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
a10ca8f
·
verified ·
1 Parent(s): f13cfa7

Model save

Browse files
Files changed (2) hide show
  1. README.md +24 -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: 0.8664521319388576
29
  - name: Recall
30
  type: recall
31
- value: 0.8897149938042132
32
  - name: F1
33
  type: f1
34
- value: 0.8779294884858366
35
  - name: Accuracy
36
  type: accuracy
37
- value: 0.9714616833260901
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: 0.2219
48
- - Precision: 0.8665
49
- - Recall: 0.8897
50
- - F1: 0.8779
51
- - Accuracy: 0.9715
52
 
53
  ## Model description
54
 
@@ -68,25 +68,27 @@ More information needed
68
 
69
  The following hyperparameters were used during training:
70
  - learning_rate: 2e-05
71
- - train_batch_size: 2
72
- - eval_batch_size: 2
73
  - seed: 42
74
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
75
  - lr_scheduler_type: linear
76
- - num_epochs: 8
77
 
78
  ### Training results
79
 
80
- | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
- |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
- | 0.228 | 1.0 | 3597 | 0.1773 | 0.8036 | 0.8364 | 0.8197 | 0.9616 |
83
- | 0.176 | 2.0 | 7194 | 0.1703 | 0.8002 | 0.8505 | 0.8246 | 0.9605 |
84
- | 0.1245 | 3.0 | 10791 | 0.1698 | 0.8009 | 0.8377 | 0.8189 | 0.9643 |
85
- | 0.0916 | 4.0 | 14388 | 0.1898 | 0.8246 | 0.8662 | 0.8449 | 0.9658 |
86
- | 0.082 | 5.0 | 17985 | 0.2007 | 0.8369 | 0.8711 | 0.8537 | 0.9675 |
87
- | 0.0608 | 6.0 | 21582 | 0.1945 | 0.8446 | 0.8802 | 0.8621 | 0.9698 |
88
- | 0.05 | 7.0 | 25179 | 0.2043 | 0.8614 | 0.8885 | 0.8747 | 0.9714 |
89
- | 0.0334 | 8.0 | 28776 | 0.2219 | 0.8665 | 0.8897 | 0.8779 | 0.9715 |
 
 
90
 
91
 
92
  ### Framework versions
 
25
  metrics:
26
  - name: Precision
27
  type: precision
28
+ value: 0.8675762439807384
29
  - name: Recall
30
  type: recall
31
+ value: 0.8930194134655102
32
  - name: F1
33
  type: f1
34
+ value: 0.880113983309587
35
  - name: Accuracy
36
  type: accuracy
37
+ value: 0.9709981167608286
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: 0.1744
48
+ - Precision: 0.8676
49
+ - Recall: 0.8930
50
+ - F1: 0.8801
51
+ - Accuracy: 0.9710
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
+ - num_epochs: 10
77
 
78
  ### Training results
79
 
80
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
+ | 0.4736 | 1.0 | 900 | 0.1585 | 0.7678 | 0.8319 | 0.7986 | 0.9597 |
83
+ | 0.1665 | 2.0 | 1800 | 0.1418 | 0.8237 | 0.8550 | 0.8391 | 0.9650 |
84
+ | 0.129 | 3.0 | 2700 | 0.1361 | 0.8299 | 0.8686 | 0.8488 | 0.9682 |
85
+ | 0.0998 | 4.0 | 3600 | 0.1322 | 0.8474 | 0.8852 | 0.8659 | 0.9698 |
86
+ | 0.0867 | 5.0 | 4500 | 0.1479 | 0.8419 | 0.8823 | 0.8616 | 0.9704 |
87
+ | 0.0709 | 6.0 | 5400 | 0.1418 | 0.8539 | 0.8815 | 0.8675 | 0.9708 |
88
+ | 0.0635 | 7.0 | 6300 | 0.1579 | 0.8626 | 0.8819 | 0.8721 | 0.9704 |
89
+ | 0.0512 | 8.0 | 7200 | 0.1624 | 0.8649 | 0.8910 | 0.8777 | 0.9704 |
90
+ | 0.0444 | 9.0 | 8100 | 0.1670 | 0.8702 | 0.8914 | 0.8806 | 0.9712 |
91
+ | 0.0399 | 10.0 | 9000 | 0.1744 | 0.8676 | 0.8930 | 0.8801 | 0.9710 |
92
 
93
 
94
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f9215a7cfbc3992dac25376bcda68481f59672dd73ba67cdc6e1a559d5d1c34
3
  size 2235481556
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bbc2cf3a5cbfa18d7b77e37d79af09975ff6bb63b060add83ad406f4616b595
3
  size 2235481556