Hugging Face's logo

Aleksandar
/
electra-srb-ner

Token Classification
Transformers
PyTorch
Safetensors
electra
generated_from_trainer
Inference Endpoints
Model card Files Community
1
Aleksandar commited on
Commit
4b51dbc
•
1 Parent(s): 66caa2f

add model

Browse files
Files changed (3) hide show
  1. README.md +29 -13
  2. pytorch_model.bin +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -21,7 +21,7 @@ model_index:
21
  metric:
22
  name: Accuracy
23
  type: accuracy
24
- value: 0.9500777931962491
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,11 +31,11 @@ should probably proofread and complete it, then remove this comment. -->
31
 
32
  This model was trained from scratch on the wikiann dataset.
33
  It achieves the following results on the evaluation set:
34
- - Loss: 0.1859
35
- - Precision: 0.8742
36
- - Recall: 0.8907
37
- - F1: 0.8824
38
- - Accuracy: 0.9501
39
 
40
  ## Model description
41
 
@@ -60,16 +60,32 @@ The following hyperparameters were used during training:
60
  - seed: 42
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
- - num_epochs: 4
64
 
65
  ### Training results
66
 
67
- | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
68
- |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
69
- | 0.3627 | 1.0 | 625 | 0.2077 | 0.8382 | 0.8545 | 0.8463 | 0.9349 |
70
- | 0.1894 | 2.0 | 1250 | 0.1764 | 0.8640 | 0.8760 | 0.8700 | 0.9453 |
71
- | 0.1326 | 3.0 | 1875 | 0.1848 | 0.8618 | 0.8873 | 0.8744 | 0.9473 |
72
- | 0.0712 | 4.0 | 2500 | 0.1859 | 0.8742 | 0.8907 | 0.8824 | 0.9501 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
73
 
74
 
75
  ### Framework versions
21
  metric:
22
  name: Accuracy
23
  type: accuracy
24
+ value: 0.9568394937134688
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
31
 
32
  This model was trained from scratch on the wikiann dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 0.3406
35
+ - Precision: 0.8934
36
+ - Recall: 0.9087
37
+ - F1: 0.9010
38
+ - Accuracy: 0.9568
39
 
40
  ## Model description
41
 
60
  - seed: 42
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
+ - num_epochs: 20
64
 
65
  ### Training results
66
 
67
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
68
+ |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
69
+ | 0.3686 | 1.0 | 625 | 0.2108 | 0.8326 | 0.8494 | 0.8409 | 0.9335 |
70
+ | 0.1886 | 2.0 | 1250 | 0.1784 | 0.8737 | 0.8713 | 0.8725 | 0.9456 |
71
+ | 0.1323 | 3.0 | 1875 | 0.1805 | 0.8654 | 0.8870 | 0.8760 | 0.9468 |
72
+ | 0.0675 | 4.0 | 2500 | 0.2018 | 0.8736 | 0.8880 | 0.8807 | 0.9502 |
73
+ | 0.0425 | 5.0 | 3125 | 0.2162 | 0.8818 | 0.8945 | 0.8881 | 0.9512 |
74
+ | 0.0343 | 6.0 | 3750 | 0.2492 | 0.8790 | 0.8928 | 0.8859 | 0.9513 |
75
+ | 0.0253 | 7.0 | 4375 | 0.2562 | 0.8821 | 0.9006 | 0.8912 | 0.9525 |
76
+ | 0.0142 | 8.0 | 5000 | 0.2788 | 0.8807 | 0.9013 | 0.8909 | 0.9524 |
77
+ | 0.0114 | 9.0 | 5625 | 0.2793 | 0.8861 | 0.9002 | 0.8931 | 0.9534 |
78
+ | 0.0095 | 10.0 | 6250 | 0.2967 | 0.8887 | 0.9034 | 0.8960 | 0.9550 |
79
+ | 0.008 | 11.0 | 6875 | 0.2993 | 0.8899 | 0.9067 | 0.8982 | 0.9556 |
80
+ | 0.0048 | 12.0 | 7500 | 0.3215 | 0.8887 | 0.9038 | 0.8962 | 0.9545 |
81
+ | 0.0034 | 13.0 | 8125 | 0.3242 | 0.8897 | 0.9068 | 0.8982 | 0.9554 |
82
+ | 0.003 | 14.0 | 8750 | 0.3311 | 0.8884 | 0.9085 | 0.8983 | 0.9559 |
83
+ | 0.0025 | 15.0 | 9375 | 0.3383 | 0.8943 | 0.9062 | 0.9002 | 0.9562 |
84
+ | 0.0011 | 16.0 | 10000 | 0.3346 | 0.8941 | 0.9112 | 0.9026 | 0.9574 |
85
+ | 0.0015 | 17.0 | 10625 | 0.3362 | 0.8944 | 0.9081 | 0.9012 | 0.9567 |
86
+ | 0.001 | 18.0 | 11250 | 0.3464 | 0.8877 | 0.9100 | 0.8987 | 0.9559 |
87
+ | 0.0012 | 19.0 | 11875 | 0.3415 | 0.8944 | 0.9089 | 0.9016 | 0.9568 |
88
+ | 0.0005 | 20.0 | 12500 | 0.3406 | 0.8934 | 0.9087 | 0.9010 | 0.9568 |
89
 
90
 
91
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e704d485234a893ecf737c6e250580e9dcf0ef3e5a1e200e500e673215c275a4
3
  size 435672753
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86592cace69a7de3e92e1086e0e7118efb547425449d8a48504463299656d55d
3
  size 435672753
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b46a59921cb24bd5481f53740647d36b6e2bdc137016ef8859eb3e9045cdee26
3
  size 2671
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:128fb9fd2730730652ec5f5172eb8b404c12bfe8727a602e88dd79e5b74c32bb
3
  size 2671