376812, 'recall': 0.8635097493036211, 'f1': 0.8806818181818181, 'number': 1077} | 0.8519 | 0.8684 | 0.8600 | 0.7941 |
60
- | 0.0126 | 31.58 | 600 | 1.3685 | {'precision': 0.8654073199527745, 'recall': 0.8971848225214198, 'f1': 0.8810096153846154, 'number': 817} | {'precision': 0.6041666666666666, 'recall': 0.48739495798319327, 'f1': 0.5395348837209302, 'number': 119} | {'precision': 0.8660245183887916, 'recall': 0.9182915506035283, 'f1': 0.8913925191527715, 'number': 1077} | 0.8537 | 0.8843 | 0.8687 | 0.8073 |
61
- | 0.006 | 42.11 | 800 | 1.6230 | {'precision': 0.8476977567886659, 'recall': 0.8788249694002448, 'f1': 0.8629807692307692, 'number': 817} | {'precision': 0.6, 'recall': 0.4789915966386555, 'f1': 0.5327102803738317, 'number': 119} | {'precision': 0.872207327971403, 'recall': 0.9062209842154132, 'f1': 0.8888888888888888, 'number': 1077} | 0.8496 | 0.8698 | 0.8596 | 0.7927 |
62
- | 0.005 | 52.63 | 1000 | 1.5735 | {'precision': 0.8246392896781354, 'recall': 0.9094247246022031, 'f1': 0.8649592549476135, 'number': 817} | {'precision': 0.5897435897435898, 'recall': 0.5798319327731093, 'f1': 0.5847457627118645, 'number': 119} | {'precision': 0.8932316491897044, 'recall': 0.8700092850510678, 'f1': 0.8814675446848542, 'number': 1077} | 0.8462 | 0.8689 | 0.8574 | 0.7970 |
63
- | 0.0025 | 63.16 | 1200 | 1.6481 | {'precision': 0.8327721661054994, 'recall': 0.9082007343941249, 'f1': 0.8688524590163934, 'number': 817} | {'precision': 0.5688073394495413, 'recall': 0.5210084033613446, 'f1': 0.543859649122807, 'number': 119} | {'precision': 0.9084778420038536, 'recall': 0.8755803156917363, 'f1': 0.8917257683215132, 'number': 1077} | 0.8572 | 0.8679 | 0.8625 | 0.7981 |
64
- | 0.002 | 73.68 | 1400 | 1.5911 | {'precision': 0.8459743290548425, 'recall': 0.8873929008567931, 'f1': 0.8661887694145758, 'number': 817} | {'precision': 0.6122448979591837, 'recall': 0.5042016806722689, 'f1': 0.5529953917050692, 'number': 119} | {'precision': 0.8736462093862816, 'recall': 0.8987929433611885, 'f1': 0.8860411899313502, 'number': 1077} | 0.8497 | 0.8708 | 0.8602 | 0.8120 |
65
- | 0.0009 | 84.21 | 1600 | 1.6905 | {'precision': 0.8041575492341356, 'recall': 0.8996328029375765, 'f1': 0.8492201039861352, 'number': 817} | {'precision': 0.6020408163265306, 'recall': 0.4957983193277311, 'f1': 0.543778801843318, 'number': 119} | {'precision': 0.900375939849624, 'recall': 0.8895078922934077, 'f1': 0.8949089210649229, 'number': 1077} | 0.8439 | 0.8703 | 0.8569 | 0.7985 |
66
- | 0.0007 | 94.74 | 1800 | 1.7006 | {'precision': 0.8256467941507312, 'recall': 0.8984088127294981, 'f1': 0.8604923798358733, 'number': 817} | {'precision': 0.5573770491803278, 'recall': 0.5714285714285714, 'f1': 0.5643153526970954, 'number': 119} | {'precision': 0.8952830188679245, 'recall': 0.8811513463324049, 'f1': 0.888160973327094, 'number': 1077} | 0.8455 | 0.8698 | 0.8575 | 0.7981 |
67
- | 0.0002 | 105.26 | 2000 | 1.6531 | {'precision': 0.8352402745995423, 'recall': 0.8935128518971848, 'f1': 0.8633944411590775, 'number': 817} | {'precision': 0.5784313725490197, 'recall': 0.4957983193277311, 'f1': 0.5339366515837104, 'number': 119} | {'precision': 0.8848987108655617, 'recall': 0.8922934076137419, 'f1': 0.888580674988442, 'number': 1077} | 0.8487 | 0.8693 | 0.8589 | 0.8140 |
68
- | 0.0002 | 115.79 | 2200 | 1.6520 | {'precision': 0.8342857142857143, 'recall': 0.8935128518971848, 'f1': 0.8628841607565011, 'number': 817} | {'precision': 0.625, 'recall': 0.5462184873949579, 'f1': 0.5829596412556054, 'number': 119} | {'precision': 0.8868445262189513, 'recall': 0.8950789229340761, 'f1': 0.8909426987060998, 'number': 1077} | 0.8514 | 0.8738 | 0.8625 | 0.8153 |
69
- | 0.0003 | 126.32 | 2400 | 1.6411 | {'precision': 0.830316742081448, 'recall': 0.8984088127294981, 'f1': 0.8630217519106408, 'number': 817} | {'precision': 0.6055045871559633, 'recall': 0.5546218487394958, 'f1': 0.5789473684210525, 'number': 119} | {'precision': 0.8976744186046511, 'recall': 0.8960074280408542, 'f1': 0.8968401486988847, 'number': 1077} | 0.8535 | 0.8768 | 0.8650 | 0.8183 |
70
 
