Hugging Face's logo

Luciano
/
xlm-roberta-large-finetuned-lener-br

Token Classification
Transformers
PyTorch
TensorBoard
Safetensors
Portuguese
xlm-roberta
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
5
Luciano commited on
Commit
6bfa4d3
•
1 Parent(s): 75725e0

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +24 -110
README.md CHANGED
@@ -24,103 +24,16 @@ model-index:
24
  metrics:
25
  - name: Precision
26
  type: precision
27
- value: 0.8545767716535433
28
  - name: Recall
29
  type: recall
30
- value: 0.8976479710519514
31
  - name: F1
32
  type: f1
33
- value: 0.8755830076893987
34
  - name: Accuracy
35
  type: accuracy
36
- value: 0.979126510974644
37
- - task:
38
- type: token-classification
39
- name: Token Classification
40
- dataset:
41
- name: lener_br
42
- type: lener_br
43
- config: lener_br
44
- split: test
45
- metrics:
46
- - name: Accuracy
47
- type: accuracy
48
- value: 0.9842606502473917
49
- verified: true
50
- - name: Precision
51
- type: precision
52
- value: 0.9880888491353608
53
- verified: true
54
- - name: Recall
55
- type: recall
56
- value: 0.9863977974551678
57
- verified: true
58
- - name: F1
59
- type: f1
60
- value: 0.9872425991435487
61
- verified: true
62
- - name: loss
63
- type: loss
64
- value: 0.12697908282279968
65
- verified: true
66
- - task:
67
- type: token-classification
68
- name: Token Classification
69
- dataset:
70
- name: lener_br
71
- type: lener_br
72
- config: lener_br
73
- split: validation
74
- metrics:
75
- - name: Accuracy
76
- type: accuracy
77
- value: 0.979126510974644
78
- verified: true
79
- - name: Precision
80
- type: precision
81
- value: 0.9846948786709399
82
- verified: true
83
- - name: Recall
84
- type: recall
85
- value: 0.9839386958155646
86
- verified: true
87
- - name: F1
88
- type: f1
89
- value: 0.9843166420124387
90
- verified: true
91
- - name: loss
92
- type: loss
93
- value: 0.17586557567119598
94
- verified: true
95
- - task:
96
- type: token-classification
97
- name: Token Classification
98
- dataset:
99
- name: lener_br
100
- type: lener_br
101
- config: lener_br
102
- split: train
103
- metrics:
104
- - name: Accuracy
105
- type: accuracy
106
- value: 0.9986508230532317
107
- verified: true
108
- - name: Precision
109
- type: precision
110
- value: 0.9980332928982356
111
- verified: true
112
- - name: Recall
113
- type: recall
114
- value: 0.998726011303645
115
- verified: true
116
- - name: F1
117
- type: f1
118
- value: 0.998379531941543
119
- verified: true
120
- - name: loss
121
- type: loss
122
- value: 0.002737082075327635
123
- verified: true
124
  ---
125
 
126
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -131,10 +44,10 @@ should probably proofread and complete it, then remove this comment. -->
131
  This model is a fine-tuned version of [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) on the lener_br dataset.
132
  It achieves the following results on the evaluation set:
133
  - Loss: nan
134
- - Precision: 0.8546
135
- - Recall: 0.8976
136
- - F1: 0.8756
137
- - Accuracy: 0.9791
138
 
139
  ## Model description
140
 
@@ -160,26 +73,27 @@ The following hyperparameters were used during training:
160
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
161
  - lr_scheduler_type: linear
162
  - num_epochs: 15
 
