Hugging Face's logo

BERRAMOU
/
camembert-math-classification

Text Classification
Transformers
Safetensors
camembert
Generated from Trainer
Model card Files
xet
 Community
BERRAMOU commited on
Commit
b9603b2
·
verified ·
1 Parent(s): 36aeec6

Model save

Browse files
Files changed (3) hide show
  1. README.md +12 -22
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [camembert-base](https://huggingface.co/camembert-base) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.0007
22
- - F1 Macro: 1.0
23
- - F1 Weighted: 1.0
24
  - F1 Correct: 1.0
25
- - F1 Partiel: 1.0
26
- - F1 Incorrect: 1.0
27
- - Accuracy: 1.0
28
 
29
  ## Model description
30
 
@@ -50,28 +50,18 @@ The following hyperparameters were used during training:
50
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
51
  - lr_scheduler_type: linear
52
  - lr_scheduler_warmup_steps: 0.1
53
- - num_epochs: 15
54
  - mixed_precision_training: Native AMP
55
 
56
  ### Training results
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 Weighted | F1 Correct | F1 Partiel | F1 Incorrect | Accuracy |
59
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------:|:----------:|:----------:|:------------:|:--------:|
60
- | 0.8191 | 1.0 | 184 | 0.8873 | 0.4551 | 0.4551 | 0.7628 | 0.0 | 0.6024 | 0.5370 |
61
- | 0.3850 | 2.0 | 368 | 0.2883 | 0.9321 | 0.9321 | 0.9882 | 0.9054 | 0.9028 | 0.9325 |
62
- | 0.0963 | 3.0 | 552 | 0.1260 | 0.9679 | 0.9679 | 0.9902 | 0.95 | 0.9637 | 0.9683 |
63
- | 0.0478 | 4.0 | 736 | 0.0117 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
64
- | 0.0138 | 5.0 | 920 | 0.0113 | 0.9974 | 0.9974 | 1.0 | 0.9960 | 0.9960 | 0.9974 |
65
- | 0.0067 | 6.0 | 1104 | 0.0030 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
66
- | 0.0122 | 7.0 | 1288 | 0.0021 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
67
- | 0.0127 | 8.0 | 1472 | 0.0016 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
68
- | 0.0125 | 9.0 | 1656 | 0.0012 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
69
- | 0.0015 | 10.0 | 1840 | 0.0010 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
70
- | 0.0085 | 11.0 | 2024 | 0.0009 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
71
- | 0.0119 | 12.0 | 2208 | 0.0008 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
72
- | 0.0026 | 13.0 | 2392 | 0.0007 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
73
- | 0.0010 | 14.0 | 2576 | 0.0007 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
74
- | 0.0010 | 15.0 | 2760 | 0.0007 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
75
 
76
 
77
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [camembert-base](https://huggingface.co/camembert-base) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.0166
22
+ - F1 Macro: 0.9987
23
+ - F1 Weighted: 0.9987
24
  - F1 Correct: 1.0
25
+ - F1 Partiel: 0.9980
26
+ - F1 Incorrect: 0.9980
27
+ - Accuracy: 0.9987
28
 
29
  ## Model description
30
 
 
50
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
51
  - lr_scheduler_type: linear
52
  - lr_scheduler_warmup_steps: 0.1
53
+ - num_epochs: 5
54
  - mixed_precision_training: Native AMP
55
 
56
  ### Training results
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 Weighted | F1 Correct | F1 Partiel | F1 Incorrect | Accuracy |
59
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------:|:----------:|:----------:|:------------:|:--------:|
60
+ | 0.6561 | 1.0 | 184 | 0.8086 | 0.4912 | 0.4912 | 0.8169 | 0.0204 | 0.6364 | 0.5675 |
61
+ | 0.1997 | 2.0 | 368 | 0.1530 | 0.9669 | 0.9669 | 0.9902 | 0.9513 | 0.9592 | 0.9669 |
62
+ | 0.0648 | 3.0 | 552 | 0.0360 | 0.9960 | 0.9960 | 1.0 | 0.9940 | 0.9941 | 0.9960 |
63
+ | 0.0261 | 4.0 | 736 | 0.0227 | 0.9974 | 0.9974 | 0.9980 | 0.9960 | 0.9980 | 0.9974 |
64
+ | 0.0147 | 5.0 | 920 | 0.0166 | 0.9987 | 0.9987 | 1.0 | 0.9980 | 0.9980 | 0.9987 |
 
 
 
 
 
 
 
 
 
 
65
 
66
 
67
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:12c616ee6df4664b4fe951cc7c639491b31745df6c663e3a0d7c718e7000abe3
3
  size 442521156
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bae4df3055e9f62c84a4dabfaa3959fb8d96802877f84f9a55ba06a1a9f1f43
3
  size 442521156
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30ffdefe3d44f7c764e6377313c1bab5a61a187a767833fa4985497d5b8fe1f3
3
  size 5329
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a24a2f699ff82c5351c481d8040acc718ea658eebbaef72fee2ee2a35a405d00
3
  size 5329