Hugging Face's logo

tiagoblima
/
newsdata-bert

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
tiagoblima commited on
Commit
62f842e
•
1 Parent(s): f76da88

End of training

Browse files
Files changed (1) hide show
  1. README.md +15 -15
README.md CHANGED
@@ -6,19 +6,19 @@ tags:
6
  metrics:
7
  - accuracy
8
  model-index:
9
- - name: newsdata-cls
10
  results: []
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
  should probably proofread and complete it, then remove this comment. -->
15
 
16
- # newsdata-cls
17
 
18
  This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.0625
21
- - Accuracy: 0.8124
22
 
23
  ## Model description
24
 
@@ -49,17 +49,17 @@ The following hyperparameters were used during training:
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:------:|:-----:|:---------------:|:--------:|
52
- | 1.342 | 0.0859 | 5000 | 1.7155 | 0.6436 |
53
- | 1.2536 | 0.1718 | 10000 | 1.3484 | 0.7139 |
54
- | 1.1442 | 0.2577 | 15000 | 1.2988 | 0.7495 |
55
- | 1.0014 | 0.3436 | 20000 | 1.4252 | 0.7492 |
56
- | 0.8824 | 0.4295 | 25000 | 1.2261 | 0.7733 |
57
- | 0.9017 | 0.5155 | 30000 | 1.1556 | 0.7840 |
58
- | 0.7934 | 0.6014 | 35000 | 1.1842 | 0.7917 |
59
- | 0.9238 | 0.6873 | 40000 | 1.0854 | 0.7990 |
60
- | 0.9034 | 0.7732 | 45000 | 1.1318 | 0.7978 |
61
- | 0.7515 | 0.8591 | 50000 | 1.0742 | 0.8049 |
62
- | 0.7735 | 0.9450 | 55000 | 1.0625 | 0.8124 |
63
 
64
 
65
  ### Framework versions
 
6
  metrics:
7
  - accuracy
8
  model-index:
9
+ - name: newsdata-bert
10
  results: []
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
  should probably proofread and complete it, then remove this comment. -->
15
 
16
+ # newsdata-bert
17
 
18
  This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 1.0878
21
+ - Accuracy: 0.8087
22
 
23
  ## Model description
24
 
 
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:------:|:-----:|:---------------:|:--------:|
52
+ | 1.3096 | 0.0859 | 5000 | 1.4907 | 0.7014 |
53
+ | 1.2402 | 0.1718 | 10000 | 1.2411 | 0.7285 |
54
+ | 1.1273 | 0.2577 | 15000 | 1.3464 | 0.7514 |
55
+ | 1.0028 | 0.3436 | 20000 | 1.4583 | 0.7323 |
56
+ | 0.9333 | 0.4295 | 25000 | 1.2102 | 0.7713 |
57
+ | 0.9045 | 0.5155 | 30000 | 1.1515 | 0.7801 |
58
+ | 0.7642 | 0.6014 | 35000 | 1.1968 | 0.7873 |
59
+ | 0.8657 | 0.6873 | 40000 | 1.0961 | 0.7967 |
60
+ | 0.8082 | 0.7732 | 45000 | 1.1199 | 0.7977 |
61
+ | 0.7657 | 0.8591 | 50000 | 1.1115 | 0.8029 |
62
+ | 0.7556 | 0.9450 | 55000 | 1.0878 | 0.8087 |
63
 
64
 
65
  ### Framework versions