Hugging Face's logo

Tirendaz
/
roberta-base-NER

Token Classification
Transformers
PyTorch
English
xlm-roberta
Eval Results
Inference Endpoints
Model card Files Community
1
Tirendaz commited on
Commit
060ba85
•
1 Parent(s): 2e78894

End of training

Browse files
Files changed (1) hide show
  1. README.md +24 -8
README.md CHANGED
@@ -6,7 +6,10 @@ tags:
6
  datasets:
7
  - xtreme
8
  metrics:
 
 
9
  - f1
 
10
  model-index:
11
  - name: roberta-base-NER
12
  results:
@@ -20,9 +23,18 @@ model-index:
20
  split: validation
21
  args: PAN-X.en
22
  metrics:
 
 
 
 
 
 
23
  - name: F1
24
  type: f1
25
- value: 0.7749031543995573
 
 
 
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +44,11 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the xtreme dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.3068
36
- - F1: 0.7749
 
 
 
37
 
38
  ## Model description
39
 
@@ -58,14 +73,15 @@ The following hyperparameters were used during training:
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
- - num_epochs: 2
62
 
63
  ### Training results
64
 
65
- | Training Loss | Epoch | Step | Validation Loss | F1 |
66
- |:-------------:|:-----:|:----:|:---------------:|:------:|
67
- | No log | 1.0 | 417 | 0.3361 | 0.7477 |
68
- | 0.5196 | 2.0 | 834 | 0.3068 | 0.7749 |
 
69
 
70
 
71
  ### Framework versions
 
6
  datasets:
7
  - xtreme
8
  metrics:
9
+ - precision
10
+ - recall
11
  - f1
12
+ - accuracy
13
  model-index:
14
  - name: roberta-base-NER
15
  results:
 
23
  split: validation
24
  args: PAN-X.en
25
  metrics:
26
+ - name: Precision
27
+ type: precision
28
+ value: 0.7779299014238773
29
+ - name: Recall
30
+ type: recall
31
+ value: 0.8005071851225697
32
  - name: F1
33
  type: f1
34
+ value: 0.7890570754061935
35
+ - name: Accuracy
36
+ type: accuracy
37
+ value: 0.912818107767877
38
  ---
39
 
40
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
44
 
45
  This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the xtreme dataset.
46
  It achieves the following results on the evaluation set:
47
+ - Loss: 0.2988
48
+ - Precision: 0.7779
49
+ - Recall: 0.8005
50
+ - F1: 0.7891
51
+ - Accuracy: 0.9128
52
 
53
  ## Model description
54
 
 
73
  - seed: 42
74
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
75
  - lr_scheduler_type: linear
76
+ - num_epochs: 3
77
 
78
  ### Training results
79
 
80
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
+ | No log | 1.0 | 417 | 0.3344 | 0.7337 | 0.7732 | 0.7529 | 0.9019 |
83
+ | 0.5039 | 2.0 | 834 | 0.2995 | 0.7588 | 0.7932 | 0.7756 | 0.9104 |
84
+ | 0.2841 | 3.0 | 1251 | 0.2988 | 0.7779 | 0.8005 | 0.7891 | 0.9128 |
85
 
86
 
87
  ### Framework versions