MrSemyon12 commited on
Commit
0fde76d
1 Parent(s): 17efc23

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +40 -11
README.md CHANGED
@@ -4,9 +4,34 @@ tags:
4
  - generated_from_trainer
5
  datasets:
6
  - skript
 
 
 
 
 
7
  model-index:
8
  - name: wikineural-multilingual-ner-finetuned-ner
9
- results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  ---
11
 
12
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,16 +41,11 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [Babelscape/wikineural-multilingual-ner](https://huggingface.co/Babelscape/wikineural-multilingual-ner) on the skript dataset.
18
  It achieves the following results on the evaluation set:
19
- - eval_loss: 0.1202
20
- - eval_precision: 0.8561
21
- - eval_recall: 0.8932
22
- - eval_f1: 0.8743
23
- - eval_accuracy: 0.9637
24
- - eval_runtime: 235.7895
25
- - eval_samples_per_second: 4.334
26
- - eval_steps_per_second: 0.271
27
- - epoch: 2.0
28
- - step: 596
29
 
30
  ## Model description
31
 
@@ -52,6 +72,15 @@ The following hyperparameters were used during training:
52
  - lr_scheduler_type: linear
53
  - num_epochs: 3
54
 
 
 
 
 
 
 
 
 
 
55
  ### Framework versions
56
 
57
  - Transformers 4.20.1
 
4
  - generated_from_trainer
5
  datasets:
6
  - skript
7
+ metrics:
8
+ - precision
9
+ - recall
10
+ - f1
11
+ - accuracy
12
  model-index:
13
  - name: wikineural-multilingual-ner-finetuned-ner
14
+ results:
15
+ - task:
16
+ name: Token Classification
17
+ type: token-classification
18
+ dataset:
19
+ name: skript
20
+ type: skript
21
+ args: conll2003
22
+ metrics:
23
+ - name: Precision
24
+ type: precision
25
+ value: 0.9013505175841503
26
+ - name: Recall
27
+ type: recall
28
+ value: 0.9308318584070796
29
+ - name: F1
30
+ type: f1
31
+ value: 0.9158539983282251
32
+ - name: Accuracy
33
+ type: accuracy
34
+ value: 0.9658385093167702
35
  ---
36
 
37
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
41
 
42
  This model is a fine-tuned version of [Babelscape/wikineural-multilingual-ner](https://huggingface.co/Babelscape/wikineural-multilingual-ner) on the skript dataset.
43
  It achieves the following results on the evaluation set:
44
+ - Loss: 0.1219
45
+ - Precision: 0.9014
46
+ - Recall: 0.9308
47
+ - F1: 0.9159
48
+ - Accuracy: 0.9658
 
 
 
 
 
49
 
50
  ## Model description
51
 
 
72
  - lr_scheduler_type: linear
73
  - num_epochs: 3
74
 
75
+ ### Training results
76
+
77
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
78
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
79
+ | No log | 1.0 | 298 | 0.1208 | 0.9016 | 0.8988 | 0.9002 | 0.9604 |
80
+ | 0.118 | 2.0 | 596 | 0.1152 | 0.9016 | 0.9210 | 0.9112 | 0.9645 |
81
+ | 0.118 | 3.0 | 894 | 0.1219 | 0.9014 | 0.9308 | 0.9159 | 0.9658 |
82
+
83
+
84
  ### Framework versions
85
 
86
  - Transformers 4.20.1