Hugging Face's logo

Huseyin
/
bert-base-turkish-cased-ner-finetuned-ner

Token Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Huseyin commited on
Commit
e6c600d
•
1 Parent(s): 124cede

Model save

Browse files
Files changed (2) hide show
  1. README.md +16 -11
  2. runs/Sep04_19-15-01_846893b2349c/events.out.tfevents.1725477303.846893b2349c.1444.0 +2 -2
README.md CHANGED
@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
21
 
22
  This model is a fine-tuned version of [akdeniz27/bert-base-turkish-cased-ner](https://huggingface.co/akdeniz27/bert-base-turkish-cased-ner) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 0.1768
25
- - Precision: 0.9689
26
- - Recall: 0.9688
27
- - F1: 0.9688
28
- - Accuracy: 0.9711
29
 
30
  ## Model description
31
 
@@ -50,17 +50,22 @@ The following hyperparameters were used during training:
50
  - seed: 42
51
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
  - lr_scheduler_type: linear
53
- - num_epochs: 5
54
 
55
  ### Training results
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
58
  |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
59
- | 0.1616 | 1.0 | 3334 | 0.1414 | 0.9622 | 0.9624 | 0.9623 | 0.9651 |
60
- | 0.1143 | 2.0 | 6668 | 0.1483 | 0.9667 | 0.9672 | 0.9670 | 0.9694 |
61
- | 0.0957 | 3.0 | 10002 | 0.1531 | 0.9680 | 0.9682 | 0.9681 | 0.9705 |
62
- | 0.0488 | 4.0 | 13336 | 0.1720 | 0.9690 | 0.9688 | 0.9689 | 0.9713 |
63
- | 0.03 | 5.0 | 16670 | 0.1768 | 0.9689 | 0.9688 | 0.9688 | 0.9711 |
 
 
 
 
 
64
 
65
 
66
  ### Framework versions
 
21
 
22
  This model is a fine-tuned version of [akdeniz27/bert-base-turkish-cased-ner](https://huggingface.co/akdeniz27/bert-base-turkish-cased-ner) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 0.2379
25
+ - Precision: 0.9707
26
+ - Recall: 0.9708
27
+ - F1: 0.9708
28
+ - Accuracy: 0.9729
29
 
30
  ## Model description
31
 
 
50
  - seed: 42
51
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
  - lr_scheduler_type: linear
53
+ - num_epochs: 10
54
 
55
  ### Training results
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
58
  |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
59
+ | 0.1631 | 1.0 | 3334 | 0.1465 | 0.9620 | 0.9627 | 0.9624 | 0.9651 |
60
+ | 0.1162 | 2.0 | 6668 | 0.1524 | 0.9659 | 0.9655 | 0.9657 | 0.9683 |
61
+ | 0.0938 | 3.0 | 10002 | 0.1452 | 0.9686 | 0.9691 | 0.9688 | 0.9712 |
62
+ | 0.048 | 4.0 | 13336 | 0.1734 | 0.9698 | 0.9697 | 0.9698 | 0.9719 |
63
+ | 0.0359 | 5.0 | 16670 | 0.1810 | 0.9701 | 0.9703 | 0.9702 | 0.9723 |
64
+ | 0.0274 | 6.0 | 20004 | 0.1941 | 0.9713 | 0.9713 | 0.9713 | 0.9734 |
65
+ | 0.0187 | 7.0 | 23338 | 0.2185 | 0.9700 | 0.9700 | 0.9700 | 0.9722 |
66
+ | 0.0229 | 8.0 | 26672 | 0.2265 | 0.9706 | 0.9707 | 0.9707 | 0.9728 |
67
+ | 0.015 | 9.0 | 30006 | 0.2325 | 0.9706 | 0.9705 | 0.9706 | 0.9729 |
68
+ | 0.009 | 10.0 | 33340 | 0.2379 | 0.9707 | 0.9708 | 0.9708 | 0.9729 |
69
 
70
 
71
  ### Framework versions
runs/Sep04_19-15-01_846893b2349c/events.out.tfevents.1725477303.846893b2349c.1444.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ddd81968ae835e82cc974b4d196487de56e34aa5e0d9964326cd36d4f4887af
3
- size 24141
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17b355bd761a4f48433f63da066cbb12e1c8b46e9d1172258415141a0cd592ec
3
+ size 24982