Hugging Face's logo

stulcrad
/
CNEC2_0_Supertypes_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
91325d7
·
verified ·
1 Parent(s): c720959

Model save

Browse files
Files changed (1) hide show
  1. README.md +18 -18
README.md CHANGED
@@ -25,16 +25,16 @@ model-index:
25
  metrics:
26
  - name: Precision
27
  type: precision
28
- value: 0.8317152103559871
29
  - name: Recall
30
  type: recall
31
- value: 0.8682432432432432
32
  - name: F1
33
  type: f1
34
- value: 0.8495867768595041
35
  - name: Accuracy
36
  type: accuracy
37
- value: 0.9680139069969579
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: 0.2072
48
- - Precision: 0.8317
49
- - Recall: 0.8682
50
- - F1: 0.8496
51
- - Accuracy: 0.9680
52
 
53
  ## Model description
54
 
@@ -79,15 +79,15 @@ The following hyperparameters were used during training:
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
- | 0.2727 | 1.11 | 500 | 0.1414 | 0.7268 | 0.8012 | 0.7622 | 0.9594 |
83
- | 0.1146 | 2.22 | 1000 | 0.1338 | 0.7697 | 0.8581 | 0.8115 | 0.9657 |
84
- | 0.0725 | 3.33 | 1500 | 0.1444 | 0.7953 | 0.8625 | 0.8275 | 0.9668 |
85
- | 0.0492 | 4.44 | 2000 | 0.1513 | 0.8085 | 0.8760 | 0.8409 | 0.9675 |
86
- | 0.0388 | 5.56 | 2500 | 0.1604 | 0.8257 | 0.8731 | 0.8487 | 0.9674 |
87
- | 0.0244 | 6.67 | 3000 | 0.1754 | 0.8278 | 0.8629 | 0.8450 | 0.9666 |
88
- | 0.0169 | 7.78 | 3500 | 0.1877 | 0.8282 | 0.8653 | 0.8464 | 0.9677 |
89
- | 0.0102 | 8.89 | 4000 | 0.1974 | 0.8252 | 0.8634 | 0.8439 | 0.9674 |
90
- | 0.0068 | 10.0 | 4500 | 0.2072 | 0.8317 | 0.8682 | 0.8496 | 0.9680 |
91
 
92
 
93
  ### Framework versions
 
25
  metrics:
26
  - name: Precision
27
  type: precision
28
+ value: 0.8314350797266514
29
  - name: Recall
30
  type: recall
31
+ value: 0.8807915057915058
32
  - name: F1
33
  type: f1
34
+ value: 0.8554019217248652
35
  - name: Accuracy
36
  type: accuracy
37
+ value: 0.970911198029842
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: 0.1616
48
+ - Precision: 0.8314
49
+ - Recall: 0.8808
50
+ - F1: 0.8554
51
+ - Accuracy: 0.9709
52
 
53
  ## Model description
54
 
 
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
+ | 0.3363 | 1.11 | 500 | 0.1563 | 0.7344 | 0.8234 | 0.7763 | 0.9607 |
83
+ | 0.1372 | 2.22 | 1000 | 0.1308 | 0.7641 | 0.8692 | 0.8133 | 0.9652 |
84
+ | 0.0998 | 3.33 | 1500 | 0.1368 | 0.7912 | 0.8668 | 0.8273 | 0.9671 |
85
+ | 0.077 | 4.44 | 2000 | 0.1360 | 0.8079 | 0.8707 | 0.8381 | 0.9690 |
86
+ | 0.0623 | 5.56 | 2500 | 0.1421 | 0.8181 | 0.8707 | 0.8436 | 0.9686 |
87
+ | 0.0458 | 6.67 | 3000 | 0.1488 | 0.8129 | 0.8764 | 0.8435 | 0.9706 |
88
+ | 0.0382 | 7.78 | 3500 | 0.1585 | 0.8320 | 0.8745 | 0.8527 | 0.9693 |
89
+ | 0.0299 | 8.89 | 4000 | 0.1585 | 0.8291 | 0.8755 | 0.8516 | 0.9705 |
90
+ | 0.0257 | 10.0 | 4500 | 0.1616 | 0.8314 | 0.8808 | 0.8554 | 0.9709 |
91
 
92
 
93
  ### Framework versions