Hugging Face's logo

AntoineD
/
camembert_classification_tools_qlora

Text Classification
Transformers
PyTorch
camembert
Generated from Trainer
Inference Endpoints
Model card Files Community
AntoineD commited on
Commit
f85fb3c
•
1 Parent(s): db17ae1

End of training

Browse files
Files changed (2) hide show
  1. README.md +63 -33
  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: 1.6740
21
- - Accuracy: 0.425
22
 
23
  ## Model description
24
 
@@ -43,42 +43,72 @@ 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: 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 | 2.1007 | 0.05 |
54
- | No log | 3.0 | 15 | 2.1026 | 0.05 |
55
- | No log | 4.0 | 20 | 2.0981 | 0.1 |
56
- | No log | 5.0 | 25 | 2.0945 | 0.125 |
57
- | No log | 6.0 | 30 | 2.0925 | 0.125 |
58
- | No log | 7.0 | 35 | 2.0857 | 0.15 |
59
- | No log | 8.0 | 40 | 2.0703 | 0.175 |
60
- | No log | 9.0 | 45 | 2.0553 | 0.25 |
61
- | No log | 10.0 | 50 | 2.0371 | 0.325 |
62
- | No log | 11.0 | 55 | 2.0138 | 0.325 |
63
- | No log | 12.0 | 60 | 1.9877 | 0.325 |
64
- | No log | 13.0 | 65 | 1.9577 | 0.4 |
65
- | No log | 14.0 | 70 | 1.9285 | 0.4 |
66
- | No log | 15.0 | 75 | 1.9028 | 0.4 |
67
- | No log | 16.0 | 80 | 1.8771 | 0.4 |
68
- | No log | 17.0 | 85 | 1.8537 | 0.4 |
69
- | No log | 18.0 | 90 | 1.8311 | 0.4 |
70
- | No log | 19.0 | 95 | 1.8051 | 0.4 |
71
- | No log | 20.0 | 100 | 1.7835 | 0.425 |
72
- | No log | 21.0 | 105 | 1.7632 | 0.425 |
73
- | No log | 22.0 | 110 | 1.7449 | 0.425 |
74
- | No log | 23.0 | 115 | 1.7284 | 0.425 |
75
- | No log | 24.0 | 120 | 1.7144 | 0.425 |
76
- | No log | 25.0 | 125 | 1.7027 | 0.425 |
77
- | No log | 26.0 | 130 | 1.6925 | 0.425 |
78
- | No log | 27.0 | 135 | 1.6846 | 0.425 |
79
- | No log | 28.0 | 140 | 1.6789 | 0.425 |
80
- | No log | 29.0 | 145 | 1.6753 | 0.425 |
81
- | No log | 30.0 | 150 | 1.6740 | 0.425 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
82
 
