Hugging Face's logo

dtorber
/
bert-base-cased

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files
xet
Metrics Community
dtorber commited on
Commit
828728a
·
verified ·
1 Parent(s): 140d660

Model save

Browse files
Files changed (1) hide show
  1. README.md +12 -18
README.md CHANGED
@@ -15,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 1.1793
19
- - Icm: 0.1480
20
- - Icmnorm: 0.5752
21
- - Fmeasure: 0.7194
22
 
23
  ## Model description
24
 
@@ -44,27 +44,21 @@ The following hyperparameters were used during training:
44
  - distributed_type: multi-GPU
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
- - num_epochs: 9
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss | Icm | Icmnorm | Fmeasure |
53
- |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
54
- | No log | 1.0 | 193 | 0.6062 | 0.0275 | 0.5140 | 0.6639 |
55
- | No log | 2.0 | 386 | 0.5694 | 0.0336 | 0.5171 | 0.6785 |
56
- | 0.5724 | 3.0 | 579 | 0.8413 | 0.0158 | 0.5080 | 0.6641 |
57
- | 0.5724 | 4.0 | 772 | 1.1793 | 0.1480 | 0.5752 | 0.7194 |
58
- | 0.5724 | 5.0 | 965 | 1.4878 | 0.0672 | 0.5341 | 0.6892 |
59
- | 0.2239 | 6.0 | 1158 | 1.6802 | 0.0966 | 0.5491 | 0.7019 |
60
- | 0.2239 | 7.0 | 1351 | 1.8348 | 0.0799 | 0.5406 | 0.6964 |
61
- | 0.0665 | 8.0 | 1544 | 1.9795 | 0.0606 | 0.5308 | 0.6897 |
62
- | 0.0665 | 9.0 | 1737 | 2.0300 | 0.0606 | 0.5308 | 0.6897 |
63
 
64
 
65
  ### Framework versions
66
 
67
- - Transformers 4.38.2
68
- - Pytorch 2.2.1+cu121
69
  - Datasets 2.18.0
70
  - Tokenizers 0.15.2
 
15
 
16
  This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.5716
19
+ - Icm: 0.1185
20
+ - Icmnorm: 0.5602
21
+ - Fmeasure: 0.7096
22
 
23
  ## Model description
24
 
 
44
  - distributed_type: multi-GPU
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
+ - num_epochs: 3
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss | Icm | Icmnorm | Fmeasure |
53
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:--------:|
54
+ | No log | 1.0 | 193 | 0.6638 | -0.4059 | 0.2938 | 0.3647 |
55
+ | No log | 2.0 | 386 | 0.5637 | -0.0203 | 0.4897 | 0.6511 |
56
+ | 0.6281 | 3.0 | 579 | 0.5716 | 0.1185 | 0.5602 | 0.7096 |
 
 
 
 
 
 
57
 
58
 
59
  ### Framework versions
60
 
61
+ - Transformers 4.39.3
62
+ - Pytorch 2.2.2+cu121
63
  - Datasets 2.18.0
64
  - Tokenizers 0.15.2