Hugging Face's logo

annavtkn
/
ru_sentiment_classification_model

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
Metrics Community
annavtkn commited on
Commit
3d1ca25
·
verified ·
1 Parent(s): 7d7a9e8

End of training

Browse files
Files changed (2) hide show
  1. README.md +13 -16
  2. model.safetensors +1 -1
README.md CHANGED
@@ -1,11 +1,8 @@
1
  ---
2
  license: mit
3
- language: ru
4
- widget:
5
- - text: "Пусть в жизни будут только удача, мир и радость, чтобы каждый новый день был праздником!"
6
  tags:
7
  - generated_from_trainer
8
- base_model: r1char9/rubert-base-cased-russian-sentiment
9
  metrics:
10
  - accuracy
11
  - precision
@@ -23,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
23
 
24
  This model is a fine-tuned version of [r1char9/rubert-base-cased-russian-sentiment](https://huggingface.co/r1char9/rubert-base-cased-russian-sentiment) on an unknown dataset.
25
  It achieves the following results on the evaluation set:
26
- - Loss: 1.7114
27
- - Accuracy: 0.7556
28
- - Precision: 0.7599
29
- - Recall: 0.7556
30
- - F1: 0.7572
31
 
32
  ## Model description
33
 
@@ -52,22 +49,22 @@ The following hyperparameters were used during training:
52
  - seed: 42
53
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
54
  - lr_scheduler_type: linear
55
- - num_epochs: 5.0
56
 
57
  ### Training results
58
 
59
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
60
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:|
61
- | 0.5784 | 1.0 | 2500 | 0.6348 | 0.7398 | 0.7469 | 0.7398 | 0.7421 |
62
- | 0.4404 | 2.0 | 5000 | 0.7082 | 0.7671 | 0.7636 | 0.7671 | 0.7640 |
63
- | 0.3333 | 3.0 | 7500 | 1.1448 | 0.7538 | 0.7497 | 0.7538 | 0.7507 |
64
- | 0.1922 | 4.0 | 10000 | 1.4089 | 0.7594 | 0.7638 | 0.7594 | 0.7606 |
65
- | 0.0561 | 5.0 | 12500 | 1.7114 | 0.7556 | 0.7599 | 0.7556 | 0.7572 |
66
 
67
 
68
  ### Framework versions
69
 
70
  - Transformers 4.40.0
71
- - Pytorch 2.2.1+cu121
72
  - Datasets 2.19.0
73
  - Tokenizers 0.19.1
 
1
  ---
2
  license: mit
3
+ base_model: r1char9/rubert-base-cased-russian-sentiment
 
 
4
  tags:
5
  - generated_from_trainer
 
6
  metrics:
7
  - accuracy
8
  - precision
 
20
 
21
  This model is a fine-tuned version of [r1char9/rubert-base-cased-russian-sentiment](https://huggingface.co/r1char9/rubert-base-cased-russian-sentiment) on an unknown dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.5070
24
+ - Accuracy: 0.8204
25
+ - Precision: 0.7323
26
+ - Recall: 0.8204
27
+ - F1: 0.7715
28
 
29
  ## Model description
30
 
 
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
+ - num_epochs: 5
53
 
54
  ### Training results
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
57
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:|
58
+ | 0.5712 | 1.0 | 4574 | 0.5314 | 0.8280 | 0.7820 | 0.8280 | 0.7843 |
59
+ | 0.6346 | 2.0 | 9148 | 0.5961 | 0.7612 | 0.7128 | 0.7612 | 0.7101 |
60
+ | 0.7566 | 3.0 | 13722 | 0.7483 | 0.7451 | 0.5552 | 0.7451 | 0.6363 |
61
+ | 0.6369 | 4.0 | 18296 | 0.7451 | 0.7475 | 0.6487 | 0.7475 | 0.6425 |
62
+ | 0.4977 | 5.0 | 22870 | 0.5070 | 0.8204 | 0.7323 | 0.8204 | 0.7715 |
63
 
64
 
65
  ### Framework versions
66
 
67
  - Transformers 4.40.0
68
+ - Pytorch 2.3.0+cu121
69
  - Datasets 2.19.0
70
  - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6eb56d1e87ae72a5340cccbb6f669494ad843b079e25fd1667b0c51634c78f1a
3
  size 711446532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54c75ea301abc4b289e732ab15f4d59ef7457a094d1df4ff04b4ad3c3aafb54f
3
  size 711446532