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
cd41955
•
1 Parent(s): 7827125

Model save

Browse files
Files changed (2) hide show
  1. README.md +17 -19
  2. model.safetensors +1 -1
README.md CHANGED
@@ -25,16 +25,16 @@ model-index:
25
  metrics:
26
  - name: Precision
27
  type: precision
28
- value: 0.8497409326424871
29
  - name: Recall
30
  type: recall
31
- value: 0.8806278397356464
32
  - name: F1
33
  type: f1
34
- value: 0.8649087221095335
35
  - name: Accuracy
36
  type: accuracy
37
- value: 0.9709691438504998
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: 0.1149
48
- - Precision: 0.8497
49
- - Recall: 0.8806
50
- - F1: 0.8649
51
- - Accuracy: 0.9710
52
 
53
  ## Model description
54
 
@@ -68,22 +68,20 @@ More information needed
68
 
69
  The following hyperparameters were used during training:
70
  - learning_rate: 2e-05
71
- - train_batch_size: 32
72
- - eval_batch_size: 32
73
  - seed: 42
74
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
75
  - lr_scheduler_type: linear
76
- - num_epochs: 5
77
 
78
  ### Training results
79
 
80
- | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
- |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
- | No log | 1.0 | 225 | 0.1406 | 0.7940 | 0.8278 | 0.8105 | 0.9617 |
83
- | No log | 2.0 | 450 | 0.1137 | 0.8142 | 0.8781 | 0.8450 | 0.9684 |
84
- | 0.2248 | 3.0 | 675 | 0.1070 | 0.8455 | 0.8769 | 0.8609 | 0.9709 |
85
- | 0.2248 | 4.0 | 900 | 0.1190 | 0.8494 | 0.8852 | 0.8669 | 0.9698 |
86
- | 0.0604 | 5.0 | 1125 | 0.1149 | 0.8497 | 0.8806 | 0.8649 | 0.9710 |
87
 
88
 
89
  ### Framework versions
 
25
  metrics:
26
  - name: Precision
27
  type: precision
28
+ value: 0.8473042109405746
29
  - name: Recall
30
  type: recall
31
+ value: 0.889301941346551
32
  - name: F1
33
  type: f1
34
+ value: 0.867795243853285
35
  - name: Accuracy
36
  type: accuracy
37
+ value: 0.9698392003476749
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: 0.1673
48
+ - Precision: 0.8473
49
+ - Recall: 0.8893
50
+ - F1: 0.8678
51
+ - Accuracy: 0.9698
52
 
53
  ## Model description
54
 
 
68
 
69
  The following hyperparameters were used during training:
70
  - learning_rate: 2e-05
71
+ - train_batch_size: 1
72
+ - eval_batch_size: 1
73
  - seed: 42
74
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
75
  - lr_scheduler_type: linear
76
+ - num_epochs: 3
77
 
78
  ### Training results
79
 
80
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
+ |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
+ | 0.2246 | 1.0 | 7193 | 0.1918 | 0.8122 | 0.8505 | 0.8309 | 0.9616 |
83
+ | 0.1431 | 2.0 | 14386 | 0.1665 | 0.8241 | 0.8748 | 0.8487 | 0.9671 |
84
+ | 0.0845 | 3.0 | 21579 | 0.1673 | 0.8473 | 0.8893 | 0.8678 | 0.9698 |
 
 
85
 
86
 
87
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e87aef059a76f7b0cae494de5b2751f6a923c0e8b3dc16b23aa4a2415485a44
3
  size 2235481556
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b39a7d95087631f3766f774671ddea7528693e22941fa34f37e2984b4892d32
3
  size 2235481556