Hugging Face's logo

dl-ru
/
rubert-electra-srl

Token Classification
Transformers
PyTorch
Safetensors
electra
Generated from Trainer
Inference Endpoints
Model card Files Community
dl-ru commited on
Commit
e3db370
•
1 Parent(s): 1bdd317

New version with explicit predicate marking

Browse files
Files changed (3) hide show
  1. README.md +58 -58
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -15,67 +15,67 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [ai-forever/ruElectra-medium](https://huggingface.co/ai-forever/ruElectra-medium) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.0564
19
- - Addressee Precision: 0.8710
20
- - Addressee Recall: 0.9153
21
- - Addressee F1: 0.8926
22
- - Addressee Number: 59
23
  - Benefactive Precision: 0.0
24
  - Benefactive Recall: 0.0
25
  - Benefactive F1: 0.0
26
- - Benefactive Number: 8
27
- - Causator Precision: 0.9007
28
- - Causator Recall: 0.9379
29
- - Causator F1: 0.9189
30
- - Causator Number: 145
31
- - Cause Precision: 0.8491
32
- - Cause Recall: 0.7895
33
- - Cause F1: 0.8182
34
- - Cause Number: 114
35
- - Contrsubject Precision: 0.872
36
- - Contrsubject Recall: 0.9008
37
- - Contrsubject F1: 0.8862
38
- - Contrsubject Number: 121
39
- - Deliberative Precision: 0.7439
40
- - Deliberative Recall: 0.9385
41
- - Deliberative F1: 0.8299
42
- - Deliberative Number: 65
43
  - Destinative Precision: 1.0
44
- - Destinative Recall: 0.5238
45
- - Destinative F1: 0.6875
46
- - Destinative Number: 21
47
  - Directivefinal Precision: 1.0
48
- - Directivefinal Recall: 0.7
49
- - Directivefinal F1: 0.8235
50
- - Directivefinal Number: 10
51
- - Experiencer Precision: 0.9132
52
- - Experiencer Recall: 0.9374
53
- - Experiencer F1: 0.9252
54
- - Experiencer Number: 1055
55
- - Instrument Precision: 0.8409
56
- - Instrument Recall: 0.7255
57
- - Instrument F1: 0.7789
58
- - Instrument Number: 51
 
 
 
 
 
 
 
 
 
 
59
  - Limitative Precision: 0.0
60
  - Limitative Recall: 0.0
61
- - Limitative F1: 0.0
62
- - Limitative Number: 3
63
- - Object Precision: 0.9449
64
- - Object Recall: 0.9389
65
- - Object F1: 0.9419
66
- - Object Number: 1898
67
- - Overall Precision: 0.9210
68
- - Overall Recall: 0.9228
69
- - Overall F1: 0.9219
70
- - Overall Accuracy: 0.9855
71
- - Mediative Number: 0.0
72
- - Mediative F1: 0.0
73
- - Mediative Precision: 0.0
74
- - Mediative Recall: 0.0
75
- - Directiveinitial Number: 0.0
76
  - Directiveinitial F1: 0.0
 
77
  - Directiveinitial Precision: 0.0
78
  - Directiveinitial Recall: 0.0
 
 
 
 
79
 
80
  ## Model description
81
 
@@ -98,8 +98,8 @@ The following hyperparameters were used during training:
98
  - train_batch_size: 1
99
  - eval_batch_size: 1
100
  - seed: 708526
101
- - gradient_accumulation_steps: 4
102
- - total_train_batch_size: 4
103
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
104
  - lr_scheduler_type: linear
105
  - lr_scheduler_warmup_ratio: 0.21
@@ -108,11 +108,11 @@ The following hyperparameters were used during training:
108
 
