Hugging Face's logo

stulcrad
/
CNEC_2_0_Supertypes_slavicbert

Token Classification
Transformers
Safetensors
bert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
stulcrad commited on
Commit
2b7b1bc
·
verified ·
1 Parent(s): 260f014

Model save

Browse files
Files changed (2) hide show
  1. README.md +19 -19
  2. model.safetensors +1 -1
README.md CHANGED
@@ -24,16 +24,16 @@ model-index:
24
  metrics:
25
  - name: Precision
26
  type: precision
27
- value: 0.850996015936255
28
  - name: Recall
29
  type: recall
30
- value: 0.8822800495662949
31
  - name: F1
32
  type: f1
33
- value: 0.8663557087811803
34
  - name: Accuracy
35
  type: accuracy
36
- value: 0.9634174051351966
37
  ---
38
 
39
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -43,11 +43,11 @@ should probably proofread and complete it, then remove this comment. -->
43
 
44
  This model is a fine-tuned version of [DeepPavlov/bert-base-bg-cs-pl-ru-cased](https://huggingface.co/DeepPavlov/bert-base-bg-cs-pl-ru-cased) on the cnec dataset.
45
  It achieves the following results on the evaluation set:
46
- - Loss: 0.1734
47
- - Precision: 0.8510
48
- - Recall: 0.8823
49
- - F1: 0.8664
50
- - Accuracy: 0.9634
51
 
52
  ## Model description
53
 
@@ -72,21 +72,21 @@ The following hyperparameters were used during training:
72
  - seed: 42
73
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
74
  - lr_scheduler_type: linear
75
- - num_epochs: 10
76
 
77
  ### Training results
78
 
79
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
80
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
81
- | 0.3523 | 1.11 | 500 | 0.1580 | 0.7835 | 0.8104 | 0.7968 | 0.9522 |
82
- | 0.1519 | 2.22 | 1000 | 0.1615 | 0.8092 | 0.8567 | 0.8323 | 0.9578 |
83
- | 0.1066 | 3.33 | 1500 | 0.1453 | 0.8456 | 0.8662 | 0.8557 | 0.9633 |
84
- | 0.0818 | 4.44 | 2000 | 0.1649 | 0.8279 | 0.8781 | 0.8523 | 0.9616 |
85
- | 0.0695 | 5.56 | 2500 | 0.1571 | 0.8327 | 0.8761 | 0.8539 | 0.9613 |
86
- | 0.0517 | 6.67 | 3000 | 0.1582 | 0.8365 | 0.8835 | 0.8594 | 0.9631 |
87
- | 0.0448 | 7.78 | 3500 | 0.1656 | 0.8456 | 0.8777 | 0.8614 | 0.9621 |
88
- | 0.037 | 8.89 | 4000 | 0.1738 | 0.8443 | 0.8848 | 0.8641 | 0.9633 |
89
- | 0.0341 | 10.0 | 4500 | 0.1734 | 0.8510 | 0.8823 | 0.8664 | 0.9634 |
90
 
91
 
92
  ### Framework versions
 
24
  metrics:
25
  - name: Precision
26
  type: precision
27
+ value: 0.8494666139865665
28
  - name: Recall
29
  type: recall
30
+ value: 0.8880627839735646
31
  - name: F1
32
  type: f1
33
+ value: 0.8683360258481422
34
  - name: Accuracy
35
  type: accuracy
36
+ value: 0.9631901840490797
37
  ---
38
 
39
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
43
 
44
  This model is a fine-tuned version of [DeepPavlov/bert-base-bg-cs-pl-ru-cased](https://huggingface.co/DeepPavlov/bert-base-bg-cs-pl-ru-cased) on the cnec dataset.
45
  It achieves the following results on the evaluation set:
46
+ - Loss: 0.2536
47
+ - Precision: 0.8495
48
+ - Recall: 0.8881
49
+ - F1: 0.8683
50
+ - Accuracy: 0.9632
51
 
52
  ## Model description
53
 
 
72
  - seed: 42
73
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
74
  - lr_scheduler_type: linear
75
+ - num_epochs: 20
76
 
77
  ### Training results
78
 
79
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
80
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
81
+ | 0.1513 | 2.22 | 1000 | 0.1556 | 0.8152 | 0.8563 | 0.8352 | 0.9577 |
82
+ | 0.0832 | 4.44 | 2000 | 0.1692 | 0.8263 | 0.8703 | 0.8477 | 0.9594 |
83
+ | 0.0542 | 6.67 | 3000 | 0.1692 | 0.8135 | 0.8686 | 0.8402 | 0.9602 |
84
+ | 0.0354 | 8.89 | 4000 | 0.1921 | 0.8375 | 0.8810 | 0.8587 | 0.9614 |
85
+ | 0.0246 | 11.11 | 5000 | 0.2066 | 0.8462 | 0.8798 | 0.8627 | 0.9626 |
86
+ | 0.0153 | 13.33 | 6000 | 0.2333 | 0.8524 | 0.8872 | 0.8695 | 0.9633 |
87
+ | 0.0135 | 15.56 | 7000 | 0.2478 | 0.8463 | 0.8757 | 0.8607 | 0.9614 |
88
+ | 0.0105 | 17.78 | 8000 | 0.2494 | 0.8538 | 0.8831 | 0.8682 | 0.9635 |
89
+ | 0.0085 | 20.0 | 9000 | 0.2536 | 0.8495 | 0.8881 | 0.8683 | 0.9632 |
90
 
91
 
92
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:12e6a3e7cde7df63324f9d13d7942417e2371cdf15344498998f8431b8e37c2c
3
  size 709127044
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cff8ceda3e82a328574c963100d952e4168eca2bf972fd18af7eeedd7beb1889
3
  size 709127044