Hugging Face's logo

stulcrad
/
CNEC1_1_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
e1373f1
·
verified ·
1 Parent(s): 0d18a32

Model save

Browse files
Files changed (2) hide show
  1. README.md +33 -29
  2. model.safetensors +1 -1
README.md CHANGED
@@ -25,16 +25,16 @@ model-index:
25
  metrics:
26
  - name: Precision
27
  type: precision
28
- value: 0.8482029598308668
29
  - name: Recall
30
  type: recall
31
- value: 0.8721739130434782
32
  - name: F1
33
  type: f1
34
- value: 0.8600214362272238
35
  - name: Accuracy
36
  type: accuracy
37
- value: 0.9539427501754933
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: 0.3393
48
- - Precision: 0.8482
49
- - Recall: 0.8722
50
- - F1: 0.8600
51
- - Accuracy: 0.9539
52
 
53
  ## Model description
54
 
@@ -73,29 +73,33 @@ The following hyperparameters were used during training:
73
  - seed: 42
74
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
75
  - lr_scheduler_type: linear
76
- - num_epochs: 15
77
 
78
  ### Training results
79
 
80
- | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
- |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
- | 0.4206 | 0.85 | 500 | 0.1966 | 0.7729 | 0.8258 | 0.7985 | 0.9465 |
83
- | 0.2031 | 1.7 | 1000 | 0.1723 | 0.7984 | 0.8599 | 0.8280 | 0.9559 |
84
- | 0.1471 | 2.56 | 1500 | 0.1821 | 0.8363 | 0.8625 | 0.8492 | 0.9562 |
85
- | 0.1267 | 3.41 | 2000 | 0.1712 | 0.8269 | 0.8873 | 0.8560 | 0.9598 |
86
- | 0.1048 | 4.26 | 2500 | 0.1948 | 0.8293 | 0.8718 | 0.8500 | 0.9578 |
87
- | 0.088 | 5.11 | 3000 | 0.1961 | 0.8467 | 0.8837 | 0.8648 | 0.9607 |
88
- | 0.0745 | 5.96 | 3500 | 0.1944 | 0.8570 | 0.8714 | 0.8641 | 0.9604 |
89
- | 0.0572 | 6.81 | 4000 | 0.2151 | 0.8548 | 0.8904 | 0.8722 | 0.9615 |
90
- | 0.0527 | 7.67 | 4500 | 0.2147 | 0.8542 | 0.8886 | 0.8711 | 0.9627 |
91
- | 0.0408 | 8.52 | 5000 | 0.2193 | 0.8614 | 0.8877 | 0.8744 | 0.9624 |
92
- | 0.0359 | 9.37 | 5500 | 0.2344 | 0.8597 | 0.8859 | 0.8726 | 0.9620 |
93
- | 0.0303 | 10.22 | 6000 | 0.2524 | 0.8621 | 0.8868 | 0.8743 | 0.9628 |
94
- | 0.0248 | 11.07 | 6500 | 0.2563 | 0.8605 | 0.8890 | 0.8745 | 0.9632 |
95
- | 0.0199 | 11.93 | 7000 | 0.2783 | 0.8561 | 0.8837 | 0.8697 | 0.9605 |
96
- | 0.0163 | 12.78 | 7500 | 0.2891 | 0.8505 | 0.8851 | 0.8674 | 0.9607 |
97
- | 0.0132 | 13.63 | 8000 | 0.2891 | 0.8579 | 0.8912 | 0.8742 | 0.9633 |
98
- | 0.0119 | 14.48 | 8500 | 0.2922 | 0.8589 | 0.8935 | 0.8758 | 0.9638 |
 
 
 
