Hugging Face's logo

Jsevisal
/
ft-roberta-gest-pred-seqeval-partialmatch

Token Classification
Transformers
PyTorch
TensorBoard
Safetensors
xlm-roberta
Generated from Trainer
Model card Files
xet
Metrics Community
1
Jsevisal commited on
Commit
472b748
·
1 Parent(s): 20dad92

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +17 -22
README.md CHANGED
@@ -9,11 +9,6 @@ metrics:
9
  model-index:
10
  - name: roberta-gest-pred-seqeval-partialmatch
11
  results: []
12
- datasets:
13
- - Jsevisal/gesture_pred
14
- language:
15
- - en
16
- pipeline_tag: token-classification
17
  ---
18
 
19
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -23,11 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
23
 
24
  This model is a fine-tuned version of [xlm-roberta-large-finetuned-conll03-english](https://huggingface.co/xlm-roberta-large-finetuned-conll03-english) on the None dataset.
25
  It achieves the following results on the evaluation set:
26
- - Loss: 0.602216
27
- - Precision: 0.833532
28
- - Recall: 0.833532
29
- - F1: 0.833532
30
- - Accuracy: 0.822830
31
 
32
  ## Model description
33
 
@@ -58,21 +53,21 @@ The following hyperparameters were used during training:
58
 
59
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
60
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
61
- | 1.7547 | 1.0 | 147 | 0.9698 | 0.7634 | 0.7634 | 0.7634 | 0.7426 |
62
- | 0.8657 | 2.0 | 294 | 0.6433 | 0.8300 | 0.8300 | 0.8300 | 0.8127 |
63
- | 0.5629 | 3.0 | 441 | 0.6167 | 0.8383 | 0.8383 | 0.8383 | 0.8270 |
64
- | 0.3763 | 4.0 | 588 | 0.6022 | 0.8335 | 0.8335 | 0.8335 | 0.8228 |
65
- | 0.2507 | 5.0 | 735 | 0.7089 | 0.8424 | 0.8424 | 0.8424 | 0.8317 |
66
- | 0.165 | 6.0 | 882 | 0.7194 | 0.8650 | 0.8650 | 0.8650 | 0.8537 |
67
- | 0.1224 | 7.0 | 1029 | 0.8469 | 0.8532 | 0.8532 | 0.8532 | 0.8478 |
68
- | 0.0759 | 8.0 | 1176 | 0.9850 | 0.8365 | 0.8365 | 0.8365 | 0.8288 |
69
- | 0.0548 | 9.0 | 1323 | 0.9934 | 0.8490 | 0.8490 | 0.8490 | 0.8424 |
70
- | 0.0418 | 10.0 | 1470 | 0.9911 | 0.8401 | 0.8401 | 0.8401 | 0.8347 |
71
 
72
 
73
  ### Framework versions
74
 
75
- - Transformers 4.26.1
76
  - Pytorch 1.13.1+cu116
77
  - Datasets 2.10.1
78
- - Tokenizers 0.13.2
 
9
  model-index:
10
  - name: roberta-gest-pred-seqeval-partialmatch
11
  results: []
 
 
 
 
 
12
  ---
13
 
14
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
18
 
19
  This model is a fine-tuned version of [xlm-roberta-large-finetuned-conll03-english](https://huggingface.co/xlm-roberta-large-finetuned-conll03-english) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.9160
22
+ - Precision: 0.8093
23
+ - Recall: 0.7469
24
+ - F1: 0.7331
25
+ - Accuracy: 0.8633
26
 
27
  ## Model description
28
 
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
55
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
56
+ | 1.8351 | 1.0 | 147 | 0.9547 | 0.5114 | 0.4560 | 0.4404 | 0.7414 |
57
+ | 0.8448 | 2.0 | 294 | 0.6491 | 0.7273 | 0.6873 | 0.6768 | 0.8103 |
58
+ | 0.5622 | 3.0 | 441 | 0.7047 | 0.7169 | 0.6724 | 0.6631 | 0.8044 |
59
+ | 0.3594 | 4.0 | 588 | 0.6258 | 0.7927 | 0.7354 | 0.7381 | 0.8323 |
60
+ | 0.2304 | 5.0 | 735 | 0.7149 | 0.7861 | 0.7029 | 0.7086 | 0.8389 |
61
+ | 0.1566 | 6.0 | 882 | 0.7313 | 0.8518 | 0.8039 | 0.7852 | 0.8549 |
62
+ | 0.1021 | 7.0 | 1029 | 0.7592 | 0.8084 | 0.7493 | 0.7462 | 0.8639 |
63
+ | 0.0718 | 8.0 | 1176 | 0.8252 | 0.8115 | 0.7470 | 0.7336 | 0.8591 |
64
+ | 0.0518 | 9.0 | 1323 | 0.9014 | 0.8112 | 0.7495 | 0.7343 | 0.8639 |
65
+ | 0.0395 | 10.0 | 1470 | 0.9160 | 0.8093 | 0.7469 | 0.7331 | 0.8633 |
66
 
67
 
68
  ### Framework versions
69
 
70
+ - Transformers 4.27.3
71
  - Pytorch 1.13.1+cu116
72
  - Datasets 2.10.1
73
+ - Tokenizers 0.13.2