109
  ### Training results
110
 
111
- | Training Loss | Epoch | Step | Validation Loss | Addressee Precision | Addressee Recall | Addressee F1 | Addressee Number | Benefactive Precision | Benefactive Recall | Benefactive F1 | Benefactive Number | Causator Precision | Causator Recall | Causator F1 | Causator Number | Cause Precision | Cause Recall | Cause F1 | Cause Number | Contrsubject Precision | Contrsubject Recall | Contrsubject F1 | Contrsubject Number | Deliberative Precision | Deliberative Recall | Deliberative F1 | Deliberative Number | Destinative Precision | Destinative Recall | Destinative F1 | Destinative Number | Directivefinal Precision | Directivefinal Recall | Directivefinal F1 | Directivefinal Number | Experiencer Precision | Experiencer Recall | Experiencer F1 | Experiencer Number | Instrument Precision | Instrument Recall | Instrument F1 | Instrument Number | Limitative Precision | Limitative Recall | Limitative F1 | Limitative Number | Object Precision | Object Recall | Object F1 | Object Number | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy | Mediative Number | Mediative F1 | Mediative Precision | Mediative Recall | Directiveinitial Number | Directiveinitial F1 | Directiveinitial Precision | Directiveinitial Recall |
112
- |:-------------:|:-----:|:----:|:---------------:|:-------------------:|:----------------:|:------------:|:----------------:|:---------------------:|:------------------:|:--------------:|:------------------:|:------------------:|:---------------:|:-----------:|:---------------:|:---------------:|:------------:|:--------:|:------------:|:----------------------:|:-------------------:|:---------------:|:-------------------:|:----------------------:|:-------------------:|:---------------:|:-------------------:|:---------------------:|:------------------:|:--------------:|:------------------:|:------------------------:|:---------------------:|:-----------------:|:---------------------:|:---------------------:|:------------------:|:--------------:|:------------------:|:--------------------:|:-----------------:|:-------------:|:-----------------:|:--------------------:|:-----------------:|:-------------:|:-----------------:|:----------------:|:-------------:|:---------:|:-------------:|:-----------------:|:--------------:|:----------:|:----------------:|:----------------:|:------------:|:-------------------:|:----------------:|:-----------------------:|:-------------------:|:--------------------------:|:-----------------------:|
113
- | 0.574 | 1.0 | 2942 | 0.5853 | 0.0 | 0.0 | 0.0 | 59 | 0.0 | 0.0 | 0.0 | 8 | 0.0 | 0.0 | 0.0 | 145 | 0.0 | 0.0 | 0.0 | 114 | 0.0 | 0.0 | 0.0 | 121 | 0.0 | 0.0 | 0.0 | 65 | 0.0 | 0.0 | 0.0 | 21 | 0.0 | 0.0 | 0.0 | 10 | 0.0 | 0.0 | 0.0 | 1055 | 0.0 | 0.0 | 0.0 | 51 | 0.0 | 0.0 | 0.0 | 3 | 0.0 | 0.0 | 0.0 | 1898 | 0.0 | 0.0 | 0.0 | 0.8893 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
114
- | 0.1625 | 2.0 | 5884 | 0.1573 | 0.5714 | 0.8136 | 0.6713 | 59 | 0.0 | 0.0 | 0.0 | 8 | 0.6966 | 0.8552 | 0.7678 | 145 | 0.3186 | 0.6316 | 0.4235 | 114 | 0.6875 | 0.4545 | 0.5473 | 121 | 0.0 | 0.0 | 0.0 | 65 | 0.0 | 0.0 | 0.0 | 21 | 0.0 | 0.0 | 0.0 | 10 | 0.8504 | 0.8246 | 0.8373 | 1055 | 0.4769 | 0.6078 | 0.5345 | 51 | 0.0 | 0.0 | 0.0 | 3 | 0.8923 | 0.8161 | 0.8525 | 1898 | 0.8104 | 0.7744 | 0.7920 | 0.9634 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
115
- | 0.0838 | 3.0 | 8826 | 0.0564 | 0.8710 | 0.9153 | 0.8926 | 59 | 0.0 | 0.0 | 0.0 | 8 | 0.9007 | 0.9379 | 0.9189 | 145 | 0.8491 | 0.7895 | 0.8182 | 114 | 0.872 | 0.9008 | 0.8862 | 121 | 0.7439 | 0.9385 | 0.8299 | 65 | 1.0 | 0.5238 | 0.6875 | 21 | 1.0 | 0.7 | 0.8235 | 10 | 0.9132 | 0.9374 | 0.9252 | 1055 | 0.8409 | 0.7255 | 0.7789 | 51 | 0.0 | 0.0 | 0.0 | 3 | 0.9449 | 0.9389 | 0.9419 | 1898 | 0.9210 | 0.9228 | 0.9219 | 0.9855 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
116
 
