Hugging Face's logo

stulcrad
/
CNEC_2_0_ext_robeczech-base

Token Classification
Transformers
Safetensors
Czech
roberta
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Community
stulcrad commited on
Commit
dbd2428
·
verified ·
1 Parent(s): 2cacf3b

Model save

Browse files
Files changed (2) hide show
  1. README.md +25 -19
  2. model.safetensors +1 -1
README.md CHANGED
@@ -25,16 +25,16 @@ model-index:
25
  metrics:
26
  - name: Precision
27
  type: precision
28
- value: 0.8721215090641842
29
  - name: Recall
30
  type: recall
31
- value: 0.8833746898263027
32
  - name: F1
33
  type: f1
34
- value: 0.8777120315581853
35
  - name: Accuracy
36
  type: accuracy
37
- value: 0.9689010132501948
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: 0.1565
48
- - Precision: 0.8721
49
- - Recall: 0.8834
50
- - F1: 0.8777
51
- - Accuracy: 0.9689
52
 
53
  ## Model description
54
 
@@ -68,22 +68,28 @@ More information needed
68
 
69
  The following hyperparameters were used during training:
70
  - learning_rate: 2e-05
71
- - train_batch_size: 64
72
- - eval_batch_size: 64
73
  - seed: 42
74
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
75
  - lr_scheduler_type: linear
76
- - num_epochs: 25
77
 
78
  ### Training results
79
 
80
- | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
- |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
- | 0.4321 | 4.46 | 500 | 0.1753 | 0.8613 | 0.8352 | 0.8481 | 0.9643 |
83
- | 0.0909 | 8.93 | 1000 | 0.1457 | 0.8640 | 0.8888 | 0.8762 | 0.9695 |
84
- | 0.0484 | 13.39 | 1500 | 0.1493 | 0.8662 | 0.8834 | 0.8747 | 0.9681 |
85
- | 0.0328 | 17.86 | 2000 | 0.1515 | 0.8710 | 0.8844 | 0.8776 | 0.9691 |
86
- | 0.0255 | 22.32 | 2500 | 0.1565 | 0.8721 | 0.8834 | 0.8777 | 0.9689 |
 
 
 
 
 
 
87
 
88
 
89
  ### Framework versions
 
25
  metrics:
26
  - name: Precision
27
  type: precision
28
+ value: 0.8633093525179856
29
  - name: Recall
30
  type: recall
31
+ value: 0.8933002481389578
32
  - name: F1
33
  type: f1
34
+ value: 0.8780487804878048
35
  - name: Accuracy
36
  type: accuracy
37
+ value: 0.9703429462197973
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: 0.1663
48
+ - Precision: 0.8633
49
+ - Recall: 0.8933
50
+ - F1: 0.8780
51
+ - Accuracy: 0.9703
52
 
53
  ## Model description
54
 
 
68
 
69
  The following hyperparameters were used during training:
70
  - learning_rate: 2e-05
71
+ - train_batch_size: 32
72
+ - eval_batch_size: 32
73
  - seed: 42
74
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
75
  - lr_scheduler_type: linear
76
+ - num_epochs: 50
77
 
78
  ### Training results
79
 
80
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
+ |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
+ | 0.2593 | 4.46 | 1000 | 0.1653 | 0.8195 | 0.8223 | 0.8209 | 0.9593 |
83
+ | 0.1209 | 8.93 | 2000 | 0.1355 | 0.8441 | 0.8789 | 0.8612 | 0.9679 |
84
+ | 0.0763 | 13.39 | 3000 | 0.1310 | 0.8591 | 0.8893 | 0.8739 | 0.9709 |
85
+ | 0.0539 | 17.86 | 4000 | 0.1383 | 0.8656 | 0.8953 | 0.8802 | 0.9719 |
86
+ | 0.0403 | 22.32 | 5000 | 0.1392 | 0.8626 | 0.8943 | 0.8782 | 0.9710 |
87
+ | 0.0316 | 26.79 | 6000 | 0.1539 | 0.8606 | 0.8948 | 0.8774 | 0.9712 |
88
+ | 0.0254 | 31.25 | 7000 | 0.1552 | 0.8660 | 0.8913 | 0.8785 | 0.9706 |
89
+ | 0.0211 | 35.71 | 8000 | 0.1621 | 0.8658 | 0.8968 | 0.8810 | 0.9701 |
90
+ | 0.0183 | 40.18 | 9000 | 0.1593 | 0.8688 | 0.8973 | 0.8828 | 0.9718 |
91
+ | 0.0161 | 44.64 | 10000 | 0.1638 | 0.8653 | 0.8993 | 0.8820 | 0.9714 |
92
+ | 0.015 | 49.11 | 11000 | 0.1663 | 0.8633 | 0.8933 | 0.8780 | 0.9703 |
93
 
94
 
95
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa3dda85a314fcd26054cf8662c61b477a9af0da84b1fa489aa7191423fd5881
3
  size 501610932
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fef7fc94ab37e0f6cfa318bee1e76862a530f2cd9e499d9377cced0fa2afe148
3
  size 501610932