Hugging Face's logo

Tanor
/
BERTicSENTPOS4

Text Classification
Transformers
PyTorch
Safetensors
Serbian
electra
serbian
sentiment-analysis
wordnet
sentiwordnet
lexicon-induction
Model card Files
xet
 Community
Tanor commited on
Commit
7ff98da
·
1 Parent(s): 97ad6d3

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -19
README.md CHANGED
@@ -1,4 +1,6 @@
1
  ---
 
 
2
  tags:
3
  - generated_from_trainer
4
  metrics:
@@ -6,10 +8,6 @@ metrics:
6
  model-index:
7
  - name: BERTicSENTPOS4
8
  results: []
9
- license: apache-2.0
10
- language:
11
- - sr
12
- pipeline_tag: text-classification
13
  ---
14
 
15
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -17,11 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  # BERTicSENTPOS4
19
 
20
- This model is a fine-tuned version of [classla/bcms-bertic](https://huggingface.co/classla/bcms-bertic)
21
- modified for text classification on the curated definitions from Serbian Wordent.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.0444
24
- - F1: 0.5263
25
 
26
  ## Model description
27
 
@@ -54,18 +51,17 @@ The following hyperparameters were used during training:
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | F1 |
56
  |:-------------:|:-----:|:----:|:---------------:|:------:|
57
- | No log | 1.0 | 53 | 0.0756 | 0.0 |
58
- | No log | 2.0 | 106 | 0.0437 | 0.0 |
59
- | No log | 3.0 | 159 | 0.0371 | 0.3750 |
60
- | No log | 4.0 | 212 | 0.0369 | 0.3871 |
61
- | No log | 5.0 | 265 | 0.0376 | 0.4848 |
62
- | No log | 6.0 | 318 | 0.0424 | 0.5263 |
63
- | No log | 7.0 | 371 | 0.0444 | 0.5263 |
64
 
65
 
66
  ### Framework versions
67
 
68
- - Transformers 4.30.2
69
- - Pytorch 2.0.1
70
- - Datasets 2.13.1
71
- - Tokenizers 0.13.3
 
1
  ---
2
+ license: apache-2.0
3
+ base_model: Tanor/BERTicSENTPOS4
4
  tags:
5
  - generated_from_trainer
6
  metrics:
 
8
  model-index:
9
  - name: BERTicSENTPOS4
10
  results: []
 
 
 
 
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
15
 
16
  # BERTicSENTPOS4
17
 
18
+ This model is a fine-tuned version of [Tanor/BERTicSENTPOS4](https://huggingface.co/Tanor/BERTicSENTPOS4) on the None dataset.
 
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.0550
21
+ - F1: 0.5143
22
 
23
  ## Model description
24
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | F1 |
53
  |:-------------:|:-----:|:----:|:---------------:|:------:|
54
+ | No log | 0.98 | 47 | 0.0692 | 0.0 |
55
+ | No log | 1.99 | 95 | 0.0492 | 0.0 |
56
+ | No log | 2.99 | 143 | 0.0470 | 0.3158 |
57
+ | No log | 4.0 | 191 | 0.0471 | 0.4815 |
58
+ | No log | 4.98 | 238 | 0.0513 | 0.5172 |
59
+ | No log | 5.99 | 286 | 0.0550 | 0.5143 |
 
60
 
61
 
62
  ### Framework versions
63
 
64
+ - Transformers 4.31.0
65
+ - Pytorch 2.1.0.dev20230801
66
+ - Datasets 2.14.2
67
+ - Tokenizers 0.13.3