Hugging Face's logo

Alizee
/
xlm-roberta-large-finetuned-wikiner-fr

Token Classification
Transformers
Safetensors
French
xlm-roberta
Inference Endpoints
Model card Files Community
Alizee commited on
Commit
e6cf178
•
1 Parent(s): 49d37c5

cosine_lr-1.5e-05_ep-3_bs-32-End_of_training

Browse files
Files changed (3) hide show
  1. README.md +42 -42
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -4,10 +4,10 @@ base_model: xlm-roberta-large
4
  tags:
5
  - generated_from_trainer
6
  metrics:
7
- - accuracy
8
- - f1
9
  - precision
10
  - recall
 
 
11
  model-index:
12
  - name: xlm-roberta-large-finetuned-wikiner-fr
13
  results: []
@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) on the Alizee/wikiner_fr_mixed_caps dataset.
22
  It achieves the following results on the evaluation set:
23
- - Accuracy: 0.9854
24
- - F1: 0.8928
25
- - Loss: 0.0507
26
- - Precision: 0.8851
27
- - Recall: 0.9007
28
 
29
  ## Model description
30
 
@@ -43,7 +43,7 @@ More information needed
43
  ### Training hyperparameters
44
 
45
  The following hyperparameters were used during training:
46
- - learning_rate: 1e-05
47
  - train_batch_size: 32
48
  - eval_batch_size: 32
49
  - seed: 42
@@ -54,40 +54,40 @@ The following hyperparameters were used during training:
54
 
55
  ### Training results
56
 
57
- | Training Loss | Epoch | Step | Accuracy | F1 | Validation Loss | Precision | Recall |
58
- |:-------------:|:-----:|:-----:|:--------:|:------:|:---------------:|:---------:|:------:|
59
- | 0.0977 | 0.1 | 374 | 0.9759 | 0.8002 | 0.0796 | 0.7787 | 0.8229 |
60
- | 0.074 | 0.2 | 748 | 0.9783 | 0.8178 | 0.0727 | 0.8010 | 0.8353 |
61
- | 0.0721 | 0.3 | 1122 | 0.9792 | 0.8283 | 0.0660 | 0.8146 | 0.8424 |
62
- | 0.0632 | 0.4 | 1496 | 0.9812 | 0.8571 | 0.0625 | 0.8460 | 0.8685 |
63
- | 0.0604 | 0.5 | 1870 | 0.9811 | 0.8587 | 0.0604 | 0.8455 | 0.8723 |
64
- | 0.0592 | 0.6 | 2244 | 0.9824 | 0.8669 | 0.0572 | 0.8585 | 0.8755 |