 
99
 
100
 
101
  ### Framework versions
 
25
  metrics:
26
  - name: Precision
27
  type: precision
28
+ value: 0.8579351535836177
29
  - name: Recall
30
  type: recall
31
+ value: 0.8890362511052167
32
  - name: F1
33
  type: f1
34
+ value: 0.8732088580112897
35
  - name: Accuracy
36
  type: accuracy
37
+ value: 0.9613177719661189
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: 0.3156
48
+ - Precision: 0.8579
49
+ - Recall: 0.8890
50
+ - F1: 0.8732
51
+ - Accuracy: 0.9613
52
 
53
  ## Model description
54
 
 
73
  - seed: 42
74
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
75
  - lr_scheduler_type: linear
76
+ - num_epochs: 18
77
 
78
  ### Training results
79
 
80
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
+ |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
+ | 0.4473 | 0.85 | 500 | 0.1990 | 0.7879 | 0.8263 | 0.8066 | 0.9488 |
83
+ | 0.2061 | 1.7 | 1000 | 0.1800 | 0.8151 | 0.8537 | 0.8339 | 0.9544 |
84
+ | 0.1501 | 2.56 | 1500 | 0.1782 | 0.8145 | 0.8638 | 0.8384 | 0.9541 |
85
+ | 0.1257 | 3.41 | 2000 | 0.1613 | 0.8266 | 0.8767 | 0.8509 | 0.9606 |
86
+ | 0.1039 | 4.26 | 2500 | 0.1812 | 0.8359 | 0.8762 | 0.8556 | 0.9600 |
87
+ | 0.0859 | 5.11 | 3000 | 0.1949 | 0.8356 | 0.8811 | 0.8578 | 0.9594 |
88
+ | 0.0705 | 5.96 | 3500 | 0.1965 | 0.8323 | 0.8753 | 0.8533 | 0.9588 |
89
+ | 0.0549 | 6.81 | 4000 | 0.2135 | 0.8469 | 0.8899 | 0.8679 | 0.9619 |
90
+ | 0.0513 | 7.67 | 4500 | 0.2137 | 0.8488 | 0.8912 | 0.8695 | 0.9608 |
91
+ | 0.0374 | 8.52 | 5000 | 0.2099 | 0.8564 | 0.8908 | 0.8732 | 0.9625 |
92
+ | 0.0326 | 9.37 | 5500 | 0.2388 | 0.8617 | 0.8868 | 0.8741 | 0.9619 |
93
+ | 0.03 | 10.22 | 6000 | 0.2796 | 0.8569 | 0.8868 | 0.8716 | 0.9601 |
94
+ | 0.0258 | 11.07 | 6500 | 0.2669 | 0.8584 | 0.8899 | 0.8739 | 0.9607 |
95
+ | 0.018 | 11.93 | 7000 | 0.2855 | 0.8580 | 0.8815 | 0.8696 | 0.9592 |
96
+ | 0.0165 | 12.78 | 7500 | 0.2838 | 0.8612 | 0.8939 | 0.8772 | 0.9609 |
97
+ | 0.0133 | 13.63 | 8000 | 0.2903 | 0.8593 | 0.8855 | 0.8722 | 0.9605 |
98
+ | 0.0128 | 14.48 | 8500 | 0.3064 | 0.8529 | 0.8921 | 0.8721 | 0.9610 |
99
+ | 0.0092 | 15.33 | 9000 | 0.3078 | 0.8552 | 0.8904 | 0.8724 | 0.9607 |
100
+ | 0.0089 | 16.18 | 9500 | 0.3088 | 0.8570 | 0.8899 | 0.8731 | 0.9615 |
101
+ | 0.0077 | 17.04 | 10000 | 0.3099 | 0.8571 | 0.8912 | 0.8739 | 0.9612 |
102
+ | 0.0057 | 17.89 | 10500 | 0.3156 | 0.8579 | 0.8890 | 0.8732 | 0.9613 |
103
 
104
 
105
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f54a84c541cae1036fb54ddf2b66a01d0818b0aafd7461f208adb2962232fa5
3
  size 2235497956
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87a283c1950139a45299cdfd0f3b6a6e4f3216c610134e403eee85f61027f210
3
  size 2235497956