117
 
118
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [ai-forever/ruElectra-medium](https://huggingface.co/ai-forever/ruElectra-medium) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.0448
19
+ - Addressee Precision: 0.9583
20
+ - Addressee Recall: 1.0
21
+ - Addressee F1: 0.9787
22
+ - Addressee Number: 23
23
  - Benefactive Precision: 0.0
24
  - Benefactive Recall: 0.0
25
  - Benefactive F1: 0.0
26
+ - Benefactive Number: 2
27
+ - Causator Precision: 0.9773
28
+ - Causator Recall: 0.9773
29
+ - Causator F1: 0.9773
30
+ - Causator Number: 44
31
+ - Cause Precision: 0.9259
32
+ - Cause Recall: 0.7143
33
+ - Cause F1: 0.8065
34
+ - Cause Number: 35
35
+ - Contrsubject Precision: 1.0
36
+ - Contrsubject Recall: 0.9429
37
+ - Contrsubject F1: 0.9706
38
+ - Contrsubject Number: 35
39
+ - Deliberative Precision: 0.9231
40
+ - Deliberative Recall: 1.0
41
+ - Deliberative F1: 0.9600
42
+ - Deliberative Number: 24
43
  - Destinative Precision: 1.0
44
+ - Destinative Recall: 1.0
45
+ - Destinative F1: 1.0
46
+ - Destinative Number: 7
47
  - Directivefinal Precision: 1.0
48
+ - Directivefinal Recall: 1.0
49
+ - Directivefinal F1: 1.0
50
+ - Directivefinal Number: 1
51
+ - Experiencer Precision: 0.9030
52
+ - Experiencer Recall: 0.9441
53
+ - Experiencer F1: 0.9231
54
+ - Experiencer Number: 286
55
+ - Instrument Precision: 0.9
56
+ - Instrument Recall: 0.9
57
+ - Instrument F1: 0.9
58
+ - Instrument Number: 10
59
+ - Object Precision: 0.9484
60
+ - Object Recall: 0.9519
61
+ - Object F1: 0.9502
62
+ - Object Number: 541
63
+ - Overall Precision: 0.9369
64
+ - Overall Recall: 0.9425
65
+ - Overall F1: 0.9397
66
+ - Overall Accuracy: 0.9883
67
+ - Limitative F1: 0.0
68
+ - Limitative Number: 0.0
69
  - Limitative Precision: 0.0
70
  - Limitative Recall: 0.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
71
  - Directiveinitial F1: 0.0
72
+ - Directiveinitial Number: 0.0
73
  - Directiveinitial Precision: 0.0
74
  - Directiveinitial Recall: 0.0
75
+ - Mediative F1: 0.0
76
+ - Mediative Number: 0.0
77
+ - Mediative Precision: 0.0
78
+ - Mediative Recall: 0.0
79
 
80
  ## Model description
81
 
 
98
  - train_batch_size: 1
99
  - eval_batch_size: 1
100
  - seed: 708526
101
+ - gradient_accumulation_steps: 8
102
+ - total_train_batch_size: 8
103
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
104
  - lr_scheduler_type: linear
105
  - lr_scheduler_warmup_ratio: 0.21
 