65
- | 0.0584 | 0.7 | 2618 | 0.9824 | 0.8706 | 0.0558 | 0.8624 | 0.8790 |
66
- | 0.0548 | 0.8 | 2992 | 0.9834 | 0.8742 | 0.0530 | 0.8648 | 0.8838 |
67
- | 0.0515 | 0.9 | 3366 | 0.9824 | 0.8728 | 0.0544 | 0.8633 | 0.8826 |
68
- | 0.0513 | 1.0 | 3739 | 0.9831 | 0.8786 | 0.0549 | 0.8709 | 0.8865 |
69
- | 0.0379 | 1.0 | 3740 | 0.9830 | 0.8778 | 0.0552 | 0.8697 | 0.8860 |
70
- | 0.041 | 1.1 | 4114 | 0.9833 | 0.8781 | 0.0545 | 0.8702 | 0.8862 |
71
- | 0.037 | 1.2 | 4488 | 0.9842 | 0.8857 | 0.0538 | 0.8781 | 0.8936 |
72
- | 0.0395 | 1.3 | 4862 | 0.9834 | 0.8807 | 0.0536 | 0.8703 | 0.8913 |
73
- | 0.0372 | 1.4 | 5236 | 0.9845 | 0.8851 | 0.0518 | 0.8783 | 0.8921 |
74
- | 0.0369 | 1.5 | 5610 | 0.9849 | 0.8880 | 0.0506 | 0.8804 | 0.8957 |
75
- | 0.0377 | 1.6 | 5984 | 0.9844 | 0.8854 | 0.0487 | 0.8776 | 0.8934 |
76
- | 0.0361 | 1.7 | 6358 | 0.9851 | 0.8895 | 0.0497 | 0.8815 | 0.8977 |
77
- | 0.0351 | 1.8 | 6732 | 0.9850 | 0.8904 | 0.0497 | 0.8807 | 0.9003 |
78
- | 0.0348 | 1.9 | 7106 | 0.9848 | 0.8876 | 0.0490 | 0.8778 | 0.8976 |
79
- | 0.0338 | 2.0 | 7478 | 0.9848 | 0.8892 | 0.0497 | 0.8811 | 0.8975 |
80
- | 0.0128 | 2.0 | 7480 | 0.9848 | 0.8891 | 0.0497 | 0.8810 | 0.8974 |
81
- | 0.026 | 2.1 | 7854 | 0.9853 | 0.8941 | 0.0509 | 0.8865 | 0.9017 |
82
- | 0.0265 | 2.2 | 8228 | 0.9845 | 0.8878 | 0.0527 | 0.8797 | 0.8960 |
83
- | 0.0236 | 2.3 | 8602 | 0.9851 | 0.8914 | 0.0529 | 0.8833 | 0.8996 |
84
- | 0.0261 | 2.4 | 8976 | 0.9856 | 0.8953 | 0.0518 | 0.8890 | 0.9018 |
85
- | 0.0263 | 2.5 | 9350 | 0.9854 | 0.8944 | 0.0511 | 0.8868 | 0.9022 |
86
- | 0.0261 | 2.6 | 9724 | 0.9853 | 0.8931 | 0.0509 | 0.8854 | 0.9010 |
87
- | 0.0257 | 2.7 | 10098 | 0.9855 | 0.8936 | 0.0504 | 0.8863 | 0.9011 |
88
- | 0.0253 | 2.8 | 10472 | 0.9854 | 0.8936 | 0.0506 | 0.8865 | 0.9009 |
89
- | 0.0259 | 2.9 | 10846 | 0.9854 | 0.8930 | 0.0507 | 0.8855 | 0.9006 |
90
- | 0.0269 | 3.0 | 11217 | 0.9854 | 0.8928 | 0.0507 | 0.8851 | 0.9007 |
91
 
