Hugging Face's logo

stulcrad
/
CNEC1_1_extended_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
f0727ec
•
1 Parent(s): a540168

Model save

Browse files
Files changed (3) hide show
  1. README.md +21 -26
  2. model.safetensors +1 -1
  3. runs/Mar06_15-54-44_n21/events.out.tfevents.1709736885.n21.3385858.0 +2 -2
README.md CHANGED
@@ -25,16 +25,16 @@ model-index:
25
  metrics:
26
  - name: Precision
27
  type: precision
28
- value: 0.8595505617977528
29
  - name: Recall
30
  type: recall
31
- value: 0.8995189738107964
32
  - name: F1
33
  type: f1
34
- value: 0.8790806999216505
35
  - name: Accuracy
36
  type: accuracy
37
- value: 0.9695206428373511
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: 0.2397
48
- - Precision: 0.8596
49
- - Recall: 0.8995
50
- - F1: 0.8791
51
- - Accuracy: 0.9695
52
 
53
  ## Model description
54
 
@@ -68,31 +68,26 @@ 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
- - num_epochs: 25
77
 
78
  ### Training results
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
- | 0.3533 | 1.72 | 500 | 0.1415 | 0.7483 | 0.8439 | 0.7933 | 0.9609 |
83
- | 0.1509 | 3.44 | 1000 | 0.1352 | 0.8073 | 0.8685 | 0.8368 | 0.9664 |
84
- | 0.1072 | 5.15 | 1500 | 0.1533 | 0.8151 | 0.8739 | 0.8434 | 0.9674 |
85
- | 0.0778 | 6.87 | 2000 | 0.1740 | 0.8400 | 0.8781 | 0.8586 | 0.9668 |
86
- | 0.059 | 8.59 | 2500 | 0.1676 | 0.8365 | 0.8942 | 0.8644 | 0.9699 |
87
- | 0.0475 | 10.31 | 3000 | 0.1699 | 0.8295 | 0.8813 | 0.8546 | 0.9678 |
88
- | 0.0381 | 12.03 | 3500 | 0.1876 | 0.8418 | 0.8985 | 0.8692 | 0.9686 |
89
- | 0.0287 | 13.75 | 4000 | 0.2100 | 0.8446 | 0.8979 | 0.8705 | 0.9681 |
90
- | 0.0238 | 15.46 | 4500 | 0.2007 | 0.8466 | 0.8995 | 0.8722 | 0.9702 |
91
- | 0.0186 | 17.18 | 5000 | 0.2201 | 0.8568 | 0.8926 | 0.8743 | 0.9689 |
92
- | 0.0161 | 18.9 | 5500 | 0.2200 | 0.8573 | 0.8990 | 0.8776 | 0.9700 |
93
- | 0.014 | 20.62 | 6000 | 0.2326 | 0.8601 | 0.8974 | 0.8784 | 0.9697 |
94
- | 0.0104 | 22.34 | 6500 | 0.2370 | 0.8639 | 0.8990 | 0.8811 | 0.9696 |
95
- | 0.0099 | 24.05 | 7000 | 0.2397 | 0.8596 | 0.8995 | 0.8791 | 0.9695 |
96
 
97
 
98
  ### Framework versions
 
25
  metrics:
26
  - name: Precision
27
  type: precision
28
+ value: 0.8425832492431887
29
  - name: Recall
30
  type: recall
31
+ value: 0.8925708177445216
32
  - name: F1
33
  type: f1
34
+ value: 0.8668569945497016
35
  - name: Accuracy
36
  type: accuracy
37
+ value: 0.968847721964929
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: 0.1815
48
+ - Precision: 0.8426
49
+ - Recall: 0.8926
50
+ - F1: 0.8669
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
+ - num_epochs: 8
77
 
78
  ### Training results
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
+ | 0.3568 | 0.86 | 500 | 0.1652 | 0.7278 | 0.8290 | 0.7751 | 0.9578 |
83
+ | 0.175 | 1.72 | 1000 | 0.1474 | 0.7862 | 0.8530 | 0.8183 | 0.9662 |
84
+ | 0.1225 | 2.58 | 1500 | 0.1417 | 0.8013 | 0.8642 | 0.8316 | 0.9650 |
85
+ | 0.0994 | 3.44 | 2000 | 0.1673 | 0.8095 | 0.8744 | 0.8407 | 0.9654 |
86
+ | 0.0781 | 4.3 | 2500 | 0.1568 | 0.8383 | 0.8808 | 0.8590 | 0.9686 |
87
+ | 0.0638 | 5.16 | 3000 | 0.1653 | 0.8272 | 0.8851 | 0.8552 | 0.9683 |
88
+ | 0.0521 | 6.02 | 3500 | 0.1680 | 0.8419 | 0.8995 | 0.8698 | 0.9695 |
89
+ | 0.0394 | 6.88 | 4000 | 0.1761 | 0.8374 | 0.8920 | 0.8639 | 0.9685 |
90
+ | 0.0326 | 7.75 | 4500 | 0.1815 | 0.8426 | 0.8926 | 0.8669 | 0.9688 |
 
 
 
 
 
91
 
92
 
93
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd343f4159b6742e0ecb5f720368c798643f9e2adace7b4f924ac1f988b6e5b5
3
  size 2235473356
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:504cdfa9dc50d823939f02b59a578c4094de7388f30b9bcbcd58c29bbdceeb5c
3
  size 2235473356
runs/Mar06_15-54-44_n21/events.out.tfevents.1709736885.n21.3385858.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9fe3006ff0b848fa047fb67a96aeac983ab051324824334d0ca43ca1690b27ce
3
- size 10568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a29ae78b2feda3ce39a27943183352f569814f0ebf7a268a89b3d8805edac7cb
3
+ size 10922