Hugging Face's logo

AntoineD
/
camembert_question_answering_tools_qlora_fr

Generated from Trainer
Model card Files Community
AntoineD commited on
Commit
7dd043f
·
1 Parent(s): 7077e4e

End of training

Browse files
Files changed (1) hide show
  1. README.md +117 -0
README.md ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: camembert-base
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: camembert_question_answering_tools_qlora_fr
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # camembert_question_answering_tools_qlora_fr
15
+
16
+ This model is a fine-tuned version of [camembert-base](https://huggingface.co/camembert-base) on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 2.3275
19
+ - Learning Rate: 0.0
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 0.0001
39
+ - train_batch_size: 24
40
+ - eval_batch_size: 192
41
+ - seed: 42
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: linear
44
+ - num_epochs: 60
45
+
46
+ ### Training results
47
+
48
+ | Training Loss | Epoch | Step | Validation Loss | Rate |
49
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
50
+ | No log | 1.0 | 7 | 5.8555 | 0.0001 |
51
+ | No log | 2.0 | 14 | 5.7277 | 0.0001 |
52
+ | No log | 3.0 | 21 | 5.5916 | 0.0001 |
53
+ | No log | 4.0 | 28 | 5.4433 | 0.0001 |
54
+ | No log | 5.0 | 35 | 5.2833 | 0.0001 |
55
+ | No log | 6.0 | 42 | 5.1312 | 9e-05 |
56
+ | No log | 7.0 | 49 | 4.9815 | 0.0001 |
57
+ | No log | 8.0 | 56 | 4.8317 | 0.0001 |
58
+ | No log | 9.0 | 63 | 4.6800 | 0.0001 |
59
+ | No log | 10.0 | 70 | 4.5265 | 0.0001 |
60
+ | No log | 11.0 | 77 | 4.3673 | 0.0001 |
61
+ | No log | 12.0 | 84 | 4.2002 | 8e-05 |
62
+ | No log | 13.0 | 91 | 4.0344 | 0.0001 |
63
+ | No log | 14.0 | 98 | 3.8807 | 0.0001 |
64
+ | No log | 15.0 | 105 | 3.7267 | 0.0001 |
65
+ | No log | 16.0 | 112 | 3.5812 | 0.0001 |
66
+ | No log | 17.0 | 119 | 3.4528 | 0.0001 |
67
+ | No log | 18.0 | 126 | 3.3323 | 7e-05 |
68
+ | No log | 19.0 | 133 | 3.2173 | 0.0001 |
69
+ | No log | 20.0 | 140 | 3.1382 | 0.0001 |
70
+ | No log | 21.0 | 147 | 3.0190 | 0.0001 |
71
+ | No log | 22.0 | 154 | 2.9614 | 0.0001 |
72
+ | No log | 23.0 | 161 | 2.8867 | 0.0001 |
73
+ | No log | 24.0 | 168 | 2.8360 | 6e-05 |
74
+ | No log | 25.0 | 175 | 2.7882 | 0.0001 |
75
+ | No log | 26.0 | 182 | 2.7450 | 0.0001 |
76
+ | No log | 27.0 | 189 | 2.6969 | 0.0001 |
77
+ | No log | 28.0 | 196 | 2.6651 | 0.0001 |
78
+ | No log | 29.0 | 203 | 2.6440 | 0.0001 |
79
+ | No log | 30.0 | 210 | 2.6032 | 5e-05 |
80
+ | No log | 31.0 | 217 | 2.5762 | 0.0000 |
81
+ | No log | 32.0 | 224 | 2.5473 | 0.0000 |
82
+ | No log | 33.0 | 231 | 2.5338 | 0.0000 |
83
+ | No log | 34.0 | 238 | 2.5056 | 0.0000 |
84
+ | No log | 35.0 | 245 | 2.4919 | 0.0000 |
85
+ | No log | 36.0 | 252 | 2.4773 | 4e-05 |
86
+ | No log | 37.0 | 259 | 2.4594 | 0.0000 |
87
+ | No log | 38.0 | 266 | 2.4429 | 0.0000 |
88
+ | No log | 39.0 | 273 | 2.4275 | 0.0000 |
89
+ | No log | 40.0 | 280 | 2.4184 | 0.0000 |
90
+ | No log | 41.0 | 287 | 2.4123 | 0.0000 |
91
+ | No log | 42.0 | 294 | 2.3951 | 3e-05 |
92
+ | No log | 43.0 | 301 | 2.3963 | 0.0000 |
93
+ | No log | 44.0 | 308 | 2.3848 | 0.0000 |
94
+ | No log | 45.0 | 315 | 2.3714 | 0.0000 |
95
+ | No log | 46.0 | 322 | 2.3696 | 0.0000 |
96
+ | No log | 47.0 | 329 | 2.3626 | 0.0000 |
97
+ | No log | 48.0 | 336 | 2.3545 | 2e-05 |
98
+ | No log | 49.0 | 343 | 2.3523 | 0.0000 |
99
+ | No log | 50.0 | 350 | 2.3492 | 0.0000 |
100
+ | No log | 51.0 | 357 | 2.3429 | 0.0000 |
101
+ | No log | 52.0 | 364 | 2.3364 | 0.0000 |
102
+ | No log | 53.0 | 371 | 2.3371 | 0.0000 |
103
+ | No log | 54.0 | 378 | 2.3360 | 1e-05 |
104
+ | No log | 55.0 | 385 | 2.3329 | 0.0000 |
105
+ | No log | 56.0 | 392 | 2.3316 | 0.0000 |
106
+ | No log | 57.0 | 399 | 2.3292 | 5e-06 |
107
+ | No log | 58.0 | 406 | 2.3281 | 0.0000 |
108
+ | No log | 59.0 | 413 | 2.3278 | 0.0000 |
109
+ | No log | 60.0 | 420 | 2.3275 | 0.0 |
110
+
111
+
112
+ ### Framework versions
113
+
114
+ - Transformers 4.34.0
115
+ - Pytorch 2.0.1+cu117
116
+ - Datasets 2.14.5
117
+ - Tokenizers 0.14.1