Hugging Face's logo

stulcrad
/
CNEC_extended_xlm-roberta-large

Token Classification
Transformers
TensorBoard
Safetensors
Czech
xlm-roberta
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
stulcrad commited on
Commit
d2b7e36
·
verified ·
1 Parent(s): a2c4c0b

Model save

Browse files
Files changed (3) hide show
  1. README.md +22 -16
  2. model.safetensors +1 -1
  3. runs/Feb26_15-35-45_n29/events.out.tfevents.1708958147.n29.26646.0 +2 -2
README.md CHANGED
@@ -25,16 +25,16 @@ model-index:
25
  metrics:
26
  - name: Precision
27
  type: precision
28
- value: 0.8625413320736892
29
  - name: Recall
30
  type: recall
31
- value: 0.9062034739454095
32
  - name: F1
33
  type: f1
34
- value: 0.8838334946757018
35
  - name: Accuracy
36
  type: accuracy
37
- value: 0.9776053864168618
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: 0.1207
48
- - Precision: 0.8625
49
- - Recall: 0.9062
50
- - F1: 0.8838
51
- - Accuracy: 0.9776
52
 
53
  ## Model description
54
 
@@ -73,18 +73,24 @@ The following hyperparameters were used during training:
73
  - seed: 42
74
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
75
  - lr_scheduler_type: linear
76
- - num_epochs: 7
77
 
78
  ### Training results
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
- | 0.2631 | 1.12 | 500 | 0.1266 | 0.7607 | 0.8660 | 0.8099 | 0.9688 |
83
- | 0.1089 | 2.24 | 1000 | 0.1050 | 0.8199 | 0.8854 | 0.8513 | 0.9743 |
84
- | 0.0719 | 3.36 | 1500 | 0.1008 | 0.8400 | 0.8913 | 0.8649 | 0.9768 |
85
- | 0.0512 | 4.47 | 2000 | 0.1027 | 0.8394 | 0.8923 | 0.8650 | 0.9775 |
86
- | 0.0381 | 5.59 | 2500 | 0.1169 | 0.8588 | 0.9027 | 0.8802 | 0.9777 |
87
- | 0.0265 | 6.71 | 3000 | 0.1207 | 0.8625 | 0.9062 | 0.8838 | 0.9776 |
 
 
 
 
 
 
88
 
89
 
90
  ### Framework versions
 
25
  metrics:
26
  - name: Precision
27
  type: precision
28
+ value: 0.8493919550982226
29
  - name: Recall
30
  type: recall
31
+ value: 0.9012406947890819
32
  - name: F1
33
  type: f1
34
+ value: 0.8745485191427884
35
  - name: Accuracy
36
  type: accuracy
37
+ value: 0.977195550351288
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: 0.1518
48
+ - Precision: 0.8494
49
+ - Recall: 0.9012
50
+ - F1: 0.8745
51
+ - Accuracy: 0.9772
52
 
53
  ## Model description
54
 
 
73
  - seed: 42
74
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
75
  - lr_scheduler_type: linear
76
+ - num_epochs: 14
77
 
78
  ### Training results
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
+ | 0.3244 | 1.12 | 500 | 0.1364 | 0.7215 | 0.8462 | 0.7789 | 0.9654 |
83
+ | 0.1375 | 2.24 | 1000 | 0.1184 | 0.7865 | 0.8610 | 0.8221 | 0.9723 |
84
+ | 0.097 | 3.36 | 1500 | 0.1156 | 0.7943 | 0.8680 | 0.8295 | 0.9737 |
85
+ | 0.0754 | 4.47 | 2000 | 0.1192 | 0.7978 | 0.8794 | 0.8366 | 0.9738 |
86
+ | 0.0619 | 5.59 | 2500 | 0.1185 | 0.8168 | 0.8849 | 0.8495 | 0.9751 |
87
+ | 0.0524 | 6.71 | 3000 | 0.1291 | 0.8237 | 0.8834 | 0.8525 | 0.9752 |
88
+ | 0.0417 | 7.83 | 3500 | 0.1251 | 0.8405 | 0.8968 | 0.8677 | 0.9776 |
89
+ | 0.0342 | 8.95 | 4000 | 0.1197 | 0.8280 | 0.8913 | 0.8585 | 0.9771 |
90
+ | 0.0274 | 10.07 | 4500 | 0.1434 | 0.8415 | 0.8983 | 0.8689 | 0.9762 |
91
+ | 0.0233 | 11.19 | 5000 | 0.1527 | 0.8547 | 0.8993 | 0.8764 | 0.9757 |
92
+ | 0.0196 | 12.3 | 5500 | 0.1566 | 0.8531 | 0.9022 | 0.8770 | 0.9766 |
93
+ | 0.0169 | 13.42 | 6000 | 0.1518 | 0.8494 | 0.9012 | 0.8745 | 0.9772 |
94
 
95
 
96
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72638b49a98595a0635d4345f003b1777232801a801fceec7c1eceed668cfbc3
3
  size 2235473356
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:075dbbff49ea7e980579aa41fcc01e4f997fbb7ac43664983fee799234821a88
3
  size 2235473356
runs/Feb26_15-35-45_n29/events.out.tfevents.1708958147.n29.26646.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:74266316676692c423e3e287a7b5f91cbb7c9a8d176276367927bf5303ba8be5
3
- size 12426
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afaf41ad9dfed4419e83ae117e006597b79df366dca1c9712827380d911f96bb
3
+ size 12780