Hugging Face's logo

stulcrad
/
CNEC_1_1_robeczech-base

Token Classification
Transformers
Safetensors
roberta
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
stulcrad commited on
Commit
5153cac
•
1 Parent(s): 3770f36

Model save

Browse files
Files changed (1) hide show
  1. README.md +14 -18
README.md CHANGED
@@ -25,16 +25,16 @@ model-index:
25
  metrics:
26
  - name: Precision
27
  type: precision
28
- value: 0.8457943925233645
29
  - name: Recall
30
  type: recall
31
- value: 0.879028697571744
32
  - name: F1
33
  type: f1
34
- value: 0.8620913617666162
35
  - name: Accuracy
36
  type: accuracy
37
- value: 0.9463553826199741
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 [ufal/robeczech-base](https://huggingface.co/ufal/robeczech-base) on the cnec dataset.
46
  It achieves the following results on the evaluation set:
47
- - Loss: 0.2802
48
- - Precision: 0.8458
49
- - Recall: 0.8790
50
- - F1: 0.8621
51
- - Accuracy: 0.9464
52
 
53
  ## Model description
54
 
@@ -73,20 +73,16 @@ 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: 60
77
 
78
  ### Training results
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
- | 0.7893 | 6.8 | 1000 | 0.5640 | 0.5842 | 0.4671 | 0.5191 | 0.8830 |
83
- | 0.3629 | 13.61 | 2000 | 0.3352 | 0.7879 | 0.8035 | 0.7956 | 0.9299 |
84
- | 0.2227 | 20.41 | 3000 | 0.2793 | 0.8264 | 0.8490 | 0.8375 | 0.9437 |
85
- | 0.1577 | 27.21 | 4000 | 0.2646 | 0.8495 | 0.8649 | 0.8571 | 0.9477 |
86
- | 0.1193 | 34.01 | 5000 | 0.2713 | 0.8491 | 0.8720 | 0.8604 | 0.9478 |
87
- | 0.0947 | 40.82 | 6000 | 0.2670 | 0.8560 | 0.8742 | 0.8650 | 0.9494 |
88
- | 0.0792 | 47.62 | 7000 | 0.2791 | 0.8551 | 0.8804 | 0.8675 | 0.9479 |
89
- | 0.0706 | 54.42 | 8000 | 0.2802 | 0.8458 | 0.8790 | 0.8621 | 0.9464 |
90
 
91
 
92
  ### Framework versions
 
25
  metrics:
26
  - name: Precision
27
  type: precision
28
+ value: 0.8540680154972019
29
  - name: Recall
30
  type: recall
31
+ value: 0.8759381898454747
32
  - name: F1
33
  type: f1
34
+ value: 0.8648648648648649
35
  - name: Accuracy
36
  type: accuracy
37
+ value: 0.9496757457846952
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 [ufal/robeczech-base](https://huggingface.co/ufal/robeczech-base) on the cnec dataset.
46
  It achieves the following results on the evaluation set:
47
+ - Loss: 0.2682
48
+ - Precision: 0.8541
49
+ - Recall: 0.8759
50
+ - F1: 0.8649
51
+ - Accuracy: 0.9497
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: 30
77
 
78
  ### Training results
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
+ | 0.5187 | 6.8 | 1000 | 0.3863 | 0.7882 | 0.8115 | 0.7997 | 0.9328 |
83
+ | 0.222 | 13.61 | 2000 | 0.2829 | 0.8376 | 0.8561 | 0.8467 | 0.9463 |
84
+ | 0.1408 | 20.41 | 3000 | 0.2662 | 0.8493 | 0.8684 | 0.8588 | 0.9493 |
85
+ | 0.1071 | 27.21 | 4000 | 0.2682 | 0.8541 | 0.8759 | 0.8649 | 0.9497 |
 
 
 
 
86
 
87
 
88
  ### Framework versions