Hugging Face's logo

Priyanka-Balivada
/
Russian-BERT

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
Priyanka-Balivada commited on
Commit
c635f6a
·
verified ·
1 Parent(s): 4d9aa63

Russian-BERT

Browse files
Files changed (2) hide show
  1. README.md +13 -11
  2. training_args.bin +1 -1
README.md CHANGED
@@ -1,13 +1,13 @@
1
  ---
2
- base_model: bert-base-uncased
3
  library_name: transformers
4
  license: apache-2.0
 
 
 
5
  metrics:
6
  - accuracy
7
  - precision
8
  - recall
9
- tags:
10
- - generated_from_trainer
11
  model-index:
12
  - name: russian-BERT
13
  results: []
@@ -20,12 +20,12 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.4908
24
- - Accuracy: 0.791
25
- - Precision: 0.7891
26
- - Recall: 0.791
27
- - Micro-avg-recall: 0.791
28
- - Micro-avg-precision: 0.791
29
 
30
  ## Model description
31
 
@@ -50,13 +50,15 @@ The following hyperparameters were used during training:
50
  - seed: 42
51
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
  - lr_scheduler_type: linear
53
- - num_epochs: 1
54
 
55
  ### Training results
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | Micro-avg-recall | Micro-avg-precision |
58
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:----------------:|:-------------------:|
59
- | 0.4459 | 1.0 | 750 | 0.4908 | 0.791 | 0.7891 | 0.791 | 0.791 | 0.791 |
 
 
60
 
61
 
62
  ### Framework versions
 
1
  ---
 
2
  library_name: transformers
3
  license: apache-2.0
4
+ base_model: bert-base-uncased
5
+ tags:
6
+ - generated_from_trainer
7
  metrics:
8
  - accuracy
9
  - precision
10
  - recall
 
 
11
  model-index:
12
  - name: russian-BERT
13
  results: []
 
20
 
21
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.5780
24
+ - Accuracy: 0.8663
25
+ - Precision: 0.8662
26
+ - Recall: 0.8663
27
+ - Micro-avg-recall: 0.8663
28
+ - Micro-avg-precision: 0.8663
29
 
30
  ## Model description
31
 
 
50
  - seed: 42
51
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
  - lr_scheduler_type: linear
53
+ - num_epochs: 3
54
 
55
  ### Training results
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | Micro-avg-recall | Micro-avg-precision |
58
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:----------------:|:-------------------:|
59
+ | 0.4094 | 1.0 | 750 | 0.4025 | 0.8393 | 0.8417 | 0.8393 | 0.8393 | 0.8393 |
60
+ | 0.3033 | 2.0 | 1500 | 0.4566 | 0.8617 | 0.8618 | 0.8617 | 0.8617 | 0.8617 |
61
+ | 0.0816 | 3.0 | 2250 | 0.5780 | 0.8663 | 0.8662 | 0.8663 | 0.8663 | 0.8663 |
62
 
63
 
64
  ### Framework versions
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c09802d493eb7d0b790c01e02b34eb4bb6a849f1ad39c9ea859b8fcc1ac5ee44
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71371b9ca85f849e225e34e91f4bbf10c682c49ba537adf32caff12695e456fc
3
  size 5176