Hugging Face's logo

stulcrad
/
CNEC_1_1_ext_slavicbert

Token Classification
Transformers
Safetensors
bert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
stulcrad commited on
Commit
54cec44
·
verified ·
1 Parent(s): 5532a59

End of training

Browse files
Files changed (4) hide show
  1. README.md +23 -23
  2. config.json +2 -2
  3. model.safetensors +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -24,16 +24,16 @@ model-index:
24
  metrics:
25
  - name: Precision
26
  type: precision
27
- value: 0.8562564632885212
28
  - name: Recall
29
  type: recall
30
- value: 0.8850881881346874
31
  - name: F1
32
  type: f1
33
- value: 0.8704336399474377
34
  - name: Accuracy
35
  type: accuracy
36
- value: 0.9598901383634761
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: 0.2811
47
- - Precision: 0.8563
48
- - Recall: 0.8851
49
- - F1: 0.8704
50
- - Accuracy: 0.9599
51
 
52
  ## Model description
53
 
@@ -78,20 +78,20 @@ The following hyperparameters were used during training:
78
 
79
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
80
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
81
- | 0.3365 | 1.72 | 500 | 0.1751 | 0.8068 | 0.8546 | 0.8300 | 0.9522 |
82
- | 0.1326 | 3.44 | 1000 | 0.1573 | 0.8427 | 0.8675 | 0.8549 | 0.9589 |
83
- | 0.0901 | 5.15 | 1500 | 0.1800 | 0.8401 | 0.8707 | 0.8551 | 0.9582 |
84
- | 0.0631 | 6.87 | 2000 | 0.1975 | 0.8490 | 0.8803 | 0.8643 | 0.9589 |
85
- | 0.0453 | 8.59 | 2500 | 0.2075 | 0.8447 | 0.8808 | 0.8624 | 0.9608 |
86
- | 0.034 | 10.31 | 3000 | 0.2156 | 0.8497 | 0.8824 | 0.8658 | 0.9605 |
87
- | 0.0268 | 12.03 | 3500 | 0.2378 | 0.8499 | 0.8808 | 0.8651 | 0.9596 |
88
- | 0.0205 | 13.75 | 4000 | 0.2446 | 0.8557 | 0.8878 | 0.8715 | 0.9611 |
89
- | 0.0176 | 15.46 | 4500 | 0.2494 | 0.8571 | 0.8883 | 0.8724 | 0.9611 |
90
- | 0.0141 | 17.18 | 5000 | 0.2607 | 0.8586 | 0.8824 | 0.8703 | 0.9597 |
91
- | 0.0105 | 18.9 | 5500 | 0.2793 | 0.8542 | 0.8830 | 0.8683 | 0.9599 |
92
- | 0.0091 | 20.62 | 6000 | 0.2738 | 0.8487 | 0.8846 | 0.8663 | 0.9586 |
93
- | 0.0076 | 22.34 | 6500 | 0.2773 | 0.8556 | 0.8867 | 0.8709 | 0.9604 |
94
- | 0.0075 | 24.05 | 7000 | 0.2811 | 0.8563 | 0.8851 | 0.8704 | 0.9599 |
95
 
96
 
97
  ### Framework versions
 
24
  metrics:
25
  - name: Precision
26
  type: precision
27
+ value: 0.8606811145510835
28
  - name: Recall
29
  type: recall
30
+ value: 0.8915018706574025
31
  - name: F1
32
  type: f1
33
+ value: 0.8758204253084799
34
  - name: Accuracy
35
  type: accuracy
36
+ value: 0.9626885008032336
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: 0.2572
47
+ - Precision: 0.8607
48
+ - Recall: 0.8915
49
+ - F1: 0.8758
50
+ - Accuracy: 0.9627
51
 
52
  ## Model description
53
 
 
78
 
79
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
80
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
81
+ | 0.3946 | 1.72 | 500 | 0.1925 | 0.7835 | 0.8471 | 0.8141 | 0.9467 |
82
+ | 0.1653 | 3.44 | 1000 | 0.1627 | 0.8340 | 0.8675 | 0.8504 | 0.9572 |
83
+ | 0.1183 | 5.15 | 1500 | 0.1700 | 0.8378 | 0.8808 | 0.8588 | 0.9595 |
84
+ | 0.0869 | 6.87 | 2000 | 0.1901 | 0.8554 | 0.8728 | 0.8640 | 0.9589 |
85
+ | 0.0661 | 8.59 | 2500 | 0.2037 | 0.8482 | 0.8867 | 0.8670 | 0.9595 |
86
+ | 0.053 | 10.31 | 3000 | 0.2011 | 0.8460 | 0.8867 | 0.8659 | 0.9609 |
87
+ | 0.043 | 12.03 | 3500 | 0.2216 | 0.8555 | 0.8888 | 0.8718 | 0.9593 |
88
+ | 0.0358 | 13.75 | 4000 | 0.2245 | 0.8492 | 0.8878 | 0.8680 | 0.9603 |
89
+ | 0.0296 | 15.46 | 4500 | 0.2401 | 0.8513 | 0.8872 | 0.8689 | 0.9603 |
90
+ | 0.0264 | 17.18 | 5000 | 0.2415 | 0.8564 | 0.8862 | 0.8710 | 0.9610 |
91
+ | 0.0212 | 18.9 | 5500 | 0.2570 | 0.8557 | 0.8872 | 0.8712 | 0.9622 |
92
+ | 0.0205 | 20.62 | 6000 | 0.2540 | 0.8567 | 0.8883 | 0.8722 | 0.9616 |
93
+ | 0.0167 | 22.34 | 6500 | 0.2573 | 0.8568 | 0.8894 | 0.8728 | 0.9614 |
94
+ | 0.0161 | 24.05 | 7000 | 0.2572 | 0.8607 | 0.8915 | 0.8758 | 0.9627 |
95
 
96
 
97
  ### Framework versions
config.json CHANGED
@@ -3,11 +3,11 @@
3
  "architectures": [
4
  "BertForTokenClassification"
5
  ],
6
- "attention_probs_dropout_prob": 0.2,
7
  "classifier_dropout": null,
8
  "directionality": "bidi",
9
  "hidden_act": "gelu",
10
- "hidden_dropout_prob": 0.2,
11
  "hidden_size": 768,
12
  "id2label": {
13
  "0": "O",
 
3
  "architectures": [
4
  "BertForTokenClassification"
5
  ],
6
+ "attention_probs_dropout_prob": 0.25,
7
  "classifier_dropout": null,
8
  "directionality": "bidi",
9
  "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.25,
11
  "hidden_size": 768,
12
  "id2label": {
13
  "0": "O",
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f47ad202035e914421575684fb0e0d300e4e243c5995019a49a425ed2a6be53
3
  size 709120892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0e7ed7b2f0a383fb42f326aec99b4e9d86ad31f79108387e2d08226cac7b2c5
3
  size 709120892
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc69bb8a341bf9f8e86fccf8322066958128491e182e96f7e21b34713eb24b31
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3302de9de94fb5ee05ad0c98a1ea6b3a542d27d68cb9f15b444a5baf10c8e3e4
3
  size 4664