108
 
109
  ### Training results
110
 
111
+ | Training Loss | Epoch | Step | Validation Loss | Addressee Precision | Addressee Recall | Addressee F1 | Addressee Number | Benefactive Precision | Benefactive Recall | Benefactive F1 | Benefactive Number | Causator Precision | Causator Recall | Causator F1 | Causator Number | Cause Precision | Cause Recall | Cause F1 | Cause Number | Contrsubject Precision | Contrsubject Recall | Contrsubject F1 | Contrsubject Number | Deliberative Precision | Deliberative Recall | Deliberative F1 | Deliberative Number | Destinative Precision | Destinative Recall | Destinative F1 | Destinative Number | Directivefinal Precision | Directivefinal Recall | Directivefinal F1 | Directivefinal Number | Experiencer Precision | Experiencer Recall | Experiencer F1 | Experiencer Number | Instrument Precision | Instrument Recall | Instrument F1 | Instrument Number | Object Precision | Object Recall | Object F1 | Object Number | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy | Limitative F1 | Limitative Number | Limitative Precision | Limitative Recall | Directiveinitial F1 | Directiveinitial Number | Directiveinitial Precision | Directiveinitial Recall | Mediative F1 | Mediative Number | Mediative Precision | Mediative Recall |
112
+ |:-------------:|:-----:|:----:|:---------------:|:-------------------:|:----------------:|:------------:|:----------------:|:---------------------:|:------------------:|:--------------:|:------------------:|:------------------:|:---------------:|:-----------:|:---------------:|:---------------:|:------------:|:--------:|:------------:|:----------------------:|:-------------------:|:---------------:|:-------------------:|:----------------------:|:-------------------:|:---------------:|:-------------------:|:---------------------:|:------------------:|:--------------:|:------------------:|:------------------------:|:---------------------:|:-----------------:|:---------------------:|:---------------------:|:------------------:|:--------------:|:------------------:|:--------------------:|:-----------------:|:-------------:|:-----------------:|:----------------:|:-------------:|:---------:|:-------------:|:-----------------:|:--------------:|:----------:|:----------------:|:-------------:|:-----------------:|:--------------------:|:-----------------:|:-------------------:|:-----------------------:|:--------------------------:|:-----------------------:|:------------:|:----------------:|:-------------------:|:----------------:|
113
+ | 0.1548 | 1.0 | 1471 | 0.1755 | 0.6667 | 0.5217 | 0.5854 | 23 | 0.0 | 0.0 | 0.0 | 2 | 0.5714 | 0.8182 | 0.6729 | 44 | 0.5217 | 0.3429 | 0.4138 | 35 | 0.4103 | 0.4571 | 0.4324 | 35 | 0.0 | 0.0 | 0.0 | 24 | 0.0 | 0.0 | 0.0 | 7 | 0.0 | 0.0 | 0.0 | 1 | 0.8645 | 0.8252 | 0.8444 | 286 | 0.0 | 0.0 | 0.0 | 10 | 0.7711 | 0.8965 | 0.8291 | 541 | 0.7627 | 0.7907 | 0.7764 | 0.9582 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
114
+ | 0.1209 | 2.0 | 2942 | 0.0797 | 0.9130 | 0.9130 | 0.9130 | 23 | 0.0 | 0.0 | 0.0 | 2 | 0.9348 | 0.9773 | 0.9556 | 44 | 0.8462 | 0.6286 | 0.7213 | 35 | 0.8889 | 0.9143 | 0.9014 | 35 | 0.75 | 0.875 | 0.8077 | 24 | 1.0 | 0.4286 | 0.6 | 7 | 0.0 | 0.0 | 0.0 | 1 | 0.8993 | 0.8741 | 0.8865 | 286 | 0.875 | 0.7 | 0.7778 | 10 | 0.9336 | 0.9094 | 0.9213 | 541 | 0.9138 | 0.8839 | 0.8986 | 0.9808 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
115
+ | 0.0559 | 3.0 | 4413 | 0.0448 | 0.9583 | 1.0 | 0.9787 | 23 | 0.0 | 0.0 | 0.0 | 2 | 0.9773 | 0.9773 | 0.9773 | 44 | 0.9259 | 0.7143 | 0.8065 | 35 | 1.0 | 0.9429 | 0.9706 | 35 | 0.9231 | 1.0 | 0.9600 | 24 | 1.0 | 1.0 | 1.0 | 7 | 1.0 | 1.0 | 1.0 | 1 | 0.9030 | 0.9441 | 0.9231 | 286 | 0.9 | 0.9 | 0.9 | 10 | 0.9484 | 0.9519 | 0.9502 | 541 | 0.9369 | 0.9425 | 0.9397 | 0.9883 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
116
 
117
 
118
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8dc983e23ebf1a46a93b9ffb6bb8dfcc4f96b632c2282ab78edd817e53106b5c
3
  size 340184276
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8785a743b89774ab6f9dd50c0335b7a1c0940b89d59b792a79c2b6073f1b5beb
3
  size 340184276
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e293be6da178e0dad7a21799fcc806409ec27abe94b264bcf829fab4f996651
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38121bb19930abbe9fe43c2882365fe3897e692d8af4dabe0178c24e5df8ed1b
3
  size 5240