Hugging Face's logo

stulcrad
/
CNEC_1_1_slavicbert

Token Classification
Transformers
Safetensors
bert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
stulcrad commited on
Commit
1faa97a
·
verified ·
1 Parent(s): a8b8377

Model save

Browse files
Files changed (1) hide show
  1. README.md +26 -26
README.md CHANGED
@@ -24,16 +24,16 @@ model-index:
24
  metrics:
25
  - name: Precision
26
  type: precision
27
- value: 0.8452586206896552
28
  - name: Recall
29
  type: recall
30
- value: 0.8657836644591611
31
  - name: F1
32
  type: f1
33
- value: 0.8553980370774263
34
  - name: Accuracy
35
  type: accuracy
36
- value: 0.9498620055197792
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: 0.3745
47
- - Precision: 0.8453
48
- - Recall: 0.8658
49
- - F1: 0.8554
50
- - Accuracy: 0.9499
51
 
52
  ## Model description
53
 
@@ -78,23 +78,23 @@ The following hyperparameters were used during training:
78
 
79
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
80
  |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
81
- | 0.4005 | 0.85 | 1000 | 0.2993 | 0.7886 | 0.8150 | 0.8016 | 0.9323 |
82
- | 0.25 | 1.7 | 2000 | 0.2942 | 0.8057 | 0.8128 | 0.8092 | 0.9357 |
83
- | 0.1629 | 2.56 | 3000 | 0.2406 | 0.8247 | 0.8433 | 0.8339 | 0.9454 |
84
- | 0.1144 | 3.41 | 4000 | 0.2402 | 0.8261 | 0.8472 | 0.8365 | 0.9456 |
85
- | 0.1045 | 4.26 | 5000 | 0.2547 | 0.8430 | 0.8631 | 0.8530 | 0.9490 |
86
- | 0.0896 | 5.11 | 6000 | 0.2545 | 0.8417 | 0.8592 | 0.8503 | 0.9495 |
87
- | 0.0677 | 5.96 | 7000 | 0.2587 | 0.8448 | 0.8698 | 0.8571 | 0.9510 |
88
- | 0.0444 | 6.81 | 8000 | 0.3026 | 0.8396 | 0.8623 | 0.8508 | 0.9482 |
89
- | 0.0357 | 7.67 | 9000 | 0.3058 | 0.8400 | 0.8645 | 0.8520 | 0.9471 |
90
- | 0.0255 | 8.52 | 10000 | 0.3153 | 0.8512 | 0.8640 | 0.8576 | 0.9510 |
91
- | 0.0212 | 9.37 | 11000 | 0.3255 | 0.8480 | 0.8645 | 0.8561 | 0.9502 |
92
- | 0.014 | 10.22 | 12000 | 0.3430 | 0.8409 | 0.8658 | 0.8532 | 0.9495 |
93
- | 0.014 | 11.07 | 13000 | 0.3433 | 0.8403 | 0.8640 | 0.8520 | 0.9507 |
94
- | 0.0128 | 11.93 | 14000 | 0.3654 | 0.8438 | 0.8631 | 0.8533 | 0.9501 |
95
- | 0.0092 | 12.78 | 15000 | 0.3683 | 0.8398 | 0.8636 | 0.8515 | 0.9500 |
96
- | 0.0079 | 13.63 | 16000 | 0.3710 | 0.8416 | 0.8609 | 0.8512 | 0.9501 |
97
- | 0.0077 | 14.48 | 17000 | 0.3745 | 0.8453 | 0.8658 | 0.8554 | 0.9499 |
98
 
99
 
100
  ### Framework versions
 
24
  metrics:
25
  - name: Precision
26
  type: precision
27
+ value: 0.8513220632856524
28
  - name: Recall
29
  type: recall
30
+ value: 0.8671081677704194
31
  - name: F1
32
  type: f1
33
+ value: 0.8591426071741033
34
  - name: Accuracy
35
  type: accuracy
36
+ value: 0.9509352959214965
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: 0.3720
47
+ - Precision: 0.8513
48
+ - Recall: 0.8671
49
+ - F1: 0.8591
50
+ - Accuracy: 0.9509
51
 
52
  ## Model description
53
 
 
78
 
79
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
80
  |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
81
+ | 0.3658 | 0.85 | 1000 | 0.2671 | 0.8101 | 0.8172 | 0.8136 | 0.9366 |
82
+ | 0.227 | 1.7 | 2000 | 0.2624 | 0.8190 | 0.8172 | 0.8181 | 0.9380 |
83
+ | 0.141 | 2.56 | 3000 | 0.2474 | 0.8317 | 0.8424 | 0.8370 | 0.9448 |
84
+ | 0.092 | 3.41 | 4000 | 0.2498 | 0.8412 | 0.8534 | 0.8472 | 0.9460 |
85
+ | 0.0839 | 4.26 | 5000 | 0.2689 | 0.8438 | 0.8583 | 0.8510 | 0.9489 |
86
+ | 0.0698 | 5.11 | 6000 | 0.2830 | 0.8420 | 0.8539 | 0.8479 | 0.9473 |
87
+ | 0.0507 | 5.96 | 7000 | 0.2902 | 0.8359 | 0.8503 | 0.8431 | 0.9468 |
88
+ | 0.0344 | 6.81 | 8000 | 0.3221 | 0.8310 | 0.8512 | 0.8410 | 0.9478 |
89
+ | 0.0249 | 7.67 | 9000 | 0.3262 | 0.8444 | 0.8508 | 0.8476 | 0.9478 |
90
+ | 0.0185 | 8.52 | 10000 | 0.3214 | 0.8458 | 0.8525 | 0.8492 | 0.9502 |
91
+ | 0.0151 | 9.37 | 11000 | 0.3399 | 0.8382 | 0.8578 | 0.8479 | 0.9499 |
92
+ | 0.01 | 10.22 | 12000 | 0.3348 | 0.8385 | 0.8574 | 0.8478 | 0.9492 |
93
+ | 0.0086 | 11.07 | 13000 | 0.3636 | 0.8395 | 0.8543 | 0.8468 | 0.9479 |
94
+ | 0.0092 | 11.93 | 14000 | 0.3644 | 0.8419 | 0.8578 | 0.8498 | 0.9485 |
95
+ | 0.0058 | 12.78 | 15000 | 0.3624 | 0.8450 | 0.8618 | 0.8533 | 0.9503 |
96
+ | 0.0032 | 13.63 | 16000 | 0.3703 | 0.8483 | 0.8614 | 0.8548 | 0.9507 |
97
+ | 0.003 | 14.48 | 17000 | 0.3720 | 0.8513 | 0.8671 | 0.8591 | 0.9509 |
98
 
99
 
100
  ### Framework versions