Hugging Face's logo

dtorber
/
roberta-base

Text Classification
Transformers
TensorBoard
Safetensors
roberta
Generated from Trainer
Model card Files
xet
Metrics Community
dtorber commited on
Commit
e4631f4
·
verified ·
1 Parent(s): c75601f

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 [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.5272
19
- - Icm: 0.2125
20
- - Icmnorm: 0.6079
21
- - Fmeasure: 0.7412
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 | 0.5272 | 0.2125 | 0.6079 | 0.7412 |
55
- | No log | 2.0 | 386 | 0.5666 | 0.1794 | 0.5911 | 0.7232 |
56
- | 0.5355 | 3.0 | 579 | 0.5858 | 0.2074 | 0.6054 | 0.7394 |
57
- | 0.5355 | 4.0 | 772 | 0.9107 | 0.0682 | 0.5346 | 0.6930 |
58
- | 0.5355 | 5.0 | 965 | 1.4701 | 0.0555 | 0.5282 | 0.6870 |
59
- | 0.2599 | 6.0 | 1158 | 1.5765 | 0.1378 | 0.5700 | 0.7162 |
60
- | 0.2599 | 7.0 | 1351 | 1.8163 | 0.1302 | 0.5661 | 0.7128 |
61
- | 0.1043 | 8.0 | 1544 | 1.8608 | 0.1134 | 0.5576 | 0.7074 |
62
- | 0.1043 | 9.0 | 1737 | 1.8539 | 0.1403 | 0.5713 | 0.7171 |
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 [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.6584
19
+ - Icm: 0.0568
20
+ - Icmnorm: 0.5288
21
+ - Fmeasure: 0.6851
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 | 0.6695 | -0.1296 | 0.4342 | 0.6006 |
55
+ | No log | 2.0 | 386 | 0.6774 | -0.1417 | 0.4281 | 0.5798 |
56
+ | 0.5681 | 3.0 | 579 | 0.6584 | 0.0568 | 0.5288 | 0.6851 |
 
 
 
 
 
 
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