Hugging Face's logo

Mbabazi
/
results_distilbert-base-uncased

Text Classification
Transformers
PyTorch
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Community
Mbabazi commited on
Commit
99a67e5
•
1 Parent(s): 322c19b

End of training

Browse files
Files changed (2) hide show
  1. README.md +32 -12
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.4989
21
- - Accuracy: 0.699
22
 
23
  ## Model description
24
 
@@ -37,24 +37,44 @@ More information needed
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
- - learning_rate: 2.8596890720295276e-05
41
- - train_batch_size: 16
42
- - eval_batch_size: 16
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
- - lr_scheduler_warmup_steps: 73
47
- - num_epochs: 5
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
- | 0.399 | 1.0 | 500 | 0.5386 | 0.6795 |
54
- | 0.419 | 2.0 | 1000 | 0.5159 | 0.6805 |
55
- | 0.3266 | 3.0 | 1500 | 0.5357 | 0.686 |
56
- | 0.3992 | 4.0 | 2000 | 0.5063 | 0.6945 |
57
- | 0.33 | 5.0 | 2500 | 0.4989 | 0.699 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
58
 
59
 
60
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.3782
21
+ - Accuracy: 0.744
22
 
23
  ## Model description
24
 
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - learning_rate: 1e-05
41
+ - train_batch_size: 32
42
+ - eval_batch_size: 32
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_steps: 600
47
+ - num_epochs: 3
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | 0.6859 | 0.12 | 30 | 0.6867 | 0.304 |
54
+ | 0.6759 | 0.24 | 60 | 0.6723 | 0.3535 |
55
+ | 0.6508 | 0.36 | 90 | 0.6433 | 0.43 |
56
+ | 0.6046 | 0.48 | 120 | 0.5999 | 0.4915 |
57
+ | 0.5845 | 0.6 | 150 | 0.5733 | 0.491 |
58
+ | 0.579 | 0.72 | 180 | 0.5633 | 0.6455 |
59
+ | 0.5599 | 0.84 | 210 | 0.5484 | 0.5705 |
60
+ | 0.526 | 0.96 | 240 | 0.5208 | 0.679 |
61
+ | 0.4968 | 1.08 | 270 | 0.4765 | 0.7115 |
62
+ | 0.4763 | 1.2 | 300 | 0.4524 | 0.7165 |
63
+ | 0.4565 | 1.32 | 330 | 0.4341 | 0.7205 |
64
+ | 0.4345 | 1.44 | 360 | 0.4254 | 0.7235 |
65
+ | 0.4338 | 1.56 | 390 | 0.4161 | 0.73 |
66
+ | 0.4292 | 1.68 | 420 | 0.4119 | 0.729 |
67
+ | 0.4129 | 1.8 | 450 | 0.4061 | 0.7345 |
68
+ | 0.4036 | 1.92 | 480 | 0.3966 | 0.739 |
69
+ | 0.4019 | 2.04 | 510 | 0.3984 | 0.726 |
70
+ | 0.3794 | 2.16 | 540 | 0.3961 | 0.74 |
71
+ | 0.3756 | 2.28 | 570 | 0.3981 | 0.728 |
72
+ | 0.4565 | 2.4 | 600 | 0.3903 | 0.73 |
73
+ | 0.376 | 2.52 | 630 | 0.3997 | 0.7285 |
74
+ | 0.4023 | 2.64 | 660 | 0.3850 | 0.7435 |
75
+ | 0.3511 | 2.76 | 690 | 0.3802 | 0.742 |
76
+ | 0.3601 | 2.88 | 720 | 0.3782 | 0.744 |
77
+ | 0.3771 | 3.0 | 750 | 0.3792 | 0.742 |
78
 
79
 
80
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dec627e35311e137493689e12b197cf19ea8dbcf6115e1b0ba3e48e8b38b11a0
3
  size 267859050
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36e9e380f920abd8d633472fdb3bfc281e98b1e622612f0e5224f025f6397740
3
  size 267859050