Hugging Face's logo

AntoineD
/
camembert_ccnet_classification_tools_fr

Text Classification
Transformers
PyTorch
camembert
Generated from Trainer
Inference Endpoints
Model card Files Community
AntoineD commited on
Commit
58c9f1b
•
1 Parent(s): eeeb81c

End of training

Browse files
Files changed (2) hide show
  1. README.md +19 -23
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [camembert/camembert-base-ccnet](https://huggingface.co/camembert/camembert-base-ccnet) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 1.3899
20
- - Accuracy: 0.7
21
  - Learning Rate: 0.0001
22
 
23
  ## Model description
@@ -43,33 +43,29 @@ 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
- - lr_scheduler_warmup_ratio: 0.01
47
  - num_epochs: 60
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Rate |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
53
- | No log | 1.0 | 5 | 2.0931 | 0.125 | 0.0001 |
54
- | No log | 2.0 | 10 | 1.9035 | 0.325 | 0.0001 |
55
- | No log | 3.0 | 15 | 1.7443 | 0.525 | 0.0001 |
56
- | No log | 4.0 | 20 | 1.6035 | 0.575 | 0.0001 |
57
- | No log | 5.0 | 25 | 1.4599 | 0.525 | 0.0001 |
58
- | No log | 6.0 | 30 | 1.4177 | 0.575 | 0.0001 |
59
- | No log | 7.0 | 35 | 1.2438 | 0.675 | 0.0001 |
60
- | No log | 8.0 | 40 | 1.2116 | 0.65 | 0.0001 |
61
- | No log | 9.0 | 45 | 1.2569 | 0.625 | 0.0001 |
62
- | No log | 10.0 | 50 | 1.1010 | 0.7 | 0.0001 |
63
- | No log | 11.0 | 55 | 1.0926 | 0.7 | 0.0001 |
64
- | No log | 12.0 | 60 | 1.1022 | 0.725 | 0.0001 |
65
- | No log | 13.0 | 65 | 1.1841 | 0.725 | 0.0001 |
66
- | No log | 14.0 | 70 | 1.2344 | 0.725 | 0.0001 |
67
- | No log | 15.0 | 75 | 1.3195 | 0.7 | 0.0001 |
68
- | No log | 16.0 | 80 | 1.3959 | 0.7 | 0.0001 |
69
- | No log | 17.0 | 85 | 1.3734 | 0.725 | 0.0001 |
70
- | No log | 18.0 | 90 | 1.3948 | 0.725 | 0.0001 |
71
- | No log | 19.0 | 95 | 1.4222 | 0.7 | 0.0001 |
72
- | No log | 20.0 | 100 | 1.3899 | 0.7 | 0.0001 |
73
 
74
 
75
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [camembert/camembert-base-ccnet](https://huggingface.co/camembert/camembert-base-ccnet) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.5125
20
+ - Accuracy: 0.9
21
  - Learning Rate: 0.0001
22
 
23
  ## Model description
 
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 | Rate |
51
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
52
+ | No log | 1.0 | 7 | 1.8894 | 0.525 | 0.0001 |
53
+ | No log | 2.0 | 14 | 1.4269 | 0.675 | 0.0001 |
54
+ | No log | 3.0 | 21 | 1.1038 | 0.75 | 0.0001 |
55
+ | No log | 4.0 | 28 | 0.8014 | 0.85 | 0.0001 |
56
+ | No log | 5.0 | 35 | 0.6406 | 0.85 | 0.0001 |
57
+ | No log | 6.0 | 42 | 0.6220 | 0.875 | 9e-05 |
58
+ | No log | 7.0 | 49 | 0.4642 | 0.875 | 0.0001 |
59
+ | No log | 8.0 | 56 | 0.5596 | 0.85 | 0.0001 |
60
+ | No log | 9.0 | 63 | 0.5648 | 0.85 | 0.0001 |
61
+ | No log | 10.0 | 70 | 0.5025 | 0.9 | 0.0001 |
62
+ | No log | 11.0 | 77 | 0.5263 | 0.9 | 0.0001 |
63
+ | No log | 12.0 | 84 | 0.5062 | 0.9 | 8e-05 |
64
+ | No log | 13.0 | 91 | 0.4950 | 0.9 | 0.0001 |
65
+ | No log | 14.0 | 98 | 0.4981 | 0.9 | 0.0001 |
66
+ | No log | 15.0 | 105 | 0.5036 | 0.9 | 0.0001 |
67
+ | No log | 16.0 | 112 | 0.5075 | 0.9 | 0.0001 |
68
+ | No log | 17.0 | 119 | 0.5125 | 0.9 | 0.0001 |
 
 
 
69
 
70
 
71
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:269811464583d5545e0d6c20d830d016333c08fa249a9ce06d0ac47555392ec3
3
  size 442581361
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f2abf4ade09b12c834707dea36ec6c36f0c76b2e5639d68d1fbc0b51a6e160a
3
  size 442581361