83
 
84
  ### 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: 0.7844
21
+ - Accuracy: 0.7
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: 60
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | No log | 1.0 | 5 | 2.0913 | 0.05 |
53
+ | No log | 2.0 | 10 | 2.1000 | 0.05 |
54
+ | No log | 3.0 | 15 | 2.0985 | 0.1 |
55
+ | No log | 4.0 | 20 | 2.0854 | 0.15 |
56
+ | No log | 5.0 | 25 | 2.0667 | 0.275 |
57
+ | No log | 6.0 | 30 | 2.0459 | 0.35 |
58
+ | No log | 7.0 | 35 | 2.0092 | 0.325 |
59
+ | No log | 8.0 | 40 | 1.9610 | 0.375 |
60
+ | No log | 9.0 | 45 | 1.9182 | 0.4 |
61
+ | No log | 10.0 | 50 | 1.8769 | 0.425 |
62
+ | No log | 11.0 | 55 | 1.8349 | 0.425 |
63
+ | No log | 12.0 | 60 | 1.7894 | 0.425 |
64
+ | No log | 13.0 | 65 | 1.7395 | 0.425 |
65
+ | No log | 14.0 | 70 | 1.6914 | 0.425 |
66
+ | No log | 15.0 | 75 | 1.6472 | 0.45 |
67
+ | No log | 16.0 | 80 | 1.6029 | 0.45 |
68
+ | No log | 17.0 | 85 | 1.5619 | 0.475 |
69
+ | No log | 18.0 | 90 | 1.5190 | 0.5 |
70
+ | No log | 19.0 | 95 | 1.4621 | 0.575 |
71
+ | No log | 20.0 | 100 | 1.4180 | 0.55 |
72
+ | No log | 21.0 | 105 | 1.3786 | 0.575 |
73
+ | No log | 22.0 | 110 | 1.3384 | 0.575 |
74
+ | No log | 23.0 | 115 | 1.2975 | 0.625 |
75
+ | No log | 24.0 | 120 | 1.2561 | 0.65 |
76
+ | No log | 25.0 | 125 | 1.2164 | 0.675 |
77
+ | No log | 26.0 | 130 | 1.1839 | 0.675 |
78
+ | No log | 27.0 | 135 | 1.1602 | 0.65 |
79
+ | No log | 28.0 | 140 | 1.1304 | 0.625 |
80
+ | No log | 29.0 | 145 | 1.1029 | 0.625 |
81
+ | No log | 30.0 | 150 | 1.0744 | 0.625 |
82
+ | No log | 31.0 | 155 | 1.0482 | 0.625 |
83
+ | No log | 32.0 | 160 | 1.0197 | 0.675 |
84
+ | No log | 33.0 | 165 | 0.9967 | 0.725 |
85
+ | No log | 34.0 | 170 | 0.9793 | 0.725 |
86
+ | No log | 35.0 | 175 | 0.9640 | 0.725 |
87
+ | No log | 36.0 | 180 | 0.9502 | 0.675 |
88
+ | No log | 37.0 | 185 | 0.9390 | 0.65 |
89
+ | No log | 38.0 | 190 | 0.9183 | 0.7 |
90
+ | No log | 39.0 | 195 | 0.8987 | 0.725 |
91
+ | No log | 40.0 | 200 | 0.8817 | 0.775 |
92
+ | No log | 41.0 | 205 | 0.8684 | 0.725 |
93
+ | No log | 42.0 | 210 | 0.8611 | 0.7 |
94
+ | No log | 43.0 | 215 | 0.8607 | 0.7 |
95
+ | No log | 44.0 | 220 | 0.8592 | 0.7 |
96
+ | No log | 45.0 | 225 | 0.8471 | 0.725 |
97
+ | No log | 46.0 | 230 | 0.8306 | 0.725 |
98
+ | No log | 47.0 | 235 | 0.8189 | 0.75 |
99
+ | No log | 48.0 | 240 | 0.8136 | 0.725 |
100
+ | No log | 49.0 | 245 | 0.8142 | 0.7 |
101
+ | No log | 50.0 | 250 | 0.8092 | 0.7 |
102
+ | No log | 51.0 | 255 | 0.8053 | 0.75 |
103
+ | No log | 52.0 | 260 | 0.7995 | 0.75 |
104
+ | No log | 53.0 | 265 | 0.7917 | 0.75 |
105
+ | No log | 54.0 | 270 | 0.7901 | 0.725 |
106
+ | No log | 55.0 | 275 | 0.7910 | 0.7 |
107
+ | No log | 56.0 | 280 | 0.7904 | 0.7 |
108
+ | No log | 57.0 | 285 | 0.7884 | 0.7 |
109
+ | No log | 58.0 | 290 | 0.7863 | 0.7 |
110
+ | No log | 59.0 | 295 | 0.7851 | 0.7 |
111
+ | No log | 60.0 | 300 | 0.7844 | 0.7 |
112
 
113
 
114
  ### Framework versions
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f3576a85dafbbd38531c044319f0829020a8fe3fb1d9396ecae5bde2832d303
3
  size 7571689
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ead9f8544f4515482eefa97456c349bd8b3ec100fd151846cb8362283d53947b
3
  size 7571689