Hugging Face's logo

stulcrad
/
CNEC1_1_xlm-roberta-large

Token Classification
Transformers
TensorBoard
Safetensors
xlm-roberta
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
stulcrad commited on
Commit
4c91c3f
·
verified ·
1 Parent(s): 9f3c100

Model save

Browse files
Files changed (1) hide show
  1. README.md +24 -24
README.md CHANGED
@@ -25,16 +25,16 @@ model-index:
25
  metrics:
26
  - name: Precision
27
  type: precision
28
- value: 0.8562231759656652
29
  - name: Recall
30
  type: recall
31
- value: 0.8807947019867549
32
  - name: F1
33
  type: f1
34
- value: 0.868335146898803
35
  - name: Accuracy
36
  type: accuracy
37
- value: 0.9576876536945236
38
  ---
39
 
40
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -44,11 +44,11 @@ should probably proofread and complete it, then remove this comment. -->
44
 
45
  This model is a fine-tuned version of [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) on the cnec dataset.
46
  It achieves the following results on the evaluation set:
47
- - Loss: 0.3619
48
- - Precision: 0.8562
49
- - Recall: 0.8808
50
- - F1: 0.8683
51
- - Accuracy: 0.9577
52
 
53
  ## Model description
54
 
@@ -79,21 +79,21 @@ The following hyperparameters were used during training:
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
  |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
- | 0.4347 | 1.0 | 1174 | 0.2695 | 0.7621 | 0.8004 | 0.7808 | 0.9404 |
83
- | 0.2912 | 2.0 | 2348 | 0.2377 | 0.7989 | 0.8172 | 0.8079 | 0.9479 |
84
- | 0.2204 | 3.0 | 3522 | 0.2530 | 0.8120 | 0.8393 | 0.8254 | 0.9501 |
85
- | 0.1924 | 4.0 | 4696 | 0.2313 | 0.8241 | 0.8605 | 0.8419 | 0.9559 |
86
- | 0.1401 | 5.0 | 5870 | 0.2534 | 0.8296 | 0.8596 | 0.8443 | 0.9555 |
87
- | 0.1227 | 6.0 | 7044 | 0.2782 | 0.8188 | 0.8596 | 0.8387 | 0.9526 |
88
- | 0.1034 | 7.0 | 8218 | 0.2645 | 0.8233 | 0.8534 | 0.8381 | 0.9543 |
89
- | 0.0858 | 8.0 | 9392 | 0.2877 | 0.8404 | 0.8623 | 0.8512 | 0.9552 |
90
- | 0.0657 | 9.0 | 10566 | 0.3009 | 0.8469 | 0.8645 | 0.8556 | 0.9548 |
91
- | 0.0587 | 10.0 | 11740 | 0.3235 | 0.8493 | 0.8759 | 0.8624 | 0.9571 |
92
- | 0.0455 | 11.0 | 12914 | 0.3326 | 0.8495 | 0.8675 | 0.8585 | 0.9560 |
93
- | 0.0394 | 12.0 | 14088 | 0.3496 | 0.8454 | 0.8715 | 0.8583 | 0.9568 |
94
- | 0.0325 | 13.0 | 15262 | 0.3571 | 0.8483 | 0.8693 | 0.8587 | 0.9560 |
95
- | 0.0293 | 14.0 | 16436 | 0.3545 | 0.8585 | 0.8812 | 0.8697 | 0.9577 |
96
- | 0.0236 | 15.0 | 17610 | 0.3619 | 0.8562 | 0.8808 | 0.8683 | 0.9577 |
97
 
98
 
99
  ### Framework versions
 
25
  metrics:
26
  - name: Precision
27
  type: precision
28
+ value: 0.8521036974075649
29
  - name: Recall
30
  type: recall
31
+ value: 0.8721183123096998
32
  - name: F1
33
  type: f1
34
+ value: 0.8619948409286329
35
  - name: Accuracy
36
  type: accuracy
37
+ value: 0.9512518524296076
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 [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) on the cnec dataset.
46
  It achieves the following results on the evaluation set:
47
+ - Loss: 0.3816
48
+ - Precision: 0.8521
49
+ - Recall: 0.8721
50
+ - F1: 0.8620
51
+ - Accuracy: 0.9513
52
 
53
  ## Model description
54
 
 
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
  |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
+ | 0.4004 | 1.0 | 1174 | 0.2747 | 0.7598 | 0.7876 | 0.7735 | 0.9381 |
83
+ | 0.2765 | 2.0 | 2348 | 0.2268 | 0.8181 | 0.8340 | 0.8260 | 0.9506 |
84
+ | 0.2104 | 3.0 | 3522 | 0.2400 | 0.8318 | 0.8561 | 0.8438 | 0.9524 |
85
+ | 0.1713 | 4.0 | 4696 | 0.2285 | 0.8353 | 0.8645 | 0.8496 | 0.9552 |
86
+ | 0.1241 | 5.0 | 5870 | 0.2278 | 0.8458 | 0.8715 | 0.8584 | 0.9585 |
87
+ | 0.0997 | 6.0 | 7044 | 0.2717 | 0.8372 | 0.8653 | 0.8511 | 0.9559 |
88
+ | 0.0878 | 7.0 | 8218 | 0.2599 | 0.8439 | 0.8830 | 0.8630 | 0.9583 |
89
+ | 0.0585 | 8.0 | 9392 | 0.2868 | 0.8415 | 0.8764 | 0.8586 | 0.9564 |
90
+ | 0.0489 | 9.0 | 10566 | 0.2900 | 0.8594 | 0.8795 | 0.8693 | 0.9568 |
91
+ | 0.0416 | 10.0 | 11740 | 0.3061 | 0.8646 | 0.8852 | 0.8748 | 0.9598 |
92
+ | 0.0316 | 11.0 | 12914 | 0.3240 | 0.8567 | 0.8843 | 0.8703 | 0.9576 |
93
+ | 0.0264 | 12.0 | 14088 | 0.3329 | 0.8546 | 0.8795 | 0.8668 | 0.9588 |
94
+ | 0.0184 | 13.0 | 15262 | 0.3475 | 0.8628 | 0.8804 | 0.8715 | 0.9584 |
95
+ | 0.0156 | 14.0 | 16436 | 0.3472 | 0.8654 | 0.8826 | 0.8739 | 0.9592 |
96
+ | 0.0125 | 15.0 | 17610 | 0.3539 | 0.8670 | 0.8861 | 0.8764 | 0.9593 |
97
 
98
 
99
  ### Framework versions