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
070a88e
·
verified ·
1 Parent(s): 2098d98

Model save

Browse files
Files changed (3) hide show
  1. README.md +11 -11
  2. config.json +0 -1
  3. model.safetensors +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: 1.6519
22
- - F1 Macro: 0.6973
23
- - F1 Weighted: 0.7076
24
- - F1 Correct: 0.8571
25
- - F1 Partiel: 0.8
26
- - F1 Incorrect: 0.4348
27
- - Accuracy: 0.75
28
 
29
  ## Model description
30
 
@@ -57,10 +57,10 @@ The following hyperparameters were used during training:
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 Weighted | F1 Correct | F1 Partiel | F1 Incorrect | Accuracy |
59
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------:|:----------:|:----------:|:------------:|:--------:|
60
- | No log | 1.0 | 15 | 2.1103 | 0.1905 | 0.2286 | 0.0 | 0.5714 | 0.0 | 0.4 |
61
- | 2.1496 | 2.0 | 30 | 1.9187 | 0.2928 | 0.3228 | 0.2857 | 0.5926 | 0.0 | 0.45 |
62
- | 2.0111 | 3.0 | 45 | 1.7323 | 0.7855 | 0.7870 | 0.9412 | 0.8 | 0.6154 | 0.8 |
63
- | 1.8019 | 4.0 | 60 | 1.6519 | 0.6973 | 0.7076 | 0.8571 | 0.8 | 0.4348 | 0.75 |
64
 
65
 
66
  ### 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: 0.3711
22
+ - F1 Macro: 0.9159
23
+ - F1 Weighted: 0.9139
24
+ - F1 Correct: 1.0
25
+ - F1 Partiel: 0.8953
26
+ - F1 Incorrect: 0.8525
27
+ - Accuracy: 0.9143
28
 
29
  ## Model description
30
 
 
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 Weighted | F1 Correct | F1 Partiel | F1 Incorrect | Accuracy |
59
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------:|:----------:|:----------:|:------------:|:--------:|
60
+ | 1.0746 | 1.0 | 53 | 0.8969 | 0.7007 | 0.7086 | 0.8227 | 0.7795 | 0.5 | 0.7381 |
61
+ | 0.7178 | 2.0 | 106 | 0.5763 | 0.8772 | 0.8761 | 0.9767 | 0.8663 | 0.7885 | 0.8810 |
62
+ | 0.5751 | 3.0 | 159 | 0.4265 | 0.9180 | 0.9169 | 1.0 | 0.9071 | 0.8468 | 0.9190 |
63
+ | 0.4558 | 4.0 | 212 | 0.3711 | 0.9159 | 0.9139 | 1.0 | 0.8953 | 0.8525 | 0.9143 |
64
 
65
 
66
  ### Framework versions
config.json CHANGED
@@ -31,7 +31,6 @@
31
  "num_hidden_layers": 12,
32
  "output_past": true,
33
  "pad_token_id": 1,
34
- "problem_type": "single_label_classification",
35
  "transformers_version": "5.0.0",
36
  "type_vocab_size": 1,
37
  "use_cache": false,
 
31
  "num_hidden_layers": 12,
32
  "output_past": true,
33
  "pad_token_id": 1,
 
34
  "transformers_version": "5.0.0",
35
  "type_vocab_size": 1,
36
  "use_cache": false,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f1fd8ea1fc9e0427bb286e697e31e6d8253a6f35dfdaaed457312b3ee34c8b5
3
  size 442521156
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36121d9283ea563331757b39ae7d6d3fa7e72e834e3d007416547af6b69e3782
3
  size 442521156