163
 
164
  ### Training results
165
 
166
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
167
  |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
168
- | 0.0836 | 1.0 | 3914 | nan | 0.5735 | 0.8348 | 0.6799 | 0.9526 |
169
- | 0.0664 | 2.0 | 7828 | nan | 0.8153 | 0.8315 | 0.8233 | 0.9658 |
170
- | 0.0505 | 3.0 | 11742 | nan | 0.6885 | 0.9147 | 0.7857 | 0.9644 |
171
- | 0.1165 | 4.0 | 15656 | nan | 0.7572 | 0.8067 | 0.7811 | 0.9641 |
172
- | 0.0206 | 5.0 | 19570 | nan | 0.8678 | 0.8770 | 0.8723 | 0.9774 |
173
- | 0.02 | 6.0 | 23484 | nan | 0.7285 | 0.8907 | 0.8015 | 0.9669 |
174
- | 0.0248 | 7.0 | 27398 | nan | 0.8717 | 0.9095 | 0.8902 | 0.9793 |
175
- | 0.0223 | 8.0 | 31312 | nan | 0.8407 | 0.8801 | 0.8600 | 0.9766 |
176
- | 0.0084 | 9.0 | 35226 | nan | 0.8354 | 0.8684 | 0.8516 | 0.9705 |
177
- | 0.0067 | 10.0 | 39140 | nan | 0.8312 | 0.9062 | 0.8671 | 0.9753 |
178
- | 0.006 | 11.0 | 43054 | nan | 0.8866 | 0.8953 | 0.8909 | 0.9784 |
179
- | 0.0058 | 12.0 | 46968 | nan | 0.8961 | 0.8987 | 0.8974 | 0.9807 |
180
- | 0.0062 | 13.0 | 50882 | nan | 0.8360 | 0.8785 | 0.8567 | 0.9783 |
181
- | 0.0053 | 14.0 | 54796 | nan | 0.8327 | 0.8749 | 0.8533 | 0.9782 |
182
- | 0.003 | 15.0 | 58710 | nan | 0.8546 | 0.8976 | 0.8756 | 0.9791 |
183
 
184
 
185
  ### Framework versions
 
24
  metrics:
25
  - name: Precision
26
  type: precision
27
+ value: 0.8762313715584744
28
  - name: Recall
29
  type: recall
30
+ value: 0.8966141121736882
31
  - name: F1
32
  type: f1
33
+ value: 0.8863055697496168
34
  - name: Accuracy
35
  type: accuracy
36
+ value: 0.979500052295785
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
37
  ---
38
 
39
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
44
  This model is a fine-tuned version of [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) on the lener_br dataset.
45
  It achieves the following results on the evaluation set:
46
  - Loss: nan
47
+ - Precision: 0.8762
48
+ - Recall: 0.8966
49
+ - F1: 0.8863
50
+ - Accuracy: 0.9795
51
 
52
  ## Model description
53
 
 
73
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
74
  - lr_scheduler_type: linear
75
  - num_epochs: 15
76
+ - mixed_precision_training: Native AMP
77
 
78
  ### Training results
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
  |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
+ | 0.0785 | 1.0 | 3914 | nan | 0.7119 | 0.8410 | 0.7711 | 0.9658 |
83
+ | 0.076 | 2.0 | 7828 | nan | 0.8397 | 0.8679 | 0.8536 | 0.9740 |
84
+ | 0.0434 | 3.0 | 11742 | nan | 0.8545 | 0.8666 | 0.8605 | 0.9693 |
85
+ | 0.022 | 4.0 | 15656 | nan | 0.8293 | 0.8573 | 0.8431 | 0.9652 |
86
+ | 0.0284 | 5.0 | 19570 | nan | 0.8789 | 0.8571 | 0.8678 | 0.9776 |
87
+ | 0.029 | 6.0 | 23484 | nan | 0.8521 | 0.8788 | 0.8653 | 0.9771 |
88
+ | 0.0227 | 7.0 | 27398 | nan | 0.7648 | 0.8873 | 0.8215 | 0.9686 |
89
+ | 0.0219 | 8.0 | 31312 | nan | 0.8609 | 0.9026 | 0.8813 | 0.9780 |
90
+ | 0.0121 | 9.0 | 35226 | nan | 0.8746 | 0.8979 | 0.8861 | 0.9812 |
91
+ | 0.0087 | 10.0 | 39140 | nan | 0.8829 | 0.8827 | 0.8828 | 0.9808 |
92
+ | 0.0081 | 11.0 | 43054 | nan | 0.8740 | 0.8749 | 0.8745 | 0.9765 |
93
+ | 0.0058 | 12.0 | 46968 | nan | 0.8838 | 0.8842 | 0.8840 | 0.9788 |
94
+ | 0.0044 | 13.0 | 50882 | nan | 0.869 | 0.8984 | 0.8835 | 0.9788 |
95
+ | 0.002 | 14.0 | 54796 | nan | 0.8762 | 0.8966 | 0.8863 | 0.9795 |
96
+ | 0.0017 | 15.0 | 58710 | nan | 0.8729 | 0.8982 | 0.8854 | 0.9791 |
97
 
98
 
99
  ### Framework versions