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
ca42a6c
·
verified ·
1 Parent(s): 78367d3

Model save

Browse files
Files changed (2) hide show
  1. README.md +19 -31
  2. runs/Mar05_20-38-08_n21/events.out.tfevents.1709667489.n21.1798944.0 +2 -2
README.md CHANGED
@@ -25,16 +25,16 @@ model-index:
25
  metrics:
26
  - name: Precision
27
  type: precision
28
- value: 0.8087233075874602
29
  - name: Recall
30
  type: recall
31
- value: 0.859073359073359
32
  - name: F1
33
  type: f1
34
- value: 0.8331383103206178
35
  - name: Accuracy
36
  type: accuracy
37
- value: 0.9666232073011733
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: 0.2110
48
- - Precision: 0.8087
49
- - Recall: 0.8591
50
- - F1: 0.8331
51
- - Accuracy: 0.9666
52
 
53
  ## Model description
54
 
@@ -67,36 +67,24 @@ More information needed
67
  ### Training hyperparameters
68
 
69
  The following hyperparameters were used during training:
70
- - learning_rate: 5e-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
- - num_epochs: 10
77
 
78
  ### Training results
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
- | 0.4116 | 0.56 | 500 | 0.1954 | 0.6187 | 0.7761 | 0.6885 | 0.9480 |
83
- | 0.2334 | 1.11 | 1000 | 0.1743 | 0.6863 | 0.7920 | 0.7354 | 0.9535 |
84
- | 0.1897 | 1.67 | 1500 | 0.2003 | 0.6759 | 0.7447 | 0.7086 | 0.9464 |
85
- | 0.1706 | 2.22 | 2000 | 0.1633 | 0.7333 | 0.8388 | 0.7825 | 0.9576 |
86
- | 0.1492 | 2.78 | 2500 | 0.1581 | 0.7396 | 0.8045 | 0.7707 | 0.9582 |
87
- | 0.1198 | 3.33 | 3000 | 0.1699 | 0.7558 | 0.8378 | 0.7947 | 0.9591 |
88
- | 0.1171 | 3.89 | 3500 | 0.1814 | 0.7197 | 0.8118 | 0.7630 | 0.9569 |
89
- | 0.0988 | 4.44 | 4000 | 0.1671 | 0.7795 | 0.8378 | 0.8076 | 0.9618 |
90
- | 0.0974 | 5.0 | 4500 | 0.1547 | 0.7656 | 0.8277 | 0.7955 | 0.9621 |
91
- | 0.0691 | 5.56 | 5000 | 0.1800 | 0.7423 | 0.8243 | 0.7812 | 0.9600 |
92
- | 0.0741 | 6.11 | 5500 | 0.1801 | 0.7465 | 0.8127 | 0.7782 | 0.9612 |
93
- | 0.0563 | 6.67 | 6000 | 0.1942 | 0.7835 | 0.8436 | 0.8125 | 0.9635 |
94
- | 0.045 | 7.22 | 6500 | 0.1929 | 0.7819 | 0.8460 | 0.8127 | 0.9637 |
95
- | 0.0377 | 7.78 | 7000 | 0.1867 | 0.8005 | 0.8518 | 0.8253 | 0.9659 |
96
- | 0.034 | 8.33 | 7500 | 0.2140 | 0.8054 | 0.8451 | 0.8248 | 0.9643 |
97
- | 0.0278 | 8.89 | 8000 | 0.2137 | 0.7953 | 0.8552 | 0.8242 | 0.9649 |
98
- | 0.0224 | 9.44 | 8500 | 0.2105 | 0.8060 | 0.8581 | 0.8312 | 0.9662 |
99
- | 0.021 | 10.0 | 9000 | 0.2110 | 0.8087 | 0.8591 | 0.8331 | 0.9666 |
100
 
101
 
102
  ### Framework versions
 
25
  metrics:
26
  - name: Precision
27
  type: precision
28
+ value: 0.8265817023213473
29
  - name: Recall
30
  type: recall
31
+ value: 0.8764478764478765
32
  - name: F1
33
  type: f1
34
+ value: 0.850784727102366
35
  - name: Accuracy
36
  type: accuracy
37
+ value: 0.9683326090105752
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: 0.1794
48
+ - Precision: 0.8266
49
+ - Recall: 0.8764
50
+ - F1: 0.8508
51
+ - Accuracy: 0.9683
52
 
53
  ## Model description
54
 
 
67
  ### Training hyperparameters
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: 15
77
 
78
  ### Training results
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
+ | 0.2748 | 2.22 | 500 | 0.1464 | 0.7658 | 0.8364 | 0.7995 | 0.9622 |
83
+ | 0.0997 | 4.44 | 1000 | 0.1377 | 0.7822 | 0.8716 | 0.8245 | 0.9653 |
84
+ | 0.0677 | 6.67 | 1500 | 0.1525 | 0.7997 | 0.8769 | 0.8366 | 0.9657 |
85
+ | 0.0452 | 8.89 | 2000 | 0.1426 | 0.8162 | 0.8832 | 0.8484 | 0.9698 |
86
+ | 0.0316 | 11.11 | 2500 | 0.1737 | 0.8232 | 0.8697 | 0.8458 | 0.9683 |
87
+ | 0.023 | 13.33 | 3000 | 0.1794 | 0.8266 | 0.8764 | 0.8508 | 0.9683 |
 
 
 
 
 
 
 
 
 
 
 
 
88
 
89
 
90
  ### Framework versions
runs/Mar05_20-38-08_n21/events.out.tfevents.1709667489.n21.1798944.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd07d6e78ab1d171253e51254760001279cf8587fb16c8d436ea681c11fb2ae7
3
- size 8755
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54b480d8e61d33c8924989e18d61ba0a8c3d1ea63031c91800a9d6ca2002d61b
3
+ size 9109