Hugging Face's logo

stulcrad
/
CNEC_2_0_slavicbert

Token Classification
Transformers
Safetensors
bert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
stulcrad commited on
Commit
f15681c
·
verified ·
1 Parent(s): 8adec18

Model save

Browse files
Files changed (1) hide show
  1. README.md +24 -24
README.md CHANGED
@@ -24,16 +24,16 @@ model-index:
24
  metrics:
25
  - name: Precision
26
  type: precision
27
- value: 0.8315461777931512
28
  - name: Recall
29
  type: recall
30
- value: 0.8597997138769671
31
  - name: F1
32
  type: f1
33
- value: 0.8454369614911201
34
  - name: Accuracy
35
  type: accuracy
36
- value: 0.9522835719154737
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: 0.3767
47
- - Precision: 0.8315
48
- - Recall: 0.8598
49
- - F1: 0.8454
50
- - Accuracy: 0.9523
51
 
52
  ## Model description
53
 
@@ -67,8 +67,8 @@ More information needed
67
 
68
  The following hyperparameters were used during training:
69
  - learning_rate: 2e-05
70
- - train_batch_size: 8
71
- - eval_batch_size: 8
72
  - seed: 42
73
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
74
  - lr_scheduler_type: linear
@@ -78,19 +78,19 @@ The following hyperparameters were used during training:
78
 
79
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
80
  |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
81
- | 0.2166 | 2.22 | 2000 | 0.2339 | 0.7952 | 0.8222 | 0.8085 | 0.9430 |
82
- | 0.1161 | 4.44 | 4000 | 0.2299 | 0.8069 | 0.8412 | 0.8237 | 0.9479 |
83
- | 0.0695 | 6.67 | 6000 | 0.2593 | 0.8184 | 0.8559 | 0.8367 | 0.9497 |
84
- | 0.0478 | 8.89 | 8000 | 0.2730 | 0.8246 | 0.8573 | 0.8406 | 0.9497 |
85
- | 0.0301 | 11.11 | 10000 | 0.2964 | 0.8350 | 0.8634 | 0.8490 | 0.9533 |
86
- | 0.0179 | 13.33 | 12000 | 0.3348 | 0.8337 | 0.8605 | 0.8469 | 0.9525 |
87
- | 0.0135 | 15.56 | 14000 | 0.3302 | 0.8238 | 0.8612 | 0.8421 | 0.9518 |
88
- | 0.0095 | 17.78 | 16000 | 0.3534 | 0.8287 | 0.8562 | 0.8422 | 0.9499 |
89
- | 0.0076 | 20.0 | 18000 | 0.3684 | 0.8350 | 0.8562 | 0.8455 | 0.9520 |
90
- | 0.0048 | 22.22 | 20000 | 0.3823 | 0.8328 | 0.8619 | 0.8471 | 0.9527 |
91
- | 0.0057 | 24.44 | 22000 | 0.3834 | 0.8340 | 0.8609 | 0.8472 | 0.9518 |
92
- | 0.0031 | 26.67 | 24000 | 0.3743 | 0.8334 | 0.8609 | 0.8469 | 0.9525 |
93
- | 0.004 | 28.89 | 26000 | 0.3767 | 0.8315 | 0.8598 | 0.8454 | 0.9523 |
94
 
95
 
96
  ### Framework versions
 
24
  metrics:
25
  - name: Precision
26
  type: precision
27
+ value: 0.8427043808209728
28
  - name: Recall
29
  type: recall
30
+ value: 0.8737482117310443
31
  - name: F1
32
  type: f1
33
+ value: 0.8579455662862159
34
  - name: Accuracy
35
  type: accuracy
36
+ value: 0.9552753162160115
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: 0.3354
47
+ - Precision: 0.8427
48
+ - Recall: 0.8737
49
+ - F1: 0.8579
50
+ - Accuracy: 0.9553
51
 
52
  ## Model description
53
 
 
67
 
68
  The following hyperparameters were used during training:
69
  - learning_rate: 2e-05
70
+ - train_batch_size: 16
71
+ - eval_batch_size: 16
72
  - seed: 42
73
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
74
  - lr_scheduler_type: linear
 
78
 
79
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
80
  |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
81
+ | 0.288 | 2.22 | 1000 | 0.2461 | 0.7705 | 0.7926 | 0.7814 | 0.9413 |
82
+ | 0.1551 | 4.44 | 2000 | 0.2270 | 0.8116 | 0.8444 | 0.8277 | 0.9503 |
83
+ | 0.0963 | 6.67 | 3000 | 0.2220 | 0.8181 | 0.8623 | 0.8396 | 0.9533 |
84
+ | 0.0619 | 8.89 | 4000 | 0.2520 | 0.8202 | 0.8598 | 0.8395 | 0.9507 |
85
+ | 0.044 | 11.11 | 5000 | 0.2613 | 0.8332 | 0.8680 | 0.8502 | 0.9535 |
86
+ | 0.0283 | 13.33 | 6000 | 0.2734 | 0.8377 | 0.8673 | 0.8522 | 0.9546 |
87
+ | 0.0227 | 15.56 | 7000 | 0.2908 | 0.8390 | 0.8687 | 0.8536 | 0.9546 |
88
+ | 0.0173 | 17.78 | 8000 | 0.3083 | 0.8393 | 0.8670 | 0.8529 | 0.9528 |
89
+ | 0.013 | 20.0 | 9000 | 0.3238 | 0.8333 | 0.8673 | 0.8500 | 0.9522 |
90
+ | 0.0103 | 22.22 | 10000 | 0.3352 | 0.8325 | 0.8712 | 0.8515 | 0.9539 |
91
+ | 0.0091 | 24.44 | 11000 | 0.3299 | 0.8400 | 0.8655 | 0.8526 | 0.9542 |
92
+ | 0.0073 | 26.67 | 12000 | 0.3376 | 0.8387 | 0.8666 | 0.8524 | 0.9535 |
93
+ | 0.0065 | 28.89 | 13000 | 0.3354 | 0.8427 | 0.8737 | 0.8579 | 0.9553 |
94
 
95
 
96
  ### Framework versions