Hugging Face's logo

AntoineD
/
camembert_classification_tools_qlora

Text Classification
Transformers
PyTorch
camembert
Generated from Trainer
Model card Files Community
1
AntoineD commited on
Commit
d1a8027
·
1 Parent(s): c1321ca

End of training

Browse files
Files changed (2) hide show
  1. README.md +36 -11
  2. adapter_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: 2.1038
21
- - Accuracy: 0.075
22
 
23
  ## Model description
24
 
@@ -37,23 +37,48 @@ More information needed
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
- - learning_rate: 2e-05
41
- - train_batch_size: 48
42
- - eval_batch_size: 48
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
- - num_epochs: 5
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
- | No log | 1.0 | 3 | 2.1032 | 0.075 |
53
- | No log | 2.0 | 6 | 2.1037 | 0.1 |
54
- | No log | 3.0 | 9 | 2.1038 | 0.075 |
55
- | No log | 4.0 | 12 | 2.1037 | 0.075 |
56
- | No log | 5.0 | 15 | 2.1038 | 0.075 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
57
 
58
 
59
  ### 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: 1.6618
21
+ - Accuracy: 0.425
22
 
23
  ## Model description
24
 
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - learning_rate: 0.0001
41
+ - train_batch_size: 24
42
+ - eval_batch_size: 192
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
+ - num_epochs: 30
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | No log | 1.0 | 5 | 2.0911 | 0.075 |
53
+ | No log | 2.0 | 10 | 2.1008 | 0.05 |
54
+ | No log | 3.0 | 15 | 2.1027 | 0.05 |
55
+ | No log | 4.0 | 20 | 2.0983 | 0.1 |
56
+ | No log | 5.0 | 25 | 2.0928 | 0.125 |
57
+ | No log | 6.0 | 30 | 2.0899 | 0.15 |
58
+ | No log | 7.0 | 35 | 2.0827 | 0.175 |
59
+ | No log | 8.0 | 40 | 2.0689 | 0.175 |
60
+ | No log | 9.0 | 45 | 2.0537 | 0.25 |
61
+ | No log | 10.0 | 50 | 2.0350 | 0.3 |
62
+ | No log | 11.0 | 55 | 2.0110 | 0.325 |
63
+ | No log | 12.0 | 60 | 1.9837 | 0.35 |
64
+ | No log | 13.0 | 65 | 1.9513 | 0.4 |
65
+ | No log | 14.0 | 70 | 1.9203 | 0.4 |
66
+ | No log | 15.0 | 75 | 1.8931 | 0.4 |
67
+ | No log | 16.0 | 80 | 1.8668 | 0.4 |
68
+ | No log | 17.0 | 85 | 1.8440 | 0.4 |
69
+ | No log | 18.0 | 90 | 1.8216 | 0.425 |
70
+ | No log | 19.0 | 95 | 1.7954 | 0.425 |
71
+ | No log | 20.0 | 100 | 1.7735 | 0.425 |
72
+ | No log | 21.0 | 105 | 1.7529 | 0.425 |
73
+ | No log | 22.0 | 110 | 1.7339 | 0.425 |
74
+ | No log | 23.0 | 115 | 1.7168 | 0.425 |
75
+ | No log | 24.0 | 120 | 1.7025 | 0.425 |
76
+ | No log | 25.0 | 125 | 1.6904 | 0.425 |
77
+ | No log | 26.0 | 130 | 1.6798 | 0.425 |
78
+ | No log | 27.0 | 135 | 1.6723 | 0.425 |
79
+ | No log | 28.0 | 140 | 1.6667 | 0.425 |
80
+ | No log | 29.0 | 145 | 1.6632 | 0.425 |
81
+ | No log | 30.0 | 150 | 1.6618 | 0.425 |
82
 
83
 
84
  ### Framework versions
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c373aeedaa8faf861de5ec89fa6fc5efb037702c378bc4549c585e51e27e8b7
3
  size 4765133
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a09d81a135751a43c855a49c19ab4a75bab43eb3a02442008f017f3de699723a
3
  size 4765133