Hugging Face's logo

RKessler
/
VogagenRelation

Text Classification
Transformers
PyTorch
camembert
Generated from Trainer
Inference Endpoints
Model card Files Community
RKessler commited on
Commit
560e03d
•
1 Parent(s): dd4e066

End of training

Browse files
Files changed (2) hide show
  1. README.md +21 -41
  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 [camembert-base](https://huggingface.co/camembert-base) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.6923
21
- - Accuracy: 0.5413
22
 
23
  ## Model description
24
 
@@ -37,7 +37,7 @@ More information needed
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
- - learning_rate: 1e-08
41
  - train_batch_size: 8
42
  - eval_batch_size: 8
43
  - seed: 42
@@ -49,44 +49,24 @@ The following hyperparameters were used during training:
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
- | No log | 0.21 | 100 | 0.6924 | 0.5398 |
53
- | No log | 0.42 | 200 | 0.6924 | 0.5406 |
54
- | No log | 0.62 | 300 | 0.6924 | 0.5421 |
55
- | No log | 0.83 | 400 | 0.6924 | 0.5406 |
56
- | 0.6921 | 1.04 | 500 | 0.6924 | 0.5421 |
57
- | 0.6921 | 1.25 | 600 | 0.6923 | 0.5406 |
58
- | 0.6921 | 1.46 | 700 | 0.6923 | 0.5406 |
59
- | 0.6921 | 1.66 | 800 | 0.6923 | 0.5406 |
60
- | 0.6921 | 1.87 | 900 | 0.6923 | 0.5398 |
61
- | 0.6923 | 2.08 | 1000 | 0.6923 | 0.5406 |
62
- | 0.6923 | 2.29 | 1100 | 0.6923 | 0.5406 |
63
- | 0.6923 | 2.49 | 1200 | 0.6923 | 0.5390 |
64
- | 0.6923 | 2.7 | 1300 | 0.6923 | 0.5390 |
65
- | 0.6923 | 2.91 | 1400 | 0.6923 | 0.5398 |
66
- | 0.6927 | 3.12 | 1500 | 0.6923 | 0.5406 |
67
- | 0.6927 | 3.33 | 1600 | 0.6923 | 0.5398 |
68
- | 0.6927 | 3.53 | 1700 | 0.6923 | 0.5398 |
69
- | 0.6927 | 3.74 | 1800 | 0.6923 | 0.5398 |
70
- | 0.6927 | 3.95 | 1900 | 0.6923 | 0.5413 |
71
- | 0.6933 | 4.16 | 2000 | 0.6923 | 0.5413 |
72
- | 0.6933 | 4.37 | 2100 | 0.6923 | 0.5413 |
73
- | 0.6933 | 4.57 | 2200 | 0.6923 | 0.5413 |
74
- | 0.6933 | 4.78 | 2300 | 0.6923 | 0.5406 |
75
- | 0.6933 | 4.99 | 2400 | 0.6923 | 0.5406 |
76
- | 0.6932 | 5.2 | 2500 | 0.6923 | 0.5406 |
77
- | 0.6932 | 5.41 | 2600 | 0.6923 | 0.5413 |
78
- | 0.6932 | 5.61 | 2700 | 0.6923 | 0.5429 |
79
- | 0.6932 | 5.82 | 2800 | 0.6923 | 0.5421 |
80
- | 0.6932 | 6.03 | 2900 | 0.6923 | 0.5406 |
81
- | 0.6917 | 6.24 | 3000 | 0.6923 | 0.5421 |
82
- | 0.6917 | 6.44 | 3100 | 0.6923 | 0.5421 |
83
- | 0.6917 | 6.65 | 3200 | 0.6923 | 0.5421 |
84
- | 0.6917 | 6.86 | 3300 | 0.6923 | 0.5413 |
85
- | 0.6917 | 7.07 | 3400 | 0.6923 | 0.5413 |
86
- | 0.6929 | 7.28 | 3500 | 0.6923 | 0.5413 |
87
- | 0.6929 | 7.48 | 3600 | 0.6923 | 0.5413 |
88
- | 0.6929 | 7.69 | 3700 | 0.6923 | 0.5413 |
89
- | 0.6929 | 7.9 | 3800 | 0.6923 | 0.5413 |
90
 
91
 
92
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [camembert-base](https://huggingface.co/camembert-base) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.4131
21
+ - Accuracy: 0.9071
22
 
23
  ## Model description
24
 
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - learning_rate: 5e-05
41
  - train_batch_size: 8
42
  - eval_batch_size: 8
43
  - seed: 42
 
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | No log | 0.21 | 100 | 0.5924 | 0.7073 |
53
+ | No log | 0.42 | 200 | 0.4924 | 0.7955 |
54
+ | No log | 0.62 | 300 | 0.4830 | 0.8126 |
55
+ | No log | 0.83 | 400 | 0.3957 | 0.8595 |
56
+ | 0.5304 | 1.04 | 500 | 0.4586 | 0.8462 |
57
+ | 0.5304 | 1.25 | 600 | 0.4679 | 0.8353 |
58
+ | 0.5304 | 1.46 | 700 | 0.4326 | 0.8579 |
59
+ | 0.5304 | 1.66 | 800 | 0.3330 | 0.8876 |
60
+ | 0.5304 | 1.87 | 900 | 0.3848 | 0.8790 |
61
+ | 0.3573 | 2.08 | 1000 | 0.4247 | 0.8798 |
62
+ | 0.3573 | 2.29 | 1100 | 0.4536 | 0.8767 |
63
+ | 0.3573 | 2.49 | 1200 | 0.4686 | 0.8751 |
64
+ | 0.3573 | 2.7 | 1300 | 0.4457 | 0.8899 |
65
+ | 0.3573 | 2.91 | 1400 | 0.4325 | 0.8860 |
66
+ | 0.2462 | 3.12 | 1500 | 0.4730 | 0.8759 |
67
+ | 0.2462 | 3.33 | 1600 | 0.4275 | 0.9009 |
68
+ | 0.2462 | 3.53 | 1700 | 0.4365 | 0.8993 |
69
+ | 0.2462 | 3.74 | 1800 | 0.4131 | 0.9071 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
70
 
71
 
72
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d95a135fd28bbfb5a0e8f6951b04e38bbb322f42cb21a100740440ac1332b796
3
  size 442563374
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7db8c35ecca0ea1b94987840e62f79273c4a6727285bfcf0fbbd18094081e1d
3
  size 442563374