Hugging Face's logo

AntoineD
/
camembert_classification_tools_qlora_fr

Generated from Trainer
Model card Files Community
AntoineD commited on
Commit
e5bd53e
•
1 Parent(s): 8ca608a

End of training

Browse files
Files changed (2) hide show
  1. README.md +119 -0
  2. adapter_model.bin +1 -1
README.md ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: camembert-base
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: camembert_classification_tools_qlora_fr
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # camembert_classification_tools_qlora_fr
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: 0.7203
21
+ - Accuracy: 0.875
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
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: 60
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | No log | 1.0 | 5 | 2.0791 | 0.075 |
53
+ | No log | 2.0 | 10 | 2.0909 | 0.075 |
54
+ | No log | 3.0 | 15 | 2.0903 | 0.075 |
55
+ | No log | 4.0 | 20 | 2.0790 | 0.075 |
56
+ | No log | 5.0 | 25 | 2.0606 | 0.075 |
57
+ | No log | 6.0 | 30 | 2.0206 | 0.1 |
58
+ | No log | 7.0 | 35 | 1.9780 | 0.25 |
59
+ | No log | 8.0 | 40 | 1.9250 | 0.375 |
60
+ | No log | 9.0 | 45 | 1.8724 | 0.5 |
61
+ | No log | 10.0 | 50 | 1.8129 | 0.525 |
62
+ | No log | 11.0 | 55 | 1.7570 | 0.55 |
63
+ | No log | 12.0 | 60 | 1.7009 | 0.65 |
64
+ | No log | 13.0 | 65 | 1.6472 | 0.625 |
65
+ | No log | 14.0 | 70 | 1.5928 | 0.675 |
66
+ | No log | 15.0 | 75 | 1.5434 | 0.7 |
67
+ | No log | 16.0 | 80 | 1.4880 | 0.675 |
68
+ | No log | 17.0 | 85 | 1.4333 | 0.7 |
69
+ | No log | 18.0 | 90 | 1.3811 | 0.7 |
70
+ | No log | 19.0 | 95 | 1.3339 | 0.7 |
71
+ | No log | 20.0 | 100 | 1.2919 | 0.75 |
72
+ | No log | 21.0 | 105 | 1.2493 | 0.725 |
73
+ | No log | 22.0 | 110 | 1.2091 | 0.725 |
74
+ | No log | 23.0 | 115 | 1.1707 | 0.75 |
75
+ | No log | 24.0 | 120 | 1.1311 | 0.775 |
76
+ | No log | 25.0 | 125 | 1.0946 | 0.825 |
77
+ | No log | 26.0 | 130 | 1.0642 | 0.8 |
78
+ | No log | 27.0 | 135 | 1.0363 | 0.8 |
79
+ | No log | 28.0 | 140 | 1.0172 | 0.8 |
80
+ | No log | 29.0 | 145 | 0.9939 | 0.825 |
81
+ | No log | 30.0 | 150 | 0.9682 | 0.825 |
82
+ | No log | 31.0 | 155 | 0.9443 | 0.8 |
83
+ | No log | 32.0 | 160 | 0.9289 | 0.825 |
84
+ | No log | 33.0 | 165 | 0.9113 | 0.85 |
85
+ | No log | 34.0 | 170 | 0.9017 | 0.85 |
86
+ | No log | 35.0 | 175 | 0.8804 | 0.85 |
87
+ | No log | 36.0 | 180 | 0.8598 | 0.85 |
88
+ | No log | 37.0 | 185 | 0.8484 | 0.825 |
89
+ | No log | 38.0 | 190 | 0.8361 | 0.825 |
90
+ | No log | 39.0 | 195 | 0.8306 | 0.825 |
91
+ | No log | 40.0 | 200 | 0.8242 | 0.825 |
92
+ | No log | 41.0 | 205 | 0.8198 | 0.85 |
93
+ | No log | 42.0 | 210 | 0.8051 | 0.85 |
94
+ | No log | 43.0 | 215 | 0.7854 | 0.85 |
95
+ | No log | 44.0 | 220 | 0.7727 | 0.9 |
96
+ | No log | 45.0 | 225 | 0.7626 | 0.9 |
97
+ | No log | 46.0 | 230 | 0.7579 | 0.9 |
98
+ | No log | 47.0 | 235 | 0.7500 | 0.9 |
99
+ | No log | 48.0 | 240 | 0.7477 | 0.875 |
100
+ | No log | 49.0 | 245 | 0.7517 | 0.85 |
101
+ | No log | 50.0 | 250 | 0.7484 | 0.85 |
102
+ | No log | 51.0 | 255 | 0.7446 | 0.85 |
103
+ | No log | 52.0 | 260 | 0.7414 | 0.85 |
104
+ | No log | 53.0 | 265 | 0.7357 | 0.875 |
105
+ | No log | 54.0 | 270 | 0.7303 | 0.875 |
106
+ | No log | 55.0 | 275 | 0.7249 | 0.875 |
107
+ | No log | 56.0 | 280 | 0.7232 | 0.875 |
108
+ | No log | 57.0 | 285 | 0.7228 | 0.875 |
109
+ | No log | 58.0 | 290 | 0.7215 | 0.875 |
110
+ | No log | 59.0 | 295 | 0.7206 | 0.875 |
111
+ | No log | 60.0 | 300 | 0.7203 | 0.875 |
112
+
113
+
114
+ ### Framework versions
115
+
116
+ - Transformers 4.34.0
117
+ - Pytorch 2.0.1+cu117
118
+ - Datasets 2.14.5
119
+ - Tokenizers 0.14.1
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b64d27aabdaf1822fac9d4ffe9d282915b83c3a6d889ba13d0af849aff842b0
3
  size 7571689
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e1efe0fc729782d1080db5015314719ce7c0f5d88313655923105db65a14a0f
3
  size 7571689