Hugging Face's logo

stulcrad
/
CNEC_1_1_ext_Czert-B-base-cased

Token Classification
Transformers
Safetensors
bert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
stulcrad commited on
Commit
12ed00c
•
1 Parent(s): 5264b3b

End of training

Browse files
Files changed (4) hide show
  1. README.md +18 -14
  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: 0.8373035985808414
28
  - name: Recall
29
  type: recall
30
- value: 0.882950293960449
31
  - name: F1
32
  type: f1
33
- value: 0.8595213319458898
34
  - name: Accuracy
35
  type: accuracy
36
- value: 0.9564921160210239
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: 0.2425
47
- - Precision: 0.8373
48
- - Recall: 0.8830
49
- - F1: 0.8595
50
- - Accuracy: 0.9565
51
 
52
  ## Model description
53
 
@@ -67,8 +67,8 @@ More information needed
67
 
68
  The following hyperparameters were used during training:
69
  - learning_rate: 2e-05
70
- - train_batch_size: 64
71
- - eval_batch_size: 64
72
  - seed: 42
73
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
74
  - lr_scheduler_type: linear
@@ -78,9 +78,13 @@ The following hyperparameters were used during training:
78
 
79
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
80
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
81
- | 0.2228 | 6.85 | 500 | 0.1804 | 0.8316 | 0.8685 | 0.8497 | 0.9540 |
82
- | 0.0528 | 13.7 | 1000 | 0.2139 | 0.8366 | 0.8813 | 0.8584 | 0.9567 |
83
- | 0.0283 | 20.55 | 1500 | 0.2425 | 0.8373 | 0.8830 | 0.8595 | 0.9565 |
 
 
 
 
84
 
85
 
86
  ### Framework versions
 
24
  metrics:
25
  - name: Precision
26
  type: precision
27
+ value: 0.8383838383838383
28
  - name: Recall
29
  type: recall
30
+ value: 0.8872260823089257
31
  - name: F1
32
  type: f1
33
+ value: 0.8621137366917683
34
  - name: Accuracy
35
  type: accuracy
36
+ value: 0.9569787813899163
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: 0.2513
47
+ - Precision: 0.8384
48
+ - Recall: 0.8872
49
+ - F1: 0.8621
50
+ - Accuracy: 0.9570
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
 
78
 
79
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
80
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
81
+ | 0.3012 | 3.42 | 500 | 0.1677 | 0.8115 | 0.8626 | 0.8363 | 0.9518 |
82
+ | 0.1081 | 6.85 | 1000 | 0.1869 | 0.8218 | 0.8749 | 0.8475 | 0.9548 |
83
+ | 0.0654 | 10.27 | 1500 | 0.2132 | 0.8311 | 0.8813 | 0.8555 | 0.9559 |
84
+ | 0.0449 | 13.7 | 2000 | 0.2284 | 0.8296 | 0.8797 | 0.8540 | 0.9559 |
85
+ | 0.0341 | 17.12 | 2500 | 0.2353 | 0.8348 | 0.8856 | 0.8594 | 0.9575 |
86
+ | 0.0267 | 20.55 | 3000 | 0.2413 | 0.8397 | 0.8872 | 0.8628 | 0.9581 |
87
+ | 0.0227 | 23.97 | 3500 | 0.2513 | 0.8384 | 0.8872 | 0.8621 | 0.9570 |
88
 
89
 
90
  ### 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
  "gradient_checkpointing": false,
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
  "gradient_checkpointing": false,
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:fb4e69a5cb9975765f849fb1ee5e60866b0eed1c001427da75b2d9d06ca7646c
3
  size 435636076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:865f2e9ef40a41f5eca3869e95c3069720ec0ac686f26468e2e7162ae6c6be30
3
  size 435636076
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a723514b6dabb4a26429b166ab4402f751a876b7d8b0de64e1e0209f59a6f689
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baac67bd063bdd12190f8f78097c4da13b3a661f5f2630e0c0e73b7455ceed94
3
  size 4728