92
 
93
  ### Framework versions
 
4
  tags:
5
  - generated_from_trainer
6
  metrics:
 
 
7
  - precision
8
  - recall
9
+ - f1
10
+ - accuracy
11
  model-index:
12
  - name: xlm-roberta-large-finetuned-wikiner-fr
13
  results: []
 
20
 
21
  This model is a fine-tuned version of [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) on the Alizee/wikiner_fr_mixed_caps dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.0518
24
+ - Precision: 0.8881
25
+ - Recall: 0.9014
26
+ - F1: 0.8947
27
+ - Accuracy: 0.9855
28
 
29
  ## Model description
30
 
 
43
  ### Training hyperparameters
44
 
45
  The following hyperparameters were used during training:
46
+ - learning_rate: 1.5e-05
47
  - train_batch_size: 32
48
  - eval_batch_size: 32
49
  - seed: 42
 
54
 
55
  ### Training results
56
 
57
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
58
+ |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
59
+ | 0.1032 | 0.1 | 374 | 0.0853 | 0.7645 | 0.8170 | 0.7899 | 0.9742 |
60
+ | 0.0767 | 0.2 | 748 | 0.0721 | 0.8111 | 0.8423 | 0.8264 | 0.9785 |
61
+ | 0.074 | 0.3 | 1122 | 0.0655 | 0.8252 | 0.8502 | 0.8375 | 0.9797 |
62
+ | 0.0634 | 0.4 | 1496 | 0.0629 | 0.8423 | 0.8694 | 0.8556 | 0.9809 |
63
+ | 0.0605 | 0.5 | 1870 | 0.0610 | 0.8515 | 0.8711 | 0.8612 | 0.9808 |
64
+ | 0.0578 | 0.6 | 2244 | 0.0594 | 0.8633 | 0.8744 | 0.8688 | 0.9822 |
65
+ | 0.0592 | 0.7 | 2618 | 0.0555 | 0.8624 | 0.8833 | 0.8727 | 0.9825 |
66
+ | 0.0567 | 0.8 | 2992 | 0.0534 | 0.8626 | 0.8838 | 0.8731 | 0.9830 |
67
+ | 0.0522 | 0.9 | 3366 | 0.0563 | 0.8560 | 0.8771 | 0.8664 | 0.9818 |
68
+ | 0.0516 | 1.0 | 3739 | 0.0556 | 0.8702 | 0.8869 | 0.8785 | 0.9831 |
69
+ | 0.0438 | 1.0 | 3740 | 0.0558 | 0.8712 | 0.8873 | 0.8792 | 0.9831 |
70
+ | 0.0395 | 1.1 | 4114 | 0.0565 | 0.8696 | 0.8856 | 0.8775 | 0.9830 |
71
+ | 0.0371 | 1.2 | 4488 | 0.0536 | 0.8762 | 0.8910 | 0.8835 | 0.9838 |
72
+ | 0.0403 | 1.3 | 4862 | 0.0531 | 0.8709 | 0.8887 | 0.8797 | 0.9835 |
73
+ | 0.0366 | 1.4 | 5236 | 0.0517 | 0.8791 | 0.8912 | 0.8851 | 0.9843 |
74
+ | 0.037 | 1.5 | 5610 | 0.0510 | 0.8830 | 0.8936 | 0.8883 | 0.9847 |
75
+ | 0.0368 | 1.6 | 5984 | 0.0492 | 0.8795 | 0.8940 | 0.8867 | 0.9845 |
76
+ | 0.0359 | 1.7 | 6358 | 0.0501 | 0.8833 | 0.8986 | 0.8909 | 0.9850 |
77
+ | 0.034 | 1.8 | 6732 | 0.0496 | 0.8852 | 0.8986 | 0.8918 | 0.9852 |
78
+ | 0.0327 | 1.9 | 7106 | 0.0512 | 0.8762 | 0.8948 | 0.8854 | 0.9843 |
79
+ | 0.0325 | 2.0 | 7478 | 0.0512 | 0.8829 | 0.8945 | 0.8887 | 0.9844 |
80
+ | 0.01 | 2.0 | 7480 | 0.0512 | 0.8836 | 0.8945 | 0.8890 | 0.9843 |
81
+ | 0.0232 | 2.1 | 7854 | 0.0526 | 0.8870 | 0.9002 | 0.8936 | 0.9852 |
82
+ | 0.0235 | 2.2 | 8228 | 0.0530 | 0.8841 | 0.8983 | 0.8911 | 0.9848 |
83
+ | 0.0211 | 2.3 | 8602 | 0.0542 | 0.8875 | 0.9008 | 0.8941 | 0.9852 |
84
+ | 0.0235 | 2.4 | 8976 | 0.0525 | 0.8883 | 0.9008 | 0.8945 | 0.9855 |
85
+ | 0.0232 | 2.5 | 9350 | 0.0525 | 0.8874 | 0.9013 | 0.8943 | 0.9855 |
86
+ | 0.0238 | 2.6 | 9724 | 0.0517 | 0.8861 | 0.9011 | 0.8935 | 0.9854 |
87
+ | 0.0223 | 2.7 | 10098 | 0.0513 | 0.8893 | 0.9016 | 0.8954 | 0.9856 |
88
+ | 0.0226 | 2.8 | 10472 | 0.0517 | 0.8892 | 0.9017 | 0.8954 | 0.9856 |
89
+ | 0.0228 | 2.9 | 10846 | 0.0517 | 0.8879 | 0.9013 | 0.8945 | 0.9855 |
90
+ | 0.0235 | 3.0 | 11217 | 0.0518 | 0.8881 | 0.9014 | 0.8947 | 0.9855 |
91
 
92
 
93
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:073834ee54e94e08a7cdc41deffa07f3c9b5dbd7b1d605d4c2ac2309b6aae4bf
3
  size 2235432356
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dea8e6d8d4e01c25fe6b0683c6c633af358d66bbe37d0b75fa7149767fcd8df6
3
  size 2235432356
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d79e5690183759400e28d63cce5e86cf710ac00af175a7cf509cc698cc719934
3
  size 4411
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4387d0ead30ba02a973a913f3670e5286811cf66973a20e7161fd4fc8d4cb229
3
  size 4411