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
2412186
·
verified ·
1 Parent(s): c5c81bb

Model save

Browse files
Files changed (2) hide show
  1. README.md +31 -22
  2. model.safetensors +1 -1
README.md CHANGED
@@ -25,16 +25,16 @@ model-index:
25
  metrics:
26
  - name: Precision
27
  type: precision
28
- value: 0.8375401560348784
29
  - name: Recall
30
  type: recall
31
- value: 0.8807915057915058
32
  - name: F1
33
  type: f1
34
- value: 0.8586215008233357
35
  - name: Accuracy
36
  type: accuracy
37
- value: 0.9697233087063596
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: 0.1726
48
- - Precision: 0.8375
49
- - Recall: 0.8808
50
- - F1: 0.8586
51
- - Accuracy: 0.9697
52
 
53
  ## Model description
54
 
@@ -68,28 +68,37 @@ More information needed
68
 
69
  The following hyperparameters were used during training:
70
  - learning_rate: 2e-05
71
- - train_batch_size: 16
72
- - eval_batch_size: 16
73
  - seed: 42
74
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
75
  - lr_scheduler_type: linear
76
- - lr_scheduler_warmup_ratio: 0.1
77
- - lr_scheduler_warmup_steps: 500
78
  - num_epochs: 10
79
 
80
  ### Training results
81
 
82
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
83
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
84
- | 0.6046 | 1.11 | 500 | 0.1815 | 0.6422 | 0.7693 | 0.7000 | 0.9498 |
85
- | 0.1671 | 2.22 | 1000 | 0.1389 | 0.7436 | 0.8456 | 0.7913 | 0.9620 |
86
- | 0.1141 | 3.33 | 1500 | 0.1455 | 0.7949 | 0.8813 | 0.8359 | 0.9686 |
87
- | 0.0854 | 4.44 | 2000 | 0.1455 | 0.8012 | 0.8678 | 0.8332 | 0.9684 |
88
- | 0.0716 | 5.56 | 2500 | 0.1418 | 0.7996 | 0.8663 | 0.8316 | 0.9682 |
89
- | 0.0506 | 6.67 | 3000 | 0.1570 | 0.8138 | 0.8793 | 0.8453 | 0.9690 |
90
- | 0.0399 | 7.78 | 3500 | 0.1701 | 0.8363 | 0.8803 | 0.8577 | 0.9689 |
91
- | 0.0324 | 8.89 | 4000 | 0.1720 | 0.8313 | 0.8798 | 0.8549 | 0.9691 |
92
- | 0.0265 | 10.0 | 4500 | 0.1726 | 0.8375 | 0.8808 | 0.8586 | 0.9697 |
 
 
 
 
 
 
 
 
 
93
 
94
 
95
  ### Framework versions
 
25
  metrics:
26
  - name: Precision
27
  type: precision
28
+ value: 0.8296228986824171
29
  - name: Recall
30
  type: recall
31
+ value: 0.8812741312741312
32
  - name: F1
33
  type: f1
34
+ value: 0.8546688509244091
35
  - name: Accuracy
36
  type: accuracy
37
+ value: 0.9687672026655078
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: 0.1851
48
+ - Precision: 0.8296
49
+ - Recall: 0.8813
50
+ - F1: 0.8547
51
+ - Accuracy: 0.9688
52
 
53
  ## Model description
54
 
 
68
 
69
  The following hyperparameters were used during training:
70
  - learning_rate: 2e-05
71
+ - train_batch_size: 8
72
+ - eval_batch_size: 8
73
  - seed: 42
74
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
75
  - lr_scheduler_type: linear
76
+ - lr_scheduler_warmup_ratio: 0.01
77
+ - lr_scheduler_warmup_steps: 100
78
  - num_epochs: 10
79
 
80
  ### Training results
81
 
82
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
83
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
84
+ | 0.607 | 0.56 | 500 | 0.1967 | 0.6391 | 0.7881 | 0.7059 | 0.9475 |
85
+ | 0.2143 | 1.11 | 1000 | 0.1735 | 0.6993 | 0.8282 | 0.7583 | 0.9591 |
86
+ | 0.1756 | 1.67 | 1500 | 0.1550 | 0.7363 | 0.8016 | 0.7676 | 0.9605 |
87
+ | 0.1458 | 2.22 | 2000 | 0.1674 | 0.7549 | 0.8591 | 0.8036 | 0.9624 |
88
+ | 0.1323 | 2.78 | 2500 | 0.1575 | 0.7802 | 0.8460 | 0.8118 | 0.9619 |
89
+ | 0.112 | 3.33 | 3000 | 0.1627 | 0.7602 | 0.8369 | 0.7967 | 0.9625 |
90
+ | 0.1082 | 3.89 | 3500 | 0.1510 | 0.7774 | 0.8697 | 0.8210 | 0.9662 |
91
+ | 0.0862 | 4.44 | 4000 | 0.1544 | 0.7820 | 0.8552 | 0.8170 | 0.9655 |
92
+ | 0.0878 | 5.0 | 4500 | 0.1399 | 0.8044 | 0.8692 | 0.8355 | 0.9679 |
93
+ | 0.0657 | 5.56 | 5000 | 0.1518 | 0.8038 | 0.8639 | 0.8328 | 0.9671 |
94
+ | 0.0741 | 6.11 | 5500 | 0.1704 | 0.8031 | 0.8562 | 0.8288 | 0.9664 |
95
+ | 0.0575 | 6.67 | 6000 | 0.1774 | 0.8109 | 0.8649 | 0.8370 | 0.9664 |
96
+ | 0.0497 | 7.22 | 6500 | 0.1801 | 0.8129 | 0.8682 | 0.8397 | 0.9667 |
97
+ | 0.0419 | 7.78 | 7000 | 0.1659 | 0.8337 | 0.8687 | 0.8509 | 0.9692 |
98
+ | 0.0445 | 8.33 | 7500 | 0.1752 | 0.8340 | 0.8755 | 0.8543 | 0.9687 |
99
+ | 0.037 | 8.89 | 8000 | 0.1823 | 0.8213 | 0.8764 | 0.8480 | 0.9680 |
100
+ | 0.0324 | 9.44 | 8500 | 0.1854 | 0.8268 | 0.8798 | 0.8525 | 0.9686 |
101
+ | 0.0313 | 10.0 | 9000 | 0.1851 | 0.8296 | 0.8813 | 0.8547 | 0.9688 |
102
 
103
 
104
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09a26ac97cf5c3aeb9c560468cb3b46dcad4d4e5252381b317c1882e4da7db41
3
  size 2235481556
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1683fa310eec5d9d4dd1f5c94ceedbeebf41d81a4e478b893f17a4a7b0cafc8f
3
  size 2235481556