71
 
72
  ### Framework versions
 
16
 
17
  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 funsd-layoutlmv3 dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 1.1677
20
+ - Answer: {'precision': 0.8481735159817352, 'recall': 0.9094247246022031, 'f1': 0.8777318369757826, 'number': 817}
21
+ - Header: {'precision': 0.5725806451612904, 'recall': 0.5966386554621849, 'f1': 0.5843621399176955, 'number': 119}
22
+ - Question: {'precision': 0.8793418647166362, 'recall': 0.89322191272052, 'f1': 0.8862275449101795, 'number': 1077}
23
+ - Overall Precision: 0.8481
24
+ - Overall Recall: 0.8823
25
+ - Overall F1: 0.8649
26
+ - Overall Accuracy: 0.7998
27
 
28
  ## Model description
29
 
 
48
  - seed: 42
49
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
  - lr_scheduler_type: linear
51
+ - training_steps: 500
52
  - mixed_precision_training: Native AMP
53
 
54
  ### Training results
55
 
56
+ | Training Loss | Epoch | Step | Validation Loss | Answer | Header | Question | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
57
+ |:-------------:|:-----:|:----:|:---------------:|:--------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
58
+ | 0.4341 | 10.53 | 200 | 0.8988 | {'precision': 0.8283166109253066, 'recall': 0.9094247246022031, 'f1': 0.8669778296382731, 'number': 817} | {'precision': 0.6630434782608695, 'recall': 0.5126050420168067, 'f1': 0.5781990521327014, 'number': 119} | {'precision': 0.8692170818505338, 'recall': 0.9071494893221913, 'f1': 0.8877782825988189, 'number': 1077} | 0.8429 | 0.8847 | 0.8633 | 0.7895 |
59
+ | 0.0382 | 21.05 | 400 | 1.1677 | {'precision': 0.8481735159817352, 'recall': 0.9094247246022031, 'f1': 0.8777318369757826, 'number': 817} | {'precision': 0.5725806451612904, 'recall': 0.5966386554621849, 'f1': 0.5843621399176955, 'number': 119} | {'precision': 0.8793418647166362, 'recall': 0.89322191272052, 'f1': 0.8862275449101795, 'number': 1077} | 0.8481 | 0.8823 | 0.8649 | 0.7998 |
 
 
 
 
 
 
 
 
 
 
60
 
61
 
62
  ### Framework versions
logs/events.out.tfevents.1670920837.ip-172-31-89-140.197324.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a9e61adc93b4b1f550e96fc38fa676dd2bffd642ed39f2c52ced6982ae8cad42
3
- size 5441
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fd2643e840fce59e2f8c25daea851d8889539b9d1e480c00494ec88c08c2801
3
+ size 5795
logs/events.out.tfevents.1670921146.ip-172-31-89-140.197324.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:514b10676ee95677ad56679f18cce01a7a05dcf9b802999622c80dda35e32120
3
+ size 544