Hugging Face's logo

hugsao123
/
XLM-R-fine-tuned-for-ner

Token Classification
Transformers
PyTorch
TensorBoard
xlm-roberta
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hugsao123 commited on
Commit
149679a
•
1 Parent(s): 1da0fae

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -14
README.md CHANGED
@@ -19,7 +19,7 @@ model-index:
19
  metrics:
20
  - name: F1
21
  type: f1
22
- value: 0.8446526439389049
23
  ---
24
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,8 +29,8 @@ should probably proofread and complete it, then remove this comment. -->
29
 
30
  This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the xtreme dataset.
31
  It achieves the following results on the evaluation set:
32
- - Loss: 0.5652
33
- - F1: 0.8447
34
 
35
  ## Model description
36
 
@@ -61,21 +61,21 @@ The following hyperparameters were used during training:
61
 
62
  | Training Loss | Epoch | Step | Validation Loss | F1 |
63
  |:-------------:|:-----:|:-----:|:---------------:|:------:|
64
- | 0.4183 | 1.0 | 2500 | 0.3474 | 0.7941 |
65
- | 0.3083 | 2.0 | 5000 | 0.2748 | 0.8059 |
66
- | 0.2291 | 3.0 | 7500 | 0.3024 | 0.8126 |
67
- | 0.1837 | 4.0 | 10000 | 0.3396 | 0.8282 |
68
- | 0.1476 | 5.0 | 12500 | 0.3557 | 0.8333 |
69
- | 0.1144 | 6.0 | 15000 | 0.4174 | 0.8387 |
70
- | 0.0869 | 7.0 | 17500 | 0.4431 | 0.8353 |
71
- | 0.0602 | 8.0 | 20000 | 0.4739 | 0.8355 |
72
- | 0.0383 | 9.0 | 22500 | 0.5389 | 0.8411 |
73
- | 0.0264 | 10.0 | 25000 | 0.5652 | 0.8447 |
74
 
75
 
76
  ### Framework versions
77
 
78
  - Transformers 4.15.0
79
- - Pytorch 1.8.2+cu111
80
  - Datasets 1.18.3
81
  - Tokenizers 0.10.3
 
19
  metrics:
20
  - name: F1
21
  type: f1
22
+ value: 0.8377982238973259
23
  ---
24
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
29
 
30
  This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the xtreme dataset.
31
  It achieves the following results on the evaluation set:
32
+ - Loss: 0.5679
33
+ - F1: 0.8378
34
 
35
  ## Model description
36
 
 
61
 
62
  | Training Loss | Epoch | Step | Validation Loss | F1 |
63
  |:-------------:|:-----:|:-----:|:---------------:|:------:|
64
+ | 0.4202 | 1.0 | 2500 | 0.3449 | 0.7963 |
65
+ | 0.2887 | 2.0 | 5000 | 0.2756 | 0.8057 |
66
+ | 0.2309 | 3.0 | 7500 | 0.2971 | 0.8040 |
67
+ | 0.1832 | 4.0 | 10000 | 0.3319 | 0.8167 |
68
+ | 0.1461 | 5.0 | 12500 | 0.3958 | 0.8350 |
69
+ | 0.114 | 6.0 | 15000 | 0.4087 | 0.8316 |
70
+ | 0.0833 | 7.0 | 17500 | 0.4320 | 0.8361 |
71
+ | 0.0614 | 8.0 | 20000 | 0.4885 | 0.8353 |
72
+ | 0.039 | 9.0 | 22500 | 0.5408 | 0.8390 |
73
+ | 0.0251 | 10.0 | 25000 | 0.5679 | 0.8378 |
74
 
75
 
76
  ### Framework versions
77
 
78
  - Transformers 4.15.0
79
+ - Pytorch 1.9.1
80
  - Datasets 1.18.3
81
  - Tokenizers 0.10.3