Hugging Face's logo

stulcrad
/
CNEC_2_0_Czert-B-base-cased

Token Classification
Transformers
Safetensors
bert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
stulcrad commited on
Commit
adf0bad
·
verified ·
1 Parent(s): 6d9bbaf

Model save

Browse files
Files changed (2) hide show
  1. README.md +25 -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: 0.8184647302904564
28
  - name: Recall
29
  type: recall
30
- value: 0.8465665236051502
31
  - name: F1
32
  type: f1
33
- value: 0.8322784810126581
34
  - name: Accuracy
35
  type: accuracy
36
- value: 0.9457392050328853
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 [UWB-AIR/Czert-B-base-cased](https://huggingface.co/UWB-AIR/Czert-B-base-cased) on the cnec dataset.
45
  It achieves the following results on the evaluation set:
46
- - Loss: 0.2936
47
- - Precision: 0.8185
48
- - Recall: 0.8466
49
- - F1: 0.8323
50
- - Accuracy: 0.9457
51
 
52
  ## Model description
53
 
@@ -67,22 +67,28 @@ More information needed
67
 
68
  The following hyperparameters were used during training:
69
  - learning_rate: 2e-05
70
- - train_batch_size: 2
71
- - eval_batch_size: 2
72
  - seed: 42
73
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
74
  - lr_scheduler_type: linear
75
- - num_epochs: 5
76
 
77
  ### Training results
78
 
79
- | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
80
- |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
81
- | 0.2505 | 1.0 | 3597 | 0.2431 | 0.7812 | 0.8008 | 0.7909 | 0.9338 |
82
- | 0.1743 | 2.0 | 7194 | 0.2344 | 0.8126 | 0.8358 | 0.8240 | 0.9399 |
83
- | 0.0829 | 3.0 | 10791 | 0.2416 | 0.8124 | 0.8333 | 0.8227 | 0.9429 |
84
- | 0.0591 | 4.0 | 14388 | 0.2782 | 0.8177 | 0.8455 | 0.8314 | 0.9452 |
85
- | 0.0306 | 5.0 | 17985 | 0.2936 | 0.8185 | 0.8466 | 0.8323 | 0.9457 |
 
 
 
 
 
 
86
 
87
 
88
  ### Framework versions
 
24
  metrics:
25
  - name: Precision
26
  type: precision
27
+ value: 0.8034274193548387
28
  - name: Recall
29
  type: recall
30
+ value: 0.8551502145922747
31
  - name: F1
32
  type: f1
33
+ value: 0.8284823284823285
34
  - name: Accuracy
35
  type: accuracy
36
+ value: 0.9442021732913927
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 [UWB-AIR/Czert-B-base-cased](https://huggingface.co/UWB-AIR/Czert-B-base-cased) on the cnec dataset.
45
  It achieves the following results on the evaluation set:
46
+ - Loss: 0.3023
47
+ - Precision: 0.8034
48
+ - Recall: 0.8552
49
+ - F1: 0.8285
50
+ - Accuracy: 0.9442
51
 
52
  ## Model description
53
 
 
67
 
68
  The following hyperparameters were used during training:
69
  - learning_rate: 2e-05
70
+ - train_batch_size: 32
71
+ - eval_batch_size: 32
72
  - seed: 42
73
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
74
  - lr_scheduler_type: linear
75
+ - num_epochs: 25
76
 
77
  ### Training results
78
 
79
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
80
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
81
+ | 0.6206 | 2.22 | 500 | 0.3126 | 0.7032 | 0.7489 | 0.7253 | 0.9228 |
82
+ | 0.2721 | 4.44 | 1000 | 0.2733 | 0.7487 | 0.8065 | 0.7765 | 0.9338 |
83
+ | 0.1976 | 6.67 | 1500 | 0.2585 | 0.7652 | 0.8230 | 0.7930 | 0.9372 |
84
+ | 0.1538 | 8.89 | 2000 | 0.2489 | 0.7823 | 0.8391 | 0.8097 | 0.9419 |
85
+ | 0.1265 | 11.11 | 2500 | 0.2603 | 0.7937 | 0.8448 | 0.8184 | 0.9424 |
86
+ | 0.1044 | 13.33 | 3000 | 0.2814 | 0.7933 | 0.8494 | 0.8204 | 0.9430 |
87
+ | 0.0915 | 15.56 | 3500 | 0.2855 | 0.7987 | 0.8512 | 0.8241 | 0.9432 |
88
+ | 0.0803 | 17.78 | 4000 | 0.2921 | 0.8035 | 0.8569 | 0.8294 | 0.9440 |
89
+ | 0.0738 | 20.0 | 4500 | 0.2936 | 0.8020 | 0.8530 | 0.8267 | 0.9433 |
90
+ | 0.0668 | 22.22 | 5000 | 0.3020 | 0.8042 | 0.8552 | 0.8289 | 0.9445 |
91
+ | 0.0643 | 24.44 | 5500 | 0.3023 | 0.8034 | 0.8552 | 0.8285 | 0.9442 |
92
 
93
 
94
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c920774a707a388402b950f1c8ed9a0119114cd5f67be36f06cb2266287217ca
3
  size 435876004
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e1a00497c66133b5e032d05c160bb6bc82bba8f5fbef4869ab4945c5460def2
3
  size 435876004