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
fa771c9
·
1 Parent(s): 1ddcc03

End of training

Browse files
Files changed (2) hide show
  1. README.md +8 -53
  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: 1.8996
21
- - Accuracy: 0.2941
22
 
23
  ## Model description
24
 
@@ -43,62 +43,17 @@ The following hyperparameters were used during training:
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
- - num_epochs: 50
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
- | No log | 1.0 | 4 | 2.0661 | 0.2157 |
53
- | No log | 2.0 | 8 | 2.0535 | 0.2745 |
54
- | No log | 3.0 | 12 | 2.0413 | 0.2941 |
55
- | No log | 4.0 | 16 | 2.0300 | 0.2941 |
56
- | No log | 5.0 | 20 | 2.0194 | 0.2941 |
57
- | No log | 6.0 | 24 | 2.0096 | 0.2941 |
58
- | No log | 7.0 | 28 | 2.0004 | 0.2941 |
59
- | No log | 8.0 | 32 | 1.9918 | 0.2941 |
60
- | No log | 9.0 | 36 | 1.9840 | 0.2941 |
61
- | No log | 10.0 | 40 | 1.9767 | 0.2941 |
62
- | No log | 11.0 | 44 | 1.9697 | 0.2941 |
63
- | No log | 12.0 | 48 | 1.9631 | 0.2941 |
64
- | No log | 13.0 | 52 | 1.9573 | 0.2941 |
65
- | No log | 14.0 | 56 | 1.9519 | 0.2941 |
66
- | No log | 15.0 | 60 | 1.9472 | 0.2941 |
67
- | No log | 16.0 | 64 | 1.9428 | 0.2941 |
68
- | No log | 17.0 | 68 | 1.9388 | 0.2941 |
69
- | No log | 18.0 | 72 | 1.9353 | 0.2941 |
70
- | No log | 19.0 | 76 | 1.9320 | 0.2941 |
71
- | No log | 20.0 | 80 | 1.9292 | 0.2941 |
72
- | No log | 21.0 | 84 | 1.9267 | 0.2941 |
73
- | No log | 22.0 | 88 | 1.9242 | 0.2941 |
74
- | No log | 23.0 | 92 | 1.9220 | 0.2941 |
75
- | No log | 24.0 | 96 | 1.9199 | 0.2941 |
76
- | No log | 25.0 | 100 | 1.9179 | 0.2941 |
77
- | No log | 26.0 | 104 | 1.9162 | 0.2941 |
78
- | No log | 27.0 | 108 | 1.9144 | 0.2941 |
79
- | No log | 28.0 | 112 | 1.9128 | 0.2941 |
80
- | No log | 29.0 | 116 | 1.9114 | 0.2941 |
81
- | No log | 30.0 | 120 | 1.9101 | 0.2941 |
82
- | No log | 31.0 | 124 | 1.9090 | 0.2941 |
83
- | No log | 32.0 | 128 | 1.9079 | 0.2941 |
84
- | No log | 33.0 | 132 | 1.9069 | 0.2941 |
85
- | No log | 34.0 | 136 | 1.9059 | 0.2941 |
86
- | No log | 35.0 | 140 | 1.9050 | 0.2941 |
87
- | No log | 36.0 | 144 | 1.9042 | 0.2941 |
88
- | No log | 37.0 | 148 | 1.9035 | 0.2941 |
89
- | No log | 38.0 | 152 | 1.9029 | 0.2941 |
90
- | No log | 39.0 | 156 | 1.9023 | 0.2941 |
91
- | No log | 40.0 | 160 | 1.9018 | 0.2941 |
92
- | No log | 41.0 | 164 | 1.9014 | 0.2941 |
93
- | No log | 42.0 | 168 | 1.9010 | 0.2941 |
94
- | No log | 43.0 | 172 | 1.9006 | 0.2941 |
95
- | No log | 44.0 | 176 | 1.9004 | 0.2941 |
96
- | No log | 45.0 | 180 | 1.9001 | 0.2941 |
97
- | No log | 46.0 | 184 | 1.9000 | 0.2941 |
98
- | No log | 47.0 | 188 | 1.8998 | 0.2941 |
99
- | No log | 48.0 | 192 | 1.8997 | 0.2941 |
100
- | No log | 49.0 | 196 | 1.8996 | 0.2941 |
101
- | No log | 50.0 | 200 | 1.8996 | 0.2941 |
102
 
103
 
104
  ### 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: 2.0628
21
+ - Accuracy: 0.2444
22
 
23
  ## Model description
24
 
 
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 | 2.0695 | 0.1778 |
53
+ | No log | 2.0 | 6 | 2.0665 | 0.2444 |
54
+ | No log | 3.0 | 9 | 2.0646 | 0.2444 |
55
+ | No log | 4.0 | 12 | 2.0633 | 0.2444 |
56
+ | No log | 5.0 | 15 | 2.0628 | 0.2444 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
57
 
58
 
59
  ### Framework versions
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e5bedad24fb741ab52fdca3e709a3738eac1940a9f84dd15efaed8b07215ee1
3
  size 3585485
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a20e4f88928331b8202f37269032f03c62f4b7280abd1eb9d1882ce0f32a4bf9
3
  size 3585485